Atypicality for Heart Rate Variability Using a Pattern-Tree Weighting Method
This work addresses cardiovascular condition monitoring for medical applications, but it appears incremental as it extends an existing atypicality framework to real-valued data.
The paper tackled the problem of analyzing heart rate variability (HRV) for cardiovascular health by proposing a pattern-tree method to detect arrhythmias and unknown patterns, resulting in successful discovery in HRV Holter Monitoring data.
Heart rate variability (HRV) is a vital measure of the autonomic nervous system functionality and a key indicator of cardiovascular condition. This paper proposes a novel method, called pattern tree which is an extension of Willem's context tree to real-valued data, to investigate HRV via an atypicality framework. In a previous paper atypicality was developed as method for mining and discovery in "Big Data," which requires a universal approach. Using the proposed pattern tree as a universal source coder in this framework led to discovery of arrhythmias and unknown patterns in HRV Holter Monitoring.