Design of Interoperable Electronic Health Record (EHR) Application for Early Detection of Lung Diseases Using a Decision Support System by Expanding Deep Learning Techniques.

Background: Electronic health records (EHRs) are live, digital patient records that provide a thorough overview of a person's complete health data. Electronic health records (EHRs) provide better healthcare decisions and evidence-based patient treatment and track patients' clinical development. The EHR offers a new range of opportunities for analyzing and contrasting exam findings and other data, creating a proper information management mechanism to boost effectiveness, quick resolutions, and identifications. Aim: The aim of this studywas to implement an interoperable EHR system to improve the quality of care through the decision support system for the identification of lung cancer in its early stages. Objective: The main objective of the proposed system was to develop an Android application for maintaining an EHR system and decision support system using deep learning for the early detection of diseases. The second objective was to study the early stages of lung disease to predict/detect it using a decision support system. Methods: To extract the EHR data of patients, an android application was developed. The android application helped in accumulating the data of each patient. The accumulated data were used to create a decision support system for the early prediction of lung cancer. To train, test, and validate the prediction of lung cancer, a few samples from the ready dataset and a few data from patients were collected. The valid data collection from patients included an age range of 40 to 70, and both male and female patients. In the process of experimentation, a total of 316 images were considered. The testing was done by considering the data set into 80:20 partitions. For the evaluation purpose, a manual classification was done for 3 different diseases, such as large cell carcinoma, adenocarcinoma, and squamous cell carcinoma diseases in lung cancer detection. Results: The first model was tested for interoperability constraints of EHR with data collection and updations. When it comes to the disease detection system, lung cancer was predicted for large cell carcinoma, adenocarcinoma, and squamous cell carcinoma type by considering 80:20 training and testing ratios. Among the considered 336 images, the prediction of large cell carcinoma was less compared to adenocarcinoma and squamous cell carcinoma. The analysis also showed that large cell carcinoma occurred majorly in males due to smoking and was found as breast cancer in females. Conclusion: As the challenges are increasing daily in healthcare industries, a secure, interoperable EHR could help patients and doctors access patient data efficiently and effectively using an Android application. Therefore, a decision support system using a deep learning model was attempted and successfully used for disease detection. Early disease detection for lung cancer was evaluated, and the model achieved an accuracy of 93%. In future work, the integration of EHR data can be performed to detect various diseases early.

Transforming Primary Care Data Into the Observational Medical Outcomes Partnership Common Data Model: Development and Usability Study.

Background: Patient-monitoring software generates a large amount of data that can be reused for clinical audits and scientific research. The Observational Health Data Sciences and Informatics (OHDSI) consortium developed the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) to standardize electronic health record data and promote large-scale observational and longitudinal research. Objective: This study aimed to transform primary care data into the OMOP CDM format. Methods: We extracted primary care data from electronic health records at a multidisciplinary health center in Wattrelos, France. We performed structural mapping between the design of our local primary care database and the OMOP CDM tables and fields. Local French vocabularies concepts were mapped to OHDSI standard vocabularies. To validate the implementation of primary care data into the OMOP CDM format, we applied a set of queries. A practical application was achieved through the development of a dashboard. Results: Data from 18,395 patients were implemented into the OMOP CDM, corresponding to 592,226 consultations over a period of 20 years. A total of 18 OMOP CDM tables were implemented. A total of 17 local vocabularies were identified as being related to primary care and corresponded to patient characteristics (sex, location, year of birth, and race), units of measurement, biometric measures, laboratory test results, medical histories, and drug prescriptions. During semantic mapping, 10,221 primary care concepts were mapped to standard OHDSI concepts. Five queries were used to validate the OMOP CDM by comparing the results obtained after the completion of the transformations with the results obtained in the source software. Lastly, a prototype dashboard was developed to visualize the activity of the health center, the laboratory test results, and the drug prescription data. Conclusions: Primary care data from a French health care facility have been implemented into the OMOP CDM format. Data concerning demographics, units, measurements, and primary care consultation steps were already available in OHDSI vocabularies. Laboratory test results and drug prescription data were mapped to available vocabularies and structured in the final model. A dashboard application provided health care professionals with feedback on their practice.

