Accessibility settings

This paper is in the following e-collection/theme issue:

Responsible Health AI (222) Clinical Informatics (2237) mHealth in a Clinical Setting (1134) Decision Support for Health Professionals (2209) Generative Language Models Including ChatGPT (1498)

Published on in Vol 5 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/83640, first published .
Tablet displaying medical icons: first aid kit, pills, and a red dot.

Performance of Large Language Models Under Input Variability in Health Care Applications: Dataset Development and Experimental Evaluation

Performance of Large Language Models Under Input Variability in Health Care Applications: Dataset Development and Experimental Evaluation

Authors of this article:

Saubhagya Joshi1 Author Orcid Image ;   Monjil Mehta2 Author Orcid Image ;   Sarjak Maniar2 Author Orcid Image ;   Mengqian Wang3 Author Orcid Image ;   Vivek Kumar Singh1 Author Orcid Image
Article Authors Cited by (2) Tweetations Metrics

Journals

  1. Harada Y. Safety Audit of a Large Language Model for Lay Self-Triage Using Japanese Symptom Vignettes: Persistent Red-Flag Under-Triage Despite Improved Reproducibility Under Near-Deterministic Decoding. Cureus 2026 View

Conference Proceedings

  1. Padilha B, Barros J, Cerri G, Ferreira J. Anais do I Simpósio de Infraestrutura Digital/Nuvem para Pesquisa (Pesquisa@Nuvem 2026). MedJus: A Cloud-based LLM Application to Expedite Decision Making for Health Judicialization in Brazil View