Performance of Sybil AI for lung cancer risk assessment: a head-to-head comparison of cardiac vs. lung CT scans

ESC Congress 2026 - 28 - 31 Aug 2026

Munich, Germany

Organised by: European Society of Cardiology (ESC) visual

Can AI assess lung cancer risk from a cardiac CT—even when the entire lung isn’t visible?

In this study, Sybil AI was evaluated head-to-head on cardiac coronary artery calcium (CAC) scans and full chest CT scans across 4,486 scans from the FHS and MESA cohorts.

Despite the limited lung field of view, Sybil maintained strong lung cancer risk prediction on cardiac CT, with AUC remaining above 0.80 through 6 years.

These findings highlight an important opportunity: using existing CAC scans acquired for cardiovascular prevention to provide additional insight into lung cancer risk—without requiring an additional scan.

Download the full presentation below to explore the study, results, and clinical implications.

ESC2026-LungVsCAC_v7.pptx

Download PPTX • 4.89MB