Search

Background: In the healthcare domain today, despite the substantial adoption of electronic health information systems, a significant proportion of medical reports still exist in paper-based formats. As a result, there is a significant demand for the digitization of information from these paper-based reports. However, the digitization of paper-based laboratory reports into a structured data format can be challenging due to their non-standard layouts, which includes various data types such as text, numeric values, reference ranges, and units. Therefore, it is crucial to develop a highly scalable and lightweight technique that can effectively identify and extract information from laboratory test reports and convert them into a structured data format for downstream tasks. Methods: We developed an end-to-end Natural Language Processing (NLP)-based pipeline for extracting information from paper-based laboratory test reports. Our pipeline consists of two main modules: an optical character recognition (OCR) module and an information extraction (IE) module. The OCR module is applied to locate and identify text from scanned laboratory test reports using state-of-the-art OCR algorithms. The IE module is then used to extract meaningful information from the OCR results to form digitalized tables of the test reports. The IE module consists of five sub-modules, which are time detection, headline position, line normalization, Named Entity Recognition (NER) with a Conditional Random Fields (CRF)-based method, and step detection for multi-column. Finally, we evaluated the performance of the proposed pipeline on 153 laboratory test reports collected from Peking University First Hospital (PKU1). Results: In the OCR module, we evaluate the accuracy of text detection and recognition results at three different levels and achieved an averaged accuracy of 0.93. In the IE module, we extracted four laboratory test entities, including test item name, test result, test unit, and reference value range. The overall F1 score is 0.86 on the 153 laboratory test reports collected from PKU1. With a single CPU, the average inference time of each report is only 0.78 s. Conclusion: In this study, we developed a practical lightweight pipeline to digitalize and extract information from paper-based laboratory test reports in diverse types and with different layouts that can be adopted in real clinical environments with the lowest possible computing resources requirements. The high evaluation performance on the real-world hospital dataset validated the feasibility of the proposed pipeline. [ABSTRACT FROM AUTHOR]

Background: To deliver evidence-based medicine, clinicians often reference resources that are useful to their respective medical practices. Owing to their busy schedules, however, clinicians typically find it challenging to locate these relevant resources out of the rapidly growing number of journals and articles currently being published. The literature-recommender system may provide a possible solution to this issue if the individual needs of clinicians can be identified and applied.Methods: We thus collected from the CiteULike website a sample of 96 clinicians and 6,221 scientific articles that they read. We examined the journal distributions, publication types, reading times, and geographic locations. We then compared the distributions of MeSH terms associated with these articles with those of randomly sampled MEDLINE articles using two-sample Z-test and multiple comparison correction, in order to identify the important topics relevant to clinicians.Results: We determined that the sampled clinicians followed the latest literature in a timely manner and read papers that are considered landmarks in medical research history. They preferred to read scientific discoveries from human experiments instead of molecular-, cellular- or animal-model-based experiments. Furthermore, the country of publication may impact reading preferences, particularly for clinicians from Egypt, India, Norway, Senegal, and South Africa.Conclusion: These findings provide useful guidance for developing personalized literature-recommender systems for clinicians. [ABSTRACT FROM AUTHOR]

Background: Enhancing Local Control (LC) of brain metastases is pivotal for improving overall survival, which makes the prediction of local treatment failure a crucial aspect of treatment planning. Understanding the factors that influence LC of brain metastases is imperative for optimizing treatment strategies and subsequently extending overall survival. Machine learning algorithms may help to identify factors that predict outcomes. Methods: This paper systematically reviews these factors associated with LC to select candidate predictor features for a practical application of predictive modeling. A systematic literature search was conducted to identify studies in which the LC of brain metastases is assessed for adult patients. EMBASE, PubMed, Web-of-Science, and the Cochrane Database were searched up to December 24, 2020. All studies investigating the LC of brain metastases as one of the endpoints were included, regardless of primary tumor type or treatment type. We first grouped studies based on primary tumor types resulting in lung, breast, and melanoma groups. Studies that did not focus on a specific primary cancer type were grouped based on treatment types resulting in surgery, SRT, and whole-brain radiotherapy groups. For each group, significant factors associated with LC were identified and discussed. As a second project, we assessed the practical importance of selected features in predicting LC after Stereotactic Radiotherapy (SRT) with a Random Forest machine learning model. Accuracy and Area Under the Curve (AUC) of the Random Forest model, trained with the list of factors that were found to be associated with LC for the SRT treatment group, were reported. Results: The systematic literature search identified 6270 unique records. After screening titles and abstracts, 410 full texts were considered, and ultimately 159 studies were included for review. Most of the studies focused on the LC of the brain metastases for a specific primary tumor type or after a specific treatment type. Higher SRT radiation dose was found to be associated with better LC in lung cancer, breast cancer, and melanoma groups. Also, a higher dose was associated with better LC in the SRT group, while higher tumor volume was associated with worse LC in this group. The Random Forest model predicted the LC of brain metastases with an accuracy of 80% and an AUC of 0.84. Conclusion: This paper thoroughly examines factors associated with LC in brain metastases and highlights the translational value of our findings for selecting variables to predict LC in a sample of patients who underwent SRT. The prediction model holds great promise for clinicians, offering a valuable tool to predict personalized treatment outcomes and foresee the impact of changes in treatment characteristics such as radiation dose. [ABSTRACT FROM AUTHOR]

Background: The Longshi Scale is a pictorial assessment tool for evaluating activities of daily living (ADL) in patients with stroke. The paper-based version presents challenges; thus, the WeChat version was created to enhance accessibility. Herein, we aimed to validate the inter-rater and test–retest reliabilities of the WeChat version of the Longshi Scale and explore its potential clinical applications. Methods: We recruited 115 patients with stroke in the study. The ADL results of each patient were assessed using both the WeChat and paper-based version of the Longshi Scale; each evaluation was conducted by 28 health professionals and 115 caregivers separately. To explore the test–retest reliability of the WeChat version, 22 patients were randomly selected and re-evaluated by health professionals using the WeChat version. All evaluation criteria were recorded, and all evaluators were surveyed to indicate their preference between the two versions. Results: Consistency between WeChat and the paper-based Longshi Scale was high for ADL scores by health professionals (ICC2,1 = 0.803–0.988) and caregivers (ICC2,1 = 0.845–0.983), as well as for degrees of disability (κw = 0.870 by professionals; κw = 0.800 by caregivers). Bland–Altman analysis showed no significant discrepancies. The WeChat version exhibited good test–retest reliability (κw = 0.880). The WeChat version showed similar inter-rater reliability in terms of the ADL score evaluated using the paper-based version (ICC2,1 = 0.781–0.941). The time to complete assessments did not differ significantly, although the WeChat version had a shorter information entry time (P < 0.001, 95% confidence interval: –43.463 to –15.488). Health professionals favored the WeChat version (53.6%), whereas caregivers had no significant preference. Conclusions: The WeChat version of the Longshi Scale is reliable and serves as a suitable alternative for health professionals and caregivers to assess ADL levels in patients with stroke. The WeChat version of the Longshi Scale is considered user-friendly by health professionals, although it is not preferred by caregivers. Trial registration: This study was approved by the Ethics Committee of the Second People's Hospital of Shenzhen (approval number: 20210812003-FS01) and registered on the Clinical Trial Register Center website: clinicaltrials.gov on January 31, 2022 (registration no.: NCT05214638). [ABSTRACT FROM AUTHOR]

Background: Nutritional risk situations related to decreased food intake in the hospital environment hinder nutritional care and increase malnutrition in hospitalized patients and are often associated with increased morbidity and mortality. The objective of this study is to develop and test the reliability and data similarity of a mobile application as a virtual instrument to assess the acceptability and quality of hospital diets for inpatients. Methods: This intra- and interobserver development and reliability study investigated an in-hospital food intake monitoring application based on a validated instrument for patients with infectious diseases who were treated at the Evandro Chagas National Institute of Infectious Diseases (INI/FIOCRUZ). The instrument was sequentially administered to patients 48 h after admission to INI hospital units using the printed instrument (paper) and the digital application (ARIETI) simultaneously. The tested reliability factor was the consistency of the method in the digital platform, checking whether the application provided equivalent data to the paper instrument, and finally, a statistical analysis plan was performed in the R platform version 4.2.0. This project was authorized by the FIOCRUZ/INI Research Ethics Committee. Results: The ARIETI was developed and tested for reliability in 70 participants, showing a similar ability to calculate caloric intake in Kcal, protein intake (g), the proportion of caloric intake and protein intake relative to the prescribed goal. These instrument comparison analyses showed statistical significance (p < 0.001). The application was superior to the paper-based instrument, accelerating the time to perform the nutritional risk diagnosis based on food intake by approximately 250 s (average time). Conclusions: The ARIETI application has demonstrated equivalent reliability compared to the original instrument. Moreover, it optimized the time between the diagnosis of nutritional risk related to dietary intake and the nutritionist's decision making, showing an improved ability to maintain information quality compared to the paper-based instrument. [ABSTRACT FROM AUTHOR]

