scholarly journals Network Analysis: A Novel Approach to Understand Suicidal Behavior

2017 ◽  
Author(s):  
Derek de Beurs
Keyword(s):  
Risk Factors ◽  
Network Analysis ◽  
Suicidal Behavior ◽  
Epidemiological Studies ◽  
Public Health Issue ◽  
Biological Factors ◽  
Major Public Health Issue ◽  
New Approach ◽  
Novel Approach ◽  
Suicidal Patients

Although suicide is a major public health issue worldwide, we understand little of the onset and development of suicidal behavior. Suicidal behavior is argued to be the end result of the complex interaction between psychological, social and biological factors. Epidemiological studies resulted in a range of risk factors for suicidal behavior, but we do not yet understand how their interaction increases the risk for suicidal behavior.  A new approach called network analysis can help us better understand this process as it allows to visualize and quantify complex association between many different symptoms or risk factors. A network analysis of data contain information on suicidal patients can help us understand how risk factors interact and how their interaction is related to suicidal thoughts and behaviour. A network perspective has been successfully applied to the field of depression and psychosis, but not yet to the field of suicidology. In this theoretical article, I will introduce the concept of network analysis to the field of suicide prevention, and offer directions for future applications and studies.

scholarly journals Network Analysis: A Novel Approach to Understand Suicidal Behavior

2017 ◽  
Author(s):  
Derek de Beurs
Keyword(s):  
Risk Factors ◽  
Network Analysis ◽  
Suicidal Behavior ◽  
Suicidal Behaviour ◽  
Complex Interaction ◽  
Public Health Issue ◽  
Biological Factors ◽  
Major Public Health Issue ◽  
New Approach ◽  
Novel Approach

Although suicide is a major public health issue worldwide, we understand little of the onset and development of suicidal behavior. Suicidal behavior is argued to be the end result of the complex interaction between psychological, social and biological factors. A new approach called network analysis can help us better understand suicidal behavior as it allows to visualize and quantify complex association between many different symptoms or risk factors. Risk factors for suicidal behaviour such as intensity of suicidal thoughts and impulsivity are thought to cause each other. A network perspective can help us understand how these risk factors interact and how their interaction is related to future suicidal behaviour. A network perspective has been successfully applied to the field of depression and psychosis, but not yet to the field of suicidology. In this theoretical article, I will introduce the concept of network analysis to the field of suicide prevention, and offer directions for future applications and studies.

scholarly journals A Network Perspective on Suicidal Behaviour

2017 ◽  
Author(s):  
Derek de Beurs
Keyword(s):  
Public Health ◽  
Suicidal Behavior ◽  
Real Data ◽  
Complex Interaction ◽  
Diagnostic Tools ◽  
Public Health Issue ◽  
Major Public Health Issue ◽  
Common Cause ◽  
Future Studies ◽  
A New Technique

Although suicide is a major public health issue worldwide, we understand little of the onset and development of suicidal behavior. Suicidal behavior is argued to be the end result of the complex interaction between social, biological and environmental factors. Traditional epidemiological analytics techniques are not equipped to deal with this complexity. A new technique called network analysis can help us better understand suicidal behavior as it allows to visualize and quantify complex association between many symptoms. It moves away from the idea that symptoms are caused by an underlying common cause such as depression or suicidality. Instead, symptoms are thought to cause each other. A network perspective has been successfully applied to the field of depression, psychosis and PTSD, but not yet to the field of suicidology. In this perspective article, I will argue that a network perspective on suicidal behavior can help us to 1) better understand suicidal behavior, 2) develop more sensitive diagnostic tools for subgroups of patients, and 3) help the personalized treatment of suicidal behavior. I will provide examples based on real data, and offer directions for future studies.

scholarly journals Discovery of Depression-Associated Factors From a Nationwide Population-Based Survey: Epidemiological Study Using Machine Learning and Network Analysis (Preprint)

2021 ◽  
Author(s):  
Sang Min Nam ◽  
Thomas A Peterson ◽  
Kyoung Yul Seo ◽  
Hyun Wook Han ◽  
Jee In Kang
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Network Analysis ◽  
Survey Data ◽  
Associated Factors ◽  
Statistical Tests ◽  
Epidemiological Studies ◽  
Gradient Boosting ◽  
Data Set ◽  
Extreme Gradient Boosting

BACKGROUND In epidemiological studies, finding the best subset of factors is challenging when the number of explanatory variables is large. OBJECTIVE Our study had two aims. First, we aimed to identify essential depression-associated factors using the extreme gradient boosting (XGBoost) machine learning algorithm from big survey data (the Korea National Health and Nutrition Examination Survey, 2012-2016). Second, we aimed to achieve a comprehensive understanding of multifactorial features in depression using network analysis. METHODS An XGBoost model was trained and tested to classify “current depression” and “no lifetime depression” for a data set of 120 variables for 12,596 cases. The optimal XGBoost hyperparameters were set by an automated machine learning tool (TPOT), and a high-performance sparse model was obtained by feature selection using the feature importance value of XGBoost. We performed statistical tests on the model and nonmodel factors using survey-weighted multiple logistic regression and drew a correlation network among factors. We also adopted statistical tests for the confounder or interaction effect of selected risk factors when it was suspected on the network. RESULTS The XGBoost-derived depression model consisted of 18 factors with an area under the weighted receiver operating characteristic curve of 0.86. Two nonmodel factors could be found using the model factors, and the factors were classified into direct (<i>P</i>&lt;.05) and indirect (<i>P</i>≥.05), according to the statistical significance of the association with depression. Perceived stress and asthma were the most remarkable risk factors, and urine specific gravity was a novel protective factor. The depression-factor network showed clusters of socioeconomic status and quality of life factors and suggested that educational level and sex might be predisposing factors. Indirect factors (eg, diabetes, hypercholesterolemia, and smoking) were involved in confounding or interaction effects of direct factors. Triglyceride level was a confounder of hypercholesterolemia and diabetes, smoking had a significant risk in females, and weight gain was associated with depression involving diabetes. CONCLUSIONS XGBoost and network analysis were useful to discover depression-related factors and their relationships and can be applied to epidemiological studies using big survey data.

scholarly journals Adolescent suicide and suicidal behavior: a review

2021 ◽  
Vol 3 (Number 2) ◽  
pp. 38-42
Author(s):  
Mohammad Nurunnabi ◽  
Monowar Ahmad Tarafdar ◽  
Afroza Begum ◽  
Sultana Jahan ◽  
A F M Rezaul Islam
Keyword(s):  
Risk Factors ◽  
Psychiatric Disorders ◽  
Suicidal Behavior ◽  
Depressive Disorders ◽  
Adolescent Suicide ◽  
Suicide Attempts ◽  
Public Health Issue ◽  
Family Adversity ◽  
Middle Income ◽  
Effective Prevention

Suicide among adolescent has emerged as a major public health issue in many low and middle-income (LAMI) countries. Suicidal behavior including ideation and attempt are the most important predictors of completed suicide and offer critical points for intervention. This article reviews recent population and national data based studies of adolescent suicide and suicide attempters for analyzing risk factors for adolescent suicide and suicidal behavior. According to WHO estimates, 800,000 suicide deaths occurred worldwide in 2016 and it is the third leading cause of death for 15-19 year olds. The suicide rate in Bangladesh was 5.9 per 100,000 population in 2016 (4.7 for males and 7.0 for females). Approximately, 90 percent of suicide cases meet criteria for a psychiatric disorder, particularly major depression, substance abuse and prior suicide attempts are strongly related to adolescent suicides. The relationship between psychiatric disorders and adolescent suicide is now well established. Factors related to family adversity, social alienation and precipitating problems also contribute to the risk of suicide. The main target of effective prevention of adolescent suicides is to reduce suicide risk factors. Recognition and effective management and control of psychiatric disorders, e.g. depression, are essential in preventing adolescent suicides. Research on the treatment of diagnosed depressive disorders and of those with suicidal behavior is reviewed.

A new approach for reducing diffuse agricultural pollution in water supply ponds

2013 ◽  
Vol 8 (2) ◽  
pp. 190-201
Author(s):  
André Berne
Keyword(s):  
Water Supply ◽  
Public Health Issue ◽  
Raw Water ◽  
High Stakes ◽  
Major Public Health Issue ◽  
New Approach ◽  
Essential Problem ◽  
Technical Measures

Preserving the quality of raw water for drinking likely to be affected by diffuse pollution in water supply ponds (WSPs) is a major public health issue. We must therefore implement efficient and sustainable technical measures that guarantee the long-term protection of this resource. Such measures can prove to be a considerable constraint for farm managers and farm owners. It is consequently absolutely necessary that the compensation provided for is in line with these constraints. High stakes and high constraints must result in high compensation. The catchment protection perimeter tool, reviewed and enlarged to encompass up to 100% of the WSP, renewed and in-depth dialogue based on solid technical and economic studies and a new compensation method established from the principle of discounted loss capitalisation over a duration equal to the lease, are all new and promising tools to solve this essential problem for sustainable development throughout the territory and to preserve the health of its population.

Interpersonal Gun Violence Research in the Social Work Literature

2019 ◽  
Vol 44 (4) ◽  
pp. 224-231
Author(s):  
Roberto R Aspholm ◽  
Christopher St Vil ◽  
Kimberly A E Carter
Keyword(s):  
Public Health ◽  
Risk Factors ◽  
Social Work ◽  
The United States ◽  
Gun Violence ◽  
Public Health Issue ◽  
Future Research ◽  
Major Public Health Issue ◽  
Analytic Treatment ◽  
The Social

Abstract Interpersonal gun violence remains a major public health issue in the United States and beyond. This article explores the research on interpersonal gun violence published in peer-reviewed social work journals since the mid-1990s. Findings from this review indicate that the existing scholarship offers some important insights into this topic, particularly related to risk factors for and the effects of exposure to gun violence. These findings, however, also point to some shortcomings in the literature, including problems with the measurement and analytic treatment of exposure to gun violence and a lack of research with direct victims and perpetrators of gun violence. Implications for future research are discussed.

scholarly journals Ontological representation, classification and data-driven computing of phenotypes

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Alexandr Uciteli ◽  
Christoph Beger ◽  
Toralf Kirsten ◽  
Frank A. Meineke ◽  
Heinrich Herre
Keyword(s):  
Risk Factors ◽  
Economic Status ◽  
Epidemiological Studies ◽  
Diagnostic Process ◽  
New Approach ◽  
Healthcare Data ◽  
Treatment Optimisation ◽  
Core Ontology ◽  
Classification Tasks ◽  
Input Variables

Abstract Background The successful determination and analysis of phenotypes plays a key role in the diagnostic process, the evaluation of risk factors and the recruitment of participants for clinical and epidemiological studies. The development of computable phenotype algorithms to solve these tasks is a challenging problem, caused by various reasons. Firstly, the term ‘phenotype’ has no generally agreed definition and its meaning depends on context. Secondly, the phenotypes are most commonly specified as non-computable descriptive documents. Recent attempts have shown that ontologies are a suitable way to handle phenotypes and that they can support clinical research and decision making. The SMITH Consortium is dedicated to rapidly establish an integrative medical informatics framework to provide physicians with the best available data and knowledge and enable innovative use of healthcare data for research and treatment optimisation. In the context of a methodological use case ‘phenotype pipeline’ (PheP), a technology to automatically generate phenotype classifications and annotations based on electronic health records (EHR) is developed. A large series of phenotype algorithms will be implemented. This implies that for each algorithm a classification scheme and its input variables have to be defined. Furthermore, a phenotype engine is required to evaluate and execute developed algorithms. Results In this article, we present a Core Ontology of Phenotypes (COP) and the software Phenotype Manager (PhenoMan), which implements a novel ontology-based method to model, classify and compute phenotypes from already available data. Our solution includes an enhanced iterative reasoning process combining classification tasks with mathematical calculations at runtime. The ontology as well as the reasoning method were successfully evaluated with selected phenotypes including SOFA score, socio-economic status, body surface area and WHO BMI classification based on available medical data. Conclusions We developed a novel ontology-based method to model phenotypes of living beings with the aim of automated phenotype reasoning based on available data. This new approach can be used in clinical context, e.g., for supporting the diagnostic process, evaluating risk factors, and recruiting appropriate participants for clinical and epidemiological studies.

scholarly journals A case control study of risk factors associated with pulmonary tuberculosis in Romania: Experience at a clinical hospital of pneumology

2017 ◽  
Vol 90 (1) ◽  
pp. 54-59 ◽  
Author(s):  
Pacifique Ndishimye ◽  
Bianca Domokos ◽  
Jonathan Stillo ◽  
Fouad Seghrouchni ◽  
Oulaya Mrabet ◽  
...  
Keyword(s):  
Risk Factors ◽  
Case Control Study ◽  
Case Control ◽  
Public Health Issue ◽  
Behavioral Risk ◽  
Major Public Health Issue ◽  
Clinical Hospital ◽  
Patient Interviews ◽  
Tb Treatment ◽  
Control Study

