Estimation of optimal treatment regimes with electronic medical record data using the residual life value estimator.

Clinicians and patients must make treatment decisions at a series of key decision points throughout disease progression. A dynamic treatment regime is a set of sequential decision rules that return treatment decisions based on accumulating patient information, like that commonly found in electronic medical record (EMR) data. When applied to a patient population, an optimal treatment regime leads to the most favorable outcome on average. Identifying optimal treatment regimes that maximize residual life is especially desirable for patients with life-threatening diseases such as sepsis, a complex medical condition that involves severe infections with organ dysfunction. We introduce the residual life value estimator (ReLiVE), an estimator for the expected value of cumulative restricted residual life under a fixed treatment regime. Building on ReLiVE, we present a method for estimating an optimal treatment regime that maximizes expected cumulative restricted residual life. Our proposed method, ReLiVE-Q, conducts estimation via the backward induction algorithm Q-learning. We illustrate the utility of ReLiVE-Q in simulation studies, and we apply ReLiVE-Q to estimate an optimal treatment regime for septic patients in the intensive care unit using EMR data from the Multiparameter Intelligent Monitoring Intensive Care database. Ultimately, we demonstrate that ReLiVE-Q leverages accumulating patient information to estimate personalized treatment regimes that optimize a clinically meaningful function of residual life.

Clinical signatures of genetic epilepsies precede diagnosis in electronic medical records of 32,000 individuals.

PURPOSE: An early genetic diagnosis can guide the time-sensitive treatment of individuals with genetic epilepsies. However, most genetic diagnoses occur long after disease onset. We aimed to identify early clinical features suggestive of genetic diagnoses in individuals with epilepsy through large-scale analysis of full-text electronic medical records. METHODS: We extracted 89 million time-stamped standardized clinical annotations using Natural Language Processing from 4,572,783 clinical notes from 32,112 individuals with childhood epilepsy, including 1925 individuals with known or presumed genetic epilepsies. We applied these features to train random forest models to predict SCN1A-related disorders and any genetic diagnosis. RESULTS: We identified 47,774 age-dependent associations of clinical features with genetic etiologies a median of 3.6 years before molecular diagnosis. Across all 710 genetic etiologies identified in our cohort, neurodevelopmental differences between 6 to 9 months increased the likelihood of a later molecular diagnosis 5-fold (P < .0001, 95% CI = 3.55-7.42). A later diagnosis of SCN1A-related disorders (area under the curve [AUC] = 0.91) or an overall positive genetic diagnosis (AUC = 0.82) could be reliably predicted using random forest models. CONCLUSION: Clinical features predictive of genetic epilepsies precede molecular diagnoses by up to several years in conditions with known precision treatments. An earlier diagnosis facilitated by automated electronic medical records analysis has the potential for earlier targeted therapeutic strategies in the genetic epilepsies.

Advantages of a Data-Capture System with Video to Record Neonatal Resuscitation Interventions.

OBJECTIVE: To assess the completeness and accuracy of neonatal resuscitation documentation the electronic medical record (EMR) compared with a data-capture system including video. STUDY DESIGN: Retrospective observational study of 226 infants assessed for resuscitation at birth between April 2019 and October 2021 at Sharp Mary Birch Hospital, San Diego. Completeness was defined as the presence of documented resuscitative interventions in the EMR. We assessed the timing and frequency of interventions to determine the accuracy of the EMR documentation using video recordings as an objective record for comparison. Inaccuracy of EMR documentation was scored as missing (not documented), under-reported, or over-reported. RESULTS: Overall, the completeness of resuscitation interventions documented in the EMR was high (85%-100%), but the accuracy of documentation varied between 39% and 100% Modes of respiratory support were accurately captured in 96%-100% of the EMRs. Time to successful intubation (39%) and maximum fraction of inspired oxygen (47%) were the least accurately documented interventions in the EMR. Under-reporting of interventions with several events (eg, number of positive pressure ventilation events and intubation attempts) were also common errors in the EMR. CONCLUSIONS: The self-reported modes of respiratory support were accurately documented in the EMR, whereas the timing of interventions was inaccurate when compared with video recordings. The use of a video-capture system in the delivery room provided a more objective record of the timing of specific interventions during neonatal resuscitations.

Using linked electronic medical record-pharmacy data to examine lupus medication adherence: A retrospective cohort study.

INTRODUCTION: Medication nonadherence is common in systemic lupus erythematosus (SLE) and associated with morbidity and mortality. We explored the reliability of pharmacy data within the electronic medical record (EMR) to examine factors associated with nonadherence to SLE medications. METHODS: We included patients with SLE who were prescribed ≥1 SLE medication for ≥90 days. We compared two datasets of pharmacy fill data, one within the EMR and another from the vendor who obtained this information from pharmacies and prescription benefit managers. Adherence was defined by medication possession ratio (MPR) ≥80%. In addition to MPR for each SLE medication, we evaluated the weighted-average MPR and the proportion of patients adherent to ≥1 SLE medication and to all SLE medications. We used logistic regression to examine factors associated with adherence. RESULTS: Among 181 patients (median age 36, 96% female, 58% Black), 98% were prescribed hydroxychloroquine, 34% azathioprine, 33% mycophenolate, 18% methotrexate, and 7% belimumab. Among 1276 pharmacy records, 74% overlapped between linked EMR-pharmacy data and data obtained directly from the vendor. Only 9% were available from the vendor but not through linked EMR-pharmacy data. The weighted-average MPR was 57%; 45% were adherent to hydroxychloroquine, 46% to ≥1 SLE medication, and 32% to all SLE medications. Older age was associated with adherence in univariable and multivariable analyses. DISCUSSION: Our study showed that obtaining linked EMR-pharmacy data is feasible with minimal missing data and can be leveraged in future adherence research. Younger patients were more likely to be nonadherent and may benefit from targeted intervention.

Anomaly Detection and Correction in Dense Functional Data Within Electronic Medical Records.

In medical research, the accuracy of data from electronic medical records (EMRs) is critical, particularly when analyzing dense functional data, where anomalies can severely compromise research integrity. Anomalies in EMRs often arise from human errors in data measurement and entry, and increase in frequency with the volume of data. Despite the established methods in computer science, anomaly detection in medical applications remains underdeveloped. We address this deficiency by introducing a novel tool for identifying and correcting anomalies specifically in dense functional EMR data. Our approach utilizes studentized residuals from a mean-shift model, and therefore assumes that the data adheres to a smooth functional trajectory. Additionally, our method is tailored to be conservative, focusing on anomalies that signify actual errors in the data collection process while controlling for false discovery rates and type II errors. To support widespread implementation, we provide a comprehensive R package, ensuring that our methods can be applied in diverse settings. Our methodology's efficacy has been validated through rigorous simulation studies and real-world applications, confirming its ability to accurately identify and correct errors, thus enhancing the reliability and quality of medical data analysis.

Search Engines to Capture Missing Deaths From Institutional Data Warehouse.

INTRODUCTION: Clinical publications use mortality as a hard end point. It is unknown how many patient deaths are under-reported in institutional databases. The objective of this study was to query mortality in our patient cohort from our data warehouse and compare these deaths to those identified in different databases. METHODS: We passed the first/last name and date of birth of 134 patients through online mortality search engines (Find a Grave Index, US Cemetery and Funeral Home Collection, etc.) to assess their ability to capture patient deaths and compared that to deaths recorded from our institutional data warehouse. RESULTS: Our institutional data warehouse found approximately one-third of the total patient mortalities. After the Social Security Death Index, we found that the Find a Grave Index captured the most mortalities missed by the institutional data warehouse. These results highlight the advantages of incorporating readily available search engines into institutional data warehouses for the accurate collection of patient mortalities, particularly those that occur outside of index operative admission. CONCLUSIONS: The incorporation of the mortality search engines significantly augmented the capture of patient deaths. Our approach may be useful for tailored patient outreach and reporting mortalities with institutional data.

Characteristics associated with response to subcutaneously administered anti-CGRP monoclonal antibody medications in a real-world community cohort of persons living with migraine: A retrospective clinical and genetic study.

OBJECTIVE: To evaluate response to anti-calcitonin gene-related peptide (CGRP) migraine preventives in a real-world community cohort of persons living with migraine and to identify clinical and genetic characteristics associated with efficacious response. BACKGROUND: Erenumab-aooeb, fremanezumab-vrfm, and galcanezumab-gnlm target CGRP or its receptor; however, many patients are non-responsive. METHODS: In this retrospective clinical and genetic study, we identified 1077 adult patients who satisfied the International Classification of Headache Disorders, 3rd edition, criteria for migraine without aura, migraine with aura, or chronic migraine and who were prescribed an anti-CGRP migraine preventive between May 2018 and May 2021. Screening of 558 patients identified 289 with data at baseline and first follow-up visits; data were available for 161 patients at a second follow-up visit. The primary outcome was migraine days per month (MDM). In 198 genotyped patients, we evaluated associations between responders (i.e., patients with ≥50% reduction in MDM at follow-up) and genes involved in CGRP signaling or pharmacological response, and genetic and polygenic risk scores. RESULTS: The median time to first follow-up was 4.4 (0.9-22) months after preventive start. At the second follow-up, 5.7 (0.9-13) months later, 145 patients had continued on the same preventive. Preventives had strong, persistent effects in reducing MDM in responders (follow-up 1: η2 = 0.26, follow-up 2: η2 = 0.22). At the first but not second follow-up: galcanezumab had a larger effect than erenumab, while no difference was seen at either follow-up between galcanezumab and fremanezumab or fremanezumab and erenumab. The decrease in MDM at follow-up was generally proportional to baseline MDM, larger in females, and increased with months on medication. At the first follow-up only, patients with prior hospitalization for migraine or who had not responded to more preventive regimens had a smaller decrease in MDM. Reasons for stopping or switching a preventive varied between medications and were often related to cost and insurance coverage. At both follow-ups, patient tolerance (1: 92.2% [262/284]; 2: 95.2% [141/145]) and continued use (1: 77.5% [224/289]; 2: 80.6% [116/145]) were high and similar across preventives. Response consistency (always non-responders: 31.7% [46/145]; always responders: 56.5% [82/145], and one-time only responders: 11.7% [17/145]) was also similar across preventives. Non-responder status had nominally significant associations with rs12615320-G in RAMP1 (odds ratio [95% confidence interval]: 4.7 [1.5, 14.7]), and rs4680-A in COMT (0.6[0.4, 0.9]). Non-responders had a lower mean genetic risk score than responders (1.0 vs. 1.1; t(df) = -1.75(174.84), p = 0.041), and the fraction of responders increased with genetic and polygenic risk score percentile. CONCLUSIONS: In this real-world setting, anti-CGRP preventives reduced MDM persistently and had similar and large effect sizes on MDM reduction; however, clinical and genetic factors influenced response.

Efficacy and safety of a low-dose sulfamethoxazole/trimethoprim regimen in preventing pneumocystis pneumonia: A retrospective study using a large-scale electronic medical record database.

INTRODUCTION: Sulfamethoxazole/trimethoprim (ST) is a first-line drug for preventing pneumocystis pneumonia (PCP). Several small-scale studies have suggested the usefulness of the low-dose regimen of ST (200/40 mg/day) over the standard-dose one (400/80 mg/day). Thus, this study aimed to investigate the efficacy and safety of low-dose and standard-dose regimens of ST in preventing PCP in patients with non human immunodeficiency virus infection using a large-scale electronic medical record database. METHODS: This retrospective study included patients who received ST prophylaxis for PCP registered in the RWD database between June 2007 and February 2023. Patients received either standard-dose (400/80 mg/day) or low-dose (200/40 mg/day) regimen groups. The incidence of cases initiated PCP therapeutic dose (ci-PCPTD) (ST ≥ 3600/720 mg/day) and adverse events (AEs) was evaluated, and risk factors for ci-PCPTD were investigated. RESULTS: A total of 11,384 patients received the standard-dose, whereas 7973 received the low-dose regimen groups. No significant difference in the cumulative incidence of ci-PCPTD was observed between the standard-dose (0.67%) and low-dose regimen group (0.47%). Lung disease was a significant risk factor for ci-PCPTD. The cumulative incidence of ci-PCPTD in patients with acute exacerbation of interstitial pneumonia was 1.3% in both groups, and no significant difference was observed between the two groups. The low-dose regimen group had a lower incidence of all AEs than the standard-dose regimen group. CONCLUSION: These results based on a large-scale electronic medical record database provide important evidence supporting the clinical significance of low-dose regimen of ST.

Prediction of hospitalization and waiting time within 24 hours of emergency department patients with unstructured text data.

Overcrowding of emergency departments is a global concern, leading to numerous negative consequences. This study aimed to develop a useful and inexpensive tool derived from electronic medical records that supports clinical decision-making and can be easily utilized by emergency department physicians. We presented machine learning models that predicted the likelihood of hospitalizations within 24 hours and estimated waiting times. Moreover, we revealed the enhanced performance of these machine learning models compared to existing models by incorporating unstructured text data. Among several evaluated models, the extreme gradient boosting model that incorporated text data yielded the best performance. This model achieved an area under the receiver operating characteristic curve score of 0.922 and an area under the precision-recall curve score of 0.687. The mean absolute error revealed a difference of approximately 3 hours. Using this model, we classified the probability of patients not being admitted within 24 hours as Low, Medium, or High and identified important variables influencing this classification through explainable artificial intelligence. The model results are readily displayed on an electronic dashboard to support the decision-making of emergency department physicians and alleviate overcrowding, thereby resulting in socioeconomic benefits for medical facilities.

The long and the short of pediatric emergency department antibiotic prescribing: A retrospective observational study.

BACKGROUND: Most antibiotics prescribed to children are provided in the outpatient and emergency department (ED) settings, yet these prescribers are seldom engaged by antibiotic stewardship programs. We reviewed ED antibiotic prescriptions for three common infections to describe current prescribing practices. METHODS: Prescription data between 2018 and 2021 were extracted from the electronic records of children discharged from the Children's Hospital of Eastern Ontario ED with urinary tract infection (UTI), community acquired pneumonia (CAP), and acute otitis media ≥2 years of age (AOM). Antibiotic choice, duration, as well as the provider's time in practice and training background were collected. Antibiotic durations were compared with Canadian guideline recommendations to assess concordance. Provider-level prescribing practices were analyzed using k-means cluster analysis. RESULTS: 10,609 prescriptions were included: 2868 for UTI, 2958 for CAP, and 4783 for AOM. Guideline-concordant durations prescribed was generally high (UTI 84.9%, CAP 94.0%, AOM 52.8%), a large proportion of antibiotic-days prescribed were in excess of the minimally recommended duration for each infection (UTI 16.8%, 19.3%, AOM 25.5%). Cluster analysis yielded two clusters of prescribers, with those in one cluster more commonly prescribing durations at the lower end of recommended interval, and the others more commonly prescribing longer durations for all three infections reviewed. No statistically significant differences were found between clusters by career stage or training background. CONCLUSIONS: While guideline-concordant antibiotic prescribing was generally high, auditing antibiotic prescriptions identified shifting prescribing towards the minimally recommended duration as a potential opportunity to reduce antibiotic use among children for these infections.

The Minhang Pediatric Biobank cohort study: protocol overview and baseline characteristics.

BACKGROUND: Little has been done to establish biobanks for studying the environment and lifestyle risk factors for diseases among the school-age children. The Minhang Pediatric Biobank (MPB) cohort study aims to identify factors associated with health and diseases of school-aged children living in the urban or suburban area of Shanghai. METHODS: This population-based cohort study was started in all sub-districts/towns of Minhang district of Shanghai in 2014. First-grade students in elementary school were enrolled during the time of their routine physical examinations, with self-administered questionnaires completed by their primary caregivers. Additional information was extracted from multiple health information systems. Urine and saliva samples were collected during the baseline survey and follow-up visits. RESULTS: At the end of 2014 academic year, a total number of 8412 children and their parents were recruited, including 4339 boys and 4073 girls. All the participants completed the baseline survey and physical examination, and 7128 urine and 2767 saliva samples were collected. The five most prevalent childhood diseases in this population were dental caries, bronchitis, pneumonia, asthma and overweight/obese. CONCLUSIONS: The MPB cohort has been successfully established, serving as a useful platform for future research relating to the genetic, environmental and lifestyle risk factors for childhood diseases.

Strategies used to detect and mitigate system-related errors over time: A qualitative study in an Australian health district.

BACKGROUND: Electronic medical record (EMR) systems provide timely access to clinical information and have been shown to improve medication safety. However, EMRs can also create opportunities for error, including system-related errors or errors that were unlikely or not possible with the use of paper medication charts. This study aimed to determine the detection and mitigation strategies adopted by a health district in Australia to target system-related errors and to explore stakeholder views on strategies needed to curb future system-related errors from emerging. METHODS: A qualitative descriptive study design was used comprising semi-structured interviews. Data were collected from three hospitals within a health district in Sydney, Australia, between September 2020 and May 2021. Interviews were conducted with EMR users and other key stakeholders (e.g. clinical informatics team members). Participants were asked to reflect on how system-related errors changed over time, and to describe approaches taken by their organisation to detect and mitigate these errors. Thematic analysis was conducted iteratively using a general inductive approach, where codes were assigned as themes emerged from the data. RESULTS: Interviews were conducted with 25 stakeholders. Participants reported that most system-related errors were detected by front-line clinicians. Following error detection, clinicians either reported system-related errors directly to the clinical informatics team or submitted reports to the incident information management system. System-related errors were also reported to be detected via reports run within the EMR, or during organisational processes such as incident investigations or system enhancement projects. EMR redesign was the main approach described by participants for mitigating system-related errors, however other strategies, like regular user education and minimising the use of hybrid systems, were also reported. CONCLUSIONS: Initial detection of system-related errors relies heavily on front-line clinicians, however other organisational strategies that are proactive and layered can improve the systemic detection, investigation, and management of errors. Together with EMR design changes, complementary error mitigation strategies, including targeted staff education, can support safe EMR use and development.

Development and validation of an electronic health record-based algorithm for identifying TBI in the VA: A VA Million Veteran Program study.

The purpose of this study was to develop and validate an algorithm for identifying Veterans with a history of traumatic brain injury (TBI) in the Veterans Affairs (VA) electronic health record using VA Million Veteran Program (MVP) data. Manual chart review (n = 200) was first used to establish 'gold standard' diagnosis labels for TBI ('Yes TBI' vs. 'No TBI'). To develop our algorithm, we used PheCAP, a semi-supervised pipeline that relied on the chart review diagnosis labels to train and create a prediction model for TBI. Cross-validation was used to train and evaluate the proposed algorithm, 'TBI-PheCAP.' TBI-PheCAP performance was compared to existing TBI algorithms and phenotyping methods, and the final algorithm was run on all MVP participants (n = 702,740) to assign a predicted probability for TBI and a binary classification status choosing specificity = 90%. The TBI-PheCAP algorithm had an area under the receiver operating characteristic curve of 0.92, sensitivity of 84%, and positive predictive value (PPV) of 98% at specificity = 90%. TBI-PheCAP generally performed better than other classification methods, with equivalent or higher sensitivity and PPV than existing rules-based TBI algorithms and MVP TBI-related survey data. Given its strong classification metrics, the TBI-PheCAP algorithm is recommended for use in future population-based TBI research.

Effective Privacy Protection Strategies for Pregnancy and Gestation Information From Electronic Medical Records: Retrospective Study in a National Health Care Data Network in China.

BACKGROUND: Pregnancy and gestation information is routinely recorded in electronic medical record (EMR) systems across China in various data sets. The combination of data on the number of pregnancies and gestations can imply occurrences of abortions and other pregnancy-related issues, which is important for clinical decision-making and personal privacy protection. However, the distribution of this information inside EMR is variable due to inconsistent IT structures across different EMR systems. A large-scale quantitative evaluation of the potential exposure of this sensitive information has not been previously performed, ensuring the protection of personal information is a priority, as emphasized in Chinese laws and regulations. OBJECTIVE: This study aims to perform the first nationwide quantitative analysis of the identification sites and exposure frequency of sensitive pregnancy and gestation information. The goal is to propose strategies for effective information extraction and privacy protection related to women's health. METHODS: This study was conducted in a national health care data network. Rule-based protocols for extracting pregnancy and gestation information were developed by a committee of experts. A total of 6 different sub-data sets of EMRs were used as schemas for data analysis and strategy proposal. The identification sites and frequencies of identification in different sub-data sets were calculated. Manual quality inspections of the extraction process were performed by 2 independent groups of reviewers on 1000 randomly selected records. Based on these statistics, strategies for effective information extraction and privacy protection were proposed. RESULTS: The data network covered hospitalized patients from 19 hospitals in 10 provinces of China, encompassing 15,245,055 patients over an 11-year period (January 1, 2010-December 12, 2020). Among women aged 14-50 years, 70% were randomly selected from each hospital, resulting in a total of 1,110,053 patients. Of these, 688,268 female patients with sensitive reproductive information were identified. The frequencies of identification were variable, with the marriage history in admission medical records being the most frequent at 63.24%. Notably, more than 50% of female patients were identified with pregnancy and gestation history in nursing records, which is not generally considered a sub-data set rich in reproductive information. During the manual curation and review process, 1000 cases were randomly selected, and the precision and recall rates of the information extraction method both exceeded 99.5%. The privacy-protection strategies were designed with clear technical directions. CONCLUSIONS: Significant amounts of critical information related to women's health are recorded in Chinese routine EMR systems and are distributed in various parts of the records with different frequencies. This requires a comprehensive protocol for extracting and protecting the information, which has been demonstrated to be technically feasible. Implementing a data-based strategy will enhance the protection of women's privacy and improve the accessibility of health care services.

Evaluating a Natural Language Processing-Driven, AI-Assisted International Classification of Diseases, 10th Revision, Clinical Modification, Coding System for Diagnosis Related Groups in a Real Hospital Environment: Algorithm Development and Validation Study.

BACKGROUND: International Classification of Diseases codes are widely used to describe diagnosis information, but manual coding relies heavily on human interpretation, which can be expensive, time consuming, and prone to errors. With the transition from the International Classification of Diseases, Ninth Revision, to the International Classification of Diseases, Tenth Revision (ICD-10), the coding process has become more complex, highlighting the need for automated approaches to enhance coding efficiency and accuracy. Inaccurate coding can result in substantial financial losses for hospitals, and a precise assessment of outcomes generated by a natural language processing (NLP)-driven autocoding system thus assumes a critical role in safeguarding the accuracy of the Taiwan diagnosis related groups (Tw-DRGs). OBJECTIVE: This study aims to evaluate the feasibility of applying an International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM), autocoding system that can automatically determine diagnoses and codes based on free-text discharge summaries to facilitate the assessment of Tw-DRGs, specifically principal diagnosis and major diagnostic categories (MDCs). METHODS: By using the patient discharge summaries from Kaohsiung Medical University Chung-Ho Memorial Hospital (KMUCHH) from April 2019 to December 2020 as a reference data set we developed artificial intelligence (AI)-assisted ICD-10-CM coding systems based on deep learning models. We constructed a web-based user interface for the AI-assisted coding system and deployed the system to the workflow of the certified coding specialists (CCSs) of KMUCHH. The data used for the assessment of Tw-DRGs were manually curated by a CCS with the principal diagnosis and MDC was determined from discharge summaries collected at KMUCHH from February 2023 to April 2023. RESULTS: Both the reference data set and real hospital data were used to assess performance in determining ICD-10-CM coding, principal diagnosis, and MDC for Tw-DRGs. Among all methods, the GPT-2 (OpenAI)-based model achieved the highest F1-score, 0.667 (F1-score 0.851 for the top 50 codes), on the KMUCHH test set and a slightly lower F1-score, 0.621, in real hospital data. Cohen κ evaluation for the agreement of MDC between the models and the CCS revealed that the overall average κ value for GPT-2 (κ=0.714) was approximately 12.2 percentage points higher than that of the hierarchy attention network (κ=0.592). GPT-2 demonstrated superior agreement with the CCS across 6 categories of MDC, with an average κ value of approximately 0.869 (SD 0.033), underscoring the effectiveness of the developed AI-assisted coding system in supporting the work of CCSs. CONCLUSIONS: An NLP-driven AI-assisted coding system can assist CCSs in ICD-10-CM coding by offering coding references via a user interface, demonstrating the potential to reduce the manual workload and expedite Tw-DRG assessment. Consistency in performance affirmed the effectiveness of the system in supporting CCSs in ICD-10-CM coding and the judgment of Tw-DRGs.

The Impact of Digital Hospitals on Patient and Clinician Experience: Systematic Review and Qualitative Evidence Synthesis.

