Search Articles

View query in Help articles search

Search Results (1 to 10 of 46 Results)

Download search results: CSV END BibTex RIS


AI-Driven Integrated System for Burn Depth Prediction With Electronic Medical Records: Algorithm Development and Validation

AI-Driven Integrated System for Burn Depth Prediction With Electronic Medical Records: Algorithm Development and Validation

AI: artificial intelligence; BURN-AID: Burn Diagnosis with Artificial Intelligence; EMR: electronic medical record; TDI: tissue Doppler imaging. The method integrates digital photographs and ultrasound tissue Doppler imaging (TDI) data stored within an electronic medical record (EMR) system. The initial phase of burn assessment uses digital photographs of the burn wound. These images are processed to rapidly classify burns as first degree or second degree [6].

Md Masudur Rahman, Mohamed El Masry, Surya C Gnyawali, Yexiang Xue, Gayle Gordillo, Juan P Wachs

JMIR Med Inform 2025;13:e68366

Machine Learning Models to Predict Risk of Maternal Morbidity and Mortality From Electronic Medical Record Data: Scoping Review

Machine Learning Models to Predict Risk of Maternal Morbidity and Mortality From Electronic Medical Record Data: Scoping Review

The increased use of electronic medical record (EMR) systems has produced vast volumes of structured and unstructured health care data, offering opportunities for early intervention using machine learning (ML) models that identify individuals at risk of maternal morbidity and mortality [15,16].

Lavanya Vasudevan, Mohammad Golam Kibria, Lauren M Kucirka, Karl Shieh, Mian Wei, Safoora Masoumi, Subha Balasubramanian, Ashley Victor, Jamie L Conklin, Metin Nafi Gurcan, Alison M Stuebe, David Page

J Med Internet Res 2025;27:e68225

Outcomes of an Advanced Epic Personalization Course on Clinician Efficiency through Use of Electronic Medical Records: Retrospective Study

Outcomes of an Advanced Epic Personalization Course on Clinician Efficiency through Use of Electronic Medical Records: Retrospective Study

Epic Systems is the most widely used electronic medical record (EMR) system globally [3] and was ranked as the number one EMR system in the United States for the 13th consecutive year in 2023 [4]. The adoption of EMRs, including Epic, is mandatory in Singapore’s public health care institutions to establish standardization, data interoperability, and enhanced patient safety [5].

Junye George Chen, Hao Xing Lai, Shi Min Wong, Terry Ling Te Pan, Er Luen Lim, Zi Qiang Glen Liau

JMIR Form Res 2025;9:e68491

Methods of Piloting an Abstraction Tool to Describe Family Engagement in the Hospital Setting: Retrospective Chart Review

Methods of Piloting an Abstraction Tool to Describe Family Engagement in the Hospital Setting: Retrospective Chart Review

The absence of a standardized EMR template further complicates the documentation of family engagement, limiting our understanding of how it affects patient outcomes in both acute care and the transition from acute care [17]. Retrospective chart review (RCR) is an effective methodology for investigating clinical practices, such as the current standard for documenting family engagement in medical records.

Jennifer Morgan, Jennifer Cahill, Christine Ritchie, Lingling Zhang, Priscilla Gazarian

JMIR Form Res 2025;9:e66549

Pharmaceutical Analysis of Inpatient Prescriptions: Systematic Observation of Hospital Pharmacists’ Practices in the Early User-Centered Design Phase

Pharmaceutical Analysis of Inpatient Prescriptions: Systematic Observation of Hospital Pharmacists’ Practices in the Early User-Centered Design Phase

Between 28% and 64% of the analysis time, the EMR is in the majority, representing around 40% of all activities performed during this period. The proportion of “biology results” remains fairly constant, as do “pharmacy logistics,” “other information,” and “alerts from prescriptions.” Pharmaceutical interventions and drug information are poorly represented at the outset but increase to reach a peak of around 82% of analysis time.

Jesse Butruille, Natalina Cirnat, Mariem Alaoui, Jérôme Saracco, Etienne Cousein, Noémie Chaniaud

JMIR Hum Factors 2025;12:e65959

Applying Robotic Process Automation to Monitor Business Processes in Hospital Information Systems: Mixed Method Approach

Applying Robotic Process Automation to Monitor Business Processes in Hospital Information Systems: Mixed Method Approach

This study explored the potential of RPA in complex EMR systems with its role as “a canary in a coal mine” [11], presenting generalizable findings from a 3-year project at Seoul National University Bundang Hospital (SNUBH). The paper posits RPA as a means to bridge the gap between the limitations of both component-level system monitoring and application-level monitoring.

Adam Park, Se Young Jung, Ilha Yune, Ho-Young Lee

JMIR Med Inform 2025;13:e59801

Deep Learning Models to Predict Diagnostic and Billing Codes Following Visits to a Family Medicine Practice: Development and Validation Study

Deep Learning Models to Predict Diagnostic and Billing Codes Following Visits to a Family Medicine Practice: Development and Validation Study

Following a patient visit, physicians document their note in an EMR often in the SOAP (subjective, objective, assessment, plan) format. To submit an invoice, physicians must select 1 or more diagnostic codes and 1 or more billing codes. Invoices are compiled electronically in the EMR, reviewed by FHT billing personnel, and subsequently submitted to the provincial health insurance plan for payment every month.

Akshay Rajaram, Michael Judd, David Barber

JMIR AI 2025;4:e64279