Prediction of success of slings in female stress incontinence, statistical and AI modeling

Prediction of success of slings in female stress incontinence, statistical and AI modeling | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Prediction of success of slings in female stress incontinence, statistical and AI modeling Ahmed Abdelrasheed, Mohammed Taha, Ahmed Abdelrahman, Bassam Mohamed, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5617887/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Aug, 2025 Read the published version in Scientific Reports → Version 1 posted 11 You are reading this latest preprint version Abstract Objectives: Studies on predicting the outcome of sling surgery are limited. Most depend on analysis of multiple confounding factors using regression models. However, their prediction results are limited. In this study, we tested a statistical regression model and an AI model for the prediction of the outcome of mid-urethral sling. Methods : Data were collected from 151 patients who underwent MUS surgery in our center from 2002 to 2022 and confounding factors that affect the outcome of the surgery at a minimum of one year. The study was divided into two phases. Phase I included the construction of a prediction model using binomial logistic regression. In phase II, we applied an AI preferences (Support Vector Machines (SVM) and Artificial neural network (ANN) trying to obtain better predictions. Results: Phase I: The logistic regression model predicted the outcome of surgery with overall accuracy of 90.7% and positive predictive value of 61.5% [X 2 (11) = 46.24, P < 0.001]. Phase II: The data of the patients were entered as 10 features; 9 were predictors and the 10 th was the output. The output comprised 18 cases designated as ‘failure’ and 133 as ‘success’ output. The best model performance-wise was the (SVM) with 92% accuracy and 96% F1-score, which meets the industrial standards for predictive models. However, ANN produced 90% accuracy and 94% F1-score. However, our sample size is small Conclusion : Prediction of the outcome of MUS surgery was achieved using different modalities with the best prediction of the outcome obtained by SVM method. Biological sciences/Biotechnology Health sciences/Urology Sling female incontinence prediction AI Figures Figure 1 Figure 2 Figure 3 Figure 4 Introduction Stress urinary incontinence (SUI) is the most prevalent type of urinary incontinence (UI). Age, parity, and obesity were globally considered risk factors for the development of SUI. Other reports demonstrated factors such as hysterectomy, medical co morbidities, smoking, DM, and major depression 1 2 3 & 4 While pubovaginal sling (PVS) is the gold standard, the use of mid-urethral slings (MUS) became the most popular procedure since Ulmsten published his study on tension-free vaginal tape (TVT) 5 & 6 . In addition, some studies demonstrated that primary and secondary outcomes of PVS and TVT were better than those of TOT 7 & 8 Different predictive models for prognostic and diagnostic purposes were created using "experience”. Logistic regression (LR) and artificial neural networks (ANN) are two examples. These models are based on 2 distinct yet similar fields; statistics and computer science 9 . Compared to LR, ANN has various benefits: requiring less statistical training, detecting potential interactions between predictors, and complex nonlinear correlations. However, drawbacks include its black-box nature, the need for more complex computing procedures, the empirical nature of model construction, and the possibility of over-fitting the data, which could compromise the model’s ability to generalize 10 . Support Vector Machines (SVM) is an algorithmic application of concepts from statistical learning, which helps constructing reliable estimators from data 11 . By resolving a constrained quadratic optimization problem, SVM construct the best separation boundaries between data sets. Different levels of nonlinearity and flexibility can be incorporated into the model by employing different kernel functions. SVM is developed from sophisticated statistical concepts and limitations on the generalization error can be eliminated 12 & 13 . Our study aims at exploring different models which can help in predicting the outcome of MUS. Materials and Methods All women underwent MUS in our facility from January 2002 to January 2020 with a minimum follow- up of 1 year, were retrospectively studied. All methods were performed in accordance with the relevant guidelines and regulations. Inclusion and exclusion criteria were similar to previous report 7 . 257 patients were contacted by phone and asked to attend an outpatient clinic visit. Informed consent was obtained from all patients. The study design and protocol were approved by the local ethical/scientific committee of UNC. Confounding factors were: age, body mass index (BMI), parity, previous pelvic surgery, pre-operative urodynamics (UDS).The follow up visits, included per vaginal examination, stress test, pad test, post-void residual (PVR) and symptom scores. The primary outcome is the construction of a prediction model that selects the patient with the best success rate. Cure is defined according to objective criteria (a negative stress test, a negative 1-hour pad test and no retreatment) and subjective criteria (self-reported absence of symptoms, no leakage episodes). Failure was defined as persistent stress component. Patients’ data were retrieved and reviewed regarding demographic data, surgical history, preoperative examination, pre-operative UDS, type of the sling, concomitant repair of prolapse, and BMI which was classified into values of more or less than 30. Parity was classified into values of more or less than 3. Abdominal leak point pressure (ALPP) was classified into 3 grades; > 90 (grade 1), 90 − 60 (grade 2) and < 60 (grade 3) 14 . Pre-operative bladder capacity was classified as normal or low (< 250 ml). The type of sling used was TVT, TOT or PVS. Statistical analysis was carried out using SPSS version 24. In phase I, variables were categorical and Chi-Square test and McNemar’s test were used. Spearman’s correlation coefficient was used to define the association between variables. Binomial logistic regression analysis was used for the evaluation of the impact of independent variables on the prediction of the outcome of surgery. Phase II included analysis of data through AI model (ANN and SVM). The output was divided into success or failure. ANN consists of neurons in several layers, where each neuron is considered a mathematical unit. Each input is given a weight. During training, the weights and biases of all neurons get modified as the training continues with the target of reaching the best accuracy. Our model consists of 3 layers: input layer, a hidden layer, and an output layer. The first has 10 neurons (the number of input features). The hidden layer has 13 neurons and the output layer has 2 which correspond to the output classes 0 and 1. The first 2 layers use the Rectified Linear Unit (ReLU) as the activation function while the output layer uses the Log-Softmax. $$\:ReLU\left(x\right)=\text{max}\left(0,\:x\right)$$ $$\:\text{log}\_\text{s}\text{o}\text{f}\text{t}\text{m}\text{a}\text{x}\left({x}_{j}\right)=\text{log}\left(\frac{{exp}\left({x}_{j}\right)}{{\sum\:}_{i=0}^{c-1}{exp}\left({x}_{i}\right)}\right)\:\:\:\:\text{w}\text{h}\text{e}\text{r}\text{e}\:\text{c}\:\text{i}\text{s}\:\text{t}\text{h}\text{e}\:\text{n}\text{u}\text{m}\text{b}\text{e}\text{r}\:\text{o}\text{f}\:\text{c}\text{l}\text{a}\text{s}\text{s}\text{e}\text{s}\:$$ In our study, we used the negative log-likelihood loss: $$\:\text{n}\text{e}\text{g}\text{a}\text{t}\text{i}\text{v}\text{e}\_\text{l}\text{o}\text{g}\_\text{l}\text{i}\text{k}\text{e}\text{l}\text{i}\text{h}\text{o}\text{o}\text{d}\left(\text{X},\:\text{c}\right)=\:-{X}_{c}$$ With this loss, we can calculate the gradients for each weight and bias of each neuron with a proper optimization function. We used the adaptive moment estimation (ADAM) optimizer, which modifies the weights and biases with the gradients calculated from the loss function. We trained the model for 50 epochs and used that number for quick redoing of iterations. Results Phase I: Analysis of data showed no statistical significance regarding different age groups or BMI groups. However, cases with BMI over 30 had the highest failure . Parity was statistically insignificant even though more failures were noted when parity was > 3. Women with previous pelvic surgery showed higher failure rate than those who had no pelvic surgery (P value <0.05) (table 1). Analysis of pre-operative UDS showed statistical significance regarding ALPP and pre-operative maximum bladder capacity. ALPP is thought to be a crucial predictor for the outcome of MUS. Patients with ALPP below 60 cmH2O showed higher failure rate than those with over 60 H2O (P< 0.05) . Also, low bladder capacity before surgery was accompanied with higher failure rate than those with normal capacity (P<0.001) . A moderate correlation was reported between pre-operative bladder capacity and the outcome of surgery ( r = 0.4). (Supplementary figure 1) Increased failure rate was noted in cases having TOT. (P<0.05), while concomitant repair of POP, had no effect on the outcome of surgery. (Table 1). Logistic regression: Binomial logistic regression was performed including 151 patients in total, to assess the effects of age, BMI, parity, previous pelvic surgery (PPS), abdominal leak point pressure (ALPP), pre-operative maximum bladder capacity (Pre-Cap), uninhibited contraction (UC), concomitant repair of POP (CRPOP), and the type of the sling (independent variables) on the likelihood of success. The LR model was statistically significant in prediction of the results with an accuracy of 90.7% [X 2 (11) = 46.24, P < 0.001]. According to the accuracy of this model, the area under the ROC curve was 0.93 (95% CI 0.883 to 0.977) (Figure 1) , which is important in discrimination according to Hosmer et al, 15 with overall accuracy 90.7%, positive predictive value of 61.5% and negative predictive value of 93.4%. Many predictive variables of this model were found statistically significant in the prediction of dependent variable as shown in table 2, which demonstrates that: patients with previous pelvic surgery were 8 times more likely to have failure than those without, patients with 90 and 90-60 ALPP, respectively, patients with low pre-operative maximum bladder capacity had 29 times higher odds to fail surgery than those with normal capacity. Spearman’s correlation coefficient between bladder capacity and outcome of surgery was strong with r = 0.415 (P<0.001) (Figure 2) Patients with TOT sling type had 22 times higher odds to fail surgery than those with PVS. Phase II: Despite the promising results of binominal LR model, we explored ANN in an attempt to reach more accurate predictability. The training set consisted of the records of 90 patients. After the network was trained accordingly, it predicted the outcome in a further 61 patients who comprised the testing set. The network was blinded to the output in the testing set. We evaluated the sensitivity and specificity of training as well as the testing sets using a confusion matrix. Figure 3 depicts the construction of the ANN. Because of data imbalance and the relatively-small sample size, the neural network plateaued at 90.14% accuracy and F1-Score was 94.8% . Accuracy of ANN in discrimination between success and failure rendered an area under ROC curve of 0.7232 . (Figure 4) The ANN model was not able to predict a single failure case. Therefore, we run our data via SVM and calculated accuracy, sensitivity, specificity, positive and negative predictive values. Figure 2 shows the structure of the ANN model used. The accuracy of the SVM model in the training set (using the records of 151 patients) was 93% accuracy and 96% F1-score. Table 3 shows the confusion matrix of SVM . In this model, accuracy is acceptable but its capability of prediction of failure is still unsatisfactory as positive predictive value did not exceed 40%. Discussion In our study, cases were done only by 2 surgeons, accordingly the effect of the operator as a confounding factor could have been eliminated. BMI ranged from 21.6 to 34.7 and despite of having statistically insignificant impact on the outcome. Our results were supported by the study of Bach et al 16 who reported low incidence of failure among patients with similar BMI range. Patients with BMI ranged from 35 to 50 reported higher incidence of failure and they should be offered weight loss first before surgery. This is going along with what Lee et al 17 have found in 138 women with SUI who underwent TVT and concluded that high BMI, low ALPP, and high grade of incontinence may impair the cure rate of the TVT. Salhi et al did a systematic review to evaluate the effect of previous pelvic surgery on the outcome of MUS. They conlcuded that one of the main predictive variables for adverse events following MUS was previous pelvic surgery [OR: 3.7 (CI 95%: 1.14–12.33); P = 0.029] 18 and this is similar to what we found in our study where previous pelvic surgery is associated with higher failure rate [OR: 7.847 (CI 95%: 1.642–37.504); P < 0.05]. Nager et al analyzed 260 cases of failure post MUS and reported that when ALPP is less than 86 cm H2O, risk of failure is 2-folds, regardless of the sling type [OR 2.23 (CI 95%: 1.20–4.14)] 19 which is similar to what we reported in our study, when ALPP was less than 60 H2O, the chance of failure was 24 - and 6 -times higher odds to have failure than patients with > 90 and 90 − 60 ALPP, respectively [OR 0.041(CI 95%: 0.002– 0.879), p < 0.05]. In a landmark study including 565 women followed for 12-month, the rate of objectively-assessed success was 80.8% in the retropubic-sling group and 77.7% in the TOT group (3.0 percentage-point difference; 95% [CI], − 3.6 to 9.6) 20 . In our study, 151 patients had a success rate of 89.1% in the retropubic-sling group and 76.6% in the TOT group [OR :0.045 (CI 95%: 0.004–0.464), p < 0.01]. Data on statistical models that predict the outcome of MUS are scarce. Through LR, four prediction models were applied to the Trial of Mid-urethral Slings (TOMUS) data set, to predict bothersome SUI, positive stress test, bothersome UUI, and adverse events within 12 months. The accuracy of these models reached 73% for discrimination between women who will or will not develop UI and 66% for prediction of adverse events 21 & 22 . In our study, success was defined as absence of SUI during follow up. UUI was also evaluated and treated but not considered as failure. Our prediction model based on LR achieved an overall accuracy of 90.7%. Our ANN is a back-propagation, feed forward type. Similar models were used in urology to diagnose and predict the prognosis of prostatic cancer 23 & 24 achieving a positive predictive value of 94% for survival, and to form a reliable diagnostic tool based on symptoms and objective measurements 25 . As