This study aimed to analyze the effect of laterality and instructional video on the soccer goalkeepers’ dive kinematics in penalty. Eight goalkeepers from youth categories (U15, U17, U20) were randomly divided into control (CG) and video instruction groups (VG). The latter performed 20 penalty defense trials on the field with balls launched by a machine, ten before and after watching a video instruction to improve the diving kinematics. The CG only performed the dives. Three cameras recorded the collections. A markerless motion capture technique (OpenPose) was used for identification and tracking of joints and anatomical references on video. The pose data were used for 3D reconstruction. In the post-instruction situation, the VG presented differences in comparison to the CG in the: knee flexion/extension angle, time to reach peak resultant velocity, frontal step distance, and frontal departure angle, which generated greater acceleration during the dive. Non-dominant leg side dives had higher resultant velocity during 88.4 – 100% of the diving cycle, different knee flexion/extension angle, and higher values ​​in the frontal step distance. The instructional video generated an acute change in the diving movement pattern of young goalkeepers when comparing the control and the video instruction group in the post condition.

BACKGROUND: Traditional gait analysis relies on motion capture systems and sensor mats, which are precise but costly and constrained to specialized environments. Markerless pose estimation combined with machine learning offers a low-cost alternative for gait analysis. AIM: This study aimed to develop and validate a markerless method for predicting spatiotemporal gait parameters using video-based pose detection and machine learning, leveraging the GAITRite™ system as a reference. METHODS: Ten healthy adults walked barefoot on a GAITRite™ mat while their movements were recorded. Videos were processed using the vailá Multimodal Toolbox, which integrates MediaPipe for pose estimation and various machine learning algorithms. Gait parameters such as step length, stride velocity, and support time were predicted using regression models trained on pixel-based data. RESULTS: The results demonstrate a clear division in model performance based on the target variable. For metrics related to spatial characteristics, such as Step Length, Step Width, Stride Length, Stride Width, and Stride Velocity, the Gradient Boosting (GBR) delivered the best results, exhibiting lower error metrics and higher R2 scores. Only for the Support Base data the best model differed, with the Random Forest (RFR) outperforming the others. This model also displayed lower error values and higher R2 and EVS score. INTERPRETATION: The results indicate the feasibility of markerless pixel-based gait analysis as a low-cost alternative to traditional methods, broadening the accessibility of precise gait assessment for both clinical and research applications.

Parkinson’s disease (PD) is associated with debilitating motor symptoms, including gait impairments and stooped posture. While markerless motion capture offers a scalable alternative to quantify these deficits, the acute biomechanical effects of interventions like Dry Needling (DN) on PD gait remain under-investigated. This randomized clinical trial investigated the acute effects of upper trapezius myofascial release via DN on gait and turning biomechanics in individuals with PD, utilizing a 3D markerless motion capture system. Thirty-eight participants with mild-to-moderate PD and bilateral upper trapezius trigger points were randomly assigned to a DN or Sham group. Gait was evaluated during a modified Timed Up and Go (TUG) test at baseline, immediately post-intervention, and at a one-week follow-up. Video data were processed using the open-source vailá toolbox, which applied a rigorous spatial segmentation algorithm to isolate postural transitions, steady-state gait, and turning phases. Thirty-seven participants completed the protocol (DN = 18; Sham = 19). The algorithm-driven markerless pipeline successfully extracted high-fidelity spatiotemporal parameters and automated gait event detection. However, the quantitative analysis revealed no significant Group × Time interactions for spatiotemporal parameters or turning kinematics, with both groups exhibiting similar trajectories across all assessment points. In conclusion, a single session of upper trapezius DN does not yield superior acute improvements in gait or turning biomechanics compared to a sham intervention in PD, suggesting that macro-level motor adaptations likely require cumulative therapeutic sessions. Nevertheless, the successful implementation of this markerless workflow provides an objective, cost-effective framework for precisely tracking phase-specific kinematic changes in routine clinical settings.

Respiratory function problems are caused by both motor and non-motor symptoms of Parkinson’s disease (PD). One major problem involving the changes in respiratory function in people with PD is a decrease in chest movement caused by musculoskeletal problems around the neck and upper trunk. The relationship between these respiratory changes and pulmonary volume in people with PD can lead to the main cause of mortality as the disease progresses. Dry needling technique (DNT) is a myofascial release technique that has been reported to provide an immediate effect on pain, decreased muscle spasm or tightness and lead to restoration of range of motion of upper trunk by using needles to stimulate hypersensitive and painful nodules in the musculature called trigger points (TP). However, to date, the use of this technique has not been reported to release muscle tightness or pain in people with PD. The present study aimed to explore the effects of a single session of bilateral DNT to the trapezius muscles trigger point on chest expansion and vital capacity which could lead to improvements in respiratory function in people with PD. Thirty-eight people with PD were randomly allocated to DN and Sham needling treatment groups. The maximum and mean volumes of vital capacity were assessed by using a ventilometer at pre-intervention, immediately after intervention, and one-week follow-up. Mixed Model Analysis of Variance (MM ANOVA) tests with post hoc pairwise comparisons were used to test the differences between groups and assessment time points. No interaction effects were found between groups and assessment time points for maximum and mean vital capacity volume. In addition, no statistically significant main effects of DNT were found for both groups and assessment time points for either maximum or mean vital capacity volume. These findings can provide evidence that a single session of dry needling does not help to improve respiratory function in people with PD. However, slight improvements in vital capacity were observed in the DN group, which may be clinically relevant when considering progressive neurodegenerative disease. More sessions of dry needling need to be explored over a greater time period to determine if longer term effect are possible with this treatment.