Large language models in spirometry interpretation: impact of guideline-based prompting
Croatian Medical Journal · 2026-10 · 67 (5) · 338-346
DOI: 10.3325/cmj.2026.67.338 ↗Kurz gefasst
Leitlinie in der Zeitschrift Croatian Medical Journal, 2026-10. Verfasst von Muazzez Elçi̇n Özkan und 8 weiteren Autor:innen.
Abstract (Originalsprache)
AIM: To compare the performance of ChatGPT and Gemini with pulmonologist assessment in spirometry interpretation based on European Respiratory Society and American Thoracic Society (ERS/ATS) standards and to evaluate the effect of structured guideline-based prompting on diagnostic accuracy. METHODS: This cross-sectional diagnostic study involved 500 anonymized spirometry reports. Quality control (QC) assessment and ventilatory pattern classification were based on pulmonologist consensus as the reference standard. The same cases were evaluated by ChatGPT and Gemini before and after structured guideline-based prompting derived from ERS/ATS criteria. Analyses were restricted to 362 tests deemed interpretable by all groups. Agreement was assessed with McNemar and McNemar-Bowker tests, and diagnostic performance was evaluated with class-specific and overall multiclass measures. RESULTS: Both models correctly extracted all numerical spirometric parameters but overestimated test interpretability compared with specialists (all P
Zitieren
APA
Özkan, M. E., Unat, D. S., Unat, Ö. S., Güçsav, M. O., Özgen, M. H., Özdemi̇r, D., İlhan, E., Meral, O., & Akçay, O. (2026). Large language models in spirometry interpretation: impact of guideline-based prompting. Croatian Medical Journal, 67(5), 338-346. https://doi.org/10.3325/cmj.2026.67.338
Vancouver
Özkan ME, Unat DS, Unat ÖS, Güçsav MO, Özgen MH, Özdemi̇r D, et al. Large language models in spirometry interpretation: impact of guideline-based prompting. Croatian Medical Journal. 2026;67(5):338-346. doi:10.3325/cmj.2026.67.338
BibTeX
@article{zkan2026,
author = {Özkan, Muazzez Elçi̇n and Unat, Damla Serçe and Unat, Ömer Seli̇m and Güçsav, Mutlu Onur and Özgen, Mukaddes Hande and Özdemi̇r, Di̇lara and İlhan, Erdal and Meral, Orhan and Akçay, Onur},
title = {Large language models in spirometry interpretation: impact of guideline-based prompting},
journal = {Croatian Medical Journal},
year = {2026},
volume = {67},
number = {5},
pages = {338--346},
doi = {10.3325/cmj.2026.67.338}
}
EUVIMED