scholarly journals Monitoring Information-Seeking Patterns and Obesity Prevalence in Africa With Internet Search Data: Observational Study (Preprint)

2020 ◽  
Author(s):  
Olubusola Oladeji ◽  
Chi Zhang ◽  
Tiam Moradi ◽  
Dharmesh Tarapore ◽  
Andrew C Stokes ◽  
...  
Keyword(s):  
Risk Factors ◽  
Information Seeking ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Obesity Prevalence ◽  
African Countries ◽  
Search Terms ◽  
Obesity And Overweight ◽  
Search Data ◽  
Overweight Prevalence

BACKGROUND The prevalence of chronic conditions such as obesity, hypertension, and diabetes is increasing in African countries. Many chronic diseases have been linked to risk factors such as poor diet and physical inactivity. Data for these behavioral risk factors are usually obtained from surveys, which can be delayed by years. Behavioral data from digital sources, including social media and search engines, could be used for timely monitoring of behavioral risk factors. OBJECTIVE The objective of our study was to propose the use of digital data from internet sources for monitoring changes in behavioral risk factors in Africa. METHODS We obtained the adjusted volume of search queries submitted to Google for 108 terms related to diet, exercise, and disease from 2010 to 2016. We also obtained the obesity and overweight prevalence for 52 African countries from the World Health Organization (WHO) for the same period. Machine learning algorithms (ie, random forest, support vector machine, Bayes generalized linear model, gradient boosting, and an ensemble of the individual methods) were used to identify search terms and patterns that correlate with changes in obesity and overweight prevalence across Africa. Out-of-sample predictions were used to assess and validate the model performance. RESULTS The study included 52 African countries. In 2016, the WHO reported an overweight prevalence ranging from 20.9% (95% credible interval [CI] 17.1%-25.0%) to 66.8% (95% CI 62.4%-71.0%) and an obesity prevalence ranging from 4.5% (95% CI 2.9%-6.5%) to 32.5% (95% CI 27.2%-38.1%) in Africa. The highest obesity and overweight prevalence were noted in the northern and southern regions. Google searches for diet-, exercise-, and obesity-related terms explained 97.3% (root-mean-square error [RMSE] 1.15) of the variation in obesity prevalence across all 52 countries. Similarly, the search data explained 96.6% (RMSE 2.26) of the variation in the overweight prevalence. The search terms yoga, exercise, and gym were most correlated with changes in obesity and overweight prevalence in countries with the highest prevalence. CONCLUSIONS Information-seeking patterns for diet- and exercise-related terms could indicate changes in attitudes toward and engagement in risk factors or healthy behaviors. These trends could capture population changes in risk factor prevalence, inform digital and physical interventions, and supplement official data from surveys.

scholarly journals Monitoring Information-Seeking Patterns and Obesity Prevalence in Africa With Internet Search Data: Observational Study

10.2196/24348 ◽  
2021 ◽  
Vol 7 (4) ◽  
pp. e24348
Author(s):  
Olubusola Oladeji ◽  
Chi Zhang ◽  
Tiam Moradi ◽  
Dharmesh Tarapore ◽  
Andrew C Stokes ◽  
...  
Keyword(s):  
Risk Factors ◽  
Information Seeking ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Obesity Prevalence ◽  
African Countries ◽  
Search Terms ◽  
Obesity And Overweight ◽  
Search Data ◽  
Overweight Prevalence

Background The prevalence of chronic conditions such as obesity, hypertension, and diabetes is increasing in African countries. Many chronic diseases have been linked to risk factors such as poor diet and physical inactivity. Data for these behavioral risk factors are usually obtained from surveys, which can be delayed by years. Behavioral data from digital sources, including social media and search engines, could be used for timely monitoring of behavioral risk factors. Objective The objective of our study was to propose the use of digital data from internet sources for monitoring changes in behavioral risk factors in Africa. Methods We obtained the adjusted volume of search queries submitted to Google for 108 terms related to diet, exercise, and disease from 2010 to 2016. We also obtained the obesity and overweight prevalence for 52 African countries from the World Health Organization (WHO) for the same period. Machine learning algorithms (ie, random forest, support vector machine, Bayes generalized linear model, gradient boosting, and an ensemble of the individual methods) were used to identify search terms and patterns that correlate with changes in obesity and overweight prevalence across Africa. Out-of-sample predictions were used to assess and validate the model performance. Results The study included 52 African countries. In 2016, the WHO reported an overweight prevalence ranging from 20.9% (95% credible interval [CI] 17.1%-25.0%) to 66.8% (95% CI 62.4%-71.0%) and an obesity prevalence ranging from 4.5% (95% CI 2.9%-6.5%) to 32.5% (95% CI 27.2%-38.1%) in Africa. The highest obesity and overweight prevalence were noted in the northern and southern regions. Google searches for diet-, exercise-, and obesity-related terms explained 97.3% (root-mean-square error [RMSE] 1.15) of the variation in obesity prevalence across all 52 countries. Similarly, the search data explained 96.6% (RMSE 2.26) of the variation in the overweight prevalence. The search terms yoga, exercise, and gym were most correlated with changes in obesity and overweight prevalence in countries with the highest prevalence. Conclusions Information-seeking patterns for diet- and exercise-related terms could indicate changes in attitudes toward and engagement in risk factors or healthy behaviors. These trends could capture population changes in risk factor prevalence, inform digital and physical interventions, and supplement official data from surveys.

scholarly journals Identification of Risk Factors Associated with Obesity and Overweight—A Machine Learning Overview

Sensors ◽  
2020 ◽  
Vol 20 (9) ◽  
pp. 2734 ◽  
Author(s):  
Ayan Chatterjee ◽  
Martin W. Gerdes ◽  
Santiago G. Martinez
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Diabetes Type ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Type Ii ◽  
Diabetes Type Ii ◽  
Obesity And Overweight ◽  
Potential Risk Factors ◽  
Lifestyle Diseases

Social determining factors such as the adverse influence of globalization, supermarket growth, fast unplanned urbanization, sedentary lifestyle, economy, and social position slowly develop behavioral risk factors in humans. Behavioral risk factors such as unhealthy habits, improper diet, and physical inactivity lead to physiological risks, and “obesity/overweight” is one of the consequences. “Obesity and overweight” are one of the major lifestyle diseases that leads to other health conditions, such as cardiovascular diseases (CVDs), chronic obstructive pulmonary disease (COPD), cancer, diabetes type II, hypertension, and depression. It is not restricted within the age and socio-economic background of human beings. The “World Health Organization” (WHO) has anticipated that 30% of global death will be caused by lifestyle diseases by 2030 and it can be prevented with the appropriate identification of associated risk factors and behavioral intervention plans. Health behavior change should be given priority to avoid life-threatening damages. The primary purpose of this study is not to present a risk prediction model but to provide a review of various machine learning (ML) methods and their execution using available sample health data in a public repository related to lifestyle diseases, such as obesity, CVDs, and diabetes type II. In this study, we targeted people, both male and female, in the age group of >20 and <60, excluding pregnancy and genetic factors. This paper qualifies as a tutorial article on how to use different ML methods to identify potential risk factors of obesity/overweight. Although institutions such as “Center for Disease Control and Prevention (CDC)” and “National Institute for Clinical Excellence (NICE)” guidelines work to understand the cause and consequences of overweight/obesity, we aimed to utilize the potential of data science to assess the correlated risk factors of obesity/overweight after analyzing the existing datasets available in “Kaggle” and “University of California, Irvine (UCI) database”, and to check how the potential risk factors are changing with the change in body-energy imbalance with data-visualization techniques and regression analysis. Analyzing existing obesity/overweight related data using machine learning algorithms did not produce any brand-new risk factors, but it helped us to understand: (a) how are identified risk factors related to weight change and how do we visualize it? (b) what will be the nature of the data (potential monitorable risk factors) to be collected over time to develop our intended eCoach system for the promotion of a healthy lifestyle targeting “obesity and overweight” as a study case in the future? (c) why have we used the existing “Kaggle” and “UCI” datasets for our preliminary study? (d) which classification and regression models are performing better with a corresponding limited volume of the dataset following performance metrics?

scholarly journals Psychological and Behavioral Predictors of Vaccine Efficacy: Considerations for COVID-19

2021 ◽  
pp. 174569162198924
Author(s):  
Annelise A. Madison ◽  
M. Rosie Shrout ◽  
Megan E. Renna ◽  
Janice K. Kiecolt-Glaser
Keyword(s):  
Risk Factors ◽  
Side Effects ◽  
Vaccine Efficacy ◽  
Psychological Factors ◽  
Behavioral Interventions ◽  
Vulnerable Groups ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Vaccine Response ◽  
The Impact

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccine candidates are being evaluated, with the goal of conferring immunity on the highest percentage of people who receive the vaccine as possible. It is noteworthy that vaccine efficacy depends not only on the vaccine but also on characteristics of the vaccinated. Over the past 30 years, a series of studies has documented the impact of psychological factors on the immune system’s vaccine response. Robust evidence has demonstrated that stress, depression, loneliness, and poor health behaviors can impair the immune system’s response to vaccines, and this effect may be greatest in vulnerable groups such as the elderly. Psychological factors are also implicated in the prevalence and severity of vaccine-related side effects. These findings have generalized across many vaccine types and therefore may be relevant to the SARS-CoV-2 vaccine. In this review, we discuss these psychological and behavioral risk factors for poor vaccine responses, their relevance to the COVID-19 pandemic, as well as targeted psychological and behavioral interventions to boost vaccine efficacy and reduce side effects. Recent data suggest these psychological and behavioral risk factors are highly prevalent during the COVID-19 pandemic, but intervention research suggests that psychological and behavioral interventions can increase vaccine efficacy.

scholarly journals Effects of Behavioral Risk Factors and Social-Environmental Factors on Non-Communicable Diseases in South Korea: A National Survey Approach

2021 ◽  
Vol 18 (2) ◽  
pp. 612
Author(s):  
Nam Jeong Jeong ◽  
Eunil Park ◽  
Angel P. del Pobil
Keyword(s):  
Risk Factors ◽  
Environmental Factors ◽  
South Korea ◽  
Communicable Diseases ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Non Communicable Diseases ◽  
Path Analyses ◽  
Social Environmental ◽  
Social Environmental Factors

Non-communicable diseases (NCDs) are one of the major health threats in the world. Thus, identifying the factors that influence NCDs is crucial to monitor and manage diseases. This study investigates the effects of social-environmental and behavioral risk factors on NCDs as well as the effects of social-environmental factors on behavioral risk factors using an integrated research model. This study used a dataset from the 2017 Korea National Health and Nutrition Examination Survey. After filtering incomplete responses, 5462 valid responses remained. Items including one’s social-environmental factors (household income, education level, and region), behavioral factors (alcohol use, tobacco use, and physical activity), and NCDs histories were used for analyses. To develop a comprehensive index of each factor that allows comparison between different concepts, the researchers assigned scores to indicators of the factors and calculated a ratio of the scores. A series of path analyses were conducted to determine the extent of relationships among NCDs and risk factors. The results showed that social-environmental factors have notable effects on stroke, myocardial infarction, angina, diabetes, and gastric, liver, colon, lung, and thyroid cancers. The results indicate that the effects of social-environmental and behavioral risk factors on NCDs vary across the different types of diseases. The effects of social-environmental factors and behavioral risk factors significantly affected NCDs. However, the effect of social-environmental factors on behavioral risk factors was not supported. Furthermore, social-environmental factors and behavioral risk factors affect NCDs in a similar way. However, the effects of behavioral risk factors were smaller than those of social-environmental factors. The current research suggests taking a comprehensive view of risk factors to further understand the antecedents of NCDs in South Korea.

Abstract WP182: Trends in Acute Ischemic Stroke Hospitalizations and Risk Factors Among Young Adults: 12 Years of Nationally Representative Data

Stroke ◽  
2017 ◽  
Vol 48 (suppl_1) ◽  
Author(s):  
Urvish K Patel ◽  
Priti Poojary ◽  
Vishal Jani ◽  
Mandip S Dhamoon
Keyword(s):  
Risk Factors ◽  
Older Adults ◽  
Young Adults ◽  
Ischemic Stroke ◽  
Length Of Stay ◽  
Acute Ischemic Stroke ◽  
Stroke Risk ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Stroke Risk Factors

