119 posters, 6 topics, 524 authors, 243 institutions
ePostersLive by SciGen Technologies S.A. All rights reserved.
RCR Global AI Conference 2026
29-30 June, 2026 | QEII Centre, Westminster
156
Integrating imaging and clinical data for enhanced Lung cancer risk prediction: A weighted average ensemble approach
Poster Presenter
Part of Topic
AI Education and research: examples of proof of concept or AI in development, technical advances, teaching approaches or pre-clinical testing
Integrating imaging and clinical data for enhanced Lung cancer risk prediction: A weighted average ensemble approach
Mayur Munshi, Gareth Price, Andrew Reilly, Gordon Cowell
Purpose
•To improve lung cancer risk prediction among screening trial participants by integrating imaging and clinical data using a weighted average ensemble approach.
•To compare ensemble performance with individual image-based and clinical risk models.
•To benchmark model discrimination against published lung cancer risk prediction studies.
Conclusion
•Weighted average ensemble model achieved the highest performance (AUC 0.91).
•Combining image-based and clinical risk-based features improves prediction accuracy.
•Image-based and hence weighted average ensemble models demonstrated strong performance despite no nodule annotation.
•This approach demonstrated superior lung cancer risk prediction based on longitudinal screening data.