Related Experiment Video
Updated: Oct 26, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Development of an artificial intelligence diagnostic system for lower urinary tract dysfunction in men
Yoshihisa Matsukawa1, Yoshitaka Kameya2, Tomoichi Takahashi3
1Department of Urology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan.
An artificial intelligence system accurately diagnoses lower urinary tract symptoms in men using only uroflowmetry data. This AI tool shows higher diagnostic accuracy than urologists for conditions like detrusor underactivity and bladder outlet obstruction.
Area of Science:
- Urology
- Medical Artificial Intelligence
- Diagnostic Systems
Background:
- Lower urinary tract symptoms (LUTS) significantly impact men's quality of life.
- Accurate diagnosis of underlying causes, such as detrusor underactivity (DU) and bladder outlet obstruction (BOO), is crucial for effective treatment.
- Current diagnostic methods can be invasive or require specialized equipment.
Purpose of the Study:
- To develop an artificial intelligence (AI) diagnostic system for male lower urinary tract dysfunction.
- To utilize only uroflowmetry data for AI model training and validation.
- To evaluate the diagnostic performance and usefulness of the AI system.
Main Methods:
- Neural networks were employed for AI learning and validation using uroflowmetry data from 256 men.
- An optimal AI diagnostic model was established via 10-fold cross-validation and data augmentation.
- The AI system's diagnostic accuracy was compared against trained urologists using data from 25 additional patients.
Main Results:
- The AI system demonstrated strong positive correlations between its estimated and pressure flow study-derived indices (BCI: r=0.60, BOI: r=0.46).
- Diagnostic performance for detrusor underactivity: 79.7% sensitivity, 88.7% specificity.
- Diagnostic performance for bladder outlet obstruction: 76.8% sensitivity, 84.7% specificity.
- The AI system achieved an average diagnostic accuracy of 84%, significantly outperforming urologists (56%).
Conclusions:
- An AI diagnostic system utilizing uroflowmetry waveforms can effectively differentiate between DU and BOO in men with LUTS.
- The developed AI system exhibits high sensitivity and specificity for diagnosing these conditions.
- This AI approach offers a non-invasive and accurate method for diagnosing lower urinary tract dysfunction.
Related Concept Videos
Urinary Tract Infection III: Diagnostic Studies and Interprofessional Care
Anatomy of the Genitourinary System II: Bladder and Urethra
Nursing Assessment of the Genitourinary System I: Health History
Disorders of the Male Reproductive System
Prostate disorders are another major concern. These conditions can impair urinary flow due to the prostate's location around the urethra....
Urinary Tract Calculi III: Medical Management
Urinary Tract Infection IV: Nursing Management