Background: There is limited recent population-based data of trends in acute ischemic stroke (AIS) hospitalization rates among young adults (YA). Rising prevalence of stroke risk factors may increase stroke rates in YA. We hypothesized that 1) stroke hospitalizations and mortality among YA are increasing over time (2000-2011), 2) besides traditional stroke risk factors, non-traditional factors are associated with stroke in YA, 3) stroke hospitalization among YA is associated with higher mortality, length of stay (LOS), and cost. Methods: In the Nationwide Inpatient Sample database (years 2000-2011), adult hospitalizations for AIS and concurrent diagnoses were identified by ICD-9-CM codes; the analytic cohort constituted all AIS hospitalizations. We performed weighted analysis using chi-square, t-test, and Jonckheere trend test. Multivariable survey regression models evaluated interactions between age group (18-45 vs. >45 years) and traditional and non-traditional risk factors, with outcomes including mortality, LOS, and cost. Models were adjusted for race, sex, Charlson’s Comorbidity Index, primary payer, location and teaching status of hospital, and admission day. Results: Among 5220960 AIS hospitalizations, 231858 (4.4%) were YA. On trend analysis, proportion of YA amongst AIS increased from 3.6% in 2000 to 4.7% in 2011 (p<0.0001) but mortality in YA decreased from 3.7% in 2000 to 2.6% in 2011, compared to 7.1% in 2000 to 4.6% in 2011 (p<0.0001) among older adults. Non-traditional, especially behavioral, risk factors were more common among YA, and LOS and cost were higher (Table). Conclusion: There was a trend for higher proportion of YA among AIS hospitalizations, though there was a decreasing mortality trend over 10 years. Behavioral risk factors were more common among YA, and there was an increased length of stay and cost. AIS in YA may require different preventive approaches compared to AIS among older adults.

Monitoring the dynamics of behavioral risk factors in patients with angina pectoris and comorbid condition

Therapy ◽  
2021 ◽  
Vol 6_2021 ◽  
pp. 51-55
Author(s):  
Didigova R.T. Didigova ◽  
Evloeva D.A. Evloeva ◽  
Ugurchieva Z.O. Ugurchieva ◽  
Ugurchieva P.O. Ugurchieva ◽  
Malsagova I.Ya. Malsagova ◽  
...  
Keyword(s):  
Risk Factors ◽  
Angina Pectoris ◽  
Comorbid Condition ◽  
Behavioral Risk Factors ◽  
Behavioral Risk

Comprehensive Assessment of Behavioral Risk Factors within the Health Risk Management System for Oil Refinery Operators

2021 ◽  
pp. 16-21
Author(s):  
NI Latyshevskaya ◽  
VV Mirochnik ◽  
LA Davydenko ◽  
AI Kireeva ◽  
AV Belyaeva
Keyword(s):  
Risk Factors ◽  
Risk Management ◽  
Health Risk ◽  
Oil Refinery ◽  
Behavioral Risk Factors ◽  
Behavioral Risk ◽  
Age Group ◽  
Volgograd Region ◽  
Comprehensive Health ◽  
Health Risk Management

Summary. Introduction: Comprehensive risk management considering behavioral risk factors is a possible way to minimize adverse health effects of occupational factors. The purpose of the study was assess behavioral risk factors and to develop appropriate measures for preventing occupational diseases in oil refinery operators. Materials and methods: The observation groups included crude oil treatment operators of Ritek LLC in the Volgograd Region located in the subarid climatic zone. The first group consisted of 100 workers under the age of 35 while the second group consisted of 106 workers aged 36-60. Previously published studies were used to substantiate priority occupational risk factors for the operators. To assess lifestyle habits, we conducted a questionnaire-based survey and analyzed data in terms of their statistical significance and real controllability using a multidimensional confirmatory factor analysis. Results: We established that the priority occupational health risks of operators in the climatic conditions of the Volgograd Region included labor severity and intensity (3.1) and hot environment (3.2) posing a high occupational risk of disrupting the thermal state (overheating) of workers. We also identified typical behavioral risk factors, the prevalence and quantitative burden of which was age-specific. In the younger age group, bad habits and poor healthcare activity (reluctance to seek medical advice) generated the highest burdens (943 conditional units each) while in the older age group, major burdens were generated by bad habits and malnutrition (849 and 501 units, respectively). The developed mathematical model proved that a comprehensive health risk management for workers exposed to occupational hazards is feasible by correcting certain behavioral risk factors: a 10 % and 50 % decrease in the burden of bad habits and poor healthcare activity led to a 1.1 and 1.5-fold decrease in the extent of health risk, respectively. Conclusion: The study revealed the most significant behavioral risk factors affecting health of oil refinery operators and substantiated options of the most optimal interaction between the elements of the system reducing the overall risk to human health. Comprehensive health risk management based on optimal interaction of system elements (both occupational and behavioral risk factors) reduces health risks for oil refinery operators.

Sign in / Sign up

Export Citation Format

Share Document