# Construction and validation of a multimodal predictive model incorporating catecholamines and uric acid for early detection of hypertensive organ damage

## TL;DR

This study builds a model using catecholamines and uric acid to predict organ damage in hypertension patients, improving early detection and clinical decisions.

## Contribution

A novel multimodal predictive model combining catecholamines and uric acid for early detection of hypertensive organ damage is developed and validated.

## Key findings

- The model achieved C-indices of 0.834 in training and 0.823 in validation sets.
- Norepinephrine, normetanephrine, metanephrine, and uric acid were key predictors of organ damage.
- The model showed good calibration with P-values of 0.617 and 0.472 in training and validation sets.

## Abstract

To investigate the feasibility and clinical value of constructing a predictive model for early detection of organ damage in hypertensive patients based on catecholamine-related indicators (norepinephrine, normetanephrine, and metanephrine), serum uric acid, and other clinical parameters.

A total of 421 hypertensive patients were enrolled and divided into a training set (n = 295) and a validation set (n = 126) in a 7:3 ratio. Baseline data were collected, including catecholamine-related indicators (norepinephrine, epinephrine, normetanephrine, and metanephrine), serum uric acid, blood pressure parameters, target organ structural markers (left ventricular posterior wall thickness, carotid intima-media thickness, etc.), and clinical characteristics. Organ damage (defined as left ventricular hypertrophy, carotid intima-media thickness ≥1.0 mm, or elevated serum creatinine) was set as the outcome event. Univariate and multivariate logistic regression analyses were performed to identify independent predictors, followed by the construction of a nomogram model for performance evaluation and validation.

The incidence of organ damage was 44.07% (130/295) in the training set and 42.06% (53/126) in the validation set. Multivariate regression revealed that norepinephrine, normetanephrine, metanephrine, serum uric acid, serum creatinine, duration of hypertension, and cystatin C were independent predictors of organ damage (all P < 0.05). The nomogram model demonstrated C-indices of 0.834 and 0.823 in the training and validation sets, respectively, with AUCs of 0.834 (95% CI: 0.779–0.888) and 0.823 (95% CI: 0.732–0.914). Sensitivity and specificity were 0.717 and 0.819 in the training set and 0.711 and 0.776 in the validation set. Calibration curves indicated good agreement between predicted and observed values, with Hosmer-Lemeshow test P-values of 0.617 and 0.472, respectively.

The predictive model constructed based on relevant indicators such as catecholamines and serum uric acid in this study can effectively predict the risk of organ damage in hypertensive patients, intervene early, and provide a quantitative basis for clinical decision-making.