Loading...
35 results
Search Results
Now showing 1 - 10 of 35
- A Deep Learning Neural Network to Classify Obesity Risk in Portuguese Adolescents Based on Physical Fitness Levels and Body Mass Index Percentiles: Insights for National Health PoliciesPublication . Forte, Pedro; Encarnação, Samuel; Monteiro, A.M.; Teixeira, José Eduardo; Hattabi, Soukaina; Sortwell, Andrew; Branquinho, Luís; Amaro, Bruna; Sampaio, Tatiana; Flores, Pedro Miguel; Silva-Santos, Sandra; Ribeiro, Joana; Batista, Amanda; Ferraz, Ricardo; Rodrigues, FilipeThe increasing prevalence of overweight and obesity among adults is a risk factor for many chronic diseases and death. In addition, obesity among children and adolescents has reached unprecedented levels and studies show that obese children and adolescents are more likely to become obese adults. Therefore, both the prevention and treatment of obesity in adolescents are critical. This study aimed to develop an artificial intelligence (AI) neural network (NNET) model that identifies the risk of obesity in Portuguese adolescents based on their body mass index (BMI) percentiles and levels of physical fitness. Using datasets from the FITescola® project, 654 adolescents aged between 10–19 years old, male: 334 (51%), female: n = 320 (49%), age 13.8 ± 2 years old, were selected to participate in a cross-sectional observational study. Physical fitness variables, age, and sex were used to identify the risk of obesity. The NNET had good accuracy (75%) and performance validation through the Receiver Operating Characteristic using the Area Under the Curve (ROC AUC = 64%) in identifying the risk of obesity in Portuguese adolescents based on the BMI percentiles. Correlations of moderate effect size were perceived for aerobic fitness (AF), upper limbs strength (ULS), and sprint time (ST), showing that some physical fitness variables contributed to the obesity risk of the adolescents. Our NNET presented a good accuracy (75%) and was validated with the K-Folds Cross-Validation (K-Folds CV) with good accuracy (71%) and ROC AUC (66%). According to the NNET, there was an increased risk of obesity linked to low physical fitness in Portuguese teenagers.
- Comparison of Physical Activity Level, Body Composition, Strength, and Flexibility of Teen Basketball Players and Adolescents Non-Practitioners of Sport: An Observational Study with Machine Learning AnalysisPublication . Encarnação, Samuel; Rezende, Vitor Hugo Santos; Gonçalves, Iarni Martins; Prata, Patrícia de Oliveira Ramalho; Mansur, Henrique Novais; Sampaio, Tatiana; Forte, Pedro; Teixeira, José Eduardo; Monteiro, A.M.; Guttierres, Ana Paula MunizIncreasing youths’ physical activity is mandatory to reduce the risk of non-communicable diseases (NCCDs). Basketball is a team sport that is potentially positive in increasing teenagers’ physical performance, health indicators, and well-being. Objective: The objective was to compare the physical activity level (PAL), body composition, strength, and flexibility of teen male basketball players (BG) (n = 15) and adolescent non-practitioners of sport (NS: n = 14). Methodology: All participants were healthy and free from any health disability from a Brazilian high school. A linear regression machine learning algorithm was applied to predict the adolescent´s physical components. In a quasi-experimental analysis, data were extracted by PAL, body fat percentage (BF%), handgrip strength (HG), back extensor muscle’s’ strength (BMS), lower limb power (LLP), and lower limb flexibility (LLF). Parametric (independent T-test) and non-parametric (Mann-Whitney U test) were employed to compare the variable’s average and chi-square was applied to compare categorical data. Results: BG presented an upper number of adolescents classified with high PAL than the NS group (p = 0.0002, large ES, V = 0.73) and a lower number of adolescents classified with low PAL than the NS group (p = 0.0002, V = 0.73), less BF% (p = 0.02, r = 0.85), greater values of HGS (p = 0.005, r = 0.34), greater values of BMSLS (p = 0.005, r = 0.33), greater values of LLP (p = 0.007, r = 0.30), and greater values for LLF (p = 0.02, r = 0.17). Therefore, there was a positive effect of high PAL compared with low PAL in HG, (p = 0.005, r = 0.24) and also for high PAL in LLF, (High PAL: (p = 0.006, r = 0.23). Regarding machine learning analysis, the four models (linear regression, Ridge regression, random forest regression, and Bayesian regression) expressed good generalization performance, with a coefficient of determination (R2) ranging from 0.77 to 0.88, root mean square error (RMSE) from 1.01 to 3.92, with an average mean difference of four points between the predicted and real values. The worst model was random forest regression R2 = 0.77, RMSE = 3.92, and the best model was Bayesian regression (R2 = 0.88, RMSE = 1.01). Conclusion: The BG group presented better results than the NS group for PAL, BF%, HG, BMS, LLP, and LLF. Body fat percentage precisely predicted the player’s’ vertical jump (VJ). In addition to the physical superiority of the BG, this study revealed the importance of managing body composition for both health and performance improvements.
