Using Bayesian Networks to Explore Risk Factors for Sports Injuries in Chinese Adult Women Who Exercise Regularly: A Nationwide Study

Using Bayesian Networks to Explore Risk Factors for Sports Injuries in Chinese Adult Women Who Exercise Regularly: A Nationwide Study | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Using Bayesian Networks to Explore Risk Factors for Sports Injuries in Chinese Adult Women Who Exercise Regularly: A Nationwide Study He Xinhao, Song Wenzhu, Ran Ruimeng, Li Xuemei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7081577/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Objective Given the influence of women's unique joint structures and hormonal levels, sports injuries among females have become a focus in sports research. This study aimed to use Logistic regression and Bayesian networks (BNs) models to explore factors associated with sports injuries in Chinese adult females who exercise regularly. Methods This was a cross - sectional study. From October to November 2021, data on sports - injury - related factors were collected through online questionnaires from adult females aged 18 and above who exercised regularly in 336 cities across 34 provinces nationwide. Logistic regression and BNs models were used to explore factors associated with sports injuries in Chinese adult females with regular exercise. Results A total of 6,912 valid questionnaires were included, with a median age of 34.00 (31.00–39.00) years. Among the participants, 4,265 (61.70%) had experienced sports injuries. Logistic regression indicated that age grouping, body mass index (BMI), the most frequent daily exercise time, learning of specialized movement, insufficient energy to complete daily tasks, fatigue or illness status, sleep quality, and awareness of sports injury risks were all risk factors for sports injuries. BNs revealed that age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were directly correlated with sports injuries. Moreover, exercise venue type and learning of specialized movement were indirectly associated with sports injuries through the mediating variable of the most frequent daily exercise time. Conclusion BNs can identify both direct and indirect correlates of sports injuries, and Bayesian risk inference enables risk prediction for sports injuries. BNs serve as a complementary method to logistic regression, providing deeper insights into complex risk factor interactions. Exercise injury adult women bayesian networks influencing factors Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Introduction As China's sports - exercising population grows, sports injury prevention has become a key focus in sports research. The General Administration of Sport of China indicates that 30.3% of China's adult regular exercisers[ 1 ] and 36% of women are engaged in regular fitness activities[ 2 ]. However, However, exercise routines are often accompanied by the risk of sports injuries, which pose health threats such as pain, discomfort, and even sudden death to individuals[ 3 ]. Studies show that 43.6% of athletes have suffered from acute sports injuries[ 4 ], and female athletes have a 21% higher injury risk compared to male athletes[ 5 ]. Consequently, identifying the factors related to sports injuries in adult women and implementing targeted measures to reduce their risk are still urgent issues to be tackled currently. Anatomical characteristics in women, such as knee and ligament structure, put them at a higher risk of anterior cruciate ligament injuries[ 6 , 7 ]. Additionally, fluctuations in hormone levels may influence muscle strength and joint stability, exacerbating the occurrence of sports injuries[ 8 ]. Furthermore, women’s exercise - related behavioral patterns[ 9 ], sports equipment choices[ 10 ], and psychological states[ 11 ] have emerged as significant correlates of injury risk. Beyond affecting physical health and athletic performance[ 3 ], sports injuries can also have a negative impact on their daily life and long - term exercise habits[ 12 ]. Although numerous studies have explored the causes and preventive strategies for sports injuries, most of them have focused on athletes or mixed - gender samples[ 13 , 14 ], with logistic regression being used to discuss influencing factors[ 15 , 16 ]. These studies have proposed risk factors such as gender, age, body mass index (BMI), exercise habits, external environment, and intrapersonal factors[ 15 , 16 ]. However, this approach has significant limitations. First, injury risk factors are often interdependent, which violates the statistical assumption of independence required by the regression model. Second, traditional regression models cannot capture the direct and indirect associations between variables[ 17 ]. Finally, from a medical - biological perspective, sports injuries and their associated factors (or among the factors themselves) may present complex network - structured relationships, which are characterized by holistic linkage effects that include both main and interaction effects. In such networks, a change in one controllable factor can trigger an impact on the overall injury risk. Therefore, using a more suitable model to explore the factors associated with exercise - related injuries in Chinese women has considerable practical significance. Bayesian Networks (BNs) offer a superior solution. BNs represent directed acyclic graphs for probabilistic inference[ 18 ]. Recently, they have gained popularity in medicine[ 19 ], health management[ 20 ], and exercise science[ 21 ]. The core strength of BNs is their ability to deal with multi - variable interactions in complex networks and to quantify the strength of probabilistic dependencies between different nodes through conditional probability distribution tables[ 22 ]. Additionally, Bayesian risk inference can bring scientific value to clinical decision - making by flexibly realizing risk inference for outcomes of interest by inferring unknown nodes from known nodes[ 23 ]. Different from traditional regression models, BNs can capture not only direct variable associations but also reveal latent indirect effects, making them a valuable tool for predicting and preventing sports injuries. Thus, BNs could offer a more comprehensive framework for injury - risk analysis, serving as a robust complement to logistic regression models. Therefore, this study made use of sports injury data from Chinese adult women who engage in regular exercise to construct a Bayesian Networks (BNs) model. The aim was to reveal the complex network - dependent relationships among injury - related factors and to achieve individualized sports injury risk prediction via Bayesian inference. The findings will be conducive to reducing the incidence of exercise - related injuries, enhancing the quality of life, and providing scientific and practical guidance for sports health management organizations and policymakers. Consequently, this will promote the healthy development of the national fitness initiatives in China. Methods Participants It is a cross - sectional study. The data were collected through questionnaires on two major Chinese online platforms, Wenjuan Xing and NetEase, from October to November in 2021. The questionnaires were distributed to cover users across the nation, aiming to investigate information related to sports injuries among adult females aged 18 and above who exercise regularly in China. These users are from 336 cities in 34 provinces, so the information is representative of the whole country. Inclusion Criteria: (1) Meeting the regular exercise criteria: exercising at least 3 times per week, with each session lasting at least 30 minutes at moderate intensity or higher, or accumulating 150 minutes of moderate - intensity or 75 minutes of vigorous - intensity physical activity; (2) Being female adults aged 18 or above; (3) Having no clinically diagnosed chronic diseases. Exclusion Criteria: (1) Samples with missing variable data; (2) Response time less than 90 seconds (indicating insufficient engagement); (3) Inconsistent or contradictory responses among variables; (4) Body weight less than 40 kg or greater than 90 kg; (5) Body mass index (BMI) less than 16 kg/m² or greater than 35 kg/m²; (6) Samples with insufficient data for statistical aggregation (Fig. 1 ). All participants provided informed consent, and the study was approved by the Ethics Committee of Beijing Sport University. Variable collection Based on a comprehensive literature review, risk factors related to sports injuries were systematically screened to determine the core modules of the questionnaire, which include basic demographics, exercise habits, environmental factors, and sports - related cognition. Expert validation was carried out to assess reliability and validity, with a Cronbach's coefficient of 0.714 and a KMO value of 0.721 obtained. The study variables were as follows: (1) Basic demographics: age, body mass index (BMI); (2) Exercise history: learning of specialized movement, participation in regular strength training; (3) Exercise habits: the most frequent daily exercise time, pre - exercise warm - up, post - exercise relaxation, use of specialized athletic footwear; (4) Individual and environmental factors: exercise venue type, insufficient energy to complete daily tasks, fatigue/illness status, sleep quality, awareness of sports injury risks, and other relevant psychosocial/environmental variables. Additionally, exercise-related injury occurrence was collected as the primary outcome measure in this population. Variable definition In the study, age was divided into four groups: 18–29 years, 30–39 years, 40–49 years, and 50 years or older. Body mass index (BMI) was classified in line with the World Health Organization's Chinese reference standards, including four categories: underweight (< 18.5 kg/m²), normal weight (18.5–23.9 kg/m²), overweight (24.0–27.9 kg/m²), and obesity (≥ 28 kg/m²)[ 24 ]. Regarding exercise history, whether having learned specialized movement and having regular strength training were both categorized as binary variables (yes/no). In terms of exercise habits, the most common daily exercise time was divided into five categories: early morning, morning, afternoon, evening, or irregular. Pre - exercise warm - up, post - exercise relaxation, and the use of specialized athletic footwear were all defined as always, often, sometimes, occasionally, and never. Exercise venue types were classified as non - specialized (such as marble, concrete, land or other surfaces) or specialized (such as plastic, wooden floors or dedicated tracks). The insufficient energy to complete daily tasks was assessed on a four - point scale: often, sometimes, occasionally or never. Fatigue or illness status was categorized as no, yes or not sure. Sleep quality was evaluated as very good, better, okay or poor (including very poor). Awareness of sports injury risks was measured in four groups: fully understand, some, a little or none. The outcome variable, sports injury occurrence, was defined as a binary variable (yes/no), indicating whether an injury had been reported previously. Max-Min Hill Climbing (MMHC) Algorithm Common algorithms for Bayesian network (BN) model construction mainly include the constraint - based (CB) algorithm[ 25 ] and the score - and - search (SS) algorithm[ 26 ]. The CB algorithm has high learning efficiency and can obtain globally optimal solutions. Nevertheless, as the number of variables grows, the exponential growth of conditional set combinations for independence testing restricts its scalability to high - dimensional datasets. On the contrary, the SS algorithm overcomes this drawback but is highly reliant on variable ordering; sub optimal structures or missed true relationships may occur if the initial sequence is suboptima[ 27 ]. The MMHC algorithm combines the strengths of the CB and SS approaches in two phases. One of these phases is Local Structure Identification. It utilizes the Max - Min Parents and Children (MMPC) algorithm to quickly identify parent - child relationships through local search. In this way, it can reduce computational complexity by minimizing the number of conditional independence tests. The second phase is Global Structure Optimization, which employs a hill - climbing approach to optimize network scoring, thus enhancing the accuracy of the global topological structure. Bayesian networks BNs consist of a DAG and a CPT. The former comprises nodes and edges. Nodes represent variables in the network; if variable A points to variable B, this indicates a direct probability dependency between A and B. A is referred to as the parental node of B, and B as the child node of A. The CPT quantitatively describes the strength of probability dependence of a node and its parent node[ 28 ]. Thus, BNs utilize the graphical structure and determine the joint probability distribution of the random variable = \(\:x\) { \(\:{x}_{1}\) , \(\:{x}_{n}\) }, denoted as follows: $$\:\begin{array}{c}P\left({x}_{1},{x}_{2},\dots\:,{x}_{n}\right)=P\left({x}_{1}\right)P\left({x}_{2}|{x}_{1}\right)\cdots\:P\left({x}_{n}|{x}_{1},{x}_{2},\dots\:{,x}_{n-1}\right)\#\left(1\right)\end{array}$$ $$\:={{\Pi\:}}_{1}^{\text{n}}\text{P}\left({x}_{i}|\pi\:\left({x}_{i}\right)\right)$$ Given \(\:{\pi\:}\left({x}_{i}\right)\:\) denote the set of parent nodes of variable \(\:{x}_{1}\) , where \(\:{\pi\:}\left({\text{x}}_{\text{i}}\right)\subseteq\:\{{x}_{1},{x}_{2},\dots\:{,x}_{i-1}\}\) .When the values of the parent nodes in \(\:{\pi\:}\left({x}_{i}\right)\) are known, \(\:{x}_{i}\) becomes conditionally independent of other variables in \(\:\{{x}_{1},{x}_{2},\dots\:{,x}_{i-1}\}\) . Statistical analyses Statistical data were analyzed using R software (4.4.0). Base data were expressed as mean ± standard deviation or median ( P 25 , P 75 ); count data were expressed as number of cases (%), and χ2 test was used for comparison between groups. Indicators with statistically significant differences were included in the construction of logistic regression models and BNs models, and BNs results were visualized using Netica software. P < 0.05 was regarded as statistically significant. Results Baseline characteristics A total of 21,448 electronic questionnaires were distributed. After excluding males, samples with an answer time of less than 90 seconds, samples whose weight was outside the 40–90 kg range, samples with a BMI not in the 16–35 kg/m² range, samples containing missing values, samples with variable inconsistencies, and samples with too little data and unable to be merged, a total of 6,912 cases met the inclusion criteria, as shown in Fig. 1 . In this study, the median age of the overall sample was 34.00 (31.00–39.00) years. The median age of the group without sports injuries was 35.00 (32.00–43.00) years, while that of the group with sports injuries was 33.00 (30.00–38.00) years. There were 4,265 (61.70%) individuals with sports injuries and 2,647 (38.30%) without. The study demonstrated that different age groups, different BMI classes, learning of specialized movements, whether regular strength training was carried out, the most frequent daily exercise time, pre - exercise warm - up, post - exercise relaxation, use of specialized athletic footwear, exercise venue types, insufficient energy to complete daily tasks, fatigue or illness status, and sleep quality differed significantly in the sports injury group (P < 0.05), as shown in Table 1 . Table 1 Baseline characteristics Variables sports injuries N (N = 2647) Yes (N = 4265) P Age (years), n(%) < 0.001 18–29 349 (13.2) 1051 (24.6) 30–39 1402 (53) 2393 (56.1) 40–49 571 (21.6) 670 (15.7) ≥ 50 325 (12.3) 151 (3.5) BMI, n(%) < 0.001 underweight 313 (11.8) 722 (16.9) normal weight 1812 (68.5) 3009 (70.6) overweight 461 (17.4) 456 (10.7) obesity 61 (2.3) 78 (1.8) Learning of specialized movement, n(%) < 0.001 No 1865 (70.5) 2667 (62.5) Yes 782 (29.5) 1598 (37.5) Regular strength training, n(%) < 0.001 No 1819 (68.7) 2512 (58.9) Yes 828 (31.3) 1753 (41.1) Most frequent daily exercise time, n(%) < 0.001 early morning 504 (19) 784 (18.4) morning 237 (9) 735 (17.2) afternoon 235 (8.9) 973 (22.8) evening 1402 (53) 1428 (33.5) no regularity 269 (10.2) 345 (8.1) Pre-exercise warm-up, n(%) < 0.001 never 295 (11.1) 216 (5.1) occasionally 510 (19.3) 753 (17.7) sometimes 643 (24.3) 1232 (28.9) often 619 (23.4) 1224 (28.7) always 580 (21.9) 840 (19.7) Post-exercise relaxation, n(%) < 0.001 never 214 (8.1) 186 (4.4) occasionally 463 (17.5) 724 (17) sometimes 621 (23.5) 1189 (27.9) often 698 (26.4) 1351 (31.7) always 651 (24.6) 815 (19.1) Use of specialized athletic footwear, n(%) < 0.001 never 279 (10.5) 322 (7.5) occasionally 318 (12) 562 (13.2) sometimes 522 (19.7) 904 (21.2) often 815 (30.8) 1387 (32.5) always 713 (26.9) 1090 (25.6) Exercise venue type, n(%) 0.017 non-specialized 1599 (60.4) 2451 (57.5) specialized 1048 (39.6) 1814 (42.5) Insufficient energy to complete daily tasks, n(%) < 0.001 never 894 (33.8) 1103 (25.9) occasionally 1075 (40.6) 1618 (37.9) sometimes 496 (18.7) 1234 (28.9) often 182 (6.9) 310 (7.3) Fatigue or illness status, n(%) < 0.001 no 2203 (83.2) 2657 (62.3) yes 258 (9.7) 1244 (29.2) not sure 186 (7) 364 (8.5) Sleep quality, n(%) < 0.001 poor 309 (11.7) 779 (18.3) okay 996 (37.6) 1876 (44) better 864 (32.6) 1211 (28.4) very good 478 (18.1) 399 (9.4) Awareness of sports injury risks, n(%) 0.442 none 59 (2.2) 118 (2.8) a little 558 (21.1) 860 (20.2) some 1344 (50.8) 2193 (51.4) fully understand 686 (25.9) 1094 (25.7) Logistic regression analysis of sports injuries Due to the large sample size, this study included all potential variables in a multivariate logistic regression analysis. The model showed that age grouping, body mass index, the most frequent daily exercise time, learning of specialized movement, insufficient energy to do things, fatigue or illness status, quality of sleep, and knowing the risk of sports injuries were all correlates of sports injuries ( P < 0.05), as shown in Table 2 . Table 2 Logistic regression analysis of sports injuries Variables Wald χ 2 OR (95% CI ) p Age (years), n(%) 18–29 1 30–39 -4.612 0.648 (0.538, 0.778) < 0.001 40–49 -6.852 0.458 (0.366, 0.572) < 0.001 ≥ 50 -8.530 0.258 (0.189, 0.352) < 0.001 BMI, n(%) Underweight 1 Normal weight -0.069 0.993 (0.820, 1.202) 0.945 Overweight -2.870 0.693 (0.539, 0.890) 0.004 Obesity -1.641 0.676 (0.423, 1.081) 0.101 Most frequent daily exercise time, n(%) e arly morning 1 m orning 4.846 1.803 (1.422, 2.291) < 0.001 a fternoon 6.438 2.135 (1.697, 2.693) < 0.001 e vening -5.668 0.600 (0.502, 0.715) < 0.001 n o regularity -1.601 0.814 (0.633, 1.047) 0.109 Learning of specialized movement, n(%) No 1 Yes 3.110 1.294 (1.100, 1.523) 0.002 Regular strength training, n(%) No 1 Yes 0.653 1.057 (0.896, 1.247) 0.514 Pre-exercise warm-up, n(%) n ever 1 o ccasionally 2.693 1.541 (1.126, 2.113) 0.007 s ometimes 3.866 1.891 (1.370, 2.615) < 0.001 o ften 3.548 1.845 (1.317, 2.592) < 0.001 a lways 2.183 1.492 (1.043, 2.140) 0.029 Post-exercise relaxation, n(%) n ever 1 o ccasionally 1.176 1.232 (0.870, 1.743) 0.240 s ometimes 0.728 1.143 (0.797, 1.636) 0.467 o ften 0.752 1.153 (0.796, 1.668) 0.452 a lways -1.586 0.730 (0.495, 1.077) 0.113 Use of specialized athletic footwear, n(%) n ever 1.000 o ccasionally 0.189 1.029 (0.768, 1.377) 0.850 s ometimes -1.410 0.821 (0.624, 1.079) 0.159 o ften -1.304 0.838 (0.642, 1.092) 0.192 a lways -1.239 0.841 (0.639, 1.105) 0.215 Exercise venue type, n(%) n on-specialized s pecialized -1.454 0.903 (0.788, 1.036) 0.146 Insufficient energy to complete daily tasks, n(%) Never 1.000 o ccasionally -3.867 0.725 (0.615, 0.853) < 0.001 s ometimes -1.135 0.893 (0.734, 1.086) 0.257 o ften -5.448 0.437 (0.325, 0.589) < 0.001 Fatigue or illness status, n(%) n o 1.000 y es 12.431 3.624 (2.965, 4.451) < 0.001 n ot sure 5.648 2.023 (1.588, 2.590) < 0.001 Sleep quality, n(%) p oor 1.000 o kay -0.942 0.904 (0.732, 1.114) 0.346 b etter -2.488 0.752 (0.601, 0.941) 0.013 v ery good -6.167 0.434 (0.333, 0.565) < 0.001 Awareness of sports injury risks, n(%) n one 1 a little -1.961 0.640 (0.406, 0.994) 0.050 s ome -2.308 0.596 (0.381, 0.919) 0.021 f ully understand -1.852 0.653 (0.413, 1.019) 0.064 Bayesian networks The study incorporated variables with statistically significant differences into the construction of BNs based on logistic regression. Additionally, owing to the large sample size, the remaining variables were also included in the BN construction. The results indicated that the BNs comprised 14 nodes and 25 directed edges. Age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were direct correlates of sports injury occurrence. By contrast, exercise venue type and having learned specialized movements could be indirectly correlated with sports injury occurrence through the most frequent daily exercise time; regular strength training could be indirectly correlated with sports injury occurrence through age, the most frequent daily exercise time, and fatigue or illness status; and insufficient energy to complete daily tasks could be indirectly related to sports injuries through sleep quality and fatigue or illness status, as shown in Fig. 2. The values in the nodes’ boxes with matrix bars in the figure represent the prior probability of each node. For example, the value corresponding to the “sports injury occurrence” group is 61.2%, indicating that 61.2% of the total population has experienced sports injuries—this is the node’s prior probability. The arrows in the figure represent dependencies between nodes[ 29 ]. For instance, if “age” points to “sports injuries,” this signifies that age is the parent node of sports injuries, meaning age is directly related to exercise injury. Bayesian Risk Inference BNs enable inference of unknown nodes from known nodes, thereby facilitating risk prediction of disease occurrence. Probabilistic models can quantitatively analyze how relevant factors influence sports injury occurrence by calculating conditional probabilities, allowing the impact of each node in the BNs on sports injury risk to be inferred via Bayesian reasoning[ 23 ]. BNs revealed that if a regular-exercising adult female was in a state of fatigue or illness, her risk of sports injury increased from 0.612 to 0.793, i.e., P(Sports Injury | Fatigue or Illness Status) = 0.793 (Fig. 3 ). If her sleep quality was also poor, the risk further increased to 0.854, i.e., P(Sports Injury | Fatigue or Illness Status, Poor Sleep Quality) = 0.854 (Fig. 4 ). Among young individuals (18–29 years old) with both fatigue/illness and poor sleep quality, the injury risk rose to 0.915, i.e., P(Sports Injury | Fatigue or Illness Status, Poor Sleep Quality, Young Age) = 0.915 (Fig. 5 ). Conversely, if such an individual habitually exercised in the morning, the risk escalated to 0.962, i.e., P(Sports Injury | Fatigue or Illness Status, Poor Sleep Quality, Young Age, Morning Exercise Habit) = 0.962 (Fig. 6). If regular-exercising adult females experienced fatigue or illness, their risk of sports injury increased to 0.793. If an individual experienced both fatigue/illness and poor sleep quality, their risk of sports injury rose to 0.854. If an individual with fatigue or illness and poor sleep quality was also young (aged 18–29 years), their risk of sports injury rose to 0.915. If an individual with fatigue/illness, poor sleep quality, and young age (18–29 years) was also accustomed to morning exercise, their risk of sports injury rose to 0.962. Discussion In this study, we comprehensively explored the associations between sports injuries in Chinese adult women who engage in regular exercise by using both logistic regression and Bayesian networks (BNs).The results of the logistic regression demonstrated significant associations between sports injuries and variables such as age, body mass index (BMI), learning of specific movements, the most frequent daily exercise time, pre - exercise warm - up, fatigue or illness status, insufficient energy to complete daily tasks, sleep quality, and awareness of sports injury risks, thus identifying the main correlates. In contrast, BNs further revealed complex probabilistic dependency paths among variables, constructing a network structure with 14 nodes and 25 directed edges and clearly depicting the interconnections between direct and indirect risk factors. Through BN inference, we found that the superposition of multiple factors can significantly increase the risk of sports injury, which reflects the unique advantages of BNs in structural modeling and risk prediction. These findings provide a theoretical basis for precise prevention and intervention in the female sports population. As age increases, the injury risk shows a gradual decrease. The middle - aged and elderly groups have a significantly lower risk compared to young adults. This may be related to their relatively moderate exercise intensity, more conservative movement choices and stronger risk - avoidance awareness[ 30 ]. In terms of body mass index (BMI), overweight individuals have a significantly lower injury risk than those with low body weight, indicating that moderate fat and muscle reserves may provide better joint cushioning and energy storage. On the contrary, low - body - weight individuals often have lower bone mass and insufficient muscle support, which increases their susceptibility to injury[ 31 , 32 ]. Regarding exercise timing, compared with early morning exercise, afternoon and morning exercise are associated with a higher injury risk, possibly because the exercise intensity is higher during these periods. In contrast, people who exercise in the evening more often choose low - demand activities such as jogging or brisk walking[ 33 ]. Paradoxically, individuals who have learned specialized movements face a higher injury risk, probably because their participation in complex or difficult techniques increases the probability of making technical errors. A higher frequency of pre - exercise warm - up is also associated with an increased risk, perhaps indicating that those who warm up frequently engage in more sports (higher risk exposure) or use inappropriate warm - up techniques. In terms of physical state and subjective perception, insufficient energy to complete daily tasks was associated with a lower injury risk, suggesting that individuals may actively reduce exercise when unwell[ 34 ]. In contrast, exercising while fatigued or ill substantially increased the risk[ 35 ], highlighting the need to regulate exercise behavior during poor health. Good sleep quality significantly reduced injury risk[ 36 ], emphasizing the role of recovery mechanisms. Cognitively, partial awareness of sports - injury risks was correlated with a lower injury incidence[ 37 ], indicating that risk awareness positively affects behavioral norms and prevention strategies. These findings reveal the multifactorial mechanisms of female sports injuries across physiological, behavioral, and cognitive dimensions, providing a foundation for targeted interventions. Bayesian networks (BNs) revealed that, in addition to direct risk factors, multiple indirect correlates influence sports injury through mediating pathways, deepening the systematic understanding of injury mechanisms. The results showed that age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were direct determinants of sports injury, together forming the core nodes of injury risk. Notably, variables such as exercise venue type and learning of specialized movement did not directly contribute to injury outcomes but influenced injury risk through the mediating variable of exercise duration. This implies that poor exercise environments and technical complexity may indirectly increase injury incidence by prolonging or intensifying exercise sessions. Additionally, although regular strength training was not a direct risk factor, it had multi - path linkages with injury risk through age, the most frequent daily exercise time, and physical status (such as fatigue or illness status). This implies that high - intensity training may be a predisposing factor for sports injuries in certain populations or physiological states. Moreover, while insufficient energy to complete daily tasks did not directly correlate with injury, it affected injury risk through “sleep quality” and “fatigue or illness status,” highlighting the crucial role of physical condition and recovery mechanisms in the occurrence of injury. These findings stress that sports injury is not caused by single variables but results from multifactorial processes mediated by causal chains, thus demonstrating the unique value of Bayesian Networks (BNs) in modeling complex health - behavior systems. By revealing both direct associations and indirect dependency paths, BNs offer a comprehensive framework for identifying high - risk profiles and designing tiered intervention strategies for female exercisers. Compared to logistic regression models, Bayesian Networks (BNs) have distinct advantages in modeling variable relationships, especially in three key aspects.Firstly, BNs can identify both direct and indirect correlations[ 38 ]. For example, in the study of sports injury, age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were direct correlates. Meanwhile, variables such as exercise venue type, learning of specialized movement, regular strength training, and energy levels influenced injury outcomes indirectly through mediating pathways. This pathway structure reveals multilevel causal chains that link behavioral, environmental, and physiological factors - complex interactions that regression analysis alone cannot fully capture. Second, BNs visualize variable linkages and conditional dependencies[ 39 ]. For instance, regular strength training indirectly affects injury risk through age, the most frequent daily exercise time, and physical status (such as fatigue or illness status). This highlights the need for intervention strategies that take into account synergistic effects rather than isolating risk factors. This networked structure reflects how injury risk spreads in real - world behavioral systems, enhancing the model's explanatory power for complex interactions. Thirdly, BNs have a unique advantage in conditional - probability - based inference: they can dynamically estimate injury probability based on known individual characteristics, enabling personalized, context - specific risk prediction 38 . This ability is of great value for practical health management, facilitating the development of targeted preventive measures. For example, the incremental risk increases shown in Figs. 3 –6 illustrate how the combination of fatigue, poor sleep, youth, and morning exercise habits amplifies injury probability in a predictable, layered manner. Thus, Bayesian Networks (BNs) outperform traditional regression methods in structural modeling. They can disentangle direct - indirect relationships, visualize dependency networks and enable dynamic risk inference. These features lay a solid theoretical and technical foundation for multi - dimensional, real - time injury risk assessment among female exercisers, providing actionable insights for precision public health interventions. Strengths and limitations This study has multiple advantages. First, a large sample size contributes to statistical stability, providing a solid foundation for model construction. Second, this study is the first to apply Bayesian Networks (BNs) to explore sports injury correlates in Chinese adult women who exercise regularly. It fills a gap in quantitative modeling research for this population and promotes the shift from traditional descriptive analyses to intelligent inference models in injury prevention. However, the study also has limitations. First, the questionnaire - based design is prone to recall bias and potential ambiguity in response options, which may affect the accuracy of certain variables. Future research could enhance data quality by integrating sports recording devices (such as accelerometers, heart rate monitors) with open - ended questions to capture more detailed behavioral information. Second, the cross - sectional design does not allow for definitive inference of causal temporal sequences. Prospective cohort studies are required to validate the hypothesized causal chains identified by the BNs. Third, the current BN model demands that variables be discretized into categorical types, which may potentially limit the use of continuous data (for example, the most frequent daily exercise time and intensity). Future versions could explore hybrid BNs or use nested discretization and sensitivity analysis to maximize the retention of information from continuous variables. Conclusion Overall, this study systematically identified and analyzed multi - level factors affecting sports injuries among Chinese adult female exercisers and constructed a novel Bayesian Networks (BNs) model that incorporates both direct and indirect risk pathways. This work offers a new framework for individualized risk prediction and comprehensive intervention strategies. Besides enriching the theoretical basis of women's sports health research, the findings provide a scientific foundation for optimizing sports population management. In the future, longitudinal research designs and model refinements (such as hybrid BN development) will be crucial for translating risk identification into precision prevention, ultimately creating a safer and more sustainable exercise environment for women. Declarations Ethics approval and consent to participate All participants provided informed consent, and the study was approved by the Ethics Committee of Beijing Sport University. This study performed on human data or materials complied with the Declaration of Helsinki. Consent for publication Not applicable. Competing interests The authors declare no competing interests. Funding This work was supported by a National Key Research and Development Program of China–Key Factors and Fitness Guidance Programs to Improve the Effectiveness of Exercise and Fitness (Project No. 2018YFC2000603) Author Contribution He Xinhao drafted the manuscript. Song Wenzhu, Ran Ruimeng, and Li Xuemei helped with data analysis and polished the manuscript. Song Wenzhu and Li Xuemei provided valuable advice on statistical methods and were responsible for the conception and design of the research. All authors contributed to the article and approved the final version of this manuscript. Acknowledgements Not Applicable. Data Availability The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. References The National Center for National Physical Fitness Monitoring released the. 2020 Survey Bulletin on the Status of National Fitness Activity_National Sports Administration. https://www.sport.gov.cn/n315/n329/c24335053/content.html . Accessed 26 Feb 2025. Mao Y, Zhu Y, Sun F, Jia C, Liu B. An analysis of women’s fitness demands and their influencing factors in urban china. Healthc (basel Switz). 2022;10:187. van Mechelen W, Hlobil H, Kemper HC. Incidence, severity, aetiology and prevention of sports injuries. A review of concepts. Sports Med (Auckl NZ). 1992;14:82–99. Kelly S, Pollock N, Polglass G, Clarsen B. Injury and illness in elite athletics: a prospective cohort study over three seasons. Int J Sports Phys Ther 17:420–33. Fukuda N, Hangai M, Hashimoto R, Nishida Y, Mizutani Y, Okuwaki T et al. Injury characteristics among japanese international athletes: report on the pre-competition medical check-up data of the japanese olympic committee. Cureus 16:e72869. Arendt E, Dick R. Knee injury patterns among men and women in collegiate basketball and soccer. NCAA data and review of literature. Am J Sports Med. 1995;23:694–701. Toth AP, Cordasco FA. Anterior cruciate ligament injuries in the female athlete. j gend-specif med: JGSM: off j Partnersh Women. ’s Health Columbia. 2001;4:25–34. Martínez-Fortuny N, Alonso-Calvete A, Da Cuña-Carrera I, Abalo-Núñez R. Menstrual cycle and sport injuries: a systematic review. Int J Environ Res Public Health. 2023;20:3264. Ruffault A, Sorg M, Martin S, Hanon C, Jacquet L, Verhagen E, et al. Determinants of the adoption of injury risk reduction programmes in athletics (track and field): an online survey of 7715 french athletes. Br J Sports Med. 2022;56:499–505. Willems TM, Ley C, Goetghebeur E, Theisen D, Malisoux L. Motion-control shoes reduce the risk of pronation-related pathologies in recreational runners: a secondary analysis of a randomized controlled trial. J Orthop Sports Phys Ther. 2021;51:135–43. Tranaeus U, Martin S, Ivarsson A. Psychosocial risk factors for overuse injuries in competitive athletes: a mixed-studies systematic review. Sports Med (auckl N.z,). 2022;52:773–88. Kvist J, Silbernagel KG. Fear of movement and reinjury in sports medicine: relevance for rehabilitation and return to sport. Phys Ther. 2022;102:pzab272. Crossley KM, Patterson BE, Culvenor AG, Bruder AM, Mosler AB, Mentiplay BF. Making football safer for women: a systematic review and meta-analysis of injury prevention programmes in 11 773 female football (soccer) players. Br J Sports Med. 2020;54:1089–98. Truong LK, Mosewich AD, Holt CJ, Le CY, Miciak M, Whittaker JL. Psychological, social and contextual factors across recovery stages following a sport-related knee injury: a scoping review. Br J Sports Med. 2020;54:1149–56. Ding L, Brewer BW, Mackey M, Cai H, Zhang J, Song Y, et al. Factors associated with school sports injury among elementary and middle school students in shanghai, china. Int J Environ Res Public Health. 2022;19:6406. Franettovich Smith MM, Mendis MD, Parker A, Grantham B, Stewart S, Hides J. Injury surveillance of an australian community netball club. Phys Ther Sport: Off J Assoc Chart Physiother Sports Med. 2020;44:41–6. Song W, Gong H, Wang Q, Zhang L, Qiu L, Hu X, et al. Using bayesian networks with max-min hill-climbing algorithm to detect factors related to multimorbidity. Front Cardiovasc Med. 2022;9:984883. Briganti G, Scutari M, McNally RJ. A tutorial on bayesian networks for psychopathology researchers. Psychol Methods. 2023;28:947–61. Angelopoulos N, Chatzipli A, Nangalia J, Maura F, Campbell PJ. Bayesian networks elucidate complex genomic landscapes in cancer. Commun Biol. 2022;5:306. Ordovas JM, Rios-Insua D, Santos-Lozano A, Lucia A, Torres A, Kosgodagan A, et al. A bayesian network model for predicting cardiovascular risk. Comput Methods Programs Biomed. 2023;231:107405. Yung KKY, Wu PPY, aus der Fünten K, Hecksteden A, Meyer T. Using a bayesian network to classify time to return to sport based on football injury epidemiological data. PLoS ONE. 2025;20:e0314184. Song W, Qiu L, Qing J, Zhi W, Zha Z, Hu X, et al. Using bayesian network model with MMHC algorithm to detect risk factors for stroke. Math Biosci Eng: MBE. 2022;19:13660–74. Ma SX, Dhanaliwala AH, Rudie JD, Rauschecker AM, Roberts-Wolfe D, Haddawy P, et al. Bayesian networks in radiology. Radiol: Artif Intell. 2023;5:e210187. Pan X-F, Wang L, Pan A. Epidemiology and determinants of obesity in China. Lancet Diabetes Endocrinol. 2021;9:373–92. Campos LMD. Independency relationships and learning algorithms for singly connected networks. J Exp Theor Artif Intell. 1998. https://doi.org/10.1080/095281398146743 . Heckerman D, Geiger D, Chickering DM. Learning bayesian networks: the combination of knowledge and statistical data. Mach Learn. 1995;20:197–243. Tsamardinos I, Brown LE, Aliferis CF. The max-min hill-climbing bayesian network structure learning algorithm. Mach Learn. 2006;65:31–78. Quan D, Ren J, Ren H, Linghu L, Wang X, Li M, et al. Exploring influencing factors of chronic obstructive pulmonary disease based on elastic net and bayesian network. Sci Rep. 2022;12:7563. Quan D, Ren J, Ren H, Linghu L, Wang X, Li M, et al. Exploring influencing factors of chronic obstructive pulmonary disease based on elastic net and bayesian network. Sci Rep. 2022;12:7563. Davison RCR, Cowan DT. Ageing, sport and physical activity participation in Scotland. Front Sports Act Living. 2023;5:1213924. Cederholm T, Jensen GL, Correia MITD, Gonzalez MC, Fukushima R, Pisprasert V, et al. The GLIM consensus approach to diagnosis of malnutrition: a 5-year update. Clin Nutr (edinb Scotl). 2025;49:11–20. Han S, Park J, Jang H, Nah S, Boo J, Han K, et al. Incidence of hip fracture in underweight individuals: a nationwide population-based cohort study in korea. J Cachexia Sarcopenia Muscle. 2022;13:2473–9. Su Y, Li H, Jiang S, Li Y, Li Y, Zhang G. The relationship between nighttime exercise and problematic smartphone use before sleep and associated health issues: a cross-sectional study. BMC Public Health. 2024;24:590. De Ste Croix MBA, Hughes JD, Lloyd RS, Oliver JL, Read PJ. Leg stiffness in female soccer players: intersession reliability and the fatiguing effects of soccer-specific exercise. J Strength Cond Res. 2017;31:3052–8. Pires FO, Silva-Júnior FL, Brietzke C, Franco-Alvarenga PE, Pinheiro FA, de França NM, et al. Mental Fatigue Alters Cortical Activation and Psychological Responses, Impairing Performance in a Distance-Based Cycling Trial. Front Physiol. 2018;9:227. Huang K, Ihm J. Sleep and injury risk. Curr Sports Med Rep. 2021;20:286–90. Edouard P, Sorg M, Martin S, Verhagen E, Ruffault A. Athletes who have already experienced an injury are more prone to adhere to an injury risk reduction approach than those who do not: an online survey of 7870 french athletics (track and field) athletes. BMJ Open Sport Exerc Med. 2024;10:e001768. Yung KKY, Wu PPY, aus der Fünten K, Hecksteden A, Meyer T. Using a bayesian network to classify time to return to sport based on football injury epidemiological data. PLoS ONE. 2025;20:e0314184. Lalika L, Kitali AE, Haule HJ, Kidando E, Sando T, Alluri P. What are the leading causes of fatal and severe injury crashes involving older pedestrian? Evidence from bayesian network model. J Saf Res. 2022;80:281–92. Additional Declarations No competing interests reported. Supplementary Files Questionnaire.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 24 Aug, 2025 Reviews received at journal 24 Aug, 2025 Reviewers agreed at journal 24 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers invited by journal 11 Aug, 2025 Editor assigned by journal 06 Aug, 2025 Editor invited by journal 21 Jul, 2025 Submission checks completed at journal 21 Jul, 2025 First submitted to journal 21 Jul, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7081577","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":502200396,"identity":"0d3ec96c-80a7-4b35-a2a0-e0fb6e38ba3a","order_by":0,"name":"He Xinhao","email":"","orcid":"","institution":"Beijing Sport University","correspondingAuthor":false,"prefix":"","firstName":"He","middleName":"","lastName":"Xinhao","suffix":""},{"id":502200397,"identity":"4aabe958-58cb-48e7-8715-02edfd31dc5a","order_by":1,"name":"Song Wenzhu","email":"","orcid":"","institution":"Zhejiang University","correspondingAuthor":false,"prefix":"","firstName":"Song","middleName":"","lastName":"Wenzhu","suffix":""},{"id":502200400,"identity":"93fde315-2166-4586-b2b9-a78c84f39f81","order_by":2,"name":"Ran Ruimeng","email":"","orcid":"","institution":"Beijing Sport University","correspondingAuthor":false,"prefix":"","firstName":"Ran","middleName":"","lastName":"Ruimeng","suffix":""},{"id":502200402,"identity":"c006a9ea-fa07-46c8-8c5f-82f094f5fadc","order_by":3,"name":"Li Xuemei","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYBACfvbmAwYfG8BsA+K0SPYcSyicSZIWgxs5Bp95SdLCcCDHcLPtjrrEBvbmbRIMNXcI62BsOFZsnHvmcGIDz7EyCYZjzwhrYWZs3mac23YgsUEix0yCseEwYS1szAzmvy3bgA6Tf0OkFh42FgNjxjZmoC08RGqR4GFLMOw9c9i4jSet2CLhGBFa7O8/PmDwc0edbD/74Y03PtQQoQUO2EBEAgkaRsEoGAWjYBTgAQAD5TniqkTRHgAAAABJRU5ErkJggg==","orcid":"","institution":"Beijing Sport University","correspondingAuthor":true,"prefix":"","firstName":"Li","middleName":"","lastName":"Xuemei","suffix":""}],"badges":[],"createdAt":"2025-07-09 08:23:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7081577/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7081577/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89385182,"identity":"50c9b545-c897-4a17-810e-93a8ece0d7a4","added_by":"auto","created_at":"2025-08-19 12:28:42","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":125125,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of the research object of this study\u003c/p\u003e","description":"","filename":"image1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/d5d0453aad92bb43769d5b89.jpeg"},{"id":89385183,"identity":"6bfe91c9-593d-4a78-a39f-1b033a086fb9","added_by":"auto","created_at":"2025-08-19 12:28:42","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":267793,"visible":true,"origin":"","legend":"\u003cp\u003eNetwork probability plot of sports injuries and related factors in Chinese regular-exercise adult females\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/172065da0538568012bb1904.png"},{"id":89386754,"identity":"ce91738b-ea97-4024-91ac-d4179d280731","added_by":"auto","created_at":"2025-08-19 12:36:42","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":284890,"visible":true,"origin":"","legend":"\u003cp\u003eChanges in network structure showing the effect of fatigue or illness status on sports injuries\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/7994271fc31cf78e82f735e4.png"},{"id":89388880,"identity":"586e818a-9287-4244-854b-301ddded1b76","added_by":"auto","created_at":"2025-08-19 12:44:42","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":229135,"visible":true,"origin":"","legend":"\u003cp\u003eChanges in network structure showing the effects of fatigue or illness status and sleep quality on sports injuries\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/922daa58a623aa4f94f700f1.png"},{"id":89385187,"identity":"ea41a4e8-623d-4ad2-b27e-c5fd96be6c8c","added_by":"auto","created_at":"2025-08-19 12:28:42","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":228721,"visible":true,"origin":"","legend":"\u003cp\u003eChanges in network structure showing the effects of fatigue or illness status, sleep quality, and age on sports injuries\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/a3ef11a7333bd79f65c102ef.png"},{"id":89386756,"identity":"95cf85fb-0fc2-4233-aaad-316cd0e7ff23","added_by":"auto","created_at":"2025-08-19 12:36:42","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":227415,"visible":true,"origin":"","legend":"\u003cp\u003eChanges in network structure showing the effects of fatigue or illness status, sleep quality, age, and the most frequent daily exercise time on sports injuries\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/bf72e35b0255e415f2b4bd11.png"},{"id":89389962,"identity":"5994daba-f157-4675-a7b3-a43d900bb729","added_by":"auto","created_at":"2025-08-19 12:52:44","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2168779,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/9066439f-fef8-48a9-8c43-dad51775e685.pdf"},{"id":89385180,"identity":"c8e7f200-427e-4381-8aca-202a0231d4fd","added_by":"auto","created_at":"2025-08-19 12:28:42","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":23204,"visible":true,"origin":"","legend":"","description":"","filename":"Questionnaire.docx","url":"https://assets-eu.researchsquare.com/files/rs-7081577/v1/302d0f481ea92e1766b855c2.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Using Bayesian Networks to Explore Risk Factors for Sports Injuries in Chinese Adult Women Who Exercise Regularly: A Nationwide Study","fulltext":[{"header":"Introduction","content":"\u003cp\u003eAs China's sports - exercising population grows, sports injury prevention has become a key focus in sports research. The General Administration of Sport of China indicates that 30.3% of China's adult regular exercisers[\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e] and 36% of women are engaged in regular fitness activities[\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. However, However, exercise routines are often accompanied by the risk of sports injuries, which pose health threats such as pain, discomfort, and even sudden death to individuals[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Studies show that 43.6% of athletes have suffered from acute sports injuries[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e], and female athletes have a 21% higher injury risk compared to male athletes[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Consequently, identifying the factors related to sports injuries in adult women and implementing targeted measures to reduce their risk are still urgent issues to be tackled currently.\u003c/p\u003e\u003cp\u003eAnatomical characteristics in women, such as knee and ligament structure, put them at a higher risk of anterior cruciate ligament injuries[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Additionally, fluctuations in hormone levels may influence muscle strength and joint stability, exacerbating the occurrence of sports injuries[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Furthermore, women\u0026rsquo;s exercise - related behavioral patterns[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e], sports equipment choices[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e], and psychological states[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] have emerged as significant correlates of injury risk. Beyond affecting physical health and athletic performance[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], sports injuries can also have a negative impact on their daily life and long - term exercise habits[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAlthough numerous studies have explored the causes and preventive strategies for sports injuries, most of them have focused on athletes or mixed - gender samples[\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e], with logistic regression being used to discuss influencing factors[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. These studies have proposed risk factors such as gender, age, body mass index (BMI), exercise habits, external environment, and intrapersonal factors[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. However, this approach has significant limitations. First, injury risk factors are often interdependent, which violates the statistical assumption of independence required by the regression model. Second, traditional regression models cannot capture the direct and indirect associations between variables[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. Finally, from a medical - biological perspective, sports injuries and their associated factors (or among the factors themselves) may present complex network - structured relationships, which are characterized by holistic linkage effects that include both main and interaction effects. In such networks, a change in one controllable factor can trigger an impact on the overall injury risk. Therefore, using a more suitable model to explore the factors associated with exercise - related injuries in Chinese women has considerable practical significance.\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eBayesian Networks (BNs) offer a superior solution. BNs represent directed acyclic graphs for probabilistic inference[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. Recently, they have gained popularity in medicine[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e], health management[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e], and exercise science[\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The core strength of BNs is their ability to deal with multi - variable interactions in complex networks and to quantify the strength of probabilistic dependencies between different nodes through conditional probability distribution tables[\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Additionally, Bayesian risk inference can bring scientific value to clinical decision - making by flexibly realizing risk inference for outcomes of interest by inferring unknown nodes from known nodes[\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Different from traditional regression models, BNs can capture not only direct variable associations but also reveal latent indirect effects, making them a valuable tool for predicting and preventing sports injuries. Thus, BNs could offer a more comprehensive framework for injury - risk analysis, serving as a robust complement to logistic regression models.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e\u003cp\u003eTherefore, this study made use of sports injury data from Chinese adult women who engage in regular exercise to construct a Bayesian Networks (BNs) model. The aim was to reveal the complex network - dependent relationships among injury - related factors and to achieve individualized sports injury risk prediction via Bayesian inference. The findings will be conducive to reducing the incidence of exercise - related injuries, enhancing the quality of life, and providing scientific and practical guidance for sports health management organizations and policymakers. Consequently, this will promote the healthy development of the national fitness initiatives in China.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003e\u003cstrong\u003eParticipants\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIt is a cross - sectional study. The data were collected through questionnaires on two major Chinese online platforms, Wenjuan Xing and NetEase, from October to November in 2021. The questionnaires were distributed to cover users across the nation, aiming to investigate information related to sports injuries among adult females aged 18 and above who exercise regularly in China. These users are from 336 cities in 34 provinces, so the information is representative of the whole country.\u003c/p\u003e\n\u003cp\u003eInclusion Criteria: (1) Meeting the regular exercise criteria: exercising at least 3 times per week, with each session lasting at least 30 minutes at moderate intensity or higher, or accumulating 150 minutes of moderate - intensity or 75 minutes of vigorous - intensity physical activity; (2) Being female adults aged 18 or above; (3) Having no clinically diagnosed chronic diseases.\u003c/p\u003e\n\u003cp\u003eExclusion Criteria: (1) Samples with missing variable data; (2) Response time less than 90 seconds (indicating insufficient engagement); (3) Inconsistent or contradictory responses among variables; (4) Body weight less than 40 kg or greater than 90 kg; (5) Body mass index (BMI) less than 16 kg/m\u0026sup2; or greater than 35 kg/m\u0026sup2;; (6) Samples with insufficient data for statistical aggregation (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e). All participants provided informed consent, and the study was approved by the Ethics Committee of Beijing Sport University.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eVariable collection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBased on a comprehensive literature review, risk factors related to sports injuries were systematically screened to determine the core modules of the questionnaire, which include basic demographics, exercise habits, environmental factors, and sports - related cognition. Expert validation was carried out to assess reliability and validity, with a Cronbach's coefficient of 0.714 and a KMO value of 0.721 obtained. The study variables were as follows: (1) Basic demographics: age, body mass index (BMI); (2) Exercise history: learning of specialized movement, participation in regular strength training; (3) Exercise habits: the most frequent daily exercise time, pre - exercise warm - up, post - exercise relaxation, use of specialized athletic footwear; (4) Individual and environmental factors: exercise venue type, insufficient energy to complete daily tasks, fatigue/illness status, sleep quality, awareness of sports injury risks, and other relevant psychosocial/environmental variables.\u003c/p\u003e\n\u003cp\u003eAdditionally, exercise-related injury occurrence was collected as the primary outcome measure in this population.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eVariable definition\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn the study, age was divided into four groups: 18\u0026ndash;29 years, 30\u0026ndash;39 years, 40\u0026ndash;49 years, and 50 years or older. Body mass index (BMI) was classified in line with the World Health Organization's Chinese reference standards, including four categories: underweight (\u0026lt;\u0026thinsp;18.5 kg/m\u0026sup2;), normal weight (18.5\u0026ndash;23.9 kg/m\u0026sup2;), overweight (24.0\u0026ndash;27.9 kg/m\u0026sup2;), and obesity (\u0026ge;\u0026thinsp;28 kg/m\u0026sup2;)[\u003cspan class=\"CitationRef\"\u003e24\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eRegarding exercise history, whether having learned specialized movement and having regular strength training were both categorized as binary variables (yes/no). In terms of exercise habits, the most common daily exercise time was divided into five categories: early morning, morning, afternoon, evening, or irregular. Pre - exercise warm - up, post - exercise relaxation, and the use of specialized athletic footwear were all defined as always, often, sometimes, occasionally, and never.\u003c/p\u003e\n\u003cp\u003eExercise venue types were classified as non - specialized (such as marble, concrete, land or other surfaces) or specialized (such as plastic, wooden floors or dedicated tracks). The insufficient energy to complete daily tasks was assessed on a four - point scale: often, sometimes, occasionally or never. Fatigue or illness status was categorized as no, yes or not sure. Sleep quality was evaluated as very good, better, okay or poor (including very poor). Awareness of sports injury risks was measured in four groups: fully understand, some, a little or none. The outcome variable, sports injury occurrence, was defined as a binary variable (yes/no), indicating whether an injury had been reported previously.