Search

ObjectiveMethodologyResultsSignificance of the ResearchIn this study, we aimed to develop a machine learning (ML) model for predicting Polycystic Ovary Syndrome (PCOS) based on demographic, clinical, and biochemical parameters.We collected data from Kaggle, which included information on age, body mass index, menstrual cycle length, follicle-stimulating hormone, hair growth, and more. Using this data, we trained several traditional ML and ensemble algorithms to predict PCOS.Among the traditional ML algorithms, Logistic Regression emerged as the best, boasting the highest accuracy of 0.91 and an AUC of 0.90. In ensemble algorithms, the Blending algorithm outperformed other ensemble methods, also achieving an accuracy of 0.91 and an AUC of 0.90, with a balanced precision and recall of 0.88.These results establish Logistic Regression and the Blending algorithm as optimal choices for accurate and reliable PCOS prediction, demonstrating strong discriminative power and the ability to correctly classify PCOS cases. [ABSTRACT FROM AUTHOR]

Background: The biomedical and health informatics (BMHI) fields have been advancing rapidly, a trend particularly emphasised during the recent COVID-19 pandemic, introducing innovations in BMHI. Over nearly 50 years since its establishment as a scientific discipline, BMHI has encountered several challenges, such as mishaps, delays, failures, and moments of enthusiastic expectations and notable successes. This paper focuses on reviewing the progress made in the BMHI discipline, evaluating key milestones, and discussing future challenges. Methods: To, Structured, step-by-step qualitative methodology was developed and applied, centred on gathering expert opinions and analysing trends from the literature to provide a comprehensive assessment. Experts and pioneers in the BMHI field were assigned thematic tasks based on the research question, providing critical inputs for the thematic analysis. This led to the identification of five key dimensions used to present the findings in the paper: informatics in biomedicine and healthcare, health data in Informatics, nurses in informatics, education and accreditation in health informatics, and ethical, legal, social, and security issues. Results: Each dimension is examined through recently emerging innovations, linking them directly to the future of healthcare, like the role of artificial intelligence, innovative digital health tools, the expansion of telemedicine, and the use of mobile health apps and wearable devices. The new approach of BMHI covers newly introduced clinical needs and approaches like patient-centric, remote monitoring, and precision medicine clinical approaches. Conclusions: These insights offer clear recommendations for improving education and developing experts to advance future innovations. Notably, this narrative review presents a body of knowledge essential for a deep understanding of the BMHI field from a human-centric perspective and, as such, could serve as a reference point for prospective analysis and innovation development. [ABSTRACT FROM AUTHOR]

Background: Antibiotic resistant infections cause over 700,000 deaths worldwide annually. As antimicrobial stewardship (AMS) helps minimise the emergence of antibiotic resistance resulting from inappropriate use of antibiotics in healthcare, we developed ePAMS+ (ePrescribing-based Anti-Microbial Stewardship), an ePrescribing and Medicines Administration (EPMA) system decision-support tool complemented by educational, behavioural and organisational elements. Methods: We conducted a non-randomised before-and-after feasibility trial, implementing ePAMS+ in two English hospitals using the Cerner Millennium EPMA system. Wards of several specialties were included. Patient participants were blinded to whether ePAMS+ was in use; prescribers were not. A mixed-methods evaluation aimed to establish: acceptability and usability of ePAMS+ and trial processes; feasibility of ePAMS+ implementation and quantitative outcome recording; and a Fidelity Index measuring the extent to which ePAMS+ was delivered as intended. Longitudinal semi-structured interviews of doctors, nurses and pharmacists, alongside non-participant observations, gathered qualitative data; we extracted quantitative prescribing data from the EPMA system. Normal linear modelling of the defined daily dose (DDD) of antibiotic per admission quantified its variability, to inform sample size calculations for a future trial of ePAMS+ effectiveness. Results: The research took place during the SARS-CoV-2 pandemic, from April 2021 to November 2022. 60 qualitative interviews were conducted (33 before ePAMS+ implementation, 27 after). 1,958 admissions (1,358 before ePAMS+ implementation; 600 after) included 24,884 antibiotic orders. Qualitative interviews confirmed that some aspects of ePAMS+ , its implementation and training were acceptable, while other features (e.g. enabling combinations of antibiotics to be prescribed) required further development. ePAMS+ uptake was low (28 antibiotic review records from 600 admissions; 0.047 records per admission), preventing full development of a Fidelity Index. Normal linear modelling of antibiotic DDD per admission showed a residual variance of 1.086 (log-transformed scale). Unavailability of indication data prevented measurement of some outcomes (e.g. number of antibiotic courses per indication). Conclusions: This feasibility trial encountered unforeseen circumstances due to contextual factors and a global pandemic, highlighting the need for careful adaptation of complex intervention implementations to the local setting. We identified key refinements to ePAMS+ to support its wider adoption in clinical practice, requiring further piloting before a confirmatory effectiveness trial. Trial registration: ISRCTN Registry ISRCTN13429325, 24 March 2022. [ABSTRACT FROM AUTHOR]

People are becoming more reliant on social media networks to express their opinions about various topics and obtain health information. The study is intended to explore and analyse the sentiments of Indian people related to Covid-19 vaccines as well as to visualise the top most frequently occurring terms individuals have used to communicate their ideas on Twitter about Covid-19 vaccines in India. The Tweet Archiver was used to retrieve the Tweets against 'Covid19vaccine' and 'Coronavirusvaccine' hashtags for the period of 2 months 18 days (4 January 2021–22 March 2021). After collecting data, the Orange software and VOSviewer were used for further analysis. The Tweets were posted across the country, with an immense contribution from Maharashtra (223, 15.58%), followed by Delhi (220, 15.37%) and Tamil Nadu (73, 5.10%). The majority (639, 44.65%) of the Tweets reflect positive sentiments, followed by neutral (521, 38.50%) and negative (241, 16.84%) sentiments, respectively. This signifies that most Twitter users have a favourable opinion towards Covid vaccines in India. Based on the relevance score of the words, the words 'Delhi heart', 'Lung institute', 'Gift', 'Unite2fightcorona', and 'Covid-19 Vaccine' are the leading words appearing in Tweets. The study illustrates the sentiments of the Indian people towards 'Covid-19 vaccines', gains some insights into overall public communication about the topic and complements the existing literature. It can assist health policymakers and administrators in better understanding the polarity (positive, negative, and neutral) of Tweets about Covid-19 vaccines on Twitter to raise public awareness about health concerns and misinformation about the vaccine. [ABSTRACT FROM AUTHOR]

This article centers around the development and analysis of machine learning (ML) and deep learning models aimed at enhancing diabetes diagnosis. In the swiftly evolving landscape of data technologies, it becomes crucial to explore the applications of these methods for accurate predictions and improved medical decision-making. Our research encompasses diverse datasets, leveraging state-of-the-art algorithms and technologies for model training and testing. The primary emphasis lies in evaluating the accuracy, sensitivity, and specificity of models within the realm of diabetes diagnosis. The study results reveal significant advancements in disease prediction, underscoring the potential of ML and deep learning in medical applications. This work introduces fresh perspectives on the utilization of computational methods in healthcare and serves as a foundation for prospective research in this domain. [ABSTRACT FROM AUTHOR]

Objective To allow health professionals to monitor and anticipate demands for emergency care in the Île-de-France region of France. Materials and Methods Data from emergency departments and emergency medical services are automatically processed on a daily basis and visualized through an interactive online dashboard. Forecasting methods are used to provide 7 days predictions. Results The dashboard displays data at regional and departmental levels or for 5 different age categories. It features summary statistics, historical values, predictions, comparisons to previous years, and monitoring of common reasons for care and outcomes. Discussion A large number of health professionals have already requested access to the dashboard (n = 606). Although the quality of data transmitted may vary slightly, the dashboard has already helped improve health situational awareness and anticipation. Conclusions The high access demand to the dashboard demonstrates the operational usefulness of real-time visualization of multisource data coupled with advanced analytics. [ABSTRACT FROM AUTHOR]

