Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach
Simple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormaliti...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9834 |
| _version_ | 1797379354371555328 |
|---|---|
| author | Takeru Shiraga Hisaki Makimoto Benita Kohlmann Christofori-Eleni Magnisali Yoshie Imai Yusuke Itani Asuka Makimoto Fabian Schölzel Alexandru Bejinariu Malte Kelm Obaida Rana |
| author_facet | Takeru Shiraga Hisaki Makimoto Benita Kohlmann Christofori-Eleni Magnisali Yoshie Imai Yusuke Itani Asuka Makimoto Fabian Schölzel Alexandru Bejinariu Malte Kelm Obaida Rana |
| author_sort | Takeru Shiraga |
| collection | DOAJ |
| description | Simple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormalities and ventricular dysfunction. Data from auscultation at three distinct locations and 12-lead ECGs were collected from 1052 patients undergoing echocardiography. An independent cohort of 103 patients was used for clinical validation. These patients were screened for severe aortic stenosis (AS), severe mitral regurgitation (MR), and left ventricular dysfunction (LVD) with ejection fractions ≤ 40%. Optimal neural networks were identified by a fourfold cross-validation training process using heart sounds and various ECG leads, and their outputs were combined using a stacking technique. This composite sensor model had high diagnostic efficiency (area under the receiver operating characteristic curve (AUC) values: AS, 0.93; MR, 0.80; LVD, 0.75). Notably, the contribution of individual sensors to disease detection was found to be disease-specific, underscoring the synergistic potential of the sensor fusion approach. Thus, machine learning models that integrate auscultation and ECG can efficiently detect conditions typically diagnosed via imaging. Moreover, this study highlights the potential of multimodal artificial intelligence applications. |
| first_indexed | 2024-03-08T20:22:58Z |
| format | Article |
| id | doaj.art-57e5f3d5049d4ee0b81078b0cb5c07f2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:22:58Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-57e5f3d5049d4ee0b81078b0cb5c07f22023-12-22T14:40:59ZengMDPI AGSensors1424-82202023-12-012324983410.3390/s23249834Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI ApproachTakeru Shiraga0Hisaki Makimoto1Benita Kohlmann2Christofori-Eleni Magnisali3Yoshie Imai4Yusuke Itani5Asuka Makimoto6Fabian Schölzel7Alexandru Bejinariu8Malte Kelm9Obaida Rana10Mitsubishi Electric Inc., Kamakura 247-0056, JapanDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyMitsubishi Electric Inc., Kamakura 247-0056, JapanMitsubishi Electric Inc., Kamakura 247-0056, JapanDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanyDivision of Cardiology, Pulmonology and Vascular Medicine, Medical Faculty, Heinrich-Heine-University Düsseldorf, 40225 Düsseldorf, GermanySimple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormalities and ventricular dysfunction. Data from auscultation at three distinct locations and 12-lead ECGs were collected from 1052 patients undergoing echocardiography. An independent cohort of 103 patients was used for clinical validation. These patients were screened for severe aortic stenosis (AS), severe mitral regurgitation (MR), and left ventricular dysfunction (LVD) with ejection fractions ≤ 40%. Optimal neural networks were identified by a fourfold cross-validation training process using heart sounds and various ECG leads, and their outputs were combined using a stacking technique. This composite sensor model had high diagnostic efficiency (area under the receiver operating characteristic curve (AUC) values: AS, 0.93; MR, 0.80; LVD, 0.75). Notably, the contribution of individual sensors to disease detection was found to be disease-specific, underscoring the synergistic potential of the sensor fusion approach. Thus, machine learning models that integrate auscultation and ECG can efficiently detect conditions typically diagnosed via imaging. Moreover, this study highlights the potential of multimodal artificial intelligence applications.https://www.mdpi.com/1424-8220/23/24/9834auscultationelectrocardiographyvalvular diseaseheart failuremultimodal artificial intelligence |
| spellingShingle | Takeru Shiraga Hisaki Makimoto Benita Kohlmann Christofori-Eleni Magnisali Yoshie Imai Yusuke Itani Asuka Makimoto Fabian Schölzel Alexandru Bejinariu Malte Kelm Obaida Rana Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach Sensors auscultation electrocardiography valvular disease heart failure multimodal artificial intelligence |
| title | Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach |
| title_full | Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach |
| title_fullStr | Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach |
| title_full_unstemmed | Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach |
| title_short | Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach |
| title_sort | improving valvular pathologies and ventricular dysfunction diagnostic efficiency using combined auscultation and electrocardiography data a multimodal ai approach |
| topic | auscultation electrocardiography valvular disease heart failure multimodal artificial intelligence |
| url | https://www.mdpi.com/1424-8220/23/24/9834 |
| work_keys_str_mv | AT takerushiraga improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT hisakimakimoto improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT benitakohlmann improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT christoforielenimagnisali improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT yoshieimai improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT yusukeitani improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT asukamakimoto improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT fabianscholzel improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT alexandrubejinariu improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT maltekelm improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach AT obaidarana improvingvalvularpathologiesandventriculardysfunctiondiagnosticefficiencyusingcombinedauscultationandelectrocardiographydataamultimodalaiapproach |