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMax-Min Hill Climbing (MMHC) Algorithm\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCommon algorithms for Bayesian network (BN) model construction mainly include the constraint - based (CB) algorithm[\u003cspan class=\"CitationRef\"\u003e25\u003c/span\u003e] and the score - and - search (SS) algorithm[\u003cspan class=\"CitationRef\"\u003e26\u003c/span\u003e]. The CB algorithm has high learning efficiency and can obtain globally optimal solutions. Nevertheless, as the number of variables grows, the exponential growth of conditional set combinations for independence testing restricts its scalability to high - dimensional datasets. On the contrary, the SS algorithm overcomes this drawback but is highly reliant on variable ordering; sub optimal structures or missed true relationships may occur if the initial sequence is suboptima[\u003cspan class=\"CitationRef\"\u003e27\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe MMHC algorithm combines the strengths of the CB and SS approaches in two phases. One of these phases is Local Structure Identification. It utilizes the Max - Min Parents and Children (MMPC) algorithm to quickly identify parent - child relationships through local search. In this way, it can reduce computational complexity by minimizing the number of conditional independence tests. The second phase is Global Structure Optimization, which employs a hill - climbing approach to optimize network scoring, thus enhancing the accuracy of the global topological structure.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eBayesian networks\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBNs consist of a DAG and a CPT. The former comprises nodes and edges. Nodes represent variables in the network; if variable A points to variable B, this indicates a direct probability dependency between A and B. A is referred to as the parental node of B, and B as the child node of A. The CPT quantitatively describes the strength of probability dependence of a node and its parent node[\u003cspan class=\"CitationRef\"\u003e28\u003c/span\u003e]. Thus, BNs utilize the graphical structure and determine the joint probability distribution of the random variable =\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:x\\)\u003c/span\u003e\u003c/span\u003e{\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{x}_{1}\\)\u003c/span\u003e\u003c/span\u003e, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{x}_{n}\\)\u003c/span\u003e\u003c/span\u003e}, denoted as follows:\u003c/p\u003e\n\u003cdiv id=\"Equa\" class=\"Equation\"\u003e\n\u003cdiv id=\"FileID_Equa\" class=\"mathdisplay\"\u003e$$\\:\\begin{array}{c}P\\left({x}_{1},{x}_{2},\\dots\\:,{x}_{n}\\right)=P\\left({x}_{1}\\right)P\\left({x}_{2}|{x}_{1}\\right)\\cdots\\:P\\left({x}_{n}|{x}_{1},{x}_{2},\\dots\\:{,x}_{n-1}\\right)\\#\\left(1\\right)\\end{array}$$\u003c/div\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Equb\" class=\"Equation\"\u003e\n\u003cdiv id=\"FileID_Equb\" class=\"mathdisplay\"\u003e$$\\:={{\\Pi\\:}}_{1}^{\\text{n}}\\text{P}\\left({x}_{i}|\\pi\\:\\left({x}_{i}\\right)\\right)$$\u003c/div\u003e\n\u003c/div\u003e\n\u003cp\u003eGiven \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\pi\\:}\\left({x}_{i}\\right)\\:\\)\u003c/span\u003e\u003c/span\u003edenote the set of parent nodes of variable \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{x}_{1}\\)\u003c/span\u003e\u003c/span\u003e, where \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\pi\\:}\\left({\\text{x}}_{\\text{i}}\\right)\\subseteq\\:\\{{x}_{1},{x}_{2},\\dots\\:{,x}_{i-1}\\}\\)\u003c/span\u003e\u003c/span\u003e.When the values of the parent nodes in \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\pi\\:}\\left({x}_{i}\\right)\\)\u003c/span\u003e\u003c/span\u003e are known, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{x}_{i}\\)\u003c/span\u003e\u003c/span\u003e becomes conditionally independent of other variables in \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:\\{{x}_{1},{x}_{2},\\dots\\:{,x}_{i-1}\\}\\)\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStatistical analyses\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eStatistical data were analyzed using R software (4.4.0). Base data were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation or median (\u003cem\u003eP\u003c/em\u003e\u003csub\u003e\u003cem\u003e25\u003c/em\u003e\u003c/sub\u003e, \u003cem\u003eP\u003c/em\u003e\u003csub\u003e\u003cem\u003e75\u003c/em\u003e\u003c/sub\u003e); count data were expressed as number of cases (%), and \u0026chi;2 test was used for comparison between groups. Indicators with statistically significant differences were included in the construction of logistic regression models and BNs models, and BNs results were visualized using Netica software. \u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was regarded as statistically significant.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003eBaseline characteristics\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 21,448 electronic questionnaires were distributed. After excluding males, samples with an answer time of less than 90 seconds, samples whose weight was outside the 40\u0026ndash;90 kg range, samples with a BMI not in the 16\u0026ndash;35 kg/m\u0026sup2; range, samples containing missing values, samples with variable inconsistencies, and samples with too little data and unable to be merged, a total of 6,912 cases met the inclusion criteria, as shown in Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\n\u003cp\u003eIn this study, the median age of the overall sample was 34.00 (31.00\u0026ndash;39.00) years. The median age of the group without sports injuries was 35.00 (32.00\u0026ndash;43.00) years, while that of the group with sports injuries was 33.00 (30.00\u0026ndash;38.00) years. There were 4,265 (61.70%) individuals with sports injuries and 2,647 (38.30%) without. The study demonstrated that different age groups, different BMI classes, learning of specialized movements, whether regular strength training was carried out, the most frequent daily exercise time, pre - exercise warm - up, post - exercise relaxation, use of specialized athletic footwear, exercise venue types, insufficient energy to complete daily tasks, fatigue or illness status, and sleep quality differed significantly in the sports injury group (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05), as shown in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab1\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eBaseline characteristics\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth rowspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eVariables\u003c/p\u003e\n\u003c/th\u003e\n\u003cth colspan=\"3\" align=\"left\"\u003e\n\u003cp\u003esports injuries\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eN (N\u0026thinsp;=\u0026thinsp;2647)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eYes (N\u0026thinsp;=\u0026thinsp;4265)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAge (years), n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e18\u0026ndash;29\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e349 (13.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1051 (24.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e30\u0026ndash;39\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1402 (53)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2393 (56.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e40\u0026ndash;49\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e571 (21.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e670 (15.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026ge;\u0026thinsp;50\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e325 (12.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e151 (3.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBMI, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eunderweight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e313 (11.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e722 (16.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enormal weight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1812 (68.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e3009 (70.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoverweight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e461 (17.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e456 (10.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eobesity\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e61 (2.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e78 (1.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eLearning of specialized movement, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1865 (70.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2667 (62.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e782 (29.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1598 (37.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRegular strength training, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1819 (68.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2512 (58.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e828 (31.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1753 (41.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMost frequent daily exercise time, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eearly morning\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e504 (19)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e784 (18.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003emorning\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e237 (9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e735 (17.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eafternoon\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e235 (8.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e973 (22.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eevening\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1402 (53)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1428 (33.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eno regularity\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e269 (10.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e345 (8.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePre-exercise warm-up, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e295 (11.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e216 (5.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e510 (19.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e753 (17.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003esometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e643 (24.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1232 (28.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e619 (23.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1224 (28.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ealways\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e580 (21.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e840 (19.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePost-exercise relaxation, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e214 (8.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e186 (4.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e463 (17.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e724 (17)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003esometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e621 (23.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1189 (27.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e698 (26.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1351 (31.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ealways\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e651 (24.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e815 (19.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eUse of specialized athletic footwear, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e279 (10.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e322 (7.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e318 (12)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e562 (13.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003esometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e522 (19.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e904 (21.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e815 (30.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1387 (32.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ealways\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e713 (26.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1090 (25.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eExercise venue type, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.017\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enon-specialized\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1599 (60.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2451 (57.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003especialized\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1048 (39.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1814 (42.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eInsufficient energy to complete daily tasks, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e894 (33.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1103 (25.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1075 (40.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1618 (37.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003esometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e496 (18.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1234 (28.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eoften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e182 (6.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e310 (7.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eFatigue or illness status, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eno\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2203 (83.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2657 (62.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eyes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e258 (9.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1244 (29.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enot sure\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e186 (7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e364 (8.5)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSleep quality, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003epoor\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e309 (11.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e779 (18.3)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eokay\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e996 (37.