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

Abstract

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

Can Artificial Intelligence Enhance Syncope Management?

“…Artificial intelligence (AI) and machine learning (ML) may help address some of these issues ( Table 1 ). Preliminary AI-based risk stratification and diagnostic methods are encouraging, 11 and include predicting short-term adverse events 12 , 13 and hospitalization, 14 , 15 diagnosing vasovagal syncope, 16 , 17 differentiating syncope from other forms of TLOC, 18 assisting in ECG interpretation, 19 interpreting ambulatory ECG monitors and implantable loop recorders, 19 and reviewing records via natural language processing (NLP). 20 However, the ultimate role for AI in syncope management remains undeveloped.…”

“…Hussain et al 16 employed a support vector machine model capable of using patient vital signs during the head-up tilt test to diagnose vasovagal syncope. Raphan et al 17 developed a ML approach to identify vasovagal responses in an animal model during tilt table testing. Wardrope et al 18 used patient and witness questionnaires to develop a ML model that accurately predicted the diagnosis in 86% of 249 patients known to have syncope, epilepsy, or psychogenic nonepileptic seizures.…”

El tiempo de tránsito del pulso detecta cambios en la presión arterial en respuesta a estimulación eléctrica vestibular y cambio de postura

“…DISCUSIÓN El uso de GVS para el estudio de la modulación cardiovascular en respuesta a estímulos vestibulares es un área de estudio en desarrollo con un amplio campo de aplicaciones. La modulación de la función cardiovascular debe corresponder con los movimientos de la cabeza y corporales para mantener una irrigación óptima de los órganos vitales, por ejemplo, el síndrome vasovagal es un padecimiento común que implica la respuesta tardía de la función cardiaca a los cambios de postura [16]. Hasta el momento, no se ha reportado ningún trabajo que use el cálculo del PTT en experimentos con GVS para estudiar la modulación cardiovascular.…”