An international study led by the Hematological Tumor Unit at Hospital 12 de Octubre-CNIO, in collaboration with California Hospital, has made significant advancements in predicting the evolution of multiple myeloma (MM) using artificial intelligence (AI) for the first time. The research, published in the Blood Cancer Journal, identified patterns of treatment response in patients with MM, enabling more accurate predictions regarding tumor evolution and potential relapses.
Multiple myeloma is the most prevalent hematological tumor, and while a cure remains elusive, the introduction of new therapies has notably improved patient prognoses. In this study, researchers focused on minimal residual disease (MRD)—the smallest number of cancer cells left in the body post-treatment—as a critical factor in making informed clinical decisions. Joaquín Martínez, head of the Hematological Tumor Research Unit at Hospital 12 de Octubre-CNIO and principal investigator, stated, “This work with AI allows us to make a much more accurate prediction of the evolution of the patient’s myeloma, which will let us make with much greater certainty clinical choices, such as the withdrawal of maintenance treatment on the basis of more reliable results, and benefit more patients.”
The AI-driven approach could potentially allow up to 30% of patients to safely discontinue maintenance therapies, thus avoiding the adverse side effects, including gastrointestinal issues and the risk of new tumors. The study also revealed a new parameter called clonal diversity, which reflects the recovery of the immune system. Higher clonal diversity correlates with a better prognosis, as it indicates a greater presence of normal immunoglobulins.
For this research, 482 MM patients diagnosed between 2008 and 2020 at the University of California, San Francisco (UCSF) were retrospectively analyzed, including 304 newly diagnosed and 178 with relapsed disease. The findings underscore the potential of AI to transform treatment strategies and enhance patient outcomes in multiple myeloma.
