Developing a machine learning model for predicting varicocelectomy outcomes: a pilot study

A further debatable issue in the treatment of varicocele is which men would benefit from a varicocelectomy. Despite the increasing interest in Machine Learning (ML) in urology, there have been limited studies on the detection and prediction of varicocelectomy using artificial intelligence. We aimed to develop a model to predict the improvement in semen parameters after varicocelectomy using ML.The data for male patients who had clinical varicocele, abnormal semen parameters (low sperm concentration, reduced total motile sperm count, decreased progressive motility, and/or poor sperm morphology) and had received a varicocelectomy were recorded retrospectively. Demographic, anthropometric variables, physical examination findings, hematological, radiological, and semen analysis parameters were evaluated. The patients were separated into two groups according to the improvement in total motile sperm count postoperatively as improvement (Group 1) and no improvement (Group 2). The Extra Trees Classifier, Light Gradient Boosting Machine Classifier, eXtreme Gradient Boosting Classifier, Logistic Regression, and Random Forest Classifier techniques were used as ML algorithms.41 males were included in the study. 31 (75.6%) and 10 (24.4%) patients were classified as Group 1 and 2, respectively. The Extra Trees Classifier algorithm was found to be the best ML technique for predictions, according to the accuracy rates (92.3%) with an Area Under Curve of 0.92. We have shown for the first time in the literature that basic laboratory and semen analysis findings can be used to select patients who will benefit from varicocelectomy with the use of five ML methods. ML models could be identified as a new prediction tool for selecting the patients who will benefit from varicocelectomy. More detailed ML studies will be needed a larger number of patients.

Spermiogram; Varicocelectomy; Machine learning; Artificial intelligence

[1] Ghanem MA, Adawi EA, Safan MA, Ghanem AA. Outcome of varicoceles scrotal sclerotherapy in infertile patients with recurrent varicocele. International Archives of Urology and Complications. 2018; 4: 037.

[2] European Association of Urology. EAU guidelines. EAU Guidelines Office: Arnhem, the Netherlands. 2023.

[3] Agarwal A, Cannarella R, Saleh R, Boitrelle F, Gül M, Toprak T, et al. Impact of varicocele repair on semen parameters in infertile men: a systematic review and meta-analysis. The World Journal of Men’s Health. 2023; 41: 289–310.

[4] Cannarella R, Shah R, Hamoda TAA, Boitrelle F, Saleh R, Gul M, et al. Does varicocele repair improve conventional semen parameters? A meta-analytic study of before-after data. The World Journal of Men’s Health. 2024; 42: 92–132.

[5] Persad E, O’Loughlin CA, Kaur S, Wagner G, Matyas N, Hassler-Di Fratta MR, et al. Surgical or radiological treatment for varicoceles in subfertile men. Cochrane Database of Systematic Reviews. 2021; 4: CD000479.

[6] Shomarufov AB, Bozhedomov VA, Sorokin NI, Matyukhov IP, Fozilov AA, Abbosov SA, Kamalov AA. Predictors of microsurgical varicocelectomy efficacy in male infertility treatment: critical assessment and systematization. Asian Journal of Andrology. 2023; 25: 21–28.

[7] Samplaski M, Jarvi K. Prognostic factors for a favorable outcome after varicocele repair in adolescents and adults. Asian Journal of Andrology. 2016; 18: 217–221.

[8] Ghanem MA, Adawi EA, Hakami NA, Ghanem AM, Ghanem HA. The predictive value of the platelet volume parameters in evaluation of varicocelectomy outcome in infertile patients. Andrologia. 2020; 52: e13574.

[9] Eyler Dang L, Hubbard A, Dissak-Delon FN, Chichom Mefire A, Juillard C. Right population, right resources, right algorithm: Using machine learning efficiently and effectively in surgical systems where data are a limited resource. Surgery. 2021; 170: 325–328.

[10] Loftus TJ, Vlaar APJ, Hung AJ, Bihorac A, Dennis BM, Juillard C, et al. Executive summary of the artificial intelligence in surgery series. Surgery. 2022; 171: 1435–1439.

[11] Abid R, Hussein AA, Guru KA. Artificial intelligence in urology: current status and future perspectives. Urologic Clinics of North America. 2024; 51: 117–130.

[12] Ory J, Tradewell MB, Blankstein U, Lima TF, Nackeeran S, Gonzalez DC, et al. Artificial intelligence based machine learning models predict sperm parameter upgrading after varicocele repair: a multi-institutional analysis. The World Journal of Men’s Health. 2022; 40: 618–626.

[13] AlZoubi O, Abu Awad M, Abdalla AM, Samrraie L. Varicocele detection in ultrasound images using deep learning. Multimedia Tools and Applications. 2024; 83: 63617–63634.

[14] Foroughi AA, Yazdanpanah E, Nazeri M, Eghbali T, Arasteh P, Ariafar A. Clinical grading and color Doppler ultrasonography-based grading of varicocele: how compatible are the two grading systems? World Journal of Urology. 2019; 37: 1461–1465.

[15] Dubin L, Amelar RD. Varicocele size and results of varicocelectomy in selected subfertile men with varicocele. Fertility and Sterility. 1970; 21: 606–609.

[16] Sarteschi MF. Andrological ultrasound. 1st edn. Athena audiovisuals: Modena. 2003.

[17] Freeman S, Bertolotto M, Richenberg J, Belfield J, Dogra V, Huang DY, et al. Ultrasound evaluation of varicoceles: guidelines and recommendations of the European Society of Urogenital Radiology Scrotal and Penile Imaging Working Group (ESUR-SPIWG) for detection, classification, and grading. European Radiology. 2020; 30: 11–25.

[18] Ayala C, Steinberger E, Smith DP. The influence of semen analysis parameters on the fertility potential of infertile couples. Journal of Andrology. 1996; 17: 718–725.

[19] Björndahl L, Barratt CLR, Mortimer D, Agarwal A, Aitken RJ, Alvarez JG, et al. Standards in semen examination: publishing reproducible and reliable data based on high-quality methodology. Human Reproduction. 2022; 37: 2497–2502.

[20] Johnson D, Sandlow J. Treatment of varicoceles: techniques and outcomes. Fertility and Sterility. 2017; 108: 378–384.

[21] D'Andrea S, Micillo A, Barbonetti A, Giordano AV, Carducci S, Mancini A, et al. Determination of spermatic vein reflux after varicocele repair helps to define the efficacy of treatment in improving sperm parameters of subfertile men. Journal of Endocrinological Investigation. 2017; 40: 1145–1153.

[22] Hamilton JA, Cissen M, Brandes M, Smeenk JM, de Bruin JP, Kremer JA, et al. Total motile sperm count: a better indicator for the severity of male factor infertility than the WHO sperm classification system. Human Reproduction. 2015; 30: 1110–1121.

[23] Borges E Jr. Total motile sperm count: a better way to rate the severity of male factor infertility? JBRA Assisted Reproduction. 2016; 20: 47–48.

[24] Bai X, Zhou Z, Luo Y, Yang H, Zhu H, Chen S, et al. Development and evaluation of a machine learning prediction model for small-for-gestational-age births in women exposed to radiation before pregnancy. Journal of Personalized Medicine. 2022; 12: 550.

[25] Yakar M, Etiz D, Metintas M, Ak G, Celik O. Prediction of radiation pneumonitis with machine learning in stage III lung cancer: a pilot study. Technology in Cancer Research & Treatment. 2021; 20: 15330338211016373.

[26] Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning: data mining, inference, and prediction. 1st edn. Springer: New York, NY. 2009.

[27] Bishop CM, Nasrabadi NM. Pattern recognition and machine learning. 1st edn. Springer-Verlag: New York. 2006.

[28] Schlegel PN, Sigman M, Collura B, De Jonge CJ, Eisenberg ML, Lamb DJ, et al. Diagnosis and treatment of infertility in men: AUA/ASRM guideline part I. Fertility and Sterility. 2021; 115: 54–61.

[29] Minhas S, Bettocchi C, Boeri L, Capogrosso P, Carvalho J, Cilesiz NC, et al. European association of urology guidelines on male sexual and reproductive health: 2021 update on male infertility. European Urology. 2021; 80: 603–620.

[30] Abdel-Meguid TA. Predictors of sperm recovery and azoospermia relapse in men with nonobstructive azoospermia after varicocele repair. The Journal of Urology. 2012; 187: 222–226.

