Search

Background: As global aging intensifies, the prevalence of ocular fundus diseases continues to rise. In China, the tense doctor-patient ratio poses numerous challenges for the early diagnosis and treatment of ocular fundus diseases. To reduce the high risk of missed or misdiagnosed cases, avoid irreversible visual impairment for patients, and ensure good visual prognosis for patients with ocular fundus diseases, it is particularly important to enhance the growth and diagnostic capabilities of junior doctors. This study aims to leverage the value of electronic medical record data to developing a diagnostic intelligent decision support platform. This platform aims to assist junior doctors in diagnosing ocular fundus diseases quickly and accurately, expedite their professional growth, and prevent delays in patient treatment. An empirical evaluation will assess the platform's effectiveness in enhancing doctors' diagnostic efficiency and accuracy. Methods: In this study, eight Chinese Named Entity Recognition (NER) models were compared, and the SoftLexicon-Glove-Word2vec model, achieving a high F1 score of 93.02%, was selected as the optimal recognition tool. This model was then used to extract key information from electronic medical records (EMRs) and generate feature variables based on diagnostic rule templates. Subsequently, an XGBoost algorithm was employed to construct an intelligent decision support platform for diagnosing ocular fundus diseases. The effectiveness of the platform in improving diagnostic efficiency and accuracy was evaluated through a controlled experiment comparing experienced and junior doctors. Results: The use of the diagnostic intelligent decision support platform resulted in significant improvements in both diagnostic efficiency and accuracy for both experienced and junior doctors (P < 0.05). Notably, the gap in diagnostic speed and precision between junior doctors and experienced doctors narrowed considerably when the platform was used. Although the platform also provided some benefits to experienced doctors, the improvement was less pronounced compared to junior doctors. Conclusion: The diagnostic intelligent decision support platform established in this study, based on the XGBoost algorithm and NER, effectively enhances the diagnostic efficiency and accuracy of junior doctors in ocular fundus diseases. This has significant implications for optimizing clinical diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) is a progressive neurodegenerative condition. Chinese medicine therapies have demonstrated effectiveness for PD in controlled settings. However, the utilization of Chinese medicine therapies for PD in real-world clinical practice and the characteristics of patients seeking these therapies have not been thoroughly summarized. Method: The study retrospectively analyzed initial patient encounters (PEs) with a first-listed diagnosis of PD, based on electronic medical records from Guangdong Provincial Hospital of Chinese Medicine between July 2018 and July 2023. Results: A total of 3,206 PEs, each corresponding to an individual patient, were eligible for analyses. Approximately 60% of patients made initial visits to the Chinesemedicine hospital after receiving a PD diagnosis, around 4.59 years after the onset of motor symptoms. Over 75% of the patients visited the Internal Medicine Outpatient Clinic at their initial visits, while a mere 13.85% visited PD Chronic Care Clinic. Rest tremor (61.98%) and bradykinesia (52.34%) are the most commonly reported motor symptoms, followed by rigidity (40.70%). The most commonly recorded non-motor symptoms included constipation (31.88%) and sleep disturbance (25.27%). Integration of Chinese medicine and conventional medicine therapies was the most common treatment method (39.15%), followed by single use of Chinese herbal medicine (27.14%). The most frequently prescribed herbs for PD included Glycyrrhiza uralensis Fisch. (gan cao), Astragalus mongholicus Bunge (huang qi), Atractylodes macrocephala Koidz. (bai zhu), Angelica sinensis (Oliv.) Diels (dang gui), Rehmannia glutinosa (Gaertn.) DC. (di huang), Paeonia lactiflora Pall. (bai shao), Bupleurum chinense DC. (chai hu), Citrus aurantium L. (zhi qiao/zhi shi/chen pi), Panax ginseng C. A. Mey. (ren shen), and Poria cocos (Schw.) Wolf (fu ling). These herbs contribute to formulation of Bu zhong yi qi tang (BZYQT). Conclusion: Patients typically initiated Chinese medical care after the establishment of PD diagnosis, 4.59 years post-onset of motor symptoms. The prevalent utilization of CHM decoctions and patented Chinese herbal medicine products, underscores its potential in addressing both motor and non-motor symptoms. Despite available evidence, rigorous clinical trials are needed to validate and optimize the integration of CHM, particularly BZYQT, into therapeutic strategies for PD. [ABSTRACT FROM AUTHOR]

Objective: We aimed to develop a 5-year overall survival prediction model for patients with oral tongue squamous cell carcinoma based on machine learning methods. Subjects and methods: The data were obtained from electronic medical records of 224 OTSCC patients at the PLA General Hospital. A five-year overall survival prediction model was constructed using logistic regression, Support Vector Machines, Decision Tree, Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine. Model performance was evaluated according to the area under the curve (AUC) of the receiver operating characteristic curve. The output of the optimal model was explained using the Python package (SHapley Additive exPlanations, SHAP). Results: After passing through the grid search and secondary modeling, the Light Gradient Boosting Machine was the best prediction model (AUC = 0.860). As explained by SHapley Additive exPlanations, N-stage, age, systemic inflammation response index, positive lymph nodes, plasma fibrinogen, lymphocyte-to-monocyte ratio, neutrophil percentage, and T-stage could perform a 5-year overall survival prediction for OTSCC. The 5-year survival rate was 42%. Conclusion: The Light Gradient Boosting Machine prediction model predicted 5-year overall survival in OTSCC patients, and this predictive tool has potential prognostic implications for patients with OTSCC. [ABSTRACT FROM AUTHOR]

