Emerging Artificial Intelligence Technologies for Risk Assessment and Management in Acute Myeloid Leukemia: A Review
Mohammad Amin Ansarian1, Mahsa Fatahichegeni1, Rui Xu1
1Department of Hematology, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, Shaanxi, People's Republic of China.
Importance:
Acute myeloid leukemia (AML) is a severe hematologic cancer with complex genetic heterogeneity necessitating personalized treatment approaches. Artificial intelligence (AI) technologies may revolutionize risk stratification, diagnosis enhancement, and treatment planning in addressing critical gaps in AML management, particularly in low-resource health care environments.
Observations:
This narrative review synthesizes existing AI applications in 3 primary areas of AML management. Machine learning algorithms integrating clinical, cytogenetic, and molecular data demonstrate greater prognostic accuracy than conventional European LeukemiaNet (ELN) guidelines. Deep learning approaches to image analysis yield excellent results for AML subtype identification from bone marrow smears (area under the receiver operating characteristic curve [AUROC]: 0.97) and genetic variant prediction (eg, NPM1 status [AUROC: 0.92]). AI-driven genomic analysis reveals novel prognostic signatures and therapeutic targets through advanced pattern recognition, with high-dimensional machine learning achieving greater than 99% accuracy in AML classification from transcriptomic data. Explainable AI models overcome the black box limitation through interpretable algorithms with Shapley Additive Explanations values and local interpretable model-agnostic explanation techniques. Federated learning approaches enable multi-institutional collaboration with protection of patient privacy, with 96.5% accuracy in leukemia classification on heterogeneous datasets.
Conclusions And Relevance:
AI technologies hold potential to improve AML treatment through enhanced risk stratification, early detection capabilities, and individualized treatment optimization. The transition toward explainable AI models is essential to clinical readiness, with federated learning architectures resolving data scarcity concerns. Seamless integration requires harmonized data standards, robust regulatory frameworks, and equitable access to technology to fully realize the transformative potential of AI in improving outcomes for patients with AML globally.
