Heart beats in the cloud: distributed analysis of electrophysiological 'Big Data' using cloud computing for epilepsy clinical research

Abstract

Objective: The rapidly growing volume of multimodal electrophysiological signal data is playing a critical role in patient care and clinical research across multiple disease domains, such as epilepsy and sleep medicine. To facilitate secondary use of these data, there is an urgent need to develop novel algorithms and informatics approaches using new cloud computing technologies as well as ontologies for collaborative multicenter studies.

Materials and methods: We present the Cloudwave platform, which (a) defines parallelized algorithms for computing cardiac measures using the MapReduce parallel programming framework, (b) supports real-time interaction with large volumes of electrophysiological signals, and (c) features signal visualization and querying functionalities using an ontology-driven web-based interface. Cloudwave is currently used in the multicenter National Institute of Neurological Diseases and Stroke (NINDS)-funded Prevention and Risk Identification of SUDEP (sudden unexplained death in epilepsy) Mortality (PRISM) project to identify risk factors for sudden death in epilepsy.

Results: Comparative evaluations of Cloudwave with traditional desktop approaches to compute cardiac measures (eg, QRS complexes, RR intervals, and instantaneous heart rate) on epilepsy patient data show one order of magnitude improvement for single-channel ECG data and 20 times improvement for four-channel ECG data. This enables Cloudwave to support real-time user interaction with signal data, which is semantically annotated with a novel epilepsy and seizure ontology.

Discussion: Data privacy is a critical issue in using cloud infrastructure, and cloud platforms, such as Amazon Web Services, offer features to support Health Insurance Portability and Accountability Act standards.

Conclusion: The Cloudwave platform is a new approach to leverage of large-scale electrophysiological data for advancing multicenter clinical research.

Keywords: Cloudwave; Electrophsyiological Big Data; Epilepsy and Seizure; MapReduce; Ontology; SUDEP.

Figure 1

(A) Total number of patients admitted to the Case Western University Hospital epilepsy monitoring unit (EMU) and number of patients recruited for the Prevention and Risk Identification of SUDEP Mortality (PRISM) project. (B) Cumulative growth in volume of electrophysiological signal data collected from all EMU patients and PRISM project-specific patients.

Figure 2

Architecture of the Cloudwave platform consisting of two components: (A) Hadoop-based storage and computation module with semantic metadata layer; (B) ontology-driven signal query and visualization module.

Figure 3

Cardiac measurement workflow implemented in Cloudwave to identify QRS complexes and compute RR intervals and instantaneous heart rate (IHR) values from ECG signal data. bpm, beats/min; EDF, European Data Format; HRV, heart rate variability.

Figure 4

(A) Cloudwave MapReduce algorithm for cardiac measurements from the ECG data. (B) Implementation of the algorithm with specialized Cloudwave classes corresponding to the Map phases and Reduce phases. EDF, European Data Format; HDFS, Hadoop Distributed File System; IHR, instantaneous heart rate.

Figure 5

Cloudwave web interface for querying signal data using epilepsy and seizure ontology (EpSO) concepts (marked as annotations such as ‘onset of clonic seizure’) and visualization (note that, during a seizure, the EKG3–EKG4 signal moves beyond the reference frame). The ‘montage builder’ allows the clinician to create different combinations of electrodes.

Figure 6

Comparative evaluation of computing three cardiac measures of QRS complex detection, RR intervals, and instantaneous heart rate (IHR) values using a desktop computer and two implementations of Cloudwave over (A) 640 MB data from one European Data Format (EDF) file, (B) 3.2 GB data from five EDF files and (C) 10 min data segments (optimized for use by Cloudwave interface), and (D) scalability of multi-node Cloudwave implementation for one to four ECG channels.