The impact of the 2019 coronavirus disease (COVID-19) pandemic is still being revealed, and little is known about the effect of COVID-19-induced outpatient and inpatient losses on hospital operations in many counties. Hence, we aimed to explore whether hospitals adopted profit compensation activities after the 2020 first-wave outbreak of COVID-19 in China. A total of 2,616,589 hospitalization records from 2018, 2019, and 2020 were extracted from 36 tertiary hospitals in a western province in China; we applied a difference-in-differences event study design to estimate the dynamic effect of COVID-19 on hospitalized patients' total expenses before and after the last confirmed case. We found that average total expenses for each patient increased by 8.7% to 16.7% in the first 25 weeks after the city reopened and hospital admissions returned to normal. Our findings emphasize that the increase in total inpatient expenses was mainly covered by claiming expenses from health insurance and was largely driven by an increase in the expenses for laboratory tests and medical consumables. Our study documents that there were profit compensation activities in hospitals after the 2020 first-wave outbreak of COVID-19 in China, which was driven by the loss of hospitalization admissions during this wave outbreak. [ABSTRACT FROM AUTHOR]

Purpose: In the context of Chinese clinical texts, this paper aims to propose a deep learning algorithm based on Bidirectional Encoder Representation from Transformers (BERT) to identify privacy information and to verify the feasibility of our method for privacy protection in the Chinese clinical context. Methods: We collected and double-annotated 33,017 discharge summaries from 151 medical institutions on a municipal regional health information platform, developed a BERT-based Bidirectional Long Short-Term Memory Model (BiLSTM) and Conditional Random Field (CRF) model, and tested the performance of privacy identification on the dataset. To explore the performance of different substructures of the neural network, we created five additional baseline models and evaluated the impact of different models on performance. Results: Based on the annotated data, the BERT model pre-trained with the medical corpus showed a significant performance improvement to the BiLSTM-CRF model with a micro-recall of 0.979 and an F1 value of 0.976, which indicates that the model has promising performance in identifying private information in Chinese clinical texts. Conclusions: The BERT-based BiLSTM-CRF model excels in identifying privacy information in Chinese clinical texts, and the application of this model is very effective in protecting patient privacy and facilitating data sharing., Competing Interests: Declaration of conflicting interestsThe author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Our aim was to investigate the association of glycated haemoglobin A1c (HbA1c) variability score (HVS) with estimated glomerular filtration rate (eGFR) slope in Chinese adults living with type 2 diabetes. This cohort study included adults with type 2 diabetes attending outpatient clinics between 2011 and 2019 from a large electronic medical record-based database of diabetes in China (WECODe). We estimated the individual-level visit-to-visit HbA1c variability using HVS, a proportion of changes in HbA1c of ≥0.5% (5.5 mmol/mol). We estimated the odds of people experiencing a rapid eGFR annual decline using a logistic regression and differences across HVS categories in the mean eGFR slope using a mixed-effect model. The analysis involved 2397 individuals and a median follow-up of 4.7 years. Compared with people with HVS ≤ 20%, those with HVS of 60% to 80% had 11% higher odds of experiencing rapid eGFR annual decline, with an extra eGFR decline of 0.93 mL/min/1.73 m2 per year on average; those with HVS > 80% showed 26% higher odds of experiencing a rapid eGFR annual decline, with an extra decline of 1.83 mL/min/1.73 m2 per year on average. Chinese adults with type 2 diabetes and HVS > 60% could experience a more rapid eGFR decline. [ABSTRACT FROM AUTHOR]

Cardiovascular disease is currently one of the most important diseases causing death in China and the world, and acute myocardial infarction is a major cause of cardiovascular disease. This study provides an analytical technique for predicting the prognosis of patients with severe acute myocardial infarction using a support vector machine (SVM) technique based on information gleaned from electronic medical records in the Medical Information Marketplace for Intensive Care (MIMIC)-III database. The MIMIC-III database provided 4785 electronic medical records data for inclusion in the model development after screening 7070 electronic medical records of patients admitted to the intensive care unit for treatment of acute myocardial infarction. Adopting the APS-III score as the criterion for identifying anticipated risk, the dimensions of data information incorporated into the mathematical model design were found using correlation coefficient matrix heatmaps and ordered logistic analysis. An automated prognostic risk-prediction model was developed using SVM, and the fit was evaluated by 5x cross-validation. We used a grid search method to further optimize the parameters and improve the model fit. The excellent generalization ability of SVM was fully verified by calculating the 95% confidence interval of the area under the receiver operating characteristic curve (AUC) for six algorithms (linear discriminant, tree, Kernel Naive Bayes, RUSBoost, KNN, and SVM). Compared to the remaining five models, its confidence interval was the narrowest with higher fitting accuracy and better performance. The patient prognostic risk prediction model constructed using SVM had a relatively impressive accuracy (92.2%) and AUC value (0.98). In this study, a model was designed for fitting that can maximize the potential information to be gleaned in the electronic medical records data. It was demonstrated that SVM models based on electronic medical records data can offer an effective solution for clinical disease prognostic risk assessment and improved clinical outcomes and have great potential for clinical application in the clinical treatment of myocardial infarction. [ABSTRACT FROM AUTHOR]

Background: The impact of the Plan-Do-Check-Act (PDCA) cycle in improving the timeliness of electronic medical record documentation (EMRd) remains uncertain. EMRd that is completed beyond the specified time is classified as late EMRd, while unqualified EMRd refers to electronic medical records with important sections that are not completed on time according to the Chinese Basic Norms of Medical Records Writing. This study aimed to evaluate the effectiveness of PDCA management in improving the timeliness of EMRd among resident doctors., Method: This study utilized a before and after design. Resident doctors rotating in the Head and Neck Oncology Department of West China Hospital, Sichuan University, from November 2021 to August 2022 were classified as the control group and did not receive specific training on the timeliness of EMRd. Those rotating from September 2022 to June 2023 were assigned to the PDCA group, which was managed using the PDCA cycle. The effectiveness of PDCA cycle management was evaluated by comparing the incidence of late EMRd and unqualified EMRd between two groups. Univariate and multivariate binary logistic regression analyses were conducted tocontrol for confounding factors., Results: A total of 245 resident doctors were included, with 162 doctors in the PDCA group and 152 doctors in the control group. The incidences of late EMRd (5.40% vs. 2.56%, P = 0.005) and unqualified EMRd (1.05% vs. 0.00%, P < 0.001) were significantly lower in the PDCA group than those in the control group. After adjusting confounding factors, PDCA management still significantly reduced the occurrence of unqualified EMRd (P < 0.001) with an adjusted odds ratio (OR) of 0.166 (95% CI 0.067-0.416) and late EMRd (P < 0.001) with an adjusted OR of 0.318 (95% CI 0.181-0.557)., Conclusion: This study successfully developed PDCA management and demonstrated its effectiveness in improving the timeliness of EMRd while concurrently reducing the incidence of unqualified and late entries among resident doctors., Competing Interests: Declarations. Ethics approval and consent to participate: Written informed consent was obtained from the individual participants or their guardians. The study was approved by the medical ethics committee of West China Hospital, Sichuan University, with the approval number 2024 − 1658. All procedures involving human participants performed in this study were in accordance with the ethical standards of the institutional research committee and the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests., (© 2024. The Author(s).)

Background Globally, geriatric patients are the dominant population requiring global medical care. We established a frailty index for geriatric trauma patients by retrospectively analysing electronic hospital records to identify patients with frailty characteristics and poor prognostic outcomes. Method Data were obtained from 2016 US National Emergency Department Sample and Shanghai Trauma Emergency Medical Association (2015–18). Overall, 141,267 hospitalised geriatric trauma patients (age ≥ 65 years) were included. We used a three-step method to construct geriatric trauma frailty index (GTFI) based on the International Statistical Classification of Diseases and Related Health Problems, Tenth Revision diagnostic codes. Systematic cluster analysis was used. The accuracy of GTFI was verified in national validation cohort, and its applicability to Chinese patients was assessed in local validation cohort. Results In development cohort (n  = 28,179), frail patients had longer lengths of stay and higher Charlson co-morbidity index than non-frail patients (18.2 ± 12.4 days, 5.59 ± 2.0 versus 5.3 ± 5.3 days, 5.33 ± 1.8, respectively). In national validation cohort (n  = 113,089), frail patients had longer lengths of stay (8.5 ± 8.8 days versus 4.5 ± 3.1 days) and higher in-hospital mortality than non-frail patients (2,795, 11.69% versus 589, 0.66%). Areas under the curves for GTFI for length of stay (>14 days) and in-hospital mortality were 0.848 (0.841, 0.854) and 0.885 (0.880, 0.891) in national validation cohort, and were 0.791 (0.779, 0.804) and 0.903 (0.885, 0.922) in local validation cohort (n  = 14,827). Conclusions The GTFI helps hospitals and emergency departments to identify geriatric trauma patients with poor prognostic outcomes, and has been proven to be useful in China. [ABSTRACT FROM AUTHOR]

Objectives: Early recognition and intervention of patients with the anti‐N‐methyl‐d‐aspartate receptor (NMDAR) encephalitis are important to achieve a better prognosis. The study aims to summarize the real‐world perspectives of anti‐NMDAR encephalitis patients in China via electronic medical records (EMRs). Methods: Using EMRs of patients from 2013 to 2019 from West China Hospital in China, a retrospective research was conducted to demonstrate the temporary rank of clinical characteristics and disease prognosis of anti‐NMDAR encephalitis. The modified Rankin Scale (mRS) scores were used to divide the anti‐NMDAR‐encephalitis into two groups (poor prognosis vs. good prognosis). Chi‐square test and logistic regression were used to analyze factors associated with prognosis. Results: Here, 78 patients were included. The most common clinical characteristics are cognitive dysfunction (86.0%) and thought disorder (86.0%). Cognitive dysfunction, thought disorder, and seizures tended to appear soon after prodrome symptoms. Logistics analysis results showed that cognitive dysfunction (OR = 4.48, 95% CI = 1.09–18.47), the score of (GCS ≤ 8) (OR = 4.52, 95% CI = 1.18–17.32), positive antibodies in serum (OR = 4.89, 95% CI = 1.19–20.13) and delay immunotherapy (OR = 4.76, 95% CI = 1.79–12.60) were risk factors of poor clinical outcomes. Conclusions: There are two peaks in the development of autoimmune encephalitis (AE). The first peak is cognitive dysfunction, and the second peak is autonomic dysfunction. Cognitive dysfunction and GCS score ≤8 at admission, antibodies positive in serum, and delay immunotherapy were risk factors for a poor prognosis at discharge. [ABSTRACT FROM AUTHOR]

Background: Efficacy of pancreatic enzyme inhibitors in acute pancreatitis (AP) is unclear in China.Aims: We aimed to present the current status of AP and evaluate the efficacy of pancreatic enzyme inhibitors in a larger population in China.Method: A retrospective, cross-sectional, real-world, multicenter analysis of a large dataset of patients presenting with AP from four hospitals of China over a two-year period was performed. Data were collected from the existing clinical records and the patients were grouped into medication group (somatostatin or octreotide or somatostatin and octreotide) and no medication group. Pair wise propensity score matching was performed for comparing somatostatin, octreotide and somatostatin/octreotide. The end points were incidence of disease complications, organ failure, hospitalization duration, and recovery time taken (hours) for serum amylase/serum lipase to normalcy.Results: A total of 3900 patients were recruited and 2775 patients were included for analysis. A total of 1100, 661, 676 and 338 patients received either somatostatin or octreotide or somatostatin and octreotide or no medication, respectively. The incidence of complications (7.6% vs 13.6%), organ failure (4.5% vs 7.4%), and the instances of entering ICU (9.3% vs 13.3%) were higher in unmedicated group. Complications at discharge (2.91 times), organ failure (2.53 times), and hospitalization stay were higher in octreotide-treated patients compared with somatostatin-treated patients. In comparison to the octreotide group, the serum amylase/lipase recovery time was shorter in the somatostatin group.Conclusion: This real-world study suggested that the use of pancreatic enzyme inhibitors was positively associated with greater clinical efficacy in AP patients and somatostatin might be more effective than octreotide in real-world settings in China. [ABSTRACT FROM AUTHOR]

