Related Experiment Video
Updated: Jun 27, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Artificial Intelligence-Derived Risk Prediction: A Novel Risk Calculator Using Office and Ambulatory Blood Pressure
Pedro Guimarães1,2, Andreas Keller1,3, Michael Böhm4
1Chair for Clinical Bioinformatics, Saarland University, Saarbrücken, Germany (P.G., A.K., T.F.).
Insights
A new machine learning model accurately predicts cardiovascular mortality risk using blood pressure data. Ambulatory blood pressure measurements significantly improved prediction accuracy compared to office blood pressure, outperforming existing risk scores.
Area of Science:
- Cardiovascular disease risk prediction
- Machine learning in healthcare
- Hypertension management
Background:
- Accurate cardiovascular risk quantification is crucial for personalized hypertension treatment.
- Existing risk scores may not fully capture individual patient risk.
- Novel predictive models are needed to improve cardiovascular event prediction.
Purpose of the Study:
- To develop and validate a machine learning model for predicting cardiovascular mortality risk.
- To compare the novel model's performance against established risk scores.
- To assess the utility of clinical variables in predicting ambulatory blood pressure phenotypes.
Main Methods:
- Utilized a large dataset (59,124 patients) from the Spanish Ambulatory Blood Pressure Monitoring registry.
- Applied machine learning techniques including logistic regression, gradient-boosted decision trees, and deep neural networks.
- Employed stepwise forward feature selection to identify key predictive variables.
Main Results:
- Deep neural networks achieved the highest performance in predicting cardiovascular mortality.
- The novel model, using both office blood pressure (OBP) and ambulatory blood pressure (ABP), outperformed existing risk scores (Framingham, SCORE2, ASCVD).
- ABP-based prediction significantly increased the area under the curve (AUC) compared to OBP (0.870 vs. 0.865), enhancing accuracy and specificity.
Conclusions:
- Machine learning models, particularly deep neural networks, show significant potential for improving cardiovascular risk prediction.
- Utilizing ambulatory blood pressure data substantially enhances the accuracy of cardiovascular mortality prediction over office blood pressure.
- The developed model offers a promising advancement for individualizing hypertension treatment and cardiovascular risk assessment.
Background:
Quantification of total cardiovascular risk is essential for individualizing hypertension treatment. This study aimed to develop and validate a novel, machine-learning-derived model to predict cardiovascular mortality risk using office blood pressure (OBP) and ambulatory blood pressure (ABP).
Methods:
The performance of the novel risk score was compared with existing risk scores, and the possibility of predicting ABP phenotypes utilizing clinical variables was assessed. Using data from 59 124 patients enrolled in the Spanish ABP Monitoring registry, machine-learning approaches (logistic regression, gradient-boosted decision trees, and deep neural networks) and stepwise forward feature selection were used.
Results:
For the prediction of cardiovascular mortality, deep neural networks yielded the highest clinical performance. The novel mortality prediction models using OBP and ABP outperformed other risk scores. The area under the curve achieved by the novel approach, already when using OBP variables, was significantly higher when compared with the area under the curve of the Framingham risk score, Systemic Coronary Risk Estimation 2, and Atherosclerotic Cardiovascular Disease score. However, the prediction of cardiovascular mortality with ABP instead of OBP data significantly increased the area under the curve (0.870 versus 0.865; P=3.61×10-28), accuracy, and specificity, respectively. The prediction of ABP phenotypes (ie, white-coat, ambulatory, and masked hypertension) using clinical characteristics was limited.
Conclusions:
The receiver operating characteristic curves for cardiovascular mortality using ABP and OBP with deep neural network models outperformed all other risk metrics, indicating the potential for improving current risk scores by applying state-of-the-art machine learning approaches. The prediction of cardiovascular mortality using ABP data led to a significant increase in area under the curve and performance metrics.
Related Concept Videos
01:10Pre-Procedural Guidelines for Assessing Blood Pressure
01:25Errors occurring during blood pressure monitoring
Several factors...
01:23Assessment of blood pressure in brachial artery(two-step method)
01:15Assessment of blood pressure in brachial artery(one-step method)
Prepare for the Procedure:
01:28Special considerations while measuring blood pressure
Monitoring Both Arms:
Monitoring BP in both arms during the initial assessment is advisable, as the systolic value may differ by five to ten mm Hg between arms. For subsequent BP assessments, use the arm with the higher reading.
01:17Measurement of Blood Pressure