Multimodal AI for Aging: Integrating Clinical, Imaging, Sensor, and Omics Data

Aging is a complex, multi-system process that shapes health trajectories and risk for age-related outcomes across the life course. At the same time, aging research is generating rapidly expanding datasets—ranging from electronic health records and laboratory measures to medical imaging, wearable and mobile sensor streams, and high-dimensional omics profiles. These modalities capture complementary signals, but they are often analyzed in isolation, limiting our ability to build coherent, clinically useful models of aging.This Research Topic focuses on computational, AI, and machine-learning approaches for modeling aging and age-related outcomes. We encourage submissions that leverage multimodal data to generate interpretable, actionable insights into aging, including approaches that improve prediction, phenotyping, risk stratification, and mechanistic understanding. Particular emphasis is placed on models that are transparent, robust, and designed for translation—supporting reproducibility, fairness, and deployment across diverse populations and real-world settings.We welcome contributions that address (but are not limited to):1. Multimodal integration of clinical, imaging, sensor/wearable, and omics data for aging-related research2. AI/ML methods for biological age estimation, aging clocks, and digital biomarkers3. Prediction of age-related outcomes (e.g., frailty, functional decline, multimorbidity, hospitalization, mortality)4. Interpretable and causal modeling approaches linking multimodal features to aging mechanisms and trajectories5. Validation, benchmarking, and external generalization across cohorts, sites, and populations6. Bias, fairness, privacy, and governance considerations in AI for aging7. Tools, pipelines, and best practices that enable reproducible multimodal aging researchThis Topic aims to bring together method developers and applied researchers to accelerate the development of reliable multimodal AI systems that advance aging science and support decision-making in research and clinical practice. Topic editors: Eloïse Berson, Jorge Sanz Ros Source: https://www.frontiersin.org/research-topics/77516/multimodal-ai-for-aging-integrating-clinical-imaging-sensor-and-omics-data