In this prospective study, we used the random number table method to equally divide 141 patients with chronic nonspecific low back pain (CNLBP) who met the inclusion criteria into 3 groups. One group who received massage manipulation therapy was recorded as the manipulation group (n = 47), one other group who received core strength training therapy was recorded as the training group (n = 47), and the other group who received massage manipulation combined with core strength training was recorded as the combination group (n = 47). All the patients were treated for 1w as the course of treatment, with the treatment conducted for 5 d/w for 4 w and 12 w of follow-up. The efficacies of the 3 groups were evaluated after treatment, and the visual analog scale (VAS) scores, Oswestry disability index (ODI) scores, and waist dynamic and static muscle endurance before and after treatment of the 3 groups were compared, and the long-term efficacies of the 3 groups were evaluated combined with the VAS scores at 6 w and 12 w after treatment. Our result was that, after treatment, the total effective rate of the combination group (95.74%) is significantly better than that of the manipulation group (80.85%) and the training group (78.72%) ( P < 0.05 ). After treatment, the VAS and ODI scores of the 3 groups significantly decreased, and the waist dynamic endurance and static muscle endurance significantly increased, and the condition of the combination group was significantly improved compared with that of the manipulation group and the training group ( P < 0.05 ). At 6w and 12w after treatment, the VAS scores of the manipulation group and training group were increased compared with those at the end of treatment ( P < 0.05 ), there was no significant change in the combination group ( P < 0.05 ), and the VAS scores of the combination group at 6 w and 12 w after treatment were lower than those of the manipulation group and training group at the same time point ( P < 0.05 ). This suggests that the synergistic effect of massage manipulation combined with core strength training in the treatment of CNLBP can effectively alleviate patients’ pain and waist dysfunction, enhance dynamic and static muscle endurance, and have significant short-term and long-term effects, which are worthy of promotion.

During rehabilitation, many postoperative patients need to perform autonomous massage on time and on demand. Thus, this paper develops an individualized, intelligent, and independent rehabilitation training system for based on image feature deep learning model acupoint massage that excludes human factors. The system, which innovatively integrates massage gesture recognition with human pose recognition. It relies on the binocular depth camera Kinect DK and Google MediaPipe Holistic pipeline to collect the real-time image feature data on joints and gestures of the patient in autonomous massage. Then the system calculates the coordinates of each finger joint, and computes the human poses with VGG-16, a convolutional neural network (CNN); the calculated results are translated, and presented in a virtual reality (VR) model based on Unity 3D, aiming to guide the patient actions in autonomous massage. This is because the image feature of the gesture recognition and pose recognition is hindered, when the hand or the human is occluded by the body or other things, owing to the limited recognition range of the hardware. The experimental results show that, the proposed system could correctly recognize up to 84% of non-occluded gestures, and up to 93% of non-occluded poses; the system also exhibited a good real-time performance, a high operability, and a low cost. Facing the lack of medical staff, our system can effectively improve the life quality of patients.