Massachusetts Institute of TechnologyJun 28 2024 Artificial intelligence models often play a role in medical diagnoses, especially when it comes to analyzing images such as X-rays. However, studies have found that these models don't always perform well across all demographic groups, usually faring worse on women and people of color.
The researchers also found that they could retrain the models in a way that improves their fairness. However, their approached to "debiasing" worked best when the models were tested on the same types of patients they were trained on, such as patients from the same hospital. When these models were applied to patients from different hospitals, the fairness gaps reappeared.
Using publicly available chest X-ray datasets from Beth Israel Deaconess Medical Center in Boston, the researchers trained models to predict whether patients had one of three different medical conditions: fluid buildup in the lungs, collapsed lung, or enlargement of the heart. Then, they tested the models on X-rays that were held out from the training data.
In another set of models, the researchers forced them to remove any demographic information from the images, using "group adversarial" approaches. Both of these strategies worked fairly well, the researchers found.