FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283271411> ?p ?o ?g. }

• W4283271411 abstract "Abstract The timely identification of cohort participants at higher risk for attrition is important to earlier interventions and efficient use of research resources. Machine learning may have advantages over the conventional approaches to improve discrimination by analysing complex interactions among predictors. We developed predictive models of attrition applying a conventional regression model and different machine learning methods. A total of 542 very preterm (< 32 gestational weeks) infants born in Portugal as part of the European Effective Perinatal Intensive Care in Europe (EPICE) cohort were included. We tested a model with a fixed number of predictors (Baseline) and a second with a dynamic number of variables added from each follow-up (Incremental). Eight classification methods were applied: AdaBoost, Artificial Neural Networks, Functional Trees, J48, J48Consolidated, K-Nearest Neighbours, Random Forest and Logistic Regression. Performance was compared using AUC- PR (Area Under the Curve—Precision Recall), Accuracy, Sensitivity and F-measure. Attrition at the four follow-ups were, respectively: 16%, 25%, 13% and 17%. Both models demonstrated good predictive performance, AUC-PR ranging between 69 and 94.1 in Baseline and from 72.5 to 97.1 in Incremental model. Of the whole set of methods, Random Forest presented the best performance at all follow-ups [AUC-PR 1 : 94.1 (2.0); AUC-PR 2 : 91.2 (1.2); AUC-PR 3 : 97.1 (1.0); AUC-PR 4 : 96.5 (1.7)]. Logistic Regression performed well below Random Forest. The top-ranked predictors were common for both models in all follow-ups: birthweight, gestational age, maternal age, and length of hospital stay. Random Forest presented the highest capacity for prediction and provided interpretable predictors. Researchers involved in cohorts can benefit from our robust models to prepare for and prevent loss to follow-up by directing efforts toward individuals at higher risk." @default.
• W4283271411 created "2022-06-23" @default.
• W4283271411 creator A5000045150 @default.
• W4283271411 creator A5024183114 @default.
• W4283271411 creator A5052801467 @default.
• W4283271411 creator A5054960351 @default.
• W4283271411 creator A5080805828 @default.
• W4283271411 date "2022-06-22" @default.
• W4283271411 modified "2023-10-09" @default.
• W4283271411 title "Machine learning methods to predict attrition in a population-based cohort of very preterm infants" @default.
• W4283271411 cites W14889875 @default.
• W4283271411 cites W1523646822 @default.
• W4283271411 cites W1678356000 @default.
• W4283271411 cites W1968185435 @default.
• W4283271411 cites W1991663474 @default.
• W4283271411 cites W1994373098 @default.
• W4283271411 cites W2000100883 @default.
• W4283271411 cites W2018129692 @default.
• W4283271411 cites W2035317753 @default.
• W4283271411 cites W2039363170 @default.
• W4283271411 cites W2049342566 @default.
• W4283271411 cites W2100483895 @default.
• W4283271411 cites W2102385550 @default.
• W4283271411 cites W2104408964 @default.
• W4283271411 cites W2112927272 @default.
• W4283271411 cites W2113996138 @default.
• W4283271411 cites W2138702343 @default.
• W4283271411 cites W2144638606 @default.
• W4283271411 cites W2148143831 @default.
• W4283271411 cites W2169460734 @default.
• W4283271411 cites W2181198841 @default.
• W4283271411 cites W2213612645 @default.
• W4283271411 cites W2330219538 @default.
• W4283271411 cites W2549885908 @default.
• W4283271411 cites W2605512411 @default.
• W4283271411 cites W2607507174 @default.
• W4283271411 cites W2611242934 @default.
• W4283271411 cites W2754847445 @default.
• W4283271411 cites W2787894218 @default.
• W4283271411 cites W2789894922 @default.
• W4283271411 cites W2791586419 @default.
• W4283271411 cites W2903398845 @default.
• W4283271411 cites W2903513624 @default.
• W4283271411 cites W2913997948 @default.
• W4283271411 cites W2936646822 @default.
• W4283271411 cites W2944413189 @default.
• W4283271411 cites W2973032093 @default.
• W4283271411 cites W2986172564 @default.
• W4283271411 cites W3005282566 @default.
• W4283271411 cites W3005282861 @default.
• W4283271411 cites W3128004879 @default.
• W4283271411 cites W3129369392 @default.
• W4283271411 cites W3168481398 @default.
• W4283271411 cites W4212883601 @default.
• W4283271411 cites W4246165039 @default.
• W4283271411 cites W429766147 @default.
• W4283271411 doi "https://doi.org/10.1038/s41598-022-13946-z" @default.
• W4283271411 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35732850" @default.
• W4283271411 hasPublicationYear "2022" @default.
• W4283271411 type Work @default.
• W4283271411 citedByCount "1" @default.
• W4283271411 countsByYear W42832714112022 @default.
• W4283271411 crossrefType "journal-article" @default.
• W4283271411 hasAuthorship W4283271411A5000045150 @default.
• W4283271411 hasAuthorship W4283271411A5024183114 @default.
• W4283271411 hasAuthorship W4283271411A5052801467 @default.
• W4283271411 hasAuthorship W4283271411A5054960351 @default.
• W4283271411 hasAuthorship W4283271411A5080805828 @default.
• W4283271411 hasBestOaLocation W42832714111 @default.
• W4283271411 hasConcept C105795698 @default.
• W4283271411 hasConcept C119857082 @default.
• W4283271411 hasConcept C12267149 @default.
• W4283271411 hasConcept C126322002 @default.
• W4283271411 hasConcept C141404830 @default.
• W4283271411 hasConcept C151956035 @default.
• W4283271411 hasConcept C154945302 @default.
• W4283271411 hasConcept C169258074 @default.
• W4283271411 hasConcept C2778376644 @default.
• W4283271411 hasConcept C2779234561 @default.
• W4283271411 hasConcept C2908647359 @default.
• W4283271411 hasConcept C33923547 @default.
• W4283271411 hasConcept C41008148 @default.
• W4283271411 hasConcept C54355233 @default.
• W4283271411 hasConcept C71924100 @default.
• W4283271411 hasConcept C72563966 @default.
• W4283271411 hasConcept C76318530 @default.
• W4283271411 hasConcept C86803240 @default.
• W4283271411 hasConcept C99454951 @default.
• W4283271411 hasConceptScore W4283271411C105795698 @default.
• W4283271411 hasConceptScore W4283271411C119857082 @default.
• W4283271411 hasConceptScore W4283271411C12267149 @default.
• W4283271411 hasConceptScore W4283271411C126322002 @default.
• W4283271411 hasConceptScore W4283271411C141404830 @default.
• W4283271411 hasConceptScore W4283271411C151956035 @default.
• W4283271411 hasConceptScore W4283271411C154945302 @default.
• W4283271411 hasConceptScore W4283271411C169258074 @default.
• W4283271411 hasConceptScore W4283271411C2778376644 @default.
• W4283271411 hasConceptScore W4283271411C2779234561 @default.
• W4283271411 hasConceptScore W4283271411C2908647359 @default.
• W4283271411 hasConceptScore W4283271411C33923547 @default.

• next