# New-onset disability risk prediction model for chronic respiratory disease patients: the first longitudinal evidence from CHARLS

## TL;DR

This study creates a model to predict new disability risk in chronic respiratory disease patients using data from the CHARLS study.

## Contribution

The study introduces a novel nomogram model for predicting new-onset disability in CRD patients using longitudinal data.

## Key findings

- Four key predictors of disability were identified: marital status, self-perceived health, depressive symptoms, and age.
- The model achieved an AUC of 0.724 in training and 0.720 in testing, showing good predictive accuracy.
- The model effectively supports clinical decision-making by identifying high-risk patients.

## Abstract

Although studies have explored the factors influencing the occurrence of disability, predictive models for disability risk in the chronic respiratory diseases (CRD) patient population remain inadequate.

This study employed baseline data from the 2015 China Health and Retirement Longitudinal Study (CHARLS) to select 803 CRD patients without disabilities, who were then followed for 3 years to observe the emergence of new disabilities. Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis was applied to identify risk factors associated with the onset of disability. Ultimately, multivariable logistic regression analysis pinpointed four critical predictive factors: marital status, self-perceived health, depressive symptoms, and age, which were subsequently incorporated into a nomogram model. The model’s predictive efficacy was evaluated using the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA).

During the 3-year follow-up, 196 patients developed new disabilities, yielding an incidence rate of 24.41%. The model evaluation results revealed that area under the curve (AUC) for the training set was 0.724 (95% confidence interval [CI]: 0.676-0.771), and the AUC for the test set was 0.720 (95% CI: 0.641-0.799), demonstrating high accuracy, sensitivity, and specificity. The calibration curve confirmed that the predicted results aligned closely with the actual outcomes, while the DCA analysis illustrated that the model provided substantial net benefits in clinical decision-making, effectively identifying high-risk patients.

The nomogram model developed in this study effectively predicts the risk of new disability occurrence in CRD patients within 3 years. By identifying high-risk patients at an early stage, this model provides scientific evidence for early intervention and health management in CRD patients.