- The effectiveness of pilates training interventions on older adults’ balance: a systematic review and meta-analysis of randomized controlled trialsPublication . Sampaio, Tatiana; Encarnação, Samuel; Santos, Olga Maria; Narciso, Diogo; Oliveira, João P.; Teixeira, José Eduardo; Forte, Pedro; Morais, J.E.; Vasques, Catarina; Monteiro, A.M.Pilates training intervention programs have gained attention as a potential approach to enhancing balance in older adults, thereby reducing the risk of falls. In light of these considerations, this systematic review and meta-analysis aimed to critically evaluate the existing evidence and determine the effect of Pilates training intervention programs on older adults’ balance. Materials and Methods: The literature was searched through the PubMed, Web of Science, and Scopus databases from inception until July 2023. The primary keywords used for the literature search included “elderly” or “older adults” and “pilates training” and “balance”. Results: The systematic review through qualitative analysis showed robust evidence about the efficacy of Pilates intervention programs in improving older adults’ balance. The pooled meta-analysis of static and dynamic balance showed that eight (53%) out of a total fifteen analyzed interventions presented a significant effect of Pilates in improving the participants’ balance, without between-study heterogeneity. In addition, the meta-analysis regarding dynamic balance showed that six (67%) out of nine analyzed interventions presented a significant effect of Pilates in improving the participants’ balance, without heterogeneity between studies. Similarly, the meta-analysis regarding static balance showed that four (50%) out of eight analyzed studies presented significant effects on the older adults’ balance, where moderate between-study heterogeneity was found. Sensitivity analysis showed that three studies reduced the between-study heterogeneity (19, 17.6, and 17%), regressing from moderate to low heterogeneity, p < 0.05. Conclusions: This systematic review and meta-analysis underscores the potential of Pilates training as a valuable intervention to enhance balance in the elderly population
- Classification of the pre-exam anxiety levels in physically inactive students from 48 countries: application of the K-means clustering machine learning algorithm.Publication . Encarnação, Samuel; Monteiro, A.M.; Sampaio, Tatiana; Vaz, Paula Marisa Fortunato; Forte, PedroPhysical inactivity is a behavioral factor that is strongly associated with anxiety symptoms in children and adolescents. Anxiety is a disabling condition that reduces academic performance (Kandola et al., 2020).
- Characterization of the lower limb dynamic balance and ankle dorsiflexion in young male futsal players: implications for performance and injury preventionPublication . Morais, J.E.; Sampaio, Tatiana; Oliveira, João P.; Lopes, Vitor P.; Barbosa, Tiago M.Dynamic balance and ankle dorsiflexion are associated with performance and injury risk in young athletes. The aim of this study was to characterize lower limb dynamic balance and ankle dorsiflexion in young futsal players and to understand their relationships. Eighteen young male futsal players (with 15.2 ± 1.2 years of age and with a right lower limb dominance) were evaluated for dynamic balance of both lower limbs using the Y-balance test (LQYBT). Ankle dorsiflexion range of motion (DROM) was measured during the weight-bearing lunge test. There were no significant differences in dynamic balance variables between the two sides (p > 0.05). However, the composite scores (CS) of both lower limbs showed a risk of injury (CS was less than 89%). Ankle dorsiflexion of the right lower limb was significantly greater than that of the left lower limb (mean difference = 1.00, 95% confidence intervals (CI) = −0.00 to 2.00, t = 2.11, p = 0.050, d = 0.50). Significant correlations and relationships between ankle dorsiflexion and dynamic balance were found only on the right side. The highest correlation (rs = 0.598; p = 0.009) and the highest relationship (R2 = 0.50; p = 0.001) were observed with the relative anterior reach. The present results indicate that young futsal players have poor dynamic balance scores. Ankle dorsiflexion was only significantly related to dynamic balance on the right side. Further research is needed to better understand these relationships in youth futsal.