BACKGROUND: The digital transformation of health care is advancing rapidly. A well-accepted framework for health care improvement is the Quadruple Aim: improved clinician experience, improved patient experience, improved population health, and reduced health care costs. Hospitals are attempting to improve care by using digital technologies, but the effectiveness of these technologies is often only measured against cost and quality indicators, and less is known about the clinician and patient experience. OBJECTIVE: This study aims to conduct a systematic review and qualitative evidence synthesis to assess the clinician and patient experience of digital hospitals. METHODS: The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and ENTREQ (Enhancing the Transparency in Reporting the Synthesis of Qualitative Research) guidelines were followed. The PubMed, Embase, Scopus, CINAHL, and PsycINFO databases were searched from January 2010 to June 2022. Studies that explored multidisciplinary clinician or adult inpatient experiences of digital hospitals (with a full electronic medical record) were included. Study quality was assessed using the Mixed Methods Appraisal Tool. Data synthesis was performed narratively for quantitative studies. Qualitative evidence synthesis was performed via (1) automated machine learning text analytics using Leximancer (Leximancer Pty Ltd) and (2) researcher-led inductive synthesis to generate themes. RESULTS: A total of 61 studies (n=39, 64% quantitative; n=15, 25% qualitative; and n=7, 11% mixed methods) were included. Most studies (55/61, 90%) investigated clinician experiences, whereas few (10/61, 16%) investigated patient experiences. The study populations ranged from 8 to 3610 clinicians, 11 to 34,425 patients, and 5 to 2836 hospitals. Quantitative outcomes indicated that clinicians had a positive overall satisfaction (17/24, 71% of the studies) with digital hospitals, and most studies (11/19, 58%) reported a positive sentiment toward usability. Data accessibility was reported positively, whereas adaptation, clinician-patient interaction, and workload burnout were reported negatively. The effects of digital hospitals on patient safety and clinicians' ability to deliver patient care were mixed. The qualitative evidence synthesis of clinician experience studies (18/61, 30%) generated 7 themes: inefficient digital documentation, inconsistent data quality, disruptions to conventional health care relationships, acceptance, safety versus risk, reliance on hybrid (digital and paper) workflows, and patient data privacy. There was weak evidence of a positive association between digital hospitals and patient satisfaction scores. CONCLUSIONS: Clinicians' experience of digital hospitals appears positive according to high-level indicators (eg, overall satisfaction and data accessibility), but the qualitative evidence synthesis revealed substantive tensions. There is insufficient evidence to draw a definitive conclusion on the patient experience within digital hospitals, but indications appear positive or agnostic. Future research must prioritize equitable investigation and definition of the digital clinician and patient experience to achieve the Quadruple Aim of health care.

Development of a quantitative index system for evaluating the quality of electronic medical records in disease risk intelligent prediction.

OBJECTIVE: This study aimed to develop and validate a quantitative index system for evaluating the data quality of Electronic Medical Records (EMR) in disease risk prediction using Machine Learning (ML). MATERIALS AND METHODS: The index system was developed in four steps: (1) a preliminary index system was outlined based on literature review; (2) we utilized the Delphi method to structure the indicators at all levels; (3) the weights of these indicators were determined using the Analytic Hierarchy Process (AHP) method; and (4) the developed index system was empirically validated using real-world EMR data in a ML-based disease risk prediction task. RESULTS: The synthesis of review findings and the expert consultations led to the formulation of a three-level index system with four first-level, 11 second-level, and 33 third-level indicators. The weights of these indicators were obtained through the AHP method. Results from the empirical analysis illustrated a positive relationship between the scores assigned by the proposed index system and the predictive performances of the datasets. DISCUSSION: The proposed index system for evaluating EMR data quality is grounded in extensive literature analysis and expert consultation. Moreover, the system's high reliability and suitability has been affirmed through empirical validation. CONCLUSION: The novel index system offers a robust framework for assessing the quality and suitability of EMR data in ML-based disease risk predictions. It can serve as a guide in building EMR databases, improving EMR data quality control, and generating reliable real-world evidence.

Predictive model and risk analysis for coronary heart disease in people living with HIV using machine learning.

