Search AMIA.org

Bias evaluations of machine learning (ML) models often focus on performance in research settings, with limited assessment of downstream bias following clinical deployment. The objective of this study was to evaluate whether CHARTwatch, a real-time ML early warning system for inpatient deterioration, demonstrated algorithmic bias in model performance, or produced disparities in care processes, and outcomes across patient sociodemographic groups.

The NIH's Bridge2AI Program has funded 4 "new flagship biomedical and behavioral datasets that are properly documented and ready for use with AI [artificial intelligence] or ML [machine learning] technologies" to promote the adoption of AI. This article discusses the challenges and lessons learned in data collection and governance to ensure their responsible use.

This study aims to develop and validate of a span-based annotation framework for clinical named entity recognition (NER) using large language models (LLMs) based on Korean emergency department clinical notes.

Identifying social determinants of mental health (SDOMH) in patients with opioid use disorder (OUD) is crucial for estimating risk and enabling early intervention. Extracting such data from unstructured clinical notes is challenging due to annotation complexity and requires advanced natural language processing (NLP) techniques. We propose the Human-in-the-Loop Large Language Model Interaction for Annotation (HLLIA) framework, combined with a Multilevel Hierarchical Clinical-Longformer Embedding (MHCLE) algorithm, to annotate and predict SDOMH [...]

This study describes the utilization and experiences of artificial intelligence (AI)-generated draft responses to patient messages in pediatric ambulatory clinicians and contextualizes their experiences in relation to those of adult specialty clinicians.

To evaluate large language models (LLMs) for extracting temporal relations from pediatric rare disease clinical reports to enable automated patient timeline creation.

To evaluate effectiveness of open-source generative models in producing high-quality tabular synthetic data using a Health and Demographic Surveillance System (HDSS) dataset from rural Kenya, as a proof of concept in a low- and middle-income (LMIC) setting.

This study evaluates and enhances language access services for Limited English Proficiency (LEP) patients in a large urban health system by integrating interpreter services into the Electronic Health Record (EHR), aiming to reduce care disparities and improve the digital experience for both patients and clinicians.

In a sample of patients with diagnosed alcohol use disorder (AUD), we examined the prevalence of both stigmatizing (eg, "alcohol abuse") and highly stigmatizing, non-medical descriptors (eg, "alcoholic") documented in electronic health records (EHRs). We also assessed whether the use of these terms-entered by clinicians when documenting AUD using search tools and picklists-varied across patient subgroups within a regional health system.