a machine learning tool for classification, SVM has gained popularity. It is straightforward and is considered as one type of data mining which is defined as obtaining valuable information from sizable data sets 26 & 27 Also, SVM was used in oncology to predict 5-year overall survival after radical cystectomy 28 , post-cystectomy recurrence and survival 29 and to differentiate angiomyolipoma from renal cell carcinoma based on texture analysis of CT images with 93.9% accuracy and 87.8% sensitivity 30 . Building a statistical model regarding outcome of MUS surgery with high accuracy and sensitivity is applicable through LR. The use of AI is a good alternative to obtain valuable prediction of outcome of sling surgery. A larger sample size is needed to obtain better prediction. We plan to further include more cases to our model so that we can improve predictive outcome. Declarations Data Availability: Data of the study are available in request from the corresponding author Conflict of interest: None of the authors has any conflict of interest Source of funding: Institutional Ethical statement: The study was approved by the urology department board before initiated. All patients provided written informed consent upon enrollment No trial registration number was obtained as the study is a retrospective data analysis Animal Studies (N/A.) Author’s contribution: B S Wadie: Designed the study, performed surgery and revised the manuscript A Abdelrasheed: Collected the data and drafted the manuscript M Taha: Performed statistical analysis A Abdelrahman: Performed the ANN testing B Mohamed: Shared in ANN development A Saber: Performed SVM construction A Badawi: Oversaw the development of ANN and SVM models References Ebbesen MH, Hunskaar S, Rortveit G et al: Prevalence, incidence and remission of urinary incontinence ‎in women: longitudinal data from the Norwegian HUNT study (EPINCONT). BMC urol. 2013; 13(1):1–10.‎ MacLennan AH, Taylor AW, Wilson DH et al: The prevalence of pelvic floor disorders and their ‎relationship to gender, age, parity and mode of delivery. BJOG. 2000; 12:1460-70.‎ Minassian VA, Stewart WF, Wood GC: Urinary incontinence in women: variation in prevalence ‎estimates and risk factors. Obst.Gynecol. 2008; 111(2):324 − 31.‎ Melville JL, Katon W, Delaney K et al: Urinary incontinence in US women: a population-based study. Arch.Int.Med. ‎2005; 165(5):537 − 42‎ Ulmsten U, Henriksson L, Johnson P et al: An ambulatory surgical procedure under local anesthesia for ‎treatment of female urinary incontinence. Int Urogynecol J. 1996; 7:81 − 6‎ Albo ME, Litman HJ, Richter HE et al: Treatment success of retropubic and transobturator mid urethral ‎slings at 24 months. J.Urol. 2012; 188(6):2281-7.‎ Wadie BS, Elhefnawy AS.: TVT versus TOT, 2-year prospective randomized study. WJU. 2013; 31(3):645-‎‎9.‎ Novara G, Galfano A, Boscolo-Berto R et al: Complication rates of tension-free midurethral slings in the ‎treatment of female stress urinary incontinence: a systematic review and meta-analysis of randomized ‎controlled trials comparing tension-free midurethral tapes to other surgical procedures and different ‎devices. Euro.Urol. 2008; 53(2):288–309.‎ Dreiseitl S, Ohno-Machado L: Logistic regression and artificial neural network classification models: a ‎methodology review. J Biomed Inform. 2002; 35(5):352-9.‎ Tu JV.: Advantages and disadvantages of using artificial neural networks versus logistic regression for ‎predicting medical outcomes. J Clin Epidemiol. 1996; 49(11):1225-31.‎ Vapnik VN, Vapnik VN.: Introduction: Four periods in the research of the learning problem. The nature ‎of statistical learning theory. 1–15, 2000. Cristianini N, Shawe-Taylor J.: An introduction to support vector machines and other kernel-based ‎learning methods: Cambridge University press, 2000. Schölkopf B, Smola AJ, Bach F.: Learning with kernels: support vector machines, regularization, ‎optimization, and beyond: MIT press; 2002.‎ McGuire EJ, Fitzpatrick CC, Wan J et al: Clinical assessment of urethral sphincter function. J Urol. ‎‎1993; 150 (5):1452-4.‎ Hosmer Jr DW, Lemeshow S, Sturdivant RX.: Applied logistic regression: John Wiley & Sons, 2013 Bach F, Hill S, Toozs-Hobson P.: The effect of body mass index on retropubic midurethral slings. Am J ‎Obstet Gynecol. 2019; 220(4):371-e1.‎ Lee KS, Choo MS, Doo CK, et al: The long term (5-years) objective TVT success rate does not depend on predictive factors at multivariate analysis: a multicentre retrospective study. 2008, Eur Urol. 53(1):176 − 82. Salhi Y, Vieillefosse S, Vandekerckhove M et al: Predictive factors of immediate post-operative acute ‎urinary retention or voiding dysfunction following mid-urethral sling surgery: a literature review. ‎Progres en Urologie. 2020; 30(17):1118-25.‎ Nager CW, Sirls L, Litman HJ et al: Baseline urodynamic predictors of treatment failure 1 year after mid ‎urethral sling surgery. J.Urol. 2011; 186(2):597–603.‎ Richter HE, Albo ME, Zyczynski HM et al: Retropubic versus Transobturator Midurethral Slings for ‎Stress Incontinence. NEJM 2010; 362(22):2066-76.‎ Urinary Incontinence Treatment Network: The trial of mid-urethral slings (TOMUS): design and ‎methodology. J Appl Res. 2008; 8(1)‎ Jelovsek JE, Hill AJ, Chagin KM, et al: Predicting Risk of Urinary Incontinence and Adverse Events After ‎Midurethral Sling Surgery in Women. Obstet.Gynecol. 2016; 127(2).‎ Snow PB, Smith DS, Catalona WJ.: Artificial neural networks in the diagnosis and prognosis of prostate ‎cancer: a pilot study. J.Urol. 1994; 152(5):1923-6.‎ tamey TA, Barnhill SD, Zhang Z et al: Effectiveness of ProstAsure in detecting prostate cancer (PCa) ‎and benign prostatic hyperplasia (BPH) in men age 50 and older. J Urol. 1996; 155(Suppl):436A.‎ Wadie BS, Badawi AM, Ghoneim MA.: The relationship of the international prostate symptom sscore ‎and objective parameters for diagnosing bladder outlet obstruction. Part II the potential usefulness of ‎artificial neural network. J. Urol. 2001; 165(1):35 − 7.‎ Wang L.: Support vector machines: theory and applications: Springer Science & Business Media.‎ 2005. Kecman V.: Learning and soft computing: support vector machines, neural networks, and fuzzy logic ‎models: MIT press.‎ 2001. Wang G, Zhang G, Choi K-S et al: Output based transfer learning with least squares support vector machine and its application in bladder cancer prognosis. Neurocomputing.(2020; 387:279 − 92. Hasnain Z, Mason J, Gill K et al: Machine learning models for predicting post-cystectomy recurrence ‎and survival in bladder cancer patients. PloS One. 2019; 14(2):e0210976.‎ Feng Z, Rong P, Cao P, et al.: Machine learning-based quantitative texture analysis of CT images of small ‎renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur.Rad. 2018; 28:1625-33‎ Tables Table 1 to 3 are available in the Supplementary Files section. Supplementary Figure Supplementary Figure 1 is not available with this version. Additional Declarations No competing interests reported. Supplementary Files Table1.docx Table2.docx Table3.docx Cite Share Download PDF Status: Published Journal Publication published 07 Aug, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 08 Apr, 2025 Reviews received at journal 05 Feb, 2025 Reviewers agreed at journal 05 Feb, 2025 Reviews received at journal 11 Jan, 2025 Reviewers agreed at journal 07 Jan, 2025 Reviewers agreed at journal 07 Jan, 2025 Reviewers invited by journal 07 Jan, 2025 Editor assigned by journal 07 Jan, 2025 Editor invited by journal 19 Dec, 2024 Submission checks completed at journal 19 Dec, 2024 First submitted to journal 10 Dec, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5617887","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":392386252,"identity":"56d18935-de5c-4de6-87d6-c9540c407c5b","order_by":0,"name":"Ahmed Abdelrasheed","email":"","orcid":"","institution":"Urology and Nephrology Center, Mansoura university, Mansoura, EGYPT","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Abdelrasheed","suffix":""},{"id":392386257,"identity":"903f3c55-cff1-4f9f-94a0-caece26b4b48","order_by":1,"name":"Mohammed Taha","email":"","orcid":"","institution":"Urology and Nephrology Center, Mansoura university, Mansoura, EGYPT","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"","lastName":"Taha","suffix":""},{"id":392386258,"identity":"f215310e-780d-4e78-963e-c7d44c63d1d9","order_by":2,"name":"Ahmed Abdelrahman","email":"","orcid":"","institution":"Cairo University","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Abdelrahman","suffix":""},{"id":392386259,"identity":"00d26c83-7a33-4d33-b830-b53f4dc03451","order_by":3,"name":"Bassam Mohamed","email":"","orcid":"","institution":"Cairo University","correspondingAuthor":false,"prefix":"","firstName":"Bassam","middleName":"","lastName":"Mohamed","suffix":""},{"id":392386260,"identity":"85767ee7-2a00-40be-ae08-7876ec89ca63","order_by":4,"name":"Alaa Saber","email":"","orcid":"","institution":"Cairo University","correspondingAuthor":false,"prefix":"","firstName":"Alaa","middleName":"","lastName":"Saber","suffix":""},{"id":392386261,"identity":"1aa61fc2-f3d1-46c9-970c-3faefc2b5a94","order_by":5,"name":"Ahmed Badawi","email":"","orcid":"","institution":"Cairo University","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Badawi","suffix":""},{"id":392386262,"identity":"1de36945-0e68-47e5-9382-a1bc398d97e0","order_by":6,"name":"Bassem Wadie","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABB0lEQVRIiWNgGAWjYBACAwQzsYHhA5QpQbQWxhkkaklgYOYhRos5+/HHHz7mMCT2tyc3PrbNscuTb2A+eJuHwcauAYcWy54cM8mZ2xgSZ5x52Gycuy252OAAW7I1D0NaMi4tBgdy2Jh5tzHkNtxIbJPO3cacuIGBx0yah+FwMk6/nH/++PNfoJb5NxLbf1tuq0+c38D/DajlP24tNxIMpBmBWjYAbWFm3HY4seEADxtQywE7XFosZ7wxk+zdxlC/EegXION44obDbMaWcwySE3BpMedPf/zh5zYGY7nj6Q+BjOrE+e3ND2+8qbCzx6UFCv4jsZnBDgYlBlIBIVtGwSgYBaNg5AAA3k9a9FTelSQAAAAASUVORK5CYII=","orcid":"","institution":"Urology and Nephrology Center, Mansoura university, Mansoura, EGYPT","correspondingAuthor":true,"prefix":"","firstName":"Bassem","middleName":"","lastName":"Wadie","suffix":""}],"badges":[],"createdAt":"2024-12-10 15:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5617887/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5617887/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-12826-6","type":"published","date":"2025-08-07T15:57:08+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":72363004,"identity":"b5159d3c-a5df-4cdc-a0b0-dbf018938a92","added_by":"auto","created_at":"2024-12-26 06:11:14","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":20104,"visible":true,"origin":"","legend":"\u003cp\u003eROC curve for accuracy of LR model on the outcome of MUS.\u003c/p\u003e","description":"","filename":"Figure131.png","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/251db72654aa326058c089f3.png"},{"id":72363020,"identity":"45b35ad0-5154-4e3a-b086-205b0fe0a7c6","added_by":"auto","created_at":"2024-12-26 06:11:15","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":389688,"visible":true,"origin":"","legend":"\u003cp\u003eA heat map of the Spearman’s correlation coefficient between each pair of features.\u003c/p\u003e","description":"","filename":"Figure132.png","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/5be03049aa868bffe894b19d.png"},{"id":72363708,"identity":"2b898fb3-68f9-4bd5-8e89-179de8dd9517","added_by":"auto","created_at":"2024-12-26 06:19:14","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":168006,"visible":true,"origin":"","legend":"\u003cp\u003eThe structure of feed forward –back propagation ANN model.\u003c/p\u003e","description":"","filename":"Figure133.png","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/f78d9bf6275da26ffd57fdd7.png"},{"id":72363707,"identity":"5ab49027-2074-4a45-80ac-aaaea9035ce0","added_by":"auto","created_at":"2024-12-26 06:19:14","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":269731,"visible":true,"origin":"","legend":"\u003cp\u003eA box plot of the AUC of ROC scores and a plot of the mean of the scores resulted from a 10-repeats 5-fold cross validation RFE for (a) random forest classifier, (b) decision tree classifier, (c) gradient boosting classifier, and (d) extra trees ensemble classifier.\u003c/p\u003e","description":"","filename":"Figure134.png","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/105b346b60d52839cb524779.png"},{"id":88814102,"identity":"81d787e1-8269-41a5-a2dc-9f7a56219ebd","added_by":"auto","created_at":"2025-08-11 16:06:21","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1392696,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/0c8210f7-2bdb-40da-b869-2c89bae4a11d.pdf"},{"id":72363002,"identity":"535e1eff-4184-460c-af43-c1fa4e826037","added_by":"auto","created_at":"2024-12-26 06:11:14","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":17891,"visible":true,"origin":"","legend":"","description":"","filename":"Table1.docx","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/bf823c57a3060356884de74f.docx"},{"id":72363009,"identity":"1b80c1c6-fb04-4fc4-94fc-8724961edfc1","added_by":"auto","created_at":"2024-12-26 06:11:14","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":16515,"visible":true,"origin":"","legend":"","description":"","filename":"Table2.docx","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/4e93e2c6612af1cf524a391f.docx"},{"id":72363008,"identity":"d2beb32d-c710-4be3-8af5-a0286ecd8b98","added_by":"auto","created_at":"2024-12-26 06:11:14","extension":"docx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":13586,"visible":true,"origin":"","legend":"","description":"","filename":"Table3.docx","url":"https://assets-eu.researchsquare.com/files/rs-5617887/v1/1409cc64075caf360fea893d.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of success of slings in female stress incontinence, statistical and AI modeling","fulltext":[{"header":"Introduction","content":"\u003cp\u003eStress urinary incontinence (SUI) is the most prevalent type of urinary incontinence (UI). Age, parity, and obesity were globally considered risk factors for the development of SUI. Other reports demonstrated factors such as hysterectomy, medical co morbidities, smoking, DM, and major depression \u003csup\u003e1\u003c/sup\u003e\u003csup\u003e2\u003c/sup\u003e\u003csup\u003e3\u003c/sup\u003e\u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e4\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eWhile pubovaginal sling (PVS) is the gold standard, the use of mid-urethral slings (MUS) became the most popular procedure since Ulmsten published his study on tension-free vaginal tape (TVT)\u003csup\u003e5\u003c/sup\u003e\u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e6\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn addition, some studies demonstrated that primary and secondary outcomes of PVS and TVT were better than those of TOT\u003csup\u003e7\u003c/sup\u003e\u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e8\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eDifferent predictive models for prognostic and diagnostic purposes were created using \"experience\u0026rdquo;. Logistic regression (LR) and artificial neural networks (ANN) are two examples. These models are based on 2 distinct yet similar fields; statistics and computer science\u003csup\u003e9\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eCompared to LR, ANN has various benefits: requiring less statistical training, detecting potential interactions between predictors, and complex nonlinear correlations. However, drawbacks include its black-box nature, the need for more complex computing procedures, the empirical nature of model construction, and the possibility of over-fitting the data, which could compromise the model\u0026rsquo;s ability to generalize\u003csup\u003e10\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eSupport Vector Machines (SVM) is an algorithmic application of concepts from statistical learning, which helps constructing reliable estimators from data\u003csup\u003e11\u003c/sup\u003e. By resolving a constrained quadratic optimization problem, SVM construct the best separation boundaries between data sets. Different levels of nonlinearity and flexibility can be incorporated into the model by employing different kernel functions. SVM is developed from sophisticated statistical concepts and limitations on the generalization error can be eliminated\u003csup\u003e12\u003c/sup\u003e\u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e13\u003c/sup\u003e. Our study aims at exploring different models which can help in predicting the outcome of MUS.\u003c/p\u003e"},{"header":"Materials and Methods","content":"\u003cp\u003eAll women underwent MUS in our facility from January 2002 to January 2020 with a minimum follow- up of 1 year, were retrospectively studied. \u003cem\u003e All methods were performed in accordance with the relevant guidelines and regulations.\u003c/em\u003e\u003c/p\u003e \u003cp\u003eInclusion and exclusion criteria were similar to previous report \u003csup\u003e7\u003c/sup\u003e. 257 patients were contacted by phone and asked to attend an outpatient clinic visit. Informed consent was obtained from all patients. The study design and protocol were approved by the local ethical/scientific committee of UNC.\u003c/p\u003e \u003cp\u003eConfounding factors were: age, body mass index (BMI), parity, previous pelvic surgery, pre-operative urodynamics (UDS).The follow up visits, included per vaginal examination, stress test, pad test, post-void residual (PVR) and symptom scores.\u003c/p\u003e \u003cp\u003eThe primary outcome is the construction of a prediction model that selects the patient with the best success rate. Cure is defined according to objective criteria (a negative stress test, a negative 1-hour pad test and no retreatment) and subjective criteria (self-reported absence of symptoms, no leakage episodes). Failure was defined as persistent stress component.\u003c/p\u003e \u003cp\u003ePatients\u0026rsquo; data were retrieved and reviewed regarding demographic data, surgical history, preoperative examination, pre-operative UDS, type of the sling, concomitant repair of prolapse, and BMI which was classified into values of more or less than 30. Parity was classified into values of more or less than 3. Abdominal leak point pressure (ALPP) was classified into 3 grades; \u0026gt; 90 (grade 1), 90\u0026thinsp;\u0026minus;\u0026thinsp;60 (grade 2) and \u0026lt;\u0026thinsp;60 (grade 3)\u003csup\u003e14\u003c/sup\u003e. Pre-operative bladder capacity was classified as normal or low (\u0026lt;\u0026thinsp;250 ml). The type of sling used was TVT, TOT or PVS.\u003c/p\u003e \u003cp\u003eStatistical analysis was carried out using SPSS version 24. In phase I, variables were categorical and Chi-Square test and McNemar\u0026rsquo;s test were used. Spearman\u0026rsquo;s correlation coefficient was used to define the association between variables. Binomial logistic regression analysis was used for the evaluation of the impact of independent variables on the prediction of the outcome of surgery.\u003c/p\u003e \u003cp\u003e \u003cb\u003ePhase II\u003c/b\u003e included analysis of data through AI model (ANN and SVM). The output was divided into success or failure.\u003c/p\u003e \u003cp\u003eANN consists of neurons in several layers, where each neuron is considered a mathematical unit. Each input is given a weight. During training, the weights and biases of all neurons get modified as the training continues with the target of reaching the best accuracy. Our model consists of 3 layers: input layer, a hidden layer, and an output layer. The first has 10 neurons (the number of input features). The hidden layer has 13 neurons and the output layer has 2 which correspond to the output classes 0 and 1. The first 2 layers use the Rectified Linear Unit (ReLU) as the activation function while the output layer uses the Log-Softmax.\u003cdiv id=\"Equa\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equa\" name=\"EquationSource\"\u003e\n$$\\:ReLU\\left(x\\right)=\\text{max}\\left(0,\\:x\\right)$$\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Equb\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equb\" name=\"EquationSource\"\u003e\n$$\\:\\text{log}\\_\\text{s}\\text{o}\\text{f}\\text{t}\\text{m}\\text{a}\\text{x}\\left({x}_{j}\\right)=\\text{log}\\left(\\frac{{exp}\\left({x}_{j}\\right)}{{\\sum\\:}_{i=0}^{c-1}{exp}\\left({x}_{i}\\right)}\\right)\\:\\:\\:\\:\\text{w}\\text{h}\\text{e}\\text{r}\\text{e}\\:\\text{c}\\:\\text{i}\\text{s}\\:\\text{t}\\text{h}\\text{e}\\:\\text{n}\\text{u}\\text{m}\\text{b}\\text{e}\\text{r}\\:\\text{o}\\text{f}\\:\\text{c}\\text{l}\\text{a}\\text{s}\\text{s}\\text{e}\\text{s}\\:$$\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eIn our study, we used the negative log-likelihood loss:\u003cdiv id=\"Equc\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equc\" name=\"EquationSource\"\u003e\n$$\\:\\text{n}\\text{e}\\text{g}\\text{a}\\text{t}\\text{i}\\text{v}\\text{e}\\_\\text{l}\\text{o}\\text{g}\\_\\text{l}\\text{i}\\text{k}\\text{e}\\text{l}\\text{i}\\text{h}\\text{o}\\text{o}\\text{d}\\left(\\text{X},\\:\\text{c}\\right)=\\:-{X}_{c}$$\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eWith this loss, we can calculate the gradients for each weight and bias of each neuron with a proper optimization function. We used the adaptive moment estimation (ADAM) optimizer, which modifies the weights and biases with the gradients calculated from the loss function. We trained the model for 50 epochs and used that number for quick redoing of iterations.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003e\u003cu\u003ePhase I:\u003c/u\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAnalysis of data showed no statistical significance regarding different age groups or BMI groups. However, cases with BMI over 30 had the highest failure\u003cstrong\u003e.\u0026nbsp;\u003c/strong\u003eParity was statistically insignificant even though more failures were noted when parity was \u0026gt; 3. Women with previous pelvic surgery showed higher failure rate than those who had no pelvic surgery (P value \u0026lt;0.05) \u003cstrong\u003e(table 1).\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAnalysis of pre-operative UDS showed statistical significance regarding ALPP and pre-operative maximum bladder capacity. ALPP is thought to be a crucial predictor for the outcome of MUS. Patients with ALPP below 60 cmH2O showed higher failure rate than those with over 60 H2O (P\u0026lt; 0.05)\u003cstrong\u003e.\u0026nbsp;\u003c/strong\u003eAlso, low bladder capacity before surgery was accompanied with higher failure rate than those with normal capacity (P\u0026lt;0.001)\u003cstrong\u003e.\u003c/strong\u003e A moderate correlation was reported between pre-operative bladder capacity and the outcome of surgery (\u003cem\u003er\u003c/em\u003e\u003cstrong\u003e\u003csub\u003e\u0026nbsp;\u003c/sub\u003e\u003c/strong\u003e= 0.4). (Supplementary figure 1)\u003c/p\u003e\n\u003cp\u003eIncreased failure rate was noted in cases having TOT. (P\u0026lt;0.05), while concomitant repair of POP, had no effect on the outcome of surgery. (Table 1).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u003cu\u003eLogistic regression:\u003c/u\u003e\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBinomial logistic regression was performed including 151 patients in total, to assess the effects of age, BMI, parity, previous pelvic surgery (PPS), abdominal leak point pressure (ALPP), pre-operative maximum bladder capacity (Pre-Cap), uninhibited contraction (UC), concomitant repair of POP (CRPOP), and the type of the sling (independent variables) on the likelihood of success. The LR model was statistically significant in prediction of the results with an accuracy of 90.7% [X\u003csup\u003e2\u003c/sup\u003e (11) = 46.24, P \u0026lt; 0.001]. According to the accuracy of this model, the area under the ROC curve was 0.93 (95% CI 0.883 to 0.977)\u003cstrong\u003e\u0026nbsp;(Figure 1)\u003c/strong\u003e, which is important in discrimination according to Hosmer et al,\u003csup\u003e15\u003c/sup\u003e with overall accuracy 90.7%, positive predictive value of 61.5% and negative predictive value of 93.4%.\u003c/p\u003e\n\u003cp\u003eMany predictive variables of this model were found statistically significant in the prediction of dependent variable as shown in \u003cstrong\u003etable 2,\u003c/strong\u003e which demonstrates that: patients with previous pelvic surgery were \u003cstrong\u003e8\u003c/strong\u003e times more likely to have failure than those without, patients with \u003cstrong\u003e\u0026lt; 60\u003c/strong\u003e ALPP had \u003cstrong\u003e24\u003c/strong\u003e- and \u003cstrong\u003e6\u003c/strong\u003e-times higher odds to have failure than patients with \u003cstrong\u003e\u0026gt; 90\u003c/strong\u003e and \u003cstrong\u003e90-60\u003c/strong\u003e ALPP, respectively, patients with low pre-operative maximum bladder capacity had \u003cstrong\u003e29\u003c/strong\u003e times higher odds to fail surgery than those with normal capacity. Spearman\u0026rsquo;s correlation coefficient between bladder capacity and outcome of surgery was strong with \u003cem\u003er\u003c/em\u003e = 0.415 (P\u0026lt;0.001) (Figure 2) Patients with TOT sling type had \u003cstrong\u003e22\u003c/strong\u003e times higher odds to fail surgery than those with PVS.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cu\u003ePhase II:\u003c/u\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDespite the promising results of binominal LR model, we explored ANN in an attempt to reach more accurate predictability.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe training set consisted of the records of 90 patients. After the network was trained accordingly, it predicted the outcome in a further 61 patients who comprised the testing set. The network was blinded to the output in the testing set. We evaluated the sensitivity and specificity of training as well as the testing sets using a confusion matrix. Figure 3 depicts the construction of the ANN.\u003c/p\u003e\n\u003cp\u003eBecause of data imbalance and the relatively-small sample size, the neural network plateaued at 90.14% accuracy and F1-Score was 94.8%\u003cstrong\u003e.\u003c/strong\u003e Accuracy of ANN in discrimination between success and failure rendered an area under ROC curve of 0.7232\u003cstrong\u003e.\u0026nbsp;\u003c/strong\u003e(Figure 4)\u003c/p\u003e\n\u003cp\u003eThe ANN model was not able to predict a single failure case. Therefore, we run our data via SVM and calculated accuracy, sensitivity, specificity, positive and negative predictive values. Figure 2 shows the structure of the ANN model used.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;The accuracy of the SVM model in the training set (using the records of 151 patients) was 93% accuracy and 96% F1-score. \u003cstrong\u003eTable 3\u003c/strong\u003e shows the confusion matrix of SVM\u003cstrong\u003e.\u003c/strong\u003e In this model, accuracy is acceptable but its capability of prediction of failure is still unsatisfactory as positive predictive value did not exceed 40%.\u0026nbsp;\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn our study, cases were done only by 2 surgeons, accordingly the effect of the operator as a confounding factor could have been eliminated.\u003c/p\u003e \u003cp\u003eBMI ranged from 21.6 to 34.7 and despite of having statistically insignificant impact on the outcome. Our results were supported by the study of Bach et al\u003csup\u003e16\u003c/sup\u003e who reported low incidence of failure among patients with similar BMI range. Patients with BMI ranged from 35 to 50 reported higher incidence of failure and they should be offered weight loss first before surgery. This is going along with what Lee et al\u003csup\u003e17\u003c/sup\u003e have found in 138 women with SUI who underwent TVT and concluded that high BMI, low ALPP, and high grade of incontinence may impair the cure rate of the TVT.\u003c/p\u003e \u003cp\u003eSalhi et al did a systematic review to evaluate the effect of previous pelvic surgery on the outcome of MUS. They conlcuded that one of the main predictive variables for adverse events following MUS was previous pelvic surgery [OR: 3.7 (CI 95%: 1.14\u0026ndash;12.33); P\u0026thinsp;=\u0026thinsp;0.029]\u003csup\u003e18\u003c/sup\u003e and this is similar to what we found in our study where previous pelvic surgery is associated with higher failure rate [OR: 7.847 (CI 95%: 1.642\u0026ndash;37.504); P\u0026thinsp;\u0026lt;\u0026thinsp;0.05].\u003c/p\u003e \u003cp\u003eNager et al analyzed 260 cases of failure post MUS and reported that when ALPP is less than 86 cm H2O, risk of failure is 2-folds, regardless of the sling type [OR 2.23 (CI 95%: 1.20\u0026ndash;4.14)]\u003csup\u003e19\u003c/sup\u003e which is similar to what we reported in our study, when ALPP was less than 60 H2O, the chance of failure was \u003cb\u003e24\u003c/b\u003e- and \u003cb\u003e6\u003c/b\u003e-times higher odds to have failure than patients with \u003cb\u003e\u0026gt;\u0026thinsp;90\u003c/b\u003e and \u003cb\u003e90\u0026thinsp;\u0026minus;\u0026thinsp;60\u003c/b\u003e ALPP, respectively [OR 0.041(CI 95%: 0.002\u0026ndash; 0.879), p\u0026thinsp;\u0026lt;\u0026thinsp;0.05].\u003c/p\u003e \u003cp\u003eIn a landmark study including 565 women followed for 12-month, the rate of objectively-assessed success was 80.8% in the retropubic-sling group and 77.7% in the TOT group (3.0 percentage-point difference; 95% [CI], \u0026minus;\u0026thinsp;3.6 to 9.6)\u003csup\u003e20\u003c/sup\u003e. In our study, 151 patients had a success rate of 89.1% in the retropubic-sling group and 76.6% in the TOT group [OR :0.045 (CI 95%: 0.004\u0026ndash;0.464), p\u0026thinsp;\u0026lt;\u0026thinsp;0.01].\u003c/p\u003e \u003cp\u003eData on statistical models that predict the outcome of MUS are scarce. Through LR, four prediction models were applied to the Trial of Mid-urethral Slings (TOMUS) data set, to predict bothersome SUI, positive stress test, bothersome UUI, and adverse events within 12 months. The accuracy of these models reached 73% for discrimination between women who will or will not develop UI and 66% for prediction of adverse events\u003csup\u003e21\u003c/sup\u003e\u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e22\u003c/sup\u003e. In our study, success was defined as absence of SUI during follow up. UUI was also evaluated and treated but not considered as failure. Our prediction model based on LR achieved an overall accuracy of 90.7%.\u003c/p\u003e \u003cp\u003eOur ANN is a back-propagation, feed forward type. Similar models were used in urology to diagnose and predict the prognosis of prostatic cancer\u003csup\u003e23\u003c/sup\u003e \u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e24\u003c/sup\u003e achieving a positive predictive value of 94% for survival, and to form a reliable diagnostic tool based on symptoms and objective measurements\u003csup\u003e25\u003c/sup\u003e. As a machine learning tool for classification, SVM has gained popularity. It is straightforward and is considered as one type of data mining which is defined as obtaining valuable information from sizable data sets \u003csup\u003e26\u003c/sup\u003e \u003csup\u003e\u0026amp;\u003c/sup\u003e\u003csup\u003e27\u003c/sup\u003e\u003c/p\u003e \u003cp\u003eAlso, SVM was used in oncology to predict 5-year overall survival after radical cystectomy\u003csup\u003e28\u003c/sup\u003e, post-cystectomy recurrence and survival\u003csup\u003e29\u003c/sup\u003e and to differentiate angiomyolipoma from renal cell carcinoma based on texture analysis of CT images with 93.9% accuracy and 87.8% sensitivity\u003csup\u003e30\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eBuilding a statistical model regarding outcome of MUS surgery with high accuracy and sensitivity is applicable through LR. The use of AI is a good alternative to obtain valuable prediction of outcome of sling surgery. A larger sample size is needed to obtain better prediction. We plan to further include more cases to our model so that we can improve predictive outcome.\u003c/p\u003e "},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eData Availability:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eData of the study are available in request from the corresponding author\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNone of the authors has any conflict of interest\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSource of funding:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eInstitutional\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical statement:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the urology department board before initiated.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAll patients provided written informed consent upon enrollment\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eNo trial registration number was obtained as the study is a retrospective data analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAnimal Studies\u003c/strong\u003e (N/A.)\u003c/p\u003e\n\u003cp\u003eAuthor\u0026rsquo;s contribution:\u003c/p\u003e\n\u003cp\u003eB S Wadie: Designed the study, performed surgery and revised the manuscript\u003c/p\u003e\n\u003cp\u003eA Abdelrasheed: Collected the data and drafted the manuscript\u003c/p\u003e\n\u003cp\u003eM Taha: Performed statistical analysis\u003c/p\u003e\n\u003cp\u003eA Abdelrahman: Performed the ANN testing\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eB Mohamed: Shared in ANN development\u003c/p\u003e\n\u003cp\u003eA Saber: Performed SVM construction\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eA Badawi: Oversaw the development of ANN and SVM models\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003e Ebbesen MH, Hunskaar S, Rortveit G et al: Prevalence, incidence and remission of urinary incontinence \u0026lrm;in women: longitudinal data from the Norwegian HUNT study (EPINCONT). BMC urol. 2013; 13(1):1\u0026ndash;10.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e MacLennan AH, Taylor AW, Wilson DH et al: The prevalence of pelvic floor disorders and their \u0026lrm;relationship to gender, age, parity and mode of delivery. BJOG. 2000; 12:1460-70.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Minassian VA, Stewart WF, Wood GC: Urinary incontinence in women: variation in prevalence \u0026lrm;estimates and risk factors. Obst.Gynecol. 2008; 111(2):324\u0026thinsp;\u0026minus;\u0026thinsp;31.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Melville JL, Katon W, Delaney K et al: Urinary incontinence in US women: a population-based study. Arch.Int.Med. \u0026lrm;2005; 165(5):537\u0026thinsp;\u0026minus;\u0026thinsp;42\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Ulmsten U, Henriksson L, Johnson P et al: An ambulatory surgical procedure under local anesthesia for \u0026lrm;treatment of female urinary incontinence. Int Urogynecol J. 1996; 7:81\u0026thinsp;\u0026minus;\u0026thinsp;6\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Albo ME, Litman HJ, Richter HE et al: Treatment success of retropubic and transobturator mid urethral \u0026lrm;slings at 24 months. J.Urol. 2012; 188(6):2281-7.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Wadie BS, Elhefnawy AS.: TVT versus TOT, 2-year prospective randomized study. WJU. 2013; 31(3):645-\u0026lrm;\u0026lrm;9.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Novara G, Galfano A, Boscolo-Berto R et al: Complication rates of tension-free midurethral slings in the \u0026lrm;treatment of female stress urinary incontinence: a systematic review and meta-analysis of randomized \u0026lrm;controlled trials comparing tension-free midurethral tapes to other surgical procedures and different \u0026lrm;devices. Euro.Urol. 2008; 53(2):288\u0026ndash;309.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Dreiseitl S, Ohno-Machado L: Logistic regression and artificial neural network classification models: a \u0026lrm;methodology review. J Biomed Inform. 2002; 35(5):352-9.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Tu JV.: Advantages and disadvantages of using artificial neural networks versus logistic regression for \u0026lrm;predicting medical outcomes. J Clin Epidemiol. 1996; 49(11):1225-31.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Vapnik VN, Vapnik VN.: Introduction: Four periods in the research of the learning problem. The nature \u0026lrm;of statistical learning theory. 1\u0026ndash;15, 2000.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Cristianini N, Shawe-Taylor J.: An introduction to support vector machines and other kernel-based \u0026lrm;learning methods: Cambridge University press, 2000.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Sch\u0026ouml;lkopf B, Smola AJ, Bach F.: Learning with kernels: support vector machines, regularization, \u0026lrm;optimization, and beyond: MIT press; 2002.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e McGuire EJ, Fitzpatrick CC, Wan J et al: Clinical assessment of urethral sphincter function. J Urol. \u0026lrm;\u0026lrm;1993; 150 (5):1452-4.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Hosmer Jr DW, Lemeshow S, Sturdivant RX.: Applied logistic regression: John Wiley \u0026amp; Sons, 2013\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Bach F, Hill S, Toozs-Hobson P.: The effect of body mass index on retropubic midurethral slings. Am J \u0026lrm;Obstet Gynecol. 2019; 220(4):371-e1.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Lee KS, Choo MS, Doo CK, et al: The long term (5-years) objective TVT success rate does not depend on predictive factors at multivariate analysis: a multicentre retrospective study. 2008, Eur Urol. 53(1):176\u0026thinsp;\u0026minus;\u0026thinsp;82.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Salhi Y, Vieillefosse S, Vandekerckhove M et al: Predictive factors of immediate post-operative acute \u0026lrm;urinary retention or voiding dysfunction following mid-urethral sling surgery: a literature review. \u0026lrm;Progres en Urologie. 2020; 30(17):1118-25.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Nager CW, Sirls L, Litman HJ et al: Baseline urodynamic predictors of treatment failure 1 year after mid \u0026lrm;urethral sling surgery. J.Urol. 2011; 186(2):597\u0026ndash;603.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Richter HE, Albo ME, Zyczynski HM et al: Retropubic versus Transobturator Midurethral Slings for \u0026lrm;Stress Incontinence. NEJM 2010; 362(22):2066-76.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Urinary Incontinence Treatment Network: The trial of mid-urethral slings (TOMUS): design and \u0026lrm;methodology. J Appl Res. 2008; 8(1)\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Jelovsek JE, Hill AJ, Chagin KM, et al: Predicting Risk of Urinary Incontinence and Adverse Events After \u0026lrm;Midurethral Sling Surgery in Women. Obstet.Gynecol. 2016; 127(2).\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Snow PB, Smith DS, Catalona WJ.: Artificial neural networks in the diagnosis and prognosis of prostate \u0026lrm;cancer: a pilot study. J.Urol. 1994; 152(5):1923-6.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e tamey TA, Barnhill SD, Zhang Z et al: Effectiveness of ProstAsure in detecting prostate cancer (PCa) \u0026lrm;and benign prostatic hyperplasia (BPH) in men age 50 and older. J Urol. 1996; 155(Suppl):436A.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Wadie BS, Badawi AM, Ghoneim MA.: The relationship of the international prostate symptom sscore \u0026lrm;and objective parameters for diagnosing bladder outlet obstruction. Part II the potential usefulness of \u0026lrm;artificial neural network. J. Urol. 2001; 165(1):35\u0026thinsp;\u0026minus;\u0026thinsp;7.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Wang L.: Support vector machines: theory and applications: Springer Science \u0026amp; Business Media.\u0026lrm; 2005.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Kecman V.: Learning and soft computing: support vector machines, neural networks, and fuzzy logic \u0026lrm;models: MIT press.\u0026lrm; 2001.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Wang G, Zhang G, Choi K-S et al: Output based transfer learning with least squares support vector machine and its application in bladder cancer prognosis. Neurocomputing.(2020; 387:279\u0026thinsp;\u0026minus;\u0026thinsp;92.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Hasnain Z, Mason J, Gill K et al: Machine learning models for predicting post-cystectomy recurrence \u0026lrm;and survival in bladder cancer patients. PloS One. 2019; 14(2):e0210976.\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e Feng Z, Rong P, Cao P, et al.: Machine learning-based quantitative texture analysis of CT images of small \u0026lrm;renal masses: differentiation of angiomyolipoma without visible fat from renal cell carcinoma. Eur.Rad. 2018; 28:1625-33\u0026lrm;\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003eTable 1 to 3 are available in the Supplementary Files section.\u003c/p\u003e"},{"header":"Supplementary Figure","content":"\u003cp\u003eSupplementary Figure 1 is not available with this version.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Sling, female, incontinence, prediction, AI","lastPublishedDoi":"10.21203/rs.3.rs-5617887/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5617887/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjectives:\u003c/strong\u003e Studies on predicting the outcome of sling surgery are limited. Most depend on analysis of multiple confounding factors using regression models. However, their prediction results are limited. In this study, we tested a statistical regression model and an AI model for the prediction of the outcome of mid-urethral sling.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods\u003c/strong\u003e: Data were collected from 151 patients who underwent MUS surgery in our center from 2002 to 2022 and confounding factors that affect the outcome of the surgery at a minimum of one year. The study was divided into two phases. Phase I included the construction of a prediction model using binomial logistic regression. In phase II, we applied an AI preferences (Support Vector Machines (SVM) and Artificial neural network (ANN) trying to obtain better predictions.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Phase I: The logistic regression model predicted the outcome of surgery with overall accuracy of 90.7% and positive predictive value of 61.5% [X\u003csup\u003e2\u003c/sup\u003e (11) = 46.24, P \u0026lt; 0.001].\u003c/p\u003e\n\u003cp\u003ePhase II: The data of the patients were entered as 10 features; 9 were predictors and the 10\u003csup\u003eth\u003c/sup\u003e was the output. The output comprised 18 cases designated as ‘failure’ and 133 as ‘success’ output. The best model performance-wise was the (SVM) with 92% accuracy and 96% F1-score, which meets the industrial standards for predictive models. However, ANN produced 90% accuracy and 94% F1-score. However, our sample size is small\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e: Prediction of the outcome of MUS surgery was achieved using different modalities with the best prediction of the outcome obtained by SVM method.\u003c/p\u003e","manuscriptTitle":"Prediction of success of slings in female stress incontinence, statistical and AI modeling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-26 06:11:07","doi":"10.21203/rs.3.rs-5617887/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-08T12:00:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-05T16:56:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"244546450381763227012526604383575403132","date":"2025-02-05T10:51:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-11T18:27:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"213055239741326125420311495871530248430","date":"2025-01-07T12:25:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"71019443823385738476501745523170505221","date":"2025-01-07T12:20:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-01-07T12:18:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-01-07T12:03:23+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-12-19T13:00:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-12-19T12:02:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-12-10T14:59:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"db7104f8-979e-45ed-aa4a-0d1854f39e50","owner":[],"postedDate":"December 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":41827305,"name":"Biological sciences/Biotechnology"},{"id":41827306,"name":"Health sciences/Urology"}],"tags":[],"updatedAt":"2025-08-11T15:59:31+00:00","versionOfRecord":{"articleIdentity":"rs-5617887","link":"https://doi.org/10.1038/s41598-025-12826-6","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-08-07 15:57:08","publishedOnDateReadable":"August 7th, 2025"},"versionCreatedAt":"2024-12-26 06:11:07","video":"","vorDoi":"10.1038/s41598-025-12826-6","vorDoiUrl":"https://doi.org/10.1038/s41598-025-12826-6","workflowStages":[]},"version":"v1","identity":"rs-5617887","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5617887","identity":"rs-5617887","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}