A new study validates the Sybil AI model for predicting lung cancer risk using low-dose CT in a predominantly Black cohort at an urban safety-net hospital.
Key Details
- 1Study presented at the 2025 IASLC World Conference on Lung Cancer.
- 2Validation conducted at UI Health on 2,092 baseline low-dose CT scans from 2014-2024.
- 3Cohort primarily Non-Hispanic Black (62%), with 13% Hispanic and 4% Asian.
- 4Sybil demonstrated strong Area Under the Curve (AUC): 0.94 (1 yr), 0.90 (2 yr), 0.86 (3 yr), 0.85 (4 yr), 0.80 (5 yr), 0.79 (6 yr).
- 5Results remained strong after restricting to Black participants and excluding recent diagnoses.
- 6The Sybil Implementation Consortium will advance to prospective clinical trials for clinical workflow integration.
Why It Matters
Demonstrating reliable AI performance in racially and socioeconomically diverse settings is crucial for equitable lung cancer screening. This validation may facilitate broader adoption and help address longstanding disparities in lung cancer outcomes.
Source
EurekAlert
Related News
•EurekAlert
New Framework Compares AI Segmentation Without Ground Truth Annotations
Researchers introduce an open-source approach for evaluating AI anatomy segmentation models in medical imaging without requiring ground truth annotations.
•EurekAlert
Sandia Labs Deploys AI-Augmented Imaging for Ceramic Component Inspections
Sandia National Laboratories is introducing AI-assisted optical and acoustic imaging systems to streamline and improve ceramic component inspections for nuclear deterrence.
•EurekAlert
New AI Vision-Language Model Enhances Chest CT Diagnostics
Researchers developed an interpretable AI model that uses visual question answering to generate detailed diagnostic findings from chest CT scans, aimed at improving lung cancer diagnosis.