JMIR Formative Research (Nov 2024)

Comparative Analysis of Diagnostic Performance: Differential Diagnosis Lists by LLaMA3 Versus LLaMA2 for Case Reports

  • Takanobu Hirosawa,
  • Yukinori Harada,
  • Kazuki Tokumasu,
  • Tatsuya Shiraishi,
  • Tomoharu Suzuki,
  • Taro Shimizu

DOI
https://doi.org/10.2196/64844
Journal volume & issue
Vol. 8
p. e64844

Abstract

Read online

BackgroundGenerative artificial intelligence (AI), particularly in the form of large language models, has rapidly developed. The LLaMA series are popular and recently updated from LLaMA2 to LLaMA3. However, the impacts of the update on diagnostic performance have not been well documented. ObjectiveWe conducted a comparative evaluation of the diagnostic performance in differential diagnosis lists generated by LLaMA3 and LLaMA2 for case reports. MethodsWe analyzed case reports published in the American Journal of Case Reports from 2022 to 2023. After excluding nondiagnostic and pediatric cases, we input the remaining cases into LLaMA3 and LLaMA2 using the same prompt and the same adjustable parameters. Diagnostic performance was defined by whether the differential diagnosis lists included the final diagnosis. Multiple physicians independently evaluated whether the final diagnosis was included in the top 10 differentials generated by LLaMA3 and LLaMA2. ResultsIn our comparative evaluation of the diagnostic performance between LLaMA3 and LLaMA2, we analyzed differential diagnosis lists for 392 case reports. The final diagnosis was included in the top 10 differentials generated by LLaMA3 in 79.6% (312/392) of the cases, compared to 49.7% (195/392) for LLaMA2, indicating a statistically significant improvement (P<.001). Additionally, LLaMA3 showed higher performance in including the final diagnosis in the top 5 differentials, observed in 63% (247/392) of cases, compared to LLaMA2’s 38% (149/392, P<.001). Furthermore, the top diagnosis was accurately identified by LLaMA3 in 33.9% (133/392) of cases, significantly higher than the 22.7% (89/392) achieved by LLaMA2 (P<.001). The analysis across various medical specialties revealed variations in diagnostic performance with LLaMA3 consistently outperforming LLaMA2. ConclusionsThe results reveal that the LLaMA3 model significantly outperforms LLaMA2 per diagnostic performance, with a higher percentage of case reports having the final diagnosis listed within the top 10, top 5, and as the top diagnosis. Overall diagnostic performance improved almost 1.5 times from LLaMA2 to LLaMA3. These findings support the rapid development and continuous refinement of generative AI systems to enhance diagnostic processes in medicine. However, these findings should be carefully interpreted for clinical application, as generative AI, including the LLaMA series, has not been approved for medical applications such as AI-enhanced diagnostics.