Search AMIA.org

Early prediction of in-hospital death remains a significant challenge due to the limited availability of structured data during initial admission. Unstructured clinical notes, which often contain important observations and impressions, are an underutilized resource for real-time risk stratification. While leveraging recent advances in large language models (LLMs) is a promising approach to use this unstructured information, the lack of understanding of the uncertainty of LLM predictions, at the patient level [...]

We aimed to (1) quantify changes in discrimination when adding intraoperative data to preoperative data and (2) compare tabular machine learning with feature engineering against a time-aware LSTM-based model.

Emergency department (ED) returns for mental health (MH) conditions pose a substantial burden on healthcare systems. Traditional machine learning (ML) models have shown promise in predicting ED returns but often fall short in clinical interpretability. This study evaluates whether integrating Large Language Models (LLMs) with ML methods can enhance both predictive performance and interpretability.

To facilitate responsible biomedical data sharing, large-scale data harmonization, and cutting-edge artificial intelligence (AI) applications by augmenting controlled-access data dissemination models (DDMs) with Data-derived Identity Verification (DIVe).

Large language models (LLMs) may improve analysis of structured clinical data by enabling natural language (NL) queries. We developed an interactive, PHI-compliant "Text2SQL" chatbot as a proof-of-concept for hepatocellular carcinoma (HCC) research.

Many patients struggle to interpret lab and test results.

Phenotype libraries accelerate health research through the reuse of algorithms. However, multiple libraries exist with differing metadata standards. We describe the integration of libraries using shared conceptual standards to harmonize definitions.

This study evaluated the quality and trustworthiness of large language model (LLM)-generated scientific and plain language summaries (PLS) from clinical oncology literature, focusing on faithfulness (absence of hallucinations), relevance, and readability.

Electronic health record (EHR) data can enrich investigation of maternal health and pregnancy in large populations. However, many outpatient care settings lack data infrastructure to record pregnancy start and end dates, limiting the reach of EHR-based research. We examined the accuracy of pregnancy dates estimated from outpatient EHR data, compared to linked state birth certificate data.

To assess the reliability and confidence calibration of Large Language Models (LLMs) when communicating multi-cancer early detection (MCED) test characteristics in an expert-informed clinical evaluation.