Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285483643> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4285483643 abstract "Objective: Machine learning techniques have been used extensively for 12-lead electrocardiogram (ECG) analysis. For physiological time series, deep learning (DL) superiority to feature engineering (FE) approaches based on domain knowledge is still an open question. Moreover, it remains unclear whether combining DL with FE may improve performance. Methods: We considered three tasks intending to address these research gaps: cardiac arrhythmia diagnosis (multiclass-multilabel classification), atrial fibrillation risk prediction (binary classification), and age estimation (regression). We used an overall dataset of 2.3M 12-lead ECG recordings to train the following models for each task: i) a random forest taking the FE as input was trained as a classical machine learning approach; ii) an end-to-end DL model; and iii) a merged model of FE+DL. Results: FE yielded comparable results to DL while necessitating significantly less data for the two classification tasks and it was outperformed by DL for the regression task. For all tasks, merging FE with DL did not improve performance over DL alone. Conclusion: We found that for traditional 12-lead ECG based diagnosis tasks DL did not yield a meaningful improvement over FE, while it improved significantly the nontraditional regression task. We also found that combining FE with DL did not improve over DL alone which suggests that the FE were redundant with the features learned by DL. Significance: Our findings provides important recommendations on what machine learning strategy and data regime to chose with respect to the task at hand for the development of new machine learning models based on the 12-lead ECG." @default.
- W4285483643 created "2022-07-15" @default.
- W4285483643 creator A5001486389 @default.
- W4285483643 creator A5038018651 @default.
- W4285483643 creator A5055668668 @default.
- W4285483643 creator A5061924893 @default.
- W4285483643 creator A5091624431 @default.
- W4285483643 date "2022-07-13" @default.
- W4285483643 modified "2023-09-26" @default.
- W4285483643 title "On Merging Feature Engineering and Deep Learning for Diagnosis, Risk-Prediction and Age Estimation Based on the 12-Lead ECG" @default.
- W4285483643 doi "https://doi.org/10.48550/arxiv.2207.06096" @default.
- W4285483643 hasPublicationYear "2022" @default.
- W4285483643 type Work @default.
- W4285483643 citedByCount "1" @default.
- W4285483643 countsByYear W42854836432023 @default.
- W4285483643 crossrefType "posted-content" @default.
- W4285483643 hasAuthorship W4285483643A5001486389 @default.
- W4285483643 hasAuthorship W4285483643A5038018651 @default.
- W4285483643 hasAuthorship W4285483643A5055668668 @default.
- W4285483643 hasAuthorship W4285483643A5061924893 @default.
- W4285483643 hasAuthorship W4285483643A5091624431 @default.
- W4285483643 hasBestOaLocation W42854836431 @default.
- W4285483643 hasConcept C105795698 @default.
- W4285483643 hasConcept C108583219 @default.
- W4285483643 hasConcept C114793014 @default.
- W4285483643 hasConcept C119857082 @default.
- W4285483643 hasConcept C12267149 @default.
- W4285483643 hasConcept C127313418 @default.
- W4285483643 hasConcept C127413603 @default.
- W4285483643 hasConcept C138885662 @default.
- W4285483643 hasConcept C154945302 @default.
- W4285483643 hasConcept C169258074 @default.
- W4285483643 hasConcept C201995342 @default.
- W4285483643 hasConcept C2776401178 @default.
- W4285483643 hasConcept C2777093003 @default.
- W4285483643 hasConcept C2778827112 @default.
- W4285483643 hasConcept C2780451532 @default.
- W4285483643 hasConcept C28006648 @default.
- W4285483643 hasConcept C33923547 @default.
- W4285483643 hasConcept C41008148 @default.
- W4285483643 hasConcept C41895202 @default.
- W4285483643 hasConcept C66905080 @default.
- W4285483643 hasConcept C83546350 @default.
- W4285483643 hasConceptScore W4285483643C105795698 @default.
- W4285483643 hasConceptScore W4285483643C108583219 @default.
- W4285483643 hasConceptScore W4285483643C114793014 @default.
- W4285483643 hasConceptScore W4285483643C119857082 @default.
- W4285483643 hasConceptScore W4285483643C12267149 @default.
- W4285483643 hasConceptScore W4285483643C127313418 @default.
- W4285483643 hasConceptScore W4285483643C127413603 @default.
- W4285483643 hasConceptScore W4285483643C138885662 @default.
- W4285483643 hasConceptScore W4285483643C154945302 @default.
- W4285483643 hasConceptScore W4285483643C169258074 @default.
- W4285483643 hasConceptScore W4285483643C201995342 @default.
- W4285483643 hasConceptScore W4285483643C2776401178 @default.
- W4285483643 hasConceptScore W4285483643C2777093003 @default.
- W4285483643 hasConceptScore W4285483643C2778827112 @default.
- W4285483643 hasConceptScore W4285483643C2780451532 @default.
- W4285483643 hasConceptScore W4285483643C28006648 @default.
- W4285483643 hasConceptScore W4285483643C33923547 @default.
- W4285483643 hasConceptScore W4285483643C41008148 @default.
- W4285483643 hasConceptScore W4285483643C41895202 @default.
- W4285483643 hasConceptScore W4285483643C66905080 @default.
- W4285483643 hasConceptScore W4285483643C83546350 @default.
- W4285483643 hasLocation W42854836431 @default.
- W4285483643 hasOpenAccess W4285483643 @default.
- W4285483643 hasPrimaryLocation W42854836431 @default.
- W4285483643 hasRelatedWork W2908875379 @default.
- W4285483643 hasRelatedWork W2968586400 @default.
- W4285483643 hasRelatedWork W3004897296 @default.
- W4285483643 hasRelatedWork W3017600792 @default.
- W4285483643 hasRelatedWork W3136979370 @default.
- W4285483643 hasRelatedWork W3196362139 @default.
- W4285483643 hasRelatedWork W4281986673 @default.
- W4285483643 hasRelatedWork W4287813963 @default.
- W4285483643 hasRelatedWork W4306175410 @default.
- W4285483643 hasRelatedWork W4311106074 @default.
- W4285483643 isParatext "false" @default.
- W4285483643 isRetracted "false" @default.
- W4285483643 workType "article" @default.