Objective:To design a center-driven upper limb rehabilitation robot, and to perform trajectory planning and simulation based experimental validation for two rehabilitation tasks: object retrieval and quadrilateral drawing.Methods:Firstly, the mechanical structure and system of the center-driven upper limb rehabilitation robot were designed. The mechanical structure included a micro-power system installed at the end of the robotic arm, enabling four-degree-of-freedom motion through a multi-stage transmission system. The system was mainly divided into two parts: the control system and the power system. Then, a kinematic model was established using the D-H method, and the safe workspace of the robot was analyzed. Finally, the quintic polynomial interpolation method was adopted to plan the motion trajectories for two typical rehabilitation actions, namely object retrieval and quadrilateral drawing, and it was validated through Matlab simulation experiments.Results:The object retrieval action of the center-driven upper limb rehabilitation robot was divided into six stages. In Stage 1, the end handle of the robotic arm was moved from the origin to the initial position within 3 s, with only shoulder flexion/extension angle ( θ1) rotated by ?60°. Stage 2 was defined as a motion interval lasting 2 s, during which all joints remained stationary. In Stage 3, the end handle was moved from the initial position to the end position within 5 s, with θ1 rotated by 30°, shoulder adduction/abduction angle ( θ2) by 15°, and elbow flexion/extension angle ( θ3) by 60°. Stage 4 was a rest interval of 3 s, with all joints kept stationary. In Stage 5, the end handle was returned to the initial position within 5 s, with θ1 rotated by ?30°, θ2 by ?15°, and θ3 by ?60°. Stage 6 was a final rest interval of 2 s, with all joints stationary. The quadrilateral drawing motion of the center-driven upper limb rehabilitation robot was also divided into six stages. In Stage 1, the end handle was moved from the origin to vertex 1 of the quadrilateral in 5 s; θ1 remained unchanged, θ2 was rotated by 30°, and θ3 by 60°. Stage 2 was defined as a motion interval lasting 2 s, during which all joints remained stationary. In Stage 3, the end handle was moved from vertex 1 to vertex 2 in 3 s, with θ1 rotated by 30°, θ2 by ?60°, and θ3 by ?60°. In Stage 4, the end handle was moved from vertex 2 to vertex 3 in 4 s, with θ1 rotated by ?60°, θ2 by 30°, and θ3 unchanged. In Stage 5, the end handle was moved from vertex 3 to vertex 4 in 4 s, with θ1 rotated by ?30°, θ2 by 15°, and θ3 by 60°. In Stage 6, the end handle was moved from vertex 4 back to vertex 1 in 2 s, with θ1 rotated by 60°, θ2 by 15°, and θ3 unchanged. Simulation results showed that the shoulder, elbow, and wrist joint angles all varied smoothly along the quintic polynomial trajectories, and the end-effector accurately tracked the predefined paths for both object retrieval and quadrilateral drawing. Conclusions:A center-driven upper limb rehabilitation robot was designed, which can realize the trajectory planning of two rehabilitation actions, namely object retrieval and quadrilateral drawing.

Creutzfeldt-Jakob disease(CJD)is a rapidly progressive and fatal neurodegenerative disorder caused by prions,with certain infectivity and iatrogenic transmission risks.With the rapid progress and application of new dia-gnostic biomarkers and detection methods,as well as the construction and improvement of surveillance and reporting systems,the detection of CJD in patients domestically and internationally has shown an increasing trend year by year.Due to its long incubation period and heterogeneity of early symptoms,early identification and diagnosis of the disease is difficult,increasing the risk of transmission within medical institutions.Currently,there is a lack of con-sensus on the infection prevention and control of CJD.In order to timely identify and diagnose CJD as well as effec-tively block its transmission in medical institutions,this consensus summarizes 15 clinical concerns and formulates 24 specific recommendations based on the latest domestic and international research findings and clinical evidence,as well as combines with clinical practice,aiming to standardize healthcare-associated infection prevention and control measures for CJD and reduce its transmission risk in medical institutions.

