1
|
Altıntaş E, Şahin A, Babayev H, Gül M, Batur AF, Kaynar M, Kılıç Ö, Göktaş S. Machine learning algorithm predicts urethral stricture following transurethral prostate resection. World J Urol 2024; 42:324. [PMID: 38748256 PMCID: PMC11096196 DOI: 10.1007/s00345-024-05017-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2024] [Accepted: 04/22/2024] [Indexed: 05/18/2024] Open
Abstract
PURPOSE To predict the post transurethral prostate resection(TURP) urethral stricture probability by applying different machine learning algorithms using the data obtained from preoperative blood parameters. METHODS A retrospective analysis of data from patients who underwent bipolar-TURP encompassing patient characteristics, preoperative routine blood test outcomes, and post-surgery uroflowmetry were used to develop and educate machine learning models. Various metrics, such as F1 score, model accuracy, negative predictive value, positive predictive value, sensitivity, specificity, Youden Index, ROC AUC value, and confidence interval for each model, were used to assess the predictive performance of machine learning models for urethral stricture development. RESULTS A total of 109 patients' data (55 patients without urethral stricture and 54 patients with urethral stricture) were included in the study after implementing strict inclusion and exclusion criteria. The preoperative Platelet Distribution Width, Mean Platelet Volume, Plateletcrit, Activated Partial Thromboplastin Time, and Prothrombin Time values were statistically meaningful between the two cohorts. After applying the data to the machine learning systems, the accuracy prediction scores for the diverse algorithms were as follows: decision trees (0.82), logistic regression (0.82), random forests (0.91), support vector machines (0.86), K-nearest neighbors (0.82), and naïve Bayes (0.77). CONCLUSION Our machine learning models' accuracy in predicting the post-TURP urethral stricture probability has demonstrated significant success. Exploring prospective studies that integrate supplementary variables has the potential to enhance the precision and accuracy of machine learning models, consequently progressing their ability to predict post-TURP urethral stricture risk.
Collapse
Affiliation(s)
- Emre Altıntaş
- Faculty of Medicine, Department of Urology, Selcuk University, Tıp Fakültesi Alaeddin Keykubat Yerleşkesi Selçuklu, Konya, 42131, Turkey.
| | - Ali Şahin
- Faculty of Medicine, Selcuk University, Konya, Turkey
| | - Huseyn Babayev
- Faculty of Medicine, University of Zurich, Zurich, Switzerland
| | - Murat Gül
- Faculty of Medicine, Department of Urology, Selcuk University, Tıp Fakültesi Alaeddin Keykubat Yerleşkesi Selçuklu, Konya, 42131, Turkey
| | - Ali Furkan Batur
- Faculty of Medicine, Department of Urology, Selcuk University, Tıp Fakültesi Alaeddin Keykubat Yerleşkesi Selçuklu, Konya, 42131, Turkey
| | - Mehmet Kaynar
- Faculty of Medicine, Department of Urology, Selcuk University, Tıp Fakültesi Alaeddin Keykubat Yerleşkesi Selçuklu, Konya, 42131, Turkey
| | - Özcan Kılıç
- Faculty of Medicine, Department of Urology, Selcuk University, Tıp Fakültesi Alaeddin Keykubat Yerleşkesi Selçuklu, Konya, 42131, Turkey
| | - Serdar Göktaş
- Faculty of Medicine, Department of Urology, Selcuk University, Tıp Fakültesi Alaeddin Keykubat Yerleşkesi Selçuklu, Konya, 42131, Turkey
| |
Collapse
|
2
|
Tokuc E, Eksi M, Kayar R, Demir S, Topaktas R, Bastug Y, Akyuz M, Ozturk M. Inflammation indexes and machine-learning algorithm in predicting urethroplasty success. Investig Clin Urol 2024; 65:240-247. [PMID: 38714514 PMCID: PMC11076797 DOI: 10.4111/icu.20230302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 10/06/2023] [Accepted: 12/29/2023] [Indexed: 05/10/2024] Open
Abstract
