Search AMIA.org

The Multiple Chronic Conditions (MCCs) Electronic Care (e-Care) Plan project aims to establish care planning data standards for individuals living with MCCs. This article reports on the portion of the project focused on long COVID and presents the process of identifying and modeling data elements using the HL7 Fast Healthcare Interoperability Resources (FHIR) standard.

 Telemetry monitoring is crucial for high-risk patients but excessive use beyond practice standards increases costs. Prior studies have shown that electronic health record (EHR) alerts reduce low-value telemetry monitoring. However, specific components of these alerts that contribute to effectiveness are unknown.

 Health-related social needs (HRSNs) are the unmet social and economic needs (e.g., housing instability) that affect individuals' health and well-being. HRSNs are associated with more emergency department (ED) visits, longer stays, and worse health outcomes. More than a third of ED patients have at least one HRSN, yet patients are rarely screened for HRSNs in the ED. A clinical decision support (CDS) system with predictive modeling offers a promising approach [...]

 Experiential learning through simulation allows students to apply didactic knowledge to real-world situations. Tabletop simulation allows for the exploration of a variety of topics, including cybersecurity in health care. Due to its low frequency, yet high-risk nature, simulation is a perfect educational modality to practice responding to a cybersecurity attack. As such, the authors designed and executed a tabletop cybersecurity simulation consisting of a prebriefing, four rounds of injects detailing [...]

 The electronic health record (EHR) has been associated with provider burnout, exacerbated by increasing In-Basket burden.

To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles.

We aim to develop a novel method for rare disease concept normalization by fine-tuning Llama 2, an open-source large language model (LLM), using a domain-specific corpus sourced from the Human Phenotype Ontology (HPO).

To automatically construct a drug indication taxonomy from drug labels using generative Artificial Intelligence (AI) represented by the Large Language Model (LLM) GPT-4 and real-world evidence (RWE).

Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from [...]

To solve major clinical natural language processing (NLP) tasks using a unified text-to-text learning architecture based on a generative large language model (LLM) via prompt tuning.