# Development and Validation of a Nomogram to Predict Depression Risk in Patients with Cardiovascular Disease

## TL;DR

This study created a tool to predict depression risk in patients with cardiovascular disease using various health and lifestyle factors.

## Contribution

A new nomogram model was developed and validated for depression risk prediction in cardiovascular disease patients.

## Key findings

- The nomogram achieved an AUC of 0.852 in the training cohort and 0.856 in the validation cohort.
- Eleven risk factors, including blood Cd concentration and sedentary time, were identified as significant predictors of depression.
- The model showed high sensitivity and specificity, indicating strong predictive accuracy.

## Abstract

Background/Objectives: Approximately one-third of patients with cardiovascular disease (CVD) experience depression. This study aimed to develop and validate a nomogram for assessing the risk of depression in patients with CVD. Methods: In a cross-sectional study design, we analyzed data obtained from 6702 patients with CVD who participated in the 2007–2018 National Health and Nutrition Examination Survey. The dataset was randomly split into training and validation cohorts at a 0.75 to 0.25 ratio. Univariate and multivariate logistic regression analyses were applied to the training cohort to identify predictors for a web-based dynamic nomogram, which was then validated in the validation cohort. Results: Blood Cd concentration, sedentary time, eosinophil count, marital status, work limitations, sleep disorders, asthma, stomach or intestinal illness, confusion or memory problems, ethnicity, and cotinine were identified as risk factors for depression in patients with CVD, and these 11 risk factors were incorporated into the nomogram. The area under the curve (AUC) of the nomogram was 0.852 (95% CI: 0.842–0.862) in the training cohort, with a sensitivity of 83.28% and specificity of 72.95%. The AUC was 0.856 (95% CI: 0.838–0.872) in the validation cohort, with a sensitivity of 79.14% and a specificity of 76.65%. The C-index of the nomogram was 0.852 in the training cohort, with a mean absolute error of 0.012 based on 1000 bootstrap replicates. The C-index of the nomogram model was 0.863 in the validation cohort, with a mean absolute error of 0.017. Conclusions: Our nomogram model demonstrates potential clinical utility for the early screening of depression risk in patients with CVD.