Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386913641> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4386913641 endingPage "100677" @default.
- W4386913641 startingPage "100677" @default.
- W4386913641 abstract "Head and neck cancer (HNC) patients treated with radiotherapy often suffer from radiation-induced toxicities. Normal Tissue Complication Probability (NTCP) modeling can be used to determine the probability to develop these toxicities based on patient, tumor, treatment and dose characteristics. Since the currently used NTCP models are developed using supervised methods that discard unlabeled patient data, we assessed whether the addition of unlabeled patient data by using semi-supervised modeling would gain predictive performance.The semi-supervised method of self-training was compared to supervised regression methods with and without prior multiple imputation by chained equation (MICE). The models were developed for the most common toxicity outcomes in HNC patients, xerostomia (dry mouth) and dysphagia (difficulty swallowing), measured at six months after treatment, in a development cohort of 750 HNC patients. The models were externally validated in a validation cohort of 395 HNC patients. Model performance was assessed by discrimination and calibration.MICE and self-training did not improve performance in terms of discrimination or calibration at external validation compared to current regression models. In addition, the relative performance of the different models did not change upon a decrease in the amount of (labeled) data available for model development. Models using ridge regression outperformed the logistic models for the dysphagia outcome.Since there was no apparent gain in the addition of unlabeled patient data by using the semi-supervised method of self-training or MICE, the supervised regression models would still be preferred in current NTCP modeling for HNC patients." @default.
- W4386913641 created "2023-09-22" @default.
- W4386913641 creator A5002522655 @default.
- W4386913641 creator A5009217884 @default.
- W4386913641 creator A5031111983 @default.
- W4386913641 creator A5041203940 @default.
- W4386913641 creator A5047626219 @default.
- W4386913641 creator A5092913478 @default.
- W4386913641 date "2023-11-01" @default.
- W4386913641 modified "2023-10-14" @default.
- W4386913641 title "Comparing supervised and semi-supervised machine learning approaches in NTCP modeling to predict complications in head and neck cancer patients" @default.
- W4386913641 cites W1983320747 @default.
- W4386913641 cites W1994682257 @default.
- W4386913641 cites W2106401878 @default.
- W4386913641 cites W2118502261 @default.
- W4386913641 cites W2118772763 @default.
- W4386913641 cites W2136716437 @default.
- W4386913641 cites W2159039804 @default.
- W4386913641 cites W2225109326 @default.
- W4386913641 cites W2484662136 @default.
- W4386913641 cites W2911635199 @default.
- W4386913641 cites W2984353870 @default.
- W4386913641 cites W2996480032 @default.
- W4386913641 cites W3127642106 @default.
- W4386913641 cites W4205229458 @default.
- W4386913641 cites W4205805845 @default.
- W4386913641 cites W4312193399 @default.
- W4386913641 doi "https://doi.org/10.1016/j.ctro.2023.100677" @default.
- W4386913641 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37822705" @default.
- W4386913641 hasPublicationYear "2023" @default.
- W4386913641 type Work @default.
- W4386913641 citedByCount "0" @default.
- W4386913641 crossrefType "journal-article" @default.
- W4386913641 hasAuthorship W4386913641A5002522655 @default.
- W4386913641 hasAuthorship W4386913641A5009217884 @default.
- W4386913641 hasAuthorship W4386913641A5031111983 @default.
- W4386913641 hasAuthorship W4386913641A5041203940 @default.
- W4386913641 hasAuthorship W4386913641A5047626219 @default.
- W4386913641 hasAuthorship W4386913641A5092913478 @default.
- W4386913641 hasBestOaLocation W43869136411 @default.
- W4386913641 hasConcept C105795698 @default.
- W4386913641 hasConcept C119857082 @default.
- W4386913641 hasConcept C126322002 @default.
- W4386913641 hasConcept C141071460 @default.
- W4386913641 hasConcept C151956035 @default.
- W4386913641 hasConcept C152877465 @default.
- W4386913641 hasConcept C154945302 @default.
- W4386913641 hasConcept C2776530083 @default.
- W4386913641 hasConcept C2780596822 @default.
- W4386913641 hasConcept C33923547 @default.
- W4386913641 hasConcept C41008148 @default.
- W4386913641 hasConcept C509974204 @default.
- W4386913641 hasConcept C71924100 @default.
- W4386913641 hasConcept C72563966 @default.
- W4386913641 hasConcept C83546350 @default.
- W4386913641 hasConceptScore W4386913641C105795698 @default.
- W4386913641 hasConceptScore W4386913641C119857082 @default.
- W4386913641 hasConceptScore W4386913641C126322002 @default.
- W4386913641 hasConceptScore W4386913641C141071460 @default.
- W4386913641 hasConceptScore W4386913641C151956035 @default.
- W4386913641 hasConceptScore W4386913641C152877465 @default.
- W4386913641 hasConceptScore W4386913641C154945302 @default.
- W4386913641 hasConceptScore W4386913641C2776530083 @default.
- W4386913641 hasConceptScore W4386913641C2780596822 @default.
- W4386913641 hasConceptScore W4386913641C33923547 @default.
- W4386913641 hasConceptScore W4386913641C41008148 @default.
- W4386913641 hasConceptScore W4386913641C509974204 @default.
- W4386913641 hasConceptScore W4386913641C71924100 @default.
- W4386913641 hasConceptScore W4386913641C72563966 @default.
- W4386913641 hasConceptScore W4386913641C83546350 @default.
- W4386913641 hasFunder F4320338019 @default.
- W4386913641 hasLocation W43869136411 @default.
- W4386913641 hasLocation W43869136412 @default.
- W4386913641 hasOpenAccess W4386913641 @default.
- W4386913641 hasPrimaryLocation W43869136411 @default.
- W4386913641 hasRelatedWork W2034959125 @default.
- W4386913641 hasRelatedWork W2147863910 @default.
- W4386913641 hasRelatedWork W2165884543 @default.
- W4386913641 hasRelatedWork W2312753042 @default.
- W4386913641 hasRelatedWork W2368989808 @default.
- W4386913641 hasRelatedWork W2389155397 @default.
- W4386913641 hasRelatedWork W2949811493 @default.
- W4386913641 hasRelatedWork W3174513558 @default.
- W4386913641 hasRelatedWork W4289356671 @default.
- W4386913641 hasRelatedWork W3186837933 @default.
- W4386913641 hasVolume "43" @default.
- W4386913641 isParatext "false" @default.
- W4386913641 isRetracted "false" @default.
- W4386913641 workType "article" @default.