[31] Bozhedomov VA, Shomarufov AB, Bozhedomova GE, D OA, Kamalov DM, Sorokin NI, et al. Varicocele and reproductive function: pathozoospermia treatment (a prospective comparative study). Urologiia. 2021; 62–68. (In Russian)

[32] Crafa A, Cannarella R, Condorelli RA, Mongioì LM, Vignera S, Calogero AE. Predictive parameters of the efficacy of varicocele repair: a review. Asian Journal of Andrology. 2024; 26: 441–450.

[33] Samplaski MK, Yu C, Kattan MW, Lo KC, Grober ED, Zini A, et al. Nomograms for predicting changes in semen parameters in infertile men after varicocele repair. Fertility and Sterility. 2014; 102: 68–74.

[34] Liu X, Liu D, Pan C, Su H. Nomogram for predicting semen parameters improvement after microscopic varicocelectomy in infertile men with abnormal semen parameters. Journal of Personalized Medicine. 2022; 13: 11.

[35] Kandevani NY, Namdari F, Hamidi M, Dialameh H, Behzadi A. Developing a novel prediction model for the impact of varicocelectomy on postoperative fertility. European Journal of Translational Myology. 2022; 32: 10411.

[36] Liu L, Li J, Liu G, Pan C, Bai S, Zhan Y, et al. Nomogram for predicting spontaneous pregnancy after microscopic varicocelectomy in infertile men with normal hormone. BMC Pregnancy and Childbirth. 2022; 22: 791.

[37] Jang WS, Kim KH, Lim KT, Lee J, Heo JE, Kwon H, et al. External validation of the post-varicocele repair semen analysis nomogram to predict total motile sperm count: a multicenter study. Andrologia. 2020; 52: e13809.

[38] Schlegel PN, Sigman M, Collura B, De Jonge CJ, Eisenberg ML, Lamb DJ, et al. Diagnosis and treatment of infertility in men: AUA/ASRM guideline PART II. The Journal of Urology. 2021; 205: 44–51.

[39] Pimenov DY, Bustillo A, Wojciechowski S, Sharma VS, Gupta MK, Kuntoğlu M. Artificial intelligence systems for tool condition monitoring in machining: analysis and critical review. Journal of Intelligent Manufacturing. 2023; 34: 2079–2121.

[40] Ghayda RA, Cannarella R, Calogero AE, Shah R, Rambhatla A, Zohdy W, et al. Artificial intelligence in andrology: from semen analysis to image diagnostics. The World Journal of Men’s Health. 2024; 42: 39–61.

[41] Calogero AE, Crafa A, Cannarella R, Saleh R, Shah R, Agarwal A. Artificial intelligence in andrology—fact or fiction: essential takeaway for busy clinicians. Asian Journal of Andrology. 2024; 26: 600–604.

[42] Peng T, Liao C, Ye X, Chen Z, Li X, Lan Y, et al. Machine learning-based clustering to identify the combined effect of the DNA fragmentation index and conventional semen parameters on in vitro fertilization outcomes. Reproductive Biology and Endocrinology. 2023; 21: 26.

[43] Tanaka T, Kojo K, Nagumo Y, Ikeda A, Shimizu T, Fujimoto S, et al. A new clustering model based on the seminal plasma/serum ratios of multiple trace element concentrations in male patients with subfertility. Reproductive Medicine and Biology. 2024; 23: e12584.

[44] Ates E, Ucar M, Keskin MZ, Gokce A. Preoperative neutrophil-to-lymphocyte ratio as a new prognostic predictor after microsurgical subinguinal varicocelectomy. Andrologia. 2019; 51: e13188.

[45] Noori Alavije H, Ahmadi-Hamedani M, Moslemi H. Evaluation of platelet indices and mean platelet volume to platelet count ratio in experimentally varicocele-induced adolescent and adult rats. Andrologia. 2022; 54: e14345.

[46] Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine. 2019; 25: 44–56.

[47] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research. 2002; 16: 321–357.

[48] He H, Garcia EA. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering. 2009; 21: 1263–1284.

[49] Brownlee J. Machine learning mastery with Python: understand your data, create accurate models, and work projects end-to-end. Machine Learning Mastery: San Francisco. 2016.

[50] Khoshgoftaar TM, Hulse JV, Napolitano A. Comparing boosting and bagging techniques with noisy and imbalanced data. IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans. 2011; 41: 552–568.