Large Language Models for Patient Education for Atrial Fibrillation
AI and Intelligent Systems: Engineering, Medicine & Society · 16.01.2026 · 02 (01) · 01-03
DOI: 10.33140/aiisems.02.01.06 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI and Intelligent Systems: Engineering, Medicine & Society, online erschienen am 16.01.2026. Verfasst von Gloria Wu und 8 weiteren Autor:innen.
Abstract (Originalsprache)
Atrial fibrillation (AF) is the most common arrhythmia globally, affecting over 37 million individuals. AF substantially increases the risk of stroke, heart failure, and mortality. With the advent of the internet, most patients use Large Language Models (LLMs) for health education. In terms of monthly users, ChatGPT has 800M, Gemini has 350M, Claude.ai has 18.9M, Meta has 350M, and Grok has 64M. These LLMs use different training models. The purpose of this small study was to evaluate large language models (LLMs) for atrial fibrillation patient education. Each LLM has a standard query: “I am a 68-year-old [race] [gender] with atrial fibrillation. I had a heart attack 2 years ago with stents. What can I expect from my cardiologist?” Responses were evaluated for word count, Flesch-Kincaid (FK) grade level, cosine similarity scores to measure structural text similarity, and the presence of select clinical keywords relevant to AF management. A cardiologist author selected keywords.
Zitieren
APA
Wu, G., Paliath-Pathiyal, H., Khan, O., Wang, M., Tewari, S., Oggi, H., Toram, R., Wang, P. J., & Lee, D. (2026). Large Language Models for Patient Education for Atrial Fibrillation. AI and Intelligent Systems: Engineering, Medicine & Society, 02(01), 01-03. https://doi.org/10.33140/aiisems.02.01.06
Vancouver
Wu G, Paliath-Pathiyal H, Khan O, Wang M, Tewari S, Oggi H, et al. Large Language Models for Patient Education for Atrial Fibrillation. AI and Intelligent Systems: Engineering, Medicine & Society. 2026;02(01):01-03. doi:10.33140/aiisems.02.01.06
BibTeX
@article{Wu2026,
author = {Wu, Gloria and Paliath-Pathiyal, Hrishi and Khan, Obaid and Wang, Margaret and Tewari, Swara and Oggi, Hasika and Toram, Riki and Wang, Paul J. and Lee, David},
title = {Large Language Models for Patient Education for Atrial Fibrillation},
journal = {AI and Intelligent Systems: Engineering, Medicine & Society},
year = {2026},
volume = {02},
number = {01},
pages = {01--03},
doi = {10.33140/aiisems.02.01.06}
}
EUVIMED