Millimeter Wave(mmWave) radar has been widely used in vital sign monitoring with non-contact and privacy protection. To reduce the effect of random body motion, respiration, and its harmonics on heart rate estimation, the heart rate monitoring based on frequency-modulated continuous-wave (FMCW) radar is researched in this paper. First, a vital sign signal extraction algorithm is designed for the Range Bin variation caused by random body motion and heavy breathing. Second, a heartbeat signal extraction algorithm is designed based on Adaptive Notch Filter (ANF) and Empirical Wavelet Transform (EWT). The harmonic of respiration will be suppressed, and the heartbeat signal will be separated. Finally, the weighted estimation is performed according to the relationship of harmonics of the heartbeat signal to obtain the heart rate. Twenty subjects are invited to the experiment. The experimental results show that the proposed method can improve the signal-to-noise ratio (SNR), reduce the harmonic interference, and estimate the heart rate with a mean absolute error less than 4 BPM.

Background: In contrast to the large and increasing number of patients with stroke, clinical rehabilitation resources cannot meet their rehabilitation needs. Especially for those discharged, ways to carry out effective rehabilitation training without the supervision of physicians and receive guidance from physicians remain urgent problems to be solved in clinical rehabilitation and have become a research hot spot at home and abroad. At present, there are many studies on home rehabilitation training based on wearable devices, Kinect, among others, but these have disadvantages (eg, complex systems, high price, and unsatisfactory rehabilitation effects). Objective: This study aims to design a remote intelligent rehabilitation training system based on wearable devices and human-computer interaction training tasks, and to evaluate the effectiveness and safety of the remote rehabilitation training system for nonphysician-supervised motor rehabilitation training of patients with stroke through a clinical trial study. Methods: A total of 120 inpatients with stroke having limb motor dysfunction were enrolled via a randomized, parallel-controlled method in the rehabilitation institutions, and a 3-week clinical trial was conducted in the rehabilitation hall with 60 patients in the experimental group and 60 in the control group. The patients in the experimental group used the remote rehabilitation training system for rehabilitation training and routine clinical physical therapy (PT) training and received routine drug treatment every day. The patients in the control group received routine clinical occupational therapy (OT) training and routine clinical PT training and routine drug treatment every day. At the beginning of the training (baseline) and after 3 weeks, the Fugl-Meyer Motor Function Rating scale was scored by rehabilitation physicians, and the results were compared and analyzed. Results: Statistics were performed using SAS software (version 9.4). The total mean Fugl-Meyer score improved by 11.98 (SD 8.46; 95% CI 9.69-14.27) in the control group and 17.56 (SD 11.65; 95% CI 14.37-20.74) in the experimental group, and the difference between the 2 groups was statistically significant (P=.005). Among them, the mean Fugl-Meyer upper extremity score improved by 7.45 (SD 7.24; 95% CI 5.50-9.41) in the control group and 11.28 (SD 8.59; 95% CI 8.93-13.62) in the experimental group, and the difference between the 2 groups was statistically significant (P=.01). The mean Fugl-Meyer lower extremity score improved by 4.53 (SD 4.42; 95% CI 3.33-5.72) in the control group and 6.28 (SD 5.28; 95% CI 4.84-7.72) in the experimental group, and there was no significant difference between the 2 groups (P=.06). The test results showed that the experimental group was better than the control group, and that the patients’ motor ability was improved. Conclusions: The remote rehabilitation training system designed based on wearable devices and human-computer interaction training tasks can replace routine clinical OT training. In the future, through medical device registration certification, the system will be used without the participation of physicians or therapists, such as in rehabilitation training halls, and in remote environments, such as communities and homes. Trial Registration: Chinese Clinical Trial Registry ChiCTR2200061310; https://tinyurl.com/34ka2725

Objective: Identifying human actions from video data is an important problem in the fields of intelligent rehabilitation assessment. Motion feature extraction and pattern recognition are the two key procedures to achieve such goals. Traditional action recognition models are usually based on the geometric features manually extracted from video frames, which are however difficult to adapt to complex scenarios and cannot achieve high-precision recognition and robustness. We investigate a motion recognition model and apply it to recognize the sequence of complicated actions of a traditional Chinese exercise (ie, Baduanjin). Methods: We first developed a combined convolutional neural network (CNN) and long short-term memory (LSTM) model for recognizing the sequence of actions captured in video frames, and applied it to recognize the actions of Baduanjin. Moreover, this method has been compared with the traditional action recognition model based on geometric motion features in which Openpose is used to identify the joint positions in the skeletons. Results: Its performance of high recognition accuracy has been verified on the testing video dataset, containing the video clips from 18 different practicers. The CNN-LSTM recognition model achieved 96.43% accuracy on the testing set; while those manually extracted features in the traditional action recognition model were only able to achieve 66.07% classification accuracy on the testing video dataset. Conclusions: The abstract image features extracted by the CNN module are more effective on improving the classification accuracy of the LSTM model. The proposed CNN-LSTM based method can be a useful tool in recognizing the complicated actions. Clinical and Translational Impact Statement: The proposed algorithm can recognize the complicated actions in rehabilitation training, and thus has the potential to realize intelligent rehabilitation assessment for home applications.

