Why the study?
Does DNN improve the prediction of incident myocardial infarction compared to traditional methods using established risk factors?
Does DNN improve the prediction of incident myocardial infarction compared to traditional methods using established risk factors?
Deep neural networks do not provide substantial predictive benefit over traditional risk factor models for incident myocardial infarction when using harmonized EHR data.
Answers are grounded in this paper and cite their sources.
Traditional models suffice for MI prediction on harmonized EHR; hypothesis-generating and does not support DNN adoption.
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.
No takes yet. Share an insight, caveat, or question.
Mandair et al. (2020) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: