Nowadays, we are observing a growing interest about Big Data applications in different healthcare sectors. One of this is definitely cardiology. In fact, electrocardiogram produces a huge amount of data about the heart health status that need to be stored and analysed in order to detect a possible issues. In this paper, we focus on the arrhythmia detection problem. Specifically, our objective is to address the problem of distributed processing considering big data generated by electrocardiogram (ECG) signals in order to carry out pre-processing analysis. Specifically, an algorithm for the identification of heartbeats and arrhythmias is proposed. Such an algorithm is designed in order to carry out distributed processing over the Cloud since big data could represent the bottleneck for cardiology applications. In particular, we implemented the Menard algorithm in Apache Spark in order to process big data coming form ECG signals in order to identify arrhythmias. Experiments conducted using a dataset provided by the Physionet.org European ST-T Database show an improvement in terms of response times. As highlighted by our outcomes, our solution provides a scalable and reliable system, which may address the challenges raised by big data in healthcare.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.