Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386585667> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4386585667 endingPage "226" @default.
- W4386585667 startingPage "213" @default.
- W4386585667 abstract "Decision support systems with Artificial intelligence (AI) and specifically Machine Learning (ML) components present many challenges when assuring trust in operational performance, particularly in a safety-critical domain such as healthcare. During operation the Human in/on The Loop (HTL) may need assistance in determining when to trust the ML output and when to override it, particularly to prevent hazardous situations. In this paper, we consider how issues with training data shortfalls can cause varying safety performance in ML. We present a case study using an ML-based clinical decision support system for Type-2 diabetes related co-morbidity prediction (DCP). The DCP ML component is trained using real patient data, but the data was taken from a very large live database gathered over many years, and the records vary in distribution and completeness. Research developing similar clinical predictor systems describe different methods to compensate for training data shortfalls, but concentrate only on fixing the data to maximise the ML performance without considering a system safety perspective. This means the impact of the ML’s varying performance is not fully understood at the system level. Further, methods such as data imputation can introduce a further risk of bias which is not addressed. This paper combines the use of ML data shortfall compensation measures with exploratory safety analysis to ensure all means of reducing risk are considered. We demonstrate that together these provide a richer picture allowing more effective identification and mitigation of risks from training data shortfalls." @default.
- W4386585667 created "2023-09-11" @default.
- W4386585667 creator A5017840476 @default.
- W4386585667 creator A5028754426 @default.
- W4386585667 creator A5058387367 @default.
- W4386585667 creator A5088697701 @default.
- W4386585667 date "2023-01-01" @default.
- W4386585667 modified "2023-09-29" @default.
- W4386585667 title "The Impact of Training Data Shortfalls on Safety of AI-Based Clinical Decision Support Systems" @default.
- W4386585667 cites W1841820628 @default.
- W4386585667 cites W1985018187 @default.
- W4386585667 cites W2066139411 @default.
- W4386585667 cites W2303437212 @default.
- W4386585667 cites W2802899394 @default.
- W4386585667 cites W2956031335 @default.
- W4386585667 cites W2970297903 @default.
- W4386585667 cites W2990795246 @default.
- W4386585667 cites W3020776760 @default.
- W4386585667 cites W3080606572 @default.
- W4386585667 cites W3090931916 @default.
- W4386585667 cites W3147797821 @default.
- W4386585667 cites W3154598968 @default.
- W4386585667 cites W3195947859 @default.
- W4386585667 cites W3196440773 @default.
- W4386585667 cites W4308441226 @default.
- W4386585667 cites W4312787967 @default.
- W4386585667 cites W4377093409 @default.
- W4386585667 cites W77869065 @default.
- W4386585667 doi "https://doi.org/10.1007/978-3-031-40923-3_16" @default.
- W4386585667 hasPublicationYear "2023" @default.
- W4386585667 type Work @default.
- W4386585667 citedByCount "0" @default.
- W4386585667 crossrefType "book-chapter" @default.
- W4386585667 hasAuthorship W4386585667A5017840476 @default.
- W4386585667 hasAuthorship W4386585667A5028754426 @default.
- W4386585667 hasAuthorship W4386585667A5058387367 @default.
- W4386585667 hasAuthorship W4386585667A5088697701 @default.
- W4386585667 hasConcept C105795698 @default.
- W4386585667 hasConcept C107327155 @default.
- W4386585667 hasConcept C112930515 @default.
- W4386585667 hasConcept C119857082 @default.
- W4386585667 hasConcept C124101348 @default.
- W4386585667 hasConcept C133462117 @default.
- W4386585667 hasConcept C33923547 @default.
- W4386585667 hasConcept C41008148 @default.
- W4386585667 hasConcept C58041806 @default.
- W4386585667 hasConcept C71924100 @default.
- W4386585667 hasConcept C9357733 @default.
- W4386585667 hasConceptScore W4386585667C105795698 @default.
- W4386585667 hasConceptScore W4386585667C107327155 @default.
- W4386585667 hasConceptScore W4386585667C112930515 @default.
- W4386585667 hasConceptScore W4386585667C119857082 @default.
- W4386585667 hasConceptScore W4386585667C124101348 @default.
- W4386585667 hasConceptScore W4386585667C133462117 @default.
- W4386585667 hasConceptScore W4386585667C33923547 @default.
- W4386585667 hasConceptScore W4386585667C41008148 @default.
- W4386585667 hasConceptScore W4386585667C58041806 @default.
- W4386585667 hasConceptScore W4386585667C71924100 @default.
- W4386585667 hasConceptScore W4386585667C9357733 @default.
- W4386585667 hasLocation W43865856671 @default.
- W4386585667 hasOpenAccess W4386585667 @default.
- W4386585667 hasPrimaryLocation W43865856671 @default.
- W4386585667 hasRelatedWork W1980812379 @default.
- W4386585667 hasRelatedWork W2347219288 @default.
- W4386585667 hasRelatedWork W2541565311 @default.
- W4386585667 hasRelatedWork W2784019465 @default.
- W4386585667 hasRelatedWork W2787083635 @default.
- W4386585667 hasRelatedWork W2989986177 @default.
- W4386585667 hasRelatedWork W3049453136 @default.
- W4386585667 hasRelatedWork W3111247184 @default.
- W4386585667 hasRelatedWork W3145321166 @default.
- W4386585667 hasRelatedWork W569810835 @default.
- W4386585667 isParatext "false" @default.
- W4386585667 isRetracted "false" @default.
- W4386585667 workType "book-chapter" @default.