Development of a prediction model to target screening for high blood pressure in children

Predicting Childhood and Adolescence Hypertension: Analysis of Predictors Using Machine Learning

BACKGROUND

There has been a substantial burden of hypertension in children and adolescents. Given the availability of primary prevention strategies, it is important to determine predictors for early identification of children and adolescents at risk of hypertension. This study aims to attempt and validate machine learning (ML) algorithms for accurately predicting blood pressure (BP) status (normal, prehypertension, and hypertension) over 1- and 3-year periods, identifying key predictors without compromising model performance.

METHODS

We included a population-based cohort of primary 1 to secondary 6 students (typically aged 6 to 18 years) during the academic years of 1995 to 1996 and 2019 to 2020 in Hong Kong. Thirty-six easy-assessed predictors were initially model childhood BP status. Multiple ML algorithms, decision tree, random forest, k-nearest neighbor, eXtreme Gradient Boosting (XGBoost), and multinomial logistic regression (MLR), were used. Model evaluation was performed by various accuracy metrics. The Shapley Additive Explanations (SHAP) was used to identify key features for both predictions.

RESULTS

A total of 923 301 and 602 179 visit pairs were used for the 1- and 3-year predictions, respectively. XGBoost demonstrated the highest prediction accuracies for 1-year (macro-area under the receiver operating characteristic curve [AUROC] = 0.92, micro-AUROC = 0.91) and 3-year (macro-AUROC = 0.91, micro-AUROC = 0.90) periods. The traditional MLR approach had the lowest accuracies for 1- (macro-AUROC = 0.70, micro-AUROC = 0.68) and 3-year (macro-AUROC = 0.70, micro-AUROC = 0.68) predictions. The SHAP values identified 17 key predictors without the need for direct BP measurements or laboratory tests.

CONCLUSION

ML prediction models can accurately predict childhood prehypertension and hypertension at 1 and 3 years, independent of BP and laboratory measurements. The identified key predictors may inform areas for personalized prevention in hypertension.

Prevalence of childhood hypertension and associated factors in Zhejiang Province: a cross-sectional analysis based on random forest model and logistic regression

With childhood hypertension emerging as a global public health concern, understanding its associated factors is crucial. This study investigated the prevalence and associated factors of hypertension among Chinese children. This cross-sectional investigation was conducted in Pinghu, Zhejiang province, involving 2,373 children aged 8-14 years from 12 schools. Anthropometric measurements were taken by trained staff. Blood pressure (BP) was measured in three separate occasions, with an interval of at least two weeks. Childhood hypertension was defined as systolic blood pressure (SBP) and/or diastolic blood pressure (DBP) ≥ age-, sex-, and height-specific 95th percentile, across all three visits. A self-administered questionnaire was utilized to collect demographic, socioeconomic, health behavioral, and parental information at the first visit of BP measurement. Random forest (RF) and multivariable logistic regression model were used collectively to identify associated factors. Additionally, population attributable fractions (PAFs) were calculated. The prevalence of childhood hypertension was 5.0% (95% confidence interval [CI]: 4.1-5.9%). Children with body mass index (BMI) ≥ 85th percentile were grouped into abnormal weight, and those with waist circumference (WC) > 90th percentile were sorted into central obesity. Normal weight with central obesity (NWCO, adjusted odds ratio [aOR] = 5.04, 95% CI: 1.96-12.98), abnormal weight with no central obesity (AWNCO, aOR = 4.60, 95% CI: 2.57-8.21), and abnormal weight with central obesity (AWCO, aOR = 9.94, 95% CI: 6.06-16.32) were associated with an increased risk of childhood hypertension. Childhood hypertension was attributable to AWCO mostly (PAF: 0.64, 95% CI: 0.50-0.75), followed by AWNCO (PAF: 0.34, 95% CI: 0.19-0.51), and NWCO (PAF: 0.13, 95% CI: 0.03-0.30). Our results indicated that obesity phenotype is associated with childhood hypertension, and the role of weight management could serve as potential target for intervention.

Neonatal AVPR1a Methylation and In-Utero Exposure to Maternal Smoking

(1) Introduction: Epigenetic changes have been proposed as a biologic link between in-utero exposure to maternal smoking and health outcomes. Therefore, we examined if in-utero exposure to maternal smoking was associated with infant DNA methylation (DNAm) of cytosine-phosphate-guanine dinucleotides (CpG sites) in the arginine vasopressin receptor 1A AVPR1a gene. The AVPR1a gene encodes a receptor that interacts with the arginine vasopressin hormone and may influence physiological stress regulation, blood pressure, and child development. (2) Methods: Fifty-two infants were included in this cohort study. Multivariable linear models were used to examine the effect of in-utero exposure to maternal smoking on the mean DNAm of CpG sites located at AVPR1a. (3) Results: After adjusting the model for substance use, infants with in-utero exposure to maternal smoking had a reduction in DNAm at AVPR1a CpG sites by -0.02 (95% CI -0.03, -0.01) at one month of age. In conclusion, in-utero exposure to tobacco smoke can lead to differential patterns of DNAm of AVPR1a among infants. Conclusions: Future studies are needed to identify how gene expression in response to early environmental exposures contributes to health outcomes.

Maternal smoking in pregnancy and blood pressure during childhood and adolescence: a meta-analysis

Arterial hypertension during childhood or adolescence is rising, and smoking during pregnancy may constitute a modifiable risk factor. This study aims to evaluate the effect of maternal smoking during pregnancy on diastolic (DBP) and systolic blood pressure (SBP) in childhood and adolescence. A bibliographic search was conducted in PubMed, Embase, and CENTRAL databases in March 2022. Meta-analysis was performed with the difference in mean-adjusted SBP/DBP of children and adolescents aged 3-17 years, according to maternal smoking/non-smoking in pregnancy. A random effects model was applied; a leave-one-out analysis and meta-analysis by subgroups were performed. A modified Newcastle-Ottawa scale was used to assess the quality of the studies. Evidence levels were rated using the GRADE system. Fifteen studies were included in the meta-analysis; all of them evaluated the mean-adjusted SBP difference in children or adolescents (N = 73,448), and 6 also that of DBP (N = 31,459). Results showed that maternal smoking during pregnancy significantly increased SBP (β = 0.31 mmHg 95% CI 0.14-0.49). A greater increase in mean-adjusted SBP was observed in those studies that completed the recruitment before 1990, were conducted in non-European countries, used standard mercury or manual sphygmomanometry, adjusted for birth weight, and were in the lowest quality subgroup. No significant association was found for DBP. The GRADE level of evidence was low for SBP and very low for DBP.

CONCLUSION

Smoking in pregnancy might increase SBP in childhood and adolescence. Due to the low level of evidence, solid inferences cannot be drawn about the clinical relevance of these findings.

WHAT IS KNOWN

• AHT is the leading cause of premature death among adults worldwide. • Deleterious effects derived from SHS exposure on children's health have been documented since early 1970. To date, there are contradictory results about the effects of prenatal SHS exposure on children's BP.

WHAT IS NEW

• Smoking in pregnancy may increase SBP during childhood and adolescence. • Maternal smoking during pregnancy could have greater influence on their offspring's SBP than on DBP.

Health Information Prediction System of Infant Sports Based on Deep Learning Network

The sensed data from infant sports and training programs are useful in analyzing their health conditions and forecasting any disorders or abnormalities. The sensed information is processed for providing errorless predictions for infant diseases/disorders, coupled with artificial intelligence and sophisticated healthcare technologies. The problem of noncongruent sensed data impacting the forecast occurs due to errors between consecutive training iterations. This problem is addressed using the deep learning (PEST-DL) proposed perceptible error segregation technique. The training process is halted between two consecutive iterations generating errors until a similarity verification based on infant history is performed. The similarity output determines the errors due to mismatching data observations, and therefore, the data augmentation is performed. The first perceptible error is mitigated by training the learning paradigm with all possible infant history data in the learning process. This prevents prediction lag and data omissions due to discrete availability. The learning is trained from the identified error with the precise detected disorder/abnormality data previously detected. Therefore, the first and consecutive training data segregate error instances from the actual training iterations. This improves the prediction accuracy and precision with controlled error and time complexity.

Development and Validation of a Nomogram-Based Prognostic Model to Predict High Blood Pressure in Children and Adolescents—Findings From 342,736 Individuals in China

Objectives

Predicting the potential risk factors of high blood pressure (HBP) among children and adolescents is still a knowledge gap. Our study aimed to establish and validate a nomogram-based model for identifying youths at risk of developing HBP.

Methods

HBP was defined as systolic blood pressure or diastolic blood pressure above the 95th percentile, using age, gender, and height-specific cut-off points. Penalized regression with Lasso was used to identify the strongest predictors of HBP. Internal validation was conducted by a 5-fold cross-validation and bootstrapping approach. The predictive variables and the advanced nomogram plot were identified by conducting univariate and multivariate logistic regression analyses. A nomogram was constructed by a training group comprised of 239,546 (69.9%) participants and subsequently validated by an external group with 103,190 (30.1%) participants.

Results

Of 342,736 children and adolescents, 55,480 (16.2%) youths were identified with HBP with mean age 11.51 ± 1.45 years and 183,487 were boys (53.5%). Nine significant relevant predictors were identified including: age, gender, weight status, birth weight, breastfeeding, gestational hypertension, family history of obesity and hypertension, and physical activity. Acceptable discrimination [area under the receiver operating characteristic curve (AUC): 0.742 (development group), 0.740 (validation group)] and good calibration (Hosmer and Lemeshow statistics, P > 0.05) were observed in our models. An available web-based nomogram was built online on https://hbpnomogram.shinyapps.io/Dyn_Nomo_HBP/.

Conclusions

This model composed of age, gender, early life factors, family history of the disease, and lifestyle factors may predict the risk of HBP among youths, which has developed a promising nomogram that may aid in more accurately identifying HBP among youths in primary care.

Prenatal nicotine exposure was associated with long-term impact on the cardiovascular system and regulation-Review

AIM

The aim of this structured review was to discuss knowledge of nicotine use during pregnancy and long-term effects on children's cardiovascular function.

METHODS

PubMed and MEDLINE were searched for original papers that covered various forms of nicotine exposure during pregnancy and this identified 314 papers published in English from inception of the databases to 1 March 2021. The research focus was prenatal exposure that had long-term effects on the cardiovascular system. The search was expanded from the reference list of the selected papers, which identified another 17 papers.

RESULTS

The 34 original papers that were included covered 172,696 subjects from foetuses to 19 years of age. Cardiovascular autonomic dysfunction was discussed in 12 of the papers and 16 studies reported on blood pressure. The remaining studies covered structural or functional changes in arterial wall or heart. There were convincing data on autonomic dysfunction and increased blood pressure. Some data were conflicting and problems with misclassification of exposure were evident.

CONCLUSION

Prenatal nicotine exposure was associated with long-term developmental changes in the cardiovascular system and regulation. There were no safe periods, doses or nicotine products during pregnancy and women should abstain when planning a pregnancy.