You have accessJournal of UrologyCME1 May 2022MP34-16 ARTIFICIAL INTELLIGENCE BASED MACHINE LEARNING MODELS PREDICT SPERM PARAMETER UPGRADING AFTER MICROSURGICAL VARICOCELE REPAIR: A MULTI-INSTITUTIONAL ANALYSIS Jesse Ory, Michael B. Tradewell, Udi Blankstein, Thiago Lima, Sirpi Nackeeran, Daniel C. Gonzales, Elie Nwefo, Vinayak Madhusoodanan, Susan Lau, Keith Jarvi, and Ranjith Ramasamy Jesse OryJesse Ory More articles by this author , Michael B. TradewellMichael B. Tradewell More articles by this author , Udi BlanksteinUdi Blankstein More articles by this author , Thiago LimaThiago Lima More articles by this author , Sirpi NackeeranSirpi Nackeeran More articles by this author , Daniel C. GonzalesDaniel C. Gonzales More articles by this author , Elie NwefoElie Nwefo More articles by this author , Vinayak MadhusoodananVinayak Madhusoodanan More articles by this author , Susan LauSusan Lau More articles by this author , Keith JarviKeith Jarvi More articles by this author , and Ranjith RamasamyRanjith Ramasamy More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000002588.16AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Varicocele repair is recommended in the presence of a clinical varicocele together with at least one abnormal semen parameter, and male infertility. We developed an artificial intelligence (AI) model to predict which men with varicocele will benefit from surgery. METHODS: We identified men with infertility, clinical varicocele, and at least one abnormal semen parameter from two large Urology centers in North America (Miami and Toronto) between 2006 and 2020. We collected pre and postoperative clinical and hormonal data following surgery. Clinical upgrading was defined as an increase in sperm concentration that would allow a couple to access previously unavailable reproductive options. The tiers used for upgrading were: 1-5 million/cc (ICSI/IVF), 5-15 million/cc (IUI) and >15 million/cc (natural conception). AI models were trained and tested using R to predict which patients were likely to upgrade after surgery. The model sorted men into categories that defined how likely they were to upgrade after surgery (likely, equivocal, and unlikely). RESULTS: Data from 240 men were included from both centers. Average age was 36 years. The majority of men had grade 2 left varicocele, and (when present) a grade 1 right varicocele. A total of 47% of men experienced an upgrade in sperm concentration following surgery, 47% did not change, and 6% downgraded. The data from Miami were used to create a random forest model for predicting upgrade in sperm concentration. The most informative parameters were preoperative FSH, sperm concentration and surgical laterality. On external validation using Toronto data, the model accurately predicted upgrade in 87% of men deemed likely to improve, and in 49% and 36% of men who were equivocal and unlikely to improve, respectively. Overall, the model performed well on external validation with an AUC of 0.72 and good calibration (Figure 1). CONCLUSIONS: A machine learning model performed well in predicting clinically meaningful post-varicocelectomy semen upgrade using pre-operative data. To our knowledge, this is the first prediction model to show the utility of hormonal data, as well as the first to use AI to predict clinically meaningful upgrading. Source of Funding: n/a © 2022 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 207Issue Supplement 5May 2022Page: e584 Advertisement Copyright & Permissions© 2022 by American Urological Association Education and Research, Inc.MetricsAuthor Information Jesse Ory More articles by this author Michael B. Tradewell More articles by this author Udi Blankstein More articles by this author Thiago Lima More articles by this author Sirpi Nackeeran More articles by this author Daniel C. Gonzales More articles by this author Elie Nwefo More articles by this author Vinayak Madhusoodanan More articles by this author Susan Lau More articles by this author Keith Jarvi More articles by this author Ranjith Ramasamy More articles by this author Expand All Advertisement PDF DownloadLoading ...