OBJECTIVE: This study aimed to construct a coronary heart disease (CHD) risk-prediction model in people living with human immunodeficiency virus (PLHIV) with the help of machine learning (ML) per electronic medical records (EMRs). METHODS: Sixty-one medical characteristics (including demography information, laboratory measurements, and complicating disease) readily available from EMRs were retained for clinical analysis. These characteristics further aided the development of prediction models by using seven ML algorithms [light gradient-boosting machine (LightGBM), support vector machine (SVM), eXtreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), decision tree, multilayer perceptron (MLP), and logistic regression]. The performance of this model was assessed using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was further applied to interpret the findings of the best-performing model. RESULTS: The LightGBM model exhibited the highest AUC (0.849; 95% CI, 0.814-0.883). Additionally, the SHAP plot per the LightGBM depicted that age, heart failure, hypertension, glucose, serum creatinine, indirect bilirubin, serum uric acid, and amylase can help identify PLHIV who were at a high or low risk of developing CHD. CONCLUSION: This study developed a CHD risk prediction model for PLHIV utilizing ML techniques and EMR data. The LightGBM model exhibited improved comprehensive performance and thus had higher reliability in assessing the risk predictors of CHD. Hence, it can potentially facilitate the development of clinical management techniques for PLHIV care in the era of EMRs.

Differences in changes of data completeness after the implementation of an electronic medical record in three surgical departments of a German hospital-a longitudinal comparative document analysis.

PURPOSE: The European health data space promises an efficient environment for research and policy-making. However, this data space is dependent on high data quality. The implementation of electronic medical record systems has a positive impact on data quality, but improvements are not consistent across empirical studies. This study aims to analyze differences in the changes of data quality and to discuss these against distinct stages of the electronic medical record's adoption process. METHODS: Paper-based and electronic medical records from three surgical departments were compared, assessing changes in data quality after the implementation of an electronic medical record system. Data quality was operationalized as completeness of documentation. Ten information that must be documented in both record types (e.g. vital signs) were coded as 1 if they were documented, otherwise as 0. Chi-Square-Tests were used to compare percentage completeness of these ten information and t-tests to compare mean completeness per record type. RESULTS: A total of N = 659 records were analyzed. Overall, the average completeness improved in the electronic medical record, with a change from 6.02 (SD = 1.88) to 7.2 (SD = 1.77). At the information level, eight information improved, one deteriorated and one remained unchanged. At the level of departments, changes in data quality show expected differences. CONCLUSION: The study provides evidence that improvements in data quality could depend on the process how the electronic medical record is adopted in the affected department. Research is needed to further improve data quality through implementing new electronical medical record systems or updating existing ones.

Measuring Emergency Department Workload Perception Using Electronic Medical Record Measures of Patient Volume and Acuity.

BACKGROUND: Workload in the emergency department (ED) fluctuates and there is no established model for measurement of clinician-level ED workload. OBJECTIVE: The aim of this study was to measure perceived ED workload and assess the relationship between perceived workload and objective measures of workload from the electronic medical record (EMR). METHODS: This study was conducted at a tertiary care, academic ED from July 1, 2020 through April 13, 2021. Attending workload perceptions were collected using a 5-point scale in three care areas with variable acuity. We collected eight EMR measures thought to correlate with perceived workload. EMR values were compared across areas of the department using ANOVA and correlated with attending workload ratings using linear regression. RESULTS: We collected 315 unique workload ratings, which were normally distributed. For the entire department, there was a weak positive correlation between reported workload perception and mean percentage of inpatient admissions (r = 0.23; p < 0.001), intensive care unit admissions (r = 0.2; p < 0.001), patient arrivals per shift (r = 0.14; p = 0.017), critical care billed visits (r = 0.22; p < 0.001), cardiopulmonary resuscitation code activations (r = 0.2; p < 0.001), and level 5 visits (r = 0.13; p = 0.02). There was weak negative correlation for ED discharges (r = -0.23; p < 0.001). Several correlations were stronger in individual care areas, including percent admissions in the lowest-acuity area (r = 0.43; p = 0.033) and patient arrivals in the highest-acuity area (r = 0.44; p < .01). No significant correlation was found in any area for observation admissions or trauma activations. CONCLUSIONS: In this study, EMR measures of workload were not closely correlated with ED attending physician workload perception. Future study should examine additional factors contributing to physician workload outside of the EMR.