Multifunctional hydrogel sensors with dynamic covalent networks for machine learning-assisted Parkinson's disease diagnosis and encrypted human-computer interaction

Flexible sensors hold significant application value in the fields of human-computer interaction and medical monitoring. In this study, we developed a smart hydrogel strain sensor based on dynamic covalent cross-linking. A multifunctional hydrogel was fabricated by constructing a multicomponent synergistic network composed of poly(acrylic acid) (PAA), dialdehyde carboxymethyl cellulose (OCMC), gelatin methacryloyl (GelMA), and lignosulfonate methacrylate (MLS). This hydrogel (AGOM) exhibited synergistically enhanced interfacial adhesion strength (>77.8 kPa) and mechanical properties, with an elongation at break exceeding 1820%. The unique gradient network structure not only provides the material with excellent electrical conductivity (conductivity > 0.55 S/m). A message transmission system has been developed based on the principles of Morse code, allowing for the coding and decoding of messages by recognizing different amplitudes of finger bending. Electrodes constructed from this hydrogel reliably record human electromyography (EMG) and electrocardiography (ECG) signals. The conductive network, combined with its wide-range and high-sensitivity characteristics (GF=5.31), enables the sensor to accurately recognize clinical symptoms. This includes the characteristic tremor signals associated with Parkinson's disease. By leveraging machine learning, the sensor achieves a high recognition rate. This technology offers an innovative solution for monitoring and assisted treatment of Parkinson's disease, presenting significant application prospects in the field of intelligent medicine. ● A smart hydrogel strain sensor based on dynamic covalent cross-linking developed by component synergy network. ● Hydrogels have excellent bacteriostatic and biological properties and can be applied to human physiological signal monitoring. ● This sensor recognizes the symptoms of Parkinson's disease and achieves high recognition rates through assisted machine learning.