A risk score predicting new incidence of hypertension in Japan

Prognostic risk models for incident hypertension: A PRISMA systematic review and meta-analysis

OBJECTIVE

Our goal was to review the available literature on prognostic risk prediction for incident hypertension, synthesize performance, and provide suggestions for future work on the topic.

METHODS

A systematic search on PUBMED and Web of Science databases was conducted for studies on prognostic risk prediction models for incident hypertension in generally healthy individuals. Study-quality was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST) checklist. Three-level meta-analyses were used to obtain pooled AUC/C-statistic estimates. Heterogeneity was explored using study and cohort characteristics in meta-regressions.

RESULTS

From 5090 hits, we found 53 eligible studies, and included 47 in meta-analyses. Only four studies were assessed to have results with low risk of bias. Few models had been externally validated, with only the Framingham risk model validated more than thrice. The pooled AUC/C-statistics were 0.82 (0.77-0.86) for machine learning models and 0.78 (0.76-0.80) for traditional models, with high heterogeneity in both groups (I2 > 99%). Intra-class correlations within studies were 60% and 90%, respectively. Follow-up time (P = 0.0405) was significant for ML models and age (P = 0.0271) for traditional models in explaining heterogeneity. Validations of the Framingham risk model had high heterogeneity (I2 > 99%).

CONCLUSION

Overall, the quality of included studies was assessed as poor. AUC/C-statistic were mostly acceptable or good, and higher for ML models than traditional models. High heterogeneity implies large variability in the performance of new risk models. Further, large heterogeneity in validations of the Framingham risk model indicate variability in model performance on new populations. To enable researchers to assess hypertension risk models, we encourage adherence to existing guidelines for reporting and developing risk models, specifically reporting appropriate performance measures. Further, we recommend a stronger focus on validation of models by considering reasonable baseline models and performing external validations of existing models. Hence, developed risk models must be made available for external researchers.

Development of risk models of incident hypertension using machine learning on the HUNT study data

In this study, we aimed to create an 11-year hypertension risk prediction model using data from the Trøndelag Health (HUNT) Study in Norway, involving 17 852 individuals (20-85 years; 38% male; 24% incidence rate) with blood pressure (BP) below the hypertension threshold at baseline (1995-1997). We assessed 18 clinical, behavioral, and socioeconomic features, employing machine learning models such as eXtreme Gradient Boosting (XGBoost), Elastic regression, K-Nearest Neighbor, Support Vector Machines (SVM) and Random Forest. For comparison, we used logistic regression and a decision rule as reference models and validated six external models, with focus on the Framingham risk model. The top-performing models consistently included XGBoost, Elastic regression and SVM. These models efficiently identified hypertension risk, even among individuals with optimal baseline BP (< 120/80 mmHg), although improvement over reference models was modest. The recalibrated Framingham risk model outperformed the reference models, approaching the best-performing ML models. Important features included age, systolic and diastolic BP, body mass index, height, and family history of hypertension. In conclusion, our study demonstrated that linear effects sufficed for a well-performing model. The best models efficiently predicted hypertension risk, even among those with optimal or normal baseline BP, using few features. The recalibrated Framingham risk model proved effective in our cohort.

A comparison of machine learning algorithms and traditional regression-based statistical modeling for predicting hypertension incidence in a Canadian population

Risk prediction models are frequently used to identify individuals at risk of developing hypertension. This study evaluates different machine learning algorithms and compares their predictive performance with the conventional Cox proportional hazards (PH) model to predict hypertension incidence using survival data. This study analyzed 18,322 participants on 24 candidate features from the large Alberta's Tomorrow Project (ATP) to develop different prediction models. To select the top features, we applied five feature selection methods, including two filter-based: a univariate Cox p-value and C-index; two embedded-based: random survival forest and least absolute shrinkage and selection operator (Lasso); and one constraint-based: the statistically equivalent signature (SES). Five machine learning algorithms were developed to predict hypertension incidence: penalized regression Ridge, Lasso, Elastic Net (EN), random survival forest (RSF), and gradient boosting (GB), along with the conventional Cox PH model. The predictive performance of the models was assessed using C-index. The performance of machine learning algorithms was observed, similar to the conventional Cox PH model. Average C-indexes were 0.78, 0.78, 0.78, 0.76, 0.76, and 0.77 for Ridge, Lasso, EN, RSF, GB and Cox PH, respectively. Important features associated with each model were also presented. Our study findings demonstrate little predictive performance difference between machine learning algorithms and the conventional Cox PH regression model in predicting hypertension incidence. In a moderate dataset with a reasonable number of features, conventional regression-based models perform similar to machine learning algorithms with good predictive accuracy.

Development and validation of a hypertension risk prediction model and construction of a risk score in a Canadian population

Identifying high-risk individuals for targeted intervention may prevent or delay hypertension onset. We developed a hypertension risk prediction model and subsequent risk sore among the Canadian population using measures readily available in a primary care setting. A Canadian cohort of 18,322 participants aged 35-69 years without hypertension at baseline was followed for hypertension incidence, and 625 new hypertension cases were reported. At a 2:1 ratio, the sample was randomly divided into derivation and validation sets. In the derivation sample, a Cox proportional hazard model was used to develop the model, and the model's performance was evaluated in the validation sample. Finally, a risk score table was created incorporating regression coefficients from the model. The multivariable Cox model identified age, body mass index, systolic blood pressure, diabetes, total physical activity time, and cardiovascular disease as significant risk factors (p < 0.05) of hypertension incidence. The variable sex was forced to enter the final model. Some interaction terms were identified as significant but were excluded due to their lack of incremental predictive capacity. Our model showed good discrimination (Harrel's C-statistic 0.77) and calibration (Grønnesby and Borgan test, [Formula: see text] statistic = 8.75, p = 0.07; calibration slope 1.006). A point-based score for the risks of developing hypertension was presented after 2-, 3-, 5-, and 6 years of observation. This simple, practical prediction score can reliably identify Canadian adults at high risk of developing incident hypertension in the primary care setting and facilitate discussions on modifying this risk most effectively.

Prediction of hypertension using traditional regression and machine learning models: A systematic review and meta-analysis

OBJECTIVE

We aimed to identify existing hypertension risk prediction models developed using traditional regression-based or machine learning approaches and compare their predictive performance.

METHODS

We systematically searched MEDLINE, EMBASE, Web of Science, Scopus, and the grey literature for studies predicting the risk of hypertension among the general adult population. Summary statistics from the individual studies were the C-statistic, and a random-effects meta-analysis was used to obtain pooled estimates. The predictive performance of pooled estimates was compared between traditional regression-based models and machine learning-based models. The potential sources of heterogeneity were assessed using meta-regression, and study quality was assessed using the PROBAST (Prediction model Risk Of Bias ASsessment Tool) checklist.

RESULTS

Of 14,778 articles, 52 articles were selected for systematic review and 32 for meta-analysis. The overall pooled C-statistics was 0.75 [0.73-0.77] for the traditional regression-based models and 0.76 [0.72-0.79] for the machine learning-based models. High heterogeneity in C-statistic was observed. The age (p = 0.011), and sex (p = 0.044) of the participants and the number of risk factors considered in the model (p = 0.001) were identified as a source of heterogeneity in traditional regression-based models.

CONCLUSION

We attempted to provide a comprehensive evaluation of hypertension risk prediction models. Many models with acceptable-to-good predictive performance were identified. Only a few models were externally validated, and the risk of bias and applicability was a concern in many studies. Overall discrimination was similar between models derived from traditional regression analysis and machine learning methods. More external validation and impact studies to implement the hypertension risk prediction model in clinical practice are required.

Development of a risk prediction score for hypertension incidence using Japanese health checkup data

