Original title: Quantifying Impairment and Disease Severity Using AI Models Trained on Healthy Subjects
Authors: Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra, Carlos Fernandez-Granda
In this article, researchers tackle a big challenge in medical science: measuring how severe impairments and diseases are without relying on time-consuming assessments. They came up with a clever idea using AI models trained only on healthy people. Imagine these AI models as expert judges who know what a healthy body looks like. They noticed that when they showed these experts a person with a problem, the experts weren’t so sure anymore.
Original article: https://arxiv.org/abs/2311.12781