Comparative accuracy, stability, and correctability of large language models in otolaryngology and pharmacovigilance
Open accessAbstract
OBJECTIVE: To compare the clinical and pharmacovigilance performance, stability, and correctability of 3 large language models (LLMs) in otolaryngology outpatient care. STUDY DESIGN: Prospective case series. SETTING: Multicenter University Hospitals. METHODS: Consecutive adults (August-October 2024) with established primary diagnoses were entered into ChatGPT-4o, Gemini-1.5-Pro, and Claude-3.5-Sonnet using only history and physical examination findings (no complementary tests) via standardized prompts. Two blinded otolaryngologists rated clinical accuracy with the Artificial Intelligence Performance Instrument (AIPI); 2 blinded pharmacists rated pharmacological information on a 5-point Likert scale. Errors were fed back to models and all cases were re-queried one month later. Interrater reliability used ICC; stability used Cronbach's α. Group differences used Kruskal-Wallis. RESULTS: Fifty-one patients with 60 diagnoses across otolaryngology subspecialties were consecutively recruited (38 females (74.5%); mean age of 42.4 ± 17.4 years). All LLMs recommended significantly more additional examinations than practitioners (P = .001), with a significant increase of the number of recommended additional examinations after regenerated inputs for ChatGPT-4o and Claude-3.5-Sonnet, respectively. Claude-3.5-Sonnet and ChatGPT-4o outperformed Gemini-1.5-Pro for AIPI-clinical management (P = .001) and pharmacovigilance findings (P = .001). The physicians (ICC = 0.853) and the pharmacists (ICC = 0.991) demonstrated an almost perfect interrater reliability. All LLMs demonstrated an almost perfect clinical stability (α = 0.831-0.856), though human feedback did not significantly reduce misdiagnosis rates in subsequent interactions. CONCLUSION: In outpatient ENT cases using clinical features alone, ChatGPT-4o and Claude-3.5-Sonnet deliver higher clinical and pharmacovigilance performance than Gemini-1.5-Pro, with almost perfect interrater reliability and stable outputs. Re-querying after feedback did not improve accuracy, questioning short-term correctability.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In a study assessing medication-dosing recommendations for long-acting injectable antipsychotics, the descriptive accuracy score was 95% for OpenEvidence, 85% for Perplexity, 62.5% for Copilot, and 40% for ChatGPT.
“The results reported a descriptive accuracy score of 95% for the medical-specialized LLM (OpenEvidence) and, for the general-purpose LLM tools, 85% for Perplexity, 62.5% for Copilot, and 40% for ChatGPT.87”
From Large Language Models in Pharmacist-Led Direct Patient Care: A Rapid Review of Published Evaluations (2026) · cites this paper as [87]
The Pharmacovigilance Performances section (page unavailable) reports scores for ChatGPT-4o, Claude-3.5-Sonnet, and Gemini-1.5-Pro, not the four tools or percentages in the claim. Searches for OpenEvidence, Perplexity, Copilot, and long-acting injectable antipsychotic dosing found no passage addressing the claimed results. (LLM, conf=0.77)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 20 · Cited by 1
- Authors
- Bruno, F., Sogalow, L., Blankert, B., & Lechien, J. R.
- Affiliations
- University of Mons (BE)
- Centre National de la Recherche Scientifique (FR)
- Corresponding author
- Lechien, Jerome R.
- Venue
- Otolaryngology–Head and Neck Surgery
- Publisher
- Wiley
- Published
- 2025-11-18
- Volume
- 174
- Issue
- 1
- Pages
- 143-151
- ISSN
- 0161-6439 (ISSN-L)
- 0194-5998
- 1097-6817
- OpenAlex
- W4416331189
- Cited by
- 1
- References
- 20
- Citations by year
- 2026: 1
- FWCI
- 0.24
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Otolaryngology (publishedVersion)
- PubMed (publishedVersion)
- ORBi UMONS (submittedVersion, other-oa)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Family Practice › Clinical Reasoning and Diagnostic Skills
- Keywords
- large language models, GPT-4o, Gemini 1.5 Pro, Claude 3.5 Sonnet, pharmacovigilance, clinical accuracy, inter-rater reliability, model stability, correctability, misdiagnosis
- MeSH terms
- Large Language Models, Adult, Female, Humans, Language, Male, Middle Aged, Otolaryngology, Prospective Studies, Reproducibility of Results, Pharmacovigilance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
