1
|
Pieszko K, Hiczkiewicz J, Łojewska K, Uziębło-Życzkowska B, Krzesiński P, Gawałko M, Budnik M, Starzyk K, Wożakowska-Kapłon B, Daniłowicz-Szymanowicz L, Kaufmann D, Wójcik M, Błaszczyk R, Mizia-Stec K, Wybraniec M, Kosmalska K, Fijałkowski M, Szymańska A, Dłużniewski M, Kucio M, Haberka M, Kupczyńska K, Michalski B, Tomaszuk-Kazberuk A, Wilk-Śledziewska K, Wachnicka-Truty R, Koziński M, Kwieciński J, Wolny R, Kowalik E, Kolasa I, Jurek A, Budzianowski J, Burchardt P, Kapłon-Cieślicka A, Slomka PJ. Artificial intelligence in detecting left atrial appendage thrombus by transthoracic echocardiography and clinical features: the Left Atrial Thrombus on Transoesophageal Echocardiography (LATTEE) registry. Eur Heart J 2024; 45:32-41. [PMID: 37453044 PMCID: PMC10757867 DOI: 10.1093/eurheartj/ehad431] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/14/2022] [Revised: 05/03/2023] [Accepted: 06/22/2023] [Indexed: 07/18/2023] Open
Abstract
AIMS Transoesophageal echocardiography (TOE) is often performed before catheter ablation or cardioversion to rule out the presence of left atrial appendage thrombus (LAT) in patients on chronic oral anticoagulation (OAC), despite associated discomfort. A machine learning model [LAT-artificial intelligence (AI)] was developed to predict the presence of LAT based on clinical and transthoracic echocardiography (TTE) features. METHODS AND RESULTS Data from a 13-site prospective registry of patients who underwent TOE before cardioversion or catheter ablation were used. LAT-AI was trained to predict LAT using data from 12 sites (n = 2827) and tested externally in patients on chronic OAC from two sites (n = 1284). Areas under the receiver operating characteristic curve (AUC) of LAT-AI were compared with that of left ventricular ejection fraction (LVEF) and CHA2DS2-VASc score. A decision threshold allowing for a 99% negative predictive value was defined in the development cohort. A protocol where TOE in patients on chronic OAC is performed depending on the LAT-AI score was validated in the external cohort. In the external testing cohort, LAT was found in 5.5% of patients. LAT-AI achieved an AUC of 0.85 [95% confidence interval (CI): 0.82-0.89], outperforming LVEF (0.81, 95% CI 0.76-0.86, P < .0001) and CHA2DS2-VASc score (0.69, 95% CI: 0.63-0.7, P < .0001) in the entire external cohort. Based on the proposed protocol, 40% of patients on chronic OAC from the external cohort would safely avoid TOE. CONCLUSION LAT-AI allows accurate prediction of LAT. A LAT-AI-based protocol could be used to guide the decision to perform TOE despite chronic OAC.
Collapse
Affiliation(s)
- Konrad Pieszko
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Interventional Cardiology and Cardiac Surgery, University of Zielona Gora, Collegium Medicum, Zielona Gora, Poland
- WSSP ZOZ Nowa Sol, Nowa Sol, Poland
| | - Jarosław Hiczkiewicz
- Department of Interventional Cardiology and Cardiac Surgery, University of Zielona Gora, Collegium Medicum, Zielona Gora, Poland
- WSSP ZOZ Nowa Sol, Nowa Sol, Poland
| | | | - Beata Uziębło-Życzkowska
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Cardiology and Internal Diseases, Military Institute of Medicine, Warsaw, Poland
| | - Paweł Krzesiński
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Cardiology and Internal Diseases, Military Institute of Medicine, Warsaw, Poland
| | - Monika Gawałko
- ‘Club 30’, Polish Cardiac Society, Poland
- First Department of Cardiology, Medical University of Warsaw, Warsaw, Poland
- Department of Cardiology, Maastricht University Medical Centre and Cardiovascular Research Institute Maastricht, Maastricht, The Netherlands
- Institute of Pharmacology, West German Heart and Vascular Centre, University Duisburg-Essen, Essen, Germany
| | - Monika Budnik
- ‘Club 30’, Polish Cardiac Society, Poland
- First Department of Cardiology, Medical University of Warsaw, Warsaw, Poland
| | - Katarzyna Starzyk
- 1st Clinic of Cardiology and Electrotherapy, Swietokrzyskie Cardiology Centre, Kielce, Poland
| | - Beata Wożakowska-Kapłon
- 1st Clinic of Cardiology and Electrotherapy, Swietokrzyskie Cardiology Centre, Kielce, Poland
| | | | - Damian Kaufmann
- Department of Cardiology and Electrotherapy, Medical University of Gdansk, Gdansk, Poland
| | - Maciej Wójcik
- Department of Cardiology, Medical University of Lublin, Lublin, Poland
| | - Robert Błaszczyk
- Department of Cardiology, Medical University of Lublin, Lublin, Poland
| | - Katarzyna Mizia-Stec
- 1st Department of Cardiology, School of Medicine in Katowice, Medical University of Silesia, Katowice, Poland
| | - Maciej Wybraniec
- 1st Department of Cardiology, School of Medicine in Katowice, Medical University of Silesia, Katowice, Poland
| | | | | | - Anna Szymańska
- Department of Heart Diseases, Postgraduate Medical School, Warsaw, Poland
| | | | - Michał Kucio
- Department of Cardiology, School of Health Sciences, Medical University of Silesia, Katowice, Poland
| | - Maciej Haberka
- Department of Cardiology, School of Health Sciences, Medical University of Silesia, Katowice, Poland
| | | | - Błażej Michalski
- Department of Cardiology, Medical University of Lodz, Lodz, Poland
| | | | | | - Renata Wachnicka-Truty
- Department of Cardiology and Internal Medicine, Medical University of Gdansk, Gdynia, Poland
| | - Marek Koziński
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Cardiology and Internal Medicine, Medical University of Gdansk, Gdynia, Poland
| | - Jacek Kwieciński
- Department of Interventional Cardiology and Angiology, Institute of Cardiology, Warsaw, Poland
| | - Rafał Wolny
- Department of Interventional Cardiology and Angiology, Institute of Cardiology, Warsaw, Poland
| | - Ewa Kowalik
- Department of Congenital Heart Diseases, National Institute of Cardiology, Warsaw, Poland
| | - Iga Kolasa
- Department of Interventional Cardiology and Cardiac Surgery, University of Zielona Gora, Collegium Medicum, Zielona Gora, Poland
| | - Agnieszka Jurek
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Cardiology and Internal Diseases, Military Institute of Medicine, Warsaw, Poland
| | - Jan Budzianowski
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Interventional Cardiology and Cardiac Surgery, University of Zielona Gora, Collegium Medicum, Zielona Gora, Poland
- WSSP ZOZ Nowa Sol, Nowa Sol, Poland
| | - Paweł Burchardt
- ‘Club 30’, Polish Cardiac Society, Poland
- Department of Biology and Lipid Disorders, Poznan University of Medical Sciences, Poznan, Poland
| | - Agnieszka Kapłon-Cieślicka
- ‘Club 30’, Polish Cardiac Society, Poland
- First Department of Cardiology, Medical University of Warsaw, Warsaw, Poland
| | - Piotr J Slomka
- Department of Medicine (Division of Artificial Intelligence in Medicine), Cedars-Sinai Medical Center, 8700 Beverly Blvd, Suite Metro 203, 90048, Los Angeles, CA, USA
| |
Collapse
|
2
|
Construction of a Clinical Predictive Model of Left Atrial and Left Atrial Appendage Thrombi in Patients with Nonvalvular Atrial Fibrillation. J Interv Cardiol 2022; 2022:7806027. [DOI: 10.1155/2022/7806027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2022] [Revised: 10/19/2022] [Accepted: 10/28/2022] [Indexed: 11/06/2022] Open
Abstract
