Previously submitted to: JMIR Biomedical Engineering (no longer under consideration since Jul 08, 2025)
Date Submitted: Apr 30, 2025
Open Peer Review Period: Jun 2, 2025 - Jul 28, 2025
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Evaluating Large Multimodal Models in COVID-19 Pneumonia Detection: A Case Study Using Chest X-Rays
ABSTRACT
Background:
Recent advances in large language models (LLMs) have enabled the development of multimodal systems capable of interpreting both text and medical images. These models show promise in automating clinical tasks such as diagnostic image review. However, their real-world performance, especially in high-stakes scenarios like detecting COVID-19 pneumonia on chest X-rays (CXRs), remains underexplored.
Objective:
To assess the diagnostic accuracy of Gemini 2.0, a state-of-the-art multimodal LLM, in detecting COVID-19 pneumonia from CXRs and compare its performance to prior evaluations of ChatGPT-4 Turbo and ChatGPT-4o on the same dataset.
Methods:
We used the publicly available COVIDx CXR-4 dataset (n=20,000), equally divided between pneumonia-positive and negative cases. Each image was submitted to Gemini 2.0 via its API with a standardized diagnostic prompt. Output responses were analyzed to calculate accuracy, precision, recall, and F1-score. Results were compared with prior benchmark evaluations using ChatGPT models.
Results:
Gemini 2.0 achieved an overall diagnostic accuracy of 45%. Precision and recall for pneumonia-positive cases were 34% and 11%, respectively. For pneumonia-negative cases, precision was 47% and recall 79%. Compared to ChatGPT-4 Turbo (54.1%) and ChatGPT-4o (61.2%), Gemini 2.0 demonstrated inferior performance on the same dataset.
Conclusions:
Despite its multimodal capabilities, Gemini 2.0 underperformed compared to other LLMs in detecting COVID-19 pneumonia from CXRs, particularly in sensitivity. These findings underscore the limitations of current multimodal AI systems for clinical imaging and highlight the need for further development and validation prior to deployment in diagnostic settings. Clinical Trial: N/A
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.