FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200186303> ?p ?o ?g. }

• W4200186303 abstract "Abstract Background The number of publications using machine learning (ML) to predict cardiovascular outcomes and identify clusters of patients at greater risk has risen dramatically in recent years. However, research papers which use ML often fail to provide sufficient information about their algorithms to enable results to be replicated by others in the same or different datasets. Aim To test the reproducibility of results from ML algorithms given three different levels of information commonly found in publications: model type alone, a description of the model, and complete algorithm. Methods MIMIC-III is a healthcare dataset comprising detailed information from over 60,000 intensive care unit (ICU) admissions from the Beth Israel Deaconess Medical Centre between 2001 and 2012. Access is available to everyone pending approval and completion of a short training course. Using this dataset, three models for predicting all-cause in-hospital mortality were created, two from a PhD student working in ML, and one from an existing research paper which used the same dataset and provided complete model information. A second researcher (a PhD student in ML and cardiology) was given the same dataset and was tasked with reproducing their results. Initially, this second researcher was told what type of model was created in each case, followed by a brief description of the algorithms. Finally, the complete algorithms from each participant were provided. In all three scenarios, recreated models were compared to original models using Area Under the Receiver Operating Characteristic Curve (AUC). Results After excluding those younger than 18 years and events with missing or invalid entries, 21,139 ICU admissions remained from 18,094 patients between 2001 and 2012, including 2,797 in-hospital deaths. Three models were produced: two Recurrent Neural Networks (RNNs) which differed significantly in internal weights and variables, and a Boosted Tree Classifier (BTC). The AUC of the first reproduced RNN matched that of the original RNN (Figure 1), however the second RNN and the BTC could not be reproduced given model type alone. As more information was provided about these algorithms, the results from the reproduced models matched the original results more closely. Conclusions In order to create clinically useful ML tools with results that are reproducible and consistent, it is vital that researchers share enough detail about their models. Model type alone is not enough to guarantee reproducibility. Although some models can be recreated with limited information, this is not always the case, and the best results are found when the complete algorithm is shared. These findings have huge relevance when trying to apply ML in clinical practice. Funding Acknowledgement Type of funding sources: None." @default.
• W4200186303 created "2021-12-31" @default.
• W4200186303 creator A5021111671 @default.
• W4200186303 creator A5036704435 @default.
• W4200186303 creator A5039245759 @default.
• W4200186303 creator A5042761326 @default.
• W4200186303 creator A5069274246 @default.
• W4200186303 date "2021-12-01" @default.
• W4200186303 modified "2023-09-27" @default.
• W4200186303 title "Inter operator variability of machine learning researchers predicting all-cause mortality in patients admitted to intensive care unit" @default.
• W4200186303 doi "https://doi.org/10.1093/ehjdh/ztab104.3052" @default.
• W4200186303 hasPublicationYear "2021" @default.
• W4200186303 type Work @default.
• W4200186303 citedByCount "0" @default.
• W4200186303 crossrefType "journal-article" @default.
• W4200186303 hasAuthorship W4200186303A5021111671 @default.
• W4200186303 hasAuthorship W4200186303A5036704435 @default.
• W4200186303 hasAuthorship W4200186303A5039245759 @default.
• W4200186303 hasAuthorship W4200186303A5042761326 @default.
• W4200186303 hasAuthorship W4200186303A5069274246 @default.
• W4200186303 hasBestOaLocation W42001863031 @default.
• W4200186303 hasConcept C119857082 @default.
• W4200186303 hasConcept C122637931 @default.
• W4200186303 hasConcept C126322002 @default.
• W4200186303 hasConcept C145420912 @default.
• W4200186303 hasConcept C154945302 @default.
• W4200186303 hasConcept C160735492 @default.
• W4200186303 hasConcept C162324750 @default.
• W4200186303 hasConcept C177713679 @default.
• W4200186303 hasConcept C194828623 @default.
• W4200186303 hasConcept C2776376669 @default.
• W4200186303 hasConcept C33923547 @default.
• W4200186303 hasConcept C41008148 @default.
• W4200186303 hasConcept C50522688 @default.
• W4200186303 hasConcept C58471807 @default.
• W4200186303 hasConcept C71924100 @default.
• W4200186303 hasConceptScore W4200186303C119857082 @default.
• W4200186303 hasConceptScore W4200186303C122637931 @default.
• W4200186303 hasConceptScore W4200186303C126322002 @default.
• W4200186303 hasConceptScore W4200186303C145420912 @default.
• W4200186303 hasConceptScore W4200186303C154945302 @default.
• W4200186303 hasConceptScore W4200186303C160735492 @default.
• W4200186303 hasConceptScore W4200186303C162324750 @default.
• W4200186303 hasConceptScore W4200186303C177713679 @default.
• W4200186303 hasConceptScore W4200186303C194828623 @default.
• W4200186303 hasConceptScore W4200186303C2776376669 @default.
• W4200186303 hasConceptScore W4200186303C33923547 @default.
• W4200186303 hasConceptScore W4200186303C41008148 @default.
• W4200186303 hasConceptScore W4200186303C50522688 @default.
• W4200186303 hasConceptScore W4200186303C58471807 @default.
• W4200186303 hasConceptScore W4200186303C71924100 @default.
• W4200186303 hasIssue "4" @default.
• W4200186303 hasLocation W42001863031 @default.
• W4200186303 hasLocation W42001863032 @default.
• W4200186303 hasOpenAccess W4200186303 @default.
• W4200186303 hasPrimaryLocation W42001863031 @default.
• W4200186303 hasRelatedWork W2023015132 @default.
• W4200186303 hasRelatedWork W2057472247 @default.
• W4200186303 hasRelatedWork W2076293151 @default.
• W4200186303 hasRelatedWork W2150979970 @default.
• W4200186303 hasRelatedWork W3155720539 @default.
• W4200186303 hasRelatedWork W3174196512 @default.
• W4200186303 hasRelatedWork W3204711385 @default.
• W4200186303 hasRelatedWork W4205639172 @default.
• W4200186303 hasRelatedWork W4287313070 @default.
• W4200186303 hasRelatedWork W4365143256 @default.
• W4200186303 hasVolume "2" @default.
• W4200186303 isParatext "false" @default.
• W4200186303 isRetracted "false" @default.
• W4200186303 workType "article" @default.