Background. The purpose of this study was to investigate the risk factors of left atrial (LA) or left atrial appendage (LAA) thrombi in patients with nonvalvular atrial fibrillation (NVAF) and to establish and validate relevant predictive models. It might improve thromboembolic risk stratification in patients with NVAF. Methods. This study retrospectively included 1210 consecutive patients with NVAF undergoing transesophageal echocardiography (TEE), of whom 139 patients had thrombi in LA or in LAA. Through literature review and the ten events per variable (10EPV) principle, 13 variables were finally identified for inclusion in multivariate analysis. Models were constructed by multivariate logistic stepwise regression and least absolute shrinkage and selection operator (lasso) regression. Results. After logistic regression, five variables (AF type, age, B-type natriuretic peptide, E/e’ ratio, and left atrial diameter) were finally screened out as model 1. After Lasso regression, AF type, age, gender, B-type natriuretic peptide, E/e’ ratio, left atrial diameter, and left ventricular ejection fraction were finally screened as model 2. After comparing the two models, the simpler model 1 was finally selected. The area under the ROC curve (AUC) of the model 1 was 0.865 (95% CI: 0.838–0.892), the Hosmer–Lemeshow test = 0.898, and the AUC = 0.861 after internal validation. The clinical decision curve showed that the new clinical prediction model could achieve a net clinical benefit when the expected threshold was between 0 and 0.6. Conclusion. This study constructed a new clinical prediction model of LA or LAA thrombi, with a higher discriminative degree than the CHADS2 and CHA2DS2-VASc scoring systems (AUC: 0.865 vs. 0.643; AUC: 0.865 vs 0.652).
Collapse
|
3
|
Lu X, Chen T, Liu G, Guo Y, Shi X, Chen Y, Li Y, Guo J. Relations between left atrial appendage contrast retention and thromboembolic risk in patients with atrial fibrillation. J Thromb Thrombolysis 2021; 53:191-201. [PMID: 34128199 DOI: 10.1007/s11239-021-02490-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 05/20/2021] [Indexed: 10/21/2022]
Abstract
Left atrial appendage (LAA), a blind pouch, accounts for more than 90% of the source of cardiac thrombus formation. Contrast retention (CR) in the LAA has been frequently observed during left atrial appendage occlusion (LAAO) procedures, especially in patients with stroke history. This study was designed to assess the relations between LAA contrast retention and thrombogenesis risk of the LAA in patients with non-valvular atrial fibrillation. A total of 132 consecutive patients who underwent LAAO were enrolled. The data collected from computed tomography (CT), transthoracic echocardiography (TTE), transesophageal echocardiography (TEE) and blood samples were analyzed. Univariate and multivariate logistic regression models were constructed to assess the association between CR, left atrial appendage thrombus (LAAT) and other factors. Contrast retention was observed in 33 patients, accounting for 25% of the population. Compared to the non-CR group, patients in the CR group had a larger left atrium anteroposterior diameter (49.64 ± 11.57 vs. 42.42 ± 7.04, P = 0.002), higher CHADS2 (3.88 ± 0.99 vs. 2.97 ± 1.35, P = 0.001) and CHA2DS2-VASc scores (5.79 ± 1.14 vs. 4.89 ± 1.56, P = 0.003), a higher rate of prior stroke (90.9% vs. 66.7%, P = 0.007), more LAA lobes (3.13 ± 1.18 vs. 2.64 ± 1.12, P = 0.038), and a higher prevalence of LAAT (63.6% vs. 13.1%, P < 0.001). After having adjusted the logistic model, only contrast retention, LAA cauliflower morphology and left ventricular ejection fraction (LVEF) were independently associated with LAAT. Patients with LAA contrast retention have a higher risk of left atrial appendage thrombosis. Contrast retention may be a cardiac factor strongly associated with cardiogenic stroke.
Collapse
Affiliation(s)
- Xu Lu
- Medical School of Chinese PLA, 28 Fuxing Road, Haidian District, Beijing, 100853, China.,Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.,Outpatient Department, The 44th Sanatorium of Retired Cadres in Haidian District, No. 19 Dahuisi Road, Beijing, 100081, China
| | - Tao Chen
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China
| | - Ge Liu
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China
| | - Yutao Guo
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China
| | - Xiangmin Shi
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China
| | - Yundai Chen
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China
| | - Yang Li
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
| | - Jun Guo
- Department of Cardiology, the Sixth Medical Centre, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
| |
Collapse
|