Evaluating ChatGPT-3.5 and ChatGPT-4.0 Responses on Hyperlipidemia for Patient Education

Evaluating ChatGPT-3.5 and ChatGPT-4.0 Responses on Hyperlipidemia for Patient Education

May 25, 2024 | Thomas J. Lee, Abhinav K. Rao, Daniel J. Campbell, Navid Radfar, Manik Dayal, Ayham Khrais
This study evaluates the accuracy, comprehensibility, and response length of ChatGPT versions 3.5 and 4.0 for patient education on hyperlipidemia. The research compares the free and paid versions, which differ in their features and pricing. The study used three prompting methods (no prompting, patient-friendly, and physician-level) and 25 questions from the Cleveland Clinic's FAQs on hyperlipidemia. The results show that both versions provided accurate responses, with no significant difference in accuracy between them (p = 0.586). However, ChatGPT version 3.5 had a higher grade reading level and word count compared to version 4.0 (p = 0.0002 and p = 0.0073, respectively). The paid version demonstrated superior adaptability in tailoring responses based on the input level. The study concludes that both versions of ChatGPT provide reliable medical information, with the paid version offering more adaptable and readable responses. Healthcare providers can recommend ChatGPT as a valuable resource for patient education, regardless of the version used. Future research should explore diverse question formulations and ChatGPT's handling of incorrect information.This study evaluates the accuracy, comprehensibility, and response length of ChatGPT versions 3.5 and 4.0 for patient education on hyperlipidemia. The research compares the free and paid versions, which differ in their features and pricing. The study used three prompting methods (no prompting, patient-friendly, and physician-level) and 25 questions from the Cleveland Clinic's FAQs on hyperlipidemia. The results show that both versions provided accurate responses, with no significant difference in accuracy between them (p = 0.586). However, ChatGPT version 3.5 had a higher grade reading level and word count compared to version 4.0 (p = 0.0002 and p = 0.0073, respectively). The paid version demonstrated superior adaptability in tailoring responses based on the input level. The study concludes that both versions of ChatGPT provide reliable medical information, with the paid version offering more adaptable and readable responses. Healthcare providers can recommend ChatGPT as a valuable resource for patient education, regardless of the version used. Future research should explore diverse question formulations and ChatGPT's handling of incorrect information.
Reach us at info@study.space
[slides and audio] Evaluating ChatGPT-3.5 and ChatGPT-4.0 Responses on Hyperlipidemia for Patient Education