Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204880206> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3204880206 endingPage "104903" @default.
- W3204880206 startingPage "104903" @default.
- W3204880206 abstract "The Prostate Biopsy Collaborative Group risk calculator (PBCG RC) has a moderate discriminatory capability. This study aimed to create automated machine learning (AutoML) PBCG RC for predicting the probability of any-grade and high-grade prostate cancer (PCa). This retrospective, single-center study was carried out using the database with 832 patients who were subject to transrectal ultrasound-guided prostate biopsy with prostate-specific antigen (PSA) values from 2 to 50 ng/ml. Information about PBCG RC predictors was gathered for all patients. We used H2O, as an open-source platform for AutoML, where the set of 20 base learning algorithms were trained. The AutoML PBCG RC was compared in terms of discrimination, calibration, and clinical utility with the original PBCG RC. PCa was detected in 341 (41%) men, and 159 (19.1%) of them had high-grade PCa. Our AutoML models demonstrated better discriminative ability than the original PBCG RC for detection of PCa (area under the curve [AUC]: 0.703 vs 0.628; P = 0.023) and high-grade PCa (AUC: 0.990 vs 0.717; P < 0.001). The decision curve analyses showed that AutoML models performed better. For high-grade PCa the PSA was the most important feature. We applied ensemble techniques to create a freely available online PCa risk tool based on PBCG RC predictors and AutoML algorithms. The AutoML models drastically improved original model performance and the predictions of high-grade PCa were nearly perfect. However, new models should be used with a reserve, because external validation has not been performed yet." @default.
- W3204880206 created "2021-10-11" @default.
- W3204880206 creator A5020300925 @default.
- W3204880206 creator A5069203609 @default.
- W3204880206 creator A5080100373 @default.
- W3204880206 date "2021-11-01" @default.
- W3204880206 modified "2023-10-02" @default.
- W3204880206 title "Improved predictive performance of prostate biopsy collaborative group risk calculator when based on automated machine learning" @default.
- W3204880206 cites W1915129189 @default.
- W3204880206 cites W2026838241 @default.
- W3204880206 cites W2063974159 @default.
- W3204880206 cites W2089378422 @default.
- W3204880206 cites W2090136295 @default.
- W3204880206 cites W2125847307 @default.
- W3204880206 cites W2225109326 @default.
- W3204880206 cites W2469679124 @default.
- W3204880206 cites W2500367737 @default.
- W3204880206 cites W2558726901 @default.
- W3204880206 cites W2784515263 @default.
- W3204880206 cites W2802565218 @default.
- W3204880206 cites W2804413706 @default.
- W3204880206 cites W2908465383 @default.
- W3204880206 cites W2911982216 @default.
- W3204880206 cites W2913997948 @default.
- W3204880206 cites W2980613434 @default.
- W3204880206 cites W2983154683 @default.
- W3204880206 cites W2984908682 @default.
- W3204880206 cites W2991440615 @default.
- W3204880206 cites W2996480032 @default.
- W3204880206 cites W3006913750 @default.
- W3204880206 cites W3013699712 @default.
- W3204880206 cites W3028871667 @default.
- W3204880206 cites W3031962179 @default.
- W3204880206 cites W3040536502 @default.
- W3204880206 cites W3146378223 @default.
- W3204880206 doi "https://doi.org/10.1016/j.compbiomed.2021.104903" @default.
- W3204880206 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34598066" @default.
- W3204880206 hasPublicationYear "2021" @default.
- W3204880206 type Work @default.
- W3204880206 sameAs 3204880206 @default.
- W3204880206 citedByCount "4" @default.
- W3204880206 countsByYear W32048802062022 @default.
- W3204880206 countsByYear W32048802062023 @default.
- W3204880206 crossrefType "journal-article" @default.
- W3204880206 hasAuthorship W3204880206A5020300925 @default.
- W3204880206 hasAuthorship W3204880206A5069203609 @default.
- W3204880206 hasAuthorship W3204880206A5080100373 @default.
- W3204880206 hasConcept C111919701 @default.
- W3204880206 hasConcept C119857082 @default.
- W3204880206 hasConcept C121608353 @default.
- W3204880206 hasConcept C126322002 @default.
- W3204880206 hasConcept C154945302 @default.
- W3204880206 hasConcept C27438332 @default.
- W3204880206 hasConcept C2776235491 @default.
- W3204880206 hasConcept C2776836400 @default.
- W3204880206 hasConcept C2780192828 @default.
- W3204880206 hasConcept C2781217009 @default.
- W3204880206 hasConcept C2781406297 @default.
- W3204880206 hasConcept C41008148 @default.
- W3204880206 hasConcept C58471807 @default.
- W3204880206 hasConcept C71924100 @default.
- W3204880206 hasConcept C97931131 @default.
- W3204880206 hasConceptScore W3204880206C111919701 @default.
- W3204880206 hasConceptScore W3204880206C119857082 @default.
- W3204880206 hasConceptScore W3204880206C121608353 @default.
- W3204880206 hasConceptScore W3204880206C126322002 @default.
- W3204880206 hasConceptScore W3204880206C154945302 @default.
- W3204880206 hasConceptScore W3204880206C27438332 @default.
- W3204880206 hasConceptScore W3204880206C2776235491 @default.
- W3204880206 hasConceptScore W3204880206C2776836400 @default.
- W3204880206 hasConceptScore W3204880206C2780192828 @default.
- W3204880206 hasConceptScore W3204880206C2781217009 @default.
- W3204880206 hasConceptScore W3204880206C2781406297 @default.
- W3204880206 hasConceptScore W3204880206C41008148 @default.
- W3204880206 hasConceptScore W3204880206C58471807 @default.
- W3204880206 hasConceptScore W3204880206C71924100 @default.
- W3204880206 hasConceptScore W3204880206C97931131 @default.
- W3204880206 hasLocation W32048802061 @default.
- W3204880206 hasLocation W32048802062 @default.
- W3204880206 hasOpenAccess W3204880206 @default.
- W3204880206 hasPrimaryLocation W32048802061 @default.
- W3204880206 hasRelatedWork W1497253641 @default.
- W3204880206 hasRelatedWork W1884231116 @default.
- W3204880206 hasRelatedWork W2042911820 @default.
- W3204880206 hasRelatedWork W2102167265 @default.
- W3204880206 hasRelatedWork W2148869351 @default.
- W3204880206 hasRelatedWork W2406073138 @default.
- W3204880206 hasRelatedWork W2566665866 @default.
- W3204880206 hasRelatedWork W2897445903 @default.
- W3204880206 hasRelatedWork W3015759778 @default.
- W3204880206 hasRelatedWork W4282843086 @default.
- W3204880206 hasVolume "138" @default.
- W3204880206 isParatext "false" @default.
- W3204880206 isRetracted "false" @default.
- W3204880206 magId "3204880206" @default.
- W3204880206 workType "article" @default.