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

Abstract

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, $$\chi^{2}$$ χ 2 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.

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

“…We compiled a list of available potential candidate features before launching the analysis. We determined the possible candidate features for model development based on a literature search 9 , features used in the past 45 , and discussion with content experts. We initially considered 24 candidate features for the model development process.…”

“…Various models have been developed that mathematically combine multiple risk factors to estimate the risk of hypertension in asymptomatic subjects in the population 9 . The regression-based methodologies, such as logistic regression and Cox regression, are the conventional approach for developing prediction models 10 , 11 . Machine learning algorithms recently emerged as a popular modeling approach that offers an alternative class of models with more computational flexibility 12 .…”

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

“…Simultaneously, a thorough development of a new risk model will likely produce a best-case scenario performance-wise, which could serve as context for the external validation. Lastly, we note that four of the included studies validated multiple models [ 30 , 43 , 69 , 74 ].…”

Predicting the risk of hypertension using machine learning algorithms: A cross sectional study in Ethiopia

“…Nevertheless, existing association studies had several limitations. Most importantly, previous existing studies considered traditional linear models, such as logistic regression (LR), Cox proportional hazard model, for identifying the significantly associated risk factors of HTN [22][23][24]. Moreover, a real data with high-dimensional non-linear pattern presents a challenge to traditional linear models, and low precision of linear models impedes patients-level use.…”