Related Experiment Video
Updated: Jun 23, 2026
05:37
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
2.0K
A machine learning-based nomogram model for predicting the recurrence of cystitis glandularis
Xuhao Liu1, Yuhang Wang1, Yinzhao Wang1
1Department of Urology, National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Changsha, Hunan, China.
Therapeutic Advances in Urology
|October 21, 2024
Summary
This study developed a nomogram using machine learning to predict recurrence in cystitis glandularis, identifying key factors like urinary infections and blood cell counts for better patient management.
Area of Science:
- Urology
- Inflammatory Diseases
- Medical Informatics
Background:
- Cystitis glandularis is a chronic urinary system inflammatory disease with high recurrence rates.
- The underlying causes of cystitis glandularis recurrence remain largely unknown.
- Understanding recurrence factors is crucial for effective patient management.
Purpose of the Study:
- To identify predictors of cystitis glandularis recurrence.
- To develop a prognostic nomogram for predicting recurrence.
- To establish a simple and feasible model for clinical application.
Main Methods:
- Machine learning techniques were employed to identify key predictors of recurrence.
- A nomogram was constructed using identified predictors.
- Model performance was validated using receiver operating characteristic curve analysis, decision curve analysis, and calibration curves.
Main Results:
- The study included 252 patients with a 12-month recurrence rate of 57.14%.
- Five predictors for recurrence were identified: urinary infections, urinary calculi, eosinophil count, lymphocyte count, and serum magnesium.
- The developed nomogram demonstrated good predictive performance with AUC values exceeding 0.75.
Conclusions:
- A reliable machine learning-based nomogram for predicting cystitis glandularis recurrence has been developed.
- This nomogram can aid in identifying patients at high risk for recurrence.
- The model offers a feasible tool for clinical prognostication and management strategies.
