Continuous in vivo monitoring (CIVM) of pH value is essential for personalized medicine, as many diseases are closely related to acid–base imbalances. However, conventional pH meters are limited in their ability to perform CIVM due to excessive blood consumption, large device volume, frequent calibration, and inadequate real-time monitoring. There is thus an urgent need for a portable method for CIVM of pH value. To address this need, we propose a minimally invasive, continuous monitoring solution in the form of an implantable pH microneedle sensor (MNS) in this study. The MNS is based on the integration of an acupuncture needle (AN) and a Ag/AgCl reference electrode. We fabricate the sensor by electrochemically depositing platinum black and gold nanoparticles onto the AN and further modifying it with polyaniline to increase its sensitivity to hydrogen ions. The pH value is obtained by calculating the open circuit voltage between the modified AN and the reference electrode. The resulting MNS demonstrates excellent selectivity and a high nernstian response to pH (−57.4 mV per pH) over a broad range (pH = 4.0 to pH = 9.0). Both in vitro and in vivo experiments have verified the performance of the sensor, showcasing its potential for biomedical research and clinical practice. The MNS provides an alternative to conventional pH meters, offering a less invasive and more convenient way to perform CIVM of pH value. Moreover, this electrochemical implantable sensor based on AN and silver wires provides a simple and sensitive method for continuous in vivo detection of other biomarkers.
This study aims to integrate a convolutional neural network (CNN) and the Random Forest Model into a rehabilitation assessment device to provide a comprehensive gait analysis in the evaluation of movement disorders to help physicians evaluate rehabilitation progress by distinguishing gait characteristics under different walking modes. Equipped with accelerometers and six-axis force sensors, the device monitors body symmetry and upper limb strength during rehabilitation. Data were collected from normal and abnormal walking groups. A knee joint limiter was applied to subjects to simulate different levels of movement disorders. Features were extracted from the collected data and analyzed using a CNN. The overall performance was scored with Random Forest Model weights. Significant differences in average acceleration values between the moderately abnormal (MA) and severely abnormal (SA) groups (without vehicle assistance) were observed (p < 0.05), whereas no significant differences were found between the MA with vehicle assistance (MA-V) and SA with vehicle assistance (SA-V) groups (p > 0.05). Force sensor data showed good concentration in the normal walking group and more scatter in the SA-V group. The CNN and Random Forest Model accurately recognized gait conditions, achieving average accuracies of 88.4% and 92.3%, respectively, proving that the method mentioned above provides more accurate gait evaluations for patients with movement disorders.