Machine learning risk stratification strategy for multiple myeloma: Insights from the EMN-HARMONY Alliance platform

This study developed and validated novel machine learning (ML)-driven prognostic scores for newly diagnosed multiple myeloma using data from 14,345 patients in the EMN–HARMONY cohort. Three ML models were developed, including a reduced model with six key variables. These models improved upon the International Staging System (ISS) and Revised International Staging System (R-ISS). The ML strategy provides individualized risk predictions, surpassing traditional methods.