FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310263731> ?p ?o ?g. }

• W4310263731 abstract "Abstract Background Machine learning (ML) algorithms have been trained to early predict critical in-hospital events from COVID-19 using patient data at admission, but little is known on how their performance compares with each other and/or with statistical logistic regression (LR). This prospective multicentre cohort study compares the performance of a LR and five ML models on the contribution of influencing predictors and predictor-to-event relationships on prediction model´s performance. Methods We used 25 baseline variables of 490 COVID-19 patients admitted to 8 hospitals in Germany (March–November 2020) to develop and validate (75/25 random-split) 3 linear (L1 and L2 penalty, elastic net [EN]) and 2 non-linear (support vector machine [SVM] with radial kernel, random forest [RF]) ML approaches for predicting critical events defined by intensive care unit transfer, invasive ventilation and/or death (composite end-point: 181 patients). Models were compared for performance (area-under-the-receiver-operating characteristic-curve [AUC], Brier score) and predictor importance (performance-loss metrics, partial-dependence profiles). Results Models performed close with a small benefit for LR (utilizing restricted cubic splines for non-linearity) and RF (AUC means: 0.763–0.731 [RF–L1]); Brier scores: 0.184–0.197 [LR–L1]). Top ranked predictor variables (consistently highest importance: C-reactive protein) were largely identical across models, except creatinine, which exhibited marginal (L1, L2, EN, SVM) or high/non-linear effects (LR, RF) on events. Conclusions Although the LR and ML models analysed showed no strong differences in performance and the most influencing predictors for COVID-19-related event prediction, our results indicate a predictive benefit from taking account for non-linear predictor-to-event relationships and effects. Future efforts should focus on leveraging data-driven ML technologies from static towards dynamic modelling solutions that continuously learn and adapt to changes in data environments during the evolving pandemic. Trial registration number : NCT04659187." @default.
• W4310263731 created "2022-11-30" @default.
• W4310263731 creator A5015346451 @default.
• W4310263731 creator A5030120350 @default.
• W4310263731 creator A5036649021 @default.
• W4310263731 creator A5044680284 @default.
• W4310263731 creator A5049925686 @default.
• W4310263731 creator A5052808201 @default.
• W4310263731 creator A5052838808 @default.
• W4310263731 creator A5055805646 @default.
• W4310263731 creator A5059701911 @default.
• W4310263731 creator A5062888430 @default.
• W4310263731 creator A5080637646 @default.
• W4310263731 creator A5082497021 @default.
• W4310263731 creator A5083684330 @default.
• W4310263731 creator A5088860959 @default.
• W4310263731 date "2022-11-28" @default.
• W4310263731 modified "2023-10-17" @default.
• W4310263731 title "Comparison of machine learning methods with logistic regression analysis in creating predictive models for risk of critical in-hospital events in COVID-19 patients on hospital admission" @default.
• W4310263731 cites W1480376833 @default.
• W4310263731 cites W1885924565 @default.
• W4310263731 cites W1994011595 @default.
• W4310263731 cites W2119910794 @default.
• W4310263731 cites W2157825442 @default.
• W4310263731 cites W2731142262 @default.
• W4310263731 cites W2782098519 @default.
• W4310263731 cites W2888109941 @default.
• W4310263731 cites W2934399013 @default.
• W4310263731 cites W2945976633 @default.
• W4310263731 cites W2990427812 @default.
• W4310263731 cites W3008090866 @default.
• W4310263731 cites W3008867523 @default.
• W4310263731 cites W3009885589 @default.
• W4310263731 cites W3011392786 @default.
• W4310263731 cites W3011605790 @default.
• W4310263731 cites W3011871622 @default.
• W4310263731 cites W3014105681 @default.
• W4310263731 cites W3014294089 @default.
• W4310263731 cites W3014524604 @default.
• W4310263731 cites W3014604938 @default.
• W4310263731 cites W3020168167 @default.
• W4310263731 cites W3024193040 @default.
• W4310263731 cites W3025349107 @default.
• W4310263731 cites W3031884707 @default.
• W4310263731 cites W3046101830 @default.
• W4310263731 cites W3092284106 @default.
• W4310263731 cites W3092436046 @default.
• W4310263731 cites W3092863233 @default.
• W4310263731 cites W3095153958 @default.
• W4310263731 cites W3096778362 @default.
• W4310263731 cites W3105811588 @default.
• W4310263731 cites W3106370138 @default.
• W4310263731 cites W3111029093 @default.
• W4310263731 cites W3112105690 @default.
• W4310263731 cites W3117730334 @default.
• W4310263731 cites W3118996476 @default.
• W4310263731 cites W3119809428 @default.
• W4310263731 cites W3129425233 @default.
• W4310263731 cites W3144611861 @default.
• W4310263731 cites W3149713727 @default.
• W4310263731 cites W3165479483 @default.
• W4310263731 cites W3166645852 @default.
• W4310263731 cites W3175417087 @default.
• W4310263731 cites W4205339139 @default.
• W4310263731 cites W4210642183 @default.
• W4310263731 cites W4242289937 @default.
• W4310263731 doi "https://doi.org/10.1186/s12911-022-02057-4" @default.
• W4310263731 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36437469" @default.
• W4310263731 hasPublicationYear "2022" @default.
• W4310263731 type Work @default.
• W4310263731 citedByCount "4" @default.
• W4310263731 countsByYear W43102637312022 @default.
• W4310263731 countsByYear W43102637312023 @default.
• W4310263731 crossrefType "journal-article" @default.
• W4310263731 hasAuthorship W4310263731A5015346451 @default.
• W4310263731 hasAuthorship W4310263731A5030120350 @default.
• W4310263731 hasAuthorship W4310263731A5036649021 @default.
• W4310263731 hasAuthorship W4310263731A5044680284 @default.
• W4310263731 hasAuthorship W4310263731A5049925686 @default.
• W4310263731 hasAuthorship W4310263731A5052808201 @default.
• W4310263731 hasAuthorship W4310263731A5052838808 @default.
• W4310263731 hasAuthorship W4310263731A5055805646 @default.
• W4310263731 hasAuthorship W4310263731A5059701911 @default.
• W4310263731 hasAuthorship W4310263731A5062888430 @default.
• W4310263731 hasAuthorship W4310263731A5080637646 @default.
• W4310263731 hasAuthorship W4310263731A5082497021 @default.
• W4310263731 hasAuthorship W4310263731A5083684330 @default.
• W4310263731 hasAuthorship W4310263731A5088860959 @default.
• W4310263731 hasBestOaLocation W43102637311 @default.
• W4310263731 hasConcept C105795698 @default.
• W4310263731 hasConcept C107038049 @default.
• W4310263731 hasConcept C119857082 @default.
• W4310263731 hasConcept C12267149 @default.
• W4310263731 hasConcept C126322002 @default.
• W4310263731 hasConcept C138885662 @default.
• W4310263731 hasConcept C151956035 @default.
• W4310263731 hasConcept C154945302 @default.
• W4310263731 hasConcept C169258074 @default.
• W4310263731 hasConcept C194828623 @default.
• W4310263731 hasConcept C2776376669 @default.

• next