Analysis of Respiratory Sinus Arrhythmia with Neural Networks

Julian Szymanski; Patryk Orkisz; Higinio Mora

cs.LGSep 4, 2026

Analysis of Respiratory Sinus Arrhythmia with Neural Networks

Authors: Julian Szymanski, Patryk Orkisz, Higinio Mora

Organizations: Gdansk University of Technology, Narutowicza 11/12, 80-233 Gdansk, Poland · University of Alicante, 03690 San Vicente del Raspeig, Alicante; Spain

Abstract

The paper introduces a neural network-based approach for analyzing ECG signals to estimate respiratory rate by leveraging the phe- nomenon of Respiratory Sinus Arrhythmia (RSA). Our method employs a deep learning model trained to predict respiratory waveforms directly from ECG input data. To achieve this, we developed and evaluated three different neural network architectures capable of automatically extract- ing relevant features from ECG signals without the need for manual preprocessing. The proposed approach offers a robust and scalable solu- tion for non-invasive respiratory monitoring, with potential applications in healthcare and wearable technology

Figures & tables

Panel of Figure 1 — Figure 1: Our model, based on a Transformer network, used for ECG signal classification.

Figure 2: ECG waveforms, along with interpolated RRI and RPA

Figure 3: Respiratory signal annotations

Panel of Figure 4 — Figure 4: Our neural model for respiratory rhythm regression based on ECG signal

Figure 5: Example of respiratory rate prediction based on ECG signal

Metric	Medium RR	Low RR	High RR	Mixed RR
Total waveforms duration [min]	63	36	24	7,83
Average breaths per minute [BPM]	8,30	4,19	13,46	8,55
Average loss function	0,0056	0,0098	0,0241	0,0141
Average NCC	0,95	0,89	0,47	0,84
Average RPE [%]	30,20	35,52	83,00	49,80

Table 1: Test metric values within different ranges of BPM

Respiratory Rate [BPM]	Algorithm	Average NCC	Average RPE [%]
Low <4,6>	NeuroKit	0,31	82,86
	Neural	0,89	35,52
Medium <7,11>	NeuroKit	0,89	49,53
	Neural	0,95	30,20
High <12, $\infty$ >	NeuroKit	0,74	69,65
	Neural	0,47	83,00

Table 2: Comparison of our algorithm (neural) with NeuroKit

Automated ECG Interval Measurement and Wave Delineation Using Fast Fourier Convolution ResNet
Jul 27, 2026Farhan Adam Mukadam, Harshit Mishra, Nachiket Makwana +3Electrocardiography Convolutional Neural Networks
Indian Institute of Science, Bengaluru, India · Gauze, India · Waikato District Health Board, Hamilton, New Zealand +1
A Skin-Tone-Aware Dual-Representation Remote Photoplethysmography Framework for Contactless Respiratory Rate Estimation
Jun 19, 2026Trishna Saikia, Anup Kumar Gupta, Puneet Gupta +1Remote Photoplethysmography Photoplethysmography
ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification
May 13, 2026Mahsa Gazeran, Sayvan Soleymanbaigi, Fatemeh Daneshfar +2Self-Supervised Time Series Representation Learning Transformer Attention
Department of Computer Engineering, University of Kurdistan, Sanandaj, Iran · Department of Mathematics and Operational Research, University of Mons, Mons, Belgium

Jul 27, 2026J/K move · Enter open · S save

Automated ECG Interval Measurement and Wave Delineation Using Fast Fourier Convolution ResNet

Farhan Adam Mukadam, Harshit Mishra, Nachiket Makwana, Pradyot Tiwari+2

Indian Institute of Science, Bengaluru, India · Gauze, India · Waikato District Health Board, Hamilton, New Zealand+1

Electrocardiography Convolutional Neural Networks Electrocardiogram Interpretation

Open paper AskPDF arXiv

Accurate measurement of ECG intervals, including PR, QRS duration, and QT/QTc, is central to cardiac diagnosis, yet the published ECG delineation literature evaluates performance almost exclusively as fiducial-point timing errors on small curated databases, rather than as clinical interval accuracy on large unselected cohorts. We bridge this gap by evaluating a complete end-to-end pipeline on 10,646 clinical 12-lead ECGs and reporting the first large-scale interval measurement accuracy study with full statistical characterisation, including bias, 95% limits of agreement (Bland-Altman), bootstrap confidence intervals, and rhythm-stratified error analysis. The underlying delineation is performed by a Fast Fourier Convolution ResNet (FFCResNet), adapting local temporal convolutions with global spectral processing via FFT and augmented with register tokens for contextual feature learning. Three per-wave models (P, QRS, and T) are trained on six public databases with ECG-specific augmentation. On 10,646 ECGs, the system achieves a QT MAE of 17.5 ms [95% CI: 16.9-18.2], with a Bland-Altman bias of +8.5 ms (LoA: -68.5 to +85.5 ms); a QRS duration MAE of 14.8 ms [95% CI: 14.6-15.0], with a bias of +12.6 ms (LoA: -12.3 to +37.6 ms); and a ventricular rate MAE of 0.8 beats/min. All biases are statistically significant by the Wilcoxon signed-rank test (p < 0.001) but remain within or near published inter-observer variability bounds for sinus rhythms. Rhythm-stratified analysis reveals substantially higher QT errors for supraventricular tachycardias (SVT MAE: 75.0 ms; AVRT MAE: 85.3 ms) than for sinus bradycardia (SB MAE: 9.3 ms) and sinus rhythm (SR MAE: 8.9 ms), providing an honest characterisation of the deployment scope. Wave segmentation achieves internal Dice scores of 95.5%, 98.2%, and 96.1% for P, QRS, and T waves, respectively, and cross-database Dice scores of 78.1%, 85.5%, and 74.2%.

Abstract

Explore similar work

Automated ECG Interval Measurement and Wave Delineation Using Fast Fourier Convolution ResNet

A Skin-Tone-Aware Dual-Representation Remote Photoplethysmography Framework for Contactless Respiratory Rate Estimation

ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification