Search AMIA.org

To develop and evaluate an automated algorithm to identify sepsis onset, referred to as time-zero (t0), from the electronic medical records (EMR).

Accurate and timely prediction of physiological deterioration in hospitalized patients is essential, but existing deep learning models, which rely solely on structured electronic health record (EHR) data, generate high false-positive rates by missing crucial contextual information in clinical notes. We present DETERIO-LLM, a hybrid prediction model that selectively integrates large language models (LLMs) with a deep learning model (DETERIO) to reclassify borderline-risk alerts using narrative clinical notes.

Social determinants of health (SDOH) are incompletely captured in structured electronic health records (EHRs) but are frequently documented in unstructured clinical notes. We evaluated large language models (LLMs) for extracting SDOH from clinical text.

To develop a generalizable framework for identifying algorithmic discrimination risks arising from subgroup imbalances in machine learning training data, with relevance to medical informatics applications where heterogeneous real-world data can bias model behavior.

Pharmacogenomics can optimize therapeutic outcomes while minimizing adverse events. However, the lack of trained healthcare professionals has impeded its widespread adoption. Current patient-facing applications are either institution-specific or vary significantly in their coverage of genetic variants, interpretation guidelines, and data privacy protection. To address these shortcomings, we developed PharMe.

Generating real-world evidence (RWE) approaches across federated evidence networks based on real-world data requires learning new methodological skills. However, standardized frameworks for defining and assessing competencies for large-scale RWE research remain limited. This study aims to develop an assessment framework for RWE studies and evaluate the competencies of RWE research professionals.

Electronic health record (EHR) data discontinuity, defined as receiving care outside of a particular EHR system, may cause misclassification of study variables. We aimed to: (1) quantify misclassification across levels of EHR data discontinuity and identify an optimal continuity threshold, (2) develop a machine learning (ML) model to predict EHR continuity and optimize fairness across racial and ethnic groups, and (3) externally validate the EHR continuity prediction model using an [...]

To describe the development and implementation of an automated platform for genomic risk prediction that integrates multiple data types.

Atrial fibrillation (AF) is a common arrhythmia affecting a large fraction of patients in intensive care units (ICUs). Predicting patients at risk of AF in the ICU is a challenging task and is not commonly practiced but could have clinical implications considering that AF is a proxy for poorer outcomes. Our goal is to develop a real-time AF prediction model using ICU numerical data to improve alarm quality, helping clinicians [...]

To develop a pipeline for evaluating large language models (LLMs) on the task of capturing symptoms from clinical encounters.