An Efficient and Affordable R-Pi Based
Cardiac Disease Detection System
Neha Arora and Biswajit Mishra
Abstract This paper proposes a Raspberry Pi (R-Pi) based system to automatically
detect and classify most of the atrial and ventricular cardiac diseases. The system
provides a necessary solution for resource constrained regions to timely detect fatal
cardiac conditions. The R-Pi receives the user specific information from the ECG
application specifically developed for the smart mobile phones and 2-Lead ECG
data from the ECG sensors connected with limb electrodes and the Arduino Nano
board. The ECG data along with the user specific information is further processed
for lead separation, ECG feature extraction, and disease classification. The obtained
results are sent to the doctor via email. Along with the system development, this work
proposes various algorithms for feature points detection and disease classifications.
Keywords ECG · R-Pi · Disease classification · Feature extraction
1 Introduction
ECG recordings are frequently used to detect Arrhythmias that are relatively quiet
in the early stages. However, they may provide valuable knowledge about an indi-
vidual’s fitness and aid in the detection of underlying heart anomalies and the timely
detection can prove to be life saving. While not all of arrhythmias are permanent
or necessitate medical treatment, they can signal the onset of serious heart diseases.
An ECG depicts the electrical activity of the heart and provides a large amount of
information on the functionality of the heart required for the proper diagnosis of
Supported by DST/SERB- CRG, Govt. of India, Research fund Ref: CRG/2019/004747.
N. Arora · B. Mishra (B )
Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT),
Gandhinagar, Gujarat, India
e-mail: biswajit_mishra@daiict.ac.in
N. Arora
e-mail: 201721007@daiict.ac.in
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2022
B. Mishra et al. (eds.), Artificial Intelligence Driven Circuits and Systems,
Lecture Notes in Electrical Engineering 811,
https://doi.org/10.1007/978-981-16-6940-8_1
1