ML Model Predicts Pathologic Complete Response After Breast Cancer Chemotherapy

Pathological complete response after neoadjuvant chemo was predicted with AUROC 0.76, 8.7% false positive rate, 75% positive predictive value by a machine learning model using breast imaging and clinical features (n=388).

• From 111 imaging and clinical variables, 14 were selected via LASSO regularization to build a logistic regression model with elastic net penalty.
• pCR rate was 40.7% (158/388); the study was retrospective and monocentric without external validation.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.