Search AMIA.org

Patients with rare diseases often struggle to find accurate medical information, and large language model (LLM)-based chatbots may help meet this need. However, evaluating LLM-generated free-text answers typically requires physician review, which is time-consuming and difficult to scale. This study compared traditional natural language processing (NLP) metrics to emerging LLM-based evaluation approaches for assessing answer quality in the context of Complex Lymphatic Anomalies (CLAs).

Implemented a tool to identify high-risk patients with atrial fibrillation (AF) with a CHA2DS2-VASc score of ≥2 (males) or ≥3 (females) who are not treated with oral anticoagulation. Aimed to evaluate the acceptability and usability of the "AF or Flutter not on Anticoagulant" electronic health record-based Care Gap (AF Care Gap) alert and associated best practice advisory (BPA) for clinicians managing patients with AF.

Patients with malignant tumors are admitted to the ICU for diverse reasons. However, the clinical utility of serum albumin as a prognostic biomarker remains unclear.

This study aimed to identify and quantify semantic drift (ie, the change in semantic meaning over time) within expert-defined anxiety-related (AR) terminology and compare it to common electronic health record (EHR) vocabulary across longitudinal pediatric clinical notes.

To develop a machine learning method that estimates future liver biomarkers' values from longitudinal lifestyle (diet, activity) data for early detection of nonalcoholic steatohepatitis (NASH).

Global immunization efforts still face major inequities and declining vaccine confidence, leaving millions of children in low- and middle-income countries unvaccinated or under-vaccinated.

This study aims to apply 2 decoder-based Generative Pre-trained Transformer (GPT) models (GPT-4o and GPT-o3-mini) in automating the methodological appraisal of randomized controlled trials (RCTs), under a variety of prompt designs, and to compare their performance to a fine-tuned encoder-only BioLinkBERT model.

To develop recommendations to inform the development and use of pragmatic workflow approaches.

To simulate shortcut learning mechanisms in AI-based breast cancer genomic subtyping and to develop an interpretable, reproducible framework capable of auditing feature over-reliance using a low-code environment.

The accurate identification of Emergency Department (ED) encounters involving opioid misuse is critical for health services, research, and surveillance. We sought to develop natural language processing (NLP)-based models for the detection of ED encounters involving opioid misuse.