Artificial Intelligence-Enabled ECG to Identify Silent Atrial Fibrillation in Embolic Stroke of Unknown Source.

Embolic strokes of unknown source (ESUS) are common and often suspected to be caused by unrecognized paroxysmal atrial fibrillation (AF). An AI-enabled ECG (AI-ECG) during sinus rhythm has been shown to identify patients with unrecognized AF. We pursued this study to determine if the AI-ECG model differentiates between patients with ESUS and those with known causes of stroke, and to evaluate whether the AF prediction by AI-ECG among patients with ESUS was associated with the results of prolonged ambulatory cardiac rhythm monitoring. We reviewed consecutive patients admitted with acute ischemic stroke to a comprehensive stroke center between January 2018 and August 2019 and employed the TOAST classification to categorize the mechanisms of ischemia. Use and results of ambulatory cardiac rhythm monitoring after discharge were gathered. We ran the AI-ECG model to obtain AF probabilities from all ECGs acquired during the hospitalization and compared those probabilities in patients with ESUS versus those with known stroke causes (apart from AF), and between patients with and without AF detected by ambulatory cardiac rhythm monitoring. The study cohort had 930 patients, including 263 patients (28.3%) with known AF or AF diagnosed during the index hospitalization and 265 cases (28.5%) categorized as ESUS. Ambulatory cardiac rhythm monitoring was performed in 226 (85.3%) patients with ESUS. AF probability by AI-ECG was not associated with ESUS. However, among patients with ESUS, the probability of AF by AI-ECG was associated with a higher likelihood of AF detection by ambulatory monitoring (P = 0.004). A probability of AF by AI-ECG greater than 0.20 was associated with AF detection by ambulatory cardiac rhythm monitoring with an OR of 5.47 (95% CI 1.51-22.51). AI-ECG may help guide the use of prolonged ambulatory cardiac rhythm monitoring in patients with ESUS to identify those who might benefit from anticoagulation.

Rabinstein AA ，Yost MD ，Faust L ，Kashou AH ，Latif OS ，Graff-Radford J ，Attia IZ ，Yao X ，Noseworthy PA ，Friedman PA ... -  《-》

Artificial intelligence predicts undiagnosed atrial fibrillation in patients with embolic stroke of undetermined source using sinus rhythm electrocardiograms.

Artificial intelligence (AI)-enabled sinus rhythm (SR) electrocardiogram (ECG) interpretation can aid in identifying undiagnosed paroxysmal atrial fibrillation (AF) in patients with embolic stroke of undetermined source (ESUS). The purpose of this study was to assess the efficacy of an AI model in identifying AF based on SR ECGs in patients with ESUS. A transformer-based vision AI model was developed using 737,815 SR ECGs from patients with and without AF to detect current paroxysmal AF or predict the future development of AF within a 2-year period. Probability of AF was calculated from baseline SR ECGs using this algorithm. Its diagnostic performance was further tested in a cohort of 352 ESUS patients from 4 tertiary hospitals, all of whom were monitored using an insertable cardiac monitor (ICM) for AF surveillance. Over 25.1-month follow-up, AF episodes lasting ≥1 hour were identified in 58 patients (14.4%) using ICMs. In the receiver operating curve (ROC) analysis, the area under the curve for the AI algorithm to identify AF ≥1 hour was 0.806, which improved to 0.880 after integrating the clinical parameters into the model. The AI algorithm exhibited greater accuracy in identifying longer AF episodes (ROC for AF ≥12 hours: 0.837, for AF ≥24 hours: 0.879) and a temporal trend indicating that the AI-based AF risk score increased as the ECG recording approached the AF onset (P for trend <.0001). Our AI model demonstrated excellent diagnostic performance in predicting AF in patients with ESUS, potentially enhancing patient prognosis through timely intervention and secondary prevention of ischemic stroke in ESUS cohorts.

Choi J ，Kim JY ，Cho MS ，Kim M ，Kim J ，Oh IY ，Cho Y ，Lee JH ... -  《-》

Supraventricular Extrasystoles on Standard 12-lead Electrocardiogram Predict New Incident Atrial Fibrillation after Embolic Stroke of Undetermined Source: The AF-ESUS Study.

