Development and validation of prediction models for hypertension risks in rural Chinese populations

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.

Survey and Evaluation of Hypertension Machine Learning Research

Background Machine learning (ML) is pervasive in all fields of research, from automating tasks to complex decision-making. However, applications in different specialities are variable and generally limited. Like other conditions, the number of studies employing ML in hypertension research is growing rapidly. In this study, we aimed to survey hypertension research using ML, evaluate the reporting quality, and identify barriers to ML's potential to transform hypertension care. Methods and Results The Harmonious Understanding of Machine Learning Analytics Network survey questionnaire was applied to 63 hypertension-related ML research articles published between January 2019 and September 2021. The most common research topics were blood pressure prediction (38%), hypertension (22%), cardiovascular outcomes (6%), blood pressure variability (5%), treatment response (5%), and real-time blood pressure estimation (5%). The reporting quality of the articles was variable. Only 46% of articles described the study population or derivation cohort. Most articles (81%) reported at least 1 performance measure, but only 40% presented any measures of calibration. Compliance with ethics, patient privacy, and data security regulations were mentioned in 30 (48%) of the articles. Only 14% used geographically or temporally distinct validation data sets. Algorithmic bias was not addressed in any of the articles, with only 6 of them acknowledging risk of bias. Conclusions Recent ML research on hypertension is limited to exploratory research and has significant shortcomings in reporting quality, model validation, and algorithmic bias. Our analysis identifies areas for improvement that will help pave the way for the realization of the potential of ML in hypertension and facilitate its adoption.

Machine Learning for Hypertension Prediction: a Systematic Review

PURPOSE OF REVIEW

To provide an overview of the literature regarding the use of machine learning algorithms to predict hypertension. A systematic review was performed to select recent articles on the subject.

RECENT FINDINGS

The screening of the articles was conducted using a machine learning algorithm (ASReview). A total of 21 articles published between January 2018 and May 2021 were identified and compared according to variable selection, train-test split, data balancing, outcome definition, final algorithm, and performance metrics. Overall, the articles achieved an area under the ROC curve (AUROC) between 0.766 and 1.00. The algorithms most frequently identified as having the best performance were support vector machines (SVM), extreme gradient boosting (XGBoost), and random forest. Machine learning algorithms are a promising tool to improve preventive clinical decisions and targeted public health policies for hypertension. However, technical factors such as outcome definition, availability of the final code, predictive performance, explainability, and data leakage need to be consistently and critically evaluated.

Evaluating the risk of hypertension in residents in primary care in Shanghai, China with machine learning algorithms

Objective

The prevention of hypertension in primary care requires an effective and suitable hypertension risk assessment model. The aim of this study was to develop and compare the performances of three machine learning algorithms in predicting the risk of hypertension for residents in primary care in Shanghai, China.

Methods

A dataset of 40,261 subjects over the age of 35 years was extracted from Electronic Healthcare Records of 47 community health centers from 2017 to 2019 in the Pudong district of Shanghai. Embedded methods were applied for feature selection. Machine learning algorithms, XGBoost, random forest, and logistic regression analyses were adopted in the process of model construction. The performance of models was evaluated by calculating the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, accuracy and F1-score.

Results

The XGBoost model outperformed the other two models and achieved an AUC of 0.765 in the testing set. Twenty features were selected to construct the model, including age, diabetes status, urinary protein level, BMI, elderly health self-assessment, creatinine level, systolic blood pressure measured on the upper right arm, waist circumference, smoking status, low-density lipoprotein cholesterol level, high-density lipoprotein cholesterol level, frequency of drinking, glucose level, urea nitrogen level, total cholesterol level, diastolic blood pressure measured on the upper right arm, exercise frequency, time spent engaged in exercise, high salt consumption, and triglyceride level.

Conclusions

XGBoost outperformed random forest and logistic regression in predicting the risk of hypertension in primary care. The integration of this risk assessment model into primary care facilities may improve the prevention and management of hypertension in residents.

