FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2988932415> ?p ?o ?g. }

• W2988932415 abstract "Abstract Introduction Metabolomics is increasingly being used in the clinical setting for disease diagnosis, prognosis and risk prediction. Machine learning algorithms are particularly important in the construction of multivariate metabolite prediction. Historically, partial least squares (PLS) regression has been the gold standard for binary classification. Nonlinear machine learning methods such as random forests (RF), kernel support vector machines (SVM) and artificial neural networks (ANN) may be more suited to modelling possible nonlinear metabolite covariance, and thus provide better predictive models. Objectives We hypothesise that for binary classification using metabolomics data, non-linear machine learning methods will provide superior generalised predictive ability when compared to linear alternatives, in particular when compared with the current gold standard PLS discriminant analysis. Methods We compared the general predictive performance of eight archetypal machine learning algorithms across ten publicly available clinical metabolomics data sets. The algorithms were implemented in the Python programming language. All code and results have been made publicly available as Jupyter notebooks. Results There was only marginal improvement in predictive ability for SVM and ANN over PLS across all data sets. RF performance was comparatively poor. The use of out-of-bag bootstrap confidence intervals provided a measure of uncertainty of model prediction such that the quality of metabolomics data was observed to be a bigger influence on generalised performance than model choice. Conclusion The size of the data set, and choice of performance metric, had a greater influence on generalised predictive performance than the choice of machine learning algorithm." @default.
• W2988932415 created "2019-11-22" @default.
• W2988932415 creator A5012899764 @default.
• W2988932415 creator A5030412255 @default.
• W2988932415 creator A5035432255 @default.
• W2988932415 date "2019-11-15" @default.
• W2988932415 modified "2023-10-03" @default.
• W2988932415 title "A comparative evaluation of the generalised predictive ability of eight machine learning algorithms across ten clinical metabolomics data sets for binary classification" @default.
• W2988932415 cites W1507985183 @default.
• W2988932415 cites W1845196127 @default.
• W2988932415 cites W1960974681 @default.
• W2988932415 cites W1974086876 @default.
• W2988932415 cites W1976251851 @default.
• W2988932415 cites W1987336542 @default.
• W2988932415 cites W1987972238 @default.
• W2988932415 cites W1997832875 @default.
• W2988932415 cites W2059327215 @default.
• W2988932415 cites W2066860102 @default.
• W2988932415 cites W2069928158 @default.
• W2988932415 cites W2079529928 @default.
• W2988932415 cites W2084341220 @default.
• W2988932415 cites W2084375915 @default.
• W2988932415 cites W2089181989 @default.
• W2988932415 cites W2113442785 @default.
• W2988932415 cites W2143283561 @default.
• W2988932415 cites W2143860368 @default.
• W2988932415 cites W2146103026 @default.
• W2988932415 cites W2154631167 @default.
• W2988932415 cites W2164334572 @default.
• W2988932415 cites W2193923663 @default.
• W2988932415 cites W2341820027 @default.
• W2988932415 cites W2342249984 @default.
• W2988932415 cites W2504691963 @default.
• W2988932415 cites W2591124526 @default.
• W2988932415 cites W2744726626 @default.
• W2988932415 cites W2767683865 @default.
• W2988932415 cites W2774287749 @default.
• W2988932415 cites W2787894218 @default.
• W2988932415 cites W2802842185 @default.
• W2988932415 cites W2857924514 @default.
• W2988932415 cites W2903406988 @default.
• W2988932415 cites W2911964244 @default.
• W2988932415 cites W2915293971 @default.
• W2988932415 cites W2972529175 @default.
• W2988932415 cites W2980773467 @default.
• W2988932415 cites W2981692361 @default.
• W2988932415 cites W4235243453 @default.
• W2988932415 cites W4301003819 @default.
• W2988932415 cites W789633868 @default.
• W2988932415 doi "https://doi.org/10.1007/s11306-019-1612-4" @default.
• W2988932415 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6856029" @default.
• W2988932415 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31728648" @default.
• W2988932415 hasPublicationYear "2019" @default.
• W2988932415 type Work @default.
• W2988932415 sameAs 2988932415 @default.
• W2988932415 citedByCount "90" @default.
• W2988932415 countsByYear W29889324152020 @default.
• W2988932415 countsByYear W29889324152021 @default.
• W2988932415 countsByYear W29889324152022 @default.
• W2988932415 countsByYear W29889324152023 @default.
• W2988932415 crossrefType "journal-article" @default.
• W2988932415 hasAuthorship W2988932415A5012899764 @default.
• W2988932415 hasAuthorship W2988932415A5030412255 @default.
• W2988932415 hasAuthorship W2988932415A5035432255 @default.
• W2988932415 hasBestOaLocation W29889324151 @default.
• W2988932415 hasConcept C11413529 @default.
• W2988932415 hasConcept C119857082 @default.
• W2988932415 hasConcept C12267149 @default.
• W2988932415 hasConcept C124101348 @default.
• W2988932415 hasConcept C154945302 @default.
• W2988932415 hasConcept C161584116 @default.
• W2988932415 hasConcept C169258074 @default.
• W2988932415 hasConcept C33923547 @default.
• W2988932415 hasConcept C41008148 @default.
• W2988932415 hasConcept C48372109 @default.
• W2988932415 hasConcept C50644808 @default.
• W2988932415 hasConcept C58489278 @default.
• W2988932415 hasConcept C66905080 @default.
• W2988932415 hasConcept C69738355 @default.
• W2988932415 hasConcept C94375191 @default.
• W2988932415 hasConceptScore W2988932415C11413529 @default.
• W2988932415 hasConceptScore W2988932415C119857082 @default.
• W2988932415 hasConceptScore W2988932415C12267149 @default.
• W2988932415 hasConceptScore W2988932415C124101348 @default.
• W2988932415 hasConceptScore W2988932415C154945302 @default.
• W2988932415 hasConceptScore W2988932415C161584116 @default.
• W2988932415 hasConceptScore W2988932415C169258074 @default.
• W2988932415 hasConceptScore W2988932415C33923547 @default.
• W2988932415 hasConceptScore W2988932415C41008148 @default.
• W2988932415 hasConceptScore W2988932415C48372109 @default.
• W2988932415 hasConceptScore W2988932415C50644808 @default.
• W2988932415 hasConceptScore W2988932415C58489278 @default.
• W2988932415 hasConceptScore W2988932415C66905080 @default.
• W2988932415 hasConceptScore W2988932415C69738355 @default.
• W2988932415 hasConceptScore W2988932415C94375191 @default.
• W2988932415 hasFunder F4320334704 @default.
• W2988932415 hasIssue "12" @default.
• W2988932415 hasLocation W29889324151 @default.
• W2988932415 hasLocation W29889324152 @default.
• W2988932415 hasLocation W29889324153 @default.

• next