Large language models (LLMs) are being explored for diagnostic decision support, yet their ability to estimate pre-test probabilities, vital for clinical decision-making, remains limited. This study evaluates two LLMs, Mistral-7B and Llama3-70B, using structured electronic health record data on three diagnosis tasks. We examined three current methods of extracting LLM probability estimations and revealed their limitations. We aim to highlight the need for improved techniques in LLM confidence estimation.

The authors have declared no competing interest.

This work is supported by the National Library of Medicine (NLM) under award R00LM014308 02 (PI: Gao), NLM award R01LM012973 05 (PI: TM, DD, MA), National Heart, Lung, and Blood Institute (NHLBI) under award R01HL157262 04 (PI: MC), NIH-USA awards U54CA274516 01A1 and R01CA294033 01 (PI: DB; SC), NSF DMS-2054346 and the University of Wisconsin School of Medicine and Public Health through the Wisconsin Partnership Program (Research Design Support: Protocol Development, Informatics, and Biostatistics Module, PI: GC).

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study was approved by the University of Wisconsin-Madison (IRB #2019-1258), University of Chicago Biological Sciences Division (IRB #18-0447), Loyola University Medical Center (IRB #215437), and NorthShore University (IRB #11-0539) Institutional Review Boards with a waiver of informed consent. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

All data produced in the present study might be available under Data Use Agreement.