Similar patient search using the results of heartbeat classification

Long-term ECG data for a patient can be acquired by integrating a Holter monitor with a mobile device. We use similar patient search to create an abstraction of a patient's typical heartbeat pattern, in the form of a regular expression, by learning heartbeat patterns. We have simulated these processes on data from the MIT-BIH arrhythmia database, and shown how we can search the database for patients with similar heartbeat patterns.