Inflammatory Biomarker Clusters Are Predictive of Response and Toxicity in Large B-Cell Lymphoma Treated With CD19 CAR-T Cell Therapy

As there are several known adverse events related to CAR T-cell therapy-related but no firm predictors for which adverse event will occur for each patient, researchers developed a machine-learning approach to identify biomarker clusters closely associated with various outcomes. As proof-of-principle, they then developed a prediction model for cluster type and applied it to an external center cohort. Results were presented at ASH.