Toward Better Patient Stratification with Machine Learning

Machine learning could better stratify patients with metastatic ER-positive, HER2-negative breast cancer who are more or less likely to benefit from CDK4/6 inhibition up front. At Memorial Sloan Kettering Cancer Center, two models trained on clinical and genomic factors, respectively, were effective in predicting disease progression risk; combining these factors produced a third model that outperformed the others in terms of analytical power.