Nirali N. Shah

Acute leukemia is a hematologic malignancy that affects people of all ages. Immunotherapies, including T-cell engagers, antibody-drug conjugates, and chimeric antigen receptor T-cell therapies have contributed to a paradigm shift in the treatment of patients with acute leukemia. Combined with advancements in allogeneic hematopoietic stem cell transplant and targeted therapy development, patients with acute leukemia have additional effective treatment options, providing the possibility of long-term remission. However, these advances have resulted in a complex and dynamic treatment landscape for clinicians to navigate. To guide the oncology community and provide a framework for patient care, the Society for Immunotherapy of Cancer convened a panel of experts to develop this clinical practice guideline on immunotherapy for the treatment of acute leukemia. Drawing from published data and clinical experience, the Expert Panel developed evidence-based and consensus-based recommendations relating to diagnostics; immunotherapies for the treatment of acute lymphoblastic leukemia, acute myeloid leukemia, and blastic plasmacytoid dendritic cell neoplasm; toxicity and safety management; treatment sequencing; and patient education and quality of life.

Supplementary Table S1 compares predictive models for CAR T-cell–associated CRS and ICANS, including study populations, modeling approaches, variable selection methods, validation strategies, and model performance metrics.

Chimeric antigen receptor (CAR) T-cell therapy is increasingly utilized with expanding indications beyond hematologic malignancies. Here, we review existing models developed for predicting toxicities in the CAR T-cell setting and identify both strengths and challenges emerging with their application. Predictive modeling approaches offer potential to guide risk stratification and inform clinical decision-making, but small sample sizes, overfitting, and poor data quality have limited model reproducibility and widespread adoption. As utilization of CAR T-cell therapy broadens, identifying additional biomarkers, developing context-specific models, standardizing guidelines for emerging toxicities, and leveraging federated learning to promote collaborative data sharing will be critical. Significance:Predictive models integrating biomarkers and clinical variables are increasingly used to forecast potential toxicities after CAR T-cell therapy. However, due to heterogeneity in patient populations and cellular therapy products, the rapidly evolving nature of the field, and continued advancements in management of inflammatory toxicities, modeling in CAR T-cell therapy faces significant challenges. This comprehensive review of existing/emerging models serves to delineate components of developing predictive models including discrimination, calibration, biomarker integration, validation, and mitigation of overfitting while highlighting strengths, opportunities for improvement, and future directions applicable to CAR T-cell therapy.

Chimeric antigen receptor (CAR) T-cell therapy is increasingly utilized with expanding indications beyond hematologic malignancies. Here, we review existing models developed for predicting toxicities in the CAR T-cell setting and identify both strengths and challenges emerging with their application. Predictive modeling approaches offer potential to guide risk stratification and inform clinical decision-making, but small sample sizes, overfitting, and poor data quality have limited model reproducibility and widespread adoption. As utilization of CAR T-cell therapy broadens, identifying additional biomarkers, developing context-specific models, standardizing guidelines for emerging toxicities, and leveraging federated learning to promote collaborative data sharing will be critical. Significance: Predictive models integrating biomarkers and clinical variables are increasingly used to forecast potential toxicities after CAR T-cell therapy. However, due to heterogeneity in patient populations and cellular therapy products, the rapidly evolving nature of the field, and continued advancements in management of inflammatory toxicities, modeling in CAR T-cell therapy faces significant challenges. This comprehensive review of existing/emerging models serves to delineate components of developing predictive models including discrimination, calibration, biomarker integration, validation, and mitigation of overfitting while highlighting strengths, opportunities for improvement, and future directions applicable to CAR T-cell therapy.