As the first point of contact for patients, General Practitioners (GPs) play a crucial role in the National Health Service (NHS). An accurate primary diagnosis from the GP can alleviate the burden on specialists and reduce the time needed to re-confirm the patient's condition, allowing for more efficient further examinations. However, GPs have broad but less specialized knowledge, which limits the accuracy of their diagnosis. Therefore, it is imperative to introduce an intelligent system to assist GPs in making decisions. This paper introduces two data augmentation methods, the Complaint Symptoms Integration Method and Symptom Dot Separating Method, to integrate essential information into the Integration dataset. Additionally, it proposes a hybrid architecture that fuses the features of words from different representation spaces. Experiments demonstrate that, compared to commonly used pre-trained attention-based models, our hybrid architecture delivers the best classification performance for four common neurological diseases on the enhanced Integration dataset. For example, the classification accuracy of the BERT+CNN hybrid architecture is 0.897, which is a 5.1% improvement over both BERT and CNN with 0.846. Finally, this paper develops an AI diagnosis assistant web application that leverages the superior performance of this architecture to help GPs complete primary diagnosis efficiently and accurately. [ABSTRACT FROM AUTHOR]

Background: Cesarean section-induced postpartum hemorrhage (PPH) potentially causes anemia and hypovolemic shock in pregnant women. Hence, it is helpful for obstetricians and anesthesiologists to prepare pre-emptive prevention when predicting PPH occurrence in advance. However, current works on PPH prediction focus on whether PPH occurs rather than assessing PPH amount. To this end, this work studies quantitative PPH prediction with machine learning (ML). Methods: The study cohort in this paper was selected from individuals with PPH who were hospitalized at Shijiazhuang Obstetrics and Gynecology Hospital from 2020 to 2022. In this study cohort, we built a dataset with 6,144 subjects covering clinical parameters, anesthesia operation records, laboratory examination results, and other information in the electronic medical record system. Based on our built dataset, we exploit six different ML models, including logistic regression, linear regression, gradient boosting, XGBoost, multilayer perceptron, and random forest, to automatically predict the amount of bleeding during cesarean section. Eighty percent of the dataset was used as model training, and 20 % was used for verification. Those ML models are constantly verified and improved by root mean squared error(RMSE) and mean absolute error(MAE). Moreover, we also leverage the importance of permutation and partial dependence plot (PDP) to discuss their feasibility. Result: The experiment results show that random forest obtains the highest accuracy for PPH amount prediction compared to other ML methods. Random forest reaches the mean absolute error of 21.7, less than 5.4 % prediction error. It also gains the root mean squared error of 33.75, less than 9.3 % prediction error. On the other hand, the experimental results also disclose indicators that contributed most to PPH prediction, including Ca, hemoglobin, white blood cells, platelets, Na, and K. Conclusion: It effectively predicts the amount of PPH during a cesarean section by ML methods, especially random forest. With the above insight, ML predicting PPH amounts provides early warning for clinicians, thus reducing complications and improving cesarean sections' safety. Furthermore, the importance of ML and permutation, complemented by incorporating PDP, promises to provide clinicians with a transparent indication of individual risk prediction. [ABSTRACT FROM AUTHOR]

Background: Pattern mining techniques are helpful tools when extracting new knowledge in real practice, but the overwhelming number of patterns is still a limiting factor in the health-care domain. Current efforts concerning the definition of measures of interest for patterns are focused on reducing the number of patterns and quantifying their relevance (utility/usefulness). However, although the temporal dimension plays a key role in medical records, few efforts have been made to extract temporal knowledge about the patient's evolution from multivariate sequential patterns. Methods: In this paper, we propose a method to extract a new type of patterns in the clinical domain called Jumping Diagnostic Odds Ratio Sequential Patterns (JDORSP). The aim of this method is to employ the odds ratio to identify a concise set of sequential patterns that represent a patient's state with a statistically significant protection factor (i.e., a pattern associated with patients that survive) and those extensions whose evolution suddenly changes the patient's clinical state, thus making the sequential patterns a statistically significant risk factor (i.e., a pattern associated with patients that do not survive), or vice versa. Results: The results of our experiments highlight that our method reduces the number of sequential patterns obtained with state-of-the-art pattern reduction methods by over 95%. Only by achieving this drastic reduction can medical experts carry out a comprehensive clinical evaluation of the patterns that might be considered medical knowledge regarding the temporal evolution of the patients. We have evaluated the surprisingness and relevance of the sequential patterns with clinicians, and the most interesting fact is the high surprisingness of the extensions of the patterns that become a protection factor, that is, the patients that recover after several days of being at high risk of dying. Conclusions: Our proposed method with which to extract JDORSP generates a set of interpretable multivariate sequential patterns with new knowledge regarding the temporal evolution of the patients. The number of patterns is greatly reduced when compared to those generated by other methods and measures of interest. An additional advantage of this method is that it does not require any parameters or thresholds, and that the reduced number of patterns allows a manual evaluation. [ABSTRACT FROM AUTHOR]

Background: BERT models have seen widespread use on unstructured text within the clinical domain. However, little to no research has been conducted into classifying unstructured clinical notes on the basis of patient lifestyle indicators, especially in Dutch. This article aims to test the feasibility of deep BERT models on the task of patient lifestyle classification, as well as introducing an experimental framework that is easily reproducible in future research. Methods: This study makes use of unstructured general patient text data from HagaZiekenhuis, a large hospital in The Netherlands. Over 148 000 notes were provided to us, which were each automatically labelled on the basis of the respective patients' smoking, alcohol usage and drug usage statuses. In this paper we test feasibility of automatically assigning labels, and justify it using hand-labelled input. Ultimately, we compare macro F1-scores of string matching, SGD and several BERT models on the task of classifying smoking, alcohol and drug usage. We test Dutch BERT models and English models with translated input. Results: We find that our further pre-trained MedRoBERTa.nl-HAGA model outperformed every other model on smoking (0.93) and drug usage (0.77). Interestingly, our ClinicalBERT model that was merely fine-tuned on translated text performed best on the alcohol task (0.80). In t-SNE visualisations, we show our MedRoBERTa.nl-HAGA model is the best model to differentiate between classes in the embedding space, explaining its superior classification performance. Conclusions: We suggest MedRoBERTa.nl-HAGA to be used as a baseline in future research on Dutch free text patient lifestyle classification. We furthermore strongly suggest further exploring the application of translation to input text in non-English clinical BERT research, as we only translated a subset of the full set and yet achieved very promising results. [ABSTRACT FROM AUTHOR]

Objective: Hospitals and healthcare providers should assess and compare the quality of care given to patients and based on this improve the care. In the Netherlands, hospitals provide data to national quality registries, which in return provide annual quality indicators. However, this process is time-consuming, resource intensive and risks patient privacy and confidentiality. In this paper, we presented a multicentric 'Proof of Principle' study for federated calculation of quality indicators in patients with colorectal cancer. The findings suggest that the proposed approach is highly time-efficient and consume significantly lesser resources. Materials and methods: Two quality indicators are calculated in an efficient and privacy presevering federated manner, by i) applying the Findable Accessible Interoperable and Reusable (FAIR) data principles and ii) using the Personal Health Train (PHT) infrastructure. Instead of sharing data to a centralized registry, PHT enables analysis by sending algorithms and sharing only insights from the data. Results: ETL process extracted data from the Electronic Health Record systems of the hospitals, converted them to FAIR data and hosted in RDF endpoints within each hospital. Finally, quality indicators from each center are calculated using PHT and the mean result along with the individual results plotted. Discussion and conclusion: PHT and FAIR data principles can efficiently calculate quality indicators in a privacy-preserving federated approach and the work can be scaled up both nationally and internationally. Despite this, application of the methodology was largely hampered by ELSI issues. However, the lessons learned from this study can provide other hospitals and researchers to adapt to the process easily and take effective measures in building quality of care infrastructures. [ABSTRACT FROM AUTHOR]

Background: Irregular time series (ITS) are common in healthcare as patient data is recorded in an electronic health record (EHR) system as per clinical guidelines/requirements but not for research and depends on a patient's health status. Due to irregularity, it is challenging to develop machine learning techniques to uncover vast intelligence hidden in EHR big data, without losing performance on downstream patient outcome prediction tasks. Methods: In this paper, we propose Perceiver, a cross-attention-based transformer variant that is computationally efficient and can handle long sequences of time series in healthcare. We further develop continuous patient state attention models, using Perceiver and transformer to deal with ITS in EHR. The continuous patient state models utilise neural ordinary differential equations to learn patient health dynamics, i.e., patient health trajectory from observed irregular time steps, which enables them to sample patient state at any time. Results: The proposed models' performance on in-hospital mortality prediction task on PhysioNet-2012 challenge and MIMIC-III datasets is examined. Perceiver model either outperforms or performs at par with baselines, and reduces computations by about nine times when compared to the transformer model, with no significant loss of performance. Experiments to examine irregularity in healthcare reveal that continuous patient state models outperform baselines. Moreover, the predictive uncertainty of the model is used to refer extremely uncertain cases to clinicians, which enhances the model's performance. Code is publicly available and verified at https://codeocean.com/capsule/4587224. Conclusions: Perceiver presents a computationally efficient potential alternative for processing long sequences of time series in healthcare, and the continuous patient state attention models outperform the traditional and advanced techniques to handle irregularity in the time series. Moreover, the predictive uncertainty of the model helps in the development of transparent and trustworthy systems, which can be utilised as per the availability of clinicians. [ABSTRACT FROM AUTHOR]

