The study presents a comprehensive genomic classification and individualized risk prediction model (IRMMa) for newly diagnosed multiple myeloma (NDMM). Using data from 1,933 patients, the researchers identified 12 distinct genomic groups, expanding on previous gene expression-based classifications. By integrating clinical, genomic, and treatment data, they developed IRMMa, which demonstrated superior accuracy compared to existing prognostic models like the International Staging System (ISS), revised ISS (R-ISS), and R2-ISS. IRMMa incorporates 20 genomic features, including chromothripsis, APOBEC mutational signatures, and copy-number variations, to predict individualized risk and outcomes. The model was validated on 256 patients from the GMMG-HD6 trial, showing improved accuracy in predicting overall survival (OS) and event-free survival (EFS). IRMMa also allows for the prediction of treatment response based on different therapeutic strategies, such as high-dose melphalan followed by autologous stem-cell transplantation (HDM-ASCT) and maintenance therapy. The model's ability to account for time-dependent variables and treatment variance makes it a valuable tool for personalized therapeutic decision-making in NDMM. The study highlights the importance of integrating genomic and clinical data to better understand and predict outcomes in NDMM, offering a more precise approach to treatment planning.The study presents a comprehensive genomic classification and individualized risk prediction model (IRMMa) for newly diagnosed multiple myeloma (NDMM). Using data from 1,933 patients, the researchers identified 12 distinct genomic groups, expanding on previous gene expression-based classifications. By integrating clinical, genomic, and treatment data, they developed IRMMa, which demonstrated superior accuracy compared to existing prognostic models like the International Staging System (ISS), revised ISS (R-ISS), and R2-ISS. IRMMa incorporates 20 genomic features, including chromothripsis, APOBEC mutational signatures, and copy-number variations, to predict individualized risk and outcomes. The model was validated on 256 patients from the GMMG-HD6 trial, showing improved accuracy in predicting overall survival (OS) and event-free survival (EFS). IRMMa also allows for the prediction of treatment response based on different therapeutic strategies, such as high-dose melphalan followed by autologous stem-cell transplantation (HDM-ASCT) and maintenance therapy. The model's ability to account for time-dependent variables and treatment variance makes it a valuable tool for personalized therapeutic decision-making in NDMM. The study highlights the importance of integrating genomic and clinical data to better understand and predict outcomes in NDMM, offering a more precise approach to treatment planning.