Social Determinants of Health Phenotypes and Cardiometabolic Condition Prevalence Among Patients in a Large Academic Health System: Latent Class Analysis.

Background: Adverse social determinants of health (SDoH) have been associated with cardiometabolic disease; however, disparities in cardiometabolic outcomes are rarely the result of a single risk factor. Objective: This study aimed to identify and characterize SDoH phenotypes based on patient-reported and neighborhood-level data from the institutional electronic medical record and evaluate the prevalence of diabetes, obesity, and other cardiometabolic diseases by phenotype status. Methods: Patient-reported SDoH were collected (January to December 2020) and neighborhood-level social vulnerability, neighborhood socioeconomic status, and rurality were linked via census tract to geocoded patient addresses. Diabetes status was coded in the electronic medical record using International Classification of Diseases codes; obesity was defined using measured BMI ≥30 kg/m2. Latent class analysis was used to identify clusters of SDoH (eg, phenotypes); we then examined differences in the prevalence of cardiometabolic conditions based on phenotype status using prevalence ratios (PRs). Results: Complete data were available for analysis for 2380 patients (mean age 53, SD 16 years; n=1405, 59% female; n=1198, 50% non-White). Roughly 8% (n=179) reported housing insecurity, 30% (n=710) reported resource needs (food, health care, or utilities), and 49% (n=1158) lived in a high-vulnerability census tract. We identified 3 patient SDoH phenotypes: (1) high social risk, defined largely by self-reported SDoH (n=217, 9%); (2) adverse neighborhood SDoH (n=1353, 56%), defined largely by adverse neighborhood-level measures; and (3) low social risk (n=810, 34%), defined as low individual- and neighborhood-level risks. Patients with an adverse neighborhood SDoH phenotype had higher prevalence of diagnosed type 2 diabetes (PR 1.19, 95% CI 1.06-1.33), hypertension (PR 1.14, 95% CI 1.02-1.27), peripheral vascular disease (PR 1.46, 95% CI 1.09-1.97), and heart failure (PR 1.46, 95% CI 1.20-1.79). Conclusions: Patients with the adverse neighborhood SDoH phenotype had higher prevalence of poor cardiometabolic conditions compared to phenotypes determined by individual-level characteristics, suggesting that neighborhood environment plays a role, even if individual measures of socioeconomic status are not suboptimal.

A GPT-based EHR modeling system for unsupervised novel disease detection.

OBJECTIVE: To develop an Artificial Intelligence (AI)-based anomaly detection model as a complement of an "astute physician" in detecting novel disease cases in a hospital and preventing emerging outbreaks. METHODS: Data included hospitalized patients (n = 120,714) at a safety-net hospital in Massachusetts. A novel Generative Pre-trained Transformer (GPT)-based clinical anomaly detection system was designed and further trained using Empirical Risk Minimization (ERM), which can model a hospitalized patient's Electronic Health Records (EHR) and detect atypical patients. Methods and performance metrics, similar to the ones behind the recent Large Language Models (LLMs), were leveraged to capture the dynamic evolution of the patient's clinical variables and compute an Out-Of-Distribution (OOD) anomaly score. RESULTS: In a completely unsupervised setting, hospitalizations for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) infection could have been predicted by our GPT model at the beginning of the COVID-19 pandemic, with an Area Under the Receiver Operating Characteristic Curve (AUC) of 92.2 %, using 31 extracted clinical variables and a 3-day detection window. Our GPT achieves individual patient-level anomaly detection and mortality prediction AUC of 78.3 % and 94.7 %, outperforming traditional linear models by 6.6 % and 9 %, respectively. Different types of clinical trajectories of a SARS-CoV-2 infection are captured by our model to make interpretable detections, while a trend of over-pessimistic outcome prediction yields a more effective detection pathway. Furthermore, our comprehensive GPT model can potentially assist clinicians with forecasting patient clinical variables and developing personalized treatment plans. CONCLUSION: This study demonstrates that an emerging outbreak can be accurately detected within a hospital, by using a GPT to model patient EHR time sequences and labeling them as anomalous when actual outcomes are not supported by the model. Such a GPT is also a comprehensive model with the functionality of generating future patient clinical variables, which can potentially assist clinicians in developing personalized treatment plans.

