Related Experiment Video
Updated: Jan 13, 2026
07:31
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
7.5K
Screening for depression risk in asthma patients: Development and external validation of a machine learning-based
Rongjun Wan1, Hao Zhou2, Peng Chen2
1Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Wannan Medical College (Yijishan Hospital of Wannan Medical College), Wuhu, China.
Journal of Affective Disorders
|October 28, 2025
Summary
This study developed a predictive model to estimate depression risk in asthma patients using clinical data. The model, visualized as a nomogram, aids in identifying individuals at higher risk for depressive episodes.
Area of Science:
- Pulmonary Medicine
- Psychiatry
- Data Science
Background:
- Depression frequently affects asthma patients, diminishing quality of life and treatment outcomes.
- Asthma patients face a higher risk of depressive episodes, impacting overall prognosis.
Purpose of the Study:
- To develop and validate a predictive model for estimating depression risk in asthma patients.
- To identify key clinical variables associated with depressive episodes in this population.
Main Methods:
- Utilized National Health and Nutrition Examination Survey (NHANES) data for clinically accessible variables.
- Employed a combined variable selection strategy and multiple machine learning methods.
- Selected and validated an optimal Logistic regression model, visualized as a nomogram.
Main Results:
- Included 3517 asthma patients, split into training (1951) and validation (1566) sets.
- Identified key predictors: asthma acute attack, smoking, PIR, total bilirubin, COPD, and serum glucose.
- The Logistic model demonstrated excellent predictive performance and clinical utility in the validation set.
Conclusions:
- A novel risk prediction model for depressive symptoms in asthma patients was successfully developed.
- The nomogram provides a practical tool for clinical application and risk assessment.
