FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386757029> ?p ?o ?g. }

• W4386757029 abstract "Allogeneic hematopoietic stem cell transplantation (HSCT) is a curative treatment for many inborn errors of immunity, metabolism, and hematopoiesis. No predictive models are available for these disorders. We created a machine learning model using XGBoost to predict survival after HSCT using European Society for Blood and Marrow Transplant registry data of 10,888 patients who underwent HSCT for inborn errors between 2006 and 2018, and compared it to a simple linear Cox model, an elastic net Cox model, and a random forest model. The XGBoost model had a cross-validated area under the curve value of .73 at 1 year, which was significantly superior to the other models, and it accurately predicted for countries excluded while training. It predicted close to 0% and >30% mortality more often than other models at 1 year, while maintaining good calibration. The 5-year survival was 94.7% in the 25% of patients at lowest risk and 62.3% in the 25% at highest risk. Within disease and donor subgroups, XGBoost outperformed the best univariate predictor. We visualized the effect of the main predictors-diagnosis, performance score, patient age and donor type-using the SHAP ML explainer and developed a stand-alone application, which can predict using the model and visualize predictions. The risk of mortality after HSCT for inborn errors can be accurately predicted using an explainable machine learning model. This exceeds the performance of models described in the literature. Doing so can help detect deviations from expected survival and improve risk stratification in trials." @default.
• W4386757029 created "2023-09-16" @default.
• W4386757029 creator A5000530040 @default.
• W4386757029 creator A5006102363 @default.
• W4386757029 creator A5007462898 @default.
• W4386757029 creator A5011534196 @default.
• W4386757029 creator A5030851924 @default.
• W4386757029 creator A5069107002 @default.
• W4386757029 creator A5073613763 @default.
• W4386757029 creator A5092875361 @default.
• W4386757029 date "2023-09-01" @default.
• W4386757029 modified "2023-10-11" @default.
• W4386757029 title "Predicting patient death after allogeneic SCT for inborn errors using machine learning (PREPAD): An EBMT IEWP study" @default.
• W4386757029 cites W2010193886 @default.
• W4386757029 cites W2017908149 @default.
• W4386757029 cites W2064085613 @default.
• W4386757029 cites W2064186732 @default.
• W4386757029 cites W2078271269 @default.
• W4386757029 cites W2112400170 @default.
• W4386757029 cites W2128812336 @default.
• W4386757029 cites W2133048986 @default.
• W4386757029 cites W2137489389 @default.
• W4386757029 cites W2157076315 @default.
• W4386757029 cites W2238351347 @default.
• W4386757029 cites W2344579973 @default.
• W4386757029 cites W2606493012 @default.
• W4386757029 cites W2889412507 @default.
• W4386757029 cites W2950244989 @default.
• W4386757029 cites W2980872770 @default.
• W4386757029 cites W3048513059 @default.
• W4386757029 cites W3099478002 @default.
• W4386757029 cites W3122108726 @default.
• W4386757029 cites W3131348164 @default.
• W4386757029 cites W3132424591 @default.
• W4386757029 cites W3209464783 @default.
• W4386757029 cites W4213125083 @default.
• W4386757029 cites W4220674845 @default.
• W4386757029 cites W4225849792 @default.
• W4386757029 cites W4280552588 @default.
• W4386757029 doi "https://doi.org/10.1016/j.jtct.2023.09.007" @default.
• W4386757029 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37709203" @default.
• W4386757029 hasPublicationYear "2023" @default.
• W4386757029 type Work @default.
• W4386757029 citedByCount "0" @default.
• W4386757029 crossrefType "journal-article" @default.
• W4386757029 hasAuthorship W4386757029A5000530040 @default.
• W4386757029 hasAuthorship W4386757029A5006102363 @default.
• W4386757029 hasAuthorship W4386757029A5007462898 @default.
• W4386757029 hasAuthorship W4386757029A5011534196 @default.
• W4386757029 hasAuthorship W4386757029A5030851924 @default.
• W4386757029 hasAuthorship W4386757029A5069107002 @default.
• W4386757029 hasAuthorship W4386757029A5073613763 @default.
• W4386757029 hasAuthorship W4386757029A5092875361 @default.
• W4386757029 hasBestOaLocation W43867570291 @default.
• W4386757029 hasConcept C109159458 @default.
• W4386757029 hasConcept C119857082 @default.
• W4386757029 hasConcept C126322002 @default.
• W4386757029 hasConcept C161584116 @default.
• W4386757029 hasConcept C187212893 @default.
• W4386757029 hasConcept C199163554 @default.
• W4386757029 hasConcept C2777408962 @default.
• W4386757029 hasConcept C28328180 @default.
• W4386757029 hasConcept C2911091166 @default.
• W4386757029 hasConcept C2993713153 @default.
• W4386757029 hasConcept C41008148 @default.
• W4386757029 hasConcept C50382708 @default.
• W4386757029 hasConcept C54355233 @default.
• W4386757029 hasConcept C71924100 @default.
• W4386757029 hasConcept C86803240 @default.
• W4386757029 hasConceptScore W4386757029C109159458 @default.
• W4386757029 hasConceptScore W4386757029C119857082 @default.
• W4386757029 hasConceptScore W4386757029C126322002 @default.
• W4386757029 hasConceptScore W4386757029C161584116 @default.
• W4386757029 hasConceptScore W4386757029C187212893 @default.
• W4386757029 hasConceptScore W4386757029C199163554 @default.
• W4386757029 hasConceptScore W4386757029C2777408962 @default.
• W4386757029 hasConceptScore W4386757029C28328180 @default.
• W4386757029 hasConceptScore W4386757029C2911091166 @default.
• W4386757029 hasConceptScore W4386757029C2993713153 @default.
• W4386757029 hasConceptScore W4386757029C41008148 @default.
• W4386757029 hasConceptScore W4386757029C50382708 @default.
• W4386757029 hasConceptScore W4386757029C54355233 @default.
• W4386757029 hasConceptScore W4386757029C71924100 @default.
• W4386757029 hasConceptScore W4386757029C86803240 @default.
• W4386757029 hasLocation W43867570291 @default.
• W4386757029 hasLocation W43867570292 @default.
• W4386757029 hasOpenAccess W4386757029 @default.
• W4386757029 hasPrimaryLocation W43867570291 @default.
• W4386757029 hasRelatedWork W1828158523 @default.
• W4386757029 hasRelatedWork W1985848810 @default.
• W4386757029 hasRelatedWork W2000145235 @default.
• W4386757029 hasRelatedWork W2049578243 @default.
• W4386757029 hasRelatedWork W2122079181 @default.
• W4386757029 hasRelatedWork W2399195672 @default.
• W4386757029 hasRelatedWork W2748838164 @default.
• W4386757029 hasRelatedWork W2889939530 @default.
• W4386757029 hasRelatedWork W3121881699 @default.
• W4386757029 hasRelatedWork W3122045730 @default.
• W4386757029 isParatext "false" @default.
• W4386757029 isRetracted "false" @default.

• next