Search AMIA.org

Poor documentation quality can significantly affect health care operations, but the feedback process for clinicians to improve clinical notes is time-consuming and often insufficient. Large language models (LLMs) such as Generative Pre-trained Transformer 4 (GPT-4) have the potential to streamline this process.

Digital health physical activity (PA) programs have shown promise for improving the health and wellness of family caregivers (FCGs). However, their use among older adult caregivers remains underexplored. To address this gap, we developed TPA4You, a tailored digital health PA program that integrates videoconferencing with a health coach, a fitness tracker, and motivational messaging. The program is designed to support older caregivers, a population whose health and self-care needs are [...]

This study evaluates the performance of multiple large language models (LLMs) on specialized otolaryngology knowledge, comparing OpenAI's GPT-4 Turbo with 10 commercially available models to assess their potential utility in otolaryngology medical education.A total of 1,075 questions from OTO QUEST, the official self-assessment resource of the American Academy of Otolaryngology-Head and Neck Surgery, were administered to GPT-4 Turbo using a zero-shot approach. Accuracy was analyzed using logistic regression, adjusting for [...]

Central line-associated bloodstream infections (CLABSIs) are a significant concern in pediatric intensive care units (PICUs), leading to increased morbidity and limited treatment options. Electronic health record (EHR)-based documentation for monitoring CLABSIs may enhance bundle compliance and reduce infection rates. However, data in pediatric settings are limited.This study evaluated the impact of transitioning from paper-based to EHR-based documentation for central line maintenance on CLABSI rates in intensive care units (ICUs).A retrospective [...]

Electronic patient-centered clinical decision support enhances chronic disease self-management, yet few studies describe how qualitative user feedback is systematically translated into programming improvements. The Collaboration-Oriented Approach to Controlling High Blood Pressure (COACH) is a patient-facing decision support tool for hypertension management, designed for primary care and integration with electronic health records (EHRs) and patient portals.This study aimed to describe how end-user feedback informed COACH programming decisions and the MoSCoW (Must [...]

The objective of this study is to determine whether primary care electronic health record (EHR) data are sufficiently complete and plausible to support automated audits of antimicrobial prescribing quality.Cross-sectional descriptive assessment of antimicrobial auditing-related fields in Patron, a large Australian primary care EHR dataset with 3.5 million patients from 129 consenting general practices. Data from 2018 to 2022 were evaluated using the Harmonized Data Quality Assessment Terminology and Framework, covering [...]

Guidelines recommend measuring glycated hemoglobin (HgbA1c) levels on all inpatients with diabetes mellitus, if untested in the prior 3 months. In response, our health system applies default HgbA1c orders in the electronic insulin orders for qualifying patients. However, recent red blood cell transfusions may cause falsely low HgbA1c values, leading to inappropriate management. Clinicians often forget to deselect default HgbA1c orders after transfusion, leading to erroneous results. We evaluated a [...]

Despite widespread adoption, electronic health records (EHRs) continue to present persistent challenges related to usability, workflow inefficiencies, and clinician burden. Structured EHR optimization programs that address these issues in a scalable and replicable manner remain limited in the literature.This study aimed to describe the development, implementation, and outcomes of the EASY (Eliminate, Automate, Standardize, and Simplify, Y'all) EHR Optimization program-designed to enhance EHR usability, provider satisfaction, and workflow efficiency through [...]

This study applies object-centric process mining (OCPM) techniques to analyze laparoscopic cholecystectomy (LC) procedures. Traditional process mining techniques are limited in analyzing workflows involving multiple interacting entities (patients, surgeries, anesthesia physical status, etc.).This study aimed to construct an Object-Centric Event Log (OCEL) from LC procedures, discover multientity process patterns, identify workflow bottlenecks, and analyze how patient complexity affects perioperative dynamics.An OCEL representing 1,186 LC cases (1,108 performed, 78 cancelled) from [...]

Federal healthcare legislation has played a central role in shaping the digital transformation of U.S. healthcare. Key legislative milestones-including the Health Security Act of 1993, the Health Insurance Portability and Accountability Act (HIPAA), the Health Information Technology for Economic and Clinical Health (HITECH) Act, the Patient Protection and Affordable Care Act (ACA), and the 21st Century Cures Act-collectively accelerated the adoption of electronic health records (EHRs), promoted interoperability, and expanded [...]