Background: Glaucoma, the second leading cause of global blindness, demands timely detection due to its asymptomatic progression. This paper introduces an advanced computerized system, integrates Machine Learning (ML), convolutional neural networks (CNNs), and image processing for accurate glaucoma detection using medical imaging data, surpassing prior research efforts. Method: Developing a hybrid glaucoma detection framework using CNNs (ResNet50, VGG-16) and Random Forest. Models analyze pre-processed retinal images independently, and post-processing rules combine predictions for an overall glaucoma impact assessment. Result: The hybrid framework achieves a significant 95.41% accuracy, with precision and recall at 99.37% and 88.37%, respectively. The F1 score, balancing precision and recall, reaches a commendable 93.52%. These results highlight the robustness and effectiveness of the hybrid framework in accurate glaucoma diagnosis. Conclusion: In summary, our research presents an innovative hybrid framework combining CNNs and traditional ML models for glaucoma detection. Using ResNet50, VGG-16, and Random Forest in an ensemble approach yields remarkable accuracy, precision, recall, and F1 score. These results showcase the methodology's potential to enhance glaucoma diagnosis, emphasizing its promising role in early detection and preventing irreversible vision loss. The integration of ML and DNNs in medical imaging analysis suggests a valuable path for future advancements in ophthalmic healthcare. [ABSTRACT FROM AUTHOR]

Brain tumors pose a significant medical challenge necessitating precise detection and diagnosis, especially in Magnetic resonance imaging(MRI). Current methodologies reliant on traditional image processing and conventional machine learning encounter hurdles in accurately discerning tumor regions within intricate MRI scans, often susceptible to noise and varying image quality. The advent of artificial intelligence (AI) has revolutionized various aspects of healthcare, providing innovative solutions for diagnostics and treatment strategies. This paper introduces a novel AI-driven methodology for brain tumor detection from MRI images, leveraging the EfficientNetB2 deep learning architecture. Our approach incorporates advanced image preprocessing techniques, including image cropping, equalization, and the application of homomorphic filters, to enhance the quality of MRI data for more accurate tumor detection. The proposed model exhibits substantial performance enhancement by demonstrating validation accuracies of 99.83%, 99.75%, and 99.2% on BD-BrainTumor, Brain-tumor-detection, and Brain-MRI-images-for-brain-tumor-detection datasets respectively, this research holds promise for refined clinical diagnostics and patient care, fostering more accurate and reliable brain tumor identification from MRI images. All data is available on Github: https://github.com/muskan258/Brain-Tumor-Detection-from-MRI-Images-Utilizing-EfficientNetB2). [ABSTRACT FROM AUTHOR]

Background: Decision-making in healthcare is increasingly complex; notably in hospital environments where the information density is high, e.g., emergency departments, oncology departments, and psychiatry departments. This study aims to discover decisions from logged data to improve the decision-making process. Methods: The Design Science Research Methodology (DSRM) was chosen to design an artifact (algorithm) for the discovery and visualization of decisions. The DSRM's different activities are explained, from the definition of the problem to the evaluation of the artifact. During the design and development activities, the algorithm itself is created. During the demonstration and evaluation activities, the algorithm was tested with an authentic synthetic dataset. Results: The results show the design and simulation of an algorithm for the discovery and visualization of decisions. A fuzzy classifier algorithm was adapted for (1) discovering decisions from a decision log and (2) visualizing the decisions using the Decision Model and Notation standard. Conclusions: In this paper, we show that decisions can be discovered from a decision log and visualized for the improvement of the decision-making process of healthcare professionals or to support the periodic evaluation of protocols and guidelines. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) signals are very important for heart disease diagnosis. In this paper, a novel early prediction method based on Nested Long Short-Term Memory (Nested LSTM) is developed for sudden cardiac death risk detection. First, wavelet denoising and normalization techniques are utilized for reliable reconstruction of ECG signals from extreme noise conditions. Then, a nested LSTM structure is adopted, which can guide the memory forgetting and memory selection of ECG signals, so as to improve the data processing ability and prediction accuracy of ECG signals. To demonstrate the effectiveness of the proposed method, four different models with different signal prediction techniques are used for comparison. The extensive experimental results show that this method can realize an accurate prediction of the cardiac beat's starting point and track the trend of ECG signals effectively. This study holds significant value for timely intervention for patients at risk of sudden cardiac death. [ABSTRACT FROM AUTHOR]

Background: The goal of this study was to assess the effectiveness of machine learning models and create an interpretable machine learning model that adequately explained 3-year all-cause mortality in patients with chronic heart failure. Methods: The data in this paper were selected from patients with chronic heart failure who were hospitalized at the First Affiliated Hospital of Kunming Medical University, from 2017 to 2019 with cardiac function class III-IV. The dataset was explored using six different machine learning models, including logistic regression, naive Bayes, random forest classifier, extreme gradient boost, K-nearest neighbor, and decision tree. Finally, interpretable methods based on machine learning, such as SHAP value, permutation importance, and partial dependence plots, were used to estimate the 3-year all-cause mortality risk and produce individual interpretations of the model's conclusions. Result: In this paper, random forest was identified as the optimal aools lgorithm for this dataset. We also incorporated relevant machine learning interpretable tand techniques to improve disease prognosis, including permutation importance, PDP plots and SHAP values for analysis. From this study, we can see that the number of hospitalizations, age, glomerular filtration rate, BNP, NYHA cardiac function classification, lymphocyte absolute value, serum albumin, hemoglobin, total cholesterol, pulmonary artery systolic pressure and so on were important for providing an optimal risk assessment and were important predictive factors of chronic heart failure. Conclusion: The machine learning-based cardiovascular risk models could be used to accurately assess and stratify the 3-year risk of all-cause mortality among CHF patients. Machine learning in combination with permutation importance, PDP plots, and the SHAP value could offer a clear explanation of individual risk prediction and give doctors an intuitive knowledge of the functions of important model components. [ABSTRACT FROM AUTHOR]

Background: Patient safety is a central healthcare policy worldwide. Adverse drug events (ADE) are among the main threats to patient safety. Children are at a higher risk of ADE in each stage of medication management process. ADE rate is high in the administration stage, as the final stage of preventing medication errors in pediatrics and neonates. The most effective way to reduce ADE rate is using medication administration clinical decision support systems (MACDSSs). The present study reviewed the literature on MACDSS for neonates and pediatrics. It identified and classified the data elements that mapped onto the Fast Healthcare Interoperability Resources (FHIR) standard and the functionalities of these systems to guide future research. Methods: PubMed/ MEDLINE, Embase, CINAHL, and ProQuest databases were searched from 1995 to June 31, 2021. Studies that addressed developing or applying medication administration software for neonates and pediatrics were included. Two authors reviewed the titles, abstracts, and full texts. The quality of eligible studies was assessed based on the level of evidence. The extracted data elements were mapped onto the FHIR standard. Results: In the initial search, 4,856 papers were identified. After removing duplicates, 3,761 titles, and abstracts were screened. Finally, 56 full-text papers remained for evaluation. The full-text review of papers led to the retention of 10 papers which met the eligibility criteria. In addition, two papers from the reference lists were included. A total number of 12 papers were included for analysis. Six papers were categorized as high-level evidence. Only three papers evaluated their systems in a real environment. A variety of data elements and functionalities could be observed. Overall, 84 unique data elements were extracted from the included papers. The analysis of reported functionalities showed that 18 functionalities were implemented in these systems. Conclusion: Identifying the data elements and functionalities as a roadmap by developers can significantly improve MACDSS performance. Though many CDSSs have been developed for different medication processes in neonates and pediatrics, few have actually evaluated MACDSSs in reality. Therefore, further research is needed on the application and evaluation of MACDSSs in the real environment. Protocol Registration: (dx.doi.org/10.17504/protocols.io.bwbwpape). [ABSTRACT FROM AUTHOR]

Background: We conducted this study with the aim of identifying factors that affect the use of health information technology in the treatment and management of hypertension. Methods: This paper is a descriptive-analytic study conducted in 2022. To obtain relevant articles, databases including Scopus, Web of Science, IEEE, and PubMed were searched and the time period was between 2013 and 2022. Based on the review of similar articles, a five-point Likert scale checklist was developed in the second phase. The statistical population of the present study was specialist physicians (N = 40) and patients (N = 384). In order to analyze the data, SPSS Statistics 24 was used. To analyze the data obtained from the checklist, we used summary statistics (mean and standard deviation). Results: As a result of the review literature process, 50 papers were screened, that based we can distinguish motivational and inhibitory factors affecting the use of health information technology in hypertension management. Indeed, Motivational factors and inhibitory factors can be classified into five groups: organizational, economic, technical, personal, and legal/moral factors. Based on the results of the checklist, the factors that were identified as most influential on motivation and inhibitory patients and specialist physicians' to use of health information technology to manage and treat hypertension. Conclusion: Utilizing technologies for hypertension, its management can be improved by identifying motivating and inhibiting factors. Our approach can improve the acceptability of these technologies, save costs, reduce long-term complications of hypertension, and improve patient quality of life. [ABSTRACT FROM AUTHOR]