- Assessing the aerodynamics of an able-bodied cyclist and a shoulder-amputee cyclist by computer fluid DynamicsPublication . Forte, Pedro; Marinho, D.A.; Neiva, Henrique P.; Sampaio, Tatiana; Teixeira, José Eduardo; Branquinho, Luís; Silva, A.J.; Monteiro, A.M.; Barbosa, Tiago M.This study aimed to analyse the aerodynamics by numerical simulations with computer fluid dynamics of an ablebodied cyclist and a shoulder-amputee cyclist. An elite cyclist volunteered for this research; the cyclist was scanned with his competition gear and bicycle and the able-bodied and shoulder amputee 3D cyclists models were created. Numerical simulations were conducted between 1 m/s and 13 m/s (with increments of 1 m/s) with the fluent code. The effective surface area (ACd) varied between 0.38 and 0.59 m2 for the able-bodied cyclist; whereas, for the shoulder amputee, it varied between 0.29 m2 and 0.62 m2. The ACd difference between the able-bodied and the amputee ranged from 3% to 28% and the drag differed between 2% and 19%. The drag coefficient ranged between 0.55 and 0.84 for the able-bodied and from 0.45 and 0.92 for the shoulder-amputee. The drag ranged across the different velocities (1-13 m/s) from 0.36 N – 39.25 N for the ablebodied cyclist and for the shoulder-amputee between 0.38 N – 31.69 N. The two cyclist models presented significant differences and small effect sizes (t = 2.720; p = 0.019; d = 0.18). The linear regression models computed the drag differences between the able-bodied and the disabled cyclist; a significant relationship and very high effect sizes for drag (R2 = 0.997; R2a = 0.995; SEE = 0.996; p < 0.001) were observed. This study allowed us to conclude that the shoulder-amputee cyclist presents a lower drag compared to the able-bodied one.
- Clustering U-14 Portuguese regional team football players by lower limb strength, power, dynamic balance, speed and change of direction: understanding the field position factorPublication . Sampaio, Tatiana; Marinho, D.A.; Teixeira, José Eduardo; Oliveira, João P.; Morais, J.E.The aim of this study was to cluster U-14 Portuguese regional team football players based on variables related to lower limb strength and power, dynamic balance, linear sprint, and change of direction. Method: The sample consisted of 22 young male soccer players (13.83 ± 0.44 years). A set of variables related to lower limb strength and power, dynamic balance, linear sprint, and change of direction was measured. Results: Overall, a non-significant field position was observed. The countermovement jump (p < 0.001, η2 = 0.73), squat jump (p < 0.001), and 30 m linear sprint (p = 0.001) were the main variables responsible for establishing the clusters. Cluster 1 was characterized by a high slalom, i.e., it took longer to complete the test (speed and change of direction) and a low composite score in the dynamic balance. Cluster 2 was characterized by high squat jump, countermovement jump, and reactive strength ratio (lower limb strength and power). Cluster 3 was characterized by low squat jump and countermovement jump (lower limb strength and power), and a high 30 m sprint, i.e., it took longer to complete the test (speed and change of direction). Based on the results of the territorial map, the clusters consisted of: (i) cluster 1: two forwards, one midfielder, and five defenders; (ii) cluster 2: three forwards, two midfielders, and two defenders, and; (iii) cluster 3: four midfielders and three defenders. Conclusions: Players from different field positions composed the three clusters. There was no cluster composed exclusively of players of the same field position. The development of individualized and specific enrichment training programs should consider a cluster analysis, as the positional effect can be overlooked.
