5
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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.

          Related collections

          Most cited references16

          • Record: found
          • Abstract: found
          • Article: not found

          Lower urinary tract symptoms revisited: a broader clinical perspective.

          The term "lower urinary tract symptoms" (LUTS) was introduced to dissociate male urinary symptoms from any implied site of symptom origin, such as the prostate. To consider a more expansive view of LUTS, moving beyond an organocentric focus. Review of the available literature by a consensus panel. A consensus group reviewed the literature and developed a conceptual framework to facilitate research and clinical practice in patients with LUTS, following steps outlined in the Delphi procedure. Committee discussion, with presentations and review of existing literature and knowledge at four separate occasions, and extensive review and discussion of draft documents encapsulating group views followed. Consensus group findings included evidence that LUTS increase with age and are prevalent in both male and female patients, with differences in the prevalence of individual storage, voiding, and postmicturition symptoms representing underlying pathophysiologic factors between the sexes. Additionally, it was recognised that patients often have underlying and overlapping pathophysiologic mechanisms that may be related to the expression of LUTS and that this global approach to LUTS reflects our contemporary recognition of the lower urinary tract as an integrated functional unit. To improve the current management of patients, education and awareness regarding LUTS, its causes, and associated comorbidities are needed. Major limitations of this work are the potential interpretive bias introduced by prior perceptions and the nature of the study populations drawn conventionally from secondary care. In conclusion, it is misleading to attribute individual symptoms to sex differences or to a specific underlying organ. LUTS are a non-sex-specific, non-organ-specific group of symptoms, which are sometimes age-related and progressive. A need exists to increase education and awareness regarding LUTS, its causes, and associated comorbidities, and to assess and treat men and women for all LUTS, not just selected symptoms.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Pressure flow urodynamic studies: the gold standard for diagnosing bladder outlet obstruction.

            Bladder outlet obstruction (BOO) is a common cause of lower urinary tract symptoms (LUTS) in men and women. By definition, BOO is determined urodynamically, assessing the pressure-flow relation during voiding. Since the 1960s much work has been done to standardize the urodynamic definitions of obstruction in men and more recently women. Today, urodynamic testing voiding pressure-flow analysis remains the gold standard for the diagnosis of BOO and the etiology of LUTS. The pressure-flow relation is much better defined in men than in women, but recent work suggests that although the definition of obstruction may differ between men and women, the concept of the pressure-flow relation to diagnose obstruction holds true for both genders.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Detrusor underactivity and the underactive bladder: a new clinical entity? A review of current terminology, definitions, epidemiology, aetiology, and diagnosis.

              Detrusor underactivity (DU) is a common cause of lower urinary tract symptoms (LUTS) in both men and women, yet is poorly understood and underresearched.
                Bookmark

                Author and article information

                Journal
                Int Neurourol J
                Int Neurourol J
                INJ
                International Neurourology Journal
                Korean Continence Society
                2093-4777
                2093-6931
                November 2024
                30 November 2024
                : 28
                : Suppl 2
                : S74-S81
                Affiliations
                [1 ]Acryl Advanced AI Research Center, Acryl Inc., Seoul, Korea
                [2 ]Department of Urology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Korea
                [3 ]College of Computing and Informatics, Sungkyunkwan University, Suwon, Korea
                Author notes
                Corresponding author: Kyu-Sung Lee Department of Urology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul 06351, Korea Email: ksleedr@ 123456skku.edu
                Co-corresponding author: Ikjun Yeom College of Computing and Informatics, Sungkyunkwan University, 2066 Seoburo, Jangan-gu, Suwon 16419, Korea Email: ikjun@ 123456skku.edu
                [*]

                Hyungkyung Shin and Kwang Jin Ko contributed equally to this study as co-first authors.

                Author information
                http://orcid.org/0009-0002-1277-7557
                http://orcid.org/0000-0003-1085-1266
                http://orcid.org/0009-0005-6313-9303
                http://orcid.org/0000-0002-9962-802X
                http://orcid.org/0000-0001-7883-2905
                http://orcid.org/0000-0003-0891-2488
                Article
                inj-2448360-180
                10.5213/inj.2448360.180
                11627226
                39638454
                ffe8b447-49ed-4c15-8c2e-9da41a4db7d8
                Copyright © 2024 Korean Continence Society

                This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( http://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

                History
                : 7 October 2024
                : 20 November 2024
                Categories
                Original Article

                Neurology
                artificial intelligence,bladder outlet obstruction,diagnosis,lower urinary tract symptoms,urinary bladder, underactive

                Comments

                Comment on this article