Raspberry Pi-Based ECG Signal Processing with Automated Arrhythmia Detection

Q: What is the clinical evidence from this study?

Population: Arrhythmia. Intervention: Raspberry Pi-based hybrid ECG signal processing system vs. Standard embedded methods (Threshold-only, Deep CNN/LSTM, Feature + SVM). Primary outcome: Overall multi-class classification accuracy.

Q: What does this research mean for the field?

A Raspberry Pi-based hybrid ECG signal processing architecture achieves an overall multi-class arrhythmia detection accuracy of 94.8% and an F1-score of 93.8% in near real-time execution. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Beeravelli Shivanjani; Naidana Yagna Karthikeya; Nallavally Sricharan; Dr. G. Jagadeeswar Reddy; Dr. Ch. Raja

doi:10.56975/ijvra.v4i4.704985

April 1, 2026International Journal of Versatile Research and AnalysisOpen Access

Raspberry Pi-Based ECG Signal Processing with Automated Arrhythmia Detection

View Full Paper

Ask AI

Bookmark

Share

Key result

Raspberry Pi-based hybrid ECG system achieves ~95% accuracy in multi-class arrhythmia detection.

Why the study?

Conventional ECG systems often rely on microcontrollers with limited processing capability that affect real-time performance, motivating the design of a faster, more flexible Raspberry Pi-based system.

Key Points

To develop and evaluate an efficient, low-cost Raspberry Pi-based ECG signal processing architecture capable of real-time digital filtering, feature extraction, and automated arrhythmia classification.
Engineered an end-to-end embedded pipeline using Python on a Raspberry Pi to digitize single-lead ECG data, eliminate baseline wander and noise artifacts, and perform QRS detection.
Implemented a hybrid classification engine combining rule-based logic and lightweight machine learning models, validated using annotated records from the MIT-BIH Arrhythmia Database.
Binary classification between normal and abnormal rhythms yielded an accuracy of 97.2%, sensitivity of 96.1%, specificity of 97.9%, and an F1-score of 96.6%.
Subtype identification demonstrated 95.4% accuracy (94.0% sensitivity, 97.1% specificity) for premature ventricular contraction (PVC) detection and 93.1% accuracy for supraventricular ectopic beat (SVEB) detection.
Overall multi-class arrhythmia detection achieved 94.8% accuracy, 93.6% sensitivity, 96.0% specificity, and a 93.8% F1-score while maintaining per-beat processing latency below standard inter-beat intervals.

Structured PICO

P

Population

Standard annotated ECG data, specifically the MIT-BIH Arrhythmia Database

I

Intervention

Raspberry Pi-based electrocardiogram (ECG) signal processing framework with automated arrhythmia detection using a hybrid detection pipeline (rule-based logic augmented by a random forest machine learning classifier)

C

Comparator

Other embedded methods (Threshold-only, Deep CNN/LSTM, Feature + SVM)

O

Outcome

Arrhythmia detection performance measured by Accuracy, Sensitivity, Specificity, Precision, and F1-scoresurrogate

Limitations

Lacks validation with live sensor data
Currently limited to single-lead ECG
Requires evaluation using larger datasets
Needs evaluation using larger datasets

Implication

A low-cost, Raspberry Pi-based ECG processing system using a hybrid machine learning approach can accurately detect arrhythmias in standard datasets, offering a potential solution for continuous decentralized cardiac monitoring.

Abstract

The objective of this project is to design an efficient Raspberry Pi–based ECG signal processing system for real-time heart activity monitoring. An Electrocardiogram (ECG) is an essential diagnostic tool used to detect cardiac conditions such as arrhythmias, tachycardia, and bradycardia. Conventional ECG systems often rely on microcontrollers with limited processing capability, affecting real-time performance. This project addresses these limitations by using a Raspberry Pi platform for faster and more flexible signal processing. The system acquires raw ECG signals, which are digitized and processed to remove noise such as baseline wander, muscle artifacts, and power-line interference. The filtered signal is analyzed to detect the QRS complex, particularly R-peaks, which are used to calculate heart rate and R–R intervals. These parameters help in evaluating cardiac rhythm accurately. The system further identifies abnormalities such as tachycardia, bradycardia, premature beats, and irregular rhythms. Alerts are generated for abnormal conditions to support timely medical response. Implemented using Python and validated with standard datasets, the system ensures reliable performance. Its low cost, portability, and efficiency make it suitable for healthcare monitoring applications.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Shivanjani et al. (2026) studied Arrhythmia. Raspberry Pi-based hybrid ECG signal processing system vs. Standard embedded methods (Threshold-only, Deep CNN/LSTM, Feature + SVM) was evaluated on Overall multi-class classification accuracy. The proposed Raspberry Pi-based hybrid ECG signal processing system achieved an overall multi-class arrhythmia detection accuracy of 94.8% and an F1-score of 93.8%.

synapsesocial.com/papers/6a0021b7c8f74e3340f9c95e https://doi.org/10.56975/ijvra.v4i4.704985

View Full Paper

Ask AI

Bookmark

Share

Raspberry Pi-Based ECG Signal Processing with Automated Arrhythmia Detection

Key Points

Structured PICO

Limitations

Implication

Abstract

Discussion

Cite This Study

Raspberry Pi-Based ECG Signal Processing with Automated Arrhythmia Detection

Key Points

Structured PICO

Limitations

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

Keep reading

More related papers