Key result
EEG features combined with a C5.0 machine-learning model classified ischemic stroke patients and healthy adults with 78% accuracy in the resting state and up to 89% accuracy during motor tasks.
Why the study?
The study aimed to quantify EEG features to understand task-induced neurological declines due to stroke and evaluate biomarkers to distinguish ischemic stroke patients from healthy adults.
Can EEG features during resting, motor, and cognitive tasks accurately distinguish ischemic stroke patients from healthy adults?
Comparison
Ischemic stroke group vs healthy adult control group
Design
Case-control study
Authors
Loading...
Inferred Key Finding:* EEG features can quantify task-induced neurological decline and distinguish ischemic stroke.
Case-Control (n=123)
Can EEG features during resting, motor, and cognitive tasks accurately distinguish ischemic stroke patients from healthy adults?
Effect estimate: 89% accuracy (motor walking condition)
EEG features during motor and cognitive tasks, combined with machine learning, can accurately distinguish ischemic stroke patients from healthy adults, offering potential biomarkers for post-stroke rehabilitation.
Hussain et al. (2021) conducted a case-control in Ischemic stroke (n=123). Ischemic stroke vs. Healthy adults was evaluated on Classification accuracy between the stroke group and the control group using the C5.0 machine-learning model (89% accuracy (motor walking condition)). EEG features combined with a C5.0 machine-learning model classified ischemic stroke patients and healthy adults with 78% accuracy in the resting state and up to 89% accuracy during motor tasks.
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: