Bayesian networks to identify statistical dependencies. A case study of Spanish university students' habits

Identification and prediction of frailty among community-dwelling older Japanese adults based on Bayesian network analysis: a cross-sectional and longitudinal study

BACKGROUND

Frailty is a multifactorial syndrome; through this study, we aimed to investigate the physiological, psychological, and social factors associated with frailty and frailty worsening in community-dwelling older adults.

METHODS

We conducted a cross-sectional and longitudinal study using data from the "Community Empowerment and Well-Being and Healthy Long-term Care: Evidence from a Cohort Study (CEC)," which focuses on community dwellers aged 65 and above in Japan. The sample of the cross-sectional study was drawn from a CEC study conducted in 2014 with a total of 673 participants. After excluding those who were frail during the baseline assessment (2014) and at the 3-year follow-up (2017), the study included 373 participants. Frailty assessment was extracted from the Kihon Checklist, while social relationships were assessed using the Social Interaction Index (ISI). Variable selection was performed using Least Absolute Shrinkage and Selection Operator (LASSO) regression and their predictive abilities were tested. Factors associated with frailty status and worsening were identified through the Maximum-min Hillclimb algorithm applied to Bayesian networks (BNs).

RESULTS

At baseline, 14.1% (95 out of 673) participants were frail, and 24.1% (90 out of 373) participants experienced frailty worsening at the 3-years follow up. LASSO regression identified key variables for frailty. For frailty identification (cross-sectional), the LASSO model's AUC was 0.943 (95%CI 0.913-0.974), indicating good discrimination, with Hosmer-Lemeshow (H-L) test p = 0.395. For frailty worsening (longitudinal), the LASSO model's AUC was 0.722 (95%CI 0.656-0.788), indicating moderate discrimination, with H-L test p = 0.26. The BNs found that age, multimorbidity, function status, and social relationships were parent nodes directly related to frailty. It revealed an 85% probability of frailty in individuals aged 75 or older with physical dysfunction, polypharmacy, and low ISI scores; however, if their social relationships and polypharmacy status improve, the probability reduces to 50.0%. In the longitudinal-level frailty worsening model, a 75% probability of frailty worsening in individuals aged 75 or older with declined physical function and ISI scores was noted; however, if physical function and ISI improve, the probability decreases to 25.0%.

CONCLUSION

Frailty and its progression are prevalent among community-dwelling older adults and are influenced by various factors, including age, physical function, and social relationships. BNs facilitate the identification of interrelationships among these variables, quantify the influence of key factors. However, further research is required to validate the proposed model.

The identification and prediction of frailty based on Bayesian network analysis in a community-dwelling older population

Background

We have witnessed frailty, which characterized by a decline in physiological reserves, become a major public health issue in older adults. Understanding the influential factors associated with frailty may help prevent or if possible reverse frailty. The present study aimed to investigate factors associated with frailty status and frailty transition in a community-dwelling older population.

Methods

A prospective cohort study on community-dwelling subjects aged ≥ 60 years was conducted, which was registered beforehand (ChiCTR 2,000,032,949). Participants who had completed two visits during 2020–2021 were included. Frailty status was evaluated using the Fried frailty phenotype. The least absolute shrinkage and selection operator (LASSO) regression was applied for variable selection. Bayesian network analysis with the max-min hill-climbing (MMHC) algorithm was used to identify factors related to frailty status and frailty transition.

Results

Of 1,981 subjects at baseline, 1,040 (52.5%) and 165 (8.33%) were classified as prefrailty and frailty. After one year, improved, stable, and worsening frailty status was observed in 460 (35.6%), 526 (40.7%), and 306 (23.7%) subjects, respectively. Based on the variables screened by LASSO regression, the Bayesian network structure suggested that age, nutritional status, instrumental activities of daily living (IADL), balance capacity, and social support were directly related to frailty status. The probability of developing frailty is 14.4% in an individual aged ≥ 71 years, which increases to 20.2% and 53.2% if the individual has balance impairment alone, or combined with IADL disability and malnutrition. At a longitudinal level, ADL/IADL decline was a direct predictor of worsening in frailty state, which further increased the risk of hospitalization. Low high-density lipoprotein cholesterol (HDL-C) and diastolic blood pressure (DBP) levels were related to malnutrition, and further had impacts on ADL/IADL decline, and ultimately led to the worsening of the frailty state. Knowing the status of any one or more of these factors can be used to infer the risk of frailty based on conditional probabilities.

Conclusion

Older age, malnutrition, IADL disability, and balance impairment are important factors for identifying frailty. Malnutrition and ADL/IADL decline further predict worsening of the frailty state.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12877-022-03520-7.

Can we speak of a negative psychological tetrad in sports? A probabilistic Bayesian study on competitive sailing

Introduction

Researchers display an interest in studying aspects like the mental health of high-performance athletes; the dark side of sport, or the earliest attempts to study the so-called dark triad of personality in both initiation and high-performance athletes. Therefore, the objective of this paper is to determine the possible existence and magnitude of negative psychological aspects within a population of competition sailors and from a probabilistic point of view, using Bayesian Network analysis.

Methods

The study was carried out on 235 semi-professional sailors of the 49er Class, aged between 16 and 52 years (M = 24.66; SD = 8.03).

Results

The results show the existence of a Negative Tetrad—formed by achievement burnout, anxiety due to concentration disruption, amotivation and importance given to error—as a probabilistic product of the psychological variables studied: motivation, anxiety, burnout and fear of error.

Conclusion

These results, supported by Bayesian networks, show holistically the influence of the social context on the psychological and emotional well-being of the athlete during competition at sea.

It Is Not Just Stress: A Bayesian Approach to the Shape of the Negative Psychological Features Associated with Sport Injuries

The main objective of this study is to extend the stress and injury model of Andersen and Williams to other "negative" psychological variables, such as anxiety and depression, encompassed in the conceptual model of Olmedilla and García-Mas. The relationship is studied of this psychological macro-variable with two other variables related to sports injuries: the search for social support and the search for connections between risk and the environment of athletes. A combination of classic methods and probabilistic approaches through Bayesian networks is used. The study samples comprised 455 traditional and indoor football players (323 male and 132 female) of an average age of 21.66 years (±4.46). An ad hoc questionnaire was used for the corresponding sociodemographic data and data relating to injuries. The variables measured were the emotional states of: stress, depression and anxiety, the attitude towards risk-taking in different areas, and the evaluation of the perception of social support. The results indicate that the probabilistic analysis conducted gives a boost to the classic model focused on stress, as well as the conceptual planning derived from the Global Model of Sports Injuries (GMSI), supporting the possibility of extending the stress model to other variables, such as anxiety and depression ("negative" triad).

Studying Well and Performing Well: A Bayesian Analysis on Team and Individual Rowing Performance in Dual Career Athletes

On many occasions, the maximum result of a team does not equate to the total maximum individual effort of each athlete (social loafing). Athletes often combine their sports life with an academic one (Dual Career), prioritizing one over the over in a difficult balancing act. The aim of this research is to examine the existence of social loafing in a group of novice university rowers and the differences that exist according to sex, academic performance, and the kind of sport previously practiced (individual or team). Therefore, a study was conducted from a probabilistic perspective using the Bayesian Network analysis methodology. The results confirm the existence of the Ringelmann effect or social loafing. The Bayesian analysis let us confirm that having a good student who practices a team sport, even in the individual rowing concept, increases the probability of obtaining greater performance (higher number of strokes and more power in each one). Therefore, when rowing partnerships are formed, the occurrence probability chain is quickly simplified, along with values of the top and bottom variables. Finally, the instantiations undertaken on the bottom variable that appears to be common in the two BNs, the watt input, enhance the results obtained. In short, rowers who have a better academic record are more involved in team testing, so this characteristic is defining when it comes to achieving better performance in team testing.

An Interdisciplinary Examination of Stress and Injury Occurrence in Athletes

This paper adopts a novel, interdisciplinary approach to explore the relationship between stress-related psychosocial factors, physiological markers and occurrence of injury in athletes using a repeated measures prospective design. At four data collection time-points, across 1-year of a total 2-year data collection period, athletes completed measures of major life events, the reinforcement sensitivity theory personality questionnaire, muscle stiffness, heart rate variability and postural stability, and reported any injuries they had sustained since the last data collection. Two Bayesian networks were used to examine the relationships between variables and model the changes between data collection points in the study. Findings revealed muscle stiffness to have the strongest relationship with injury occurrence, with high levels of stiffness increasing the probability of sustaining an injury. Negative life events did not increase the probability of injury occurrence at any single time-point; however, when examining changes between time points, increases in negative life events did increase the probability of injury. In addition, the combination of increases in negative life events and muscle stiffness resulted in the greatest probability of sustaining an injury. Findings demonstrated the importance of both an interdisciplinary approach and a repeated measures design to furthering our understanding of the relationship between stress-related markers and injury occurrence.

Self-Determined Motivation and Competitive Anxiety in Athletes/Students: A Probabilistic Study Using Bayesian Networks

This study attempts to analyze the relationship between two key psychological variables associated with performance in sports - Self-Determined Motivation and Competitive Anxiety - through Bayesian Networks (BN) analysis. We analyzed 674 university students that are athletes from 44 universities that competed at the University Games in Mexico, with an average age of 21 years (SD = 2.07) and with a mean of 8.61 years' (SD = 5.15) experience in sports. Methods: Regarding the data analysis, firstly, classification using the CHAID algorithm was carried out to determine the dependence links between variables; Secondly, a BN was developed to reduce the uncertainty in the relationships between the two key psychological variables. The validation of the BN revealed AUC values ranging from 0.5 to 0.92. Subsequently, various instantiations were performed with hypothetical values applied to the "bottom" variables. Results showed two probability trees that have extrinsic motivation and amotivation at the top, while the anxiety/activation due to worries about performance was at the bottom of the probabilities. The instantiations carried out support the existence of these probabilistic relationships, demonstrating their scarce influence on anxiety about competition generated by the intrinsic motivation, and the complex probabilistic effect of introjected and identified regulation regarding the appearance of anxiety due to worry about performance.