# Comparative machine learning models for hypertension prediction in a cohort of patients with diabetes using routine clinical variables

## TL;DR

This study compares machine learning models to predict hypertension in diabetic patients using common clinical data like BMI and age.

## Contribution

The study evaluates and compares various machine learning models for hypertension prediction in diabetic patients using routine clinical variables.

## Key findings

- A neural network model achieved the best performance with an area under the curve of 0.689 and high recall of 98.8%.
- Age and body mass index were identified as the top predictors of hypertension in diabetic patients.
- Gradient boosting models performed similarly to the neural network in terms of predictive accuracy.

## Abstract

To evaluate and to compare machine learning models for predicting
hypertension in patients with diabetes using routine clinical variables.

Using Behavioral Risk Factor Surveillance System data, models were trained on
35,346 individuals with seven variables (“HighChol”, “BMI”, “Smoker”,
“PhysActivity”, “Sex”, and “Age”) to predict the occurrence of hypertension
in patients with diabetes (“HTNinDM”). Models included neural network,
gradient boosting, random forest, Adaptive Boosting, and logistic
regression. Performance was assessed by area under the curve, accuracy,
precision, and recall, and F1 score using cross-validation. Class imbalance
was addressed via diverse models. Feature importance was evaluated by
permutation importance of a random forest model.

The neural network model achieved the best performance with area under the
curve 0.689, accuracy 76.5%, precision 76.3%, recall 98.8%. Gradient
boosting models performed similarly. Age and body mass index were the top
predictors.

Machine learning models show potential for identifying patients with diabetes
at high hypertension risk using routine clinical data. A neural network
model achieved excellent predictive performance.