Stretchable and anti-impact iontronic pressure sensor with an ultrabroad linear range for biophysical monitoring and deep learning-aided knee rehabilitation

• Published in: Microsystems & nanoengineering 2021-11, Vol.7 (1), p.92-92, Article 92
• Main Authors: Xu, Hongcheng, Gao, Libo, Zhao, Haitao, Huang, Hanlin, Wang, Yuejiao, Chen, Gang, Qin, Yuxin, Zhao, Ningjuan, Xu, Dandan, Duan, Ling, Li, Xuan, Li, Siyu, Luo, Zhongbao, Wang, Weidong, Lu, Yang
• Format: Article
• Language: English
• Subjects: 639/166/987; 639/301/357; 639/925/357; Algorithms; Bone surgery; Deep learning; Engineering; Impact loads; Knee; Machine learning; Muscles; Orthopedics; Plantar pressure; Pressure; Pressure sensors; Rehabilitation; Sensitivity; Sensors; Signal monitoring; Signal to noise ratio; Stretchability
• ISSN: 2055-7434; 2096-1030; 2055-7434
• DOI: 10.1038/s41378-021-00318-2

Monitoring biophysical signals such as body or organ movements and other physical phenomena is necessary for patient rehabilitation. However, stretchable flexible pressure sensors with high sensitivity and a broad range that can meet these requirements are still lacking. Herein, we successfully monitored various vital biophysical features and implemented in-sensor dynamic deep learning for knee rehabilitation using an ultrabroad linear range and high-sensitivity stretchable iontronic pressure sensor (SIPS). We optimized the topological structure and material composition of the electrode to build a fully stretching on-skin sensor. The high sensitivity (12.43 kPa −1 ), ultrabroad linear sensing range (1 MPa), high pressure resolution (6.4 Pa), long-term durability (no decay after 12000 cycles), and excellent stretchability (up to 20%) allow the sensor to maintain operating stability, even in emergency cases with a high sudden impact force (near 1 MPa) applied to the sensor. As a practical demonstration, the SIPS can positively track biophysical signals such as pulse waves, muscle movements, and plantar pressure. Importantly, with the help of a neuro-inspired fully convolutional network algorithm, the SIPS can accurately predict knee joint postures for better rehabilitation after orthopedic surgery. Our SIPS has potential as a promising candidate for wearable electronics and artificial intelligent medical engineering owing to its unique high signal-to-noise ratio and ultrabroad linear range. An ultrabroad-linear range (1 MPa) iontronic pressure sensor with superior sensitivity (12.43 kPa -1 ) and stretchability (up to 20%) was proposed for biophysical monitoring and deep learning-based knee-rehabilitation training.