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1876 (44)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ebetter\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e864 (32.6)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1211 (28.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003every good\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e478 (18.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e399 (9.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAwareness of sports injury risks, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.442\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003enone\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e59 (2.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e118 (2.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ea little\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e558 (21.1)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e860 (20.2)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003esome\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1344 (50.8)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2193 (51.4)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003efully understand\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e686 (25.9)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1094 (25.7)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cstrong\u003eLogistic regression analysis of sports injuries\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDue to the large sample size, this study included all potential variables in a multivariate logistic regression analysis. The model showed that age grouping, body mass index, the most frequent daily exercise time, learning of specialized movement, insufficient energy to do things, fatigue or illness status, quality of sleep, and knowing the risk of sports injuries were all correlates of sports injuries (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), as shown in Table\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e\n\u003cdiv class=\"gridtable\"\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"char\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003cdiv class=\"colspec\" align=\"left\"\u003e\u0026nbsp;\u003c/div\u003e\n\u003ctable id=\"Tab2\" border=\"1\"\u003e\u003ccaption\u003e\n\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\n\u003cdiv class=\"CaptionContent\"\u003e\n\u003cp\u003eLogistic regression analysis of sports injuries\u003c/p\u003e\n\u003c/div\u003e\n\u003c/caption\u003e\n\u003cthead\u003e\n\u003ctr\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eVariables\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003eWald \u0026chi;\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003eOR\u003c/em\u003e (95% \u003cem\u003eCI\u003c/em\u003e)\u003c/p\u003e\n\u003c/th\u003e\n\u003cth align=\"left\"\u003e\n\u003cp\u003e\u003cem\u003ep\u003c/em\u003e\u003c/p\u003e\n\u003c/th\u003e\n\u003c/tr\u003e\n\u003c/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAge (years), n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e18\u0026ndash;29\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e30\u0026ndash;39\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-4.612\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.648 (0.538, 0.778)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e40\u0026ndash;49\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-6.852\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.458 (0.366, 0.572)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026ge;\u0026thinsp;50\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-8.530\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.258 (0.189, 0.352)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eBMI, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eUnderweight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNormal weight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-0.069\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.993 (0.820, 1.202)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.945\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eOverweight\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-2.870\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.693 (0.539, 0.890)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.004\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eObesity\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.641\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.676 (0.423, 1.081)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.101\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eMost frequent daily exercise time, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ee\u003c/span\u003early morning\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003em\u003c/span\u003eorning\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e4.846\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.803 (1.422, 2.291)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ea\u003c/span\u003efternoon\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e6.438\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2.135 (1.697, 2.693)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ee\u003c/span\u003evening\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-5.668\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.600 (0.502, 0.715)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eo regularity\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.601\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.814 (0.633, 1.047)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.109\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eLearning of specialized movement, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e3.110\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.294 (1.100, 1.523)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.002\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eRegular strength training, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eYes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.653\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.057 (0.896, 1.247)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.514\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePre-exercise warm-up, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2.693\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.541 (1.126, 2.113)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.007\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003es\u003c/span\u003eometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e3.866\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.891 (1.370, 2.615)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e3.548\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.845 (1.317, 2.592)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ea\u003c/span\u003elways\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e2.183\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.492 (1.043, 2.140)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.029\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003ePost-exercise relaxation, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e1.176\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.232 (0.870, 1.743)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.240\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003es\u003c/span\u003eometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.728\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.143 (0.797, 1.636)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.467\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.752\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.153 (0.796, 1.668)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.452\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ea\u003c/span\u003elways\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.586\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.730 (0.495, 1.077)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.113\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eUse of specialized athletic footwear, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e0.189\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.029 (0.768, 1.377)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.850\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003es\u003c/span\u003eometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.410\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.821 (0.624, 1.079)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.159\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.304\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.838 (0.642, 1.092)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.192\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ea\u003c/span\u003elways\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.239\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.841 (0.639, 1.105)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.215\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eExercise venue type, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eon-specialized\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003es\u003c/span\u003epecialized\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.454\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.903 (0.788, 1.036)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.146\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd colspan=\"2\" align=\"left\"\u003e\n\u003cp\u003eInsufficient energy to complete daily tasks, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eNever\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eccasionally\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-3.867\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.725 (0.615, 0.853)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003es\u003c/span\u003eometimes\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.135\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.893 (0.734, 1.086)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.257\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003eften\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-5.448\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.437 (0.325, 0.589)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eFatigue or illness status, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eo\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ey\u003c/span\u003ees\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e12.431\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e3.624 (2.965, 4.451)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eot sure\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e5.648\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e2.023 (1.588, 2.590)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eSleep quality, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ep\u003c/span\u003eoor\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1.000\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eo\u003c/span\u003ekay\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-0.942\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.904 (0.732, 1.114)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.346\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003eb\u003c/span\u003eetter\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-2.488\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.752 (0.601, 0.941)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.013\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ev\u003c/span\u003eery good\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-6.167\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.434 (0.333, 0.565)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003eAwareness of sports injury risks, n(%)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003en\u003c/span\u003eone\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e1\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\u0026nbsp;\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ea\u003c/span\u003e little\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.961\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.640 (0.406, 0.994)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.050\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003es\u003c/span\u003eome\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-2.308\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.596 (0.381, 0.919)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.021\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e\u003cspan class=\"SmallCaps\"\u003ef\u003c/span\u003eully understand\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"char\" char=\".\"\u003e\n\u003cp\u003e-1.852\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.653 (0.413, 1.019)\u003c/p\u003e\n\u003c/td\u003e\n\u003ctd align=\"left\"\u003e\n\u003cp\u003e0.064\u003c/p\u003e\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cstrong\u003eBayesian networks\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study incorporated variables with statistically significant differences into the construction of BNs based on logistic regression. Additionally, owing to the large sample size, the remaining variables were also included in the BN construction. The results indicated that the BNs comprised 14 nodes and 25 directed edges. Age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were direct correlates of sports injury occurrence. By contrast, exercise venue type and having learned specialized movements could be indirectly correlated with sports injury occurrence through the most frequent daily exercise time; regular strength training could be indirectly correlated with sports injury occurrence through age, the most frequent daily exercise time, and fatigue or illness status; and insufficient energy to complete daily tasks could be indirectly related to sports injuries through sleep quality and fatigue or illness status, as shown in Fig.\u0026nbsp;2.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe values in the nodes\u0026rsquo; boxes with matrix bars in the figure represent the prior probability of each node. For example, the value corresponding to the \u0026ldquo;sports injury occurrence\u0026rdquo; group is 61.2%, indicating that 61.2% of the total population has experienced sports injuries\u0026mdash;this is the node\u0026rsquo;s prior probability. The arrows in the figure represent dependencies between nodes[\u003cspan class=\"CitationRef\"\u003e29\u003c/span\u003e]. For instance, if \u0026ldquo;age\u0026rdquo; points to \u0026ldquo;sports injuries,\u0026rdquo; this signifies that age is the parent node of sports injuries, meaning age is directly related to exercise injury.