Artificial intelligence in haematology laboratory diagnosis: Current applications, challenges, and future directions.

Abstract

Background: Artificial intelligence (AI) is transforming haematology diagnostics by improving accuracy, efficiency, and reproducibility in workflows traditionally reliant on manual microscopy and expert interpretation. Integrating AI into laboratory medicine presents opportunities to enhance diagnostic precision and reduce variability, particularly in resource-limited settings.

Aim: This narrative review examines the application of AI across major domains of haematology, morphological diagnosis, flow cytometry, cytogenetics, genomics, and clinical decision support, while addressing ethical, regulatory, and economic considerations relevant to global and African laboratory contexts.

Methods: A comprehensive literature search of PubMed, Scopus, Web of Science, and EMBASE identified studies describing or evaluating AI algorithms in haematologic diagnostics, focusing on model performance, validation level, and clinical applicability.

Results: Recent studies demonstrate strong performance of deep learning models, particularly convolutional neural networks and hybrid convolutional neural networks-transformer architectures, in automating blood and bone marrow morphology, detecting subtle dysplastic changes, and supporting digital workflows. In flow cytometry, AI enhances automated gating and rare event detection, while cytogenetic and genomic tools aid in karyotyping, variant classification, and structural abnormality recognition. Decision-support systems further assist in diagnostic triage and treatment planning. However, widespread implementation is limited by data heterogeneity, inadequate multicentre validation, and evolving ethical and regulatory frameworks.

Conclusion: Advancing AI integration in haematology will require robust validation studies, explainable AI approaches, and equitable adoption strategies. Strengthening African laboratory systems through such innovations offers a pathway toward improved diagnostic capacity and sustainable digital transformation.

What this study adds: The current study highlighted that AI is improving haematology laboratory tasks such as cell identification, differential diagnosis assistance, and result interpretation, but still faces challenges in validation, bias, and workflow integration. Future progress depends on stronger external validation, better explainable models, and closer collaboration between laboratory experts and AI specialists.