Purpose: The prediction of student attrition is critical to facilitate retention mechanisms. This study aims to focus on implementing a method to predict student attrition in the upper years of a physiotherapy program.Design/methodology/approach: Machine learning is a computer tool that can recognize patterns and generate predictive models. Using a quantitative research methodology, a database of 336 university students in their upper-year courses was accessed. The participant's data were collected from the Financial Academic Management and Administration System and a platform of Universidad Autónoma de Chile. Five quantitative and 11 qualitative variables were chosen, associated with university student attrition. With this database, 23 classifiers were tested based on supervised machine learning.Findings: About 23.58% of males and 17.39% of females were among the attrition student group. The mean accuracy of the classifiers increased based on the number of variables used for the training. The best accuracy level was obtained using the “Subspace KNN” algorithm (86.3%). The classifier “RUSboosted trees” yielded the lowest number of false negatives and the higher sensitivity of the algorithms used (78%) as well as a specificity of 86%.Practical implications: This predictive method identifies attrition students in the university program and could be used to improve student retention in higher grades.Originality/value: The study has developed a novel predictive model of student attrition from upper-year courses, useful for unbalanced databases with a lower number of attrition students.

Background: CrossFit^® has become a popular and effective training methodology. This study aimed to compare the effects of a four-week CrossFit training program and analyze the inter-individual variability on body composition (fat mass and fat-free mass) and physical fitness (push-ups, military press, back squat, deadlift, countermovement jump (CMJ), sit-ups, and 30 m sprint speed) in novice and advanced practitioners. Methods: A quasi-experimental design was used, with single-blinded (evaluators) and 2 parallel groups: novices (n = 10; age = 22.30 ± 0.81) and advanced practitioners (n = 11; age = 22.80 ± 1.41). The intervention consisted of 3 weekly 75 min sessions (4 weeks), with pre- and post-assessments. A two-factor mixed ANOVA and inter-individual analyses to classify responders (Rs) and non-responders (NRs) were performed. Results: No significant interaction effects were found. However, the novice group significantly improved back squat performance (p = 0.031). Inter-individual analysis showed higher proportions of Rs in the novice group for back squat (40%), deadlift (20%), military press (10%), CMJ (10%), sit-ups (30%), push-ups (30%), and 30 m sprint speed (10%) compared to the advanced group. Conclusions: CrossFit program did not significantly affect body composition, but novices exhibited significant back squat improvements. Considering experience levels can enhance training outcomes.

Background and Objectives: This systematic review aimed to analyze published peer-reviewed studies on the effects of exergaming (EXG) compared to conventional physical exercise (CPE) interventions on health status in older people with Parkinson’s disease (PD) according to training dose. Materials and Methods: Using six generic databases: PubMed, EBSCO, Medline, CINAHL Complete, Scopus, and Web of Science, the PRISMA, TESTEX, RoB 2, and GRADE tools assessed methodological quality and certainty. The protocol was registered in PROSPERO (code: CRD42024575969). Results: Out of 805 records, 14 randomized controlled trials with 406 older people with PD were included. Seven overall meta-analyses showed significant improvements (p < 0.01) in favor of EXG in the Berg Balance Scale (BBS, ES = 0.90), Dynamic Gait Index (DGI, ES = 0.77) and quality of life questionnaire (PDQ-39, ES = 0.52), without significant improvements (p > 0.05) in the Unified PD Rating Scale, Montreal Cognitive Assessment, Timed Up-and-Go and Falls Efficacy Scale-International. Four subgroup meta-analyses, according to training schedules, showed that there were significant improvements (p < 0.05) in BBS in favor of EXG at >8 weeks of training (ES = 1.38), >3 weeks per week (ES = 1.18), 20 total sessions (ES = 1.31). Both weeks and total sessions were predictors of BBS performance in EXG interventions in older people with PD. Conclusions: EXG is an innovative alternative to improve the health status in balance, gait, and quality of life variables in older people with PD, with a high potential for clinical practice in this population. The training dose is a determinant (weeks and total sessions) that varies the response to intervention in the BBS.

Background: This study investigates differences in muscle co-contraction and peak electromyography (EMG) activity between novice and advanced Taekwondo athletes during consecutive roundhouse (bandal chagui) kicks, examining the influence of body composition and experience level. Methods: Sixteen Taekwondo athletes (12 males, 4 females; mean age: 20.5 ± 4.3 years) were divided into novice (n = 8) and advanced (n = 8) groups. Muscle co-contraction indices and peak EMG activity across 15 consecutive kicks were assessed in key lower limb muscles, including the biceps femoris (BF), lateral gastrocnemius (LG), rectus femoris (RF), soleus (SO), semitendinosus (ST), tibialis anterior (TA), vastus lateralis (VL), and vastus medialis (VM). Results: Advanced athletes exhibited significantly higher co-contraction indices in BF–RF, VM–BF, and SO–TA pairs (p < 0.05) and increased peak EMG trends in the BF and LG (p < 0.05). Novice athletes showed significantly reduced peak EMG increases in the RF, VM, and VL. EMG trends were influenced by body composition, with principal component analysis indicating that higher fat mass and lower muscle mass were associated with greater variations in muscle activation. Conclusions: These findings suggest that advanced athletes refine motor control through increased co-contraction, improving stability and efficiency, while novices exhibit less optimized coordination patterns. This study provides insights into the neuromechanical adaptations associated with expertise development in Taekwondo.