An ensemble-based feature selection framework to select risk factors of childhood obesity for policy decision making.
Ontology highlight
ABSTRACT: Background
The increasing prevalence of childhood obesity makes it essential to study the risk factors with a sample representative of the population covering more health topics for better preventive policies and interventions. It is aimed to develop an ensemble feature selection framework for large-scale data to identify risk factors of childhood obesity with good interpretability and clinical relevance.Methods
We analyzed the data collected from 426,813 children under 18 during 2000-2019. A BMI above the 90th percentile for the children of the same age and gender was defined as overweight. An ensemble feature selection framework, Bagging-based Feature Selection framework integrating MapReduce (BFSMR), was proposed to identify risk factors. The framework comprises 5 models (filter with mutual information/SVM-RFE/Lasso/Ridge/Random Forest) from filter, wrapper, and embedded feature selection methods. Each feature selection model identified 10 variables based on variable importance. Considering accuracy, F-score, and model characteristics, the models were classified into 3 levels with different weights: Lasso/Ridge, Filter/SVM-RFE, and Random Forest. The voting strategy was applied to aggregate the selected features, with both feature weights and model weights taken into consideration. We compared our voting strategy with another two for selecting top-ranked features in terms of 6 dimensions of interpretability.Results
Our method performed the best to select the features with good interpretability and clinical relevance. The top 10 features selected by BFSMR are age, sex, birth year, breastfeeding type, smoking habit and diet-related knowledge of both children and mothers, exercise, and Mother's systolic blood pressure.Conclusion
Our framework provides a solution for identifying a diverse and interpretable feature set without model bias from large-scale data, which can help identify risk factors of childhood obesity and potentially some other diseases for future interventions or policies.
SUBMITTER: Shi X
PROVIDER: S-EPMC8293582 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:For decades now, normative theories of perceptual decisions, and their implementation as drift diffusion models, have driven and significantly improved our understanding of human and animal behaviour and the underlying neural processes. While similar processes seem to govern value-based decisions, we still lack the theoretical understanding of why this ought to be the case. Here, we show that, similar to perceptual decisions, drift diffusion models implement the optimal strategy for value-based decisions. Such optimal decisions require the models' decision boundaries to collapse over time, and to depend on the a priori knowledge about reward contingencies. Diffusion models only implement the optimal strategy under specific task assumptions, and cease to be optimal once we start relaxing these assumptions, by, for example, using non-linear utility functions. Our findings thus provide the much-needed theory for value-based decisions, explain the apparent similarity to perceptual decisions, and predict conditions under which this similarity should break down.
| S-EPMC4992126 | biostudies-literature
Project description:We have the capacity to follow arbitrary stimulus-response rules, meaning simple policies that guide our behavior. Rule identity is broadly encoded across decision-making circuits, but there are less data on how rules shape the computations that lead to choices. One idea is that rules could simplify these computations. When we follow a rule, there is no need to encode or compute information that is irrelevant to the current rule, which could reduce the metabolic or energetic demands of decision-making. However, it is not clear if the brain can actually take advantage of this computational simplicity. To test this idea, we recorded from neurons in 3 regions linked to decision-making, the orbitofrontal cortex (OFC), ventral striatum (VS), and dorsal striatum (DS), while macaques performed a rule-based decision-making task. Rule-based decisions were identified via modeling rules as the latent causes of decisions. This left us with a set of physically identical choices that maximized reward and information, but could not be explained by simple stimulus-response rules. Contrasting rule-based choices with these residual choices revealed that following rules (1) decreased the energetic cost of decision-making; and (2) expanded rule-relevant coding dimensions and compressed rule-irrelevant ones. Together, these results suggest that we use rules, in part, because they reduce the costs of decision-making through a distributed representational warping in decision-making circuits.
| S-EPMC7728226 | biostudies-literature
Project description:A growing number of parents delay vaccinations or are deciding not to vaccinate their children altogether. This increases the risk of contracting vaccine-preventable diseases and disrupting herd immunity, and also impairs the trust in the capacities of health care systems to protect people. Vaccine hesitancy is related to a range of both psychological and demographic determinants, such as attitudes toward vaccinations, social norms, and trust in science. Our aim is to understand those determinants in parents, because they are a special group in this issue-they act as proxy decision makers for their children, who are unable to decide for themselves. The fact that deciding to vaccinate is a socially forced choice that concerns a child's health makes vaccine-related decisions highly important and involving for parents. This high involvement might lead to parents overemphasizing the potential side effects that they know to be vaccine-related, and by amplifying those, parents are more focused on the potential outcomes of vaccine-related decisions, which can yield specific pattern of the outcome bias. We propose two related studies to investigate factors which promote vaccine hesitancy, protective factors that determine parental vaccination decisions, and outcome bias in parental vaccination intentions. We will explore demographic and psychological factors, and test parental involvement related to vaccine hesitancy using an online battery in a correlation panel design study. The second study is an experimental study, in which we will investigate the moderating role of parents' high involvement in the specific domain of vaccination decision making. We expect that higher involvement among parents, compared to non-parents, will shape the pattern of the proneness to outcome bias. The studies will be conducted across eight countries in Europe and Asia (Finland, Germany, Hong Kong, the Netherlands, Serbia, Slovenia, Spain, and the United Kingdom), rendering findings that will aid with understanding the underlying mechanisms of vaccine hesitancy and paving the way for developing interventions custom-made for parents.
| S-EPMC6008886 | biostudies-literature
Project description:ObjectiveFathers have increased their involvement in child caregiving; however, their changing role in childhood obesity is understudied. This study assessed the longitudinal association between changes in obesity among children aged 2 to 4 years and changes in fathers' involvement with raising children.MethodsLongitudinal data from the Early Childhood Longitudinal Study-Birth Cohort were used to conduct child fixed-effects linear and logistic regression analyses to assess the association between changes in childhood obesity-related outcomes (sugar-sweetened beverage consumption, screen time, BMI z score, overweight/obesity, obesity) and fathers' involvement with raising children (caregiving and influencing child-related decisions). Fixed-effects models control for all time-invariant characteristics. Analyses were controlled for time-varying confounders, including child age, maternal and paternal employment, and family poverty status.ResultsChildren whose fathers increased their frequency of taking children outside and involvement with physical childcare experienced a decrease in their odds of obesity from age 2 to age 4. Obesity-related outcomes were not associated with fathers' decision-making influence.ConclusionsIncreases in fathers' involvement with some aspects of caregiving may be associated with lower odds of childhood obesity. Encouraging fathers to increase their involvement with raising children and including fathers in childhood obesity prevention efforts may help reduce obesity risk among young children.
| S-EPMC5614806 | biostudies-literature
Project description:The ability to uniquely characterize individual subjects based on their functional connectome (FC) is a key requirement for progress toward precision psychiatry. FC fingerprinting is increasingly studied in the neuroimaging community for this purpose, where a variety of approaches have been developed for effective FC fingerprinting. Recent independent studies showed that fingerprinting accuracy suffers at large sample sizes and when coarser parcellations are used for computing the FC. Quantifying this problem and understanding the reasons these factors impact fingerprinting accuracy is crucial to develop more accurate fingerprinting methods for large sample sizes. Part of the challenge in fingerprinting is that FC captures both generic and subject-specific information. A systematic approach for identifying subject-specific FC information is crucial for making progress in addressing the fingerprinting problem. In this study, we addressed three gaps in our understanding of the FC fingerprinting problem. First, we studied the joint effect of sample size and parcellation granularity. Second, we explained the reason for reduced fingerprinting accuracy with increased sample size and reduced parcellation granularity. To this end, we used a clustering quality metric from the data mining community. Third, we developed a general feature selection framework for systematically identifying resting-state functional connectivity (RSFC) elements that capture information to uniquely identify subjects. In sum, we evaluated six different approaches from this framework by quantifying both subject-specific fingerprinting accuracy and the decrease in accuracy with an increase in sample size to identify which approach improved quality metrics the most.
| S-EPMC8288098 | biostudies-literature
Project description:Overweight/obese women are more likely to deliver newborns that also have a predisposition to store excessive amounts of fat since the early infancy period. Two evidence-based cycles are considered on the explanation of the maternal-child life-course approach for obesity prevention. The 'maternal' cycle indicates that pre-pregnancy overweight primiparous women are more likely to gain excessive weight during gestation and to retain excessive weight postpartum. The 'offspring' cycle indicates that newborns of pre-pregnancy overweight/obese women are more likely themselves to store excessive body fat starting very early on in life. The social ecological model (SEM) has been adopted as the framework needed to guide obesity prevention initiatives. The SEM considers the complex interrelationship among highly interconnected systems embedded within each other and having the individual on its inner most. Recommendations to women should include prevention of overweight/obesity prenatally, to attain adequate gestational weight and to lose the weight normally gained as part of the physiological response to pregnancy in the postpartum period. For the 'offspring' the aims should be to promote optimal breastfeeding and complementary feeding practices, and to foster physical activity and adequate dietary habits. Well-coordinated inter-sectorial national obesity prevention programs built upon the life-course framework foundation requires in-depth early life systems analyses driven by the SEM.
| S-EPMC4089584 | biostudies-other
Project description:The Centers for Disease Control and Prevention (CDC) Select Agent Program establishes a list of biological agents and toxins that potentially threaten public health and safety, the procedures governing the possession, utilization, and transfer of those agents, and training requirements for entities working with them. Every 2 years the Program reviews the select agent list, utilizing subject matter expert (SME) assessments to rank the agents. In this study, we explore the applicability of multi-criteria decision analysis (MCDA) techniques and logic tree analysis to support the CDC Select Agent Program biennial review process, applying the approach broadly to include non-select agents to evaluate its generality. We conducted a literature search for over 70 pathogens against 15 criteria for assessing public health and bioterrorism risk and documented the findings for archiving. The most prominent data gaps were found for aerosol stability and human infectious dose by inhalation and ingestion routes. Technical review of published data and associated scoring recommendations by pathogen-specific SMEs was found to be critical for accuracy, particularly for pathogens with very few known cases, or where proxy data (e.g., from animal models or similar organisms) were used to address data gaps. Analysis of results obtained from a two-dimensional plot of weighted scores for difficulty of attack (i.e., exposure and production criteria) vs. consequences of an attack (i.e., consequence and mitigation criteria) provided greater fidelity for understanding agent placement compared to a 1-to-n ranking and was used to define a region in the upper right-hand quadrant for identifying pathogens for consideration as select agents. A sensitivity analysis varied the numerical weights attributed to various properties of the pathogens to identify potential quantitative (x and y) thresholds for classifying select agents. The results indicate while there is some clustering of agent scores to suggest thresholds, there are still pathogens that score close to any threshold, suggesting that thresholding "by eye" may not be sufficient. The sensitivity analysis indicates quantitative thresholds are plausible, and there is good agreement of the analytical results with select agent designations. A second analytical approach that applied the data using a logic tree format to rule out pathogens for consideration as select agents arrived at similar conclusions.
