NeoPred, a dual-phase CT AI tool, accurately predicts major pathological response in NSCLC patients preoperatively.
Key Details
- 1NeoPred combines pre-treatment and pre-surgery CT scans with clinical data to predict major pathological response (MPR) in NSCLC undergoing neoadjuvant chemo-immunotherapy.
- 2Study included 509 patients across four oncology centers (459 retrospective, 50 prospective, 59 external validation).
- 3NeoPred reached AUCs of 0.772 (imaging only) and 0.787 (imaging plus clinical data) on external validation, outperforming thoracic surgeons (AUC 0.760 vs 0.720) in prospective testing.
- 4AI support improved surgeons' AUC to 0.829 and diagnostic accuracy to 82%.
- 5NeoPred identified 'pseudo-stable' responders missed by standard RECIST criteria, with AUCs of 0.742 (external) and 0.833 (prospective).
Why It Matters
Accurately predicting response before surgery could enable earlier, evidence-based clinical decisions for NSCLC, reducing overtreatment and personalizing care. This work demonstrates the expanding role and performance advantage of AI-assisted imaging over traditional assessment in complex oncologic management.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.