Study Finds AI and Radiologists Achieve Better Results Together

The team of researchers at AIIMS evaluated a simple radiologist-augmented AI workflow to test whether the inclusion of a radiologist’s opinion into an AI algorithm would make the algorithm achieve better accuracy as compared to an algorithm trained on imaging parameters alone. For the study, open-source BI-RADS data sets were evaluated to test whether the inclusion of a radiologist’s opinion (in the form of BI-RADS classification) in addition to image parameters improved the accuracy of prediction of histology using three machine learning algorithms vis-à-vis algorithms using image parameters alone.

According to the study results, the models using the radiologist-provided BI-RADS classification performed significantly better than the models not using them. The researchers concluded that AI and radiologists working together can achieve better results, helping in case-based decision-making. However, further evaluation of the metrics involved in predictor handling by AI algorithms would provide newer insights into imaging, according to the researchers.

Related Links:
All India Institutes of Medical Sciences