Abstract
Artificial intelligence (AI) has shown significant potential in enhancing diagnostic accuracy, refining prognostic models, guiding personalized treatment decisions, and improving clinical workflows. Across the spectrum of blood cancers, AI-based tools have demonstrated strong performance in tasks such as automated image classification, genomic and biomarker analysis, prediction of treatment response and toxicity, and estimation of measurable residual disease. Despite these promising developments, challenges remain, including limited dataset size, lack of prospective validation, concerns regarding interpretability, and ethical considerations related to data privacy and bias. The review emphasizes the need for robust clinical integration strategies, high-quality data, and multiple teams' collaboration to fully harness AI's potential in transforming the management of hematologic malignancies.