The integration of artificial intelligence (AI) is driving a third revolution in pathology, following the transformative impacts of immunohistochemistry and genomic medicine. This review aims to summarize the current landscape of AI applications in diagnostic hematology, highlighting how machine learning (ML) and deep learning (DL) models are poised to reshape clinical practice. Our investigation found that the main applications include the automated analysis of digital pathology slides and flow cytometry data, where algorithms can identify subtle morphologic patterns often invisible to the human eye. Furthermore, AI is crucial for integrating complex, high‐throughput next‐generation sequencing data to refine diagnostic accuracy and prognostic predictions for hematologic malignancies. While these tools offer the potential to surpass human capabilities in classification tasks, significant challenges remain. The primary hurdles include the need for large, high‐quality annotated datasets, the clinical imperative for model interpretability, and the practical difficulties of regulatory approval and workflow integration. Despite these obstacles, the continued advancement of AI in hematopathology promises to enhance diagnostic precision, reduce errors, and ultimately pave the way for a new era of personalized medicine.
Tsekhovska et al. (2026) studied this question.