Hypertension is a risk factor for cardiovascular disease. We developed a simple scoring method for predicting future hypertension using health checkup data. A total of 41,902 participants aged 30-69 years without baseline hypertension who underwent annual health checkups (mean age, 52.3 ± 10.2 years; male, 47.7%) were included. They were randomly assigned to derivation (n = 27,935) and validation cohorts (n = 13,967) at a ratio of 2:1. In the derivation cohort, we performed multivariable logistic regression analysis and assigned scores to each factor significantly associated with 5-year hypertension. We evaluated the predictive ability of the scores using area under the curve (AUC) analysis and then applied them to the validation cohort to assess their validity. The score including items requiring blood sampling ranged from 0 to 14 and included seven indicators (age, body mass index, blood pressure, current smoking, family history of hypertension, diabetes, and hyperuricemia). The score not including items requiring blood sampling ranged from 0 to 12 and included five indicators (the above indicators, except diabetes and hyperuricemia). The score not including items requiring blood sampling was better; blood sampling did not improve diagnostic ability. The AUC of the score not including items requiring blood sampling was 0.76, with a sensitivity and specificity of 0.82 and 0.60, respectively, for scores ≥6 points. The incidence of hypertension gradually and constantly increased (from 0.9 to 49.6%) as the score increased from 0 to ≥10. Analysis in the validation cohort yielded similar results. We developed a simple and useful clinical prediction model to predict the 5-year incidence of hypertension among a general Japanese population. The model had reasonably high predictive ability and reproducibility.

The Lifelong Health Support 10: a Japanese prescription for a long and healthy life

BACKGROUND

Although the age-adjusted incidence and mortality of cancer and cardiovascular disease (CVD) have been decreasing steadily in Japan, both diseases remain major contributors to morbidity and mortality along with the aging society. Herein, we aim to provide a prescription of 10 health tips for long and healthy life named the "Lifelong Health Support 10 (LHS10)."

METHOD

The LHS10 was developed by the preventive medicine specialists at the National Cerebral and Cardiovascular Center in Suita, where it has been used for health guidance to prevent CVD, cancer, and cognitive decline in addition to their major risk factors such as hypertension, diabetes, and obesity. It consisted of the lifestyle modification recommendations of the 2014 Japanese Society of Hypertension guidelines and the 2017 Japan Atherosclerosis Society Guidelines for preventing atherosclerotic CVD. Further, it came in line with other international lifestyle modification guidelines. In this narrative review, we summarized the results of several Japanese epidemiological studies investigating the association between the LHS10 items and the risk of cancer, CVD, and other chronic diseases including dementia, diabetes, and chronic kidney disease.

RESULTS

The LHS10 included avoiding smoking and secondhand smoke exposure, engaging in physical activity, refraining from excessive alcohol drinking, reducing fried foods and sugary soft drinks, cutting salt in food, consuming more vegetables, fruits, fish, soy foods, and fibers, and maintaining proper body weight. All items of the LHS10 were shown to reduce the risk of cancer, CVD, and other chronic diseases.

CONCLUSIONS

The LHS10 can be a helpful tool for health guidance.

The relationship between lipid risk score and new-onset hypertension in a prospective cohort study

BACKGROUND

Dyslipidemia and hypertension are both important risk factors for atherosclerotic cardiovascular diseases. However, the relationship between dyslipidemia and incident hypertension remains to be elucidated comprehensively. The main purpose of this study was to construct the lipid risk score to explore the risk prediction effect of integrated lipid indices on new-onset hypertension.

METHODS

This prospective cohort study with 2116 non-hypertensive subjects was conducted from 2009 to 2020. New hypertension events during the follow-up period were recorded and verified. The lipid risk score was calculated by summing coded total cholesterol, triglyceride, low-density lipoprotein cholesterol, and high-density lipoprotein cholesterol weighted with corresponding effect sizes. Cox regression analysis was used to estimate the association between the lipid risk score or lipid indices and incident hypertension in the subgroup of age (< 55 and≥ 55 years at baseline).

RESULTS

After a median of 10.75-year follow-up, 637 incident hypertension cases were identified. The restricted cubic spline showed that the lipid risk score had a positive linear correlation with hypertension (P< 0.001). Among people< 55 years, with every increase of 0.94 in lipid risk score, the risk of hypertension increased by 37% (adjusted HR [95%CI]: 1.369 [1.164-1.610]). This association was not modified by overweight or obesity.

CONCLUSIONS

The integrated lipid risk score, independent of traditional risk factors, has a significantly predictive effect on hypertension in people younger than 55 years. This finding may aid in identifying high-risk individuals for hypertension, as well as facilitating early intervention and management to reduce adverse cardiovascular events. Comprehensive lipid management should be attached importance in the prevention and control of hypertension.