FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4241177317> ?p ?o ?g. }

• W4241177317 abstract "You have accessJournal of UrologyBladder Cancer: Detection and Screening1 Apr 20101176 OUTCOME PREDICTION IN PATIENTS WITH BLADDER CANCER AFTER RADICAL CYSTECTOMY USING ARTIFICIAL NEURAL NETWORKS Alexander Buchner, Christian Bolenz, Edwin Herrmann, Derya Tilki, Alexander Karl, Thomas Höfner, Hans Fritsche, Christian Wülfing, Maximilian Burger, Lutz Trojan, Arne Tiermann, Axel Haferkamp, Maurice Michel, Markus Hohenfellner, Wolfgang Wieland, Stefan Mueller, Christian Stief, and Patrick Bastian Alexander BuchnerAlexander Buchner Munich, Germany More articles by this author , Christian BolenzChristian Bolenz Mannheim, Germany More articles by this author , Edwin HerrmannEdwin Herrmann Münster, Germany More articles by this author , Derya TilkiDerya Tilki Munich, Germany More articles by this author , Alexander KarlAlexander Karl Munich, Germany More articles by this author , Thomas HöfnerThomas Höfner Heidelberg, Germany More articles by this author , Hans FritscheHans Fritsche Regensburg, Germany More articles by this author , Christian WülfingChristian Wülfing Münster, Germany More articles by this author , Maximilian BurgerMaximilian Burger Regensburg, Germany More articles by this author , Lutz TrojanLutz Trojan Mannheim, Germany More articles by this author , Arne TiermannArne Tiermann Münster, Germany More articles by this author , Axel HaferkampAxel Haferkamp Heidelberg, Germany More articles by this author , Maurice MichelMaurice Michel Mannheim, Germany More articles by this author , Markus HohenfellnerMarkus Hohenfellner Heidelberg, Germany More articles by this author , Wolfgang WielandWolfgang Wieland Regensburg, Germany More articles by this author , Stefan MuellerStefan Mueller Bonn, Germany More articles by this author , Christian StiefChristian Stief Munich, Germany More articles by this author , and Patrick BastianPatrick Bastian Munich, Germany More articles by this author View All Author Informationhttps://doi.org/10.1016/j.juro.2010.02.676AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookTwitterLinked InEmail INTRODUCTION AND OBJECTIVES The oncological outcome of patients with bladder cancer that undergo radical cystectomy shows remarkable variability, and there is a need to identify prognostic parameters that allow individual prognostic stratification. Artificial neural networks (ANN) are software systems that can learn and recognize complex patterns of data. A trained ANN is able to classify new data sets according to their typical patterns. In recent years, ANN have been increasingly applied to medical questions. In this study, we used ANN to identify high-risk bladder cancer patients based on common clinical and histopathological parameters. METHODS From a multicenter database (six University hospitals) with bladder cancer patients that underwent radical cystectomy, 1062 complete datasets with follow-up data were available for analysis. The median follow-up time was 20 months. Age, gender, tumor stage and grade (in TUR-B and cystectomy), carcinoma in situ (CIS; in TUR-B and cystectomy) and (neo-)adjuvant chemo- or radiotherapy were used as input data for the artificial neural network (multilayer perceptron architecture; StatSoft, Tulsa, OK). 70% of the cases were used for the training process, and the remaining 30% served as independent validation data set. Target variables were tumor-specific survival and tumor progression/recurrence, respectively. ANN performance was assessed by classification error and ROC (receiver operating characteristic) analysis. RESULTS After training was completed, the ANN correctly assigned the survival status to 70% of patients in the training set and to 73% in the validation set, respectively. In ROC analysis, the area under curve (AUC) was 0.69. With progression/recurrence as target parameter for ANN training instead of survival, the correct classification rate was 86% in the training set and 82% in the validation set, respectively. The AUC for prediction of tumor relapse was 0.79. The parameters CIS and pT had the highest impact on the network's decision, as determined by the so-called sensitivity index. CONCLUSIONS In this study, ANN could correctly predict the tumor relapse of up to 86% of bladder cancer patients after cystectomy. Artificial neural networks are a promising approach for individual outcome prediction of bladder cancer patients, based on some common parameters. ANN can help to optimize the therapeutic strategy, e. g. by selecting high-risk patients for adjuvant therapy. An improved prediction of tumor-specific survival can probably be achieved by including data about the post-recurrence therapy in the network model. © 2010 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 183Issue 4SApril 2010Page: e456 Advertisement Copyright & Permissions© 2010 by American Urological Association Education and Research, Inc.MetricsAuthor Information Alexander Buchner Munich, Germany More articles by this author Christian Bolenz Mannheim, Germany More articles by this author Edwin Herrmann Münster, Germany More articles by this author Derya Tilki Munich, Germany More articles by this author Alexander Karl Munich, Germany More articles by this author Thomas Höfner Heidelberg, Germany More articles by this author Hans Fritsche Regensburg, Germany More articles by this author Christian Wülfing Münster, Germany More articles by this author Maximilian Burger Regensburg, Germany More articles by this author Lutz Trojan Mannheim, Germany More articles by this author Arne Tiermann Münster, Germany More articles by this author Axel Haferkamp Heidelberg, Germany More articles by this author Maurice Michel Mannheim, Germany More articles by this author Markus Hohenfellner Heidelberg, Germany More articles by this author Wolfgang Wieland Regensburg, Germany More articles by this author Stefan Mueller Bonn, Germany More articles by this author Christian Stief Munich, Germany More articles by this author Patrick Bastian Munich, Germany More articles by this author Expand All Advertisement Advertisement PDF downloadLoading ..." @default.