| S-EPMC9204104 | biostudies-literature
Project description:BackgroundThe negative consequences of energy dense foods are well known, yet people increasingly make unhealthy food choices leading to obesity (i.e., risky decisions). The aims of this study were: [1] to compare performance in decision-making tasks under risk and under ambiguity between individuals with obesity, overweight and normal weight; [2] to examine the associations between body mass index (BMI) and decision-making, and the degree to which these associations are modulated by reward sensitivity.MethodsSeventy-nine adults were recruited and classified in three groups according to their BMI: obesity, overweight and normal-weight. Groups were similar in terms of age, education and socio-economic status, and were screened for comorbid medical and mental health conditions. Decision-making under risk was measured via the Wheel of Fortune Task (WoFT) and decision-making under ambiguity via the Iowa Gambling Task (IGT). Reward sensitivity was indicated by the Sensitivity to Punishment and Sensitivity to Reward Questionnaire (SPSRQ).ResultsIndividuals with obesity made riskier choices in the WoFT, specifically in choices with an expected value close to zero and in the propensity to risk index. No differences were found in IGT performance or SPSRQ scores. BMI was associated with risk-taking (WoFT performance), independently of reward sensitivity.ConclusionsObesity is linked to a propensity to make risky decisions in experimental conditions analogous to everyday food choices.
| S-EPMC4892558 | biostudies-literature
Project description:BackgroundEngaged scholarship includes the coproduction and use of research by partnerships that blend research, policy and/or practice perspectives. This way of doing research attempts to bridge-the-gap between knowledge and its application. Recent reviews have described practices that support engagement and involve the community in research and patients in healthcare but there is less known about how to engage individuals working to inform public policy.Aims and objectivesThe purpose of this research was to articulate the actions and context that support the coproduction and use of research to inform public policy decisions. The study focuses on partnerships between researchers and stakeholders working in public policy across different levels and sectors of government.MethodsA scoping review methodology was used. Relevant articles were identified from six electronic bibliographic databases of peer-reviewed literature.FindingsA total of 9904 articles were screened and 375 full-text articles were assessed for eligibility. The included 11 studies were from research partnerships internationally and described actions and contextual factors contributing to the coproduction and use of research to inform public policy. Key actions included facilitating frequent interactions with public policy stakeholders, joint planning for research, and collaboration to execute data collection and analysis. Contextual factors included clarity in responsibilities, prior relationships, and mutual respect for partner priorities and perspectives.ConclusionsKey actions and contextual factors were identified in this review and warrant further study to strengthen research-policy partnerships and their outcomes.
| S-EPMC7449077 | biostudies-literature
Project description:BACKGROUND:Although values underpin the goals pursued in health systems, including how health systems benefit the population, it is often not clear how values are incorporated into policy decision-making about health systems. The challenge is to encompass social/citizen values, health system goals, and financial realities and to incorporate them into the policy-making process. This is a challenge for all health systems and of particular importance for Latin American (LA) countries. Our objective was to understand how and under what conditions societal values inform decisions about health system financing in LA countries. METHODS:A critical interpretive synthesis approach was utilised for this work. We searched 17 databases in December 2016 to identify articles written in English, Spanish or Portuguese that focus on values that inform the policy process for health system financing in LA countries at the macro and meso levels. Two reviewers independently screened records and assessed them for inclusion. One researcher conceptually mapped the included articles, created structured summaries of key findings from each, and selected a purposive sample of articles to thematically synthesise the results across the domains of agenda-setting/prioritisation, policy development and implementation. RESULTS:We identified 5925 references, included 199 papers, and synthesised 68 papers. We identified 116 values and developed a framework to explain how values have been used to inform policy decisions about financing in LA countries. This framework has four categories - (1) goal-related values (i.e. guiding principles of the health system); (2) technical values (those incorporated into the instruments adopted by policy-makers to ensure a sustainable and efficient health system); (3) governance values (those applied in the policy process to ensure a transparent and accountable process of decision-making); and (4) situational values (a broad category of values that represent competing strategies to make decisions in the health systems, their influence varying according to the four factors). CONCLUSIONS:It is an effort to consolidate and explain how different social values are considered and how they support policy decision-making about health system financing. This can help policy-makers to explicitly incorporate values into the policy process and understand how values are supporting the achievement of policy goals in health system financing. TRIAL REGISTRATION:The protocol was registered with PROSPERO, ID=CRD42017057049 .
| S-EPMC7487839 | biostudies-literature