Identification of Hypertension Predictors and Application to Hypertension Prediction in an Urban Han Chinese Population: A Longitudinal Study, 2005-2010

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.

Establishment and evaluation of a risk-prediction model for hypertension in elderly patients with NAFLD from a health management perspective

Elderly patients with nonalcoholic fatty liver disease are at a higher risk of developing. This study established an effective, individualised, early Hypertension risk-prediction model and proposed health management advice for patients over 60 years of age with NAFLD. Questionnaire surveys, physical examinations, and biochemical tests were conducted in 11,136 participants. The prevalence of NAFLD among 11,136 participants was 52.1%. Risk factors were screened using the least absolute shrinkage and selection operator model and random forest model. A risk-prediction model was established using logistic regression analysis and a dynamic nomogram was drawn. The model was evaluated for discrimination, calibration, and clinical applicability using receiver operating characteristic curves, calibration curves, decision curve analysis, net reclassification index (NRI), and external validation. The results suggested that the model showed moderate predictive ability. The area under curve (AUC) of internal validation was 0.707 (95% CI: 0.688-0.727) and the AUC of external validation was 0.688 (95% CI: 0.672-0.705). The calibration plots showed good calibration, the risk threshold of the decision curve was 30-56%, and the NRI value was 0.109. This Hypertension risk factor model may be used in clinical practice to predict the Hypertension risk in NAFLD patients.

Multistate Markov model application for blood pressure transition among the Chinese elderly population: a quantitative longitudinal study

OBJECTIVE

To explore the transitions of different blood pressure states based on a multistate Markov model among the Chinese elderly population.

SETTING

A community health centre in Xiamen, China.

PARTICIPANTS

1833 elderly Chinese people.

METHODS

A multistate Markov model was built based on 5001 blood pressure measurements from 2015 to 2020. Research was conducted to explore the process of hypertension progression, providing information on the transition probability, HR and the mean sojourn time in three blood pressure states, namely normal state, elevated state and hypertensive state.

RESULTS

Probabilities of moving from the normal state to the hypertensive state in the first year were 16.97% (female) and 21.73% (male); they increased dramatically to 47.31% (female) and 51.70% (male) within a 3-year follow-up period. The sojourn time in the normal state was 1.5±0.08 years. Elderly women in the normal state had a 16.97%, 33.30% and 47.31% chance of progressing to hypertension within 1, 2 and 3 years, respectively. The corresponding probabilities for elderly men were 21.73%, 38.56% and 51.70%, respectively. For elderly women starting in the elevated state, the probabilities of developing hypertension were 25.07%, 43.03% and 56.32% in the next 1, 2 and 3 years, respectively; while the corresponding changes for elderly men were 20.96%, 37.65% and 50.86%. Increasing age, body mass index (BMI) and glucose were associated with the probability of developing hypertension from the normal state or elevated state.

CONCLUSIONS

Preventive actions against progression to hypertension should be conducted at an early stage. More awareness should be paid to elderly women with elevated state and elderly men with normal state. Increasing age, BMI and glucose were critical risk factors for developing hypertension. The derived transition probabilities and sojourn time can serve as a significant reference for making targeted interventions for hypertension progression among the Chinese elderly population.

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 the Hypertension Index Model in General Adult Using the Korea National Health and Nutritional Examination Survey and the Korean Genome and Epidemiology Study

Hypertension, a risk factor for cardiovascular disease and all-cause mortality, has been increasing. Along with emphasizing awareness and control of hypertension, predicting the incidence of hypertension is important. Several studies have previously reported prediction models of hypertension. However, among the previous models for predicting hypertension, few models reflect various risk factors for hypertension. We constructed a sex-specific prediction model using Korean datasets, which included socioeconomic status, medical history, lifestyle-related variables, anthropometric status, and laboratory indices. We utilized the data from the Korea National Health and Nutrition Examination Survey from 2011 to 2015 to derive a hypertension prediction model. Participants aged 40 years or older. We constructed a sex-specific hypertension classification model using logistic regression and features obtained by literature review and statistical analysis. We constructed a sex-specific hypertension classification model including approximately 20 variables. We estimated its performance using the Korea National Health and Nutrition Examination Survey dataset from 2016 to 2018 (AUC = 0.847 in men, AUC = 0.901 in women). The performance of our hypertension model was considered significant based on the cumulative incidence calculated from a longitudinal dataset, the Korean Genome and Epidemiology Study dataset. We developed this hypertension prediction model using features that could be collected in a clinical office without difficulty. Individualized results may alert a person at high risk to modify unhealthy lifestyles.