Background: Hospitalizations for exacerbations of congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD) and diabetic ketoacidosis (DKA) are costly in the United States. The purpose of this study was to predict in-hospital charges for each condition using machine learning (ML) models. Results: We conducted a retrospective cohort study on national discharge records of hospitalized adult patients from January 1st, 2016, to December 31st, 2019. We constructed six ML models (linear regression, ridge regression, support vector machine, random forest, gradient boosting and extreme gradient boosting) to predict total in-hospital cost for admission for each condition. Our models had good predictive performance, with testing R-squared values of 0.701-0.750 (mean of 0.713) for CHF; 0.694-0.724 (mean 0.709) for COPD; and 0.615-0.729 (mean 0.694) for DKA. We identified important key features driving costs, including patient age, length of stay, number of procedures, and elective/nonelective admission. Conclusions: ML methods may be used to accurately predict costs and identify drivers of high cost for COPD exacerbations, CHF exacerbations and DKA. Overall, our findings may inform future studies that seek to decrease the underlying high patient costs for these conditions. [ABSTRACT FROM AUTHOR]

PURPOSE We undertook a trial to test the efficacy of a technology-assisted health coaching intervention for weight management, called Goals for Eating and Moving (GEM), within primary care. METHODS This cluster-randomized controlled trial enrolled 19 primary care teams with 63 clinicians; 9 teams were randomized to GEM and 10 to enhanced usual care (EUC). The GEM intervention included 1 in-person and up to 12 telephone-delivered coaching sessions. Coaches supported goal setting and engagement with weight management programs, facilitated by a software tool. Patients in the EUC arm received educational handouts. We enrolled patients who spoke English or Spanish, were aged 18 to 69 years, and either were overweight (body mass index 25-29 kg/m²) with a weight-related comorbidity or had obesity (body mass index ≥30 kg/m²). The primary outcome (weight change at 12 months) and exploratory outcomes (eg, program attendance, diet, physical activity) were analyzed according to intention to treat. RESULTS We enrolled 489 patients (220 in the GEM arm, 269 in the EUC arm). Their mean (SD) age was 49.8 (12.1) years; 44% were male, 41% Hispanic, and 44% non-Hispanic Black. At 12 months, the mean adjusted weight change (standard error) was −1.4 (0.8) kg in the GEM arm vs −0.8 (1.6) kg in the EUC arm, a nonsignificant difference (P = .48). There were no statistically significant differences in secondary outcomes. Exploratory analyses showed that the GEM arm had a greater change than the EUC arm in mean number of weekly minutes of moderate to vigorous physical activity other than walking, a finding that may warrant further exploration. CONCLUSIONS The GEM intervention did not achieve clinically important weight loss in primary care. Although this was a negative study possibly affected by health system resource limitations and disruptions, its findings can guide the development of similar interventions. Future studies could explore the efficacy of higher-intensity interventions and interventions that include medication and bariatric surgery options, in addition to lifestyle modification. [ABSTRACT FROM AUTHOR]

Generative artificial intelligence (GAI) is rapidly transforming the healthcare landscape, offering innovative solutions in areas such as medical imaging, drug discovery, and clinical decision support. This comprehensive review examines the current role of GAI in healthcare, its potential benefits, drawbacks, challenges, and future research directions. By synthesizing recent literature and expert perspectives, this review provides a critical analysis of GAI's impact on healthcare delivery, patient outcomes, and ethical considerations. While GAI shows promise in enhancing diagnostic accuracy, accelerating drug development, and improving healthcare efficiency, it also faces significant challenges related to data privacy, regulatory compliance, and ethical implementation. This review aims to inform healthcare professionals, researchers, and policymakers about the current state and future potential of GAI in healthcare, emphasizing the need for responsible development and deployment of these technologies. [ABSTRACT FROM AUTHOR]

Objective This study explores the perspectives of Australian community pharmacists regarding digital health interventions, examining adoption rates, advantages, and barriers. Methods A national voluntary online survey was conducted with Australian community pharmacists from September 2022 to June 2023. Results Of the 120 responses received, 118 were analysed. The main benefits identified included improved access to health records and patient care quality while major concerns included technical issues and data security. Suggestions for increased digital health adoption included digital health education and regulation. Conclusions Australian community pharmacists play a crucial role in adopting digital health yet face significant challenges. Despite the potential of telehealth, community pharmacists have not widely embraced its adoption in their practice. The digital healthcare transformation necessitates collaborative efforts and strict guideline adherence for effective integration. [ABSTRACT FROM AUTHOR]

Various hospitals have adopted digital technologies in the healthcare sector for various healthcare-related applications. Due to the effect of the Covid-19 pandemic, digital transformation has taken place in many domains, especially in the healthcare domain; it has streamlined various healthcare activities. With the advancement in technology concept of telemedicine evolved over the years and led to personalized healthcare and drug discovery. The use of machine learning (ML) technique in healthcare enables healthcare professionals to make a more accurate and early diagnosis. Training these ML models requires a massive amount of data, including patients' personal data, that need to be protected from unethical use. Sharing these data to train ML models may violate data privacy. A distributed ML paradigm called federated learning (FL) has allowed different medical research institutions, hospitals, and healthcare devices to train ML models without sharing raw data. This survey paper overviews existing research work on FL-related use cases and applications. This paper also discusses the state-of-the-art tools and techniques available for FL research, current shortcomings, and future challenges in using FL in healthcare. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic continues to constitute a public health emergency of international importance, although the state of emergency declaration has indeed been terminated worldwide, many people continue to be infected and present different symptoms associated with the illness. Undoubtedly, solutions based on divergent technologies such as machine learning have made great contributions to the understanding, identification, and treatment of the disease. Due to the sudden appearance of this virus, many works have been carried out by the scientific community to support the detection and treatment processes, which has generated numerous publications, making it difficult to identify the status of current research and future contributions that can continue to be generated around this problem that is still valid among us. To address this problem, this article shows the result of a scientometric analysis, which allows the identification of the various contributions that have been generated from the line of automatic learning for the monitoring and treatment of symptoms associated with this pathology. The methodology for the development of this analysis was carried out through the implementation of two phases: in the first phase, a scientometric analysis was carried out, where the countries, authors, and magazines with the greatest production associated with this subject can be identified, later in the second phase, the contributions based on the use of the Tree of Knowledge metaphor are identified. The main concepts identified in this review are related to symptoms, implemented algorithms, and the impact of applications. These results provide relevant information for researchers in the field in the search for new solutions or the application of existing ones for the treatment of still-existing symptoms of COVID-19. [ABSTRACT FROM AUTHOR]

This study provides an overview of trends and evolution in International Organization for Standardization (ISO) implementation in healthcare over the past three decades, useful for researchers, practitioners, and policymakers in the sector. As an additional contribution, we propose the NU-index, which allows the evaluation of authors' scientific output in a comprehensive way that will be valuable for researchers, institutions, and funding agencies seeking to assess researcher performance more accurately and understandably. A bibliometric analysis of 476 scientific articles from the Scopus Database was conducted, examining the scientific output, key authors, high-impact journals, and frequent keywords using VOSviewer, Bibliometrix library, and statistical analysis. Results reveal a significant increase in publications on ISO standards in healthcare since 2009, particularly in areas such as telemedicine, artificial intelligence, and information security. The emergence of ISO 11073 (health informatics) and ISO 13606 (electronic health records) highlights a growing trend towards information and communication technologies. Despite reported implementation barriers, such as lack of top management commitment and associated costs, adoption of these standards is increasing due to the demand for high-quality healthcare services and the need to comply with regulatory requirements. [ABSTRACT FROM AUTHOR]

As Internet-based technology spreads to most areas of life, it becomes a challenge to grasp opportunities arising from enormous amounts of data being generated from various sources such as smart homes, smart cities, health care systems and industries. Efficient utilization of these data can enable us to improve many human practices, including those connected to health care. In the present study, we focus on the health care sector, as it consists of large-scale organizations that rely on the processing of big data and complex processing of information. Due to the dynamic nature and complexity of this domain, it is essential to develop sophisticated technologies for the efficient processing of vast amounts of information. There is, for example, a need for interactive tools that can visualise actual care processes being executed in the hospital. A tool visualising real-time data could give a dynamic view of the processes, with accurate quantitative information, which can be used to improve the quality and efficiency of health care provision. These tools should be built on the requirements of practitioners needs and requirements, to ensure their relevance and practical utility. In this paper, we present a user-driven design process for developing therapy data visualisation components of guided Internet-based cognitive behaviour therapy (iCBT) and their evaluation. In order to ensure the reusability of the visual components, we propose to utilise a model-based approach which allows data analysts to adapt domain models by means of model transformation and transform them into visualization. [ABSTRACT FROM AUTHOR]

Background Artificial intelligence (AI) and large language models (LLMs) can play a critical role in emergency room operations by augmenting decision-making about patient admission. However, there are no studies for LLMs using real-world data and scenarios, in comparison to and being informed by traditional supervised machine learning (ML) models. We evaluated the performance of GPT-4 for predicting patient admissions from emergency department (ED) visits. We compared performance to traditional ML models both naively and when informed by few-shot examples and/or numerical probabilities. Methods We conducted a retrospective study using electronic health records across 7 NYC hospitals. We trained Bio-Clinical-BERT and XGBoost (XGB) models on unstructured and structured data, respectively, and created an ensemble model reflecting ML performance. We then assessed GPT-4 capabilities in many scenarios: through Zero-shot, Few-shot with and without retrieval-augmented generation (RAG), and with and without ML numerical probabilities. Results The Ensemble ML model achieved an area under the receiver operating characteristic curve (AUC) of 0.88, an area under the precision-recall curve (AUPRC) of 0.72 and an accuracy of 82.9%. The naïve GPT-4's performance (0.79 AUC, 0.48 AUPRC, and 77.5% accuracy) showed substantial improvement when given limited, relevant data to learn from (ie, RAG) and underlying ML probabilities (0.87 AUC, 0.71 AUPRC, and 83.1% accuracy). Interestingly, RAG alone boosted performance to near peak levels (0.82 AUC, 0.56 AUPRC, and 81.3% accuracy). Conclusions The naïve LLM had limited performance but showed significant improvement in predicting ED admissions when supplemented with real-world examples to learn from, particularly through RAG, and/or numerical probabilities from traditional ML models. Its peak performance, although slightly lower than the pure ML model, is noteworthy given its potential for providing reasoning behind predictions. Further refinement of LLMs with real-world data is necessary for successful integration as decision-support tools in care settings. [ABSTRACT FROM AUTHOR]

Abstract Background Antibiotic resistant infections cause over 700,000 deaths worldwide annually. As antimicrobial stewardship (AMS) helps minimise the emergence of antibiotic resistance resulting from inappropriate use of antibiotics in healthcare, we developed ePAMS+ (ePrescribing-based Anti-Microbial Stewardship), an ePrescribing and Medicines Administration (EPMA) system decision-support tool complemented by educational, behavioural and organisational elements. Methods We conducted a non-randomised before-and-after feasibility trial, implementing ePAMS+ in two English hospitals using the Cerner Millennium EPMA system. Wards of several specialties were included. Patient participants were blinded to whether ePAMS+ was in use; prescribers were not. A mixed-methods evaluation aimed to establish: acceptability and usability of ePAMS+ and trial processes; feasibility of ePAMS+ implementation and quantitative outcome recording; and a Fidelity Index measuring the extent to which ePAMS+ was delivered as intended. Longitudinal semi-structured interviews of doctors, nurses and pharmacists, alongside non-participant observations, gathered qualitative data; we extracted quantitative prescribing data from the EPMA system. Normal linear modelling of the defined daily dose (DDD) of antibiotic per admission quantified its variability, to inform sample size calculations for a future trial of ePAMS+ effectiveness. Results The research took place during the SARS-CoV-2 pandemic, from April 2021 to November 2022. 60 qualitative interviews were conducted (33 before ePAMS+ implementation, 27 after). 1,958 admissions (1,358 before ePAMS+ implementation; 600 after) included 24,884 antibiotic orders. Qualitative interviews confirmed that some aspects of ePAMS+ , its implementation and training were acceptable, while other features (e.g. enabling combinations of antibiotics to be prescribed) required further development. ePAMS+ uptake was low (28 antibiotic review records from 600 admissions; 0.047 records per admission), preventing full development of a Fidelity Index. Normal linear modelling of antibiotic DDD per admission showed a residual variance of 1.086 (log-transformed scale). Unavailability of indication data prevented measurement of some outcomes (e.g. number of antibiotic courses per indication). Conclusions This feasibility trial encountered unforeseen circumstances due to contextual factors and a global pandemic, highlighting the need for careful adaptation of complex intervention implementations to the local setting. We identified key refinements to ePAMS+ to support its wider adoption in clinical practice, requiring further piloting before a confirmatory effectiveness trial. Trial registration ISRCTN Registry ISRCTN13429325, 24 March 2022.

Abstract Machine learning (ML) has achieved substantial success in performing healthcare tasks in which the configuration of every part of the ML pipeline relies heavily on technical knowledge. To help professionals with borderline expertise to better use ML techniques, Automated ML (AutoML) has emerged as a prospective solution. However, most models generated by AutoML are black boxes that are challenging to comprehend and deploy in healthcare settings. We conducted a systematic review to examine AutoML with interpretation systems for healthcare. We searched four databases (MEDLINE, EMBASE, Web of Science, and Scopus) complemented with seven prestigious ML conferences (AAAI, ACL, ICLR, ICML, IJCAI, KDD, and NeurIPS) that reported AutoML with interpretation for healthcare before September 1, 2023. We included 118 articles related to AutoML with interpretation in healthcare. First, we illustrated AutoML techniques used in the included publications, including automated data preparation, automated feature engineering, and automated model development, accompanied by a real‐world case study to demonstrate the advantages of AutoML over classic ML. Then, we summarized interpretation methods: feature interaction and importance, data dimensionality reduction, intrinsically interpretable models, and knowledge distillation and rule extraction. Finally, we detailed how AutoML with interpretation has been used for six major data types: image, free text, tabular data, signal, genomic sequences, and multi‐modality. To some extent, AutoML with interpretation provides effortless development and improves users' trust in ML in healthcare settings. In future studies, researchers should explore automated data preparation, seamless integration of automation and interpretation, compatibility with multi‐modality, and utilization of foundation models.

Abstract Background Hospitalizations for exacerbations of congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD) and diabetic ketoacidosis (DKA) are costly in the United States. The purpose of this study was to predict in-hospital charges for each condition using machine learning (ML) models. Results We conducted a retrospective cohort study on national discharge records of hospitalized adult patients from January 1st, 2016, to December 31st, 2019. We constructed six ML models (linear regression, ridge regression, support vector machine, random forest, gradient boosting and extreme gradient boosting) to predict total in-hospital cost for admission for each condition. Our models had good predictive performance, with testing R-squared values of 0.701-0.750 (mean of 0.713) for CHF; 0.694-0.724 (mean 0.709) for COPD; and 0.615-0.729 (mean 0.694) for DKA. We identified important key features driving costs, including patient age, length of stay, number of procedures, and elective/nonelective admission. Conclusions ML methods may be used to accurately predict costs and identify drivers of high cost for COPD exacerbations, CHF exacerbations and DKA. Overall, our findings may inform future studies that seek to decrease the underlying high patient costs for these conditions.

Abstract Background Despite the growing adoption of digital health tools as a means to support mental health, many individuals remain unaware of the variety of mental health resources available to them through this format. To address this knowledge gap, this study advanced the design, development, and implementation of a text-based service called SaskWell to raise awareness of evidence based mental health resources and create more immediate connections to these tools. The two primary objectives of the study were to assess and evaluate the adoption of SaskWell by focusing on user acceptance, satisfaction, and perceived benefit, and to identify factors which contributed to user engagement with the SaskWell text-based service. Both quantitative and qualitative data contributed to the final study results. Results This study utilized a co-designed text-messaging service to provide residents of Saskatchewan an important connection to digital mental health and wellness resources during the height of the COVID-19 pandemic. Using the RE-AIM framework as an implementation guide, four distinct cycles of SaskWell were delivered with modifications to the service in each subsequent cycle based on user engagement, feedback, and the direction of a community advisory group. Quantitative data was collected through user engagement text message response data, along with enrollment and exit surveys, while semi-structured interviews served as the primary means of qualitative data collection. In addition to the quantitative user data, these user interviews resulted in themes exploring motivation to sign-up for the service, perceptions of texting as a mechanism to deliver mental health resources, the impact of SaskWell on mental health and well-being, and beliefs on the future potential of text-based mental health supports. Conclusions Both the user engagement survey and the qualitative data supported the worth of ongoing efforts to refine and extend the use of text messaging as a means to engage citizens around the awareness and use of digital mental health and wellness resources. As the pandemic has receded into the background in many peoples’ daily lives, for healthcare providers, and others who continue to be impacted more heavily by the persistent challenges of this global event, this type of service may continue to be timely.

