Artificial Intelligence in the Management of Leukemia

BACKGROUND: Recently, given the demonstrated ability of AI to accurately characterize complex pathologies, AI has been proposed to be of use in the diagnosis, treatment, and monitoring of leukemias given their genetic complexity and subtype heterogeneity, array of treatments, and need for relapse detection. AI has several potential applications in the management of leukemia. First, it can be used to detect leukemia; using AI to detect nuances in lab values can ensure these deadly cancers are never missed. Second, AI can be used to risk-stratify patients and personalize treatments; leukemias are among the most genetically complex cancers with well-characterized risk profiles, however, tailoring treatments remains a challenge despite our advances. And third, AI can be used for surveillance and relapse management; there is a role for AI in predicting risk of relapse and determining when an MRD+ patient needs treatment (as not all cells detected can cause relapse), then tailoring treatment plans for patients who ultimately relapse. METHODS: PubMed was indexed in May 2025 using the search terms “artificial intelligence” and “leukemia” together. Articles published within the last two years were selected and those deemed highly relevant/applicable (n = 46) were included. RESULTS: The application of AI in the treatment of leukemia is largely limited to diagnosis, specifically via routine clinical data and ancillary testing. While intriguing, the use of AI in the leukemia risk stratification, treatment planning, and relapse detection is largely unexplored. CONCLUSION: AI has great potential to improve several aspects of leukemia management. However, it is currently underutilized and most AI usage in the management of leukemia is focused on initial detection and diagnosis. We believe the real power of AI lies in optimizing treatment intensity to reduce toxicity and likelihood of relapse.