What question did this study set out to answer?

To explore the feasibility of predicting blood pressure using machine learning models based on cardiovascular disease risk factors and demographic data.

January 14, 2026ElectronicsOpen Access

Machine Learning-Based Blood Pressure Prediction Using Cardiovascular Disease Data: A Comprehensive Comparative Study

View Full Paper

Ask AI

Bookmark

To explore the feasibility of predicting blood pressure using machine learning models based on cardiovascular disease risk factors and demographic data.
Analyzed data from 68,616 individuals sourced from Kaggle's cardiovascular disease repository.
Engineered additional features related to demographics, body composition, and clinical indicators.
Evaluated nine predictive models, including CatBoost, for blood pressure forecasting.
CatBoost achieved RMSE of 14.37 mmHg for systolic and 8.57 mmHg for diastolic blood pressure predictions.
Observed modest explained variance, with R2 values of 0.265 for systolic and 0.187 for diastolic pressure.
Standard clinical variables explained only about a quarter of blood pressure variance.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Comparative analysis reveals machine learning models predict blood pressure in hypertension, indicating limits of routine clinical data.

Cite This Study

Naskinova et al. (2026) studied this question.

synapsesocial.com/papers/6966f2f013bf7a6f02c003fc https://doi.org/10.3390/electronics15020312

View Full Paper

Ask AI

Bookmark

Machine Learning-Based Blood Pressure Prediction Using Cardiovascular Disease Data: A Comprehensive Comparative Study

Key Points

Discussion

Implication

Cite This Study

Machine Learning-Based Blood Pressure Prediction Using Cardiovascular Disease Data: A Comprehensive Comparative Study

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider