Dataset Information

Prediction of Adulthood Obesity Using Genetic and Childhood Clinical Risk Factors in the Cardiovascular Risk in Young Finns Study.

ABSTRACT: BACKGROUND:Obesity is a known risk factor for cardiovascular disease. Early prediction of obesity is essential for prevention. The aim of this study is to assess the use of childhood clinical factors and the genetic risk factors in predicting adulthood obesity using machine learning methods. METHODS AND RESULTS:A total of 2262 participants from the Cardiovascular Risk in YFS (Young Finns Study) were followed up from childhood (age 3-18 years) to adulthood for 31 years. The data were divided into training (n=1625) and validation (n=637) set. The effect of known genetic risk factors (97 single-nucleotide polymorphisms) was investigated as a weighted genetic risk score of all 97 single-nucleotide polymorphisms (WGRS97) or a subset of 19 most significant single-nucleotide polymorphisms (WGRS19) using boosting machine learning technique. WGRS97 and WGRS19 were validated using external data (n=369) from BHS (Bogalusa Heart Study). WGRS19 improved the accuracy of predicting adulthood obesity in training (area under the curve [AUC=0.787 versus AUC=0.744, P<0.0001) and validation data (AUC=0.769 versus AUC=0.747, P=0.026). WGRS97 improved the accuracy in training (AUC=0.782 versus AUC=0.744, P<0.0001) but not in validation data (AUC=0.749 versus AUC=0.747, P=0.785). Higher WGRS19 associated with higher body mass index at 9 years and WGRS97 at 6 years. Replication in BHS confirmed our findings that WGRS19 and WGRS97 are associated with body mass index. CONCLUSIONS:WGRS19 improves prediction of adulthood obesity. Predictive accuracy is highest among young children (3-6 years), whereas among older children (9-18 years) the risk can be identified using childhood clinical factors. The model is helpful in screening children with high risk of developing obesity.

SUBMITTER: Seyednasrollah F

PROVIDER: S-EPMC7518570 | biostudies-literature | 2017 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of Adulthood Obesity Using Genetic and Childhood Clinical Risk Factors in the Cardiovascular Risk in Young Finns Study.

Seyednasrollah Fatemeh F Mäkelä Johanna J Pitkänen Niina N Juonala Markus M Hutri-Kähönen Nina N Lehtimäki Terho T Viikari Jorma J Kelly Tanika T Li Changwei C Bazzano Lydia L Elo Laura L LL Raitakari Olli T OT

Circulation. Cardiovascular genetics 20170601 3

<h4>Background</h4>Obesity is a known risk factor for cardiovascular disease. Early prediction of obesity is essential for prevention. The aim of this study is to assess the use of childhood clinical factors and the genetic risk factors in predicting adulthood obesity using machine learning methods.<h4>Methods and results</h4>A total of 2262 participants from the Cardiovascular Risk in YFS (Young Finns Study) were followed up from childhood (age 3-18 years) to adulthood for 31 years. The data we ...[more]

PMID: 28620069

Similar Datasets

Project description:ObjectiveSedentary behaviour may contribute to the development of obesity. We investigated the relations between different types of sedentary behaviour and adiposity markers in a well-characterised adult population after controlling for a wide range of potential confounders.DesignCross-sectional study.SettingThe Cardiovascular Risk in Young Finns Multicenter Study. Participants Sedentary time (TV viewing, computer time, reading, music/radio listening and other relaxation) was assessed with a questionnaire for 1084 women and 909 men aged 30-45 years. Other study variables included occupational and leisure-time physical activity, sleep duration, socioeconomic status, smoking, alcohol consumption, energy intake, adherence to the recommended diet, multiple individual food items, age and genetic variants associated with body mass index (BMI). Primary outcome measures BMI in kg/m(2) and waist circumference (WC in cm).ResultsOf the different sedentary behaviour types, TV viewing was most consistently related to higher BMI and WC, both in men and women. One additional daily TV hour was associated with a 1.81±0.44 cm larger WC in women and 2 cm±0.44 cm in men (both p<0.0001). The association with TV was diluted, but remained highly significant after adjustments with all measured covariates, including several potentially obesogenic food items associated with TV viewing. The intakes of food items such as sausage, beer and soft drinks were directly associated with TV viewing, while the intakes of oat and barley, fish, and fruits and berries were associated indirectly. After these adjustments, non-TV sedentary behaviour remained associated with adiposity indices only in women.ConclusionsOut of the different types of sedentary behaviour, TV viewing was most consistently associated with adiposity markers in adults. Partial dilution of these associations after adjustments for covariates suggests that the obesogenic effects of TV viewing are partly mediated by other lifestyle factors.

Project description:ImportanceIncreased left ventricular (LV) mass and diastolic dysfunction are associated with cardiovascular disease. Prospective data on effects of childhood socioeconomic status (SES) on measures of LV structure and function are lacking.ObjectiveTo examine whether family SES in childhood was associated with LV mass and diastolic function after adjustment for conventional cardiovascular disease risk factors in childhood and adulthood.Design, setting, and participantsThe analyses were performed in 2016 using data gathered in 1980 and 2011 within the longitudinal population-based Cardiovascular Risk in Young Finns Study. The sample comprised 1871 participants who reported family SES at ages 3 to 18 years and were evaluated for LV structure and function 31 years later.ExposuresSocioeconomic status was characterized as annual income of the family and classified on a 3-point scale.Main outcomes and measuresLeft ventricular mass indexed according to height at the allometric power of 2.7 and the E/e' ratio describing LV diastolic performance at ages 34 to 49 years.ResultsThe participants were aged 3 to 18 years at baseline (mean [SD], 10.8 [5.0] years), and the length of follow-up was 31 years. Family SES was inversely associated with LV mass (mean [SD] LV mass index, 31.8 [6.7], 31.0 [6.6], and 30.1 [6.4] g/m2.7 in the low, medium, and high SES groups, respectively; differences [95% CI], 1.7 [0.6 to 2.8] for low vs high SES; 0.8 [-0.3 to 1.9] for low vs medium; and 0.9 [0.1 to 1.6] for medium vs high; overall P = .001) and E/e' ratio (mean [SD] E/e' ratio, 5.0 [1.0], 4.9 [1.0], and 4.7 [1.0] in the low, medium, and high SES groups, respectively; differences [95% CI], 0.3 [0.1 to 0.4] for low vs high SES; 0.1 [-0.1 to 0.3] for low vs medium; and 0.2 [0 to 0.3] for medium vs high; overall P < .001) in adulthood. After adjustment for age, sex, and conventional cardiovascular disease risk factors in childhood and adulthood, and participants' own SES in adulthood, the relationship with LV mass (differences [95% CI], 1.5 [0.2 to 2.8] for low vs high SES; 1.3 [0 to 2.6] for low vs medium; and 0.2 [-0.6 to 1.0] for medium vs high; P = .03) and E/e' ratio (differences [95% CI], 0.2 [0 to 0.5] for low vs high SES; 0.1 [-0.1 to 0.4] for low vs medium; and 0.1 [0 to 0.3] for medium vs high; P = .02) remained significant.Conclusions and relevanceLow family SES was associated with increased LV mass and impaired diastolic performance more than 3 decades later. These findings emphasize that approaches of cardiovascular disease prevention must be directed also to the family environment of the developing child.

Project description:The relative contribution of genetic risk factors to the progression of subclinical atherosclerosis is poorly understood. It is likely that multiple variants are implicated in the development of atherosclerosis, but the subtle genotypic and phenotypic differences are beyond the reach of the conventional case-control designs and the statistical significance testing procedures being used in most association studies. Our objective here was to investigate whether an alternative approach--in which common disorders are treated as quantitative phenotypes that are continuously distributed over a population--can reveal predictive insights into the early atherosclerosis, as assessed using ultrasound imaging-based quantitative measurement of carotid artery intima-media thickness (IMT). Using our population-based follow-up study of atherosclerosis precursors as a basis for sampling subjects with gradually increasing IMT levels, we searched for such subsets of genetic variants and their interactions that are the most predictive of the various risk classes, rather than using exclusively those variants meeting a stringent level of statistical significance. The area under the receiver operating characteristic curve (AUC) was used to evaluate the predictive value of the variants, and cross-validation was used to assess how well the predictive models will generalize to other subsets of subjects. By means of our predictive modeling framework with machine learning-based SNP selection, we could improve the prediction of the extreme classes of atherosclerosis risk and progression over a 6-year period (average AUC 0.844 and 0.761), compared to that of using conventional cardiovascular risk factors alone (average AUC 0.741 and 0.629), or when combined with the statistically significant variants (average AUC 0.762 and 0.651). The predictive accuracy remained relatively high in an independent validation set of subjects (average decrease of 0.043). These results demonstrate that the modeling framework can utilize the "gray zone" of genetic variation in the classification of subjects with different degrees of risk of developing atherosclerosis.

Dataset Information

Prediction of Adulthood Obesity Using Genetic and Childhood Clinical Risk Factors in the Cardiovascular Risk in Young Finns Study.

Publications

Prediction of Adulthood Obesity Using Genetic and Childhood Clinical Risk Factors in the Cardiovascular Risk in Young Finns Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets