Powered single hip joint exoskeletons for gait rehabilitation: a systematic review and Meta-analysis

BACKGROUND

Gait disorders and as a consequence, robotic rehabilitation techniques are becoming increasingly prevalent as the population ages. In the area of rehabilitation robotics, using lightweight single hip joint exoskeletons are of significance. Considering no prior systematic review article on clinical outcomes, we aim to systematically review powered hip exoskeletons in terms of gait parameters and metabolic expenditure effects.

METHODS

Three databases of PubMed, Scopus, and Web of science were searched for clinical articles comparing outcomes of gait rehabilitation using hip motorized exoskeleton with conventional methods, on patients with gait disorder or healthy individuals. Of total number of 37 reviewed articles, 14 trials were quantitatively analyzed. Analyses performed in terms of gait spatiotemporal parameters like speed (self-speed and maximum speed), step length, stride length, cadence, and oxygen consumption.

RESULTS

Improved clinical outcomes of gait spatiotemporal parameters with hip joint exoskeletons are what our review's findings show. In terms of gait values, meta-analysis indicates that rehabilitation with single hip joint exoskeleton enhanced parameters of maximum speed by 0.13 m/s (0.10-0.17) and step length by 0.06 m (0.05-0.07). For the remaining investigated gait parameters, no statistically significant difference was observed. Regarding metabolic parameters, oxygen consumption was lower in individuals treated with hip exoskeleton (- 1.23 ml/min/kg; range - 2.13 to - 0.32).

CONCLUSION

Although the analysis demonstrated improvement with just specific gait measures utilizing powered hip exoskeletons, the lack of improvement in all parameters is likely caused by the high patient condition heterogeneity among the evaluated articles. We also noted in patients who rehabilitated with the hip exoskeleton, the oxygen cost was lower. More randomized controlled trials are needed to verify both the short- and long-term clinical outcomes, including patient-reported measures.

LEVEL OF EVIDENCE

Level I (systematic review and meta-analysis).

A hybrid evolutionary learning classification for robot ground pattern recognition

In the field of intelligent robot engineering, whether it is humanoid, bionic or vehicle robots, the driving forms of standing, moving and walking, and the consciousness discrimination of the environment in which they are located have always been the focus and difficulty of research. Based on such problems, Naive Bayes Classifier (NBC), Support Vector Machine(SVM), k-Nearest-Neighbor (KNN), Decision Tree (DT), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) were introduced to conduct experiments. The six individual classifiers have an obvious effect on a particular type of ground, but the overall performance is poor. Therefore, the paper proposes a “Novel Hybrid Evolutionary Learning” method (NHEL) which combines every single classifier by means of weighted voting and adopts an improved genetic algorithm (GA) to obtain the optimal weight. According to the fitness function and evolution times, this paper designs the adaptively changing crossover and mutation rate and applies the conjugate gradient (CG) to enhance GA. By making full use of the global search capabilities of GA and the fast local search ability of CG, the convergence speed is accelerated and the search precision is upgraded. The experimental results show that the performance of the proposed model is significantly better than individual machine learning and ensemble classifiers.