IIIT-H study caution doctors against relying entirely on AI for medical diagnosis
The researchers finds discrepancies in chest X-ray regions highlighted by vision-language models and radiologists
A recent study conducted by researchers at the International Institute of Information Technology, Hyderabad (IIIT-H) has cautioned doctors against relying entirely on AI tools for interpreting medical images, such as chest X-rays. The study, led by Parameswari Krishnamurthy and published in The Hindu Health, examined four vision-language models for analysing chest X-rays and found discrepancies between the regions highlighted by the AI models and those identified by radiologists.
The researchers questioned whether AI-generated heatmaps accurately represented the regions of an image that radiologists would identify as disease-related. The study, accepted at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2026, found that an AI model highlighting an apparently correct region of an X-ray did not necessarily mean that it had identified the disease in the same way as a radiologist.
The findings underscore the need for doctors to independently assess AI-generated outputs rather than relying on them entirely for diagnosis, as the performance of different models varied in technical audit and radiologists' assessments.
Brief written by urgent.news from The Hindu Health's own syndicated text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