The diagnosis of covert atrial fibrillation (AF) remains a major challenge to guide secondary prevention of patients with embolic stroke of undetermined source (ESUS). We analyzed consecutive ESUS patients from 3 prospective stroke registries to assess whether the presence of supraventricular extrasystoles (SVE) on standard 12-lead electrocardiogram (ECG) is associated with the detection of AF (primary outcome), stroke recurrence and death (secondary outcomes) during follow-up. We measured the number of SVEs in all available ECGs of patients hospitalized for ESUS. Multivariate stepwise regression with forward selection of covariates assessed the association between SVE (classified in 4 groups according to their number per 10 seconds of ECG: no SVE, >0-1SVEs, >1-2SVEs, and >2SVEs) and outcomes during follow-up. The Kaplan-Meier product limit method estimated the 10-year cumulative probabilities of outcomes in each SVE group. We calculated the negative prognostic value (NPV) of the presence of any SVE to predict new AF, defined as the probability that AF will not be detected during follow-up if there is no SVE. Among 853 ESUS patients followed for 2857 patient-years (median age: 67 years, 43.0% women), 226 (26.5%) patients had at least 1 SVE at the standard 12-lead ECGs performed during hospitalization. AF was detected in 125 (14.7%) of patients in the overall population during follow-up: 8.9%, 22.5%, 28.1%, and 48.3% in patients with no SVE, greater than 0-1SVE, greater than 1-2SVE and greater than 2SVE respectively. In multivariate regression analysis, compared to patients with no SVEs, the corresponding hazard-ratios were 1.80 [95% confidence intervals (95%CI):1.06-3.05], 2.26 (95%CI:1.28-4.01) and 3.19 (95%CI:1.93-5.27). The NPV of the presence of any SVE for the prediction of new AF was 91.4%. There was no statistically significant association of SVE with the risk of ischemic stroke recurrence and death. In ESUS patients without SVEs during hospitalization, the probability that AF will not be detected during a follow-up of 3.4 years is more than 91%.

Ntaios G ，Perlepe K ，Lambrou D ，Sirimarco G ，Strambo D ，Eskandari A ，Karagkiozi E ，Vemmou A ，Koroboki E ，Manios E ，Makaritsis K ，Michel P ，Vemmos K ... -  《-》

Biomarkers of Atrial Cardiopathy and Atrial Fibrillation Detection on Mobile Outpatient Continuous Telemetry After Embolic Stroke of Undetermined Source.

Biomarkers of atrial dysfunction or "cardiopathy" are associated with embolic stroke risk. However, it is unclear if this risk is mediated by undiagnosed paroxysmal atrial fibrillation or flutter (AF). We aim to determine whether atrial cardiopathy biomarkers predict AF on continuous heart-rhythm monitoring after embolic stroke of undetermined source (ESUS). This was a single-center retrospective study including all patients with ESUS undergoing 30 days of ambulatory heart-rhythm monitoring to look for AF between January 1, 2013 and December 31, 2015. We reviewed medical records for clinical, radiographic, and cardiac variables. The primary outcome was a new diagnosis of AF detected during heart-rhythm monitoring. The primary predictors were atrial biomarkers: left atrial diameter on echocardiography, P-wave terminal force in electrocardiogram (ECG) lead V1, and P wave - R wave (PR) interval on ECG. A multiple logistic regression model was used to assess the relationship between atrial biomarkers and AF detection. Among 196 eligible patients, 23 (11.7%) were diagnosed with AF. In unadjusted analyses, patients with AF were older (72.4 years versus 61.4 years, P < .001) and had larger left atrial diameter (39.2 mm versus 35.7 mm, P = .03). In a multivariable model, the only predictor of AF was age ≥ 60 years (odds ratio, 3.0; 95% CI, 1.06-8.5; P = .04). Atrial biomarkers were weakly associated with AF after ESUS. This suggests that previously reported associations between these markers and stroke may reflect independent cardiac pathways leading to stroke. Prospective studies are needed to investigate these mechanisms.

Sebasigari D ，Merkler A ，Guo Y ，Gialdini G ，Kummer B ，Hemendinger M ，Song C ，Chu A ，Cutting S ，Silver B ，Elkind MSV ，Kamel H ，Furie KL ，Yaghi S ... -  《-》

Septal total atrial conduction time for prediction of atrial fibrillation in embolic stroke of unknown source: a pilot study.

Sieweke JT ，Biber S ，Weissenborn K ，Heuschmann PU ，Akin M ，Zauner F ，Gabriel MM ，Schuppner R ，Berliner D ，Bauersachs J ，Grosse GM ，Bavendiek U ... -  《-》