Artificial Intelligence-Based Analysis of Uroflowmetry Patterns in Children: a Machine Learning Perspective

Interpretation of Uroflowmetry Samples from Pediatric Patients by Clinicians and Introduction to Artificial Intelligence, and Interpretation of the Samples by Artificial Intelligence

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT06814847

Enrollment

500

Registered

2025-02-07

Start date

2024-10-01

Completion date

2025-02-01

Last updated

2025-02-25

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Machine Learning, Voiding Disorders, Voiding Dysfunction

Keywords

Uroflowmetry voiding patterns, Interpretation differences, Machine learning, Artificial intelligence

Brief summary

Uroflowmetry is the one of the most commonly used non-invasive test for evaluating children with lower urinary tract symptoms (LUTS). However, studies have highlighted a weak agreement among experts in interpreting uroflowmetry patterns. This study aims to assess the impact of machine learning models, which have become increasingly prevalent in medicine, on the interpretation of uroflowmetry patterns.

Detailed description

The study included uroflowmetry tests of children aged 4-17 years who were referred to our clinic with lower urinary tract symptoms. Uroflowmetry patterns were independently interpreted by three pediatric urology experts. Discrepancies in interpretations were jointly re-evaluated by the three observers, and a consensus was reached. Voiding volume, voiding duration, and urine flow rates at 0.5-second intervals were converted into numerical data for analysis. Eighty percent of the dataset was used as training data for machine learning, while there maining 20% was reserved for testing. A total of five different machine learning models were employed for classification: Decision Tree, Random Forest, CatBoost, XGBoost, and LightGBM. The models that most accurately identified each uroflowmetry pattern were determined.

Interventions

None listed

Study design

Observational model

CASE_ONLY

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

4 Years to 17 Years

Healthy volunteers

Yes

Inclusion criteria

* Aged between 4 and 17 years with LUTS * Urinate more than 50% of the expected bladder capacity on UF

Exclusion criteria

* Patients who were unable to cooperate with the voiding command * Had neurological disorders * Urinate less than 50% of the expected bladder capacity on UF * Under 4 years of age, and were over 18 years of age

Design outcomes

Primary

Measure	Time frame	Description
Performance of Machine Learning Models in Evaluating Voiding Patterns	From October 2024 to January 2025	5 different machine learning models were used. Accuracy rates were determined for each model.

Countries

Turkey (Türkiye)

Outcome results