Knee joint forces (KJF) are biomechanical measures used to infer the load on knee joint structures. The purpose of this study is to develop an artificial neural network (ANN) that estimates KJF during sport movements, based on data obtained by wearable sensors. Thirteen participants were equipped with two inertial measurement units (IMUs) located on the right leg. Participants performed a variety of movements, including linear motions, changes of direction, and jumps. Biomechanical modelling was carried out to determine KJF. An ANN was trained to model the association between the IMU signals and the KJF time series. The ANN-predicted KJF yielded correlation coefficients that ranged from 0.60 to 0.94 (vertical KJF), 0.64 to 0.90 (anterior–posterior KJF) and 0.25 to 0.60 (medial–lateral KJF). The vertical KJF for moderate running showed the highest correlation (0.94 ± 0.33). The summed vertical KJF and peak vertical KJF differed between calculated and predicted KJF across all movements by an average of 5.7% ± 5.9% and 17.0% ± 13.6%, respectively. The vertical and anterior–posterior KJF values showed good agreement between ANN-predicted outcomes and reference KJF across most movements. This study supports the use of wearable sensors in combination with ANN for estimating joint reactions in sports applications.

No abstract

Skating is a fundamental movement in ice hockey; however little research has been conducted within the field of hockey skating biomechanics due to the difficulties of on-ice data collection. In this study a novel on-ice measurement approach was tested for reliability, and subsequently implemented to investigate the forward skating technique, as well as technique differences across skill levels. Nine high caliber (High) and nine low caliber (Low) hockey players performed 30m forward skating trials. A 3D accelerometer was mounted to the right skate for the purpose of stride detection, with the 2nd and 6th strides defined as acceleration and steady-state, respectively. The activity of five lower extremity muscles was recorded using surface electromyography. Biaxial electro-goniometers were used to quantify hip and knee angles, and in-skate plantar force was measured using instrumented insoles. Reliability was assessed with the coefficient of multiple correlation, which demonstrated moderate (r>0.65) to excellent (r>0.95) scores across selected measured variables. Greater plantar-flexor muscle activity and hip extension were evident during acceleration strides, while steady state strides exhibited greater knee extensor activity and hip abduction range of motion (p<0.05). High caliber exhibited greater hip range of motion and forefoot force application (p<0.05). The successful implementation of this on-ice mobile measurement approach offers potential for athlete monitoring, biofeedback and training advice.

This is the first study examining functionality of subjects with anterior cruciate ligament (ACL) tears and a subsequent reconstruction comprehensively by multiple test sessions from pre- to six months post-reconstruction. The purpose was to evaluate if a generally applied rehabilitation program restores functionality to levels of healthy controls. Subjects with unilateral tears of the ACL were compared to matched healthy controls throughout the rehabilitation. 20 recreational athletes were tested: T1 (preoperative), 6 weeks after tear; T2, 6 weeks, T3, 3 months, T4, 6 months post-reconstruction. At all test sessions, subjects self-evaluated their activity level with the Tegner activity score and their knee state with the Knee Injury and Osteoarthritis Outcome Score. Passive range of motion during knee flexion and extension and leg circumference were measured as functional clinical tests. Bilateral countermovement jumps, one-leg jumps for distance and isometric force tests in knee flexion and extension with 90° and 110° knee angle were conducted as functional performance tests. For determination of functionality, leg symmetry indices (LSIs) were calculated by dividing values of the injured by the uninjured leg. In the ACL group most LSIs decreased from T1 to T2, and increased from T2 and T3 to T4. LSIs of ACL subjects remained lower than LSIs of healthy controls at 6 months post-reconstruction in nearly all parameters. Self-evaluation of ACL subjects showed, additionally, that activity level was lower than the pre-injury level at 6 months post-reconstruction. Low LSIs and low self-evaluation indicate that knee joint functionality is not completely restored at 6 months post-reconstruction. The study shows that multiple comprehensive testing throughout the rehabilitation gives detailed images of the functional state. Therefore, the functional state of ACL reconstructed individuals should be evaluated comprehensively and continuously throughout the rehabilitation to detect persisting deficiencies detailed and adapt rehabilitation programs individually depending on the functionality.

Background: The robust identification of initial contact (IC) and toe-off (TO) events is a vital task in mobile sensor-based gait analysis. Shank attached gyroscopes in combination with suitable algorithms for data processing can robustly and accurately complete this task for gait event detection. However, little research has considered gait detection algorithms that are applicable to different locomotion tasks. Research question: Does a gait event detection algorithm for various locomotion tasks provide comparable estimation accuracies as existing task-specific algorithms? Methods: Thirteen males, equipped with a gyroscope attached to the right shank, volunteered to perform nine different locomotion tasks consisting of linear movements and movements with a change of direction. A rulebased algorithm for IC and TO events was developed based on the shank sagittal plane angular velocity. The algorithm was evaluated against events determined by vertical ground reaction force. Absolute mean error (AME), relative absolute mean error (RAME) and Bland-Altman analysis was used to assess its accuracy. Results: The average AME and RAME were 11 ± 3 ms and 3.07 ± 1.33 %, respectively, for IC and 29 ± 11 ms and 7.27 ± 2.92 %, respectively, for TO. Alterations of the walking movement, such as turns and types of running, slightly reduced the accuracy of IC and TO detection. In comparison to previous methods, increased or comparable accuracies for both IC and TO detection are shown.Significance: The study shows that the proposed algorithm is capable of detecting gait events for a variety of locomotion tasks by means of a single gyroscope located on the shank. In consequence, the algorithm can be applied to activities, which consist of various movements (e.g., soccer). Ultimately, this extends the use of mobile sensor-based gait analysis.