Artificial Intelligence-Powered Electronic Skin

Abstract

Skin-interfaced electronics is gradually changing medical practices by enabling continuous and noninvasive tracking of physiological and biochemical information. With the rise of big data and digital medicine, next-generation electronic skin (e-skin) will be able to use artificial intelligence (AI) to optimize its design as well as uncover user-personalized health profiles. Recent multimodal e-skin platforms have already employed machine learning (ML) algorithms for autonomous data analytics. Unfortunately, there is a lack of appropriate AI protocols and guidelines for e-skin devices, resulting in overly complex models and non-reproducible conclusions for simple applications. This review aims to present AI technologies in e-skin hardware and assess their potential for new inspired integrated platform solutions. We outline recent breakthroughs in AI strategies and their applications in engineering e-skins as well as understanding health information collected by e-skins, highlighting the transformative deployment of AI in robotics, prosthetics, virtual reality, and personalized healthcare. We also discuss the challenges and prospects of AI-powered e-skins as well as predictions for the future trajectory of smart e-skins.

Keywords: artificial intelligence; electronic skin; human-machine interfaces; machine learning; personalized healthcare.

Figure 1.

Overview of AI-powered electronic skin (e-skin) and machine learning (ML) pipelines. E-skin provides access to human information or serves as an interface to robotics by continuous and noninvasive monitoring of multimodal physical and biochemical sensors. The data stream is constructed and transformed into a standard numerical format through data preprocessing and feature extraction. Based on the intrinsic data properties, different ML algorithms can be selected and trained, allowing for real-world applications. GPT, generative pre-trained transformer.

Figure 2.

Emerging sensors in e-skin for health monitoring and robotics. The combination of physical and biochemical sensors provides access to force sensing and mapping, electrophysiology, as well as biochemical substances in body fluids and surroundings.

Figure 3.

ML optimizations for e-skin designs. AI algorithms serve as an alternative pathway to optimize and explore materials synthesis, facilitate automatic mass-fabrication, and optimize current sensor limits.

Figure 4.

AI-powered e-skin for human-machine interfaces (HMI). ML bridges the gap between humans and machines through task assistance, robotic control, and virtual reality.

Figure 5.

AI-powered e-skins for personalized healthcare and predictive disease diagnostics. a, Cardiovascular health can be investigated through continuous monitoring of one’s cardiac activities (ECG, pulse waveforms, etc.) with e-skins. Integrating autonomous analysis through AI algorithms creates further potential for screening urgent conditions such as arrythmias. b, The application of AI-powered e-skin can extend to mental health which is a complex event that involves behavioral and physiological responses, metabolic changes, and fluctuations in a number of stress hormones. PTSD, post-traumatic stress disorder. c, Biomarker discovery through AI algorithms will further aid in finding new missing information potential links between measured sensor data and health status of individuals. d, Personalized therapy can be achieved by measuring individual’s genetic and metabolic status using e-skins to develop highly targeted medicine for medical treatment.