Key result
Deep learning of brain MRI infarct patterns identifies AF post-stroke with an AUROC of ~87%.
Why the study?
AF substantially increases stroke risk and recurrence but remains undetected in up to 30% of cases due to its asymptomatic, paroxysmal nature and lack of routine screening.
Does a deep learning framework analyzing brain MRI infarct patterns identify underlying atrial fibrillation in post-stroke patients?
Does a deep learning framework analyzing brain MRI infarct patterns identify underlying atrial fibrillation in post-stroke patients?
A novel deep learning model analyzing brain MRI infarct patterns can effectively identify underlying atrial fibrillation in post-stroke patients, potentially guiding further cardiac investigation without additional testing costs.
Answers are grounded in this paper and cite their sources.
May guide selective cardiac monitoring in post-stroke patients; extends deep learning validation of MRI infarct patterns for AF detection.
Atrial fibrillation (AF), being the most prevalent arrhythmia around the world, is a significant health concern considering an aging population and increasing prevalence of its risk factors such as hypertension and obesity. It is estimated that AF increases the risk of stroke by about five times and the risk of its recurrence by two-fold. AF remains undetected in up to 30% of cases due to its asymptomatic and paroxysmal nature, and lack of routine screening. We present a novel AF risk stratification framework using brain magnetic resonance imaging (MRI) to identify the underlying AF in post-stroke patients and assist in preventing secondary ones. By analyzing the infarct patterns of these patients using a multitask learning framework (adopting segmentation and classification losses simultaneously), our proposed model achieves an area under the receiver operating characteristic (AUROC) of 87.48 ± 4.88, demonstrating its capability in discriminating AF patients from others. Since MRI is already an established modality in the stroke treatment and diagnosis framework, this innovative solution incurs no additional costs or tests for the patient. It can effectively select patients at elevated risk for extensive cardiac investigation and definite diagnosis of AF.
No takes yet. Share an insight, caveat, or question.
Shokri et al. (2024) studied Atrial fibrillation in post-stroke patients. Deep learning framework using brain MRI was evaluated on Discrimination of atrial fibrillation patients from others (AUROC 87.48 ± 4.88). A novel deep learning framework using brain MRI to analyze infarct patterns successfully discriminated atrial fibrillation in post-stroke patients with an AUROC of 87.48 ± 4.88.
Synapse has enriched 10 related papers. Consider them for comparative context: