FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308687480> ?p ?o ?g. }

• W4308687480 endingPage "e38053" @default.
• W4308687480 startingPage "e38053" @default.
• W4308687480 abstract "Background Clinical prediction models suffer from performance drift as the patient population shifts over time. There is a great need for model updating approaches or modeling frameworks that can effectively use the old and new data. Objective Based on the paradigm of transfer learning, we aimed to develop a novel modeling framework that transfers old knowledge to the new environment for prediction tasks, and contributes to performance drift correction. Methods The proposed predictive modeling framework maintains a logistic regression–based stacking ensemble of 2 gradient boosting machine (GBM) models representing old and new knowledge learned from old and new data, respectively (referred to as transfer learning gradient boosting machine [TransferGBM]). The ensemble learning procedure can dynamically balance the old and new knowledge. Using 2010-2017 electronic health record data on a retrospective cohort of 141,696 patients, we validated TransferGBM for hospital-acquired acute kidney injury prediction. Results The baseline models (ie, transported models) that were trained on 2010 and 2011 data showed significant performance drift in the temporal validation with 2012-2017 data. Refitting these models using updated samples resulted in performance gains in nearly all cases. The proposed TransferGBM model succeeded in achieving uniformly better performance than the refitted models. Conclusions Under the scenario of population shift, incorporating new knowledge while preserving old knowledge is essential for maintaining stable performance. Transfer learning combined with stacking ensemble learning can help achieve a balance of old and new knowledge in a flexible and adaptive way, even in the case of insufficient new data." @default.
• W4308687480 created "2022-11-14" @default.
• W4308687480 creator A5000674363 @default.
• W4308687480 creator A5005495670 @default.
• W4308687480 creator A5019956002 @default.
• W4308687480 creator A5036466755 @default.
• W4308687480 creator A5043817770 @default.
• W4308687480 creator A5051254107 @default.
• W4308687480 creator A5079920092 @default.
• W4308687480 creator A5086685216 @default.
• W4308687480 date "2022-11-09" @default.
• W4308687480 modified "2023-10-18" @default.
• W4308687480 title "A Transfer Learning Approach to Correct the Temporal Performance Drift of Clinical Prediction Models: Retrospective Cohort Study" @default.
• W4308687480 cites W1978288447 @default.
• W4308687480 cites W1997192661 @default.
• W4308687480 cites W2026274122 @default.
• W4308687480 cites W2051411536 @default.
• W4308687480 cites W2096943734 @default.
• W4308687480 cites W2114717670 @default.
• W4308687480 cites W2115538424 @default.
• W4308687480 cites W2122838776 @default.
• W4308687480 cites W2130502422 @default.
• W4308687480 cites W2132755184 @default.
• W4308687480 cites W2141559993 @default.
• W4308687480 cites W2151056789 @default.
• W4308687480 cites W2165698076 @default.
• W4308687480 cites W2229387242 @default.
• W4308687480 cites W2288769870 @default.
• W4308687480 cites W2395579298 @default.
• W4308687480 cites W2594685110 @default.
• W4308687480 cites W2604834158 @default.
• W4308687480 cites W2625625371 @default.
• W4308687480 cites W2746326048 @default.
• W4308687480 cites W2793894561 @default.
• W4308687480 cites W2794885170 @default.
• W4308687480 cites W28412257 @default.
• W4308687480 cites W2900559149 @default.
• W4308687480 cites W2900583566 @default.
• W4308687480 cites W2940010972 @default.
• W4308687480 cites W2964696298 @default.
• W4308687480 cites W2967329333 @default.
• W4308687480 cites W2997591727 @default.
• W4308687480 cites W3010261457 @default.
• W4308687480 cites W3041133507 @default.
• W4308687480 cites W3041232348 @default.
• W4308687480 cites W3096597179 @default.
• W4308687480 cites W3098674050 @default.
• W4308687480 cites W3102476541 @default.
• W4308687480 cites W3135939397 @default.
• W4308687480 cites W3137670674 @default.
• W4308687480 cites W3209074506 @default.
• W4308687480 cites W4205661592 @default.
• W4308687480 doi "https://doi.org/10.2196/38053" @default.
• W4308687480 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36350705" @default.
• W4308687480 hasPublicationYear "2022" @default.
• W4308687480 type Work @default.
• W4308687480 citedByCount "1" @default.
• W4308687480 crossrefType "journal-article" @default.
• W4308687480 hasAuthorship W4308687480A5000674363 @default.
• W4308687480 hasAuthorship W4308687480A5005495670 @default.
• W4308687480 hasAuthorship W4308687480A5019956002 @default.
• W4308687480 hasAuthorship W4308687480A5036466755 @default.
• W4308687480 hasAuthorship W4308687480A5043817770 @default.
• W4308687480 hasAuthorship W4308687480A5051254107 @default.
• W4308687480 hasAuthorship W4308687480A5079920092 @default.
• W4308687480 hasAuthorship W4308687480A5086685216 @default.
• W4308687480 hasBestOaLocation W43086874801 @default.
• W4308687480 hasConcept C105795698 @default.
• W4308687480 hasConcept C108583219 @default.
• W4308687480 hasConcept C119857082 @default.
• W4308687480 hasConcept C119898033 @default.
• W4308687480 hasConcept C124101348 @default.
• W4308687480 hasConcept C150899416 @default.
• W4308687480 hasConcept C151956035 @default.
• W4308687480 hasConcept C154945302 @default.
• W4308687480 hasConcept C169258074 @default.
• W4308687480 hasConcept C2908647359 @default.
• W4308687480 hasConcept C33923547 @default.
• W4308687480 hasConcept C41008148 @default.
• W4308687480 hasConcept C45942800 @default.
• W4308687480 hasConcept C46686674 @default.
• W4308687480 hasConcept C70153297 @default.
• W4308687480 hasConcept C71924100 @default.
• W4308687480 hasConcept C83546350 @default.
• W4308687480 hasConcept C99454951 @default.
• W4308687480 hasConceptScore W4308687480C105795698 @default.
• W4308687480 hasConceptScore W4308687480C108583219 @default.
• W4308687480 hasConceptScore W4308687480C119857082 @default.
• W4308687480 hasConceptScore W4308687480C119898033 @default.
• W4308687480 hasConceptScore W4308687480C124101348 @default.
• W4308687480 hasConceptScore W4308687480C150899416 @default.
• W4308687480 hasConceptScore W4308687480C151956035 @default.
• W4308687480 hasConceptScore W4308687480C154945302 @default.
• W4308687480 hasConceptScore W4308687480C169258074 @default.
• W4308687480 hasConceptScore W4308687480C2908647359 @default.
• W4308687480 hasConceptScore W4308687480C33923547 @default.
• W4308687480 hasConceptScore W4308687480C41008148 @default.
• W4308687480 hasConceptScore W4308687480C45942800 @default.

• next