Locomotion assistive devices equipped with a microprocessor can potentially automatically adapt their behavior when the user is transitioning from one locomotion mode to another. Many developments in the field have come from machine learning driven controllers on locomotion assistive devices that recognize/predict the current locomotion mode or the upcoming one. This review synthesizes the machine learning algorithms designed to recognize or to predict a locomotion mode in order to automatically adapt the behavior of a locomotion assistive device. A systematic review was conducted on the Web of Science and MEDLINE databases (as well as in the retrieved papers) to identify articles published between 1 January 2000 to 31 July 2020. This systematic review is reported in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines and is registered on Prospero (CRD42020149352). Study characteristics, sensors and algorithms used, accuracy and robustness were also summarized. In total, 1343 records were identified and 58 studies were included in this review. The experimental condition which was most often investigated was level ground walking along with stair and ramp ascent/descent activities. The machine learning algorithms implemented in the included studies reached global mean accuracies of around 90%. However, the robustness of those algorithms seems to be more broadly evaluated, notably, in everyday life. We also propose some guidelines for homogenizing future reports.

Improper socket fitting in lower-limb prostheses can lead to significant complications, including pain, skin lesions, and pressure ulcers. Current suspension and socket design practices rely predominantly on visual inspection of the residual limb and patient feedback. Monitoring stress distribution at the residual limb/socket interface offers a more objective approach. Finite Element Analysis (FEA) enables to estimate interface pressure distribution prior to manufacture to provide the orthoprosthetist with quantitative data during socket rectification and interface prosthetic components selection. However, although numerous FEA models are available, few have undergone rigorous validation against experimental pressure data. Indeed, limitations of commercial pressure sensors typically include cumbersomeness or imprecision, thereby hindering systematic measurements within the socket. In this study, we introduce a low-cost, accurate pressure sensing system integrated into 3D-printed sockets for FEA validation. The system is implemented on a roll-over simulator that uses a mock limb to mimic the interaction between a transtibial residual limb and socket during the unipodal stance phase. A FEA of the simulator was then conducted, and predicted interface pressures were compared to experimental measurements at seven discrete locations. The model demonstrated a high degree of sensitivity to the geometry of the mock limb; however, with an accurate shape description, it was able to predict pressure with an average absolute error of 12 kPa. This work advances the validation of residual limb FEA for estimating residual limb/socket interface pressures. It highlights the potential of FEA for designing data-driven sockets and ultimately improve the comfort of prosthesis users.

Background: Advances in prosthetic technology, especially microprocessor-controlled knees (MPKs), have helped enhance gait symmetry and reduce fall risks for individuals who have undergone transfemoral amputation. However, challenges remain in walking in constrained situations due to the limitations of passive prosthetic feet, lacking ankle mobility. This study investigates the benefits of SYNSYS^®, a new microprocessor-controlled knee–ankle–foot system (MPKA_NEW), designed to synergize knee and ankle movements. Methods: A randomized crossover trial was conducted on 12 male participants who had undergone transfemoral amputation who tested both the MPKA_NEW and their usual MPK prosthesis. Biomechanical parameters were evaluated using quantitative gait analysis in various walking conditions. Participants also completed self-reported questionnaires on their quality of life, locomotor abilities, and prosthesis satisfaction. Results: The MPKA_NEW showed a significant reduction in the risk of slipping and tripping compared to standard MPK prostheses, as evidenced by increased flat-foot time and minimum toe clearance during gait analysis. The MPKA_NEW also improved physical component scores in quality-of-life assessments (Short-Form 36 General Health Questionnaire), suggesting enhanced stability and reduced cognitive load during walking. Conclusions: The MPKA_NEW offers significant improvements in gait safety and quality of life for people who have undergone TFA, particularly in challenging conditions. Further studies are needed to assess the long-term benefits and adaptability across diverse amputee populations.

Introduction: Although the choice of a prosthetic foot is crucial for the locomotion of individuals with limb loss, it partly reposes on the subjective perception of the patient without evaluating systematically the objective foot performance in gait laboratory. However, it is still unclear whether subjective perception is sufficient to evaluate foot performance and if it is in accordance with objective foot performance during gait. Materials and Methods: We aimed to address these questions by asking five unilateral transtibial prosthesis users to rate their habitual energy-storage-and-return foot (ESAR foot) and a new ESAR foot and to perform a three-dimensional gait analysis with each foot. Results: Our results revealed that perception is globally associated with objective gait performance. More specifically, gait stability seems to be the most relevant parameter for patient perception. Conclusions: This pilot study highlights the value of the subjective perception for the fitting of a prosthetic foot and suggests that pooling together subjective and objective evaluations provides substantial benefit.

Background: Various socket designs exist, linking the residual limb together with the prosthetic components to restore the ability to walk; however, lack of socket comfort is a frequent complaint. Objective: To evaluate the impact of socket design on end-user comfort and mobility. Methods: A randomized crossover trial was set to compare comfort and mobility of above-knee amputees (AKAs) wearing an ischial containment (IC) or subischial (I-SUB) socket. Patients actively wearing IC sockets were recruited from 10 rehabilitation centers across the country. They were then fitted for an I-SUB socket by Certified Prosthetists (CPs) as an alternate socket. Participants were randomly assigned to start with one or the other socket. After a minimum of 2 weeks, each participant evaluated the Socket Comfort Score (SCS) (primary outcome) in various situations, performed the 2-min walk test, and answered the PLUS-M questionnaire (secondary outcomes). Results: A total of 25 participants were included, of whom 23 completed the study with full (n = 21) or partial data (n = 2). SCS were improved with I-SUB compared with IC in all situations, with significant differences in general, when sitting on a rigid chair, sitting in a car, and standing. The differences in self-reported mobility and walking distance at the 2-min walk test were not significant. At the end of the study, more than 80% of the participants chose to keep the I-SUB socket for their daily use. Conclusions: For the first time, this study supports that the subischial suction socket improves comfort in daily life without negatively impacting user mobility in a group of individuals with AKA.