PURPOSE To assess the predictive capability of hematological inflammatory markers for urethral stricture recurrence after primary urethroplasty and to compare traditional statistical methods with a machine-learning-based artificial intelligence algorithm. MATERIALS AND METHODS Two hundred eighty-seven patients who underwent primary urethroplasty were scanned. Ages, smoking status, comorbidities, hematological inflammatory parameters (neutrophil-lymphocyte ratios, platelet-lymphocyte ratios [PLR], systemic immune-inflammation indexes [SII], and pan-immune-inflammation values [PIV]), stricture characteristics, history of previous direct-visual internal urethrotomy, urethroplasty techniques, and grafts/flaps placements were collected. Patients were followed up for one year for recurrence and grouped accordingly. Univariate and multivariate logistic regression analyses were conducted to create a predictive model. Additionally, a machine-learning-based logistic regression analysis was implemented to compare predictive performances. p<0.05 was considered statistically significant. RESULTS Comparative analysis between the groups revealed statistically significant differences in stricture length (p=0.003), localization (p=0.027), lymphocyte counts (p=0.008), PLR (p=0.003), SII (p=0.003), and PIV (p=0.001). In multivariate analysis, stricture length (odds ratio [OR] 1.230, 95% confidence interval [CI] 1.142-1.539, p<0.0001) and PIV (OR 1.002, 95% CI 1.000-1.003, p=0.039) were identified as significant predictors of recurrence. Classical logistic regression model exhibited a sensitivity of 0.76, specificity of 0.43 with an area under curve (AUC) of 0.65. However, the machine-learning algorithm outperformed traditional methods achieving a sensitivity of 0.80, specificity of 0.76 with a higher AUC of 0.82. CONCLUSIONS PIV and machine-learning algorithms shows promise on predicting urethroplasty outcomes, potentially leading to develop possible nomograms. Evolving machine-learning algorithms will contribute to more personalized and accurate approaches in managing urethral stricture.
Collapse
Affiliation(s)
- Emre Tokuc
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye.
| | - Mithat Eksi
- Urology Clinic, Bakırkoy Dr. Sadi Konuk SUAM, University of Health Sciences, Istanbul, Türkiye
| | - Ridvan Kayar
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye
| | - Samet Demir
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye
| | - Ramazan Topaktas
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye
| | - Yavuz Bastug
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye
| | - Mehmet Akyuz
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye
| | - Metin Ozturk
- Urology Clinic, Haydarpasa Numune SUAM, University of Health Sciences, Istanbul, Türkiye
| |
Collapse
|
3
|
Özsoy E, Kutluhan MA, Tokuç E, Kayar R, Demir S, Akyüz M, Öztürk Mİ. Is testosterone deficiency a predictive factor for recurrence of urethral stricture? Andrology 2023. [PMID: 37924277 DOI: 10.1111/andr.13554] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Revised: 10/23/2023] [Accepted: 10/26/2023] [Indexed: 11/06/2023]
Abstract
BACKGROUND Testosterone plays a vital role in maintaining tissue homeostasis, and testosterone deficiency may potentially influence the likelihood of urethral stricture recurrence. OBJECTIVES To evaluate the prognostic value of testosterone levels in the recurrence after direct visual internal urethrotomy in primary short segment bulbar urethral strictures and its clinical reflections. MATERIALS AND METHODS A total of 723 patients who underwent direct vision internal urethrotomy between January 2000 and October 2022 were retrospectively analyzed. After implying exclusion criteria, 116 patients with available data were enrolled. Patients were divided into two groups as recurrence and no recurrence. Age, stricture length, etiology, time of recurrence, diagnosis of previous diabetes mellitus, hypertension, smoking, body mass index, and total testosterone levels were recorded. Free testosterone and bioavailable testosterone values were calculated using total testosterone, albumin, and sex hormone binding globulin values. Hypogonadism was considered