Background and aim. Tuberculosis (TB) remains a major public health issue in Romania. The aim of the present study was to evaluate the potential demographic, socioeconomic and behavioral risk factors for TB among hospitalized patients in Romania.Methods. This is a case-control study conducted between March 1st 2014 and March 30th 2015 at Leon Daniello Clinical Hospital of Pneumology, Cluj Napoca. A total of 150 TB patients defined as “cases” were matched for age, sex and county of residence to 150 controls selected from patients attending the same hospital with respiratory diseases other than TB. Data collection was obtained through patient interviews using a structured questionnaire. Factors potentially associated with TB infection were analyzed using univariate and multivariate logistic regression.Results. Factors independently associated with TB were illiteracy (OR=2.42, 95% CI 1.09-5.37), unemployment (OR=2.08, 95% CI 1.23-3.53), low household income (OR=4.12, 95% CI 2.53-6.71), smoking (more than 20 cigarettes per day) (OR=2.12, 95% CI 1.20-3.74), poor knowledge of TB (OR=3.46, 95% CI 1.97-6.07), presence of TB patient in household (OR=4.35, 95% CI 1.42-13.36), prior TB treatment (OR=2.2, 95% CI 1.93-2.5) and diabetes (OR=3.32, 95% CI 1.36-8.08).Conclusion. This study provided useful information that might help to develop and adapt effective policies for TB control in Romania.

scholarly journals Discovery of Depression-Associated Factors From a Nationwide Population-Based Survey: Epidemiological Study Using Machine Learning and Network Analysis

10.2196/27344 ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. e27344
Author(s):  
Sang Min Nam ◽  
Thomas A Peterson ◽  
Kyoung Yul Seo ◽  
Hyun Wook Han ◽  
Jee In Kang
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Network Analysis ◽  
Survey Data ◽  
Associated Factors ◽  
Statistical Tests ◽  
Epidemiological Studies ◽  
Gradient Boosting ◽  
Data Set ◽  
Extreme Gradient Boosting

Background In epidemiological studies, finding the best subset of factors is challenging when the number of explanatory variables is large. Objective Our study had two aims. First, we aimed to identify essential depression-associated factors using the extreme gradient boosting (XGBoost) machine learning algorithm from big survey data (the Korea National Health and Nutrition Examination Survey, 2012-2016). Second, we aimed to achieve a comprehensive understanding of multifactorial features in depression using network analysis. Methods An XGBoost model was trained and tested to classify “current depression” and “no lifetime depression” for a data set of 120 variables for 12,596 cases. The optimal XGBoost hyperparameters were set by an automated machine learning tool (TPOT), and a high-performance sparse model was obtained by feature selection using the feature importance value of XGBoost. We performed statistical tests on the model and nonmodel factors using survey-weighted multiple logistic regression and drew a correlation network among factors. We also adopted statistical tests for the confounder or interaction effect of selected risk factors when it was suspected on the network. Results The XGBoost-derived depression model consisted of 18 factors with an area under the weighted receiver operating characteristic curve of 0.86. Two nonmodel factors could be found using the model factors, and the factors were classified into direct (P<.05) and indirect (P≥.05), according to the statistical significance of the association with depression. Perceived stress and asthma were the most remarkable risk factors, and urine specific gravity was a novel protective factor. The depression-factor network showed clusters of socioeconomic status and quality of life factors and suggested that educational level and sex might be predisposing factors. Indirect factors (eg, diabetes, hypercholesterolemia, and smoking) were involved in confounding or interaction effects of direct factors. Triglyceride level was a confounder of hypercholesterolemia and diabetes, smoking had a significant risk in females, and weight gain was associated with depression involving diabetes. Conclusions XGBoost and network analysis were useful to discover depression-related factors and their relationships and can be applied to epidemiological studies using big survey data.

scholarly journals Is Atrial Fibrillation an Independent Risk Factor for Stroke?

1990 ◽  
Vol 17 (2) ◽  
pp. 163-169 ◽  
Author(s):  
Stephen J. Phillips
Keyword(s):  
Public Health ◽  
Diabetes Mellitus ◽  
Risk Factors ◽  
Atrial Fibrillation ◽  
Clinical Trials ◽  
Risk Factor ◽  
Independent Risk Factor ◽  
Warfarin Therapy ◽  
Public Health Issue ◽  
Major Public Health Issue

ABSTRACT:That non-rheumatic atrial fibrillation is an independent risk factor for cerebral infarction has not been established with certainty. The rationale underlying contemporary clinical trials of warfarin therapy for the prevention of stroke in patients who have non-rheumatic atrial fibrillation is that the majority of strokes in such patients are due to cardiogenic cerebral embolism. However, there is evidence to suggest that the increased probability of stroke attributed to this arrhythmia is due to its association with other risk factors such as hypertension, diabetes mellitus, and atherosclerosis. The question of who should be anticoagulated is a major public health issue since atrial fibrillation is present in approximately ten per cent of the general population aged 65 or more years.

Sign in / Sign up

Export Citation Format

Share Document