Validation of the Framingham hypertension risk score in a middle eastern population: Tehran lipid and glucose study (TLGS)

Background

The Framingham hypertension risk score is a well-known and simple model for predicting hypertension in adults. In the current study, we aimed to assess the predictive ability of this model in a Middle Eastern population.

Methods

We studied 5423 participants, aged 20–69 years, without hypertension, who participated in two consecutive examination cycles of the Tehran Lipid and Glucose Study (TLGS). We assessed discrimination based on Harrell’s concordance statistic (c-index) and calibration (graphical comparison of predicted vs. observed). We evaluated the original, recalibrated (for intercept and slope), and revised (for beta coefficients) models.

Results

Over the 3-year follow-up period, 319 participants developed hypertension. The Framingham hypertension risk score performed well in discriminating between individuals who developed hypertension and those who did not (c-index = 0.81, 95% CI: 0.79–0.83). Initially, there was a systematic underestimation of the original risk score (events predicted), which was readily corrected by a simple model revision.

Conclusions

The revised Framingham hypertension risk score can be used as a screening tool in public health and clinical practice to facilitate the targeting of preventive interventions in high-risk Middle Eastern people.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12889-021-10760-6.

Blood Pressure States Transition Inference Based on Multi-State Markov Model

The investigation of risk factors associated with hypertension patients has been extensively studied in the past decades. However, the pattern of natural progressive trajectories to hypertension from nonhypertensive states was rarely explored. In this study, we are interested in discovering the underlying transition patterns between different blood pressure states, namely normal state, elevated state, and hypertensive state among the working population in the United States. A multi-state Markov model was built based on 88,966 clinical records from 34,719 participants we collected during the worksite preventive screening from 2012 to 2018. We first investigated the various risk factors, and we found that body mass index (BMI) is the most critical factor for developing new-onset hypertension. The transition probabilities, survival probabilities, and sojourn time of each state were derived given different levels of BMI, age groups, and gender categories. We found the underweight participants are more likely to remain in the current nonhypertensive states within 3 years, while extremely obese participants have a higher probability of developing hypertension. We discovered the distinct transition patterns among male and female participants. On average, the sojourn time in the normal state for normal-weight participants is 4.33 years for females and 2.18 years for their male counterparts. For the extremely obese participants, the average sojourn time in the normal state is 1.38 years for females and 0.71 years for males. In the end, a web-based graphical user interface (GUI) application was developed for clinicians to visualize the impact of behavioral interventions on delaying the progression of hypertension. Our analysis can provide a unique insight into hypertension research and proactive interventions.

A novel predicted model for hypertension based on a large cross-sectional study

Hypertension is a global public health issue and leading risk for death and disability. It is urgent to search novel methods predicting hypertension. Herein, we chose 73158 samples of physical examiners in central China from June 2008 to June 2018. After strict exclusion processes, 33570 participants with hypertension and 35410 healthy controls were included. We randomly chose 70% samples as the train set and the remaining 30% as the test set. Clinical parameters including age, gender, height, weight, body mass index, triglyceride, total cholesterol, low-density lipoprotein, blood urea nitrogen, uric acid, and creatinine were significantly increased, while high-density lipoprotein was decreased in the hypertension group versus controls. Nine optimal markers were identified by a logistic regression model, and achieved AUC value of 76.52% in the train set and 75.81% in the test set for hypertension. In conclusions, this study is the first to establish predicted models for hypertension using the logistic regression model in Central China, which provide risk factors and novel prediction method to predict and prevent hypertension.

Personalized medicine-a modern approach for the diagnosis and management of hypertension

The main goal of treating hypertension is to reduce blood pressure to physiological levels and thereby prevent risk of cardiovascular disease and hypertension-associated target organ damage. Despite reductions in major risk factors and the availability of a plethora of effective antihypertensive drugs, the control of blood pressure to target values is still poor due to multiple factors including apparent drug resistance and lack of adherence. An explanation for this problem is related to the current reductionist and ‘trial-and-error’ approach in the management of hypertension, as we may oversimplify the complex nature of the disease and not pay enough attention to the heterogeneity of the pathophysiology and clinical presentation of the disorder. Taking into account specific risk factors, genetic phenotype, pharmacokinetic characteristics, and other particular features unique to each patient, would allow a personalized approach to managing the disease. Personalized medicine therefore represents the tailoring of medical approach and treatment to the individual characteristics of each patient and is expected to become the paradigm of future healthcare. The advancement of systems biology research and the rapid development of high-throughput technologies, as well as the characterization of different –omics, have contributed to a shift in modern biological and medical research from traditional hypothesis-driven designs toward data-driven studies and have facilitated the evolution of personalized or precision medicine for chronic diseases such as hypertension.

Recent development of risk-prediction models for incident hypertension: An updated systematic review

BACKGROUND

Hypertension is a leading global health threat and a major cardiovascular disease. Since clinical interventions are effective in delaying the disease progression from prehypertension to hypertension, diagnostic prediction models to identify patient populations at high risk for hypertension are imperative.

METHODS

Both PubMed and Embase databases were searched for eligible reports of either prediction models or risk scores of hypertension. The study data were collected, including risk factors, statistic methods, characteristics of study design and participants, performance measurement, etc.

RESULTS

From the searched literature, 26 studies reporting 48 prediction models were selected. Among them, 20 reports studied the established models using traditional risk factors, such as body mass index (BMI), age, smoking, blood pressure (BP) level, parental history of hypertension, and biochemical factors, whereas 6 reports used genetic risk score (GRS) as the prediction factor. AUC ranged from 0.64 to 0.97, and C-statistic ranged from 60% to 90%.

CONCLUSIONS

The traditional models are still the predominant risk prediction models for hypertension, but recently, more models have begun to incorporate genetic factors as part of their model predictors. However, these genetic predictors need to be well selected. The current reported models have acceptable to good discrimination and calibration ability, but whether the models can be applied in clinical practice still needs more validation and adjustment.

Use of Biomarkers in the Evaluation and Treatment of Hypertensive Patients

The current definition of hypertension is based on blood pressure values, and blood pressure also drives treatment decisions, is the most important treatment monitoring tool and helps estimating risk of hypertension-related organ damage. In an era of precision medicine, additional biomarkers are needed in the diagnosis and management of patients with hypertension. In this review, we outline the areas in which functional, imaging and circulating biomarkers could help in a more individualised definition of hypertension and associated risk. We will cover biomarkers for diagnosis; of pathophysiology and prediction of hypertension; response to treatment, organ damage; and to monitor treatment. A clear focus is on the vasculature, the heart and the kidneys, whereas we see a need to further develop biomarkers of cerebral function in order to diagnose cognition deficits and monitor changes in cognition in the future to support addressing the growing burden of hypertension-associated vascular dementia.

Toward Precision Healthcare: Context and Mathematical Challenges

Precision medicine refers to the idea of delivering the right treatment to the right patient at the right time, usually with a focus on a data-centered approach to this task. In this perspective piece, we use the term "precision healthcare" to describe the development of precision approaches that bridge from the individual to the population, taking advantage of individual-level data, but also taking the social context into account. These problems give rise to a broad spectrum of technical, scientific, policy, ethical and social challenges, and new mathematical techniques will be required to meet them. To ensure that the science underpinning "precision" is robust, interpretable and well-suited to meet the policy, ethical and social questions that such approaches raise, the mathematical methods for data analysis should be transparent, robust, and able to adapt to errors and uncertainties. In particular, precision methodologies should capture the complexity of data, yet produce tractable descriptions at the relevant resolution while preserving intelligibility and traceability, so that they can be used by practitioners to aid decision-making. Through several case studies in this domain of precision healthcare, we argue that this vision requires the development of new mathematical frameworks, both in modeling and in data analysis and interpretation.

Precision medicine in cardiology

The cardiovascular research and clinical communities are ideally positioned to address the epidemic of noncommunicable causes of death, as well as advance our understanding of human health and disease, through the development and implementation of precision medicine. New tools will be needed for describing the cardiovascular health status of individuals and populations, including 'omic' data, exposome and social determinants of health, the microbiome, behaviours and motivations, patient-generated data, and the array of data in electronic medical records. Cardiovascular specialists can build on their experience and use precision medicine to facilitate discovery science and improve the efficiency of clinical research, with the goal of providing more precise information to improve the health of individuals and populations. Overcoming the barriers to implementing precision medicine will require addressing a range of technical and sociopolitical issues. Health care under precision medicine will become a more integrated, dynamic system, in which patients are no longer a passive entity on whom measurements are made, but instead are central stakeholders who contribute data and participate actively in shared decision-making. Many traditionally defined diseases have common mechanisms; therefore, elimination of a siloed approach to medicine will ultimately pave the path to the creation of a universal precision medicine environment.