Differential impact of CD34+ cell dose for different age groups in allogeneic hematopoietic cell transplantation for acute leukemia: a machine learning–based discovery

• Published in: Experimental hematology Vol. 141; p. 104684
• Main Authors: Qu, Yiyang, Shourabizadeh, Hamed, Subramanian, Aravind, Aleman, Dionne M., Rousseau, Louis-Martin, Law, Arjun D., Viswabandya, Auro, Michelis, Fotios V.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Inc 01.01.2025
• Subjects: Adolescent; Adult; Advanced Basic Science; Age Factors; Aged; Antigens, CD34; Child; Female; Hematology, Oncology, and Palliative Medicine; Hematopoietic Stem Cell Transplantation - methods; Humans; Leukemia, Myeloid, Acute - mortality; Leukemia, Myeloid, Acute - therapy; Machine Learning; Male; Middle Aged; Precursor Cell Lymphoblastic Leukemia-Lymphoma - mortality; Precursor Cell Lymphoblastic Leukemia-Lymphoma - therapy; Transplantation, Homologous; Young Adult
• ISSN: 0301-472X; 1873-2399; 1873-2399
• DOI: 10.1016/j.exphem.2024.104684

Allogeneic hematopoietic cell transplantation (allo-HCT) presents a potentially curative treatment for hematologic malignancies yet carries associated risks and complications. Continuous research focuses on predicting outcomes and identifying risk factors. Notably, the influence of CD34+ cell dose on overall survival (OS) has been the subject of numerous studies yielding contradictory results. We developed machine learning (ML) models to predict allo-HCT outcomes and, through the application of SHapley Additive exPlanations (SHAP), an explainable artificial intelligence (XAI) technique enabled the identification of new and clinically relevant feature-outcome relationships. In particular, we identified a clear interaction between CD34+ cell dose of peripheral blood stem cell (PBSC) grafts and patient age at allo-HCT for patients with acute leukemia. Results of multivariable analysis validated the interaction effect: in young patients with acute leukemia (aged ≤45 years), low dose of CD34+ cells (<4.3 × 106 CD34+/kg) was associated with better OS against high dose (≥7 ×106 CD34+/kg) (hazard ratio [HR], 0.38; p = 0.019), while for older patients with acute leukemia (>45 years), low CD34+ cell dose (<3.8 ×106 CD34+/kg) was associated with worse OS against high dose (≥6.1 ×106 CD34+/kg) (HR, 1.58; p = 0.033). In conclusion, our findings suggest that tailoring CD34+ cell dose by patient age may benefit patients with acute leukemia undergoing allo-HCT, while XAI showcases excellent proficiency in revealing such interactions. •We developed machine learning models to predict allo-HCT outcomes and, through the application of SHAP, identified new and clinically relevant feature-outcome relationships.•In particular, we identified a clear interaction between CD34+ cell dose of peripheral blood stem cell grafts and patient age at allo-HCT for patients with acute leukemia.•Through the above methodology, we determined that in young patients with acute leukemia (aged ≤45 years), a lower dose of CD34+ cells was associated with better OS, while in older patients with acute leukemia (aged >45 years), a higher cell dose correlated with improved outcomes.•Our findings suggest that tailoring CD34+ cell dose by patient age may benefit patients with acute leukemia undergoing allo-HCT.