A Personalized Risk Model for Azacitidine Outcome in Myelodysplastic Syndrome and Other Myeloid Neoplasms Identified by Machine Learning Model Utilizing Real-World Data

SIMPLE SUMMARY: Myelodysplastic syndrome (MDS) is one of the most-common blood cancers in older individuals. Although azacitidine is the most-commonly used treatment for MDS, only 30–40% of patients respond to it, and responses may not be achieved up to six cycles of treatment. Moreover, there are no universally accepted prognostic models that will identify patients who are unlikely to benefit. To address this shortcoming, we used a machine learning model (“Artificial Intelligence”) to identify patients who are unlikely to benefit from azacitidine. Our study provides a machine learning model that predicts patients who are less likely to benefit from azacitidine. The median survival of Poor-risk patients was only 8 months compared to 23 months in the favorable risk group. Importantly the model can be used during routine practice not only in major hospitals, but also in small community practice. ABSTRACT: Azacitidine is an approved therapy for higher-risk myelodysplastic syndrome (MDS). However, only 30–40% patients respond to azacitidine, and the responses may take up to six cycles to become evident. Delayed responses and the myelosuppressive effects of azacitidine make it challenging to predict which patients will benefit. This is further compounded by a lack of uniform prognostic tools to identify patients at risk of early treatment failure. Hence, we performed a retrospective analysis of 273 consecutive azacytidine-treated patients. The median overall survival was 16.25 months with only 9% alive at 5 years. By using pre-treatment variables incorporated into a random forest machine learning model, we successfully identified those patients unlikely to benefit from azacytidine upfront (7.99 vs. 22.8 months, p < 0.0001). This model also identified those who required significantly more hospitalizations and transfusion support. Notably, it accurately predicted survival outcomes, outperforming the existing prognostic scoring system. By integrating somatic mutations, we further refined the model and identified three distinct risk groups with significant differences in survival (5.6 vs. 10.5 vs. 43.5 months, p < 0.0001). These real-world findings emphasize the urgent need for personalized prediction tools tailored to hypomethylating agents, reducing unnecessary complications and resource utilization in MDS treatment.