Back

Evaluation of the Diagnostic Accuracy of GPT-4 in Five Thousand Rare Disease Cases

Reese, J. T.; Chimirri, L.; Danis, D.; Caufield, J. H.; Wissink, K. W.; Casiraghi, E.; Valentini, G.; Haendel, M. A.; Mungall, C. J.; Robinson, P. N.

2024-07-22 genetic and genomic medicine
10.1101/2024.07.22.24310816 medRxiv
Show abstract

Large language models (LLMs) show promise in supporting differential diagnosis, but their performance is challenging to evaluate due to the unstructured nature of their responses and their accuracy compared to existing diagnostic tools is not well characterized. To assess the current capabilities of LLMs to diagnose genetic diseases, we benchmarked these models on 5,213 case reports using the Phenopacket Schema, the Human Phenotype Ontology and Mondo disease ontology. Prompts generated from each phenopacket were sent to seven LLMs, including four generalist models and three LLMs specialized for medical applications. The same phenopackets were used as input to a widely used diagnostic tool, Exomiser, in phenotype-only mode. The best LLM ranked the correct diagnosis first in 23.6% of cases, whereas Exomiser did so in 35.5% of cases. While the performance of LLMs for supporting differential diagnosis has been improving, it has not reached the level of commonly used traditional bioinformatics tools. Future research is needed to determine the best approach to incorporate LLMs into diagnostic pipelines.

Published in European Journal of Human Genetics (predicted rank #7) · training set

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.