Development and validation of prediction models for hypertension risks: A cross-sectional study based on 4,287,407 participants

Objective

To develop an optimal screening model to identify the individuals with a high risk of hypertension in China by comparing tree-based machine learning models, such as classification and regression tree, random forest, adaboost with a decision tree, extreme gradient boosting decision tree, and other machine learning models like an artificial neural network, naive Bayes, and traditional logistic regression models.

Methods

A total of 4,287,407 adults participating in the national physical examination were included in the study. Features were selected using the least absolute shrinkage and selection operator regression. The Borderline synthetic minority over-sampling technique was used for data balance. Non-laboratory and semi-laboratory analyses were carried out in combination with the selected features. The tree-based machine learning models, other machine learning models, and traditional logistic regression models were constructed to identify individuals with hypertension, respectively. Top features selected using the best algorithm and the corresponding variable importance score were visualized.

Results

A total of 24 variables were finally included for analyses after the least absolute shrinkage and selection operator regression model. The sample size of hypertensive patients in the training set was expanded from 689,025 to 2,312,160 using the borderline synthetic minority over-sampling technique algorithm. The extreme gradient boosting decision tree algorithm showed the best results (area under the receiver operating characteristic curve of non-laboratory: 0.893 and area under the receiver operating characteristic curve of semi-laboratory: 0.894). This study found that age, systolic blood pressure, waist circumference, diastolic blood pressure, albumin, drinking frequency, electrocardiogram, ethnicity (uyghur, hui, and other), body mass index, sex (female), exercise frequency, diabetes mellitus, and total bilirubin are important factors reflecting hypertension. Besides, some algorithms included in the semi-laboratory analyses showed less improvement in the predictive performance compared to the non-laboratory analyses.

Conclusion

Using multiple methods, a more significant prediction model can be built, which discovers risk factors and provides new insights into the prediction and prevention of hypertension.

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.

A risk scoring system to predict the risk of new-onset hypertension among patients with type 2 diabetes

Hypertension (HTN), which frequently co‐exists with diabetes mellitus, is the leading major cause of cardiovascular disease and death globally. This study aimed to develop and validate a risk scoring system considering the effects of glycemic and blood pressure (BP) variabilities to predict HTN incidence in patients with type 2 diabetes. This research is a retrospective cohort study that included 3416 patients with type 2 diabetes without HTN and who were enrolled in a managed care program in 2001–2015. The patients were followed up until April 2016, new‐onset HTN event, or death. HTN was defined as diastolic BP (DBP) ≥ 90 mm Hg, systolic BP (SBP) ≥ 140 mm Hg, or the initiation of antihypertensive medication. Cox proportional hazard regression model was used to develop the risk scoring system for HTN. Of the patients, 1738 experienced new‐onset HTN during an average follow‐up period of 3.40 years. Age, sex, physical activity, body mass index, type of DM treatment, family history of HTN, baseline SBP and DBP, variabilities of fasting plasma glucose, SBP, and DBP and macroalbuminuria were significant variables for the prediction of new‐onset HTN. Using these predictors, the prediction models for 1‐, 3‐, and 5‐year periods demonstrated good discrimination, with AUC values of 0.70–0.76. Our HTN scoring system for patients with type 2 DM, which involves innovative predictors of glycemic and BP variabilities, has good classification accuracy and identifies risk factors available in clinical settings for prevention of the progression to new‐onset HTN.

Development of a risk prediction model for incident hypertension in Japanese individuals: the Hisayama Study

