Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366829067> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4366829067 abstract "Abstract Background The use of machine learning is becoming increasingly popular in many disciplines, but there is still an implementation gap of machine learning models in clinical settings. Lack of trust in models is one of the issues that need to be addressed in an effort to close this gap. No models are perfect, and it is crucial to know in which use cases we can trust a model and for which cases it is less reliable. Methods Four different algorithms are trained on the eICU Collaborative Research Database using similar features as the APACHE IV severity-of-disease scoring system to predict hospital mortality in the ICU. The training and testing procedure is repeated 100 times on the same dataset to investigate whether predictions for single patients change with small changes in the models. Features are then analysed separately to investigate potential differences between patients consistently classified correctly and incorrectly. Results A total of 34 056 patients (58.4%) are classified as true negative, 6 527 patients (11.3%) as false positive, 3 984 patients (6.8%) as true positive, and 546 patients (0.9%) as false negatives. The remaining 13 108 patients (22.5%) are inconsistently classified across models and rounds. Histograms and distributions of feature values are compared visually to investigate differences between groups. Conclusions It is impossible to distinguish the groups using single features alone. Considering a combination of features, the difference between the groups is clearer. Incorrectly classified patients have features more similar to patients with the same prediction rather than the same outcome." @default.
- W4366829067 created "2023-04-25" @default.
- W4366829067 creator A5006361693 @default.
- W4366829067 creator A5029874932 @default.
- W4366829067 creator A5042405395 @default.
- W4366829067 creator A5044813487 @default.
- W4366829067 date "2023-04-24" @default.
- W4366829067 modified "2023-10-14" @default.
- W4366829067 title "Comparison of correctly and incorrectly classified patients for in-hospital mortality prediction in the intensive care unit" @default.
- W4366829067 cites W1657774248 @default.
- W4366829067 cites W2000566182 @default.
- W4366829067 cites W2011301426 @default.
- W4366829067 cites W2152575748 @default.
- W4366829067 cites W2487898712 @default.
- W4366829067 cites W2512395362 @default.
- W4366829067 cites W2789894922 @default.
- W4366829067 cites W2891400669 @default.
- W4366829067 cites W2943845219 @default.
- W4366829067 cites W2969097171 @default.
- W4366829067 cites W2982580298 @default.
- W4366829067 cites W2994958466 @default.
- W4366829067 cites W3043673199 @default.
- W4366829067 cites W3102476541 @default.
- W4366829067 cites W3109650690 @default.
- W4366829067 cites W3158097511 @default.
- W4366829067 cites W3170495160 @default.
- W4366829067 cites W4214520407 @default.
- W4366829067 cites W4220668093 @default.
- W4366829067 cites W4223923854 @default.
- W4366829067 cites W4248437541 @default.
- W4366829067 cites W4282976375 @default.
- W4366829067 doi "https://doi.org/10.1186/s12874-023-01921-9" @default.
- W4366829067 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37095430" @default.
- W4366829067 hasPublicationYear "2023" @default.
- W4366829067 type Work @default.
- W4366829067 citedByCount "0" @default.
- W4366829067 crossrefType "journal-article" @default.
- W4366829067 hasAuthorship W4366829067A5006361693 @default.
- W4366829067 hasAuthorship W4366829067A5029874932 @default.
- W4366829067 hasAuthorship W4366829067A5042405395 @default.
- W4366829067 hasAuthorship W4366829067A5044813487 @default.
- W4366829067 hasBestOaLocation W43668290671 @default.
- W4366829067 hasConcept C119857082 @default.
- W4366829067 hasConcept C138885662 @default.
- W4366829067 hasConcept C154945302 @default.
- W4366829067 hasConcept C177713679 @default.
- W4366829067 hasConcept C2776376669 @default.
- W4366829067 hasConcept C2776401178 @default.
- W4366829067 hasConcept C41008148 @default.
- W4366829067 hasConcept C41895202 @default.
- W4366829067 hasConcept C45804977 @default.
- W4366829067 hasConcept C71924100 @default.
- W4366829067 hasConceptScore W4366829067C119857082 @default.
- W4366829067 hasConceptScore W4366829067C138885662 @default.
- W4366829067 hasConceptScore W4366829067C154945302 @default.
- W4366829067 hasConceptScore W4366829067C177713679 @default.
- W4366829067 hasConceptScore W4366829067C2776376669 @default.
- W4366829067 hasConceptScore W4366829067C2776401178 @default.
- W4366829067 hasConceptScore W4366829067C41008148 @default.
- W4366829067 hasConceptScore W4366829067C41895202 @default.
- W4366829067 hasConceptScore W4366829067C45804977 @default.
- W4366829067 hasConceptScore W4366829067C71924100 @default.
- W4366829067 hasFunder F4320322752 @default.
- W4366829067 hasIssue "1" @default.
- W4366829067 hasLocation W43668290671 @default.
- W4366829067 hasLocation W43668290672 @default.
- W4366829067 hasLocation W43668290673 @default.
- W4366829067 hasOpenAccess W4366829067 @default.
- W4366829067 hasPrimaryLocation W43668290671 @default.
- W4366829067 hasRelatedWork W2748952813 @default.
- W4366829067 hasRelatedWork W2899084033 @default.
- W4366829067 hasRelatedWork W2961085424 @default.
- W4366829067 hasRelatedWork W3046775127 @default.
- W4366829067 hasRelatedWork W3160244858 @default.
- W4366829067 hasRelatedWork W4285260836 @default.
- W4366829067 hasRelatedWork W4286629047 @default.
- W4366829067 hasRelatedWork W4306321456 @default.
- W4366829067 hasRelatedWork W4306674287 @default.
- W4366829067 hasRelatedWork W4224009465 @default.
- W4366829067 hasVolume "23" @default.
- W4366829067 isParatext "false" @default.
- W4366829067 isRetracted "false" @default.
- W4366829067 workType "article" @default.