Development of stroke detection method by heart rate variability analysis and support vector machine

It is important to start stroke treatment as early as possible for patient prognosis. In particular, thrombolysis with the tissue plasminogen activator (tPA) that can dissolve blood clots is effective only when it is given within 4.5 hours from the symptom onset. Since it is sometimes difficult for patients to recognize their symptoms, an early stroke detection system is needed. It is possible that a stroke can be detected by monitoring heart rate variability (HRV) because a stroke affects the autonomic nervous system. In the present work, a stroke detection method was proposed by integrating HRV analysis and support vector machine (SVM). The sensitivity and the specificity of the proposed method were 100% and 80%, respectively. The possibility of realizing an HRV-based stroke detection system was shown.