Dataset Information

Popular large language model chatbots' accuracy, comprehensiveness, and self-awareness in answering ocular symptom queries.

ABSTRACT: In light of growing interest in using emerging large language models (LLMs) for self-diagnosis, we systematically assessed the performance of ChatGPT-3.5, ChatGPT-4.0, and Google Bard in delivering proficient responses to 37 common inquiries regarding ocular symptoms. Responses were masked, randomly shuffled, and then graded by three consultant-level ophthalmologists for accuracy (poor, borderline, good) and comprehensiveness. Additionally, we evaluated the self-awareness capabilities (ability to self-check and self-correct) of the LLM-Chatbots. 89.2% of ChatGPT-4.0 responses were 'good'-rated, outperforming ChatGPT-3.5 (59.5%) and Google Bard (40.5%) significantly (all p < 0.001). All three LLM-Chatbots showed optimal mean comprehensiveness scores as well (ranging from 4.6 to 4.7 out of 5). However, they exhibited subpar to moderate self-awareness capabilities. Our study underscores the potential of ChatGPT-4.0 in delivering accurate and comprehensive responses to ocular symptom inquiries. Future rigorous validation of their performance is crucial to ensure their reliability and appropriateness for actual clinical use.

SUBMITTER: Pushpanathan K

PROVIDER: S-EPMC10616302 | biostudies-literature | 2023 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Popular large language model chatbots' accuracy, comprehensiveness, and self-awareness in answering ocular symptom queries.

Pushpanathan Krithi K Lim Zhi Wei ZW Er Yew Samantha Min SM Chen David Ziyou DZ Hui'En Lin Hazel Anne HA Lin Goh Jocelyn Hui JH Wong Wendy Meihua WM Wang Xiaofei X Jin Tan Marcus Chun MC Chang Koh Victor Teck VT Tham Yih-Chung YC

iScience 20231010 11

In light of growing interest in using emerging large language models (LLMs) for self-diagnosis, we systematically assessed the performance of ChatGPT-3.5, ChatGPT-4.0, and Google Bard in delivering proficient responses to 37 common inquiries regarding ocular symptoms. Responses were masked, randomly shuffled, and then graded by three consultant-level ophthalmologists for accuracy (poor, borderline, good) and comprehensiveness. Additionally, we evaluated the self-awareness capabilities (ability t ...[more]

PMID: 37915603

Similar Datasets

Project description:ImportanceBecause more patients are presenting with self-guided research of symptoms, it is important to assess the capabilities and limitations of these available health information tools.ObjectiveTo determine the accuracy of the most popular online symptom checker for ophthalmic diagnoses.Design, setting, and participantsIn a cross-sectional study, 42 validated clinical vignettes of ophthalmic symptoms were generated and distilled to their core presenting symptoms. Cases were entered into WebMD symptom checker by both medically trained and nonmedically trained personnel blinded to the diagnosis. Output from the symptom checker, including the number of symptoms, ranking and list of diagnoses, and triage urgency were recorded. The study was conducted on October 13, 2017. Analysis was performed between October 15, 2017, and April 30, 2018.Main outcomes and measuresAccuracy of the top 3 diagnoses generated by the online symptom checker.ResultsThe mean (SD) number of symptoms entered was 3.6 (1.6) (range, 1-8). The median (SD) number of diagnoses generated by the symptom checker was 26.8 (21.8) (range, 1-99). The primary diagnosis by the symptom checker was correct in 11 of 42 (26%; 95% CI, 12%-40%) cases. The correct diagnosis was included in the online symptom checker's top 3 diagnoses in 16 of 42 (38%; 95% CI, 25%-56%) cases. The correct diagnosis was not included in the symptom checker's list in 18 of 42 (43%; 95% CI, 32%-63%) cases. Triage urgency based on the top diagnosis was appropriate in 7 of 18 (39%; 95% CI, 14%-64%) emergent cases and 21 of 24 (88%; 95% CI, 73%-100%) nonemergent cases. Interuser variability for the correct diagnosis being in the top 3 listed was at least moderate (Cohen κ = 0.74; 95% CI, 0.54-0.95).Conclusions and relevanceThe most popular online symptom checker may arrive at the correct clinical diagnosis for ophthalmic conditions, but a substantial proportion of diagnoses may not be captured. These findings suggest that further research to reflect the real-life application of internet diagnostic resources is required.

Dataset Information

Popular large language model chatbots' accuracy, comprehensiveness, and self-awareness in answering ocular symptom queries.

Publications

Popular large language model chatbots' accuracy, comprehensiveness, and self-awareness in answering ocular symptom queries.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets