Artificial intelligence tools can assist emergency room physicians in accurately predicting disease but only for patients with typical symptoms, West Virginia University scientists have found. The need for incorporating greater amounts of different types of data in training AI technology to assist in disease diagnosis. More data can make the difference in whether AI gives patients the correct diagnoses for what are called challenging cases, which don’t exhibit classic symptoms.

As an example, Hu pointed to a trio of scenarios from his study involving patients who had pneumonia without the typical fever. In these three cases, all of the GPT models failed to give an accurate diagnosis, Hu said. That made us dive in to look at the physicians’ notes and we noticed the pattern of these being challenging cases. ChatGPT tends to get a lot of information from different resources on the internet, but these may not cover atypical disease presentation.

The study analyzed data from 30 public emergency department cases, which for reasons of privacy did not include demographics. Hu explained that in using ChatGPT to assist with diagnosis, physicians’ notes are uploaded, and the tool is asked to provide its top three diagnoses. Results varied for the versions Hu tested: the GPT-3.5, GPT-4, GPT-4o and o1 series. When we looked at whether the AI models gave the correct diagnosis in any of their top three results, we didn’t see a significant improvement between the new version and the older version, he said.

But when we look at each model’s number one diagnosis, the new version is about 15% to 20% higher in accuracy than the older version. Given AI models’ current low performance on complex and atypical cases, Hu said human oversight is a necessity for high-quality, patient-centered care when using AI as an assistive tool. We didn’t do this study out of curiosity to see if the new model will give better results. We wanted to establish a basis for future studies that involve additional input, Hu said.

Source: https://wvutoday.wvu.edu/stories/2025/05/20/wvu-researchers-test-ai-s-limits-in-emergency-room-diagnoses