Named entity recognition is a critical task in the electronic medical record management system for rehabilitation robots. Handwritten documents often contain spelling errors and illegible handwriting, and healthcare professionals frequently use different terminologies. These issues adversely affect the robot's judgment and precise operations. Additionally, the same entity can have different meanings in various contexts, leading to category inconsistencies, which further increase the system's complexity. To address these challenges, a novel medical entity recognition algorithm for Chinese electronic medical records is developed to enhance the processing and understanding capabilities of rehabilitation robots for patient data. This algorithm is based on a fusion classification strategy. Specifically, a preprocessing strategy is proposed according to clinical medical knowledge, which includes redefining entities, removing outliers, and eliminating invalid characters. Subsequently, a medical entity recognition model is developed to identify Chinese electronic medical records, thereby enhancing the data analysis capabilities of rehabilitation robots. To extract semantic information, the ALBERT network is utilized, and BILSTM and MHA networks are combined to capture the dependency relationships between words, overcoming the problem of different meanings for the same entity in different contexts. The CRF network is employed to determine the boundaries of different entities. The research results indicate that the proposed model significantly enhances the recognition accuracy of electronic medical texts by rehabilitation robots, particularly in accurately identifying entities and handling terminology diversity and contextual differences. This model effectively addresses the key challenges faced by rehabilitation robots in processing Chinese electronic medical texts, and holds important theoretical and practical value.

Objectives: An outbreak of the highly contagious severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has sickened thousands of people in China. The purpose of this study was to explore the early clinical characteristics of COVID-19 patients with cardiovascular disease (CVD).Methods: This is a retrospective analysis of patients with COVID-19 from a single centre. All patients underwent real-time reverse transcription PCR for SARS-CoV-2 on admission. Demographic and clinical factors and laboratory data were reviewed and collected to evaluate for significant associations.Results: The study included 541 patients with COVID-19. A total of 144 (26.6%) patients had a history of CVD. The mortality of patients with CVD reached 22.2%, which was higher than that of the overall population of this study (9.8%). Patients with CVD were also more likely to develop liver function abnormality, elevated blood creatinine and lactic dehydrogenase (p<0.05). Symptoms of sputum production were more common in patients with CVD (p=0.026). Lymphocytes, haemoglobin and albumin below the normal range were pervasive in the CVD group (p<0.05). The proportion of critically ill patients in the CVD group (27.8%) was significantly higher than that in the non-CVD group (8.8%). Multivariable logistic regression analysis revealed that CVD (OR: 2.735 (95% CI 1.495 to 5.003), p=0.001) was associated with critical COVID-19 condition, while patients with coronary heart disease were less likely to reach recovery standards (OR: 0.331 (95% CI 0.125 to 0.880), p=0.027).Conclusions: Considering the high prevalence of CVD, a thorough CVD assessment at diagnosis and early intervention are recommended in COVID-19 patients with CVD. Patients with CVD are more vulnerable to deterioration. [ABSTRACT FROM AUTHOR]

This study evaluates the impact of health information technology in accessing medical resources and identifies its role in improving health equity. We used 262, 771 records from the electronic medical records and outpatient appointment systems of three clinics for logistic regression to analyze the impact of information technology on patients' access to medical care. We interviewed a few health professionals to gauge their reactions and to validate and understand our quantitative results. The proportion of inpatients affected by information technology is low, accounting for only 16.7% (N = 43, 870). The difference between rural and urban groups is statistically significant, and rural households are more susceptible to information technology. In addition, distance has a significant positive effect. We demonstrate an inverted U-shaped relationship between severity of disease and the impact of information technology. Moreover, our interview results are consistent with our quantitative results. Quantitative and interview results suggest that health information technology plays a positive role in accessing medical care for patients with rural household and those in remote areas. Meanwhile, this effect is complex for patients with different severities of illnesses. Governments and managers should vigorously promote health information technology for healthcare delivery in the future and focus their attention on patients with serious diseases. [ABSTRACT FROM AUTHOR]

Background: Electronic medical records provide large-scale real-world clinical data for use in developing clinical decision systems. However, sophisticated methodology and analytical skills are required to handle the large-scale datasets necessary for the optimisation of prediction accuracy. Myopia is a common cause of vision loss. Current approaches to control myopia progression are effective but have significant side effects. Therefore, identifying those at greatest risk who should undergo targeted therapy is of great clinical importance. The objective of this study was to apply big data and machine learning technology to develop an algorithm that can predict the onset of high myopia, at specific future time points, among Chinese school-aged children. Methods and findings: Real-world clinical refraction data were derived from electronic medical record systems in 8 ophthalmic centres from January 1, 2005, to December 30, 2015. The variables of age, spherical equivalent (SE), and annual progression rate were used to develop an algorithm to predict SE and onset of high myopia (SE ≤ −6.0 dioptres) up to 10 years in the future. Random forest machine learning was used for algorithm training and validation. Electronic medical records from the Zhongshan Ophthalmic Centre (a major tertiary ophthalmic centre in China) were used as the training set. Ten-fold cross-validation and out-of-bag (OOB) methods were applied for internal validation. The remaining 7 independent datasets were used for external validation. Two population-based datasets, which had no participant overlap with the ophthalmic-centre-based datasets, were used for multi-resource validation testing. The main outcomes and measures were the area under the curve (AUC) values for predicting the onset of high myopia over 10 years and the presence of high myopia at 18 years of age. In total, 687,063 multiple visit records (≥3 records) of 129,242 individuals in the ophthalmic-centre-based electronic medical record databases and 17,113 follow-up records of 3,215 participants in population-based cohorts were included in the analysis. Our algorithm accurately predicted the presence of high myopia in internal validation (the AUC ranged from 0.903 to 0.986 for 3 years, 0.875 to 0.901 for 5 years, and 0.852 to 0.888 for 8 years), external validation (the AUC ranged from 0.874 to 0.976 for 3 years, 0.847 to 0.921 for 5 years, and 0.802 to 0.886 for 8 years), and multi-resource testing (the AUC ranged from 0.752 to 0.869 for 4 years). With respect to the prediction of high myopia development by 18 years of age, as a surrogate of high myopia in adulthood, the algorithm provided clinically acceptable accuracy over 3 years (the AUC ranged from 0.940 to 0.985), 5 years (the AUC ranged from 0.856 to 0.901), and even 8 years (the AUC ranged from 0.801 to 0.837). Meanwhile, our algorithm achieved clinically acceptable prediction of the actual refraction values at future time points, which is supported by the regressive performance and calibration curves. Although the algorithm achieved balanced and robust performance, concerns about the compromised quality of real-world clinical data and over-fitting issues should be cautiously considered. Conclusions: To our knowledge, this study, for the first time, used large-scale data collected from electronic health records to demonstrate the contribution of big data and machine learning approaches to improved prediction of myopia prognosis in Chinese school-aged children. This work provides evidence for transforming clinical practice, health policy-making, and precise individualised interventions regarding the practical control of school-aged myopia. [ABSTRACT FROM AUTHOR]

• As far as we know, we are the first to develop a machine learning (ML)-based diagnostic system, based on electronic medical records (EMR) data, to mimic the clinical reasoning of human physicians to differentiate MDD and BD (especially BD depressive episodes) patients. • The diagnostic system accurately identified patients with BD in various clinical scenarios. The underlying causal reasoning for the machine decisions is explainable, enabling population-level and individual-level interventions. • Differences in patterns of peripheral markers between BD and MDD could enrich our understanding of potential underlying pathophysiological mechanisms of them. Caused by shared genetic risk factors and similar neuropsychological symptoms, bipolar disorder (BD) and major depressive disorder (MDD) are at high risk of misdiagnosis, which is associated with ineffective treatment and worsening of outcomes. We aimed to develop a machine learning (ML)-based diagnostic system, based on electronic medical records (EMR) data, to mimic the clinical reasoning of human physicians to differentiate MDD and BD (especially BD depressive episodes) patients about to be admitted to a hospital and, hence, reduce the misdiagnosis of BD as MDD on admission. In addition, we examined to what extent our ML model could be made interpretable by quantifying and visualizing the features that drive the predictions. By identifying 16,311 patients admitted to a hospital located in western China between 2009 and 2018 with a recorded main diagnosis of MDD or BD, we established three sub-cohorts with different combinations of features for both the MDD-BD cohort and the MDD-BD depressive episodes cohort, respectively. Four different ML algorithms (logistic regression, extreme gradient boosting (XGBoost), random forest, and support vector machine) and four train-test splits were used to train and validate diagnostic models, and explainable methods (SHAP and Break Down) were utilized to analyze the contribution of each of the features at both population-level and individual-level, including feature importance, feature interaction, and feature effect on prediction decision for a specific subject. The XGBoost algorithm provided the best test performance (AUC: 0.838 (0.810–0.867), PPV: 0.810 and NPV: 0.834) for separating patients with BD from those with MDD. Core predictors included symptoms (mood-up, exciting, bad sleep, loss of interest, talking, mood-down, provoke), along with age, job, myocardial enzyme markers (creatine kinase, hydroxybutyrate dehydrogenase), diabetes-associated marker (glucose), bone function marker (alkaline phosphatase), non-enzymatic antioxidant (uric acid), markers of immune/inflammation (white blood cell count, lymphocyte count, basophil percentage, monocyte count), cardiovascular function marker (low density lipoprotein), renal marker (total protein), liver biochemistry marker (indirect bilirubin), and vital signs like pulse. For separating patients with BD depressive episodes from those with MDD, the test AUC was 0.777 (0.732–0.822), with PPV 0.576 and NPV 0.899. Additional validation in models built with self-reported symptoms removed from the feature set, showed test AUC of 0.701 (0.666–0.736) for differentiating BD and MDD, and AUC of 0.564 (0.515–0.614) for detecting patients in BD depressive episodes from MDD patients. Validation in the datasets without removing the patients with comorbidity showed an AUC of 0.826 (0.806–0.846). The diagnostic system accurately identified patients with BD in various clinical scenarios, and differences in patterns of peripheral markers between BD and MDD could enrich our understanding of potential underlying pathophysiological mechanisms of them. [ABSTRACT FROM AUTHOR]

The field of Chinese medical natural language processing faces a significant challenge in training accurate entity recognition models due to the limited availability of high-quality labeled data. In response, we propose a joint training model, MCBERT-GCN-CRF, which achieves high performance in identifying medical-related entities in Chinese electronic medical records. Additionally, we introduce CM-NER, a 5-step framework that effectively mitigates the effects of noise in weakly labeled data and establishes a principled connection between supervised and weakly supervised named entity recognition. We demonstrate significant improvements in recall rate and accuracy. Our approach outperforms traditional fully supervised pre-training models and other state-of-the-art methods by suppressing noise in weakly labeled data. Our proposed framework achieves an F1 score of 86.29% on the CCKS-2019 dataset, significantly higher than pre-trained model baselines ranging from 74.17 to 83.06%, and higher than the top-performing named entity recognition supervised learning models in the CCKS-2019 competition. Our results demonstrate the effectiveness of our proposed framework and highlight the potential of leveraging unlabeled data to train accurate models for named entity recognition in Chinese medical natural language processing. This research has significant implications for advancing natural language processing techniques in the medical domain and improving patient care., (© 2023. International Federation for Medical and Biological Engineering.)

