Quantifying impairment and disease severity using AI models trained on healthy subjects

Quantifying impairment and disease severity using AI models trained on healthy subjects

Abstract Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploi...

Full description

Bibliographic Details
Main Authors: Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra, Carlos Fernandez-Granda
Format: Article
Language:English
Published: Nature Portfolio 2024-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-024-01173-x

Internet

https://doi.org/10.1038/s41746-024-01173-x

Similar Items