Hip contact forces can be predicted with a neural network using only synthesised key points and electromyography in people with hip osteoarthritis.

OBJECTIVE: To develop and validate a neural network to estimate hip contact forces (HCF), and lower body kinematics and kinetics during walking in individuals with hip osteoarthritis (OA) using synthesised anatomical key points and electromyography. To assess the capability of the neural network to detect directional changes in HCF resulting from prescribed gait modifications. DESIGN: A calibrated electromyography-informed neuromusculoskeletal model was used to compute lower body joint angles, moments, and HCF for 17 participants with mild-to-moderate hip OA. Anatomical key points (e.g., joint centres) were synthesised from marker trajectories and augmented with bias and noise expected from computer vision-based pose estimation systems. Temporal convolutional and long short-term memory neural networks (NN) were trained using leave-one-subject-out validation to predict neuromusculoskeletal modelling outputs from the synthesised key points and measured electromyography data from 5 hip-spanning muscles. RESULTS: HCF was predicted with an average error of 13.4 ± 7.1% of peak force. Joint angles and moments were predicted with an average root-mean-square-error of 5.3 degrees and 0.10 Nm/kg, respectively. The NN could detect changes in peak HCF that occur due to gait modifications with good agreement with neuromusculoskeletal modelling (r2 = 0.72) and a minimum detectable change of 9.5%. CONCLUSION: The developed neural network predicted HCF and lower body joint angles and moments in individuals with hip OA using noisy synthesised key point locations with acceptable errors. Changes in HCF magnitude due to gait modifications were predicted with high accuracy. These findings have important implications for implementation of load-modification based gait retraining interventions for people with hip OA in a natural environment (i.e., home, clinic).

Predicting Free Achilles Tendon Strain From Motion Capture Data Using Artificial Intelligence.

The Achilles tendon (AT) is sensitive to mechanical loading, with appropriate strain improving tissue mechanical and material properties. Estimating free AT strain is currently possible through personalized neuromusculoskeletal (NMSK) modeling; however, this approach is time-consuming and requires extensive laboratory data. To enable in-field assessments, we developed an artificial intelligence (AI) workflow to predict free AT strain during running from motion capture data. Ten keypoints commonly used in pose estimation algorithms (e.g., OpenPose) were synthesized from motion capture data and noise was added to represent real-world data obtained using video cameras. Two AI workflows were compared: (1) a Long Short-Term Memory (LSTM) neural network that predicted free AT strain directly (called LSTM only workflow); and (2) an LSTM neural network that predicted AT force which was subsequently converted to free AT strain using a personalized force-strain curve (called LSTM+ workflow). AI models were trained and evaluated using estimates of free AT strain obtained from a validated NMSK model with personalized AT force-strain curve. The effect of using different input features (position, velocity, and acceleration of keypoints, height and mass) on free AT strain predictions was also assessed. The LSTM+ workflow significantly improved the predictions of free AT strain compared to the LSTM only workflow (p < 0.001). The best free AT strain predictions were obtained using positions and velocities of keypoints as well as the height and mass of the participants as input, with average time-series root mean square error (RMSE) of 1.72±0.95% strain and r2 of 0.92±0.10, and peak strain RMSE of 2.20% and r2 of 0.54. In conclusion, we showed feasibility of predicting accurate free AT strain during running using low fidelity pose estimation data.

Maintaining soldier musculoskeletal health using personalised digital humans, wearables and/or computer vision.

OBJECTIVES: The physical demands of military service place soldiers at risk of musculoskeletal injuries and are major concerns for military capability. This paper outlines the development new training technologies to prevent and manage these injuries. DESIGN: Narrative review. METHODS: Technologies suitable for integration into next-generation training devices were examined. We considered the capability of technologies to target tissue level mechanics, provide appropriate real-time feedback, and their useability in-the-field. RESULTS: Musculoskeletal tissues' health depends on their functional mechanical environment experienced in military activities, training and rehabilitation. These environments result from the interactions between tissue motion, loading, biology, and morphology. Maintaining health of and/or repairing joint tissues requires targeting the "ideal" in vivo tissue mechanics (i.e., loading and strain), which may be enabled by real-time biofeedback. Recent research has shown that these biofeedback technologies are possible by integrating a patient's personalised digital twin and wireless wearable devices. Personalised digital twins are personalised neuromusculoskeletal rigid body and finite element models that work in real-time by code optimisation and artificial intelligence. Model personalisation is crucial in obtaining physically and physiologically valid predictions. CONCLUSIONS: Recent work has shown that laboratory-quality biomechanical measurements and modelling can be performed outside the laboratory with a small number of wearable sensors or computer vision methods. The next stage is to combine these technologies into well-designed easy to use products.

Factor analysis of the biomechanical parameters of pole vault run-up and takeoff: exploring sports performance.

This study aimed to explore a parameter system and build a linear prediction model to effectively and comprehensively evaluate pole vault performance. The Qualisys motion capture system (200 Hz) and three Kistler force platforms (2000 Hz) were used to collect the athletes' kinematics and ground reaction force data of run-up and takeoff. Finally, 26 biomechanical parameters of 30 successful vaults of eight athletes were analysed by factor analysis, and linear regression analysis was conducted on the extracted factors. Three factors were extracted by factor analysis: F1, F2, and F3. The mean maximum COM height of the 30 vaults was 4.974 m. The score of F2 and F1 increased by 1, and the maximum COM height increased by 0.131 m and 0.112 m, respectively. The F3 did not participate in the prediction of performance. For the training of coaches and athletes, athletes of a higher stature need to expend more effort to achieve a higher training level. Furthermore, improving the speed, mechanical energy, and horizontal propulsion GRF of run-up and takeoff, as well as optimising the force generation strategy of the three lower limb joints in the takeoff support phase, help to achieve a good pole vault performance.

A High-Performance Rectangular Gate U Channel FETs with Only 2-nm Distance between Source and Drain Contacts.

A novel high-performance rectangular gate U channel FET (RGUC FET) for extreme integrated distance between source and drain contacts is proposed in this paper. The RGUC FET represents nearly ideal subthreshold characteristics till the distance between source/drain (S/D) contacts reduced to 2 nm. Different from the other recessed or U-shaped channel-based FETs, the gate contacts do not need to be formed in the recessed region but only in a layer of spacer for the insulation between the two vertical parts on both sides of the U channel. Its structural advantages make it possible to be applied to manufacture integrated circuits with higher integration for extreme integrated distance between source and drain contacts. The electrical properties of the RGUC FET were scrupulously investigated by studying the influence of design parameters including the horizontal distance between S/D contacts, the extension height of S/D region, and the thickness and material of the gate oxide layer. The electrical properties of the RGUC FET are verified by quantum simulation. Compared to the other non-planner channel multi-gate FETs, the novel RGUC FET is suitable for higher integration.

The gait deviations of ankylosing spondylitis with hip involvement.

OBJECTIVE: The aim of the study was to investigate the gait deviations of ankylosing spondylitis (AS) patients with hip involvement. METHODS: Thirty-six subjects, including 18 AS patients with hip involvement (AS group) and 18 healthy people (control subjects, CS group), were enrolled in the study. Three-dimensional gait analysis of the AS group and CS group was performed. Kinematic parameters, kinetic parameters and surface electromyography (sEMG) during the gait cycle were measured. RESULTS: The AS patients with hip involvement had a lower gait velocity, shorter step length and shorter stride length. In the hip angles, there was significantly decreased flexion, excessive abduction and excessive external rotation; there was excessive flexion in the knee and reduction in plantar flexion of the ankle. AS patients had increased forward trunk flexion, excessive obliquity and restricted rotation of the trunk during the gait cycle. The hip moments of the AS group showed a significant reduction in flexion, abduction and external rotation during the gait cycle. The root mean square amplitude of the sEMG for the rectus femoris in the AS group was higher than that in the CS group. CONCLUSION: The gait deviations in AS patients with hip involvement were described in this study. The gait analysis results demonstrated statistically significant alterations regarding the kinematic and kinetic gait parameters for the patients included in the sample. Coordination and balance were impaired by the disease. An efficient physical exercise plan can be formulated according to the results of gait analysis.

[Detecting Down syndrome with a novel dual-color competitive quantitative fluorescent polymerase chain reaction method].

OBJECTIVE: To develop a rapid method for the detection of Down syndrome (DS) using dual-color competitive quantitative fluorescent polymerase chain reaction (DCC-QF-PCR), and to assess its feasibility for the prenatal diagnosis of Down syndrome. METHODS: DNA was extracted from peripheral blood of 30 DS patients and 60 normal men, common primers for DSCR and USC2 genes and respective TaqMan probes were designed and synthesized. The results of DCC-QF-PCR were compared with those of QF-PCR which measured the ratio between DSCR and GAPDH. Forty-six amniotic fluid samples were assayed with DCC-QF-PCR. The results were compared with that of karyotyping. Monoclone fragments for DSCR and USC2 genes were obtained from direct cloning of PCR products. DCC-QF-PCR was carried out using different DNA ratios of DSCR and USC2 as the template. The dosage ratio between DSCR and USC2 was calculated. RESULTS: The gene dosage ratio of the DS patients was 1.41-1.74, which was significantly higher than that of normal men (0.93-1.15). The dosage ratio range of DSCR and GAPDH by QF-PCR was comparatively greater than that of DSCR and USC2. Three samples were diagnosed as DS, which was in good agreement with that of karyotyping analysis. There was no significant difference between the gene dosage ratio from DCC-QF-PCR and that of predetermined (P>0.05). CONCLUSION: DCC-QF-PCR is an accurate, rapid, and low cost method, which only requires tiny amount of sample and therefore has broad application in the genetic and prenatal diagnosis.