Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313443572> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4313443572 endingPage "173" @default.
- W4313443572 startingPage "172" @default.
- W4313443572 abstract "Atrial fibrillation (AF) is the most common heart arrhythmia. Paroxysmal AF onset forecast is a more complex task than screening AF. Published methods using the Physionet AFPDB database show excellent results, suggesting that AF episodes for is possible by implementing machine learning (ML) models using heart rate variability (HRV) parameters. Reproduce previously obtained results by published studies using the Physionet database and a larger database of unselected real-life patients. We searched the literature for all articles on paroxysmal AF episodes forecast. We analysed in depth the methodology of 3 recent studies using ML methods, to replicate their results. We screened our ECG Holter monitoring database of 11,833 Holters to find those with paroxysmal AF episodes recorded. A total of 214 Holters with paroxysmal AF were labelled. We developed two ML models (deep neural network and a random forest model) for AF forecast using 13 HRV parameters. We compared performances of published models and our models using the Physionet database and our real-life database of patients. We found 21 publications dedicated to AF episodes onset forecast. They are showing exciting results culminating in sensitivities of 98%, specificity of 95% and accuracy of 98%. Using each model description available in the publications, we could not reach the published performances on the Physionet database. In addition, our models obtained a lower sensitivity of 84% for a specificity of 49% on the Physionet database (Fig. 1). The results are similar to the sensitivity of 80.1% for a specificity of 52.8% we obtained on our larger database. ML models need to be more detailed if the reported results must be reproducible. Progress must still be made before the clinical use of algorithms that can anticipate paroxysmal AF. The use of larger databases is mandatory for this type of prediction." @default.
- W4313443572 created "2023-01-06" @default.
- W4313443572 creator A5024633888 @default.
- W4313443572 creator A5055564095 @default.
- W4313443572 creator A5058580647 @default.
- W4313443572 creator A5061552895 @default.
- W4313443572 creator A5083656042 @default.
- W4313443572 date "2023-01-01" @default.
- W4313443572 modified "2023-09-26" @default.
- W4313443572 title "Reproducibility of machine learning models for paroxysmal atrial fibrillation onset forecast" @default.
- W4313443572 doi "https://doi.org/10.1016/j.acvdsp.2022.10.327" @default.
- W4313443572 hasPublicationYear "2023" @default.
- W4313443572 type Work @default.
- W4313443572 citedByCount "0" @default.
- W4313443572 crossrefType "journal-article" @default.
- W4313443572 hasAuthorship W4313443572A5024633888 @default.
- W4313443572 hasAuthorship W4313443572A5055564095 @default.
- W4313443572 hasAuthorship W4313443572A5058580647 @default.
- W4313443572 hasAuthorship W4313443572A5061552895 @default.
- W4313443572 hasAuthorship W4313443572A5083656042 @default.
- W4313443572 hasConcept C105795698 @default.
- W4313443572 hasConcept C119857082 @default.
- W4313443572 hasConcept C126322002 @default.
- W4313443572 hasConcept C154945302 @default.
- W4313443572 hasConcept C164705383 @default.
- W4313443572 hasConcept C2779161974 @default.
- W4313443572 hasConcept C2781162219 @default.
- W4313443572 hasConcept C2985986913 @default.
- W4313443572 hasConcept C33923547 @default.
- W4313443572 hasConcept C41008148 @default.
- W4313443572 hasConcept C71924100 @default.
- W4313443572 hasConcept C77088390 @default.
- W4313443572 hasConceptScore W4313443572C105795698 @default.
- W4313443572 hasConceptScore W4313443572C119857082 @default.
- W4313443572 hasConceptScore W4313443572C126322002 @default.
- W4313443572 hasConceptScore W4313443572C154945302 @default.
- W4313443572 hasConceptScore W4313443572C164705383 @default.
- W4313443572 hasConceptScore W4313443572C2779161974 @default.
- W4313443572 hasConceptScore W4313443572C2781162219 @default.
- W4313443572 hasConceptScore W4313443572C2985986913 @default.
- W4313443572 hasConceptScore W4313443572C33923547 @default.
- W4313443572 hasConceptScore W4313443572C41008148 @default.
- W4313443572 hasConceptScore W4313443572C71924100 @default.
- W4313443572 hasConceptScore W4313443572C77088390 @default.
- W4313443572 hasIssue "1" @default.
- W4313443572 hasLocation W43134435721 @default.
- W4313443572 hasOpenAccess W4313443572 @default.
- W4313443572 hasPrimaryLocation W43134435721 @default.
- W4313443572 hasRelatedWork W1965448131 @default.
- W4313443572 hasRelatedWork W1967841144 @default.
- W4313443572 hasRelatedWork W2028558747 @default.
- W4313443572 hasRelatedWork W2032236748 @default.
- W4313443572 hasRelatedWork W2319489406 @default.
- W4313443572 hasRelatedWork W2386750603 @default.
- W4313443572 hasRelatedWork W2763816051 @default.
- W4313443572 hasRelatedWork W2804271639 @default.
- W4313443572 hasRelatedWork W2805804838 @default.
- W4313443572 hasRelatedWork W2955492843 @default.
- W4313443572 hasVolume "15" @default.
- W4313443572 isParatext "false" @default.
- W4313443572 isRetracted "false" @default.
- W4313443572 workType "article" @default.