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eBayesian Risk Inference\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBNs enable inference of unknown nodes from known nodes, thereby facilitating risk prediction of disease occurrence. Probabilistic models can quantitatively analyze how relevant factors influence sports injury occurrence by calculating conditional probabilities, allowing the impact of each node in the BNs on sports injury risk to be inferred via Bayesian reasoning[\u003cspan class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eBNs revealed that if a regular-exercising adult female was in a state of fatigue or illness, her risk of sports injury increased from 0.612 to 0.793, i.e., P(Sports Injury | Fatigue or Illness Status)\u0026thinsp;=\u0026thinsp;0.793 (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e). If her sleep quality was also poor, the risk further increased to 0.854, i.e., P(Sports Injury | Fatigue or Illness Status, Poor Sleep Quality)\u0026thinsp;=\u0026thinsp;0.854 (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e4\u003c/span\u003e). Among young individuals (18\u0026ndash;29 years old) with both fatigue/illness and poor sleep quality, the injury risk rose to 0.915, i.e., P(Sports Injury | Fatigue or Illness Status, Poor Sleep Quality, Young Age)\u0026thinsp;=\u0026thinsp;0.915 (Fig.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e). Conversely, if such an individual habitually exercised in the morning, the risk escalated to 0.962, i.e., P(Sports Injury | Fatigue or Illness Status, Poor Sleep Quality, Young Age, Morning Exercise Habit)\u0026thinsp;=\u0026thinsp;0.962 (Fig.\u0026nbsp;6).\u003c/p\u003e\n\u003cp\u003eIf regular-exercising adult females experienced fatigue or illness, their risk of sports injury increased to 0.793.\u003c/p\u003e\n\u003cp\u003eIf an individual experienced both fatigue/illness and poor sleep quality, their risk of sports injury rose to 0.854.\u003c/p\u003e\n\u003cp\u003eIf an individual with fatigue or illness and poor sleep quality was also young (aged 18\u0026ndash;29 years), their risk of sports injury rose to 0.915.\u003c/p\u003e\n\u003cp\u003eIf an individual with fatigue/illness, poor sleep quality, and young age (18\u0026ndash;29 years) was also accustomed to morning exercise, their risk of sports injury rose to 0.962.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we comprehensively explored the associations between sports injuries in Chinese adult women who engage in regular exercise by using both logistic regression and Bayesian networks (BNs).The results of the logistic regression demonstrated significant associations between sports injuries and variables such as age, body mass index (BMI), learning of specific movements, the most frequent daily exercise time, pre - exercise warm - up, fatigue or illness status, insufficient energy to complete daily tasks, sleep quality, and awareness of sports injury risks, thus identifying the main correlates. In contrast, BNs further revealed complex probabilistic dependency paths among variables, constructing a network structure with 14 nodes and 25 directed edges and clearly depicting the interconnections between direct and indirect risk factors. Through BN inference, we found that the superposition of multiple factors can significantly increase the risk of sports injury, which reflects the unique advantages of BNs in structural modeling and risk prediction. These findings provide a theoretical basis for precise prevention and intervention in the female sports population.\u003c/p\u003e\n\u003cp\u003eAs age increases, the injury risk shows a gradual decrease. The middle - aged and elderly groups have a significantly lower risk compared to young adults. This may be related to their relatively moderate exercise intensity, more conservative movement choices and stronger risk - avoidance awareness[\u003cspan class=\"CitationRef\"\u003e30\u003c/span\u003e]. In terms of body mass index (BMI), overweight individuals have a significantly lower injury risk than those with low body weight, indicating that moderate fat and muscle reserves may provide better joint cushioning and energy storage. On the contrary, low - body - weight individuals often have lower bone mass and insufficient muscle support, which increases their susceptibility to injury[\u003cspan class=\"CitationRef\"\u003e31\u003c/span\u003e, \u003cspan class=\"CitationRef\"\u003e32\u003c/span\u003e].\u003c/p\u003e\n\u003cp\u003eRegarding exercise timing, compared with early morning exercise, afternoon and morning exercise are associated with a higher injury risk, possibly because the exercise intensity is higher during these periods. In contrast, people who exercise in the evening more often choose low - demand activities such as jogging or brisk walking[\u003cspan class=\"CitationRef\"\u003e33\u003c/span\u003e]. Paradoxically, individuals who have learned specialized movements face a higher injury risk, probably because their participation in complex or difficult techniques increases the probability of making technical errors. A higher frequency of pre - exercise warm - up is also associated with an increased risk, perhaps indicating that those who warm up frequently engage in more sports (higher risk exposure) or use inappropriate warm - up techniques.\u003c/p\u003e\n\u003cp\u003eIn terms of physical state and subjective perception, insufficient energy to complete daily tasks was associated with a lower injury risk, suggesting that individuals may actively reduce exercise when unwell[\u003cspan class=\"CitationRef\"\u003e34\u003c/span\u003e]. In contrast, exercising while fatigued or ill substantially increased the risk[\u003cspan class=\"CitationRef\"\u003e35\u003c/span\u003e], highlighting the need to regulate exercise behavior during poor health. Good sleep quality significantly reduced injury risk[\u003cspan class=\"CitationRef\"\u003e36\u003c/span\u003e], emphasizing the role of recovery mechanisms. Cognitively, partial awareness of sports - injury risks was correlated with a lower injury incidence[\u003cspan class=\"CitationRef\"\u003e37\u003c/span\u003e], indicating that risk awareness positively affects behavioral norms and prevention strategies. These findings reveal the multifactorial mechanisms of female sports injuries across physiological, behavioral, and cognitive dimensions, providing a foundation for targeted interventions.\u003c/p\u003e\n\u003cp\u003eBayesian networks (BNs) revealed that, in addition to direct risk factors, multiple indirect correlates influence sports injury through mediating pathways, deepening the systematic understanding of injury mechanisms. The results showed that age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were direct determinants of sports injury, together forming the core nodes of injury risk. Notably, variables such as exercise venue type and learning of specialized movement did not directly contribute to injury outcomes but influenced injury risk through the mediating variable of exercise duration. This implies that poor exercise environments and technical complexity may indirectly increase injury incidence by prolonging or intensifying exercise sessions.\u003c/p\u003e\n\u003cp\u003eAdditionally, although regular strength training was not a direct risk factor, it had multi - path linkages with injury risk through age, the most frequent daily exercise time, and physical status (such as fatigue or illness status). This implies that high - intensity training may be a predisposing factor for sports injuries in certain populations or physiological states. Moreover, while insufficient energy to complete daily tasks did not directly correlate with injury, it affected injury risk through \u0026ldquo;sleep quality\u0026rdquo; and \u0026ldquo;fatigue or illness status,\u0026rdquo; highlighting the crucial role of physical condition and recovery mechanisms in the occurrence of injury. These findings stress that sports injury is not caused by single variables but results from multifactorial processes mediated by causal chains, thus demonstrating the unique value of Bayesian Networks (BNs) in modeling complex health - behavior systems. By revealing both direct associations and indirect dependency paths, BNs offer a comprehensive framework for identifying high - risk profiles and designing tiered intervention strategies for female exercisers.\u003c/p\u003e\n\u003cp\u003eCompared to logistic regression models, Bayesian Networks (BNs) have distinct advantages in modeling variable relationships, especially in three key aspects.Firstly, BNs can identify both direct and indirect correlations[\u003cspan class=\"CitationRef\"\u003e38\u003c/span\u003e]. For example, in the study of sports injury, age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were direct correlates. Meanwhile, variables such as exercise venue type, learning of specialized movement, regular strength training, and energy levels influenced injury outcomes indirectly through mediating pathways. This pathway structure reveals multilevel causal chains that link behavioral, environmental, and physiological factors - complex interactions that regression analysis alone cannot fully capture. Second, BNs visualize variable linkages and conditional dependencies[\u003cspan class=\"CitationRef\"\u003e39\u003c/span\u003e]. For instance, regular strength training indirectly affects injury risk through age, the most frequent daily exercise time, and physical status (such as fatigue or illness status). This highlights the need for intervention strategies that take into account synergistic effects rather than isolating risk factors. This networked structure reflects how injury risk spreads in real - world behavioral systems, enhancing the model's explanatory power for complex interactions. Thirdly, BNs have a unique advantage in conditional - probability - based inference: they can dynamically estimate injury probability based on known individual characteristics, enabling personalized, context - specific risk prediction\u003csup\u003e38\u003c/sup\u003e. This ability is of great value for practical health management, facilitating the development of targeted preventive measures. For example, the incremental risk increases shown in Figs.\u0026nbsp;\u003cspan class=\"InternalRef\"\u003e3\u003c/span\u003e\u0026ndash;6 illustrate how the combination of fatigue, poor sleep, youth, and morning exercise habits amplifies injury probability in a predictable, layered manner. Thus, Bayesian Networks (BNs) outperform traditional regression methods in structural modeling. They can disentangle direct - indirect relationships, visualize dependency networks and enable dynamic risk inference. These features lay a solid theoretical and technical foundation for multi - dimensional, real - time injury risk assessment among female exercisers, providing actionable insights for precision public health interventions.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStrengths and limitations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study has multiple advantages. First, a large sample size contributes to statistical stability, providing a solid foundation for model construction. Second, this study is the first to apply Bayesian Networks (BNs) to explore sports injury correlates in Chinese adult women who exercise regularly. It fills a gap in quantitative modeling research for this population and promotes the shift from traditional descriptive analyses to intelligent inference models in injury prevention.\u003c/p\u003e\n\u003cp\u003eHowever, the study also has limitations. First, the questionnaire - based design is prone to recall bias and potential ambiguity in response options, which may affect the accuracy of certain variables. Future research could enhance data quality by integrating sports recording devices (such as accelerometers, heart rate monitors) with open - ended questions to capture more detailed behavioral information. Second, the cross - sectional design does not allow for definitive inference of causal temporal sequences. Prospective cohort studies are required to validate the hypothesized causal chains identified by the BNs. Third, the current BN model demands that variables be discretized into categorical types, which may potentially limit the use of continuous data (for example, the most frequent daily exercise time and intensity). Future versions could explore hybrid BNs or use nested discretization and sensitivity analysis to maximize the retention of information from continuous variables.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eOverall, this study systematically identified and analyzed multi - level factors affecting sports injuries among Chinese adult female exercisers and constructed a novel Bayesian Networks (BNs) model that incorporates both direct and indirect risk pathways. This work offers a new framework for individualized risk prediction and comprehensive intervention strategies. Besides enriching the theoretical basis of women's sports health research, the findings provide a scientific foundation for optimizing sports population management. In the future, longitudinal research designs and model refinements (such as hybrid BN development) will be crucial for translating risk identification into precision prevention, ultimately creating a safer and more sustainable exercise environment for women.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003cp\u003eAll participants provided informed consent, and the study was approved by the Ethics Committee of Beijing Sport University. This study performed on human data or materials complied with the Declaration of Helsinki.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003cp\u003eNot applicable.\u003c/p\u003e\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e\u003cp\u003eThis work was supported by a National Key Research and Development Program of China\u0026ndash;Key Factors and Fitness Guidance Programs to Improve the Effectiveness of Exercise and Fitness (Project No. 2018YFC2000603)\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eHe Xinhao drafted the manuscript. Song Wenzhu, Ran Ruimeng, and Li Xuemei helped with data analysis and polished the manuscript. Song Wenzhu and Li Xuemei provided valuable advice on statistical methods and were responsible for the conception and design of the research. All authors contributed to the article and approved the final version of this manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e\u003cp\u003eNot Applicable.