as a total testosterone level less than 300 ng/dL. Demographic characteristics and total testosterone, free testosterone, and bioavailable testosterone levels were compared between the two groups for statistical significance. The recurrence rates of patients with and without hypogonadism were compared. RESULTS Recurrence was observed in 41.4% of the cases (n = 48). There was no statistically significant difference between the groups in terms of age, body mass index values, diabetes mellitus, hypertension, smoking status, presence of hypogonadism, and etiology (p = 0.745, 0.863, 0.621, 0.622, 0.168, 0.051, and 0.232). In terms of total testosterone levels and bioavailable testosterone levels, the recurrence group had significantly lower values (p = 0.018 and 0.04). There was no significant difference between the two groups in terms of stricture length (p = 0.071). Sixteen of 28 patients with hypogonadism had recurrence, whereas 32 of 88 patients without hypogonadism had recurrence (p = 0.051). DISCUSSION Testosterone levels have potential to predict recurrence in primary short-segment bulbar urethral strictures. This study represents the inaugural analysis of the impact of testosterone deficiency on recurrence within the cohort of patients with primary short-segment bulbar urethral strictures. CONCLUSION Testosterone levels and ratios may serve as predictive factors for identifying recurrent cases in primary short-segment bulbar strictures. For patients at a higher risk of recurrence, urethroplasty may be considered as an initial treatment option, even in cases of primary and short-segment strictures.
Collapse
Affiliation(s)
| | - Musab Ali Kutluhan
- Department of Urology, Yildirim Beyazit University School of Medicine, Ankara, Turkey
| | - Emre Tokuç
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Rıdvan Kayar
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Samet Demir
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Mehmet Akyüz
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Metin İshak Öztürk
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| |
Collapse
|
4
|
Özsoy E, Kutluhan MA, Tokuç E, Artuk İ, Kayar R, Akyüz M, Öztürk Mİ. Predictive value of systemic immune-inflammation index in recurrent urethral strictures. Urologia 2023; 90:510-515. [PMID: 36321780 DOI: 10.1177/03915603221132033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/20/2023]
Abstract
PURPOSE To investigate the predictive value of systemic immune-inflammation index (SII) in recurrence of urethral stricture in patients undergoing internal urethrotomy. METHODS In this two-center, retrospective study, 703 patients who had internal urethrotomy for urethral stricture were included. Demographic, clinical, and laboratory characteristics and operative data were obtained. Two groups were formed from the patients as non-recurrent urethral stricture (n = 490) and recurrent urethral stricture (n = 213). RESULTS There was no significant difference in the mean age between the patients with and without recurrence. There was a significant difference in the mean SII values and albumin levels between the recurrence and non-recurrence groups (p = 0.001 and p = 0.006, respectively). Using a cut-off value of 252 for the SII; the sensitivity was 59.62%, the specificity was 70.41%, the positive predictive value was 46.69%, the negative predictive value was 80.05% and the accuracy was 67.14%, respectively. Statistically significant correlation was found between the presence of recurrence and the established cut-off value of the SII (p = 0.001 and p < 0.01, respectively). The risk of recurrence was stated that 3.514 times higher in patients with a SII value of ⩾252. CONCLUSION Using the SII the inflammatory state of the urethral tissue can be evaluated. Thus the risk of recurrence after internal urethrotomy operation can be predicted. Open urethroplasty technique instead of DVIU in patients with high SII values may increase the surgical success rates.