Background: Cytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed to evaluate the risk of cytopenia during hospitalization in HIV patients. Such a model is crucial for designing a more individualized and evidence-based treatment strategy for HIV patients., Method: The present study was conducted on HIV patients who were admitted to Guangxi Chest Hospital between June 2016 and October 2021. We extracted a total of 66 clinical features from the electronic medical records and employed them to train five machine learning prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] and support vector machine [SVM], decision tree [DT]). The models were tested using 20% of the data. The performance of the models was evaluated using indicators such as the area under the receiver operating characteristic curve (AUC). The best predictive models were interpreted using the shapley additive explanation (SHAP)., Result: The ANN models have better predictive power. According to the SHAP interpretation of the ANN model, hypoproteinemia and cancer were the most important predictive features of cytopenia in HIV hospitalized patients. Meanwhile, the lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4 + T cell counts, and creatinine clearance (Ccr) levels increase the risk of cytopenia in HIV hospitalized patients., Conclusion: The present study constructed a risk prediction model for cytopenia in HIV patients during hospitalization with machine learning and electronic medical record information. The prediction model is important for the rational management of HIV hospitalized patients and the personalized treatment plan setting., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Huang, Xie, Zhang, Xu, Su, Lv, Lu, Qin, Pang, Qiu, Li, Wei, Huang, Meng, Hu and Lv.)

Background: Named Entity Recognition (NER) is a long-standing fundamental problem in various research fields of Natural Language Processing (NLP) and has been practiced in many application scenarios. However, the application results of NER methods in Chinese electronic medical records (EMRs) are not satisfactory, mainly due to the following two problems: (1) Existing methods do not take into account the impact of medical terminology on model recognition performance, resulting in poor model performance. (2) Existing methods do not fully utilize the Chinese language features contained in EMR, resulting in poor model robustness. Therefore, it is imminent to solve these two problems regarding the performance of the NER model for EMRs., Methods: In this paper, a TENER-based radical feature and entity augmentation model for NER in Chinese EMRs is proposed. The TENER model is first used in the pre-training stage to extract deep semantic information from each layer of the feature extractor. In the decoder part, the recognition of medical entity boundary and entity category are divided into two branch tasks., Results: We compare the overall performance of the proposed model with existing models on different datasets using the computed F1 score evaluation metric. The experimental results show that our model achieves the best F1 score of 82.67%, 74.37%, 70.16% on the CCKS2019, ERTCMM, and CEMR data sets. Meanwhile, in the CMeEE challenge, our model surpassed the top-3 with the F1 score of 68.39%., Conclusions: Our proposed model is the first to divide the NER task into a two-branch tasks, entity boundary and types recognition. Firstly, the medical entity dictionary information is integrated into TENER to obtain the feature information of professional terms in Chinese EMRs. Secondly, the features of Chinese radicals in Chinese EMRs extracted by CNN are added to the entity category recognition task. Finally, the effectiveness of the model is validated on four datasets and competitive results are achieved., (© 2023. The Author(s).)

Clinical outcome prediction, as strong implications for health service delivery of clinical treatment processes (CTPs), is important for both patients and healthcare providers. Prior studies typically use a priori knowledge, such as demographics or patient physical factors, to estimate clinical outcomes at early stages of CTPs (e.g., admission). They lack the ability to deal with temporal evolution of CTPs. In addition, most of the existing studies employ data mining or machine learning methods to generate a prediction model for a specific type of clinical outcome, however, a mathematical model that predicts multiple clinical outcomes simultaneously, has not yet been established. In this study, a hybrid approach is proposed to provide a continuous predictive monitoring service on multiple clinical outcomes. More specifically, a probabilistic topic model is applied to discover underlying treatment patterns of CTPs from electronic medical records. Then, the learned treatment patterns, as low-dimensional features of CTPs, are exploited for clinical outcome prediction across various stages of CTPs based on multi-label classification. The proposal is evaluated to predict three typical classes of clinical outcomes, i.e., length of stay, readmission time, and the type of discharge, using 3492 pieces of patients' medical records of the unstable angina CTP, extracted from a Chinese hospital. The stable model was characterized by 84.9% accuracy and 6.4% hamming-loss with 3 latent treatment patterns discovered from data, which outperforms the benchmark multi-label classification algorithms for clinical outcome prediction. Our study indicates the proposed approach can potentially improve the quality of clinical outcome prediction, and assist physicians to understand the patient conditions, treatment inventions, and clinical outcomes in an integrated view. [ABSTRACT FROM AUTHOR]

Named entities are the main carriers of relevant medical knowledge in Electronic Medical Records (EMR). Clinical electronic medical records lead to problems such as word segmentation ambiguity and polysemy due to the specificity of Chinese language structure, so a Clinical Named Entity Recognition (CNER) model based on multi-head self-attention combined with BILSTM neural network and Conditional Random Fields is proposed. Firstly, the pre-trained language model organically combines char vectors and word vectors for the text sequences of the original dataset. The sequences are then fed into the parallel structure of the multi-head self-attention module and the BILSTM neural network module, respectively. By splicing the output of the neural network module to obtain multi-level information such as contextual information and feature association weights. Finally, entity annotation is performed by CRF. The results of the multiple comparison experiments show that the structure of the proposed model is very reasonable and robust, and it can effectively improve the Chinese CNER model. The model can extract multi-level and more comprehensive text features, compensate for the defect of long-distance dependency loss, with better applicability and recognition performance.

Objectives: An outbreak of the highly contagious severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has sickened thousands of people in China. The purpose of this study was to explore the early clinical characteristics of COVID-19 patients with cardiovascular disease (CVD)., Methods: This is a retrospective analysis of patients with COVID-19 from a single centre. All patients underwent real-time reverse transcription PCR for SARS-CoV-2 on admission. Demographic and clinical factors and laboratory data were reviewed and collected to evaluate for significant associations., Results: The study included 541 patients with COVID-19. A total of 144 (26.6%) patients had a history of CVD. The mortality of patients with CVD reached 22.2%, which was higher than that of the overall population of this study (9.8%). Patients with CVD were also more likely to develop liver function abnormality, elevated blood creatinine and lactic dehydrogenase (p<0.05). Symptoms of sputum production were more common in patients with CVD (p=0.026). Lymphocytes, haemoglobin and albumin below the normal range were pervasive in the CVD group (p<0.05). The proportion of critically ill patients in the CVD group (27.8%) was significantly higher than that in the non-CVD group (8.8%). Multivariable logistic regression analysis revealed that CVD (OR: 2.735 (95% CI 1.495 to 5.003), p=0.001) was associated with critical COVID-19 condition, while patients with coronary heart disease were less likely to reach recovery standards (OR: 0.331 (95% CI 0.125 to 0.880), p=0.027)., Conclusions: Considering the high prevalence of CVD, a thorough CVD assessment at diagnosis and early intervention are recommended in COVID-19 patients with CVD. Patients with CVD are more vulnerable to deterioration., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2020. No commercial re-use. See rights and permissions. Published by BMJ.)

Pediatric cough is a heterogeneous condition in terms of symptoms and the underlying disease mechanisms. Symptom phenotypes hold complicated interactions between each other to form an intricate network structure. This study aims to investigate whether the network structure of pediatric cough symptoms is associated with the prognosis and outcome of patients. A total of 384 cases were derived from the electronic medical records of a highly experienced traditional Chinese medicine (TCM) physician. The data were divided into two groups according to the therapeutic effect, namely, an invalid group (group A with 40 cases of poor efficacy) and a valid group (group B with 344 cases of good efficacy). Several well-established analysis methods, namely, statistical test, correlation analysis, and complex network analysis, were used to analyze the data. This study reports that symptom networks of patients with pediatric cough are related to the effectiveness of treatment: a dense network of symptoms is associated with great difficulty in treatment. Interventions with the most different symptoms in the symptom network may have improved therapeutic effects.

Background: This study explored the possible antecedents that will motivate hospital employees' compliance with privacy policy related to electronic medical records (EMR) from a deterrence perspective. Further, we also investigated the moderating effect of computer monitoring on relationships among the antecedents and the level of hospital employees' compliance intention., Methods: Data was collected from a large Taiwanese medical center using survey methodology. A total of 303 responses was analyzed via hierarchical regression analysis., Results: The results revealed that sanction severity and sanction certainty significantly predict hospital employees' compliance intention, respectively. Further, our study found external computer monitoring significantly moderates the relationship between sanction certainty and compliance intention., Conclusions: Based on our findings, the study suggests that healthcare facilities should take proactive countermeasures, such as computer monitoring, to better protect the privacy of EMR in addition to stated privacy policy. However, the extent of computer monitoring should be kept to minimum requirements as stated by relevant regulations.

A large amount of data has been accumulated in Chinese medical area. Problems as how to use big data to carry out randomized controlled trials have also been increasingly noteworthy. Through learning the successful experiences in conducting randomized controlled trials on big data from abroad, this article introduces the knowledge regarding sources of data, identification of research subjects and outcomes, interventions, methods of randomization and the implementation of informed consent, etc ., all related to big data, hoping to shed light on studies of this kind, for the years to come in China.

The health care reform initiative led by the Hong Kong government’s Food and Health Bureau has started the implementation of an electronic sharing platform to provide an information infrastructure that enables public hospitals and private clinics to share their electronic medical records (EMRs) for improved access to patients’ health care information. However, previous attempts to convince the private clinics to adopt EMRs to document health information have faced challenges, as the EMR adoption has been voluntary. The lack of electronic data shared by private clinics carries direct impacts to the efficacy of electronic record sharing between public and private healthcare providers. To increase the likelihood of buy-in, it is essential to proactively identify the users’ and organizations’ needs and capabilities before large-scale implementation. As part of the reform initiative, this study examined factors affecting the adoption of EMRs in small or solo private general practice clinics, by analyzing the experiences and opinions of the physicians and clinical assistants during the pilot implementation of the technology, with the purpose to learn from it before full-scale rollout. In-depth, semistructured interviews were conducted with 23 physicians and clinical assistants from seven small or solo private general practice clinics to evaluate their experiences, expectations, and opinions regarding the deployment of EMRs. Interview transcripts were content analyzed to identify key factors. Factors affecting the adoption of EMRs to record and manage health care information were identified as follows: system interface design; system functions; stability and reliability of hardware, software, and computing networks; financial and time costs; task and outcome performance, work practice, and clinical workflow; physical space in clinics; trust in technology; users’ information technology literacy; training and technical support; and social and organizational influences. The factors are interrelated with the others. The adoption factors identified are multifaceted, ranging from technological characteristics, clinician-technology interactions, skills and knowledge, and the user-workflow-technology fit. Other findings, which have been relatively underrepresented in previous studies, contribute unique insights about the influence of work and social environment on the adoption of EMRs, including limited clinic space and the effects of physicians’ decision to use the technology on clinical staffs’ adoption decisions. Potential strategies to address the concerns, overcome adoption barriers, and define relevant policies are discussed. [ABSTRACT FROM AUTHOR]

Background: Electronic Medical Record (EMR) comprises patients' medical information gathered by medical stuff for providing better health care. Named Entity Recognition (NER) is a sub-field of information extraction aimed at identifying specific entity terms such as disease, test, symptom, genes etc. NER can be a relief for healthcare providers and medical specialists to extract useful information automatically and avoid unnecessary and unrelated information in EMR. However, limited resources of available EMR pose a great challenge for mining entity terms. Therefore, a multitask bi-directional RNN model is proposed here as a potential solution of data augmentation to enhance NER performance with limited data., Methods: A multitask bi-directional RNN model is proposed for extracting entity terms from Chinese EMR. The proposed model can be divided into a shared layer and a task specific layer. Firstly, vector representation of each word is obtained as a concatenation of word embedding and character embedding. Then Bi-directional RNN is used to extract context information from sentence. After that, all these layers are shared by two different task layers, namely the parts-of-speech tagging task layer and the named entity recognition task layer. These two tasks layers are trained alternatively so that the knowledge learned from named entity recognition task can be enhanced by the knowledge gained from parts-of-speech tagging task., Results: The performance of our proposed model has been evaluated in terms of micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in all cases. For instance, experimental results conducted on the discharge summaries show that the micro average F-score and the macro average F-score are improved by 2.41% point and 4.16% point, respectively, and the overall accuracy is improved by 5.66% point., Conclusions: In this paper, a novel multitask bi-directional RNN model is proposed for improving the performance of named entity recognition in EMR. Evaluation results using real datasets demonstrate the effectiveness of the proposed model.