Creutzfeldt-Jakob disease(CJD)is a rapidly progressive and fatal neurodegenerative disorder caused by prions,with certain infectivity and iatrogenic transmission risks.With the rapid progress and application of new dia-gnostic biomarkers and detection methods,as well as the construction and improvement of surveillance and reporting systems,the detection of CJD in patients domestically and internationally has shown an increasing trend year by year.Due to its long incubation period and heterogeneity of early symptoms,early identification and diagnosis of the disease is difficult,increasing the risk of transmission within medical institutions.Currently,there is a lack of con-sensus on the infection prevention and control of CJD.In order to timely identify and diagnose CJD as well as effec-tively block its transmission in medical institutions,this consensus summarizes 15 clinical concerns and formulates 24 specific recommendations based on the latest domestic and international research findings and clinical evidence,as well as combines with clinical practice,aiming to standardize healthcare-associated infection prevention and control measures for CJD and reduce its transmission risk in medical institutions.

Objective:To design a new type of intelligent power-assisted hip disarticulation prosthesis and to use experiments to verify its kinematic performance.Methods:The main body of the prosthesis was designed using a double parallel four-link configuration based on a remote motion center mechanism. A series elastic actuator was used to provide external power for the prosthesis, and an antagonistic torsion spring structure was used to achieve bidirectional energy storage assistance in hip flexion and extension. A control system based on impedance control was established. By setting up an auxiliary force field to compensate for the difference between the actual angle of the prosthesis and the target angle, the prosthesis assist function was realized. Finally, the traditional hip disarticulation prosthesis was used as a comparison to test the overall performance of the new intelligent power-assisted hip disarticulation prosthesis worn by normal people.Results:For the new smart-assisted hip-disarticulation prosthesis, the goodness-of-fit of its hip joint angle curve to that of a normal person was 86%, which was 14% higher than that of the traditional hip-disarticulation prosthesis (72%). The goodness-of-fit of the healthy-side angle of the new smart-assisted hip disarticulation prosthesis to the normal human was 94%, which was the same as that of the traditional hip disarticulation prosthesis.Conclusions:A new type of intelligent power-assisted hip disarticulation prosthesis is designed to realize the function of prosthesis-assisted movement.

Objective:To develop an artificial intelligence model based on multi-modal endoscopic images for identifying gastric neoplasms and to compare its diagnostic efficacy with traditional models and endoscopists.Methods:A total of 3 267 images of gastric neoplasms and non-neoplastic lesions under white light (WL) endoscopy and weak magnification (WM) endoscopy from 463 patients at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from March 2018 to December 2019 were utilized. Two single-modal models (WL model and WM model) were constructed based on WL and WM images separately. WL and WM images of corresponding lesions were combined into image pairs for creating a multi-modal (MM) characteristics integration model. A test set consisting of 696 images of 102 lesions from 97 patients from March 2020 to March 2021 was used to compare the diagnostic efficacy of the single-modal models and a multi-modal model for gastric neoplastic lesions at both the image and the lesion levels. Additionally, video clips of 80 lesions from 80 patients from January 2022 to June 2022 were employed to compare diagnostic efficacy of the WM model, the MM model and 7 endoscopists at the lesion level for gastric neoplasms.Results:In the image test set, the sensitivity and accuracy of MM model were 84.96% (576/678), and 86.89% (1 220/1 289), respectively, for diagnosing gastric neoplasms at the image level, which were superior to 63.13% (113/179) and 80.59% (353/438) of WM model ( χ2=42.81, P<0.001; χ2=10.33, P=0.001), and also better than those of WL model [70.47% (74/105), χ2=13.52, P<0.001; 67.82% (175/258), χ2=57.27, P<0.001]. The MM model showed a sensitivity of 87.50% (28/32), a specificity of 88.57% (62/70), and an accuracy of 88.24% (90/102) at the lesion level. The specificity ( χ2=22.99, P<0.001) and accuracy ( χ2=19.06, P<0.001) were significantly higher than those of WL model; however, there was no significant difference compared with those of the WM model ( P>0.05). In the video test, the sensitivity, specificity and accuracy of the MM model at the lesion level were 95.00% (19/20), 93.33% (56/60) and 93.75% (75/80). These results were significantly better than those of endoscopists, who had a sensitivity of 77.14% (108/140), a specificity of 79.29% (333/420), and an accuracy of 78.75% (441/560), with significant differences ( χ2=18.62, P<0.001; χ2=35.07, P<0.001; χ2=53.12, P<0.001), and was higher than the sensitivity of advanced endoscopists [83.33% (50/60)] with significant difference ( χ2=4.23, P=0.040). Conclusion:The artificial intelligence model based on multi-modal endoscopic images for the diagnosis of gastric neoplasms shows high efficacy in both image and video test sets, outperforming the average diagnostic performance of endoscopists in the video test.

