Machine Learning Models for the Noninvasive Diagnosis of Bladder Outlet Obstruction and Detrusor Underactivity in Men With Lower Urinary Tract Symptoms
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
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.
Abstract
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.
참고문헌 (16)
- Foo KT, "What is a disease? what is the disease clinical benign prostatic hyperplasia(BPH)?", World J Urol, 37, pp.1293~1296 (2019)
- Chapple CR, "Lower urinary tract symptoms revisited : a broader clinical perspective", Eur Urol, 54, pp.563~569 (2008)
- Ko KJ, "Clinical implications of underactive bladder", Investig Clin Urol, 58(Suppl 2), pp.S75~S81 (2017)
- Murad L, "Treating LUTS in men with benign prostatic obstruction : a review article", Drugs Aging, 40, pp.815~836 (2023)
- Rademakers KL, "Detrusor underactivity in men with lower urinary tract symptoms", benign prostatic obstruction : characterization and potential impact on indications for surgical treatment of the prostate, 2016, pp.26, 3~10
- Li X, "Updates of underactive bladder : a review of the recent literature", Int Urol Nephrol, 48, pp.919~930 (2016)
- Osman NI, "Detrusor underactivity and the underactive bladder: a new clinical entity? a review of current terminology, definitions, epidemiology, aetiology, and diagnosis", Eur Urol, 65, pp.389~398 (2014)
- Swavely NR, "New diagnostics for male lower urinary tract symptoms", Curr Bladder Dysfunct Rep, 14, pp.90~97 (2019)
- Nitti VW, "Pressure flow urodynamic studies : the gold standard for diagnosing bladder outlet obstruction", Rev Urol, 7(Suppl 6), pp.S14~S21 (2005)
- Ko KJ, "Diagnosing bladder outlet obstruction using the penile cuff test in men with lower urinary tract symptoms", Neurourol Urodyn, 36, pp.1884~1889 (2017)
- Khosla L, "Use of the penile cuff test to diagnose bladder outlet obstruction : a systematic review and meta-analysis", Low Urin Tract Symptoms, 14, pp.318~328 (2022)
- Malde S, "Systematic review of the performance of noninvasive tests in diagnosing bladder outlet obstruction in men with lower urinary tract symptoms", Eur Urol, 71, pp.391~402 (2017)
- Kim ES, "The current state of artificial intelligence application in urology", Int Neurourol J, 27, pp.227~233 (2023)
- Bang S, "Feasibility of a deep learning-based diagnostic platform to evaluate lower urinary tract disorders in men using simple uroflowmetry", Investig Clin Urol, 63, pp.301~308 (2022)
- Matsukawa Y, "Development of an artificial intelligence diagnostic system for lower urinary tract dysfunction in men", Int J Urol, 28, pp.1143~1148 (2021)
- Matsukawa Y, "Characteristics of uroflowmetry patterns in men with detrusor underactivity revealed by artificial intelligence", Int J Urol, 30, pp.907~912 (2023)