Rural-urban disparity in China attracts special international attention in view of the imbalance of economic development between rural and urban areas. However, few studies used patient level data to explore the disparity of health outcomes between rural and urban patients. This study aims to evaluate the trend of health outcomes between rural and urban patients hospitalized with acute myocardial infarction (AMI) in China. Using an electronic medical records (EMRs) database in Shanxi, China, we identified 87,219 AMI patients hospitalized between 2013 and 2017. We used multivariable binary logistic regressions and two-part models to estimate the association between region of origin (rural/urban) and two outcomes, in-hospital mortality and out-of-pocket (OOP) expenses. Rural patients were associated with lower in-hospital mortality and the adjusted Odds Ratios (ORs) were 0.173, 0.34, 0.605, 0.522, 0.556 ( p -values < 0.001) from 2013 to 2017, respectively. For the OOP expenses, rural patients were experiencing increasing risk of having OOP expenses, with the ORs of 0.159, 0.573, 1.278, 1.281, 1.65. The coefficients for the log-linear models in the five years were 0.075 ( p = 0.352), 0.61, 0.565, 0.439, 0.46 ( p -values < 0.001). Policy makers in China should notice and narrow the gap of health outcomes between rural and urban patients.

Background and Objective: The application of medical knowledge strongly affects the performance of intelligent diagnosis, and method of learning the weights of medical knowledge plays a substantial role in probabilistic graphical models (PGMs). The purpose of this study is to investigate a discriminative weight-learning method based on a medical knowledge network (MKN)., Methods: We propose a training model called the maximum margin medical knowledge network (M 3 KN), which is strictly derived for calculating the weight of medical knowledge. Using the definition of a reasonable margin, the weight learning can be transformed into a margin optimization problem. To solve the optimization problem, we adopt a sequential minimal optimization (SMO) algorithm and the clique property of a Markov network. Ultimately, M 3 KN not only incorporates the inference ability of PGMs but also deals with high-dimensional logic knowledge., Results: The experimental results indicate that M 3 KN obtains a higher F-measure score than the maximum likelihood learning algorithm of MKN for both Chinese Electronic Medical Records (CEMRs) and Blood Examination Records (BERs). Furthermore, the proposed approach is obviously superior to some classical machine learning algorithms for medical diagnosis. To adequately manifest the importance of domain knowledge, we numerically verify that the diagnostic accuracy of M 3 KN is gradually improved as the number of learned CEMRs increase, which contain important medical knowledge., Conclusions: Our experimental results show that the proposed method performs reliably for learning the weights of medical knowledge. M 3 KN outperforms other existing methods by achieving an F-measure of 0.731 for CEMRs and 0.4538 for BERs. This further illustrates that M 3 KN can facilitate the investigations of intelligent healthcare., (Copyright © 2018 Elsevier B.V. All rights reserved.)

Introduction: Electronic medical records are increasingly common in medical practice. The secondary use of medical records has become increasingly important. It relies on the ability to retrieve the complete information about desired patient populations. How to effectively and accurately retrieve relevant medical records from large- scale medical big data is becoming a big challenge. Therefore, we propose an efficient and robust framework based on cloud for large-scale Traditional Chinese Medical Records (TCMRs) retrieval., Methods: We propose a parallel index building method and build a distributed search cluster, the former is used to improve the performance of index building, and the latter is used to provide high concurrent online TCMRs retrieval. Then, a real-time multi-indexing model is proposed to ensure the latest relevant TCMRs are indexed and retrieved in real-time, and a semantics-based query expansion method and a multi- factor ranking model are proposed to improve retrieval quality. Third, we implement a template-based visualization method for displaying medical reports., Results: The proposed parallel indexing method and distributed search cluster can improve the performance of index building and provide high concurrent online TCMRs retrieval. The multi-indexing model can ensure the latest relevant TCMRs are indexed and retrieved in real-time. The semantics expansion method and the multi-factor ranking model can enhance retrieval quality. The template-based visualization method can enhance the availability and universality, where the medical reports are displayed via friendly web interface., Conclusions: In conclusion, compared with the current medical record retrieval systems, our system provides some advantages that are useful in improving the secondary use of large-scale traditional Chinese medical records in cloud environment. The proposed system is more easily integrated with existing clinical systems and be used in various scenarios., (Copyright © 2017. Published by Elsevier Inc.)

De-identification, identifying and removing all protected health information (PHI) present in clinical data including electronic medical records (EMRs), is a critical step in making clinical data publicly available. The 2014 i2b2 (Center of Informatics for Integrating Biology and Bedside) clinical natural language processing (NLP) challenge sets up a track for de-identification (track 1). In this study, we propose a hybrid system based on both machine learning and rule approaches for the de-identification track. In our system, PHI instances are first identified by two (token-level and character-level) conditional random fields (CRFs) and a rule-based classifier, and then are merged by some rules. Experiments conducted on the i2b2 corpus show that our system submitted for the challenge achieves the highest micro F-scores of 94.64%, 91.24% and 91.63% under the "token", "strict" and "relaxed" criteria respectively, which is among top-ranked systems of the 2014 i2b2 challenge. After integrating some refined localization dictionaries, our system is further improved with F-scores of 94.83%, 91.57% and 91.95% under the "token", "strict" and "relaxed" criteria respectively., (Copyright © 2015 Elsevier Inc. All rights reserved.)