Related Experiment Video
Updated: Aug 5, 2026
12:31
In Vivo Modeling of the Morbid Human Genome using Danio rerio
Published on: August 24, 2013
Diagnostic Model Development for IC/BPS and Its Subtypes Using Clinical Indicators, Urinary Biomarkers, and
Cheng Luo1, Yonghui Guan1, Yifala Dilimulati1
1Department of Urology Surgery, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China.
Summary
Interstitial cystitis/bladder pain syndrome (IC/BPS) is a chronic condition. This study developed a diagnostic model using machine learning, identifying TNF-α as a key factor for better diagnosis and targeted treatments.
Area of Science:
- Urology
- Immunology
- Computational Biology
Background:
- Interstitial cystitis/bladder pain syndrome (IC/BPS) is a complex, chronic condition often misdiagnosed due to overlapping symptoms with urinary infections.
- Tumor necrosis factor-alpha (TNF-α) is implicated in IC/BPS inflammation, but its precise role and therapeutic potential require further investigation.
Purpose of the Study:
- To develop a diagnostic model for IC/BPS and its subtypes (non-Hunner IC and Hunner IC) to identify underlying mechanisms, novel biomarkers, and potential TNF-α-targeted therapies.
- To uncover the role of TNF-α in IC/BPS pathogenesis and heterogeneity.
Main Methods:
- Machine learning models, including Lasso+plsRglm, were developed using clinical and molecular data from IC/BPS patients and healthy controls.
- SHapley Additive exPlanations (SHAP) analysis identified key diagnostic features.
- Gene Expression Omnibus (GEO) data and single-cell RNA sequencing (scRNA-seq) were used for molecular analysis.
- In silico TNF-α knockout was performed using scTenifoldKnk.
Main Results:
- The optimal diagnostic model, Lasso+plsRglm, achieved high accuracy (AUC=1.000) in differentiating IC/BPS subtypes and healthy controls.
- Key diagnostic features included nocturia frequency (NUF), visual analogue scale (VAS), bladder wall thickness (BWT), and TNF-α levels.
- Molecular analysis revealed distinct inflammatory profiles and cellular heterogeneity between IC/BPS subtypes, driven by a TNF-α-related network.
- The Hunner IC subtype exhibited more severe symptoms and elevated inflammatory mediators compared to non-Hunner IC.
Conclusions:
- A robust diagnostic model for IC/BPS has been established, incorporating clinical and molecular markers, with TNF-α playing a significant role.
- The study identified novel biomarkers and elucidated a TNF-α-driven inflammatory network contributing to IC/BPS heterogeneity.
- These findings provide a foundation for developing targeted therapies and improving diagnostic accuracy for IC/BPS.