Preprints

Innovative identification technologies for hematopoietic stem cells (HSCs) have advanced the frontiers of stem cell biology. However, most analytical techniques capture only a single snapshot, disregarding the temporal context. A comprehensive understanding of the temporal heterogeneity of HSCs necessitates live-cell, real-time and non-invasive analysis. Here, we developed a prediction system for HSC diversity by integrating single-HSC ex vivo expansion technology with quantitative phase imaging (QPI)-driven machine learning. By analyzing single-cell kinetics with QPI, we discovered previously undetectable diversity among HSCs that snapshot analysis fails to capture. Our QPI-driven algorithm quantitatively evaluates the stemness of individual HSCs and incorporates temporal information to significantly improve prediction accuracy. This platform marks a paradigm shift from “identification” to “prediction”, enabling us to forecast HSC status by analyzing their past temporal kinetics.