ObjectiveAiming at the need of control strategy switching of intelligent above-knee prosthetic, taking the plantar pressure of human walking as the research object, and based on fuzzy logic algorithm, a gait phase division method based on plantar pressure of prosthetic is proposed. MethodsThree flexible force sensors installed on the soles of the false feet were used to collect the plantar pressure information of the test object under three different walking modes (walking on the flat road, walking downhill and walking down the stairs). After data fusion processing, it was sent to the fuzzy logic controller, and the recognition results were output according to the IF-THEN rule, the scale and sensitivity factor. ResultsThrough the testing of five healthy people as substitute, the results showed that the accuracy of gait phase recognition for walking on the flat road, walking down the stairs and walking downhill were (95.3±2.4)%, (81.5±6.3)% and (90.7±3.5)%, respectively. ConclusionThe accuracy of recognition basically meets the requirements in this project. This method can be applied in the gait phase recognition of intelligent above-knee prosthetic.

Objective Aiming at the problems of lacking initiative in upper limb rehabilitation training equipment, single training mode, and low active participation of patients, an upper limb continuous motion estimation algorithm model based on multi-modal information fusion was proposed, so to realize accurate estimation of elbow joint torque. Methods Firstly, the surface electromyography (sEMG) signal and posture signal of participants were collected at four angular velocities, and the time domain characteristics of the signal were extracted. The principal component analysis was adopted to multi-feature fusion. The back propagation neural network (BPNN) was optimized through the additional momentum and the adaptive learning rate method. The particle swarm optimization (PSO) algorithm was used to optimize the neural network and a continuous motion estimation model based on PSO-BPNN was constructed. Finally, the joint torque calculated by the second type of Lagrangian equation was used as the accurate value to train the model. The performance of the model was compared with the traditional BP neural network model. Results The root mean square error (RMSE) of the traditional BP neural network model was 558.9 N·m, and the R2 coefficient was 77.19%, Whereas the RMSE and the R2 coefficient of the optimized model were 113.6 mN·m and 99.12%, respectively.Thereby, the accuracy of torque estimation was improved apparently. Conclusions The method for continuous motion estimation of the elbow joint proposed in this study can estimate the motion intention accurately, and provide a practical scheme for the active control of upper exoskeleton rehabilitation robot.