The identification of individuals at high risk of developing hypertension can be of great value to improve the efficiency of primary prevention strategies for hypertension. The objective of this study was to develop a risk prediction model for incident hypertension based on prospective longitudinal data from a general Japanese population. A total of 982 subjects aged 40-59 years without hypertension at baseline were followed up for 10 years (2002-12) for the incidence of hypertension. Hypertension was defined as systolic blood pressure (SBP) ≥ 140 mmHg, diastolic blood pressure (DBP) ≥ 90 mmHg, or the use of antihypertensive agents. The risk prediction model was developed using a Cox proportional hazards model. A simple risk scoring system was also established based on the developed model. During the follow-up period (median 10 years, interquartile range 5-10 years), 302 subjects (120 men and 182 women) developed new-onset hypertension. The risk prediction model for hypertension consisted of age, sex, SBP, DBP, use of glucose-lowering agents, body mass index (BMI), parental history of hypertension, moderate-to-high alcohol intake, and the interaction between age and BMI. The developed model demonstrated good discrimination (Harrell's C statistic=0.812 [95% confidence interval, 0.791-0.834]; optimism-corrected C statistic based on 200 bootstrap samples=0.804) and calibration (Greenwood-Nam-D'Agostino χ² statistic=12.2). This risk prediction model is a useful guide for estimating an individual's absolute risk for hypertension and could facilitate the management of Japanese individuals at high risk of developing hypertension in the future.

Development and validation of a nomogram to better predict hypertension based on a 10-year retrospective cohort study in China

Background

Hypertension is a highly prevalent disorder. A nomogram to estimate the risk of hypertension in Chinese individuals is not available.

Methods

6201 subjects were enrolled in the study and randomly divided into training set and validation set at a ratio of 2:1. The LASSO regression technique was used to select the optimal predictive features, and multivariate logistic regression to construct the nomograms. The performance of the nomograms was assessed and validated by AUC, C-index, calibration curves, DCA, clinical impact curves, NRI, and IDI.

Results

The nomogram^140/90 was developed with the parameters of family history of hypertension, age, SBP, DBP, BMI, MCHC, MPV, TBIL, and TG. AUCs of nomogram^140/90 were 0.750 in the training set and 0.772 in the validation set. C-index of nomogram^140/90 were 0.750 in the training set and 0.772 in the validation set. The nomogram^130/80 was developed with the parameters of family history of hypertension, age, SBP, DBP, RDWSD, and TBIL. AUCs of nomogram^130/80 were 0.705 in the training set and 0.697 in the validation set. C-index of nomogram^130/80 were 0.705 in the training set and 0.697 in the validation set. Both nomograms demonstrated favorable clinical consistency. NRI and IDI showed that the nomogram^140/90 exhibited superior performance than the nomogram^130/80. Therefore, the web-based calculator of nomogram^140/90 was built online.

Conclusions

We have constructed a nomogram that can be effectively used in the preliminary and in-depth risk prediction of hypertension in a Chinese population based on a 10-year retrospective cohort study.

Funding

This study was supported by the Hebei Science and Technology Department Program (no. H2018206110).

Development of the prediction model for hypertension in patients with idiopathic inflammatory myopathies

Cardiac involvement is an important cause of morbidity and mortality in patients with idiopathic inflammatory myopathies (IIMs). Hypertension, an important cardiovascular risk factor for the general population, has a crucial role in heart involvement. However, few studies have focused on the hypertension associated with IIMs. This study aimed to develop and assess the prediction model for incident hypertension in patients with IIMs. A retrospective cohort study was performed on 362 patients with IIMs, of whom 54 (14.9%) were given a diagnosis of new-onset hypertension from January 2008 to December 2018. The predictors of hypertension in IIMs were selected by least absolute shrinkage and selection operator (LASSO) regression, multivariable logistic regression, and clinically relevance, and then these predictors were used to draw the nomogram. Discrimination, calibration and clinical usefulness of the model were evaluated using the C-index, calibration plot, and decision curve analysis, respectively. The predicting model was validated by the bootstrapping validation. The nomogram mainly included predictors such as age, diabetes mellitus, triglyceride, low-density lipoprotein-cholesterol (LDL-C), antinuclear antibodies (ANA), and smoking. This prediction model demonstrated good discrimination with a C-index of 0.754 (95%CI, 0.684 to 0.824) and good calibration. The C-index of internal validation was 0.728, and decision curve analysis demonstrated that this nomogram was clinically useful. Clinicians can use this prediction model to assess the risk of hypertension in IIMs patients, and early preventive measures should be taken to reduce the incidence of hypertension in high-risk patients.