Search AMIA.org

To quantify differences between (1) stratifying patients by predicted disease onset risk alone and (2) stratifying by predicted disease onset risk and severity of downstream outcomes. We perform a case study of predicting sepsis.

screening is a labor-intensive component of systematic review involving repetitive application of inclusion and exclusion criteria on a large volume of studies. We aimed to validate large language models (LLMs) used to automate abstract screening.

To measure hospital engagement in interoperable exchange of health-related social needs (HRSN) data.

The objective of this work is to demonstrate the value of simulation testing for rapidly evaluating artificial intelligence (AI) products.

This study evaluates the integration of electronic health records (EHRs) and natural language processing (NLP) with large language models (LLMs) to enhance healthcare data management and patient care, focusing on using advanced language models to create secure, Health Insurance Portability and Accountability Act-compliant synthetic patient notes for global biomedical research.

Extended reality (XR) applications are gaining support as a method of reducing anxieties about medical treatments and conditions; however, their impacts on health service inequalities remain underresearched. We therefore undertook a synthesis of evidence relating to the equity implications of these types of interventions.

To assess what practice-, provider-, and patient population-level predictors predict adoption of an ADHD ehealth technology in community pediatric settings, pediatric providers nationwide were recruited and offered free use of an evidence-based mental-health-focused ehealth quality improvement intervention (mehealth for ADHD). Practice-, provider-, and patient population-level factors predicting provider's adoption of the intervention were studied. We hypothesized that providers who were younger, nearing re-credentialing, having more patients with ADHD, working at [...]

While many aspects of nursing documentation are considered an essential part of clinical communication and care coordination, other types of nursing documentation have been implemented to meet compliance and other secondary use needs. Adding required documentation without carefully assessing its association with patient outcomes adds excessive documentation burden on nurses. There is a gap in the evidence of the association between additional required nursing documentation and improvements in patient outcomes.

Adverse event detection from Electronic Medical Records (EMRs) is challenging due to the low incidence of the event, variability in clinical documentation, and the complexity of data formats. Pulmonary embolism as an adverse event (PEAE) is particularly difficult to identify using existing approaches. This study aims to develop and evaluate a Large Language Model (LLM)-based framework for detecting PEAE from unstructured narrative data in EMRs.

Electronic health record (EHR) systems are essential for modern healthcare but contribute to significant documentation burden, affecting physician workflow and well-being. While previous studies have identified differences in EHR usage across demographics, systematic methods for identifying high-burden physician groups remain limited. This study applies cluster analysis to uncover distinct EHR usage profiles and provide a framework to inform the development of targeted interventions.