Background For disease surveillance, manual data collection using paper-based questionnaires can be time consuming and prone to errors. We introduced smartphone data collection to replace paperbased data collection for an influenza sentinel surveillance system in four hospitals in Kenya. We compared the quality, cost and timeliness of data collection between the smartphone data collection system and the paper-based system. Methods Since 2006, the Kenya Ministry of Health (MoH) with technical support from the Kenya Medical Research Institute/Centers for Disease Control and Prevention (KEMRI/CDC) conducted hospital-based sentinel surveillance for influenza in Kenya. In May 2011, the MOH replaced paper-based collection with an electronic data collection system using Field Adapted Survey Toolkit (FAST) on HTC Touch Pro2 smartphones at four sentinel sites. We compared 880 paper-based questionnaires dated Jan 2010-Jun 2011 and 880 smartphone questionnaires dated May 2011-Jun 2012 from the four surveillance sites. For each site, we compared the quality, cost and timeliness of each data collection system. Results Incomplete records were more likely seen in data collected using pen-and-paper compared to data collected using smartphones (adjusted incidence rate ratio (aIRR) 7, 95% CI: 4.4-10.3). Errors and inconsistent answers were also more likely to be seen in data collected using penand-paper compared to data collected using smartphones (aIRR: 25, 95% CI: 12.5-51.8). Smartphone data was uploaded into the database in a median time of 7 days while paperbased data took a median of 21 days to be entered (p < 0.01). It cost USD 1,501 (9.4%) more to establish the smartphone data collection system ($17,500) than the pen-and-paper system (USD $15,999). During two years, however, the smartphone data collection system was $3,801 (7%) less expensive to operate ($50,200) when compared to pen-and-paper system ($54,001). Conclusions Compared to paper-based data collection, an electronic data collection system produced fewer incomplete data, fewer errors and inconsistent responses and delivered data faster. Although start-up costs were higher, the overall costs of establishing and running the electronic data collection system were lower compared to paper-based data collection system. Electronic data collection using smartphones has potential to improve timeliness, data integrity and reduce costs. [ABSTRACT FROM AUTHOR]

Background: In an attempt to address a complex disease burden, including improving progress towards MDGs 4 and 5, South Africa recently introduced a re-engineered Primary Health Care (PHC) strategy, which has led to the development of a national community health worker (CHW) programme. The present study explored the development of a cell phone-based and paper-based monitoring and evaluation (M&E) system to support the work of the CHWs. Methods: One sub-district in the North West province was identified for the evaluation. One outreach team comprising ten CHWs maintained both the paper forms and mHealth system to record household data on community-based services. A comparative analysis was done to calculate the correspondence between the paper and phone records. A focus group discussion was conducted with the CHWs. Clinical referrals, data accuracy and supervised visits were compared and analysed for the paper and phone systems. Results: Compared to the mHealth system where data accuracy was assured, 40% of the CHWs showed a consistently high level (>90% correspondence) of data transfer accuracy on paper. Overall, there was an improvement over time, and by the fifth month, all CHWs achieved a correspondence of 90% or above between phone and paper data. The most common error that occurred was summing the total number of visits and/or activities across the five household activity indicators. Few supervised home visits were recorded in either system and there was no evidence of the team leader following up on the automatic notifications received on their cell phones. Conclusions: The evaluation emphasizes the need for regular supervision for both systems and rigorous and ongoing assessments of data quality for the paper system. Formalization of a mHealth M&E system for PHC outreach teams delivering community based services could offer greater accuracy of M&E and enhance supervision systems for CHWs. [ABSTRACT FROM AUTHOR]

Background: Providing patient information to physicians in usable form is of high importance. Electronic presentation of patient data may have benefits in efficiency and error rate reduction for these physician facing interfaces. Using a cancer symptom measurement tool (the MD Anderson Symptom Inventory (MDASI)) we assessed the usability of patient data in its raw paper form and compared that to presentation on two electronic presentation formats of different sizes. Methods: In two separate experiments, undergraduates completed two identical six-part questionnaires on two twenty-patient MDASI data sets. In Experiment 1, participants completed one questionnaire using a paper packet and the other questionnaire using an in-house designed iPad application. In Experiment 2, MDASI data was evaluated using an iPad and iPod Touch. Participants assessed the usability of the devices directly after use. In a third experiment, medical professionals evaluated the paper and iPad interfaces in order to validate the findings from Experiment 1. Results: Participants were faster and more accurate answering questions about patients when using the iPad. The results from the medical professionals were similar. No appreciable accuracy, task time, or usability differences were observed between the iPad and iPod Touch. Conclusions: Overall, the use of our tablet interface increased the accuracy and speed that users could extract pertinent information from a multiple patient MDASI data set compared to paper. Reducing the size of the interface did not negatively affect accuracy, speed, or usability. Generalization of the results to other physician facing interfaces is discussed. [ABSTRACT FROM AUTHOR]

Background: It has been shown that implementation of electronic medical records (EMR) and withdrawal of the paper-based medical record is feasible, but represents a drastic change in the information environment of hospital physicians. Previous investigations have revealed considerable inter-hospital variations in EMR system use and user satisfaction. The aim of this study was to further explore changes of clinicians' work after the EMR system implementation process and how they experienced working in a paper-deprived information environment. Methods: Qualitative study based on 18 semi-structured interviews with physicians in two Norwegian hospitals. Results: Ten different but related characteristics of work within the EMR-based practice were identified; (1) there was closer clinical and administrative cooperation during the implementation processes; (2) there were greater benefits when everybody used the system; (3) systems supported freshmen better than experienced physicians; (4) the EMR was useful in regard to professional learning; (5) new users were given an introduction to the system by experienced; (6) younger clinicians reported different attitudes than senior clinicians, but this might be related to more than age and previous experience with computers; (7) the EMR made it easier to generate free-text notes, but this also created a potential for information overflow; (8) there is little or no support for mobile work; (9) instances of downtime are still experienced, and this influenced the attitude towards the system and (10) clinicians preferred EMR-only compared to combined paper and electronic systems. Conclusion: Despite the removal of paper-based records from clinical workflow (a change that hospital clinicians perceived as highly useful), many of the old routines remained unchanged, limiting the potential of the EMR system. Thus, there is a need to not only remove paper in the physical sense, but also to established routines to fully achieve the benefits of an EMR system. [ABSTRACT FROM AUTHOR]

Background: Telemedicine has experienced rapid growth in recent years, aiming to enhance medical efficiency and reduce the workload of healthcare professionals. During the COVID-19 pandemic in 2019, it became especially crucial, enabling remote screenings and access to healthcare services while maintaining social distancing. Online consultation platforms have emerged, but the demand has strained the availability of medical professionals, directly leading to research and development in automated medical consultation. Specifically, there is a need for efficient and accurate medical dialogue summarization algorithms to condense lengthy conversations into shorter versions focused on relevant medical facts. The success of large language models like generative pre-trained transformer (GPT)-3 has recently prompted a paradigm shift in natural language processing (NLP) research. In this paper, we will explore its impact on medical dialogue summarization. Methods: We present the performance and evaluation results of two approaches on a medical dialogue dataset. The first approach is based on fine-tuned pre-trained language models, such as bert-based summarization (BERTSUM) and bidirectional auto-regressive Transformers (BART). The second approach utilizes a large language models (LLMs) GPT-3.5 with inter-context learning (ICL). Evaluation is conducted using automated metrics such as ROUGE and BERTScore. Results: In comparison to the BART and ChatGPT models, the summaries generated by the BERTSUM model not only exhibit significantly lower ROUGE and BERTScore values but also fail to pass the testing for any of the metrics in manual evaluation. On the other hand, the BART model achieved the highest ROUGE and BERTScore values among all evaluated models, surpassing ChatGPT. Its ROUGE-1, ROUGE-2, ROUGE-L, and BERTScore values were 14.94%, 53.48%, 32.84%, and 6.73% higher respectively than ChatGPT's best results. However, in the manual evaluation by medical experts, the summaries generated by the BART model exhibit satisfactory performance only in the "Readability" metric, with less than 30% passing the manual evaluation in other metrics. When compared to the BERTSUM and BART models, the ChatGPT model was evidently more favored by human medical experts. Conclusion: On one hand, the GPT-3.5 model can manipulate the style and outcomes of medical dialogue summaries through various prompts. The generated content is not only better received than results from certain human experts but also more comprehensible, making it a promising avenue for automated medical dialogue summarization. On the other hand, automated evaluation mechanisms like ROUGE and BERTScore fall short in fully assessing the outputs of large language models like GPT-3.5. Therefore, it is necessary to research more appropriate evaluation criteria. [ABSTRACT FROM AUTHOR]

