# Development and validation of a nomogram model to predict coronary heart disease in snoring patients with hypertension and non-glucose metabolism disorders

## TL;DR

This study created a prediction model to assess coronary heart disease risk in snoring, hypertensive patients without glucose metabolism issues.

## Contribution

The study introduces a novel nomogram model using apnea index as a new predictor for coronary heart disease in snoring hypertensive patients.

## Key findings

- The nomogram model showed a C-index of 0.703 in the derivation set and 0.645 in the validation set.
- Key predictors included age, gender, waist-to-height ratio, cholesterol levels, and apnea index.

## Abstract

Snoring, as a common disease, may lead to various cardiovascular diseases. scholars attach importance to the relationship between snoring or sleep breathing disorders and glucose metabolism disorders. Some predictive model for predicting sleep-disordered breathing in patients with diabetes has been developed. Studies have found that blood glucose is an inevitable predictor of the outcome of coronary heart disease. It may mask other predictive factors, leading to clinical neglect of the control of other risk factors. So we developed and validated a nomogram to predict the risk of coronary heart disease in hypertensive patients who snore, excluding those with glucose metabolism disorders.

Records from 2105 snoring patients with hypertension and non-glucose metabolism disorders. A random grouping technique was utilized to split the data into validation and derivation datasets (split ratio = 0.7: 0.3). Least absolute shrinkage and selection operator regression was applied to select predictors and constructed a nomogram model based on multivariate Cox regression analysis. The discrimination and consistency of the nomogram were evaluated using the area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis (DCA) to assess its performance. We found age, male, waist-to-height ratio (WHtR), low and high-density lipoprotein cholesterol (LDL-C and HDL-C), and apnea index (AI) identified as predictors to generate this nomogram model.

The C-index at 84 months was 0.703 (95% confidence interval 0.653-0.754) in the derivation set and 0.645 (95% confidence interval 0.562-0.728) in the validation set. The nomogram demonstrated good performance in the calibration curve and DCA.

So, our study proposed an effective nomogram model with potential application value for individualized prediction of coronary heart disease outcomes in snoring individuals with hypertension, excluding glucose metabolism disorders. And "AI" was proposed as a novel predictor.