FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312492035> ?p ?o ?g. }

• W4312492035 abstract "A major challenge in delivering reliable and trustworthy computational intelligence for practical applications in clinical medicine is interpretability. This aspect of machine learning is a major distinguishing factor compared with traditional statistical models for the stratification of patients, which typically use rules or a risk score identified by logistic regression. We show how functions of one and two variables can be extracted from pre-trained machine learning models using anchored Analysis of Variance (ANOVA) decompositions. This enables complex interaction terms to be filtered out by aggressive regularisation using the Least Absolute Shrinkage and Selection Operator (LASSO) resulting in a sparse model with comparable or even better performance than the original pre-trained black-box. Besides being theoretically well-founded, the decomposition of a black-box multivariate probabilistic binary classifier into a General Additive Model (GAM) comprising a linear combination of non-linear functions of one or two variables provides full interpretability. In effect this extends logistic regression into non-linear modelling without the need for manual intervention by way of variable transformations, using the pre-trained model as a seed. The application of the proposed methodology to existing machine learning models is demonstrated using the Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Random Forests (RF) and Gradient Boosting Machines (GBM), to model a data frame from a well-known benchmark dataset available from Physionet, the Medical Information Mart for Intensive Care (MIMIC-III). Both the classification performance and plausibility of clinical interpretation compare favourably with other state-of-the-art sparse models namely Sparse Additive Models (SAM) and the Explainable Boosting Machine (EBM)." @default.
• W4312492035 created "2023-01-05" @default.
• W4312492035 creator A5010155676 @default.
• W4312492035 creator A5012312860 @default.
• W4312492035 creator A5028083196 @default.
• W4312492035 creator A5077858988 @default.
• W4312492035 date "2022-07-18" @default.
• W4312492035 modified "2023-10-16" @default.
• W4312492035 title "Towards interpretable machine learning for clinical decision support" @default.
• W4312492035 cites W1603121691 @default.
• W4312492035 cites W1968835864 @default.
• W4312492035 cites W2088286197 @default.
• W4312492035 cites W2093827448 @default.
• W4312492035 cites W2593996946 @default.
• W4312492035 cites W2911964244 @default.
• W4312492035 cites W2913997948 @default.
• W4312492035 cites W2945976633 @default.
• W4312492035 doi "https://doi.org/10.1109/ijcnn55064.2022.9892114" @default.
• W4312492035 hasPublicationYear "2022" @default.
• W4312492035 type Work @default.
• W4312492035 citedByCount "1" @default.
• W4312492035 countsByYear W43124920352023 @default.
• W4312492035 crossrefType "proceedings-article" @default.
• W4312492035 hasAuthorship W4312492035A5010155676 @default.
• W4312492035 hasAuthorship W4312492035A5012312860 @default.
• W4312492035 hasAuthorship W4312492035A5028083196 @default.
• W4312492035 hasAuthorship W4312492035A5077858988 @default.
• W4312492035 hasBestOaLocation W43124920352 @default.
• W4312492035 hasConcept C119857082 @default.
• W4312492035 hasConcept C12267149 @default.
• W4312492035 hasConcept C136764020 @default.
• W4312492035 hasConcept C154945302 @default.
• W4312492035 hasConcept C169258074 @default.
• W4312492035 hasConcept C22019652 @default.
• W4312492035 hasConcept C2781067378 @default.
• W4312492035 hasConcept C37616216 @default.
• W4312492035 hasConcept C41008148 @default.
• W4312492035 hasConcept C50644808 @default.
• W4312492035 hasConcept C70153297 @default.
• W4312492035 hasConceptScore W4312492035C119857082 @default.
• W4312492035 hasConceptScore W4312492035C12267149 @default.
• W4312492035 hasConceptScore W4312492035C136764020 @default.
• W4312492035 hasConceptScore W4312492035C154945302 @default.
• W4312492035 hasConceptScore W4312492035C169258074 @default.
• W4312492035 hasConceptScore W4312492035C22019652 @default.
• W4312492035 hasConceptScore W4312492035C2781067378 @default.
• W4312492035 hasConceptScore W4312492035C37616216 @default.
• W4312492035 hasConceptScore W4312492035C41008148 @default.
• W4312492035 hasConceptScore W4312492035C50644808 @default.
• W4312492035 hasConceptScore W4312492035C70153297 @default.
• W4312492035 hasLocation W43124920351 @default.
• W4312492035 hasLocation W43124920352 @default.
• W4312492035 hasOpenAccess W4312492035 @default.
• W4312492035 hasPrimaryLocation W43124920351 @default.
• W4312492035 hasRelatedWork W1996541855 @default.
• W4312492035 hasRelatedWork W2003998164 @default.
• W4312492035 hasRelatedWork W2953269510 @default.
• W4312492035 hasRelatedWork W2985459377 @default.
• W4312492035 hasRelatedWork W3015057159 @default.
• W4312492035 hasRelatedWork W3195168932 @default.
• W4312492035 hasRelatedWork W3208985699 @default.
• W4312492035 hasRelatedWork W3214303109 @default.
• W4312492035 hasRelatedWork W4205958290 @default.
• W4312492035 hasRelatedWork W4221149677 @default.
• W4312492035 isParatext "false" @default.
• W4312492035 isRetracted "false" @default.
• W4312492035 workType "article" @default.