Machine Learning Assisted, Label-Free Rapid Optical Imaging Detection of Chimeric Antigen Receptor T-Cells in Whole Blood Samples

Chimeric antigen receptor (CAR) T-cell therapy is an effective treatment for hematologic malignancies. However, it is limited by high costs, risk of severe toxicities such as cytokine release syndrome and neurotoxicity, and heterogeneous patient responses. Current therapy monitoring depends largely on subjective symptom assessment, routine laboratory tests, and basic vital signs, without real-time, quantitative evaluation of CAR T-cell expansion or activation in clinical practice. This lack of timely immune monitoring hampers individualized care and contributes to increased treatment costs. To address this need, we present a proof-of-concept, label-free Rapid Optical Imaging (ROI) biosensor with automated machine learning analysis for direct quantification of functional CAR T-cells from whole blood. This microfluidic platform integrates leukocyte separation, capture, and detection on a single chip, thereby eliminating centrifugation, staining, and operator-dependent interpretation. For validation, 50 μL whole blood samples spiked with Jurkat cells expressing a CD19 CAR underwent red blood cell depletion by agglutination and microfiltration. The leukocyte-enriched fraction was then incubated on a sensor chip functionalized with recombinant CD19 protein. Captured CAR T-cells were imaged by bright-field microscopy and automatically enumerated using a machine learning algorithm. A calibration curve was established across clinically relevant concentrations (1–1,000 cells/mL), with results validated against fluorescence microscopy and flow cytometry. This ROI biosensor enables rapid, quantitative, and label-free CAR T-cell detection from whole blood without specialized equipment or infrastructure. With further development, it could provide a cost-effective point-of-care tool for real-time immune monitoring and improved clinical management of patients receiving CAR T-cell therapy.