Enhancing Clinical Relevance of Pretrained Language Models Through Integration of External Knowledge: Case Study on Cardiovascular Diagnosis From Electronic Health Records.

BACKGROUND: Despite their growing use in health care, pretrained language models (PLMs) often lack clinical relevance due to insufficient domain expertise and poor interpretability. A key strategy to overcome these challenges is integrating external knowledge into PLMs, enhancing their adaptability and clinical usefulness. Current biomedical knowledge graphs like UMLS (Unified Medical Language System), SNOMED CT (Systematized Medical Nomenclature for Medicine-Clinical Terminology), and HPO (Human Phenotype Ontology), while comprehensive, fail to effectively connect general biomedical knowledge with physician insights. There is an equally important need for a model that integrates diverse knowledge in a way that is both unified and compartmentalized. This approach not only addresses the heterogeneous nature of domain knowledge but also recognizes the unique data and knowledge repositories of individual health care institutions, necessitating careful and respectful management of proprietary information. OBJECTIVE: This study aimed to enhance the clinical relevance and interpretability of PLMs by integrating external knowledge in a manner that respects the diversity and proprietary nature of health care data. We hypothesize that domain knowledge, when captured and distributed as stand-alone modules, can be effectively reintegrated into PLMs to significantly improve their adaptability and utility in clinical settings. METHODS: We demonstrate that through adapters, small and lightweight neural networks that enable the integration of extra information without full model fine-tuning, we can inject diverse sources of external domain knowledge into language models and improve the overall performance with an increased level of interpretability. As a practical application of this methodology, we introduce a novel task, structured as a case study, that endeavors to capture physician knowledge in assigning cardiovascular diagnoses from clinical narratives, where we extract diagnosis-comment pairs from electronic health records (EHRs) and cast the problem as text classification. RESULTS: The study demonstrates that integrating domain knowledge into PLMs significantly improves their performance. While improvements with ClinicalBERT are more modest, likely due to its pretraining on clinical texts, BERT (bidirectional encoder representations from transformer) equipped with knowledge adapters surprisingly matches or exceeds ClinicalBERT in several metrics. This underscores the effectiveness of knowledge adapters and highlights their potential in settings with strict data privacy constraints. This approach also increases the level of interpretability of these models in a clinical context, which enhances our ability to precisely identify and apply the most relevant domain knowledge for specific tasks, thereby optimizing the model's performance and tailoring it to meet specific clinical needs. CONCLUSIONS: This research provides a basis for creating health knowledge graphs infused with physician knowledge, marking a significant step forward for PLMs in health care. Notably, the model balances integrating knowledge both comprehensively and selectively, addressing the heterogeneous nature of medical knowledge and the privacy needs of health care institutions.

Five-Feature Models to Predict Preeclampsia Onset Time From Electronic Health Record Data: Development and Validation Study.

BACKGROUND:  Preeclampsia is a potentially fatal complication during pregnancy, characterized by high blood pressure and the presence of excessive proteins in the urine. Due to its complexity, the prediction of preeclampsia onset is often difficult and inaccurate. OBJECTIVE:  This study aimed to create quantitative models to predict the onset gestational age of preeclampsia using electronic health records. METHODS:  We retrospectively collected 1178 preeclamptic pregnancy records from the University of Michigan Health System as the discovery cohort, and 881 records from the University of Florida Health System as the validation cohort. We constructed 2 Cox-proportional hazards models: 1 baseline model using maternal and pregnancy characteristics, and the other full model with additional laboratory findings, vitals, and medications. We built the models using 80% of the discovery data, tested the remaining 20% of the discovery data, and validated with the University of Florida data. We further stratified the patients into high- and low-risk groups for preeclampsia onset risk assessment. RESULTS:  The baseline model reached Concordance indices of 0.64 and 0.61 in the 20% testing data and the validation data, respectively, while the full model increased these Concordance indices to 0.69 and 0.61, respectively. For preeclampsia diagnosed at 34 weeks, the baseline and full models had area under the curve (AUC) values of 0.65 and 0.70, and AUC values of 0.69 and 0.70 for preeclampsia diagnosed at 37 weeks, respectively. Both models contain 5 selective features, among which the number of fetuses in the pregnancy, hypertension, and parity are shared between the 2 models with similar hazard ratios and significant P values. In the full model, maximum diastolic blood pressure in early pregnancy was the predominant feature. CONCLUSIONS:  Electronic health records data provide useful information to predict the gestational age of preeclampsia onset. Stratification of the cohorts using 5-predictor Cox-proportional hazards models provides clinicians with convenient tools to assess the onset time of preeclampsia in patients.

Evaluation of technical approaches for real-time data transfer from electronic health record systems.

BACKGROUND AND OBJECTIVE: Real-time data (RTD) are data that are delivered immediately after creation. The key feature of RTD is low delivery latency. Information systems in health care are extremely time-sensitive and their building block is the electronic health record (EHR). Real-time data from EHRs play an important role to support decision-making, analytics and coordination of care. This is well mentioned in the literature, but the process has not yet been described, providing reference implementations and testing. Real-time data delivery can technically be achieved using several methods. The objective of this work is to evaluate the performance of different transfer methods of RTD from EHRs by measuring delivery latency. METHODS: In our work we used four approaches to transfer RTD from EHRs: REST hooks, WebSocket notifications, reverse proxy and database triggers. We deployed a Fast Health Interoperability Resources (FHIR) server as it is one of the most widely used EHR standard. For the reference implementations we used Python and Golang. Delivery latency was selected as performance metric, derived by subtracting the timestamp of the EHR resource creation from the timestamp of the EHR resource receipt in millisecond. The data was analyzed using descriptive statistics, cumulative distribution function (CDF), Kruskal-Wallis and post-hoc tests. RESULTS: The database trigger approach had the best mean delivery latency 13.52±5.56 ms, followed by the reverse proxy 14.43±4.58 ms, REST hooks 19.26±5.76 ms and WebSocket 27.32±9.44 ms. The reverse proxy showed a tighter range of the values and lower variability. There were significant differences in the latencies between all pairs of approaches, except for reverse proxy and database trigger. CONCLUSION: Real-time data transfer is vital for the development of robust and innovative healthcare applications. Properties of current EHR systems as a data source predefine the approaches for transfer. In our work for the first time the performance of RTD transfer from the EHRs with reference implementations is measured and evaluated. We found that database triggers achieve lowest delivery latency. Reverse proxy performed slightly slower, but offered more stability, followed by REST hooks and WebSocket notifications.

Digital Documentation in Healthcare: Empowering Nurses and Patients for Optimal Care.

In response to challenges associated with extensive documentation practices within the NHS, this paper presents the outcomes of a structured brainstorming session as part of the Chief Nurse Fellows project titled 'Digital Documentation in Healthcare: Empowering Nurses and Patients for Optimal Care." Grounded in Dr. Rozzano Locsin's theory of "Technological Competency as Caring in Nursing," this project leverages a Venn diagram framework to integrate Digital Maturity Assessment (DMA) results with the "What Good Looks Like" (WGLL) Framework, the ANCC Pathway to Excellence, and the eHospital EPR program vision of University Hospitals of Leicester NHS Trust. Participants, including Clinical IT facilitators and nursing leaders, engaged in identifying synergies and gaps across digital proficiency, nursing excellence, and patient-centric care, contributing actionable insights towards an optimized digital patient care model. The findings emphasize the need for holistic digital solutions that enhance documentation efficiency, support staff excellence, and improve patient outcomes.

Academic-Practice Partnerships, EHR in Nursing Curriculum, and the Value Equation.

Workforce well-being and associated factors such as burnout, depression and documentation burden, have been identified as the highest concerns to be addressed. In academia, the new essentials of nursing practice including domain 8 for informatics and healthcare technology have become a focus for curricular revisions/enhancements. Our study focused on technology skills by using the technology of an academic EHR to measure baselines and progression of EHR use, sense of confidence, documentation competency, and post-graduation employer-based performance assessment. We provide results of an ongoing 1.5-year study and overarching strategy for university-wide deployment and financing.

Trial of Converting Nursing Records into Simplified and Structured Information Utilizing ChatGPT-3.5.

In Japan, the excessive length of time required for nursing records has become a social problem. A shift to concise "bulleted" records is needed to apply speech recognition and to work with foreign caregivers. Therefore, using 96,000 descriptively described anonymized nursing records, we identified typical situations for each information source and attempted to convert them to "bulleted" records using ChatGPT-3.5(For return from the operating room, Status on return, Temperature control, Blood drainage, Stoma care, Monitoring, Respiration and Oxygen, Sensation and pain, etc.). The results showed that ChatGPT-3.5 has some usable functionality as a tool for extracting keywords in "bulleted" records. Furthermore, through the process of converting to a "bulleted" record, it became clear that the transition to a standardized nursing record utilizing the "Standard Terminology for Nursing Observation and Action (STerNOA)" would be facilitated.

Impact of EHRs on Nursing Burnout in a Hospital Setting in Saudi Arabia: Mixed-Methods Study.

This study explores the association between nursing burnout and Electronic Health Record (EHR) use in a Saudi Arabian hospital adopting an advanced EHR system. Utilising a mixed-methods approach, the research combines quantitative analysis of 282 survey responses and qualitative interviews from 21 registered nurses. Despite high EHR acceptance, negative perceptions and stress related to EHR use were identified. Findings indicate a weak link between EHR use and burnout, with resilience acting as a mitigating factor. Specific stressors, including documentation workload and usability issues, were countered by individual and organisational resilience. The study introduces a novel conceptual model emphasising the pivotal role of resilience at both levels in mitigating EHR-related burnout. Recommendations include fostering resilience-building strategies in EHR implementation processes and usability to prevent burnout, emphasising self-care practices, promoting work-life balance, and improving health information infrastructure.

Navigating Alert Fatigue: A Case Study in Electronic Health Record Alert Design Optimization.

Clinical decision support (CDS) systems play a crucial role in enhancing patient outcomes, but inadequate design contributes to alert fatigue, inundating clinicians with disruptive alerts that lack clinical relevance. This case study delves into a quality improvement (QI) project addressing nursing electronic health record (EHR) alert fatigue by strategically redesigning four high-firing/low action alerts. Employing a mixed-methods approach, including quantitative analysis, empathy mapping sessions, and user feedback, the project sought to understand and alleviate the challenges posed by these alerts. Virtual empathy mapping sessions with clinical nurses provided valuable insights into user experiences. Qualitative findings, CDS design principles, and organizational practice expectations informed the redesign process, resulting in the removal of all four identified disruptive alerts and redesign of passive alerts. This initiative released 877 unactionable disruptive nursing hours, emphasizing the significance of proper alert design and the necessity for organizational structures ensuring sustained governance in healthcare system optimization.

Development and Testing of an Instrument to Measure the Impact of EHR Use on Quality of Care.

There is an increased adoption of electronic health records (EHR) motivated by many purported benefits, yet limited research has explored their impact on quality of care. We developed and tested a multidimensional measure of quality of care in relation to EHR use. 234 nurses completed a cross-sectional survey. The score of the quality of care construct reached 0.92. Four subdimensions were identified: technology impact on nursing practice, learning and improvement capability, transition accountability, and fault responsibility. The instrument has potential to advance our understanding of the impact of EHR use on quality of care.

Challenges of Teaching EHR-Based Documentation in an Obstetrical Clinical Course While Fostering Positive Student Experiences.

Perinatal documentation is challenging and complex requiring multiple documentation modalities. By customizing an academic EHR to parallel documentation in perinatal units, pre-licensure nursing students will learn and experience documentation standards and practice on the academic EHR. Student feedback and experiences will be recorded utilizing student surveys.

Association Between EHR Compatibility and Nurses' Emotional Exhaustion.

In this study we explored the relationship between nurses' emotional exhaustion and three EHR compatibility subdimensions (nurses' preferred work style, existing clinical practice, and values). We found higher emotional exhaustion with lower EHR compatibility for both preferred work style and existing clinical practice, but no relationship between emotional exhaustion and nurses' values. Efforts to improve EHR compatibility are recommended to mitigate nurses' burnout.

Improving Compliance With Evidence-Based Laboratory Testing Recommendations and Monitoring Associated Patient Outcomes.

A team comprising nursing, medical staff, and administrative leaders at an urban academic orthopedic hospital in the northeastern United States sought to revise a preoperative laboratory testing protocol based on evidence and practice guidelines. The goal was to decrease unnecessary tests by 20% without negatively affecting patient outcomes. After adding the revised protocol to the electronic health record, audits revealed that the target goal was not met and additional strategies were implemented, including educational webinars for surgeon office personnel who ordered tests, additional webinars for advanced practice professionals, and the creation of scorecards to track surgeons' progress. Overall, a downward trend in the ordering of unnecessary laboratory tests for patients without identified risks was observed, but a 20% reduction was not achieved. Surgical complications during the project were not associated with laboratory tests. Clinicians continue to use the revised preoperative laboratory testing protocol at the facility.

Common definitions and variables are needed for the United States to join the conversation on acute-on-chronic liver failure.

Acute-on-chronic liver failure (ACLF) is a variably defined syndrome characterized by acute decompensation of cirrhosis with organ failures. At least 13 different definitions and diagnostic criteria for ACLF have been proposed, and there is increasing recognition that patients with ACLF may face disadvantages in the current United States liver allocation system. There is a need, therefore, for more standardized data collection and consensus to improve study design and outcome assessment in ACLF. In this article, we discuss the current landscape of transplantation for patients with ACLF, strategies to optimize organ utility, and data opportunities based on emerging technologies to facilitate improved data collection.

Accuracy of Electronic Health Record Documentation of Parental Presence: A Data Validation and Quality Improvement Analysis.

Parental presence in the neonatal intensive care unit (NICU) is known to improve the health outcomes of an admitted infant. The use of the electronic health record (EHR) to analyze associations between parental presence and sociodemographic factors could provide important insights to families at greatest risk for limited presence during their infant's NICU stay, but there is little evidence about the accuracy of nonvital clinical measures such as parental presence in these datasets. A data validation study was conducted comparing the percentage agreement of an observational log of parental presence to the EHR documentation. Overall, high accuracy values were found when combining two methods of documentation. Additional stratification using a more specific measure, each chart's complete accuracy, instead of overall accuracy, revealed that night shift documentation was more accurate than day shift documentation (76.3% accurate during night shifts, 55.2% accurate during day shifts) and that flowsheet (FS) recordings were more accurate than the free-text plan of care (POC) notes (82.4% accurate for FS, 75.1% accurate for POC notes). This research provides a preliminary look at the accuracy of EHR documentation of nonclinical factors and can serve as a methodological roadmap for other researchers who intend to use EHR data.

Data quality and timeliness analysis for post-vaccination adverse event cases reported through healthcare data exchange to FDA BEST pilot platform.

Introduction: This study is part of the U.S. Food and Drug Administration (FDA)'s Biologics Effectiveness and Safety (BEST) initiative, which aims to improve the FDA's postmarket surveillance capabilities by using real-world data (RWD). In the United States, using RWD for postmarket surveillance has been hindered by the inability to exchange clinical data between healthcare providers and public health organizations in an interoperable format. However, the Office of the National Coordinator for Health Information Technology (ONC) has recently enacted regulation requiring all healthcare providers to support seamless access, exchange, and use of electronic health information through the interoperable HL7 Fast Healthcare Interoperability Resources (FHIR) standard. To leverage the recent ONC changes, BEST designed a pilot platform to query and receive the clinical information necessary to analyze suspected AEs. This study assessed the feasibility of using the RWD received through the data exchange of FHIR resources to study post-vaccination AE cases by evaluating the data volume, query response time, and data quality. Materials and methods: The study used RWD from 283 post-vaccination AE cases, which were received through the platform. We used descriptive statistics to report results and apply 322 data quality tests based on a data quality framework for EHR. Results: The volume analysis indicated the average clinical resources for a post-vaccination AE case was 983.9 for the median partner. The query response time analysis indicated that cases could be received by the platform at a median of 3 min and 30 s. The quality analysis indicated that most of the data elements and conformance requirements useful for postmarket surveillance were met. Discussion: This study describes the platform's data volume, data query response time, and data quality results from the queried postvaccination adverse event cases and identified updates to current standards to close data quality gaps.