Abstract Background Governments worldwide are facing growing pressure to increase transparency, as citizens demand greater insight into decision-making processes and public spending. An example is the release of open healthcare data to researchers, as healthcare is one of the top economic sectors. Significant information systems development and computational experimentation are required to extract meaning and value from these datasets. We use a large open health dataset provided by the New York State Statewide Planning and Research Cooperative System (SPARCS) containing 2.3 million de-identified patient records. One of the fields in these records is a patient’s length of stay (LoS) in a hospital, which is crucial in estimating healthcare costs and planning hospital capacity for future needs. Hence it would be very beneficial for hospitals to be able to predict the LoS early. The area of machine learning offers a potential solution, which is the focus of the current paper. Methods We investigated multiple machine learning techniques including feature engineering, regression, and classification trees to predict the length of stay (LoS) of all the hospital procedures currently available in the dataset. Whereas many researchers focus on LoS prediction for a specific disease, a unique feature of our model is its ability to simultaneously handle 285 diagnosis codes from the Clinical Classification System (CCS). We focused on the interpretability and explainability of input features and the resulting models. We developed separate models for newborns and non-newborns. Results The study yields promising results, demonstrating the effectiveness of machine learning in predicting LoS. The best R2 scores achieved are noteworthy: 0.82 for newborns using linear regression and 0.43 for non-newborns using catboost regression. Focusing on cardiovascular disease refines the predictive capability, achieving an improved R2 score of 0.62. The models not only demonstrate high performance but also provide understandable insights. For instance, birth-weight is employed for predicting LoS in newborns, while diagnostic-related group classification proves valuable for non-newborns. Conclusion Our study showcases the practical utility of machine learning models in predicting LoS during patient admittance. The emphasis on interpretability ensures that the models can be easily comprehended and replicated by other researchers. Healthcare stakeholders, including providers, administrators, and patients, stand to benefit significantly. The findings offer valuable insights for cost estimation and capacity planning, contributing to the overall enhancement of healthcare management and delivery.

Abstract Background As U.S. legislators are urged to combat ghost networks in behavioral health and address the provider data quality issue, it becomes important to better characterize the variation in data quality of provider directories to understand root causes and devise solutions. Therefore, this manuscript examines consistency of address, phone number, and specialty information for physician entries from 5 national health plan provider directories by insurer, physician specialty, and state. Methods We included all physicians in the Medicare Provider Enrollment, Chain, and Ownership System (PECOS) found in ≥ 2 health insurer physician directories across 5 large national U.S. health insurers. We examined variation in consistency of address, phone number, and specialty information among physicians by insurer, physician specialty, and state. Results Of 634,914 unique physicians in the PECOS database, 449,282 were found in ≥ 2 directories and included in our sample. Across insurers, consistency of address information varied from 16.5 to 27.9%, consistency of phone number information varied from 16.0 to 27.4%, and consistency of specialty information varied from 64.2 to 68.0%. General practice, family medicine, plastic surgery, and dermatology physicians had the highest consistency of addresses (37-42%) and phone numbers (37-43%), whereas anesthesiology, nuclear medicine, radiology, and emergency medicine had the lowest consistency of addresses (11-21%) and phone numbers (9-14%) across health insurer directories. There was marked variation in consistency of address, phone number, and specialty information by state. Conclusions In evaluating a large national sample of U.S. physicians, we found minimal variation in provider directory consistency by insurer, suggesting that this is a systemic problem that insurers have not solved, and considerable variation by physician specialty with higher quality data among more patient-facing specialties, suggesting that physicians may respond to incentives to improve data quality. These data highlight the importance of novel policy solutions that leverage technology targeting data quality to centralize provider directories so as not to not reinforce existing data quality issues or policy solutions to create national and state-level standards that target both insurers and physician groups to maximize quality of provider information.

Background: As healthcare increasingly integrates digital technologies, it is crucial to ensure that medical professionals possess robust digital competencies to maximize the benefits of these technologies. Mastering fundamental digital skills is essential before engaging with more complex digital health technologies. This study aimed to assess the general digital competencies of doctors in Chișinău, Moldova, and to identify specific areas needing improvement, thereby providing a foundation for tailored educational programs. Materials and Methods: In April 2024, data were collected using the My DigiSkills tool, a self-assessment online questionnaire developed under the European Commission's DigCompSAT project by ALL DIGITAL. This cross-sectional study involved resident doctors and specialists and from various medical institutions in Chișinău, who self-assessed their digital competence levels across five areas: Information and Data Literacy, Communication and Collaboration, Digital Content Creation, Safety, and Problem Solving. Upon completing the questionnaire, participants received their results via email and subsequently forwarded the results to the researchers. Results: The study revealed that over 50% of doctors in Chișinău demonstrated advanced skills in information and data literacy and communication. However, significant deficiencies were found in digital safety, with only 19% showing advanced skills in this area. Younger doctors generally exhibited higher digital competence levels. The results highlight the urgent need for customized training initiatives to address these gaps and enhance digital competencies among medical professionals. Conclusions: The study underscores the necessity for tailored educational programs to improve digital competencies, particularly in digital safety, because data privacy and security are paramount in the medical context.

Abstract Background Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible due to privacy concerns and parties are unable to engage in centrally coordinated joint computation. We study the feasibility of combining privacy preserving synthetic data sets in place of the original data for collaborative learning on real-world health data from the UK Biobank. Methods We perform an empirical evaluation based on an existing prospective cohort study from the literature. Multiple parties were simulated by splitting the UK Biobank cohort along assessment centers, for which we generate synthetic data using differentially private generative modelling techniques. We then apply the original study’s Poisson regression analysis on the combined synthetic data sets and evaluate the effects of 1) the size of local data set, 2) the number of participating parties, and 3) local shifts in distributions, on the obtained likelihood scores. Results We discover that parties engaging in the collaborative learning via shared synthetic data obtain more accurate estimates of the regression parameters compared to using only their local data. This finding extends to the difficult case of small heterogeneous data sets. Furthermore, the more parties participate, the larger and more consistent the improvements become up to a certain limit. Finally, we find that data sharing can especially help parties whose data contain underrepresented groups to perform better-adjusted analysis for said groups. Conclusions Based on our results we conclude that sharing of synthetic data is a viable method for enabling learning from sensitive data without violating privacy constraints even if individual data sets are small or do not represent the overall population well. Lack of access to distributed sensitive data is often a bottleneck in biomedical research, which our study shows can be alleviated with privacy-preserving collaborative learning methods.

Metaverse technology is an advanced form of virtual reality and augmented technologies. It merges the digital world with the real world, thus benefitting healthcare services. Medical informatics is promising in the metaverse. Despite the increasing adoption of the metaverse in commercial applications, a considerable research gap remains in the academic domain, which hinders the comprehensive delineation of research prospects for the metaverse in healthcare. This study employs text-mining methods to investigate the prevalence and trends of the metaverse in healthcare; in particular, more than 34,000 academic articles and news reports are analyzed. Subsequently, the topic prevalence, similarity, and correlation are measured using topic-modeling methods. Based on bibliometric analysis, this study proposes a theoretical framework from the perspectives of knowledge, socialization, digitization, and intelligence. This study provides insights into its application in healthcare via an extensive literature review. The key to promoting the metaverse in healthcare is to perform technological upgrades in computer science, telecommunications, healthcare services, and computational biology. Digitization, virtualization, and hyperconnectivity technologies are crucial in advancing healthcare systems. Realizing their full potential necessitates collective support and concerted effort toward the transformation of relevant service providers, the establishment of a digital economy value system, and the reshaping of social governance and health concepts. The results elucidate the current state of research and offer guidance for the advancement of the metaverse in healthcare.

