Longitudinal alignments and syntheses of multimodal clinical data for personalized medicine with the PULSE framework

Abstract

Multimodal models capable of imputing diverse data used in single-cell biology studies provide potential foundational opportunities in clinical practice. However, patient data uniquely comprise longitudinal mosaic measurements that reflect underlying physiological dynamics and exhibit temporal covariation, demanding a specialized approach. Here we present Patient Unified Longitudinal Signal Engine (PULSE), a longitudinal self-supervised framework that explicitly encodes personalized past states (historical paired modalities) to reconstruct full profiles from subsequent unpaired measurements, thus enhancing current visit multimodal alignment and generation. Applied to the UK Biobank, PULSE accurately generates metabolomic profiles and proteomic profiles from sparse routine blood tests. Compared with the ground truth metabolomic data (251 biomarkers), PULSE-generated profiles outperformed all benchmark methods. Furthermore, the framework accommodates incorporation of retinal images, electronic health records and blood markers with disease prediction: models trained on the generated proteomic profiles achieved areas under the curve of 0.72–0.83 for six common diseases, comparable to that using ground-truth proteomic data. The PULSE framework demonstrates that cross-modal alignment captures the continuous spectrum of disease physiology and extracts robust features that transcend the limitations of traditional binary case–controls. PULSE is an AI framework that uses patients’ longitudinal electronic health records to accurately generate within- and cross-modal data from routine clinical laboratory tests, enabling cost-effective precision medicine across diverse biomedical settings.