- Profile of female swimmers competing in the 50 m events at the 2021 LEN European ChampionshipsPublication . Oliveira, João P.; Marinho, D.A.; Barbosa, Tiago M.; Sampaio, Tatiana; Morais, J.E.This study aimed to understand whether there are significant differ- ences in stroke kinematics between tiers in female swimmers com- peting in the four 50 m events of the 2021 European Championships and to understand the speed-time relationship in the four race events per tier. Participants were all female swimmers (backstroke: 78 swim- mers; breaststroke: 75 swimmers; butterfly: 74 swimmers; freestyle: 87 swimmers) who participated in the 50 m events at the 2021 LEN European Championships held in Budapest (i.e. heats, semi-finals, and final). For each swimming stroke, swimmers were divided into three tiers (best-performing swimmers, intermedium-performing swimmers, and poorest-performing swimmers). Swimming speed revealed a significant tier effect (p < 0.05) in all race sections for all swimming strokes. The other stroke kinematic variables revealed divergent findings, but the stroke frequency presented an overall tier effect (p < 0.05) across all four swimming strokes. Curve fitting for all swimming strokes and tiers revealed a cubic relationship. Thus, it should be considered that female swimmers who compete in 50 m events in major competitions adopt an all-out strategy. The present data provide coaches with insightful information about the main trend in 50 m sprint events, specifically in each section of the race.
- Bibliometric Review of the Step Test: A Comprehensive Analysis of Research Trends and DevelopmentPublication . Sampaio, Tatiana; Marinho, D.A.; Bragada, José A.; Morais, J.E.The step test provides valuable information on cardiorespiratory parameters such as maximal oxygen uptake and heart rate. Cardiorespiratory capacity is critical to health-related fitness, with heart rate recovery after exercise serving as a predictor of mortality risk. Main Body: The primary objective of this review was to identify trends, key contributors, and emerging themes in the step test literature through 2023 using the Web of Science Core Collection. Bibliometric data extraction and analysis were performed using a dedicated bibliometric software (VOSviewer). The analysis showed continued interest through 2021. The research categories highlight the multidisciplinary nature of the step test, covering cardiovascular systems, respiratory systems, sports sciences, and medicine. It has gained global attention, with 31 countries involved, with Brazil and the United States leading the way. The diversity of contributing nations is increasing, reflecting a growing global interest. With 111 journals involved, such as Respiratory Care and Medicine and Science in Sports and Exercise, step test research is spread across the academic landscape. With 761 contributing researchers, there is a collaborative and diverse community. The top 10 institutions, including the University of Alabama System and Monash University, illustrate the variety of settings in which step test studies are conducted. Step test studies span multiple disciplines, underscoring their adaptability. The clusters identified in this bibliometric analysis of the step test literature guide future research, suggesting avenues for refining protocols, exploring health implications, optimizing tests for specific conditions such as chronic obstructive pulmonary disease, and adapting step tests in diverse populations. Conclusions: Practical implications highlight the role of the step test in cardiovascular risk assessment, fitness monitoring, and rehabilitation. This broad review underscores the relevance of the step test in diverse settings, reflecting its adaptability and ease of application across occupational and clinical settings
- Race analysis in swimming: understanding the evolution of publications, citations and networks through bibliometric reviewPublication . Morais, J.E.; Barbosa, Tiago M.; Arellano, Raúl; Silva, A.J.; Sampaio, Tatiana; Oliveira, João P.; Marinho, D.A.The aim of this study was to conduct a scoping and bibliometric review of swimming articles related to race analysis. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were used to identify relevant studies. Articles on race analysis in swimming published between 1984 and December 31, 2023 were retrieved from the Web of Science database. 366 records were screened and a total of 74 articles were retained for analysis. Until 2012, there were some time intervals with no or few publications. From 2012, there was a clear upward trend in publications and citations. This theme was led by the United States of America, Australia, and Spain. Australia and Spain maintain their status as the countries with the most publications. The analysis of author collaborations revealed two clusters with Spanish authors, and the remaining clusters are composed of Portuguese, Swiss, and Australian authors. With this bibliometric review, it has been possible to understand the evolution of the articles published on race analysis in swimming, the countries and the authors that have contributed most to this topic over the years. The prediction model shows that the number of articles and citations on this topic will continue to increase over the next 10 years (until 2034)