Key result
A machine-learning model based on baseline demographic and laboratory variables distinguished stroke etiology with an area under the curve of 0.82, classifying 40.3% of ESUS patients as cardioembolic.
Why the study?
It remains unclear if ESUS patients with a cardioembolic etiology who could benefit from oral anticoagulation can be identified from other ESUS subgroups and which markers should be used.
Can a machine-learning model based on baseline demographic and laboratory variables discriminate between cardioembolic and non-cardioembolic profiles in patients with embolic stroke of undetermined source?
Observational
Can a machine-learning model based on baseline demographic and laboratory variables discriminate between cardioembolic and non-cardioembolic profiles in patients with embolic stroke of undetermined source?
Effect estimate: AUC 0.82
A machine-learning model using simple baseline demographic and laboratory variables can accurately identify a cardioembolic profile in approximately 40% of patients with embolic stroke of undetermined source.
ML profiling may identify cardioembolic ESUS subsets for future trials; leaves open whether it guides therapy or improves outcomes.
Background and purpose It is currently thought that embolic stroke of undetermined source (ESUS) has diverse underlying hidden etiologies, of which cardioembolism is one of the most important. The subgroup of patients with this etiology could theoretically benefit from oral anticoagulation, but it remains unclear if these patients can be correctly identified from other ESUS subgroups and which markers should be used. We aimed to determine whether a machine‐learning (ML) model could discriminate between ESUS patients with cardioembolic and those with non‐cardioembolic profiles using baseline demographic and laboratory variables. Methods Based on a prospective registry of consecutive ischemic stroke patients submitted to acute revascularization therapies, an ML model was trained using the age, sex and 11 selected baseline laboratory parameters of patients with known stroke etiology, with the aim of correctly identifying patients with cardioembolic and non‐cardioembolic etiologies. The resulting model was used to classify ESUS patients into those with cardioembolic and those with non‐cardioembolic profiles. Results The ML model was able to distinguish patients with known stroke etiology into cardioembolic or non‐cardioembolic profile groups with excellent accuracy (area under the curve = 0.82). When applied to ESUS patients, the model classified 40.3% as having cardioembolic profiles. ESUS patients with cardioembolic profiles were older, more frequently female, more frequently had hypertension, less frequently were active smokers, had higher CHA2DS2‐VASc (Congestive heart failure or left ventricular systolic dysfunction, Hypertension, Age ≥ 75 [doubled], Diabetes, Stroke/transient ischemic attack [doubled], Vascular disease, Age 65–74, and Sex category) scores, and had more premature atrial complexes per hour. Conclusions An ML model based on baseline demographic and laboratory variables was able to classify ESUS patients into cardioembolic or non‐cardioembolic profile groups and predicted that 40% of the ESUS patients had a cardioembolic profile.
No takes yet. Share an insight, caveat, or question.
Martin et al. (2022) conducted an observational in Embolic stroke of undetermined source (ESUS). Machine-learning model based on baseline demographic and laboratory variables was evaluated on Distinguishing patients with known stroke etiology into cardioembolic or non-cardioembolic profile groups (AUC 0.82). A machine-learning model based on baseline demographic and laboratory variables distinguished stroke etiology with an area under the curve of 0.82, classifying 40.3% of ESUS patients as cardioembolic.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: