Abstract Artificial intelligence (AI) and machine learning (ML) have emerged as transformative tools in hematology, with growing evidence supporting their use in diagnostic interpretation, cytogenetics, molecular analysis, and outcome prediction. This review explores current applications, benefits, and implementation challenges of AI-based technologies in hematological practice. A systematic literature review was conducted across major scientific databases and relevant technical sources to identify studies employing ML and deep learning approaches in hematological diagnostics. The evidence shows that AI systems demonstrate strong capability in differentiating blood cell types, supporting leukemia and lymphoma diagnosis, enhancing chromosome banding and karyotype interpretation, and improving the efficiency and reproducibility of complex image and genomic data analysis. ML models have also been applied to prognostic modeling and patient-risk stratification. Despite these advances, major barriers remain, including data heterogeneity, limited external validation, algorithm interpretability, workflow integration issues, and ethical and regulatory considerations associated with “black-box” models. Collaboration between clinicians, data scientists, and regulatory bodies is essential to ensure responsible development and translation of AI tools into routine hematology services. Overall, AI holds substantial promise for improving diagnostic accuracy, efficiency, and precision medicine in hematology; however, further high-quality, clinically validated research is required to fully realize its potential and support safe, equitable implementation in real-world practice.
Abdullah M. Alshahrani (Tue,) studied this question.