Atrial fibrillation prediction by combining ECG markers and CMR radiomics
Abstract Atrial fibrillation (AF) is the most common cardiac arrhythmia. It is associated with a higher risk of important adverse health outcomes such as stroke and death. AF is linked to distinct electro-anatomic alterations. The main tool for AF diagnosis is the Electrocardiogram (ECG). However, a...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-21663-w |
| _version_ | 1828197959228981248 |
|---|---|
| author | Esmeralda Ruiz Pujadas Zahra Raisi-Estabragh Liliana Szabo Cristian Izquierdo Morcillo Víctor M. Campello Carlos Martin-Isla Hajnalka Vago Bela Merkely Nicholas C. Harvey Steffen E. Petersen Karim Lekadir |
| author_facet | Esmeralda Ruiz Pujadas Zahra Raisi-Estabragh Liliana Szabo Cristian Izquierdo Morcillo Víctor M. Campello Carlos Martin-Isla Hajnalka Vago Bela Merkely Nicholas C. Harvey Steffen E. Petersen Karim Lekadir |
| author_sort | Esmeralda Ruiz Pujadas |
| collection | DOAJ |
| description | Abstract Atrial fibrillation (AF) is the most common cardiac arrhythmia. It is associated with a higher risk of important adverse health outcomes such as stroke and death. AF is linked to distinct electro-anatomic alterations. The main tool for AF diagnosis is the Electrocardiogram (ECG). However, an ECG recorded at a single time point may not detect individuals with paroxysmal AF. In this study, we developed machine learning models for discrimination of prevalent AF using a combination of image-derived radiomics phenotypes and ECG features. Thus, we characterize the phenotypes of prevalent AF in terms of ECG and imaging alterations. Moreover, we explore sex-differential remodelling by building sex-specific models. Our integrative model including radiomics and ECG together resulted in a better performance than ECG alone, particularly in women. ECG had a lower performance in women than men (AUC: 0.77 vs 0.88, p < 0.05) but adding radiomics features, the accuracy of the model was able to improve significantly. The sensitivity also increased considerably in women by adding the radiomics (0.68 vs 0.79, p < 0.05) having a higher detection of AF events. Our findings provide novel insights into AF-related electro-anatomic remodelling and its variations by sex. The integrative radiomics-ECG model also presents a potential novel approach for earlier detection of AF. |
| first_indexed | 2024-04-12T10:29:18Z |
| format | Article |
| id | doaj.art-4ce0f2240d724f1681c2d270939b12e5 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T10:29:18Z |
| publishDate | 2022-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-4ce0f2240d724f1681c2d270939b12e52022-12-22T03:36:53ZengNature PortfolioScientific Reports2045-23222022-11-0112111510.1038/s41598-022-21663-wAtrial fibrillation prediction by combining ECG markers and CMR radiomicsEsmeralda Ruiz Pujadas0Zahra Raisi-Estabragh1Liliana Szabo2Cristian Izquierdo Morcillo3Víctor M. Campello4Carlos Martin-Isla5Hajnalka Vago6Bela Merkely7Nicholas C. Harvey8Steffen E. Petersen9Karim Lekadir10Artificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de BarcelonaWilliam Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of LondonWilliam Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of LondonArtificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de BarcelonaArtificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de BarcelonaArtificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de BarcelonaSemmelweis University Heart and Vascular CenterSemmelweis University Heart and Vascular CenterMRC Lifecourse Epidemiology Centre, University of SouthamptonWilliam Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of LondonArtificial Intelligence in Medicine Lab (BCN-AIM), Departament de Matemàtiques i Informàtica, Universitat de BarcelonaAbstract Atrial fibrillation (AF) is the most common cardiac arrhythmia. It is associated with a higher risk of important adverse health outcomes such as stroke and death. AF is linked to distinct electro-anatomic alterations. The main tool for AF diagnosis is the Electrocardiogram (ECG). However, an ECG recorded at a single time point may not detect individuals with paroxysmal AF. In this study, we developed machine learning models for discrimination of prevalent AF using a combination of image-derived radiomics phenotypes and ECG features. Thus, we characterize the phenotypes of prevalent AF in terms of ECG and imaging alterations. Moreover, we explore sex-differential remodelling by building sex-specific models. Our integrative model including radiomics and ECG together resulted in a better performance than ECG alone, particularly in women. ECG had a lower performance in women than men (AUC: 0.77 vs 0.88, p < 0.05) but adding radiomics features, the accuracy of the model was able to improve significantly. The sensitivity also increased considerably in women by adding the radiomics (0.68 vs 0.79, p < 0.05) having a higher detection of AF events. Our findings provide novel insights into AF-related electro-anatomic remodelling and its variations by sex. The integrative radiomics-ECG model also presents a potential novel approach for earlier detection of AF.https://doi.org/10.1038/s41598-022-21663-w |
| spellingShingle | Esmeralda Ruiz Pujadas Zahra Raisi-Estabragh Liliana Szabo Cristian Izquierdo Morcillo Víctor M. Campello Carlos Martin-Isla Hajnalka Vago Bela Merkely Nicholas C. Harvey Steffen E. Petersen Karim Lekadir Atrial fibrillation prediction by combining ECG markers and CMR radiomics Scientific Reports |
| title | Atrial fibrillation prediction by combining ECG markers and CMR radiomics |
| title_full | Atrial fibrillation prediction by combining ECG markers and CMR radiomics |
| title_fullStr | Atrial fibrillation prediction by combining ECG markers and CMR radiomics |
| title_full_unstemmed | Atrial fibrillation prediction by combining ECG markers and CMR radiomics |
| title_short | Atrial fibrillation prediction by combining ECG markers and CMR radiomics |
| title_sort | atrial fibrillation prediction by combining ecg markers and cmr radiomics |
| url | https://doi.org/10.1038/s41598-022-21663-w |
| work_keys_str_mv | AT esmeraldaruizpujadas atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT zahraraisiestabragh atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT lilianaszabo atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT cristianizquierdomorcillo atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT victormcampello atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT carlosmartinisla atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT hajnalkavago atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT belamerkely atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT nicholascharvey atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT steffenepetersen atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics AT karimlekadir atrialfibrillationpredictionbycombiningecgmarkersandcmrradiomics |