Search AMIA.org

[This corrects the article DOI: 10.1093/jamiaopen/ooaf007.].

The use of large language models (LLMs) is growing for both clinicians and patients. While researchers and clinicians have explored LLMs to manage patient portal messages and reduce burnout, there is less documentation about how patients use these tools to understand clinical notes and inform decision-making. This proof-of-concept study examined the reliability and accuracy of LLMs in responding to patient queries based on an open visit note.

This work aims to develop a methodology for transforming Health Level 7 (HL7) Clinical Document Architecture (CDA) documents into the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). The described method seeks to improve the Extract, Transform, Load (ETL) design process by using HL7 CDA Template definitions and the CDA Refined Message Information Model (CDA R-MIM).

To explore patients' use of patient portals to access lab test results, their comprehension of lab test data, and factors associated with these.

We conducted a scoping review to identify barriers to telehealth use and uptake from the perspective of patient, provider, and system that were documented in the literature. In addition to identifying and categorizing the barriers, we aimed to assess how barriers differed for studies conducted during the COVID-19 pandemic, as well as how barriers differed between the United States vs internationally based studies.

Degenerative rotator cuff tears (DCTs) are the leading cause of shoulder pain, affecting 30%-50% of individuals over 50. Current phenotyping strategies for DCT use heterogeneous combinations of procedural and diagnostic codes and are concerning for misclassification. The objective of this study was to create standardized phenotypic algorithms to classify DCT status across electronic health record (EHR) systems.

Despite the recent adoption of large language models (LLMs) for biomedical information extraction (IE), challenges in prompt engineering and algorithms persist, with no dedicated software available. To address this, we developed LLM-IE: a Python package for building complete IE pipelines.

To semantically enrich the laboratory data dictionary of the Study of Health in Pomerania (SHIP), a population-based cohort study, with LOINC to achieve better compliance with the FAIR principles for data stewardship.

Observational data have been actively used to estimate treatment effect, driven by the growing availability of electronic health records (EHRs). However, EHRs typically consist of longitudinal records, often introducing time-dependent confounding that hinder the unbiased estimation of treatment effect. Inverse probability of treatment weighting (IPTW) is a widely used propensity score method since it provides unbiased treatment effect estimation and its derivation is straightforward. In this study, we aim to [...]

Sepsis recognition among infants in the Neonatal Intensive Care Unit (NICU) is challenging and delays in recognition can result in devastating consequences. Although predictive models may improve sepsis outcomes, clinical adoption has been limited. Our focus was to align model behavior with clinician information needs by developing a machine learning (ML) pipeline with two components: (1) a model to predict baseline sepsis risk and (2) a model to detect evolving [...]