Collapse
Affiliation(s)
| | - Musab Ali Kutluhan
- Department of Urology, Yildirim Beyazit University School of Medicine, Ankara
| | - Emre Tokuç
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - İlker Artuk
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Rıdvan Kayar
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Mehmet Akyüz
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| | - Metin İshak Öztürk
- Department of Urology, Health Sciences University Haydarpasa Numune Training and Research Hospital, İstanbul, Turkey
| |
Collapse
|
5
|
Campbell JG, Hayden JP, Vanni AJ. Biomarkers in Urethral Stricture Disease and Benign Lower Urinary Tract Disease. Urol Clin North Am 2023; 50:31-38. [DOI: 10.1016/j.ucl.2022.09.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
6
|
Doersch KM, Barnett D, Chase A, Johnston D, Gabrielsen JS. The contribution of the immune system to genitourinary fibrosis. Exp Biol Med (Maywood) 2022; 247:765-778. [PMID: 35531654 PMCID: PMC9134766 DOI: 10.1177/15353702221090872] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/15/2023] Open
Abstract
Fibrotic diseases of the genitourinary tract are devastating and incompletely understood pathologies. These diseases include urethral and ureteral strictures, retroperitoneal fibrosis, and Peyronie's disease. They can contribute to obstructive uropathy and sexual dysfunction. Poor understanding of the pathophysiology of these diseases severely limits our ability to prevent and treat them. Genitourinary fibrotic diseases likely represent related pathologies that share common underlying mechanisms involving wound healing in response to injury. These diseases share the common feature of extracellular matrix abnormalities-such as collagen deposition, transforming growth factor-β accumulation, and dysregulation of collagen maturation-leading to abnormal tissue stiffness. Given the association of many of these diseases with autoimmunity, a systemic pro-inflammatory state likely contributes to their associated fibrogenesis. Herein, we explore the immunologic contribution to fibrogenesis in several fibrotic diseases of the genitourinary system. Better understanding how the immune system contributes to fibrosis in these diseases may improve prevention and therapeutic strategies and elucidate the functions of immunologic contributors to fibrosis in general.
Collapse
Affiliation(s)
- Karen M Doersch
- Department of Urology, University of
Rochester Medical Center, Rochester, NY 14642, USA
| | - Daniel Barnett
- Department of Pediatrics, University of
Toledo, Toledo, OH 43614, USA
| | - Abbie Chase
- Department of Urology, University of
Rochester Medical Center, Rochester, NY 14642, USA
| | - Daniel Johnston
- Department of Urology, University of
Rochester Medical Center, Rochester, NY 14642, USA
| | - J Scott Gabrielsen
- Department of Urology, University of
Rochester Medical Center, Rochester, NY 14642, USA
| |
Collapse
|
7
|
Urkmez A, Topaktas R, Ozsoy E, Tokuc E, Kutluhan MA, Artuk I, Kayar R, Ozturk MI. Is neutrophil to lymphocyte ratio a predictive factor for recurrence of urethral stricture? ACTA ACUST UNITED AC 2020; 65:1448-1453. [PMID: 31994624 DOI: 10.1590/1806-9282.65.12.1448] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2019] [Accepted: 06/30/2019] [Indexed: 11/21/2022]
Abstract
INTRODUCTION Due to spongiofibrosis and inflammatory processes underlying the pathogenesis of urethral stricture, it is possible that the neutrophil-lymphocyte ratio (NLR) may give essential information about the course of the disease and recurrence possibilities. Our study aims to evaluate the correlation between NLR and recurrence rates. METHODS A total of 512 patients who underwent direct visual internal urethrotomy (DVIU) due to urethral stricture in our clinic between February 2010 and January 2018 were evaluated retrospectively. RESULTS The median follow up for non-recurrent and recurrent groups after DVIU was 30 and 36 months, respectively. During the follow-up, 280 (54.7%) of the patients had recurrences, and 232 (45,3%) had no recurrences. The mean time for recurrence after DVIU was 6,5±1,4 months, with a range of 1-36 months. The mean NLR in the non-recurrence group was 2,02±0,87, with a median of 1.9, and 3,66±2,30, with a median of 3 in the recurrence group. A highly significant statistical difference was observed between two groups in terms of neutrophil count and NLR (p: 0.000 - both). The area under curve value for NLR was 0.767, with a standard error of 0.021 (95% CI 0.727-0.808). The cut-off value of NLR was determined as 2.25, with a 70% sensitivity and 67,7% specificity. CONCLUSION By using NLR, the inflammatory features of the urethral tissue can be predicted, and possible recurrences after surgery can be estimated. Consequently, open urethroplasty techniques can be used in cases with a significant NLR value instead of the recurrent endoscopic procedure.
Collapse
Affiliation(s)
- Ahmet Urkmez
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Ramazan Topaktas
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Emrah Ozsoy
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Emre Tokuc
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Musab Ali Kutluhan
- . Fatih Sultan Mehmet Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Ilker Artuk
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Ridvan Kayar
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| | - Metin Ishak Ozturk
- . Haydarpasa Numune Research & Training Hospital, Dept. of Urology, Istanbul, Turkey
| |
Collapse
|
8
|
Topaktaş R, Ürkmez A, Tokuç E, Akyüz M, Kutluhan MA. Hematologic parameters and neutrophil / lymphocyte ratio in the prediction of urethroplasty success. Int Braz J Urol 2019; 45:369-375. [PMID: 30785704 PMCID: PMC6541144 DOI: 10.1590/s1677-5538.ibju.2018.0682] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2018] [Accepted: 11/15/2018] [Indexed: 11/21/2022] Open
Abstract
Objective: The pathophysiology of urethral stricture and its recurrence remains vague and one of the important causes is progressive inflammation. It has been shown in recent years that the neutrophil / lymphocyte ratio is a marker of systemic inflammation and is associated with prognosis in many cardiovascular diseases, malignancies and chronic inflammatory diseases. We assessed simple systemic inflammation markers preoperatively and surgical techniques for urethral stricture recurrence after urethroplasty. Patients and Methods: After exclusion criteria applied, a total of 117 male cases operated with urethroplasty in our clinic between January 2012 and June 2017 were included in the study and analyzed retrospectively. Localization and length of the strictures of the patients, neutrophil counts and percentages, lymphocyte counts and percentages, and neutrophil / lymphocyte ratios in preoperative peripheral blood samples were statistically analyzed. Recurrent stricture during first 12 months follow-up after the surgery has been assessed as recurrence. Results: The mean age of the patients was 54.12 ± 16.35 and the mean urethral stricture length was 3.44 ± 1.83 cm. Recurrence was observed in 30.1% of cases who received buccal graft, 30% in penile skin applied cases and 26.1% of cases treated with end-to-end anastomosis and there was no statistically significant difference between neutrophil, lymphocyte, neutrophil / lymphocyte ratio and average stricture segment length between recurrent and non-recurrent cases (p > 0.005). Conclusions: We consider that neutrophil, lymphocyte counts and their ratio prior to urethroplasty and the technique performed are not parameters that can be used to predict stricture recurrence. Prospective and randomized new trials with larger patient populations are needed to make more accurate judgments about the role of these inflammatory parameters.
Collapse
Affiliation(s)
- Ramazan Topaktaş
- Department of Urology, Haydarpaşa Numune Training and Research Hospital, Istanbul, Turkey
| | - Ahmet Ürkmez
- Department of Urology, Haydarpaşa Numune Training and Research Hospital, Istanbul, Turkey
| | - Emre Tokuç
- Department of Urology, Haydarpaşa Numune Training and Research Hospital, Istanbul, Turkey
| | - Mehmet Akyüz
- Department of Urology, Haydarpaşa Numune Training and Research Hospital, Istanbul, Turkey
| | - Musab A Kutluhan
- Department of Urology, Haydarpaşa Numune Training and Research Hospital, Istanbul, Turkey
| |
Collapse
|
9
|
The effect of platelet-rich plasma injection on post-internal urethrotomy stricture recurrence. World J Urol 2019; 37:2809-2810. [DOI: 10.1007/s00345-018-2614-y] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2018] [Accepted: 12/19/2018] [Indexed: 01/15/2023] Open
|