Background: Economic evaluation of emerging health technologies is mandated by agencies such as the National Institute for Health and Care Excellence (NICE) to ensure their cost is proportional to their benefit. To avoid bias, NICE stipulate that the benefit of a treatment is assessed across the lifetime of the patient population, which can be many decades. Unfortunately, follow-up from a clinical trial will not usually cover the required period and the observed follow-up will require extrapolation. For survival data this is often done by selecting a preferred model from a set of candidate parametric models. This approach is limited in that the choice of model is restricted to those originally fitted. What if none of the models are consistent with clinical prediction or external data? Method/Results: This paper introduces SurvInt, a tool that estimates the parameters of common parametric survival models which interpolate key survival time co-ordinates specified by the user, which could come from external trials, real world data or expert clinical opinion. This is achieved by solving simultaneous equations based on the survival functions of the parametric models. The application of SurvInt is shown through two examples where traditional parametric modelling did not produce models that were consistent with external data or clinical opinion. Additional features include model averaging, mixture cure models, background mortality, piecewise modelling, restricted mean survival time estimation and probabilistic sensitivity analysis. Conclusions: SurvInt allows precise parametric survival models to be estimated and carried forward into economic models. It provides access to extrapolations that are consistent with multiple data sources such as observed data and clinical predictions, opening the door to precise exploration of regions of uncertainty/disagreement. SurvInt could avoid the need for post-hoc adjustments for complications such as treatment switching, which are often applied to obtain a plausible survival model but at the cost of introducing additional uncertainty. Phase III clinical trials are not designed with extrapolation in mind, and so it is sensible to consider alternative approaches to predict future survival that incorporate external information. [ABSTRACT FROM AUTHOR]

Importance: Large language models (LLMs) like OpenAI's ChatGPT are powerful generative systems that rapidly synthesize natural language responses. Research on LLMs has revealed their potential and pitfalls, especially in clinical settings. However, the evolving landscape of LLM research in medicine has left several gaps regarding their evaluation, application, and evidence base. Objective: This scoping review aims to (1) summarize current research evidence on the accuracy and efficacy of LLMs in medical applications, (2) discuss the ethical, legal, logistical, and socioeconomic implications of LLM use in clinical settings, (3) explore barriers and facilitators to LLM implementation in healthcare, (4) propose a standardized evaluation framework for assessing LLMs' clinical utility, and (5) identify evidence gaps and propose future research directions for LLMs in clinical applications. Evidence review: We screened 4,036 records from MEDLINE, EMBASE, CINAHL, medRxiv, bioRxiv, and arXiv from January 2023 (inception of the search) to June 26, 2023 for English-language papers and analyzed findings from 55 worldwide studies. Quality of evidence was reported based on the Oxford Centre for Evidence-based Medicine recommendations. Findings: Our results demonstrate that LLMs show promise in compiling patient notes, assisting patients in navigating the healthcare system, and to some extent, supporting clinical decision-making when combined with human oversight. However, their utilization is limited by biases in training data that may harm patients, the generation of inaccurate but convincing information, and ethical, legal, socioeconomic, and privacy concerns. We also identified a lack of standardized methods for evaluating LLMs' effectiveness and feasibility. Conclusions and relevance: This review thus highlights potential future directions and questions to address these limitations and to further explore LLMs' potential in enhancing healthcare delivery. [ABSTRACT FROM AUTHOR]

Background: The burden of chronic conditions is growing in Australia with people in remote areas experiencing high rates of disease, especially kidney disease. Health care in remote areas of the Northern Territory (NT) is complicated by a mobile population, high staff turnover, poor communication between health services and complex comorbid health conditions requiring multidisciplinary care. Aim: This paper aims to describe the collaborative process between research, government and non-government health services to develop an integrated clinical decision support system to improve patient care. Methods: Building on established partnerships in the government and Aboriginal Community-Controlled Health Service (ACCHS) sectors, we developed a novel digital clinical decision support system for people at risk of developing kidney disease (due to hypertension, diabetes, cardiovascular disease) or with kidney disease. A cross-organisational and multidisciplinary Steering Committee has overseen the design, development and implementation stages. Further, the system's design and functionality were strongly informed by experts (Clinical Reference Group and Technical Working Group), health service providers, and end-user feedback through a formative evaluation. Results: We established data sharing agreements with 11 ACCHS to link patient level data with 56 government primary health services and six hospitals. Electronic Health Record (EHR) data, based on agreed criteria, is automatically and securely transferred from 15 existing EHR platforms. Through clinician-determined algorithms, the system assists clinicians to diagnose, monitor and provide guideline-based care for individuals, as well as service-level risk stratification and alerts for clinically significant events. Conclusion: Disconnected health services and separate EHRs result in information gaps and a health and safety risk, particularly for patients who access multiple health services. However, barriers to clinical data sharing between health services still exist. In this first phase, we report how robust partnerships and effective governance processes can overcome these barriers to support clinical decision making and contribute to holistic care. [ABSTRACT FROM AUTHOR]

Deep learning has been increasingly utilized in the medical field and achieved many goals. Since the size of data dominates the performance of deep learning, several medical institutions are conducting joint research to obtain as much data as possible. However, sharing data is usually prohibited owing to the risk of privacy invasion. Federated learning is a reasonable idea to train distributed multicenter data without direct access; however, a central server to merge and distribute models is needed, which is expensive and hardly approved due to various legal regulations. This paper proposes a continual learning framework for a multicenter study, which does not require a central server and can prevent catastrophic forgetting of previously trained knowledge. The proposed framework contains the continual learning method selection process, assuming that a single method is not omnipotent for all involved datasets in a real-world setting and that there could be a proper method to be selected for specific data. We utilized the fake data based on a generative adversarial network to evaluate methods prospectively, not ex post facto. We used four independent electrocardiogram datasets for a multicenter study and trained the arrhythmia detection model. Our proposed framework was evaluated against supervised and federated learning methods, as well as finetuning approaches that do not include any regulation to preserve previous knowledge. Even without a central server and access to the past data, our framework achieved stable performance (AUROC 0.897) across all involved datasets, achieving comparable performance to federated learning (AUROC 0.901). [ABSTRACT FROM AUTHOR]

Introduction: Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy. Method: To optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis. Result: In this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%. Conclusion: Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models. [ABSTRACT FROM AUTHOR]

Background: To gain insight into the real-life care of patients in the healthcare system, data from hospital information systems and insurance systems are required. Consequently, linking clinical data with claims data is necessary. To ensure their syntactic and semantic interoperability, the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) from the Observational Health Data Sciences and Informatics (OHDSI) community was chosen. However, there is no detailed guide that would allow researchers to follow a generic process for data harmonization, i.e. the transformation of local source data into the standardized OMOP CDM format. Thus, the aim of this paper is to conceptualize a generic data harmonization process for OMOP CDM. Methods: For this purpose, we conducted a literature review focusing on publications that address the harmonization of clinical or claims data in OMOP CDM. Subsequently, the process steps used and their chronological order as well as applied OHDSI tools were extracted for each included publication. The results were then compared to derive a generic sequence of the process steps. Results: From 23 publications included, a generic data harmonization process for OMOP CDM was conceptualized, consisting of nine process steps: dataset specification, data profiling, vocabulary identification, coverage analysis of vocabularies, semantic mapping, structural mapping, extract-transform-load-process, qualitative and quantitative data quality analysis. Furthermore, we identified seven OHDSI tools which supported five of the process steps. Conclusions: The generic data harmonization process can be used as a step-by-step guide to assist other researchers in harmonizing source data in OMOP CDM. [ABSTRACT FROM AUTHOR]

Background: Electronic health records (EHRs) contain valuable information for clinical research; however, the sensitive nature of healthcare data presents security and confidentiality challenges. De-identification is therefore essential to protect personal data in EHRs and comply with government regulations. Named entity recognition (NER) methods have been proposed to remove personal identifiers, with deep learning-based models achieving better performance. However, manual annotation of training data is time-consuming and expensive. The aim of this study was to develop an automatic de-identification pipeline for all kinds of clinical documents based on a distant supervised method to significantly reduce the cost of manual annotations and to facilitate the transfer of the de-identification pipeline to other clinical centers. Methods: We proposed an automated annotation process for French clinical de-identification, exploiting data from the eHOP clinical data warehouse (CDW) of the CHU de Rennes and national knowledge bases, as well as other features. In addition, this paper proposes an assisted data annotation solution using the Prodigy annotation tool. This approach aims to reduce the cost required to create a reference corpus for the evaluation of state-of-the-art NER models. Finally, we evaluated and compared the effectiveness of different NER methods. Results: A French de-identification dataset was developed in this work, based on EHRs provided by the eHOP CDW at Rennes University Hospital, France. The dataset was rich in terms of personal information, and the distribution of entities was quite similar in the training and test datasets. We evaluated a Bi-LSTM + CRF sequence labeling architecture, combined with Flair + FastText word embeddings, on a test set of manually annotated clinical reports. The model outperformed the other tested models with a significant F1 score of 96,96%, demonstrating the effectiveness of our automatic approach for deidentifying sensitive information. Conclusions: This study provides an automatic de-identification pipeline for clinical notes, which can facilitate the reuse of EHRs for secondary purposes such as clinical research. Our study highlights the importance of using advanced NLP techniques for effective de-identification, as well as the need for innovative solutions such as distant supervision to overcome the challenge of limited annotated data in the medical domain. [ABSTRACT FROM AUTHOR]

This paper introduces a forensic psychiatry database established in Japan and discusses its significance and future issues. The purpose of this Database, created under the Medical Treatment and Supervision Act (MTSA) Database Project, is to improve the quality of forensic psychiatry treatment. It can collect monthly data on "basic information," "Orders and hospitalizations under the MTSA," "Treatment process," "Criminal and medical treatment history," and "problematic behavior in the unit." The online system has accumulated data on more than 8,000 items in 24 broad categories. Medical data are exported from the medical care assisting system of 32 designated inpatient facilities in XML format and then saved on USB memory sticks. The files are imported into the Database system client, which sends the data to the Database server via a virtual private network. This system minimizes errors and efficiently imports patient data. However, there is a limitation that it is difficult to set items that need to be analyzed to solve everyday clinical problems into the database system because they tend to change over time. By evaluating the effectiveness of the Database, and collecting appropriate data, it is expected to disseminate a wide range of knowledge that will contribute to the future development of mental health and welfare care. [ABSTRACT FROM AUTHOR]

Prostate cancer, the most common cancer in men, is influenced by age, family history, genetics, and lifestyle factors. Early detection of prostate cancer using screening methods improves outcomes, but the balance between overdiagnosis and early detection remains debated. Using Deep Learning (DL) algorithms for prostate cancer detection offers a promising solution for accurate and efficient diagnosis, particularly in cases where prostate imaging is challenging. In this paper, we propose a Prostate Cancer Detection Model (PCDM) model for the automatic diagnosis of prostate cancer. It proves its clinical applicability to aid in the early detection and management of prostate cancer in real-world healthcare environments. The PCDM model is a modified ResNet50-based architecture that integrates faster R-CNN and dual optimizers to improve the performance of the detection process. The model is trained on a large dataset of annotated medical images, and the experimental results show that the proposed model outperforms both ResNet50 and VGG19 architectures. Specifically, the proposed model achieves high sensitivity, specificity, precision, and accuracy rates of 97.40%, 97.09%, 97.56%, and 95.24%, respectively. [ABSTRACT FROM AUTHOR]

Background: In recent years, the discovery of clinical pathways (CPs) from electronic medical records (EMRs) data has received increasing attention because it can directly support clinical doctors with explicit treatment knowledge, which is one of the key challenges in the development of intelligent healthcare services. However, the existing work has focused on topic probabilistic models, which usually produce treatment patterns with similar treatment activities, and such discovered treatment patterns do not take into account the temporal process of patient treatment which does not meet the needs of practical medical applications. Methods: Based on the assumption that CPs can be derived from the data of EMRs which usually record the treatment process of patients, this paper proposes a new CPs mining method from EMRs, an extended form of the traditional topic model - the temporal topic model (TTM). The method can capture the treatment topics and the corresponding treatment timestamps for each treatment day. Results: Experimental research conducted on a real-world dataset of patients' hospitalization processes, and the achieved results demonstrate the applicability and usefulness of the proposed methodology for CPs mining. Compared to existing benchmarks, our model shows significant improvement and robustness. Conclusion: Our TTM provides a more competitive way to mine potential CPs considering the temporal features of the EMR data, providing a very prospective tool to support clinical diagnostic decisions. [ABSTRACT FROM AUTHOR]

Background: Handheld computers are increasingly favoured over paper and pencil methods to capture data in clinical research. Methods: This study systematically identified and reviewed randomized controlled trials (RCTs) that compared the two methods for self-recording and reporting data, and where at least one of the following outcomes was assessed: data accuracy; timeliness of data capture; and adherence to protocols for data collection. Results: A comprehensive key word search of NLM Gateway's database yielded 9 studies fitting the criteria for inclusion. Data extraction was performed and checked by two of the authors. None of the studies included all outcomes. The results overall, favor handheld computers over paper and pencil for data collection among study participants but the data are not uniform for the different outcomes. Handheld computers appear superior in timeliness of receipt and data handling (four of four studies) and are preferred by most subjects (three of four studies). On the other hand, only one of the trials adequately compared adherence to instructions for recording and submission of data (handheld computers were superior), and comparisons of accuracy were inconsistent between five studies. Conclusion: Handhelds are an effective alternative to paper and pencil modes of data collection; they are faster and were preferred by most users. [ABSTRACT FROM AUTHOR]

Background: Most hospitals keep and update their paper-based medical records after introducing an electronic medical record or a hospital information system (HIS). This case report describes a HIS in a hospital where the paper-based medical records are scanned and eliminated. To evaluate the HIS comprehensively, the perspectives of medical secretaries and nurses are described as well as that of physicians. Methods: We have used questionnaires and interviews to assess and compare frequency of use of the HIS for essential tasks, task performance and user satisfaction among medical secretaries, nurses and physicians. Results: The medical secretaries use the HIS much more than the nurses and the physicians, and they consider that the electronic HIS greatly has simplified their work. The work of nurses and physicians has also become simplified, but they find less satisfaction with the system, particularly with the use of scanned document images. Conclusions: Although the basis for reference is limited, the results support the assertion that replacing the paper-based medical record primarily benefits the medical secretaries, and to a lesser degree the nurses and the physicians. The varying results in the different employee groups emphasize the need for a multidisciplinary approach when evaluating a HIS. [ABSTRACT FROM AUTHOR]

The article focuses on informed decision making in medical care when clinical evidence and conventional wisdom collide. It also discusses the U.S. Agency for Healthcare Research & Quality (AHRQ) involvement in exploring issues that impact clinical decision making under the AHRQ Effective Health Care (EHC) Program.

Background: With the rapid development of the medical industry and the gradual increase in people's awareness of their health, the use of the Internet for medical question and answer, to obtain more accurate medical answers. It is necessary to first calculate the similarity of the questions asked by users, which further matches professional medical answers. Improving the efficiency of online medical question and answer sessions will not only reduce the burden on doctors, but also enhance the patient's experience of online medical diagnosis. Method: This paper focuses on building a bidirectional gated recurrent unit(BiGRU) deep learning model based on Siamese network for medical interrogative similarity matching, using Word2Vec word embedding tool for word vector processing of ethnic-medical corpus, and introducing an attention mechanism and convolutional neural network. Bidirectional gated recurrent unit extracts contextual semantic information and long-distance dependency features of interrogative sentences; Similar ethnic medicine interrogatives vary in length and structure, and the key information in the interrogative is crucial to similarity identification. By introducing an attention mechanism higher weight can be given to the keywords in the question, further improving the recognition of similar words in the question. Convolutional neural network takes into account the local information of interrogative sentences and can capture local position invariance, allowing feature extraction for words of different granularity through convolutional operations; By comparing the Euclidean distance, cosine distance and Manhattan distance to calculate the spatial distance of medical interrogatives, the Manhattan distance produced the best similarity result. Result: Based on the ethnic medical question dataset constructed in this paper, the accuracy and F1-score reached 97.24% and 97.98%, which is a significant improvement compared to several other models. Conclusion: By comparing with other models, the model proposed in this paper has better performance and achieve accurate matching of similar semantic question data of ethnic medicine. [ABSTRACT FROM AUTHOR]

In this paper, we present a framework for developing a Learning Health System (LHS) to provide means to a computerized clinical decision support system for allied healthcare and/or nursing professionals. LHSs are well suited to transform healthcare systems in a mission-oriented approach, and is being adopted by an increasing number of countries. Our theoretical framework provides a blueprint for organizing such a transformation with help of evidence based state of the art methodologies and techniques to eventually optimize personalized health and healthcare. Learning via health information technologies using LHS enables users to learn both individually and collectively, and independent of their location. These developments demand healthcare innovations beyond a disease focused orientation since clinical decision making in allied healthcare and nursing is mainly based on aspects of individuals' functioning, wellbeing and (dis)abilities. Developing LHSs depends heavily on intertwined social and technological innovation, and research and development. Crucial factors may be the transformation of the Internet of Things into the Internet of FAIR data & services. However, Electronic Health Record (EHR) data is in up to 80% unstructured including free text narratives and stored in various inaccessible data warehouses. Enabling the use of data as a driver for learning is challenged by interoperability and reusability. To address technical needs, key enabling technologies are suitable to convert relevant health data into machine actionable data and to develop algorithms for computerized decision support. To enable data conversions, existing classification and terminology systems serve as definition providers for natural language processing through (un)supervised learning. To facilitate clinical reasoning and personalized healthcare using LHSs, the development of personomics and functionomics are useful in allied healthcare and nursing. Developing these omics will be determined via text and data mining. This will focus on the relationships between social, psychological, cultural, behavioral and economic determinants, and human functioning. Furthermore, multiparty collaboration is crucial to develop LHSs, and man-machine interaction studies are required to develop a functional design and prototype. During development, validation and maintenance of the LHS continuous attention for challenges like data-drift, ethical, technical and practical implementation difficulties is required. [ABSTRACT FROM AUTHOR]

Purpose: Today, the Internet provides access to many patients' experiences, which is crucial in assessing the quality of healthcare services. This paper introduces a model for detecting cancer patients' opinions about healthcare services in the Persian language, both positive and negative. Method: To achieve the objectives of this study, a combination of sentiment analysis (SA) and topic modeling approaches was employed. All pertinent comments made by cancer patients were collected from the patient feedback form of the Tehran University of Medical Science (TUMS) Cancer Institute (CI) in Iran, from March to October 2021. Conventional evaluation metrics such as accuracy, precision, recall, and F-measure were utilized to assess the performance of the proposed model. Result: The experimental findings revealed that the proposed SA model achieved accuracies of 89.3%, 92.6%, and 90.8% in detecting patients' sentiments towards general services, healthcare services, and life expectancy, respectively. Based on the topic modeling results, the topic "Metastasis" exhibited lower sentiment scores compared to other topics. Additionally, cancer patients expressed dissatisfaction with the current appointment booking service, while topics such as "Good experience," "Affable staff", and "Chemotherapy" garnered higher sentiment scores. Conclusion: The combined use of SA and topic modeling offers valuable insights into healthcare services. Policymakers can utilize the knowledge obtained from these topics and associated sentiments to enhance patient satisfaction with cancer institution services. [ABSTRACT FROM AUTHOR]

Backgrounds: The size of medical strategies is expected to grow in conjunction with the expansion of modern diseases' complexity. When a strategy includes more than ten statements, its manual management becomes very challenging, and in some cases, impossible. As a result, the updates they get may result in the unavoidable appearance of anomalies. This causes an interruption in the outflow of imperfect knowledge. Methods: In this paper, we propose an approach called TAnom-HS to verify healthcare strategies. We focus on the management and maintenance, in a convenient and automatic way, of a large strategy to guarantee knowledge accuracy and enhance the efficiency of the inference process in healthcare systems. Results: We developed a prototype of our proposal and we applied it on some cases from the BioPortal repository. The evaluation of both steps of TAnom-HS proved the efficiency of our proposal. Conclusion: To increase ontologies expressiveness, a set of rules called strategy is added to it. TAnom-HS is a two-step approach that treats anomalies in healthcare strategies. Such a task helps to take automatic and efficient healthcare decisions. [ABSTRACT FROM AUTHOR]

Multiple Sclerosis (MS) is a chronic disease developed in the human brain and spinal cord, which can cause permanent damage or deterioration of the nerves. The severity of MS disease is monitored by the Expanded Disability Status Scale, composed of several functional sub-scores. Early and accurate classification of MS disease severity is critical for slowing down or preventing disease progression via applying early therapeutic intervention strategies. Recent advances in deep learning and the wide use of Electronic Health Records (EHR) create opportunities to apply data-driven and predictive modeling tools for this goal. Previous studies focusing on using single-modal machine learning and deep learning algorithms were limited in terms of prediction accuracy due to data insufficiency or model simplicity. In this paper, we proposed the idea of using patients' multimodal longitudinal and longitudinal EHR data to predict multiple sclerosis disease severity in the future. Our contribution has two main facets. First, we describe a pioneering effort to integrate structured EHR data, neuroimaging data and clinical notes to build a multi-modal deep learning framework to predict patient's MS severity. The proposed pipeline demonstrates up to 19% increase in terms of the area under the Area Under the Receiver Operating Characteristic curve (AUROC) compared to models using single-modal data. Second, the study also provides valuable insights regarding the amount useful signal embedded in each data modality with respect to MS disease prediction, which may improve data collection processes. [ABSTRACT FROM AUTHOR]

Background: Clinical practice guidelines (CPGs) are designed to assist doctors in clinical decision making. High-quality research articles are important for the development of good CPGs. Commonly used manual screening processes are time-consuming and labor-intensive. Artificial intelligence (AI)-based techniques have been widely used to analyze unstructured data, including texts and images. Currently, there are no effective/efficient AI-based systems for screening literature. Therefore, developing an effective method for automatic literature screening can provide significant advantages. Methods: Using advanced AI techniques, we propose the Paper title, Abstract, and Journal (PAJO) model, which treats article screening as a classification problem. For training, articles appearing in the current CPGs are treated as positive samples. The others are treated as negative samples. Then, the features of the texts (e.g., titles and abstracts) and journal characteristics are fully utilized by the PAJO model using the pretrained bidirectional-encoder-representations-from-transformers (BERT) model. The resulting text and journal encoders, along with the attention mechanism, are integrated in the PAJO model to complete the task. Results: We collected 89,940 articles from PubMed to construct a dataset related to neck pain. Extensive experiments show that the PAJO model surpasses the state-of-the-art baseline by 1.91% (F1 score) and 2.25% (area under the receiver operating characteristic curve). Its prediction performance was also evaluated with respect to subject-matter experts, proving that PAJO can successfully screen high-quality articles. Conclusions: The PAJO model provides an effective solution for automatic literature screening. It can screen high-quality articles on neck pain and significantly improve the efficiency of CPG development. The methodology of PAJO can also be easily extended to other diseases for literature screening. [ABSTRACT FROM AUTHOR]

Background: Lyme disease is one of the most commonly reported infectious diseases in the United States (US), accounting for more than 90 % of all vector-borne diseases in North America. Objective: In this paper, self-reported tweets on Twitter were analyzed in order to predict potential Lyme disease cases and accurately assess incidence rates in the US. Methods: The study was done in three stages: (1) Approximately 1.3 million tweets were collected and pre-processed to extract the most relevant Lyme disease tweets with geolocations. A subset of tweets were semi-automatically labelled as relevant or irrelevant to Lyme disease using a set of precise keywords, and the remaining portion were manually labelled, yielding a curated labelled dataset of 77, 500 tweets. (2) This labelled data set was used to train, validate, and test various combinations of NLP word embedding methods and prominent ML classification models, such as TF-IDF and logistic regression, Word2vec and XGboost, and BERTweet, among others, to identify potential Lyme disease tweets. (3) Lastly, the presence of spatio-temporal patterns in the US over a 10-year period were studied. Results: Preliminary results showed that BERTweet outperformed all tested NLP classifiers for identifying Lyme disease tweets, achieving the highest classification accuracy and F1-score of 90 % . There was also a consistent pattern indicating that the West and Northeast regions of the US had a higher tweet rate over time. Conclusions: We focused on the less-studied problem of using Twitter data as a surveillance tool for Lyme disease in the US. Several crucial findings have emerged from the study. First, there is a fairly strong correlation between classified tweet counts and Lyme disease counts, with both following similar trends. Second, in 2015 and early 2016, the social media network like Twitter was essential in raising popular awareness of Lyme disease. Third, counties with a high incidence rate were not necessarily related with a high tweet rate, and vice versa. Fourth, BERTweet can be used as a reliable NLP classifier for detecting relevant Lyme disease tweets. [ABSTRACT FROM AUTHOR]

Background: The American Society of Anesthesiologists Physical Status classification (ASA PS) of surgical patients is a standard element of the preoperative assessment. In early 2013, the Department of Anesthesia was notified that the distribution of ASA PS scores for sampled patients at the University of Iowa had recently begun to deviate from national comparison data. This change appeared to coincide with the transition from paper records to a new electronic Anesthesia Information Management System (AIMS). We hypothesized that the design of the AIMS was unintentionally influencing how providers assigned ASA PS values.Methods: Primary analyses were based on 12-month blocks of data from paper records and AIMS. For the purpose of analysis, ASA PS was dichotomized to ASA PS 1 and 2 vs. ASA PS >2. To ensure that changes in ASA PS were not due to "real" changes in our patient mix, we examined other relevant covariates (e.g. age, weight, case distribution across surgical services, emergency vs. elective surgeries etc.).Results: There was a 6.1 % (95 % CI: 5.1-7.1 %) absolute increase in the fraction of ASA PS 1&2 classifications after the transition from paper (54.9 %) to AIMS (61.0 %); p < 0.001. The AIMS was then modified to make ASA PS entry clearer (e.g. clearly highlighting ASA PS on the main anesthesia record). Following the modifications, the AS PS 1&2 fraction decreased by 7.7 % (95 % CI: 6.78-8.76 %) compared to the initial AIMS records (from 61.0 to 53.3 %); p < 0.001. There were no significant or meaningful differences in basic patient characteristics and case distribution during this time.Conclusion: The transition from paper to electronic AIMS resulted in an unintended but significant shift in recorded ASA PS scores. Subsequent design changes within the AIMS resulted in resetting of the ASA PS distributions to previous values. These observations highlight the importance of how user interface and cognitive demands introduced by a computational system can impact the recording of important clinical data in the medical record. [ABSTRACT FROM AUTHOR]

Background: Despite the rapid expansion of electronic health records, the use of computer mouse and keyboard, challenges the data entry into these systems. Speech recognition software is one of the substitutes for the mouse and keyboard. The objective of this study was to evaluate the use of online and offline speech recognition software on spelling errors in nursing reports and to compare them with errors in handwritten reports.Methods: For this study, online and offline speech recognition software were selected and customized based on unrecognized terms by these softwares. Two groups of 35 nurses provided the admission notes of hospitalized patients upon their arrival using three data entry methods (using the handwritten method or two types of speech recognition software). After at least a month, they created the same reports using the other methods. The number of spelling errors in each method was determined. These errors were compared between the paper method and the two electronic methods before and after the correction of errors.Results: The lowest accuracy was related to online software with 96.4% and accuracy. On the average per report, the online method 6.76, and the offline method 4.56 generated more errors than the paper method. After correcting the errors by the participants, the number of errors in the online reports decreased by 94.75% and the number of errors in the offline reports decreased by 97.20%. The highest number of reports with errors was related to reports created by online software.Conclusion: Although two software had relatively high accuracy, they created more errors than the paper method that can be lowered by optimizing and upgrading these softwares. The results showed that error correction by users significantly reduced the documentation errors caused by the software. [ABSTRACT FROM AUTHOR]

