FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4291778051> ?p ?o ?g. }

• W4291778051 endingPage "1314" @default.
• W4291778051 startingPage "1314" @default.
• W4291778051 abstract "There has been a rapid increase in the number of artificial intelligence (AI)/machine learning (ML)-based biomarker diagnostic classifiers in recent years. However, relatively little work has focused on assessing the robustness of these biomarkers, i.e., investigating the uncertainty of the AI/ML models that these biomarkers are based upon. This paper addresses this issue by proposing a framework to evaluate the already-developed classifiers with regard to their robustness by focusing on the variability of the classifiers' performance and changes in the classifiers' parameter values using factor analysis and Monte Carlo simulations. Specifically, this work evaluates (1) the importance of a classifier's input features and (2) the variability of a classifier's output and model parameter values in response to data perturbations. Additionally, it was found that one can estimate a priori how much replacement noise a classifier can tolerate while still meeting accuracy goals. To illustrate the evaluation framework, six different AI/ML-based biomarkers are developed using commonly used techniques (linear discriminant analysis, support vector machines, random forest, partial-least squares discriminant analysis, logistic regression, and multilayer perceptron) for a metabolomics dataset involving 24 measured metabolites taken from 159 study participants. The framework was able to correctly predict which of the classifiers should be less robust than others without recomputing the classifiers itself, and this prediction was then validated in a detailed analysis." @default.
• W4291778051 created "2022-08-16" @default.
• W4291778051 creator A5051700680 @default.
• W4291778051 creator A5054075262 @default.
• W4291778051 creator A5079899251 @default.
• W4291778051 creator A5082423923 @default.
• W4291778051 creator A5089210884 @default.
• W4291778051 date "2022-08-14" @default.
• W4291778051 modified "2023-09-30" @default.
• W4291778051 title "Framework for Testing Robustness of Machine Learning-Based Classifiers" @default.
• W4291778051 cites W1966089218 @default.
• W4291778051 cites W1987971958 @default.
• W4291778051 cites W1998033595 @default.
• W4291778051 cites W2007283076 @default.
• W4291778051 cites W2089468765 @default.
• W4291778051 cites W2108832705 @default.
• W4291778051 cites W2124563089 @default.
• W4291778051 cites W2128733344 @default.
• W4291778051 cites W2140405352 @default.
• W4291778051 cites W2148681431 @default.
• W4291778051 cites W2169006190 @default.
• W4291778051 cites W2470233764 @default.
• W4291778051 cites W2595641790 @default.
• W4291778051 cites W2750378047 @default.
• W4291778051 cites W2789242863 @default.
• W4291778051 cites W2802842185 @default.
• W4291778051 cites W2898280479 @default.
• W4291778051 cites W2911964244 @default.
• W4291778051 cites W2959053591 @default.
• W4291778051 cites W2981679558 @default.
• W4291778051 cites W2988932415 @default.
• W4291778051 cites W2989987020 @default.
• W4291778051 cites W2999948429 @default.
• W4291778051 cites W3004794953 @default.
• W4291778051 cites W3022436500 @default.
• W4291778051 cites W3034396232 @default.
• W4291778051 cites W3102100346 @default.
• W4291778051 cites W3107587236 @default.
• W4291778051 cites W3112212292 @default.
• W4291778051 cites W3133626685 @default.
• W4291778051 cites W3143784018 @default.
• W4291778051 cites W4221095552 @default.
• W4291778051 cites W4221114735 @default.
• W4291778051 cites W4235169531 @default.
• W4291778051 cites W4239510810 @default.
• W4291778051 cites W4286889204 @default.
• W4291778051 cites W4288618204 @default.
• W4291778051 cites W4292294985 @default.
• W4291778051 doi "https://doi.org/10.3390/jpm12081314" @default.
• W4291778051 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36013263" @default.
• W4291778051 hasPublicationYear "2022" @default.
• W4291778051 type Work @default.
• W4291778051 citedByCount "2" @default.
• W4291778051 countsByYear W42917780512023 @default.
• W4291778051 crossrefType "journal-article" @default.
• W4291778051 hasAuthorship W4291778051A5051700680 @default.
• W4291778051 hasAuthorship W4291778051A5054075262 @default.
• W4291778051 hasAuthorship W4291778051A5079899251 @default.
• W4291778051 hasAuthorship W4291778051A5082423923 @default.
• W4291778051 hasAuthorship W4291778051A5089210884 @default.
• W4291778051 hasBestOaLocation W42917780511 @default.
• W4291778051 hasConcept C104317684 @default.
• W4291778051 hasConcept C106135958 @default.
• W4291778051 hasConcept C111472728 @default.
• W4291778051 hasConcept C119857082 @default.
• W4291778051 hasConcept C12267149 @default.
• W4291778051 hasConcept C124101348 @default.
• W4291778051 hasConcept C138885662 @default.
• W4291778051 hasConcept C153180895 @default.
• W4291778051 hasConcept C154945302 @default.
• W4291778051 hasConcept C169258074 @default.
• W4291778051 hasConcept C179717631 @default.
• W4291778051 hasConcept C185592680 @default.
• W4291778051 hasConcept C41008148 @default.
• W4291778051 hasConcept C50644808 @default.
• W4291778051 hasConcept C55493867 @default.
• W4291778051 hasConcept C60908668 @default.
• W4291778051 hasConcept C63479239 @default.
• W4291778051 hasConcept C69738355 @default.
• W4291778051 hasConcept C75553542 @default.
• W4291778051 hasConcept C95623464 @default.
• W4291778051 hasConceptScore W4291778051C104317684 @default.
• W4291778051 hasConceptScore W4291778051C106135958 @default.
• W4291778051 hasConceptScore W4291778051C111472728 @default.
• W4291778051 hasConceptScore W4291778051C119857082 @default.
• W4291778051 hasConceptScore W4291778051C12267149 @default.
• W4291778051 hasConceptScore W4291778051C124101348 @default.
• W4291778051 hasConceptScore W4291778051C138885662 @default.
• W4291778051 hasConceptScore W4291778051C153180895 @default.
• W4291778051 hasConceptScore W4291778051C154945302 @default.
• W4291778051 hasConceptScore W4291778051C169258074 @default.
• W4291778051 hasConceptScore W4291778051C179717631 @default.
• W4291778051 hasConceptScore W4291778051C185592680 @default.
• W4291778051 hasConceptScore W4291778051C41008148 @default.
• W4291778051 hasConceptScore W4291778051C50644808 @default.
• W4291778051 hasConceptScore W4291778051C55493867 @default.
• W4291778051 hasConceptScore W4291778051C60908668 @default.
• W4291778051 hasConceptScore W4291778051C63479239 @default.

• next