Predicting Vasovagal Responses: A Model-Based and Machine Learning Approach.

摘要: Vasovagal syncope (VVS) or neurogenically induced fainting has resulted in falls, fractures, and death. Methods to deal with VVS are use implanted pacemakers beta blockers. These often ineffective because the underlying changes cardiovascular system that lead incompletely understood diagnosis of frequent occurrences is still based on history a tilt test, which subjects passively tilted from supine position 20° spatial vertical (to 70° position) table maintained orientation for 10-15 min. Recently, been shown vasovagal responses (VVRs), characterized by transient drops blood pressure (BP), heart rate (HR), increased amplitude low frequency oscillations BP can be sinusoidal galvanic vestibular stimulation (sGVS) were similar presaged humans. This drop HR 25 mmHg beats per minute (bpm), respectively, considered VVR. Similar thresholds have used identify VVR's human studies as well. However, this arbitrary threshold identifying VVR does not give clear understanding features nor what triggers In study, we utilized our model generation together machine learning approach learn separating hyperplane between normal patterns. methodology proposed technique more broadly trigger If feature identification could associated VVRs humans, it potentially onset VVS, i.e, fainting, real time.