AI-Driven Sustainable Textile Materials for Healthcare Monitoring: Materials Design, Composite Architectures, and Clinical Translation

Textile sensors offer a route to physiological monitoring through clothing, with practical performance determined by material properties, sensing interfaces, and stability during movement, perspiration, and repeated use. This review examines conductive fibers, polymer composites, soft ionic materials, and textile architectures for electrophysiological, respiratory, movement, temperature, and sweat monitoring. It compares application-specific material and integration strategies and examines how artificial intelligence supports composition selection, inverse design, and signal interpretation. An application-oriented framework links these choices to measurement quality, service life, repair, and recovery. Recurring trade-offs involve sensitivity and stability, conformal contact and solvent retention, and durable bonding and component separation. Data-driven methods support candidate screening and signal analysis, with their performance established through experimental validation. Heterogeneous protocols and evaluation settings limit direct comparison and translation to long-term garment use. Future priorities include durable interfaces, designs facilitating maintenance and recovery, validation across users and manufacturing batches, combined wear-and-care testing, and assessment of recovered materials in subsequent devices. These efforts would strengthen evaluation of monitoring reliability and environmental benefits over the intended service life.