Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090402404> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3090402404 abstract "Abstract Background With cardiovascular disease increasing, substantial research has focused on the development of prediction tools. We compare deep learning and machine learning models to a baseline logistic regression using only ‘known’ risk factors in predicting incident myocardial infarction (MI) from harmonized EHR data. Methods Large-scale case-control study with outcome of 6-month incident MI, conducted using the top 800, from an initial 52 k procedures, diagnoses, and medications within the UCHealth system, harmonized to the Observational Medical Outcomes Partnership common data model, performed on 2.27 million patients. We compared several over- and under- sampling techniques to address the imbalance in the dataset. We compared regularized logistics regression, random forest, boosted gradient machines, and shallow and deep neural networks. A baseline model for comparison was a logistic regression using a limited set of ‘known’ risk factors for MI. Hyper-parameters were identified using 10-fold cross-validation. Results Twenty thousand Five hundred and ninety-one patients were diagnosed with MI compared with 2.25 million who did not. A deep neural network with random undersampling provided superior classification compared with other methods. However, the benefit of the deep neural network was only moderate, showing an F1 Score of 0.092 and AUC of 0.835, compared to a logistic regression model using only ‘known’ risk factors. Calibration for all models was poor despite adequate discrimination, due to overfitting from low frequency of the event of interest. Conclusions Our study suggests that DNN may not offer substantial benefit when trained on harmonized data, compared to traditional methods using established risk factors for MI." @default.
- W3090402404 created "2020-10-08" @default.
- W3090402404 creator A5001231969 @default.
- W3090402404 creator A5013685752 @default.
- W3090402404 creator A5044041882 @default.
- W3090402404 creator A5046846922 @default.
- W3090402404 creator A5085940278 @default.
- W3090402404 date "2020-10-02" @default.
- W3090402404 modified "2023-10-01" @default.
- W3090402404 title "Prediction of incident myocardial infarction using machine learning applied to harmonized electronic health record data" @default.
- W3090402404 cites W1547859334 @default.
- W3090402404 cites W1714171183 @default.
- W3090402404 cites W1901045397 @default.
- W3090402404 cites W1926248049 @default.
- W3090402404 cites W1976153761 @default.
- W3090402404 cites W1991181258 @default.
- W3090402404 cites W2009661919 @default.
- W3090402404 cites W2010228636 @default.
- W3090402404 cites W2012942264 @default.
- W3090402404 cites W2085657320 @default.
- W3090402404 cites W2114323543 @default.
- W3090402404 cites W2140302476 @default.
- W3090402404 cites W2254984092 @default.
- W3090402404 cites W2493683088 @default.
- W3090402404 cites W2574978968 @default.
- W3090402404 cites W2586415694 @default.
- W3090402404 cites W2733294365 @default.
- W3090402404 cites W2750902029 @default.
- W3090402404 cites W2764175852 @default.
- W3090402404 cites W2797436530 @default.
- W3090402404 cites W2803982643 @default.
- W3090402404 cites W2887392710 @default.
- W3090402404 cites W2909987842 @default.
- W3090402404 cites W2913851468 @default.
- W3090402404 cites W2916823148 @default.
- W3090402404 cites W2919115771 @default.
- W3090402404 cites W2939631812 @default.
- W3090402404 cites W2946050503 @default.
- W3090402404 cites W2949495270 @default.
- W3090402404 cites W2973865313 @default.
- W3090402404 cites W2977400776 @default.
- W3090402404 doi "https://doi.org/10.1186/s12911-020-01268-x" @default.
- W3090402404 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7532582" @default.
- W3090402404 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33008368" @default.
- W3090402404 hasPublicationYear "2020" @default.
- W3090402404 type Work @default.
- W3090402404 sameAs 3090402404 @default.
- W3090402404 citedByCount "11" @default.
- W3090402404 countsByYear W30904024042021 @default.
- W3090402404 countsByYear W30904024042022 @default.
- W3090402404 countsByYear W30904024042023 @default.
- W3090402404 crossrefType "journal-article" @default.
- W3090402404 hasAuthorship W3090402404A5001231969 @default.
- W3090402404 hasAuthorship W3090402404A5013685752 @default.
- W3090402404 hasAuthorship W3090402404A5044041882 @default.
- W3090402404 hasAuthorship W3090402404A5046846922 @default.
- W3090402404 hasAuthorship W3090402404A5085940278 @default.
- W3090402404 hasBestOaLocation W30904024041 @default.
- W3090402404 hasConcept C108583219 @default.
- W3090402404 hasConcept C119857082 @default.
- W3090402404 hasConcept C151956035 @default.
- W3090402404 hasConcept C154945302 @default.
- W3090402404 hasConcept C169258074 @default.
- W3090402404 hasConcept C22019652 @default.
- W3090402404 hasConcept C41008148 @default.
- W3090402404 hasConcept C50644808 @default.
- W3090402404 hasConcept C71924100 @default.
- W3090402404 hasConceptScore W3090402404C108583219 @default.
- W3090402404 hasConceptScore W3090402404C119857082 @default.
- W3090402404 hasConceptScore W3090402404C151956035 @default.
- W3090402404 hasConceptScore W3090402404C154945302 @default.
- W3090402404 hasConceptScore W3090402404C169258074 @default.
- W3090402404 hasConceptScore W3090402404C22019652 @default.
- W3090402404 hasConceptScore W3090402404C41008148 @default.
- W3090402404 hasConceptScore W3090402404C50644808 @default.
- W3090402404 hasConceptScore W3090402404C71924100 @default.
- W3090402404 hasFunder F4320337338 @default.
- W3090402404 hasIssue "1" @default.
- W3090402404 hasLocation W30904024041 @default.
- W3090402404 hasLocation W30904024042 @default.
- W3090402404 hasOpenAccess W3090402404 @default.
- W3090402404 hasPrimaryLocation W30904024041 @default.
- W3090402404 hasRelatedWork W2121394390 @default.
- W3090402404 hasRelatedWork W2968586400 @default.
- W3090402404 hasRelatedWork W3099765033 @default.
- W3090402404 hasRelatedWork W3211546796 @default.
- W3090402404 hasRelatedWork W4223564025 @default.
- W3090402404 hasRelatedWork W4226246648 @default.
- W3090402404 hasRelatedWork W4281616679 @default.
- W3090402404 hasRelatedWork W4322727400 @default.
- W3090402404 hasRelatedWork W4361732492 @default.
- W3090402404 hasRelatedWork W4362499066 @default.
- W3090402404 hasVolume "20" @default.
- W3090402404 isParatext "false" @default.
- W3090402404 isRetracted "false" @default.
- W3090402404 magId "3090402404" @default.
- W3090402404 workType "article" @default.