System and method for predicting future lung cancer risk
JP2024525808A5Inactive Publication Date: 2025-03-19JOHNSON & JOHNSON ENTERPRISE INNOVATION INC
0 Cites 0 Cited by
Patent Information
- Application Number
- JP2024502086
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-04-07
- Filing Date
- 2022-07-13
- Publication Date
- 2025-03-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Technical Problem
Current lung cancer screening methods, such as the Lung-RADS scoring system, are inadequate for predicting long-term cancer risk and identifying patients at highest risk for future malignancy, limiting effective prevention strategies.
Method used
A risk prediction model that analyzes nodule-specific and non-nodule-specific features from CT scans, including lung parenchymal and body composition features, to predict future lung cancer risk, utilizing longitudinal data to monitor changes over time.
Benefits of technology
The model effectively predicts lung cancer risk, achieving an AUC value of at least 0.70 and odds ratio of at least 5.0, enabling early detection and targeted interventions for high-risk individuals.
✦ Generated by Eureka AI based on patent content.
Abstract
The risk prediction models are trained and deployed to analyze images, such as computed tomography scans, to predict the risk of lung cancer (e.g., current or future risk of lung cancer) for one or more subjects. Individual risk prediction models are trained on nodule-specific and non-nodule-specific features, including longitudinal nodule-specific and longitudinal non-nodule-specific features, such that each risk prediction model can predict the risk of lung cancer over different time ranges. Such risk prediction models are useful for developing preventive therapies for lung cancer by enabling enrichment of clinical trials.
Need to check novelty before this filing date? Find Prior Art