CIAdex: Label‐Free Cell Identification and Aging Quantification Using Single‐Cell Infrared Spectral Fingerprints

Ensuring accurate cell identity and monitoring aging are critical for the safety and efficacy of cell therapies. Despite rapid iteration of methodology, current methods for characterizing cell products are often multi‐label dependent and lack sensitivity to subtle aging changes. Here we present Cell Identification and Aging Index (CIAdex), a machine‐learning framework that utilizes single‐cell Fourier‐transform infrared (FTIR) spectral fingerprints to achieve label‐free, precise cell identity verification and quantitative aging assessment. By extracting intrinsic FTIR spectral variables corresponding to distinct cellular biomolecular features and applying linear discriminant analysis and XGBoost algorithms, CIAdex enables distinction of lineage‐, donor‐, and batch‐specific cell populations, and generates a quantitative aging index (trPDL/trPN) that reflects cellular aging dynamics during culture expansion. Notably, trPDL/trPN quantitatively detects subtle age‐related shifts among different batches and drug‐induced senescence or rejuvenation effects, which are unmeasurable by conventional existing methods. Together, our work demonstrates that CIAdex offers a novel, robust, label‐free approach for simultaneous cell population identity verification and aging quantification, providing valuable metrics to enhance quality control and optimize efficacy in cell manufacturing and therapy development.