Clinical rehabilitation assessment is an important part of the therapy process because it is the premise for prescribing suitable rehabilitation interventions. However, the commonly used assessment scales have the following two drawbacks: (1) they are susceptible to subjective factors; (2) they only have several rating levels and are influenced by a ceiling effect, making it impossible to exactly detect any further improvement in the movement. Meanwhile, energy constraints are a primary design consideration in wearable sensor network systems since they are often battery-operated. Traditionally, for wearable sensor network systems that follow the Shannon/Nyquist sampling theorem, there are many data that need to be sampled and transmitted. This paper proposes a novel wearable sensor network system to monitor and quantitatively assess the upper limb motion function, based on compressed sensing technology. With the sparse representation model, less data is transmitted to the computer than with traditional systems. The experimental results show that the accelerometer signals of Bobath handshake and shoulder touch exercises can be compressed, and the length of the compressed signal is less than 1/3 of the raw signal length. More importantly, the reconstruction errors have no influence on the predictive accuracy of the Brunnstrom stage classification model. It also indicated that the proposed system can not only reduce the amount of data during the sampling and transmission processes, but also, the reconstructed accelerometer signals can be used for quantitative assessment without any loss of useful information.

In order to solve the shortcomings of the current clinical scale assessment for stroke patients, such as excessive time consumption, strong subjectivity, and coarse grading, this study designed an intelligent rehabilitation assessment system based on wearable devices and a machine learning algorithm and explored the effectiveness of the system in assessing patients’ rehabilitation outcomes. The accuracy and effectiveness of the intelligent rehabilitation assessment system were verified by comparing the consistency and time between the designed intelligent rehabilitation assessment system scores and the clinical Fugl–Meyer assessment (FMA) scores. A total of 120 stroke patients from two hospitals participated as volunteers in the trial study, and statistical analyses of the two assessment methods were performed. The results showed that the R² of the total score regression analysis for both methods was 0.9667, 95% CI 0.92–0.98, p < 0.001, and the mean of the deviation was 0.30, 95% CI 0.57–1.17. The percentages of deviations/relative deviations falling within the mean ± 1.96 SD of deviations/relative deviations were 92.50% and 95.83%, respectively. The mean time for system assessment was 35.00% less than that for clinician assessment, p < 0.05. Therefore, wearable intelligent machine learning rehabilitation assessment has a strong and significant correlation with clinician assessment, and the time spent is significantly reduced, which provides an accurate, objective, and effective solution for clinical rehabilitation assessment and remote rehabilitation without the presence of physicians.

Motor function evaluation is a significant part of post-stroke rehabilitation protocols, and the evaluation of wrist motor function helps provide patients with individualized rehabilitation training programs. However, traditional assessment is coarsely graded, lacks quantitative analysis, and relies heavily on clinical experience. In order to objectively quantify wrist motor dysfunction in stroke patients, a novel quantitative evaluation system based on force feedback and machine learning algorithm was proposed. Sensors embedded in the force-feedback robot record the kinematic and movement data of the subject, and the rehabilitation doctor used an evaluation scale to score the wrist function of the subject. The quantitative evaluation models of wrist motion function based on random forest (RF), support vector machine regression (SVR), k-nearest neighbor (KNN), and back propagation neural network (BPNN) were established, respectively. To verify the effectiveness of the proposed quantitative evaluation system, 25 stroke patients and 10 healthy volunteers were recruited in this study. Experimental results show that the evaluation accuracy of the four models is all above 88%. The accuracy of BPNN model is 94.26%, and the Pearson correlation coefficient between model prediction and clinician scores is 0.964, indicating that the BPNN model can accurately evaluate the wrist motor function for stroke patients. In addition, there was a significant correlation between the prediction score of the quantitative assessment system and the physician scale score (p < 0.05). The proposed system enables quantitative and refined assessment of wrist motor function in stroke patients and has the feasibility of helping rehabilitation physicians in evaluating patients’ motor function clinically.