Automatic Stroke Screening on Mobile Application: Features of Gyroscope and Accelerometer for Arm Factor in FAST.

Area of Science:

• Biomedical Engineering
• Neurology
• Digital Health

Background:

• The FAST (Face, Arm, Speech, Time) method is a standard stroke screening tool.
• Assessing arm motor function is crucial for stroke detection.
• Mobile devices offer a potential platform for remote health monitoring and screening.

Purpose of the Study:

• To develop and evaluate a mobile-based system for automatic stroke screening focusing on arm movements.
• To assess the feasibility of using smartphone sensors (gyroscope, accelerometer) for capturing arm movement data.
• To differentiate between stroke patients and healthy individuals based on arm exercise performance.

Main Methods:

• Recruited 52 participants (20 stroke patients, 32 healthy controls).
• Developed a mobile application to guide participants through two arm movements: Curl Up and Raise Up.
• Collected gyroscope and accelerometer data during exercises, analyzing 20 handcrafted features from distinct movement phases (curl, raise, stable).

Main Results:

• The system achieved an average accuracy ranging from 61.7% to 74.2%.
• The Area Under the ROC Curve (AUC) ranged from 66.2% to 81.5%.
• Performance was comparable to traditional clinical assessments of the arm factor in stroke screening.

Conclusions:

• Mobile sensor-based analysis of arm movements presents a viable approach for stroke screening.
• This technology holds potential for early stroke identification and remote patient monitoring.
• Further research can refine the methodology and integrate it with other FAST components.