Artificial intelligence in detecting left atrial appendage thrombus by transthoracic echocardiography and clinical features: the Left Atrial Thrombus on Transoesophageal Echocardiography (LATTEE) registry

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.

Keywords: Ablation • Cardioversion • Left atrial appendage thrombus • Machine learning.

Structured Graphical Abstract

Development and validation of an artificial intelligence model (LAT-AI) to detect left atrial appendage thrombus by transoesophageal echocardiography. AI, artificial intelligence; LAT, left atrial appendage thrombus; LV, left ventricular; CHA₂DS₂-VASc, current clinical score to assess thrombo-embolic risk.

Figure 1

Average feature importance scores in the order of importance with 95% confidence intervals (whiskers) based on the internal 10-fold cross-validation in the development cohort. A, For the full LAT-AI model (top 20 features); B, for the LAT-AI-reduced model. AP, anteroposterior; INR, international normalized ratio; NYHA, New York Heart Association.

Figure 2

Receiver-operating characteristic curves for the prediction of left atrial thrombus in the external testing set. Significance for difference in AUC (by DeLong test): *P < .001; **P < .01. AUC, area under the receiver-operating characteristic curve; LAT, left atrial appendage thrombus; LVEF, left ventricular ejection fraction; ML, machine learning model; NS, non-significant.

Figure 3

Simulated application of LAT-AI and LAT-AI-reduced models to guide the decision to perform TOE in the external cohort, based on the thresholds derived from the development cohort. LAT, left atrial appendage thrombus; TOE, transoesophageal echocardiography; OAC, oral anticoagulation.