Search AMIA.org

To review the clinical evidence for small language models (SLMs), 4 billion parameters or fewer, for performance, safety, and deployment feasibility.

Precision medicine requires delivery and tracking of genome-informed risk assessments (GIRAs), often documented in unstructured electronic health record (EHR) notes, making large-scale evaluation reliant on labor-intensive manual chart review. Large language models (LLMs) offer a promising approach to automated extraction, but their performance in genome-informed clinical contexts remains incompletely characterized.

To evaluate the feasibility and applicability of the studyathon format within a pharmaceutical company setting for generating reliable real-world evidence rapidly for a business-relevant research question.

Transformer-based models for clinical prediction using longitudinal electronic health record (EHR) data are often developed with large feature sets and long patient histories under the assumption that more data improves performance. However, high-dimensional inputs and long sequences increase computational burden, potentially limiting scalability. We evaluated how feature dimensionality and sequence length affect predictive performance, calibration, risk stratification, and computational efficiency in EHR prediction.

To develop and validate a weighting framework to improve representativeness of Oracle Health Real-World Data (OHRWD).

This study aimed to develop large language models (LLMs) to automatically identify antiretroviral therapy (ART) adherence barriers and stratify nonadherence risk levels from patient-generated messages.

Characteristics of electronic health record (EHR) use associated with burnout in inpatient pediatric settings remain unclear. This study aims to (1) measure the relationship between subjective EHR experience and burnout and (2) identify objective EHR- and schedule-based measures associated with EHR experience and burnout.

We examined the intention of lung cancer patients to use virtual reality (VR) to support shared decision-making and treatment preparedness and identified predictors of this intention using the Unified Theory of Acceptance and Use of Technology (UTAUT).

This study evaluates the quality of estimated delivery dates (EDD) captured in electronic health record (EHR) systems, focusing on identifying and quantifying bias in these estimates for patients seeking prenatal care.

Comorbidity algorithms derived from International Classification of Diseases (ICD) codes are central to risk adjustment and cohort characterization, but existing software inconsistently handles mixed ICD-9/10 data and typically operates at the encounter level. We developed medicalcoder to address these limitations.