FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381330509> ?p ?o ?g. }

• W4381330509 abstract "Abstract Background Risk prediction models are used in healthcare settings to tailor therapies to individuals most likely to benefit. Despite appropriate external validation, difference in local characteristics (e.g. patient mix) may attenuate model performance. Prior to any implementation it is therefore advisable to explore local performance, typically requiring a modest amount of historic data. Depending on model performance, model adjustments might be necessary which often require large amounts of data. Here we explore a small sample size approach approximating de novo derivation, by combining model stacking and transfer learning, referred to as stacked transfer learning . As an example we focus on stacking previously trained risk prediction models for cardiovascular disease (CVD), stroke, (chronic) kidney disease, and diabetes. Methods We leverage data from the UK biobank to illustrate the benefits of stacking previously trained risk prediction models, predicting the risk of incident CVD, chronic kidney disease (CKD) or diabetes. To mimic sample sizes available in local settings, such as a small to large healthcare trust, we iterated the number of training cases between 10 and 1000. Model stacking was performed using a LASSO penalized logistic regression model, and compared performance of a de novo model estimating the local association of 33 variables used in the aforementioned risk prediction models. Results We found that stacked models require roughly one-tenths of the training sample size compared to de novo derivation of a prediction model. For example, predicting CVD the stacked model required 30 cases to reach a area under the curve (AUC) value (with 95% CI) of 0.732 (0.728, 0.735), while the de novo model required 300 cases to reach approximately the same performance. As expected, the absolute performance depended on the predicted outcome, where for example the difference between de novo and stacked modelling was smaller for CKD prediction. Conclusion We show that our proposed ”stacked transfer learning” approach closely approximated the predictive performance of a de novo model, often requiring only a fraction of the data. As such, this approach should be considered when tailoring a model to a local setting." @default.
• W4381330509 created "2023-06-21" @default.
• W4381330509 creator A5018148532 @default.
• W4381330509 creator A5031468653 @default.
• W4381330509 creator A5039782389 @default.
• W4381330509 creator A5066364214 @default.
• W4381330509 creator A5067023397 @default.
• W4381330509 creator A5080784945 @default.
• W4381330509 date "2023-06-20" @default.
• W4381330509 modified "2023-10-16" @default.
• W4381330509 title "Stacking multiple prediction models to optimise performance in local settings: exemplars in cardiometabolic disease" @default.
• W4381330509 cites W1964505066 @default.
• W4381330509 cites W2039855493 @default.
• W4381330509 cites W2049977108 @default.
• W4381330509 cites W2055838663 @default.
• W4381330509 cites W2097088950 @default.
• W4381330509 cites W2104039704 @default.
• W4381330509 cites W2154067841 @default.
• W4381330509 cites W2158810997 @default.
• W4381330509 cites W2161009717 @default.
• W4381330509 cites W2277974059 @default.
• W4381330509 cites W2399385044 @default.
• W4381330509 cites W2618596952 @default.
• W4381330509 cites W28412257 @default.
• W4381330509 cites W2911964244 @default.
• W4381330509 cites W2979648592 @default.
• W4381330509 cites W3007453563 @default.
• W4381330509 cites W3166015112 @default.
• W4381330509 cites W3188592254 @default.
• W4381330509 cites W3208674021 @default.
• W4381330509 cites W4212883601 @default.
• W4381330509 cites W4246169631 @default.
• W4381330509 cites W4255421341 @default.
• W4381330509 doi "https://doi.org/10.1101/2023.06.16.23291489" @default.
• W4381330509 hasPublicationYear "2023" @default.
• W4381330509 type Work @default.
• W4381330509 citedByCount "0" @default.
• W4381330509 crossrefType "posted-content" @default.
• W4381330509 hasAuthorship W4381330509A5018148532 @default.
• W4381330509 hasAuthorship W4381330509A5031468653 @default.
• W4381330509 hasAuthorship W4381330509A5039782389 @default.
• W4381330509 hasAuthorship W4381330509A5066364214 @default.
• W4381330509 hasAuthorship W4381330509A5067023397 @default.
• W4381330509 hasAuthorship W4381330509A5080784945 @default.
• W4381330509 hasBestOaLocation W43813305091 @default.
• W4381330509 hasConcept C119857082 @default.
• W4381330509 hasConcept C121332964 @default.
• W4381330509 hasConcept C126322002 @default.
• W4381330509 hasConcept C136764020 @default.
• W4381330509 hasConcept C149782125 @default.
• W4381330509 hasConcept C151956035 @default.
• W4381330509 hasConcept C153083717 @default.
• W4381330509 hasConcept C154945302 @default.
• W4381330509 hasConcept C2778653478 @default.
• W4381330509 hasConcept C2779134260 @default.
• W4381330509 hasConcept C33347731 @default.
• W4381330509 hasConcept C33923547 @default.
• W4381330509 hasConcept C37616216 @default.
• W4381330509 hasConcept C41008148 @default.
• W4381330509 hasConcept C45804977 @default.
• W4381330509 hasConcept C46141821 @default.
• W4381330509 hasConcept C71924100 @default.
• W4381330509 hasConceptScore W4381330509C119857082 @default.
• W4381330509 hasConceptScore W4381330509C121332964 @default.
• W4381330509 hasConceptScore W4381330509C126322002 @default.
• W4381330509 hasConceptScore W4381330509C136764020 @default.
• W4381330509 hasConceptScore W4381330509C149782125 @default.
• W4381330509 hasConceptScore W4381330509C151956035 @default.
• W4381330509 hasConceptScore W4381330509C153083717 @default.
• W4381330509 hasConceptScore W4381330509C154945302 @default.
• W4381330509 hasConceptScore W4381330509C2778653478 @default.
• W4381330509 hasConceptScore W4381330509C2779134260 @default.
• W4381330509 hasConceptScore W4381330509C33347731 @default.
• W4381330509 hasConceptScore W4381330509C33923547 @default.
• W4381330509 hasConceptScore W4381330509C37616216 @default.
• W4381330509 hasConceptScore W4381330509C41008148 @default.
• W4381330509 hasConceptScore W4381330509C45804977 @default.
• W4381330509 hasConceptScore W4381330509C46141821 @default.
• W4381330509 hasConceptScore W4381330509C71924100 @default.
• W4381330509 hasLocation W43813305091 @default.
• W4381330509 hasOpenAccess W4381330509 @default.
• W4381330509 hasPrimaryLocation W43813305091 @default.
• W4381330509 hasRelatedWork W3129804828 @default.
• W4381330509 hasRelatedWork W3167485325 @default.
• W4381330509 hasRelatedWork W3174196512 @default.
• W4381330509 hasRelatedWork W3201795316 @default.
• W4381330509 hasRelatedWork W3208954537 @default.
• W4381330509 hasRelatedWork W4283697347 @default.
• W4381330509 hasRelatedWork W4292297483 @default.
• W4381330509 hasRelatedWork W4318350883 @default.
• W4381330509 hasRelatedWork W4328100153 @default.
• W4381330509 hasRelatedWork W4376129292 @default.
• W4381330509 isParatext "false" @default.
• W4381330509 isRetracted "false" @default.
• W4381330509 workType "article" @default.