# Prevalence and prediction of masked uncontrolled hypertension in patients recently hospitalized for myocardial infarction

## TL;DR

This study finds that one in five patients recently hospitalized for heart attacks have a hidden blood pressure issue called masked uncontrolled hypertension.

## Contribution

The study introduces machine learning models to predict masked uncontrolled hypertension using clinical variables like diabetes and kidney dysfunction.

## Key findings

- 33% of patients had elevated 24-hour blood pressure despite normal office readings.
- Diabetes, hypertension, and kidney dysfunction were top predictors of masked uncontrolled hypertension.
- Machine learning models achieved an AUC of up to 0.82 in predicting the condition.

## Abstract

To study the prevalence of masked uncontrolled hypertension (MUCH) in patients recently hospitalized for myocardial infarction, and to develop machine learning-based prediction models identifying MUCH.

Ambulatory blood pressure measurement (ABPM) was performed in 99 patients following hospitalization for a myocardial infarction. Sixty-two clinical variables were eligible for machine learning. Variable importance for the prediction of MUCH (office blood pressure <140/90 mm Hg at ABPM start but mean 24-h blood pressure ≥130/80 mm Hg) was assessed using the least absolute shrinkage and selection operator (LASSO) and the Boruta algorithms. Logistic regression, LASSO, and random forest models based on the top variables were evaluated using receiver operating characteristic area under the curve (AUC) in repeated cross-validation. Mean age was 62.1 ± 8.2 years, 73 (74%) were males. The ABPM was performed at a median of 11 weeks after discharge. Among 96 patients with valid 24-h ABPM recordings, 32 (33%) had 24-h mean blood pressure ≥130/80 mm Hg and 17 (18%) were identified with MUCH. Machine learning identified discharge diagnoses of diabetes and hypertension, and kidney dysfunction as most important predictors of MUCH. The best random forest, logistic regression, and LASSO models showed mean AUC 0.82, 0.80, and 0.80, respectively, for prediction of MUCH.

One in five patients had MUCH at follow-up after a myocardial infarction. The readily available variables diabetes, hypertension, and kidney dysfunction were identified as the most important predictors of MUCH, which may be implemented in a prediction model for identifying this clinically challenging blood pressure phenotype.

Preliminary results were presented at the European Society of Cardiology Congress in London 2024 as an oral abstract presentation. Hellqvist H, Erlinge D, Lindahl B, et al. Prevalence and prediction of masked uncontrolled hypertension in patients recently hospitalised for an acute coronary syndrome. European Heart Journal 2024;45 (Suppl 1). doi: 10.1093/eurheartj/ehae666.2566

Graphical Abstract