Background: Venous thromboembolism (VTE) is a preventable medical condition which has substantial impact on patient morbidity, mortality, and disability. Unfortunately, adherence to the published best practices for VTE prevention, based on patient centered outcomes research (PCOR), is highly variable across U.S. hospitals, which represents a gap between current evidence and clinical practice leading to adverse patient outcomes. This gap is especially large in the case of traumatic brain injury (TBI), where reluctance to initiate VTE prevention due to concerns for potentially increasing the rates of intracranial bleeding drives poor rates of VTE prophylaxis. This is despite research which has shown early initiation of VTE prophylaxis to be safe in TBI without increased risk of delayed neurosurgical intervention or death. Clinical decision support (CDS) is an indispensable solution to close this practice gap; however, design and implementation barriers hinder CDS adoption and successful scaling across health systems. Clinical practice guidelines (CPGs) informed by PCOR evidence can be deployed using CDS systems to improve the evidence to practice gap. In the Scaling AcceptabLE cDs (SCALED) study, we will implement a VTE prevention CPG within an interoperable CDS system and evaluate both CPG effectiveness (improved clinical outcomes) and CDS implementation. Methods: The SCALED trial is a hybrid type 2 randomized stepped wedge effectiveness-implementation trial to scale the CDS across 4 heterogeneous healthcare systems. Trial outcomes will be assessed using the RE2-AIM planning and evaluation framework. Efforts will be made to ensure implementation consistency. Nonetheless, it is expected that CDS adoption will vary across each site. To assess these differences, we will evaluate implementation processes across trial sites using the Exploration, Preparation, Implementation, and Sustainment (EPIS) implementation framework (a determinant framework) using mixed-methods. Finally, it is critical that PCOR CPGs are maintained as evidence evolves. To date, an accepted process for evidence maintenance does not exist. We will pilot a "Living Guideline" process model for the VTE prevention CDS system. Discussion: The stepped wedge hybrid type 2 trial will provide evidence regarding the effectiveness of CDS based on the Berne-Norwood criteria for VTE prevention in patients with TBI. Additionally, it will provide evidence regarding a successful strategy to scale interoperable CDS systems across U.S. healthcare systems, advancing both the fields of implementation science and health informatics. Trial registration: Clinicaltrials.gov – NCT05628207. Prospectively registered 11/28/2022, https://classic.clinicaltrials.gov/ct2/show/NCT05628207. [ABSTRACT FROM AUTHOR]

It is since the beginning of the so-called 'digital revolution' in the 1950s that technological tools have been developed to simplify and optimise traditional, time-consuming, and laborious anamnestic collection for many physicians. In recent years, more and more sophisticated 'automated' anamnestic collection systems have been developed, to the extent that they can actually enter daily clinical practice. This article not only provides a historical overview of the evolution of such tools, but also explores the ethical and medico-legal implications of the transition from traditional to digital anamnesis, including the protection of data confidentiality, the preservation of the communicative effectiveness of the doctor–patient dialogue and the safety of care in patients with poor digital and health literacy. [ABSTRACT FROM AUTHOR]

Background: Despite the growing adoption of digital health tools as a means to support mental health, many individuals remain unaware of the variety of mental health resources available to them through this format. To address this knowledge gap, this study advanced the design, development, and implementation of a text-based service called SaskWell to raise awareness of evidence based mental health resources and create more immediate connections to these tools. The two primary objectives of the study were to assess and evaluate the adoption of SaskWell by focusing on user acceptance, satisfaction, and perceived benefit, and to identify factors which contributed to user engagement with the SaskWell text-based service. Both quantitative and qualitative data contributed to the final study results. Results: This study utilized a co-designed text-messaging service to provide residents of Saskatchewan an important connection to digital mental health and wellness resources during the height of the COVID-19 pandemic. Using the RE-AIM framework as an implementation guide, four distinct cycles of SaskWell were delivered with modifications to the service in each subsequent cycle based on user engagement, feedback, and the direction of a community advisory group. Quantitative data was collected through user engagement text message response data, along with enrollment and exit surveys, while semi-structured interviews served as the primary means of qualitative data collection. In addition to the quantitative user data, these user interviews resulted in themes exploring motivation to sign-up for the service, perceptions of texting as a mechanism to deliver mental health resources, the impact of SaskWell on mental health and well-being, and beliefs on the future potential of text-based mental health supports. Conclusions: Both the user engagement survey and the qualitative data supported the worth of ongoing efforts to refine and extend the use of text messaging as a means to engage citizens around the awareness and use of digital mental health and wellness resources. As the pandemic has receded into the background in many peoples' daily lives, for healthcare providers, and others who continue to be impacted more heavily by the persistent challenges of this global event, this type of service may continue to be timely. [ABSTRACT FROM AUTHOR]

Background: Depression is a significant mental health concern affecting the overall well-being of adolescents and young adults. Recently, the prevalence of depression has increased among young people. Nonetheless, there is little research delving into the longitudinal epidemiology of adolescent depression over time. Aims: To investigate the longitudinal epidemiology of depression among adolescents and young adults aged 10–24 years. Method: Our research focused on young people (aged 10–24 years) with depression, using data from the Global Burden of Diseases, Injuries, and Risk Factors Study 2019. We explored the age-standardised prevalence, incidence and disability-adjusted life-years (DALYs) of depression in different groups, including various regions, ages, genders and sociodemographic indices, from 1990 to 2019. Results: The prevalence, incidence and DALYs of depression in young people increased globally between 1990 and 2019. Regionally, higher-income regions like High-Income North America and Australasia recorded rising age-standardised prevalence and incidence rates, whereas low- or middle-income regions mostly saw reductions. Nationally, countries such as Greenland, the USA and Palestine reported the highest age-standardised prevalence and incidence rates in 2019, whereas Qatar witnessed the largest growth over time. The burden disproportionately affected females across age groups and world regions. The most prominent age effect on incidence and prevalence rates was in those aged 20–24 years. The depression burden showed an unfavourable trend in younger cohorts born after 1980, with females reporting a higher cohort risk than males. Conclusions: Between 1990 and 2019, the general pattern of depression among adolescents varied according to age, gender, time period and generational cohort, across regions and nations. [ABSTRACT FROM AUTHOR]

Depression significantly impacts the wellbeing of older Australians, posing considerable challenges to their overall quality of life. This study aimed to detect in-home movement patterns of participants that could be indicative of depressive states. Utilising data collected over a 12-month period via smart home ambient sensors, this feasibility study conducted a comparative analysis using machine learning techniques on features derived from motion sensors, sociodemographic variables, and the Geriatric Depression Scale. Three machine learning models, specifically Extreme Gradient Boost (XGBoost), Random Forest (RF), and Logistic Regression (LR), were implemented. Results showed that the performance of XGBoost was relatively higher compared to RF and LR, with an Area Under the Receiver Operating Characteristic Curve (AUROC) value of 0.67. Feature analysis indicated that bathroom and kitchen movements and the level of home care support were among the top influential features influencing depression assessment. This is consistent with clinical evidence on appetite, hygiene, and overall mobility changes during depression. These findings underscore the feasibility of leveraging in-home movement monitoring as an indicator of health risks among older adults. [ABSTRACT FROM AUTHOR]

Wearable sensors, among other informatics solutions, are readily accessible to enable noninvasive remote monitoring in healthcare. While providing a wealth of data, the wide variety of such sensing systems and the differing implementations of the same or similar sensors by different developers complicate comparisons of collected data. An online application as a platform technology that provides uniform methods for analysing balance data is presented as a case study. The development of balance problems is common in neurodegenerative conditions, leading to falls and a reduced quality of life. While balance can be assessed using, for example, perturbation tests, sensors offer a more quantitative and scalable way. Researchers can adjust the platform to integrate the sensors of their choice or upload data and then preprocess, featurise, analyse, and visualise them. This eases performing comparative analyses across the sensors and datasets through a reduction of heterogeneity and facilitates easy integration of machine learning and other advanced data analytics, thereby targeting personalising medical insights. [ABSTRACT FROM AUTHOR]

An urgent global imperative is to ensure health workforces have a solid digital health capability to deliver consumer-centred services now and into the future. To address a lack of formal recognition of health informatics knowledge and skills in Australia, the Certified Health Informatician Australasian (CHIA) was launched ten years ago. In that time, 3125 CHIA candidates registered to have their capabilities assessed using a core set of health informatics competencies. This paper presents the demographic profile of people undertaking the examination and trend data of the pass rate over the decade, and identifies possible factors that may lead to higher achievement. Certifications such as CHIA are critical in the professionalisation of digital health specialists and health informatics. [ABSTRACT FROM AUTHOR]

Background: Governments worldwide are facing growing pressure to increase transparency, as citizens demand greater insight into decision-making processes and public spending. An example is the release of open healthcare data to researchers, as healthcare is one of the top economic sectors. Significant information systems development and computational experimentation are required to extract meaning and value from these datasets. We use a large open health dataset provided by the New York State Statewide Planning and Research Cooperative System (SPARCS) containing 2.3 million de-identified patient records. One of the fields in these records is a patient's length of stay (LoS) in a hospital, which is crucial in estimating healthcare costs and planning hospital capacity for future needs. Hence it would be very beneficial for hospitals to be able to predict the LoS early. The area of machine learning offers a potential solution, which is the focus of the current paper. Methods: We investigated multiple machine learning techniques including feature engineering, regression, and classification trees to predict the length of stay (LoS) of all the hospital procedures currently available in the dataset. Whereas many researchers focus on LoS prediction for a specific disease, a unique feature of our model is its ability to simultaneously handle 285 diagnosis codes from the Clinical Classification System (CCS). We focused on the interpretability and explainability of input features and the resulting models. We developed separate models for newborns and non-newborns. Results: The study yields promising results, demonstrating the effectiveness of machine learning in predicting LoS. The best R2 scores achieved are noteworthy: 0.82 for newborns using linear regression and 0.43 for non-newborns using catboost regression. Focusing on cardiovascular disease refines the predictive capability, achieving an improved R2 score of 0.62. The models not only demonstrate high performance but also provide understandable insights. For instance, birth-weight is employed for predicting LoS in newborns, while diagnostic-related group classification proves valuable for non-newborns. Conclusion: Our study showcases the practical utility of machine learning models in predicting LoS during patient admittance. The emphasis on interpretability ensures that the models can be easily comprehended and replicated by other researchers. Healthcare stakeholders, including providers, administrators, and patients, stand to benefit significantly. The findings offer valuable insights for cost estimation and capacity planning, contributing to the overall enhancement of healthcare management and delivery. [ABSTRACT FROM AUTHOR]

Background: As U.S. legislators are urged to combat ghost networks in behavioral health and address the provider data quality issue, it becomes important to better characterize the variation in data quality of provider directories to understand root causes and devise solutions. Therefore, this manuscript examines consistency of address, phone number, and specialty information for physician entries from 5 national health plan provider directories by insurer, physician specialty, and state. Methods: We included all physicians in the Medicare Provider Enrollment, Chain, and Ownership System (PECOS) found in ≥ 2 health insurer physician directories across 5 large national U.S. health insurers. We examined variation in consistency of address, phone number, and specialty information among physicians by insurer, physician specialty, and state. Results: Of 634,914 unique physicians in the PECOS database, 449,282 were found in ≥ 2 directories and included in our sample. Across insurers, consistency of address information varied from 16.5 to 27.9%, consistency of phone number information varied from 16.0 to 27.4%, and consistency of specialty information varied from 64.2 to 68.0%. General practice, family medicine, plastic surgery, and dermatology physicians had the highest consistency of addresses (37-42%) and phone numbers (37-43%), whereas anesthesiology, nuclear medicine, radiology, and emergency medicine had the lowest consistency of addresses (11-21%) and phone numbers (9-14%) across health insurer directories. There was marked variation in consistency of address, phone number, and specialty information by state. Conclusions: In evaluating a large national sample of U.S. physicians, we found minimal variation in provider directory consistency by insurer, suggesting that this is a systemic problem that insurers have not solved, and considerable variation by physician specialty with higher quality data among more patient-facing specialties, suggesting that physicians may respond to incentives to improve data quality. These data highlight the importance of novel policy solutions that leverage technology targeting data quality to centralize provider directories so as not to not reinforce existing data quality issues or policy solutions to create national and state-level standards that target both insurers and physician groups to maximize quality of provider information. [ABSTRACT FROM AUTHOR]

Advancements in health informatics have significantly transformed the utilization of medical devices in nursing and hospital administration, enhancing both patient care and operational efficiency. With the integration of electronic health records (EHRs) and the Internet of Things (IoT), medical devices can now communicate real-time data directly to healthcare providers. This seamless exchange of information allows for prompt decision-making, better monitoring of patient vitals, and reduced chances of errors in medication administration. Furthermore, predictive analytics and machine learning algorithms analyze historical data to anticipate patient needs and optimize device usage, ultimately streamlining workflow in nursing practices and administrative processes. The implementation of advanced health informatics systems has also paved the way for innovative approaches to medical device management and compliance monitoring within healthcare institutions. Automated tracking systems ensure that devices are regularly maintained and compliant with safety standards, thereby enhancing patient safety. Additionally, mobile health applications allow nurses and hospital staff to access device data remotely, facilitating better coordination among team members. As a result, health informatics is not only improving clinical outcomes but also fostering a culture of accountability and continuous improvement in medical device utilization. [ABSTRACT FROM AUTHOR]

Objectives: We undertook a national analysis to characterise and identify risk factors for acute respiratory infections (ARIs) resulting in hospitalisation during the winter period in Scotland. Design: A population-based retrospective cohort analysis. Setting: Scotland. Participants: The study involved 5.4 million residents in Scotland. Main outcome measures: Cox proportional hazard models were used to estimate adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) for the association between risk factors and ARI hospitalisation. Results: Between 1 September 2022 and 31 January 2023, there were 22,284 (10.9% of 203,549 with any emergency hospitalisation) ARI hospitalisations (1759 in children and 20,525 in adults) in Scotland. Compared with the reference group of children aged 6–17 years, the risk of ARI hospitalisation was higher in children aged 3–5 years (aHR = 4.55; 95% CI: 4.11–5.04). Compared with those aged 25–29 years, the risk of ARI hospitalisation was highest among the oldest adults aged ≥80 years (aHR = 7.86; 95% CI: 7.06–8.76). Adults from more deprived areas (most deprived vs. least deprived, aHR = 1.64; 95% CI: 1.57–1.72), with existing health conditions (≥5 vs. 0 health conditions, aHR = 4.84; 95% CI: 4.53–5.18) or with history of all-cause emergency admissions (≥6 vs. 0 previous emergency admissions, aHR = 7.53; 95% CI: 5.48–10.35) were at a higher risk of ARI hospitalisations. The risk increased by the number of existing health conditions and previous emergency admission. Similar associations were seen in children. Conclusions: Younger children, older adults, those from more deprived backgrounds and individuals with greater numbers of pre-existing conditions and previous emergency admission were at increased risk for winter hospitalisations for ARI. [ABSTRACT FROM AUTHOR]

Purpose: This study aims to comprehensively assess the field of health informatics and its subdomains, addressing a gap in the literature. The primary objective is to provide insights into the integration of expertise from various disciplines and explore the impact of emerging technologies, such as artificial intelligence, machine learning, robotic process automation, and virtual reality on healthcare processes. The research question queries the current status of health informatics and how the latest technological developments affect health informatics and its subfields. Method: Conducted through an extensive literature review, this research explores medical informatics, nursing informatics, pharmacy informatics, dentistry informatics, biomedical informatics, bioinformatics, public health informatics, clinical informatics, and primary care informatics. Results: Findings highlight a comprehensive understanding of health informatics and its subdomains, emphasizing the interdisciplinary integration of expertise. The study also reveals the significant impact of new and hype technologies on various health informatics domains. Conclusions: Filling a literature gap, this study provides valuable insights into the current state of health informatics. It underscores the interdisciplinary nature of the field and emphasizes the profound influence of emerging technologies on the evolving landscape of health informatics. The study thoroughly examines nine specific informatics fields within health informatics, revealing that recent years have seen a collective influence of artificial intelligence, deep learning, and machine learning across these domainsThe findings strongly suggest that courses on these emerging current technologies be integrated into undergraduate curricula within health informatics education. [ABSTRACT FROM AUTHOR]

Objectives: To investigate long COVID (LC) symptoms self-reported via a digital application. Explore associations between various demographic factors and intensity of LC symptoms. Design: A retrospective case series study. We analysed self-reported symptoms from 1008 individuals with LC between November 30, 2020, and March 23, 2022. Setting: England and Wales. Participants: Individuals with LC using the healthcare application in 31 post-COVID-19 clinics and self-reporting LC symptoms. Main outcome measures: Highest reported LC symptoms, associations with demographic factors and intensity of symptoms. Results: 109 symptom categories were identified, with pain (26.5%), neuropsychological issues (18.4%), fatigue (14.3%) and dyspnoea (7.4%) the most prevalent. The intensity of reported symptoms increased by 3.3% per month since registration. Age groups 68–77 and 78–87 experienced higher symptom intensity (32.8% and 86% higher, respectively) compared to the 18–27 age group. Women reported 9.2% more intense symptoms than men, and non-white individuals with LC reported 23.5% more intense symptoms than white individuals with LC. Higher education levels (national vocational qualification (NVQ) 3 to NVQ 5) were associated with less symptom intensity (27.7%, 62.8% and 44.7% less, respectively) compared to the least educated (NVQ 1–2). People in less deprived areas had less intense symptoms than those in the most deprived area. No significant association was found between index of multiple deprivation (IMD) decile and number of symptoms. Conclusion: Treatment plans must prioritise addressing prevalent LC symptoms; we recommend sustained support for LC clinics. Demographic factors significantly influence symptom severity, underlining the need for targeted interventions. These findings can inform healthcare policies to better manage LC. [ABSTRACT FROM AUTHOR]

Background: This study has two primary objectives. Firstly, it aims to measure the time savings achieved through the digitization of paper forms filled out by nurses in the inpatient care process. Secondly, it seeks to reveal the financial savings resulting from reduced paper consumption due to the digitalization. The Health Information Management System Society (HIMSS)--Electronic Medical Record Adaption Model (EMRAM), which makes stage-based (0--7) evaluations, serves as a tool to measure the rate of technology utilization in public hospitals in Turkey. The study is based on the HIMSS EMRAM criteria for 2018. Bahçelievler State Hospital, a public hospital in Turkey, was chosen as the research facility. In 2017, it was accredited as Stage 6 with HIMSS EMRAM. However, not all its wards have been digitalized. Initially, pilot selected wards were digitized. Therefore, digital and non-digital wards serve together. In this context, 4 wards were randomly selected and time, paper and toner savings before and after digitalization were measured. Method: A table was created in Microsoft Excel,listing the forms used by nurses in inpatient care and the time required to fill them out.The time spent for filling paper-based forms and digital-based forms was measured in randomly selected wards. Result: The analysis showed that digital forms saved more time, paper and toner. For example, filling out the patient history form took 45 min when using paper, compared to 12 min in digital environment. Approximately 27% time savings are achieved only for the patient history form. The total time savings delivered by digitalization for 1,153 inpatients during the year were found as 117 care days, and the savings on total paper consumption was 41.289 pages. For 1,153 inpatients throughout the year, the total time savings from digitalization was 117 care days and the total paper consumption savings was 41,289 pages. In addition, in 4 wards with a total bed capacity of 25, annual paper savings of $1,705.86 and toner savings of $283,736 were achieved. Discussion: This study reveals the benefits of digitalisation in hospitals for nurses. It saves the time that nurses allocate for filling out paper forms with digitalised forms. Thus, it is a good practice example in terms of using the time allocated for form filling for patient care.When we extend this study to Turkey in general, it can be considered that the time savings achieved by nurses by digitizing inpatient forms varies between 10.8% and 13%. The number of nurses working in public hospitals in Turkey is approximately 160,000. Assuming that 60% of the nurses work in the inpatient ward, it is understood that the annual savings achieved by digitizing the forms corresponds to a range of 398--559 nursing hours. [ABSTRACT FROM AUTHOR]

Background: Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible due to privacy concerns and parties are unable to engage in centrally coordinated joint computation. We study the feasibility of combining privacy preserving synthetic data sets in place of the original data for collaborative learning on real-world health data from the UK Biobank. Methods: We perform an empirical evaluation based on an existing prospective cohort study from the literature. Multiple parties were simulated by splitting the UK Biobank cohort along assessment centers, for which we generate synthetic data using differentially private generative modelling techniques. We then apply the original study's Poisson regression analysis on the combined synthetic data sets and evaluate the effects of 1) the size of local data set, 2) the number of participating parties, and 3) local shifts in distributions, on the obtained likelihood scores. Results: We discover that parties engaging in the collaborative learning via shared synthetic data obtain more accurate estimates of the regression parameters compared to using only their local data. This finding extends to the difficult case of small heterogeneous data sets. Furthermore, the more parties participate, the larger and more consistent the improvements become up to a certain limit. Finally, we find that data sharing can especially help parties whose data contain underrepresented groups to perform better-adjusted analysis for said groups. Conclusions: Based on our results we conclude that sharing of synthetic data is a viable method for enabling learning from sensitive data without violating privacy constraints even if individual data sets are small or do not represent the overall population well. Lack of access to distributed sensitive data is often a bottleneck in biomedical research, which our study shows can be alleviated with privacy-preserving collaborative learning methods. [ABSTRACT FROM AUTHOR]

Background: Internet-based interventions produce comparable effectiveness rates as face-to-face therapy in treating depression. Still, more than half of patients do not respond to treatment. Machine learning (ML) methods could help to overcome these low response rates by predicting therapy outcomes on an individual level and tailoring treatment accordingly. Few studies implemented ML algorithms in internet-based depression treatment using baseline self-report data, but differing results hinder inferences on clinical practicability. This work compares algorithms using features gathered at baseline or early in treatment in their capability to predict non-response to a 6-week online program targeting depression. Methods: Our training and test sample encompassed 1270 and 318 individuals, respectively. We trained random forest algorithms on self-report and process features gathered at baseline and after 2 weeks of treatment. Non-responders were defined as participants not fulfilling the criteria for reliable and clinically significant change on PHQ-9 post-treatment. Our benchmark models were logistic regressions trained on baseline PHQ-9 sum or PHQ-9 early change, using 100 iterations of randomly sampled 80/20 train-test-splits. Results: Best performances were reached by our models involving early treatment characteristics (recall: 0.75–0.76; AUC: 0.71–0.77). Therapeutic alliance and early symptom change constituted the most important predictors. Models trained on baseline data were not significantly better than our benchmark. Conclusions: Fair accuracies were only attainable by involving information from early treatment stages. In-treatment adaptation, instead of a priori selection, might constitute a more feasible approach for improving response when relying on easily accessible self-report features. Implementation trials are needed to determine clinical usefulness. [ABSTRACT FROM AUTHOR]

A significant increase in the demand for quality healthcare has resulted from people becoming more aware of health issues. With blockchain, healthcare providers may safely share patient information electronically, which is especially important given the sensitive nature of the data contained inside them. However, flaws in the current blockchain design have surfaced since the dawn of quantum computing systems. The study proposes a novel quantum-inspired blockchain system (Qchain) and constructs a unique entangled quantum medical record (EQMR) system with an emphasis on privacy and security. This Qchain relies on entangled states to connect its blocks. The automated production of the chronology indicator reduces storage capacity requirements by connecting entangled BloQ (blocks with quantum properties) to controlled activities. We use one qubit to store the hash value of each block. A lot of information regarding the quantum internet is included in the protocol for the entangled quantum medical record (EQMR). The EQMR can be accessed in Medical Internet of Things (M-IoT) systems that are kept private and secure, and their whereabouts can be monitored in the event of an emergency. The protocol also uses quantum authentication in place of more conventional methods like encryption and digital signatures. Mathematical research shows that the quantum converged blockchain (QCB) is highly safe against attacks such as external attacks, intercept measure -repeat attacks, and entanglement measure attacks. We present the reliability and auditability evaluations of the entangled BloQ, along with the quantum circuit design for computing the hash value. There is also a comparison between the suggested approach and several other quantum blockchain designs. [ABSTRACT FROM AUTHOR]

Summary: Difference-in-differences (DID) is a key tool for causal impact evaluation but faces challenges when applied to sensitive data restricted by privacy regulations. Obtaining consent can shrink sample sizes and reduce statistical power, limiting the analysis’s effectiveness. Federated learning addresses these issues by sharing aggregated statistics rather than individual data, though advanced federated DID software is limited. We developed a federated version of the Callaway and Sant’Anna difference-in-differences (CSDID), integrated into the DataSHIELD platform, adhering to stringent privacy protocols. Our approach reproduces key estimates and standard errors while preserving confidentiality. Using simulated and real-world data from a malaria intervention in Mozambique, we demonstrate that federated estimates increase sample sizes, reduce estimation uncertainty, and enable analyses when data owners cannot share treated or untreated group data. Our work contributes to facilitating the evaluation of policy interventions or treatments across centers and borders.

In recent years, the use of electronic health records (EHRs) has become increasingly prevalent in healthcare settings, including emergency departments (EDs). EHRs offer numerous advantages, such as improved documentation, streamlined communication, and enhanced patient care. Additionally, EHRs contain vital information about patient care and treatment outcomes, which opens up exciting research opportunities. The objective of this study was to present a database comprising information regarding patients admitted to the emergency department of a large hospital.In this study, we are introducing an open-access database sourced from the electronic health records of a general university hospital in Isfahan, Iran. The data were collected from patients admitted to the emergency department between March 2017 and March 2022, resulting in a database containing 143,582 ED stays. The database includes triage information, ED admission patients, and services. To ensure patient privacy, all patient-specific information has been removed from the records.

The exacerbated increase in the use of ionizing radiation to obtain images, and the risks and standards that exist to preserve the health of those who use it, are not properly taken into account when carrying out radiodiagnostic examinations. The professionals who work in these environments play a decisive role in the performance of their numerous activities within radiodiagnostic services, bearing in mind that any dose of radiation is associated with a probability of biological effects occurring, no matter how low that dose may be. Thus, the aim of building a software program was to optimize the work of the multiprofessional and interdisciplinary team in radiodiagnostic services, in the management of radiological protection. This is a methodological and quasi-experimental study carried out in a university hospital in southern Brazil, intentionally chosen because it has a Radiological Protection Committee. This research design was adopted for the development of technological production, in this case software for managing radiological protection. The study was carried out in the radiological protection sector of the radiology department of a university hospital in southern Brazil. The results showed that the software, called SisPRad - Management System for Radiological Protection, is a tool that helps the service's multi-professional and interdisciplinary team in terms of managing radiological protection. Finally, it aims to ensure the safety of professionals working in the service and its users, as well as reducing repetition of activities at management level, and can be adapted for other institutions. The computer registration number 512019002125-8 was obtained from the National Institute of Industrial Property for the first version of the software and the registration number 512023003116-0 for its second version.

Summary: The malicious use of artificial intelligence is growing rapidly, creating major security threats for individuals and the healthcare sector. Individuals with mental illness may be especially vulnerable. Healthcare provider data are a prime target for cybercriminals. There is a need to improve cybersecurity to detect and prevent cyberattacks against individuals and the healthcare sector, including the use of artificial intelligence predictive tools. [ABSTRACT FROM AUTHOR]

Abstract Background The use of artificial intelligence in the field of health sciences is becoming widespread. It is known that patients benefit from artificial intelligence applications on various health issues, especially after the pandemic period. One of the most important issues in this regard is the accuracy of the information provided by artificial intelligence applications. Objective The purpose of this study was to the frequently asked questions about dental amalgam, as determined by the United States Food and Drug Administration (FDA), which is one of these information resources, to Chat Generative Pre-trained Transformer version 4 (ChatGPT-4) and to compare the content of the answers given by the application with the answers of the FDA. Methods The questions were directed to ChatGPT-4 on May 8th and May 16th, 2023, and the responses were recorded and compared at the word and meaning levels using ChatGPT. The answers from the FDA webpage were also recorded. The responses were compared for content similarity in “Main Idea”, “Quality Analysis”, “Common Ideas”, and “Inconsistent Ideas” between ChatGPT-4’s responses and FDA’s responses. Results ChatGPT-4 provided similar responses at one-week intervals. In comparison with FDA guidance, it provided answers with similar information content to frequently asked questions. However, although there were some similarities in the general aspects of the recommendation regarding amalgam removal in the question, the two texts are not the same, and they offered different perspectives on the replacement of fillings. Conclusions The findings of this study indicate that ChatGPT-4, an artificial intelligence based application, encompasses current and accurate information regarding dental amalgam and its removal, providing it to individuals seeking access to such information. Nevertheless, we believe that numerous studies are required to assess the validity and reliability of ChatGPT-4 across diverse subjects.

Abstract Prognosticating Amyotrophic Lateral Sclerosis (ALS) presents a formidable challenge due to patients exhibiting different onset sites, progression rates, and survival times. In this study, we have developed and evaluated Machine Learning (ML) algorithms that integrate Ensemble and Imbalance Learning techniques to classify patients into Short and Non-Short survival groups based on data collected during diagnosis. We aimed to identify individuals at high risk of mortality within 24 months of symptom onset through analysis of patient data commonly encountered in daily clinical practice. Our Ensemble-Imbalance approach underwent evaluation employing six ML algorithms as base classifiers. Remarkably, our results outperformed those of individual algorithms, achieving a Balanced Accuracy of 88% and a Sensitivity of 96%. Additionally, we used the Shapley Additive Explanations framework to elucidate the decision-making process of the top-performing model, pinpointing the most important features and their correlations with the target prediction. Furthermore, we presented helpful tools to visualize and compare patient similarities, offering valuable insights. Confirming the obtained results, our approach could aid physicians in devising personalized treatment plans at the time of diagnosis or serve as an inclusion/exclusion criterion in clinical trials.

Abstract Background As the healthcare sector becomes increasingly reliant on technology, it is crucial for universities to offer bachelor’s degrees in health informatics (HI). HI professionals bridge the gap between IT and healthcare, ensuring that technology complements patient care and clinical workflows; they promote enhanced patient outcomes, support clinical research, and uphold data security and privacy standards. This study aims to evaluate accredited HI academic programs in Saudi Arabia. Methods This study employed a quantitative, descriptive, cross-sectional design utilising a self-reported electronic questionnaire consisting of predetermined items and response alternatives. Probability-stratified random sampling was also performed. Result The responses rates were 39% (n = 241) for students and 62% (n = 53) for faculty members. While the participants expressed different opinions regarding the eight variables being examined, the faculty members and students generally exhibited a strong level of consensus on many variables. A notable association was observed between facilities and various other characteristics, including student engagement, research activities, admission processes, and curriculum. Similarly, a notable correlation exists between student engagement and the curriculum in connection to research, attrition, the function of faculty members, and academic outcomes. Conclusion While faculty members and students hold similar views about the institution and its offerings, certain areas of divergence highlight the distinct perspectives and priorities of each group. The perception disparity between students and faculty in areas such as admission, faculty roles, and internships sheds light on areas of improvement and alignment for universities.

Background: The use of artificial intelligence in the field of health sciences is becoming widespread. It is known that patients benefit from artificial intelligence applications on various health issues, especially after the pandemic period. One of the most important issues in this regard is the accuracy of the information provided by artificial intelligence applications. Objective: The purpose of this study was to the frequently asked questions about dental amalgam, as determined by the United States Food and Drug Administration (FDA), which is one of these information resources, to Chat Generative Pre-trained Transformer version 4 (ChatGPT-4) and to compare the content of the answers given by the application with the answers of the FDA. Methods: The questions were directed to ChatGPT-4 on May 8th and May 16th, 2023, and the responses were recorded and compared at the word and meaning levels using ChatGPT. The answers from the FDA webpage were also recorded. The responses were compared for content similarity in "Main Idea", "Quality Analysis", "Common Ideas", and "Inconsistent Ideas" between ChatGPT-4's responses and FDA's responses. Results: ChatGPT-4 provided similar responses at one-week intervals. In comparison with FDA guidance, it provided answers with similar information content to frequently asked questions. However, although there were some similarities in the general aspects of the recommendation regarding amalgam removal in the question, the two texts are not the same, and they offered different perspectives on the replacement of fillings. Conclusions: The findings of this study indicate that ChatGPT-4, an artificial intelligence based application, encompasses current and accurate information regarding dental amalgam and its removal, providing it to individuals seeking access to such information. Nevertheless, we believe that numerous studies are required to assess the validity and reliability of ChatGPT-4 across diverse subjects. [ABSTRACT FROM AUTHOR]