MP64-17 PREDICTING LONG-TERM SEXUAL FUNCTION IN POST-RADICAL PROSTATECTOMY PATIENTS BASED ON MRI AND CLINICAL FACTORS: A MULTI-CENTER STUDY

You have accessJournal of UrologyProstate Cancer: Localized: Surgical Therapy VI (MP64)1 Sep 2021MP64-17 PREDICTING LONG-TERM SEXUAL FUNCTION IN POST-RADICAL PROSTATECTOMY PATIENTS BASED ON MRI AND CLINICAL FACTORS: A MULTI-CENTER STUDY Ajith Dupati, Anna Johnson, Mahin Mirza, Nnenaya Mmonu, Brian R. Lane, Prasad Shankar, Matthew S. Davenport, Andrew Moriarity, Michael Ryan, Ali A. Dabaja, James O. Peabody, Arvin K. George, and Karandeep Singh DupatiAjith Dupati More articles by this author , JohnsonAnna Johnson MirzaMahin Mirza MmonuNnenaya Mmonu LaneBrian Lane ShankarPrasad Shankar DavenportMatthew Davenport MoriarityAndrew Moriarity RyanMichael Ryan DabajaAli Dabaja PeabodyJames Peabody GeorgeArvin George SinghKarandeep View All Author Informationhttps://doi.org/10.1097/JU.0000000000002104.17AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION OBJECTIVE: Long-term sexual dysfunction is common following radical prostatectomy (RP) for localized prostate cancer (CaP). We sought determine whether inclusion data derived from preoperative multiparametric (mpMRI) improves the prediction function at 12 months 24 RP. METHODS: The Michigan Urological Surgery Improvement Collaborative (MUSIC) a consortium 45 diverse urology practices that maintains prospective registry men with CaP. Using mpMRI 3 large hospitals linked MUSIC data, we fit random forest models predict patient reported RP; poor was defined as EPIC-26 scores <73 good ≥73. compared using baseline clinical predictors (age, body mass index, grade group, PSA, domain score, urinary incontinence score), (membranous urethral length, maximum PI-RADS v2 median lobe size, volume), both predictors. assessed model discrimination 10-fold cross-validated C-statistic. RESULTS: identified 854 patients 477 months, whom 671 (79%) had 350 (73%) months. combined strong discriminative performance C-statistics 0.94 0.96 (Table). Adding variables did not improve over factors alone. 5 most important month were age, initial volume. CONCLUSIONS: Models alone achieved very high in long-term Compared alone, adding does significantly or after Source Funding: Clinical collected through MUSIC, which funded Blue Cross Shield © 2021 American Association Education Research, Inc.FiguresReferencesRelatedDetails Volume 206Issue Supplement 3September 2021Page: e1117-e1117 Advertisement Copyright & Permissions© Inc.MetricsAuthor Information Expand Loading ...