Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms

Purpose This study aimed to develop and evaluate machine learning models, specifically CatBoost and extreme gradient boosting (XGBoost), for diagnosing lower urinary tract symptoms (LUTS) in male patients. The objective is to differentiate between bladder outlet obstruction (BOO) and detrusor undera...

Full description

Saved in:
Bibliographic Details
Main Authors: Hyungkyung Shin, Kwang Jin Ko, Wei-Jin Park, Deok Hyun Han, Ikjun Yeom, Kyu-Sung Lee
Format: Article
Language:English
Published: Korean Continence Society 2024-11-01
Series:International Neurourology Journal
Subjects:
Online Access:http://einj.org/upload/pdf/inj-2448360-180.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846150351904833536
author Hyungkyung Shin
Kwang Jin Ko
Wei-Jin Park
Deok Hyun Han
Ikjun Yeom
Kyu-Sung Lee
author_facet Hyungkyung Shin
Kwang Jin Ko
Wei-Jin Park
Deok Hyun Han
Ikjun Yeom
Kyu-Sung Lee
author_sort Hyungkyung Shin
collection DOAJ
description Purpose This study aimed to develop and evaluate machine learning models, specifically CatBoost and extreme gradient boosting (XGBoost), for diagnosing lower urinary tract symptoms (LUTS) in male patients. The objective is to differentiate between bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using a comprehensive dataset that includes patient-reported outcomes, uroflowmetry measurements, and ultrasound-derived features. Methods The dataset used in this study was collected from male patients aged 40 and older who presented with LUTS and sought treatment at the urology department of Samsung Medical Center. We developed and trained CatBoost and XGBoost models using this dataset. These models incorporated features like prostate size, voiding parameters, and responses from questionnaires. Their performance was assessed using standard metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). Results The results indicated that the CatBoost models displayed greater sensitivity, rendering them effective for initial screenings by accurately identifying true positive cases. Conversely, the XGBoost models showed higher specificity and precision, making them more suitable for confirming diagnoses and reducing false positives. In terms of overall performance for both BOO and DUA, XGBoost surpassed CatBoost, achieving an AUROC of 0.826 and 0.819, respectively. Conclusions Integrating these machine learning models into the diagnostic workflow for LUTS can significantly enhance clinical decision-making by offering noninvasive, cost-effective, and patient-friendly diagnostic alternatives. The combined application of CatBoost and XGBoost models has the potential to improve diagnostic accuracy and provide customized treatment plans for patients, ultimately leading to better clinical outcomes.
format Article
id doaj-art-dca2fc667caa40e9b081d846a5cf9301
institution Kabale University
issn 2093-4777
2093-6931
language English
publishDate 2024-11-01
publisher Korean Continence Society
record_format Article
series International Neurourology Journal
spelling doaj-art-dca2fc667caa40e9b081d846a5cf93012024-11-29T00:48:20ZengKorean Continence SocietyInternational Neurourology Journal2093-47772093-69312024-11-0128Suppl 2S748110.5213/inj.2448360.1801131Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract SymptomsHyungkyung Shin0Kwang Jin Ko1Wei-Jin Park2Deok Hyun Han3Ikjun Yeom4Kyu-Sung Lee5 Acryl Advanced AI Research Center, Acryl Inc., Seoul, Korea Department of Urology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea Acryl Advanced AI Research Center, Acryl Inc., Seoul, Korea Department of Urology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea Acryl Advanced AI Research Center, Acryl Inc., Seoul, Korea Department of Urology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, KoreaPurpose This study aimed to develop and evaluate machine learning models, specifically CatBoost and extreme gradient boosting (XGBoost), for diagnosing lower urinary tract symptoms (LUTS) in male patients. The objective is to differentiate between bladder outlet obstruction (BOO) and detrusor underactivity (DUA) using a comprehensive dataset that includes patient-reported outcomes, uroflowmetry measurements, and ultrasound-derived features. Methods The dataset used in this study was collected from male patients aged 40 and older who presented with LUTS and sought treatment at the urology department of Samsung Medical Center. We developed and trained CatBoost and XGBoost models using this dataset. These models incorporated features like prostate size, voiding parameters, and responses from questionnaires. Their performance was assessed using standard metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). Results The results indicated that the CatBoost models displayed greater sensitivity, rendering them effective for initial screenings by accurately identifying true positive cases. Conversely, the XGBoost models showed higher specificity and precision, making them more suitable for confirming diagnoses and reducing false positives. In terms of overall performance for both BOO and DUA, XGBoost surpassed CatBoost, achieving an AUROC of 0.826 and 0.819, respectively. Conclusions Integrating these machine learning models into the diagnostic workflow for LUTS can significantly enhance clinical decision-making by offering noninvasive, cost-effective, and patient-friendly diagnostic alternatives. The combined application of CatBoost and XGBoost models has the potential to improve diagnostic accuracy and provide customized treatment plans for patients, ultimately leading to better clinical outcomes.http://einj.org/upload/pdf/inj-2448360-180.pdfartificial intelligencebladder outlet obstructiondiagnosislower urinary tract symptomsurinary bladder, underactive
spellingShingle Hyungkyung Shin
Kwang Jin Ko
Wei-Jin Park
Deok Hyun Han
Ikjun Yeom
Kyu-Sung Lee
Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
International Neurourology Journal
artificial intelligence
bladder outlet obstruction
diagnosis
lower urinary tract symptoms
urinary bladder, underactive
title Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
title_full Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
title_fullStr Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
title_full_unstemmed Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
title_short Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
title_sort machine learning models for the noninvasive diagnosis of bladder outlet obstruction and detrusor underactivity in men with lower urinary tract symptoms
topic artificial intelligence
bladder outlet obstruction
diagnosis
lower urinary tract symptoms
urinary bladder, underactive
url http://einj.org/upload/pdf/inj-2448360-180.pdf
work_keys_str_mv AT hyungkyungshin machinelearningmodelsforthenoninvasivediagnosisofbladderoutletobstructionanddetrusorunderactivityinmenwithlowerurinarytractsymptoms
AT kwangjinko machinelearningmodelsforthenoninvasivediagnosisofbladderoutletobstructionanddetrusorunderactivityinmenwithlowerurinarytractsymptoms
AT weijinpark machinelearningmodelsforthenoninvasivediagnosisofbladderoutletobstructionanddetrusorunderactivityinmenwithlowerurinarytractsymptoms
AT deokhyunhan machinelearningmodelsforthenoninvasivediagnosisofbladderoutletobstructionanddetrusorunderactivityinmenwithlowerurinarytractsymptoms
AT ikjunyeom machinelearningmodelsforthenoninvasivediagnosisofbladderoutletobstructionanddetrusorunderactivityinmenwithlowerurinarytractsymptoms
AT kyusunglee machinelearningmodelsforthenoninvasivediagnosisofbladderoutletobstructionanddetrusorunderactivityinmenwithlowerurinarytractsymptoms