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eThe National Center for National Physical Fitness Monitoring released the. 2020 Survey Bulletin on the Status of National Fitness Activity_National Sports Administration. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.sport.gov.cn/n315/n329/c24335053/content.html\u003c/span\u003e\u003cspan address=\"https://www.sport.gov.cn/n315/n329/c24335053/content.html\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Accessed 26 Feb 2025.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMao Y, Zhu Y, Sun F, Jia C, Liu B. An analysis of women\u0026rsquo;s fitness demands and their influencing factors in urban china. Healthc (basel Switz). 2022;10:187.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003evan Mechelen W, Hlobil H, Kemper HC. Incidence, severity, aetiology and prevention of sports injuries. A review of concepts. Sports Med (Auckl NZ). 1992;14:82\u0026ndash;99.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKelly S, Pollock N, Polglass G, Clarsen B. Injury and illness in elite athletics: a prospective cohort study over three seasons. Int J Sports Phys Ther 17:420\u0026ndash;33.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFukuda N, Hangai M, Hashimoto R, Nishida Y, Mizutani Y, Okuwaki T et al. Injury characteristics among japanese international athletes: report on the pre-competition medical check-up data of the japanese olympic committee. Cureus 16:e72869.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eArendt E, Dick R. Knee injury patterns among men and women in collegiate basketball and soccer. NCAA data and review of literature. Am J Sports Med. 1995;23:694\u0026ndash;701.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eToth AP, Cordasco FA. Anterior cruciate ligament injuries in the female athlete. j gend-specif med: JGSM: off j Partnersh Women. \u0026rsquo;s Health Columbia. 2001;4:25\u0026ndash;34.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMart\u0026iacute;nez-Fortuny N, Alonso-Calvete A, Da Cu\u0026ntilde;a-Carrera I, Abalo-N\u0026uacute;\u0026ntilde;ez R. Menstrual cycle and sport injuries: a systematic review. Int J Environ Res Public Health. 2023;20:3264.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRuffault A, Sorg M, Martin S, Hanon C, Jacquet L, Verhagen E, et al. Determinants of the adoption of injury risk reduction programmes in athletics (track and field): an online survey of 7715 french athletes. Br J Sports Med. 2022;56:499\u0026ndash;505.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eWillems TM, Ley C, Goetghebeur E, Theisen D, Malisoux L. Motion-control shoes reduce the risk of pronation-related pathologies in recreational runners: a secondary analysis of a randomized controlled trial. J Orthop Sports Phys Ther. 2021;51:135\u0026ndash;43.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTranaeus U, Martin S, Ivarsson A. Psychosocial risk factors for overuse injuries in competitive athletes: a mixed-studies systematic review. Sports Med (auckl N.z,). 2022;52:773\u0026ndash;88.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKvist J, Silbernagel KG. Fear of movement and reinjury in sports medicine: relevance for rehabilitation and return to sport. Phys Ther. 2022;102:pzab272.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCrossley KM, Patterson BE, Culvenor AG, Bruder AM, Mosler AB, Mentiplay BF. Making football safer for women: a systematic review and meta-analysis of injury prevention programmes in 11 773 female football (soccer) players. Br J Sports Med. 2020;54:1089\u0026ndash;98.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTruong LK, Mosewich AD, Holt CJ, Le CY, Miciak M, Whittaker JL. Psychological, social and contextual factors across recovery stages following a sport-related knee injury: a scoping review. Br J Sports Med. 2020;54:1149\u0026ndash;56.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDing L, Brewer BW, Mackey M, Cai H, Zhang J, Song Y, et al. Factors associated with school sports injury among elementary and middle school students in shanghai, china. Int J Environ Res Public Health. 2022;19:6406.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFranettovich Smith MM, Mendis MD, Parker A, Grantham B, Stewart S, Hides J. Injury surveillance of an australian community netball club. Phys Ther Sport: Off J Assoc Chart Physiother Sports Med. 2020;44:41\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSong W, Gong H, Wang Q, Zhang L, Qiu L, Hu X, et al. Using bayesian networks with max-min hill-climbing algorithm to detect factors related to multimorbidity. Front Cardiovasc Med. 2022;9:984883.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBriganti G, Scutari M, McNally RJ. A tutorial on bayesian networks for psychopathology researchers. Psychol Methods. 2023;28:947\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAngelopoulos N, Chatzipli A, Nangalia J, Maura F, Campbell PJ. Bayesian networks elucidate complex genomic landscapes in cancer. Commun Biol. 2022;5:306.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOrdovas JM, Rios-Insua D, Santos-Lozano A, Lucia A, Torres A, Kosgodagan A, et al. A bayesian network model for predicting cardiovascular risk. Comput Methods Programs Biomed. 2023;231:107405.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYung KKY, Wu PPY, aus der F\u0026uuml;nten K, Hecksteden A, Meyer T. Using a bayesian network to classify time to return to sport based on football injury epidemiological data. PLoS ONE. 2025;20:e0314184.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSong W, Qiu L, Qing J, Zhi W, Zha Z, Hu X, et al. Using bayesian network model with MMHC algorithm to detect risk factors for stroke. Math Biosci Eng: MBE. 2022;19:13660\u0026ndash;74.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMa SX, Dhanaliwala AH, Rudie JD, Rauschecker AM, Roberts-Wolfe D, Haddawy P, et al. Bayesian networks in radiology. Radiol: Artif Intell. 2023;5:e210187.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePan X-F, Wang L, Pan A. Epidemiology and determinants of obesity in China. Lancet Diabetes Endocrinol. 2021;9:373\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCampos LMD. Independency relationships and learning algorithms for singly connected networks. J Exp Theor Artif Intell. 1998. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1080/095281398146743\u003c/span\u003e\u003cspan address=\"10.1080/095281398146743\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHeckerman D, Geiger D, Chickering DM. Learning bayesian networks: the combination of knowledge and statistical data. Mach Learn. 1995;20:197\u0026ndash;243.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTsamardinos I, Brown LE, Aliferis CF. The max-min hill-climbing bayesian network structure learning algorithm. Mach Learn. 2006;65:31\u0026ndash;78.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eQuan D, Ren J, Ren H, Linghu L, Wang X, Li M, et al. Exploring influencing factors of chronic obstructive pulmonary disease based on elastic net and bayesian network. Sci Rep. 2022;12:7563.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eQuan D, Ren J, Ren H, Linghu L, Wang X, Li M, et al. Exploring influencing factors of chronic obstructive pulmonary disease based on elastic net and bayesian network. Sci Rep. 2022;12:7563.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDavison RCR, Cowan DT. Ageing, sport and physical activity participation in Scotland. Front Sports Act Living. 2023;5:1213924.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCederholm T, Jensen GL, Correia MITD, Gonzalez MC, Fukushima R, Pisprasert V, et al. The GLIM consensus approach to diagnosis of malnutrition: a 5-year update. Clin Nutr (edinb Scotl). 2025;49:11\u0026ndash;20.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHan S, Park J, Jang H, Nah S, Boo J, Han K, et al. Incidence of hip fracture in underweight individuals: a nationwide population-based cohort study in korea. J Cachexia Sarcopenia Muscle. 2022;13:2473\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSu Y, Li H, Jiang S, Li Y, Li Y, Zhang G. The relationship between nighttime exercise and problematic smartphone use before sleep and associated health issues: a cross-sectional study. BMC Public Health. 2024;24:590.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eDe Ste Croix MBA, Hughes JD, Lloyd RS, Oliver JL, Read PJ. Leg stiffness in female soccer players: intersession reliability and the fatiguing effects of soccer-specific exercise. J Strength Cond Res. 2017;31:3052\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePires FO, Silva-J\u0026uacute;nior FL, Brietzke C, Franco-Alvarenga PE, Pinheiro FA, de Fran\u0026ccedil;a NM, et al. Mental Fatigue Alters Cortical Activation and Psychological Responses, Impairing Performance in a Distance-Based Cycling Trial. Front Physiol. 2018;9:227.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuang K, Ihm J. Sleep and injury risk. Curr Sports Med Rep. 2021;20:286\u0026ndash;90.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eEdouard P, Sorg M, Martin S, Verhagen E, Ruffault A. Athletes who have already experienced an injury are more prone to adhere to an injury risk reduction approach than those who do not: an online survey of 7870 french athletics (track and field) athletes. BMJ Open Sport Exerc Med. 2024;10:e001768.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYung KKY, Wu PPY, aus der F\u0026uuml;nten K, Hecksteden A, Meyer T. Using a bayesian network to classify time to return to sport based on football injury epidemiological data. PLoS ONE. 2025;20:e0314184.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLalika L, Kitali AE, Haule HJ, Kidando E, Sando T, Alluri P. What are the leading causes of fatal and severe injury crashes involving older pedestrian? Evidence from bayesian network model. J Saf Res. 2022;80:281\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-sports-science-medicine-and-rehabilitation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ssmr","sideBox":"Learn more about [BMC Sports Science, Medicine and Rehabilitation](http://bmcsportsscimedrehabil.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/ssmr/default.aspx","title":"BMC Sports Science, Medicine and Rehabilitation","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Exercise injury, adult women, bayesian networks, influencing factors","lastPublishedDoi":"10.21203/rs.3.rs-7081577/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7081577/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cb\u003eObjective\u003c/b\u003e Given the influence of women's unique joint structures and hormonal levels, sports injuries among females have become a focus in sports research. This study aimed to use Logistic regression and Bayesian networks (BNs) models to explore factors associated with sports injuries in Chinese adult females who exercise regularly.\u003c/p\u003e\u003cp\u003e\u003cb\u003eMethods\u003c/b\u003e This was a cross - sectional study. From October to November 2021, data on sports - injury - related factors were collected through online questionnaires from adult females aged 18 and above who exercised regularly in 336 cities across 34 provinces nationwide. Logistic regression and BNs models were used to explore factors associated with sports injuries in Chinese adult females with regular exercise.\u003c/p\u003e\u003cp\u003e\u003cb\u003eResults\u003c/b\u003e A total of 6,912 valid questionnaires were included, with a median age of 34.00 (31.00\u0026ndash;39.00) years. Among the participants, 4,265 (61.70%) had experienced sports injuries. Logistic regression indicated that age grouping, body mass index (BMI), the most frequent daily exercise time, learning of specialized movement, insufficient energy to complete daily tasks, fatigue or illness status, sleep quality, and awareness of sports injury risks were all risk factors for sports injuries. BNs revealed that age, sleep quality, the most frequent daily exercise time, and fatigue or illness status were directly correlated with sports injuries. Moreover, exercise venue type and learning of specialized movement were indirectly associated with sports injuries through the mediating variable of the most frequent daily exercise time.\u003c/p\u003e\u003cp\u003e\u003cb\u003eConclusion\u003c/b\u003e BNs can identify both direct and indirect correlates of sports injuries, and Bayesian risk inference enables risk prediction for sports injuries. BNs serve as a complementary method to logistic regression, providing deeper insights into complex risk factor interactions.\u003c/p\u003e","manuscriptTitle":"Using Bayesian Networks to Explore Risk Factors for Sports Injuries in Chinese Adult Women Who Exercise Regularly: A Nationwide Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-19 12:28:37","doi":"10.21203/rs.3.rs-7081577/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-08-24T20:39:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-24T08:40:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34290720083002439214826640911545268061","date":"2025-08-24T07:41:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"228660090850615848946652141184315006983","date":"2025-08-12T16:22:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-11T14:27:56+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-06T16:43:45+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-21T13:42:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-21T10:29:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Sports Science, Medicine and Rehabilitation","date":"2025-07-21T09:56:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-sports-science-medicine-and-rehabilitation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ssmr","sideBox":"Learn more about [BMC Sports Science, Medicine and Rehabilitation](http://bmcsportsscimedrehabil.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/ssmr/default.aspx","title":"BMC Sports Science, Medicine and Rehabilitation","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0a0d4d11-bbe1-4362-8582-757930ee44be","owner":[],"postedDate":"August 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-08-19T12:28:37+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-19 12:28:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7081577","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7081577","identity":"rs-7081577","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}