Artificial Intelligence Accelerates the Interpretation of Measurable Residual B Lymphoblastic Leukemia by Flow Cytometry Open Access

• Artificial intelligence reduces manual analysis time for the detection of measurable residual disease to 1 minute per case, on average.

• Our simplified AI-assisted analysis has the potential to increase accessibility to measurable residual disease testing by flow cytometry.

Measurable residual disease (MRD) assessment by flow cytometry (FC) plays an essential role in prognosis and therapy escalation of B-cell acute lymphoblastic leukemia (B-ALL). However, the high degree of expertise and manual analysis time required limits the availability of this assay. To overcome this limitation, we developed a data-enhancing artificial intelligence (AI) pipeline that accelerates and simplifies MRD analysis. Unaltered FC files from 171 B-ALL MRD-positive and 89 MRD-negative cases were processed through an AI pipeline trained with 31 expert-gated negative controls. Cluster-informed downsampling reduced FC files from 1.2 million to 155,884 cells per case, on average (87% cellularity reduction), while preserving small MRD populations (median 100% retention for MRD <1%) and allowing for true %MRD estimates using a correction factor. A deep neural network (DNN) cell classifier automatically identified normal hematopoietic subsets (macro-averaged F1 score = 0.86); and an AI measure of anomaly discriminated B-ALL from benign mononuclear (area under the curve, AUC = 0.98) or B-lymphoid cells (AUC = 0.94). Manual analysis of AI-enhanced files was completed in only 1.01 minutes per case, on average (SD = 0.57); with 100% positive agreement with conventional analysis (for MRD ≥ 0.01%), 100% negative agreement, and excellent quantitative correlation (R2 = 0.92). Our cloud-based AI-enhancement solution accelerates B-ALL MRD identification without compromising test performance, and has the potential of facilitating BALL-MRD analysis by more clinical laboratories.