Objective:To assess the diagnostic efficacy of upper gastrointestinal endoscopic image assisted diagnosis system (ENDOANGEL-LD) based on artificial intelligence (AI) for detecting gastric lesions and neoplastic lesions under white light endoscopy.Methods:The diagnostic efficacy of ENDOANGEL-LD was tested using image testing dataset and video testing dataset, respectively. The image testing dataset included 300 images of gastric neoplastic lesions, 505 images of non-neoplastic lesions and 990 images of normal stomach of 191 patients in Renmin Hospital of Wuhan University from June 2019 to September 2019. Video testing dataset was from 83 videos (38 gastric neoplastic lesions and 45 non-neoplastic lesions) of 78 patients in Renmin Hospital of Wuhan University from November 2020 to April 2021. The accuracy, the sensitivity and the specificity of ENDOANGEL-LD for image testing dataset were calculated. The accuracy, the sensitivity and the specificity of ENDOANGEL-LD in video testing dataset for gastric neoplastic lesions were compared with those of four senior endoscopists.Results:In the image testing dataset, the accuracy, the sensitivity, the specificity of ENDOANGEL-LD for gastric lesions were 93.9% (1 685/1 795), 98.0% (789/805) and 90.5% (896/990) respectively; while the accuracy, the sensitivity and the specificity of ENDOANGEL-LD for gastric neoplastic lesions were 88.7% (714/805), 91.0% (273/300) and 87.3% (441/505) respectively. In the video testing dataset, the sensitivity [100.0% (38/38) VS 85.5% (130/152), χ2=6.220, P=0.013] of ENDOANGEL-LD was higher than that of four senior endoscopists. The accuracy [81.9% (68/83) VS 72.0% (239/332), χ2=3.408, P=0.065] and the specificity [ 66.7% (30/45) VS 60.6% (109/180), χ2=0.569, P=0.451] of ENDOANGEL-LD were comparable with those of four senior endoscopists. Conclusion:The ENDOANGEL-LD can accurately detect gastric lesions and further diagnose neoplastic lesions to help endoscopists in clinical work.

Objective:To construct a real-time artificial intelligence (AI)-assisted endoscepic diagnosis system based on YOLO v3 algorithm, and to evaluate its ability of detecting focal gastric lesions in gastroscopy.Methods:A total of 5 488 white light gastroscopic images (2 733 images with gastric focal lesions and 2 755 images without gastric focal lesions) from June to November 2019 and videos of 92 cases (288 168 clear stomach frames) from May to June 2020 at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University were retrospectively collected for AI System test. A total of 3 997 prospective consecutive patients undergoing gastroscopy at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from July 6, 2020 to November 27, 2020 and May 6, 2021 to August 2, 2021 were enrolled to assess the clinical applicability of AI System. When AI System recognized an abnormal lesion, it marked the lesion with a blue box as a warning. The ability to identify focal gastric lesions and the frequency and causes of false positives and false negatives of AI System were statistically analyzed.Results:In the image test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 92.3% (5 064/5 488), 95.0% (2 597/2 733), 89.5% (2 467/ 2 755), 90.0% (2 597/2 885) and 94.8% (2 467/2 603), respectively. In the video test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 95.4% (274 792/288 168), 95.2% (109 727/115 287), 95.5% (165 065/172 881), 93.4% (109 727/117 543) and 96.7% (165 065/170 625), respectively. In clinical application, the detection rate of local gastric lesions by AI System was 93.0% (6 830/7 344). A total of 514 focal gastric lesions were missed by AI System. The main reasons were punctate erosions (48.8%, 251/514), diminutive xanthomas (22.8%, 117/514) and diminutive polyps (21.4%, 110/514). The mean number of false positives per gastroscopy was 2 (1, 4), most of which were due to normal mucosa folds (50.2%, 5 635/11 225), bubbles and mucus (35.0%, 3 928/11 225), and liquid deposited in the fundus (9.1%, 1 021/11 225).Conclusion:The application of AI System can increase the detection rate of focal gastric lesions.

ObjectiveTo present a method for evaluating the gait symmetry of microprocessor-controlled prosthetic knee (MPK). MethodsA kind of proto-MPK, AiKneeOne, and a wearable gait collect system, were made. The phases of the first double-limb support, the single-limb support, the second double-limb support, and the swing were used to calculate symmetry index (SI), ratio Ⅰ (R_I) and ratio II (R_II). Five heathy persons walked on the treadmill wearing AiKneeOne at speeds of 0.5, 0.7, 1.1 m/s, and the indice were collected with the wearable gait collect system. ResultsUnder different velocities, The absolute value of SI and R_II were very little and the R_I were close to one at the phases of the first double-limb support and the second double-limb support, but they were not very satisfactory in the phases of the single-limb support and the swing. ConclusionThe developed MPK AiKneeOne is potential to reconstruct the gait of amputees, and the gait symmetry indice can be used to evaluate the wearing performance of MPK.