MIT Develops AI That Can Detect Future Lung Cancer Risk

January 24, 2023 | Automation
MIT / Guy Zylberberg

The AI model is called Sybil and can analyze low-dose computed tomography (LDCT) lung scans without the need of a radiologist to predict the risk of a patient developing a future lung cancer within six years.

The team demonstrated that Sybil obtained C-indices of 0.75, 0.81, and 0.80 over the course of six years from diverse sets of lung LDCT scans taken from various medical intitutes (models achieving a C-index score over 0.7 are considered good and over 0.8 is considered strong).