Artificial intelligence (AI) and machine learning (ML) now reach into every stage of AML care. Deep learning models read therapy-relevant mutations directly from bone marrow smears; automated flow cytometry gating reproduces expert calls in under a minute; and the first AI pathology devices for hematology have cleared regulatory review and entered clinical use. Beyond diagnosis, ML captures the age-dependent weight of individual mutations that categorical ELN scoring misses, drug response prediction for venetoclax–azacitidine has been validated across multiple external cohorts, and large language models are being tested for tumor board support and trial matching. The next wave, from clonal architecture modeling and single-cell foundation models to digital twins and reinforcement learning for adaptive dosing, could move AML management from reactive toward predictive, evolution-aware care. This review departs from existing AI-in-hematology surveys in three ways: we (i) restrict the scope to AML and organize the field around clinical decision points rather than technology categories, (ii) grade every tool on a five-tier author-defined clinical readiness level (CRL-AML 1–5), which exposes hundreds of models clustered at CRL-AML 1–2 and none yet in prospective clinical evaluation, and (iii) close with a numbered three-year agenda naming the consortia, datasets, and pragmatic trials needed to carry the field from publication to practice.
Disease relapse remains the leading cause of treatment failure in patients with acute myeloid leukemia (AML) undergoing allogeneic hematopoietic cell transplantation (allo-HCT). This systematic review critically synthesizes the available evidence on post-transplant maintenance strategies, which have evolved over the past three decades from conventional chemotherapy to molecularly targeted agents and interventions aimed at modulating antileukemic immunity. Particular attention is given to the biological rationale, efficacy, safety, and clinical applicability of these approaches, as well as to the substantial heterogeneity in study design, patient selection, treatment initiation, and duration. The available evidence indicates that the potential benefit of maintenance is unlikely to be uniform across all recipients and should be interpreted in relation to AML molecular features, baseline relapse risk, prior treatment exposure, measurable residual disease status, expected toxicity, and the patient’s overall clinical condition. Although selected strategies may prolong remission and improve survival, the optimal agent, timing, duration, and target population remain incompletely defined. Current evidence therefore supports a risk-adapted and molecularly informed approach, while underscoring the need for adequately powered prospective studies using standardized endpoints and incorporating quality-of-life outcomes.
Disease relapse remains the leading cause of treatment failure in patients with acute myeloid leukemia (AML) undergoing allogeneic hematopoietic cell transplantation (allo-HCT). This narrative review, searched from Pubmed, from 2015 to 2026, critically synthesizes the available evidence on post-transplant maintenance strategies, which have evolved over the past three decades from conventional chemotherapy to molecularly targeted agents and interventions aimed at modulating antileukemic immunity. Particular attention is given to the biological rationale, efficacy, safety, and clinical applicability of these approaches, as well as to the substantial heterogeneity in study design, patient selection, and treatment initiation and duration. The available evidence indicates that the potential benefit of maintenance is unlikely to be uniform across all recipients and should be interpreted in relation to AML molecular features, baseline relapse risk, prior treatment exposure, measurable residual disease status, expected toxicity, and the patient’s overall clinical condition. Although selected strategies may prolong remission and improve survival, the optimal agent, timing, duration, and target population remain incompletely defined. Current evidence therefore supports a risk-adapted and molecularly informed approach, while underscoring the need for adequately powered prospective studies using standardized endpoints and incorporating quality-of-life outcomes.
22 March 2023 in International Journal of Laboratory Hematology
Acute myeloid leukemia (AML) produces more molecular, imaging, and clinical data per patient than any hematologist can hold in mind at once, and each revision of the WHO, ICC, and European LeukemiaNet (ELN) frameworks adds to the load. Artificial intelligence (AI) and machine learning (ML) now reach into every stage of AML care. Deep-learning models read therapy-relevant mutations directly from bone-marrow smears; automated flow-cytometry gating reproduces expert calls in under a minute; and the first AI pathology devices for hematology have cleared regulatory review and entered clinical use. Beyond diagnosis, ML captures the age-dependent weight of individual mutations that categorical ELN scoring misses, drug-response prediction for venetoclax–azacitidine has been validated across multiple external cohorts, and large language models are being tested for tumor-board support and trial matching. The next wave, from clonal-architecture modeling and single-cell foundation models to digital twins and reinforcement learning for adaptive dosing, could move AML management from reactive toward predictive, evolution-aware care. This review departs from existing AI-in-hematology surveys in three ways: we (i) restrict scope to AML and organize the field around clinical decision points rather than technology categories, (ii) grade every tool on a five-tier clinical-readiness level (CRL-AML 1–5), which exposes hundreds of models clustered at CRL-AML 1–2 and none yet in prospective clinical evaluation, and (iii) close with a numbered three-year agenda naming the consortia, datasets, and pragmatic trials needed to carry the field from publication to practice.