Background: The exponential growth of digital healthcare data is fueling the development of Knowledge Discovery in Databases (KDD). Extracting temporal relationships between medical events is essential to reveal hidden patterns that can help physicians find optimal treatments, diagnose illnesses, detect drug adverse reactions, and more. This paper presents an approach for the extraction of patient evolution patterns from electronic health records written in Catalan and/or Spanish. Methods: We propose a robust formulation for extracting Temporal Association Rules (TARs) that goes beyond simple rule extraction by considering the sequence of multiple visits. Our highly configurable algorithm leverages this formulation to extract Temporal Association Rules from sequences of medical instances. We can generate rules in the desired format, content, and temporal factors while accounting for different levels of abstraction of medical instances. To demonstrate the effectiveness of our methodology, we applied it to extract patient evolution patterns from clinical histories of multimorbid patients suffering from heart disease and stroke who visited Primary Care Centers (CAP) in Catalonia. Our main objective is to uncover complex rules with multiple temporal steps, that comprise a set of medical instances. Results: As we are working with real-world, error-prone data, we propose a process of validation of the results by expert practitioners in primary care. Despite our limited dataset, the high percentage of patterns deemed correct and relevant by the experts is promising. The insights gained from these patterns can inform preventive measures and help detect risk factors, ultimately leading to better treatments and outcomes for patients. Conclusion: Our algorithm successfully extracted a set of meaningful and relevant temporal patterns, especially for the specific type of multimorbid patients considered. These patterns were evaluated by experts and demonstrated the ability to predict risk factors that are commonly associated with certain diseases. Moreover, the average time gap between the occurrence of medical events provided critical insight into the term of these risk factors. This information holds significant value in the context of primary healthcare and preventive medicine, highlighting the potential of our method to serve as a valuable medical tool. [ABSTRACT FROM AUTHOR]

Background: Data mining of electronic health records (EHRs) has a huge potential for improving clinical decision support and to help healthcare deliver precision medicine. Unfortunately, the rule-based and machine learning-based approaches used for natural language processing (NLP) in healthcare today all struggle with various shortcomings related to performance, efficiency, or transparency. Methods: In this paper, we address these issues by presenting a novel method for NLP that implements unsupervised learning of word embeddings, semi-supervised learning for simplified and accelerated clinical vocabulary and concept building, and deterministic rules for fine-grained control of information extraction. The clinical language is automatically learnt, and vocabulary, concepts, and rules supporting a variety of NLP downstream tasks can further be built with only minimal manual feature engineering and tagging required from clinical experts. Together, these steps create an open processing pipeline that gradually refines the data in a transparent way, which greatly improves the interpretable nature of our method. Data transformations are thus made transparent and predictions interpretable, which is imperative for healthcare. The combined method also has other advantages, like potentially being language independent, demanding few domain resources for maintenance, and able to cover misspellings, abbreviations, and acronyms. To test and evaluate the combined method, we have developed a clinical decision support system (CDSS) named Information System for Clinical Concept Searching (ICCS) that implements the method for clinical concept tagging, extraction, and classification. Results: In empirical studies the method shows high performance (recall 92.6%, precision 88.8%, F-measure 90.7%), and has demonstrated its value to clinical practice. Here we employ a real-life EHR-derived dataset to evaluate the method's performance on the task of classification (i.e., detecting patient allergies) against a range of common supervised learning algorithms. The combined method achieves state-of-the-art performance compared to the alternative methods we evaluate. We also perform a qualitative analysis of common word embedding methods on the task of word similarity to examine their potential for supporting automatic feature engineering for clinical NLP tasks. Conclusions: Based on the promising results, we suggest more research should be aimed at exploiting the inherent synergies between unsupervised, supervised, and rule-based paradigms for clinical NLP. [ABSTRACT FROM AUTHOR]

Background: Aggregate electronic data repositories and population-level cross-sectional surveys play a critical role in HIV programme monitoring and surveillance for data-driven decision-making. However, these data sources have inherent limitations including inability to respond to public health priorities in real-time and to longitudinally follow up clients for ascertainment of long-term outcomes. Electronic medical records (EMRs) have tremendous potential to bridge these gaps when harnessed into a centralised data repository. We describe the evolution of EMRs and the development of a centralised national data warehouse (NDW) repository. Further, we describe the distribution and representativeness of data from the NDW and explore its potential for population-level surveillance of HIV testing, care and treatment in Kenya. Main body: Health information systems in Kenya have evolved from simple paper records to web-based EMRs with features that support data transmission to the NDW. The NDW design includes four layers: data warehouse application programming interface (DWAPI), central staging, integration service, and data visualization application. The number of health facilities uploading individual-level data to the NDW increased from 666 in 2016 to 1,516 in 2020, covering 41 of 47 counties in Kenya. By the end of 2020, the NDW hosted longitudinal data from 1,928,458 individuals ever started on antiretroviral therapy (ART). In 2020, there were 936,869 individuals who were active on ART in the NDW, compared to 1,219,276 individuals on ART reported in the aggregate-level Kenya Health Information System (KHIS), suggesting 77% coverage. The proportional distribution of individuals on ART by counties in the NDW was consistent with that from KHIS, suggesting representativeness and generalizability at the population level. Conclusion: The NDW presents opportunities for individual-level HIV programme monitoring and surveillance because of its longitudinal design and its ability to respond to public health priorities in real-time. A comparison with estimates from KHIS demonstrates that the NDW has high coverage and that the data maybe representative and generalizable at the population-level. The NDW is therefore a unique and complementary resource for HIV programme monitoring and surveillance with potential to strengthen timely data driven decision-making towards HIV epidemic control in Kenya. Database link: (https://dwh.nascop.org/). [ABSTRACT FROM AUTHOR]

Background: Food frequency questionnaires (FFQs) are one of the most useful tools for studying and understanding diet-disease relationships. However, because FFQs are self-reported data, they are susceptible to response bias, social desirability bias, and misclassification. Currently, several methods have been created to combat these issues by modelling the measurement error in diet-disease relationships. Method: In this paper, a novel machine learning method is proposed to adjust for measurement error found in misreported data by using a random forest (RF) classifier to label the responses in the FFQ based on the input dataset and creating an algorithm that adjusts the measurement error. We demonstrate this method by addressing underreporting in selected FFQ responses. Result: According to the results, we have high model accuracies ranging from 78% to 92% in participant collected data and 88% in simulated data. Conclusion: This shows that our proposed method of using a RF classifier and an error adjustment algorithm is efficient to correct most of the underreported entries in the FFQ dataset and could be used independent of diet-disease models. This could help nutrition researchers and other experts to use dietary data estimated by FFQs with less measurement error and create models from the data with minimal noise. [ABSTRACT FROM AUTHOR]

Background: Large-scale medical equipment, which is extensively implemented in medical services, is of vital importance for diagnosis but vulnerable to various anomalies and failures. Most hospitals that conduct regular maintenance have been suffering from medical equipment-related incidents for years. Currently, the Internet of Medical Things (IoMT) has emerged as a crucial tool in monitoring the real-time status of the medical equipment. In this paper, we develop an IoMT system of Computed Tomography (CT) equipment in the West China Hospital, Sichuan University and collected the system status time-series data. Novel multivariate time-series classification models and frameworks are proposed to predict the anomalies of CT equipment. The important features that are closely related to the equipment anomalies are identified with the model. Methods: We extracted the real-time CT equipment status time-series data of 11 equipment between May 19, 2020 and May 19, 2021 from the IoMT, which includes the equipment oil temperature, anode voltage, etc. The arcs are identified as labels of anomalies due to their relationship with decreased imaging quality and CT equipment failures. To improve prediction accuracy, the statistics and transformations of the raw historical time-series data segment in the sliding time window are used to construct new features. Due to the particularity of time-series data, two frameworks are proposed for splitting the training and test sets. Then the Decision Tree, Support Vector Machine, Logistic Regression, Naive Bayesian, and K-Nearest Neighbor classification models are used to classify the system status. We also compare our model to state-of-the-art models. Results: The results show that the anomaly prediction accuracy and recall of our method are 79% and 77%, respectively. The oil temperature and anode voltage are identified as the decisive features that may lead to anomalies. The proposed model outperforms the others when predicting the anomalies of the CT equipment based on our dataset. Conclusions: The proposed method could predict the state of CT equipment and be used as a reference for practical maintenance, where unexpected anomalies of medical equipment could be reduced. It also brings new insights into how to handle non-uniform and imbalanced time series data in practical cases. [ABSTRACT FROM AUTHOR]