Comparative Analysis of Diagnostic Performance: Differential Diagnosis Lists by LLaMA3 Versus LLaMA2 for Case Reports
Bibliographic record
Abstract
BACKGROUND: Generative 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. OBJECTIVE: We conducted a comparative evaluation of the diagnostic performance in differential diagnosis lists generated by LLaMA3 and LLaMA2 for case reports. METHODS: We 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. RESULTS: In 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. CONCLUSIONS: The 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.021 | 0.106 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.010 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".