• W4241177317 created "2022-05-12" @default.
• W4241177317 creator A5022170865 @default.
• W4241177317 creator A5030545703 @default.
• W4241177317 creator A5034143227 @default.
• W4241177317 creator A5038665193 @default.
• W4241177317 creator A5038825854 @default.
• W4241177317 creator A5045839581 @default.
• W4241177317 creator A5046084721 @default.
• W4241177317 creator A5048419761 @default.
• W4241177317 creator A5056088520 @default.
• W4241177317 creator A5060038036 @default.
• W4241177317 creator A5061644837 @default.
• W4241177317 creator A5066330818 @default.
• W4241177317 creator A5067050215 @default.
• W4241177317 creator A5073901509 @default.
• W4241177317 creator A5078943566 @default.
• W4241177317 creator A5081515243 @default.
• W4241177317 creator A5085904476 @default.
• W4241177317 creator A5087601171 @default.
• W4241177317 date "2010-04-01" @default.
• W4241177317 modified "2023-10-16" @default.
• W4241177317 title "1176 OUTCOME PREDICTION IN PATIENTS WITH BLADDER CANCER AFTER RADICAL CYSTECTOMY USING ARTIFICIAL NEURAL NETWORKS" @default.
• W4241177317 doi "https://doi.org/10.1016/j.juro.2010.02.676" @default.
• W4241177317 hasPublicationYear "2010" @default.
• W4241177317 type Work @default.
• W4241177317 citedByCount "0" @default.
• W4241177317 crossrefType "journal-article" @default.
• W4241177317 hasAuthorship W4241177317A5022170865 @default.
• W4241177317 hasAuthorship W4241177317A5030545703 @default.
• W4241177317 hasAuthorship W4241177317A5034143227 @default.
• W4241177317 hasAuthorship W4241177317A5038665193 @default.
• W4241177317 hasAuthorship W4241177317A5038825854 @default.
• W4241177317 hasAuthorship W4241177317A5045839581 @default.
• W4241177317 hasAuthorship W4241177317A5046084721 @default.
• W4241177317 hasAuthorship W4241177317A5048419761 @default.
• W4241177317 hasAuthorship W4241177317A5056088520 @default.
• W4241177317 hasAuthorship W4241177317A5060038036 @default.
• W4241177317 hasAuthorship W4241177317A5061644837 @default.
• W4241177317 hasAuthorship W4241177317A5066330818 @default.
• W4241177317 hasAuthorship W4241177317A5067050215 @default.
• W4241177317 hasAuthorship W4241177317A5073901509 @default.
• W4241177317 hasAuthorship W4241177317A5078943566 @default.
• W4241177317 hasAuthorship W4241177317A5081515243 @default.
• W4241177317 hasAuthorship W4241177317A5085904476 @default.
• W4241177317 hasAuthorship W4241177317A5087601171 @default.
• W4241177317 hasConcept C121608353 @default.
• W4241177317 hasConcept C126322002 @default.
• W4241177317 hasConcept C2775910329 @default.
• W4241177317 hasConcept C2780352672 @default.
• W4241177317 hasConcept C3020252794 @default.
• W4241177317 hasConcept C52119013 @default.
• W4241177317 hasConcept C6303427 @default.
• W4241177317 hasConcept C71924100 @default.
• W4241177317 hasConcept C74916050 @default.
• W4241177317 hasConcept C95457728 @default.
• W4241177317 hasConceptScore W4241177317C121608353 @default.
• W4241177317 hasConceptScore W4241177317C126322002 @default.
• W4241177317 hasConceptScore W4241177317C2775910329 @default.
• W4241177317 hasConceptScore W4241177317C2780352672 @default.
• W4241177317 hasConceptScore W4241177317C3020252794 @default.
• W4241177317 hasConceptScore W4241177317C52119013 @default.
• W4241177317 hasConceptScore W4241177317C6303427 @default.
• W4241177317 hasConceptScore W4241177317C71924100 @default.
• W4241177317 hasConceptScore W4241177317C74916050 @default.
• W4241177317 hasConceptScore W4241177317C95457728 @default.
• W4241177317 hasIssue "4S" @default.
• W4241177317 hasLocation W42411773171 @default.
• W4241177317 hasOpenAccess W4241177317 @default.
• W4241177317 hasPrimaryLocation W42411773171 @default.
• W4241177317 hasRelatedWork W2009115226 @default.
• W4241177317 hasRelatedWork W2120921122 @default.
• W4241177317 hasRelatedWork W2383341741 @default.
• W4241177317 hasRelatedWork W2748952813 @default.
• W4241177317 hasRelatedWork W2751371555 @default.
• W4241177317 hasRelatedWork W2904128870 @default.
• W4241177317 hasRelatedWork W2981737993 @default.
• W4241177317 hasRelatedWork W3027336582 @default.
• W4241177317 hasRelatedWork W3127820018 @default.
• W4241177317 hasRelatedWork W3128330365 @default.
• W4241177317 hasVolume "183" @default.
• W4241177317 isParatext "false" @default.
• W4241177317 isRetracted "false" @default.
• W4241177317 workType "article" @default.