Potential Embolic Sources in Embolic Stroke of Undetermined Source Patients with Patent Foramen Ovale

Machine Learning Modeling to Predict Atrial Fibrillation Detection in Embolic Stroke of Undetermined Source Patients

BACKGROUND

In patients with embolic stroke of undetermined source (ESUS), occult atrial fibrillation (AF) has been implicated as a key source of cardioembolism. However, only a minority acquire implantable cardiac loop recorders (ILRs) to detect occult paroxysmal AF, partly due to financial cost and procedural inconvenience. Without the initiation of appropriate anticoagulation, these patients are at risk of increased ischemic stroke recurrence. Hence, cost-effective and accurate methods of predicting AF in ESUS patients are highly sought after.

OBJECTIVE

We aimed to incorporate clinical and echocardiography data into machine learning (ML) algorithms for AF prediction on ILRs in ESUS.

METHODS

This was a single-center cohort study that included 157 consecutive patients diagnosed with ESUS from October 2014 to October 2017 who had ILR evaluation. We developed four ML models, with hyperparameters tuned, to predict AF detection on an ILR.

RESULTS

The median age of the cohort was 67 (IQR 59-74) years old and the median monitoring duration was 1051 (IQR 478-1287) days. Of the 157 patients, 32 (20.4%) had occult AF detected on the ILR. Support vector machine predicted for AF with a 95% confidence interval area under the receiver operating characteristic curve (AUC) of 0.736-0.737, multilayer perceptron with an AUC of 0.697-0.708, XGBoost with an AUC of 0.697-0.697, and random forest with an AUC of 0.663-0.674. ML feature importance found that age, HDL-C, and admitting heart rate were important non-echocardiography variables, while peak mitral A-wave velocity and left atrial volume were important echocardiography parameters aiding this prediction.

CONCLUSION

Machine learning modeling incorporating clinical and echocardiographic variables predicted AF in ESUS patients with moderate accuracy.

Embolic stroke of undetermined source: Focusing on atrial cardiopathy and patent foramen ovale

BACKGROUND

Atrial cardiopathy(AC) and patent foramen ovale (PFO) are two etiologies of embolic strokes of undetermined source (ESUS). We aimed to explore the relationship between them in ESUS.

METHODS

A total of 1146 participants were included from January 2019 to June 2022, which included the ESUS group and non-embolic stroke which includes LAA(large arterial atherosclerosis) + SAO(small artery occlusion) group. AC was defined as the presence of at least one of the following: PTFV1(P-wave terminal force in lead V1) > 4000 μV*ms in the electrocardiograms, NT-proBNP(N-terminal probrain natriuretic peptide) > 250 pg/mL in laboratory tests or LAD(left atrial diameter) > 3.8 cm for women and > 4.0 cm for men in cardiac ultrasound. The presence of PFO was assessed by transthoracic echocardiography, transcranial Doppler ultrasound, transesophageal echocardiography or cardiac MRI. PFO was considered pathogenic if the RoPE score was 7 to 10.

RESULTS

The prevalence of AC and PFO was higher in the ESUS group than the LAA + SAO group. The prevalence of AC was lower in ESUS patients with pathogenic PFO (37.9%) than those without PFO (68.4%) and with incidental PFO (64.0%) (p = 0.006). The prevalence of pathogenic PFO was lower in ESUS patients with AC than those without AC (6.0% vs. 17.8%, p = 0.006). The AUC(area under the curve) of PTFV1 for predicting ESUS was 0.724 [95%CI (0.686-0.762), p < 0.05)], indicating that PTFV1 the most valuable AC biomarker.

CONCLUSIONS

The prevalence of AC is inversely related to the prevalence of pathogenic PFO in ESUS patients. PTFV1 was the most valuable index to predict ESUS among the AC biomarkers.