Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evaluation of a Low-Cost Single-Lead ECG Module for Vascular Ageing Prediction and Studying Smoking-induced Changes in ECG

S. Anas Ali, M. Saqib Niaz, Mubashir Rehman, Ahsan Mehmood, M. Mahboob Ur Rahman, Kashif Riaz, Qammer H. Abbasi

TL;DR

A low-cost single-lead ECG internet of thing (IoT) module is utilized to predict the vascular age of an apparently healthy young person and the explainable AI framework is utilized to identify those ECG features that get affected due to smoking.

Abstract

Vascular age is traditionally measured using invasive methods or through 12-lead electrocardiogram (ECG). This paper utilizes a low-cost single-lead (lead-I) ECG module to predict the vascular age of an apparently healthy young person. In addition, we also study the impact of smoking on ECG traces of the light-but-habitual smokers. We begin by collecting (lead-I) ECG data from 42 apparently healthy subjects (smokers and non-smokers) aged 18 to 30 years, using our custom-built low-cost single-lead ECG module, and anthropometric data, e.g., body mass index, smoking status, blood pressure, etc. Under our proposed method, we first pre-process our dataset by denoising the ECG traces, followed by baseline drift removal, followed by z-score normalization. Next, we create another dataset by dividing the ECG traces into overlapping segments of five-second duration. We then feed both segmented and unsegmented datasets to a number of machine learning models, a 1D convolutional neural network, and ResNet18 model, for vascular ageing prediction. We also do transfer learning whereby we pre-train our models on a public PPG dataset, and later, fine-tune and evaluate them on our unsegmented ECG dataset. The random forest model outperforms all other models and previous works by achieving a mean squared error (MSE) of 0.07 and coefficient of determination R2 of 0.99, MSE of 3.56 and R2 of 0.26, MSE of 0.99 and R2 of 0.87, for segmented ECG dataset, for unsegmented ECG dataset, and for transfer learning scenario, respectively. Finally, we utilize the explainable AI framework to identify those ECG features that get affected due to smoking. This work is aligned with the sustainable development goals 3 and 10 of the United Nations which aim to provide low-cost but quality healthcare solutions to the unprivileged. This work also finds its applications in the broad domain of forensic science.

Evaluation of a Low-Cost Single-Lead ECG Module for Vascular Ageing Prediction and Studying Smoking-induced Changes in ECG

TL;DR

A low-cost single-lead ECG internet of thing (IoT) module is utilized to predict the vascular age of an apparently healthy young person and the explainable AI framework is utilized to identify those ECG features that get affected due to smoking.

Abstract

Vascular age is traditionally measured using invasive methods or through 12-lead electrocardiogram (ECG). This paper utilizes a low-cost single-lead (lead-I) ECG module to predict the vascular age of an apparently healthy young person. In addition, we also study the impact of smoking on ECG traces of the light-but-habitual smokers. We begin by collecting (lead-I) ECG data from 42 apparently healthy subjects (smokers and non-smokers) aged 18 to 30 years, using our custom-built low-cost single-lead ECG module, and anthropometric data, e.g., body mass index, smoking status, blood pressure, etc. Under our proposed method, we first pre-process our dataset by denoising the ECG traces, followed by baseline drift removal, followed by z-score normalization. Next, we create another dataset by dividing the ECG traces into overlapping segments of five-second duration. We then feed both segmented and unsegmented datasets to a number of machine learning models, a 1D convolutional neural network, and ResNet18 model, for vascular ageing prediction. We also do transfer learning whereby we pre-train our models on a public PPG dataset, and later, fine-tune and evaluate them on our unsegmented ECG dataset. The random forest model outperforms all other models and previous works by achieving a mean squared error (MSE) of 0.07 and coefficient of determination R2 of 0.99, MSE of 3.56 and R2 of 0.26, MSE of 0.99 and R2 of 0.87, for segmented ECG dataset, for unsegmented ECG dataset, and for transfer learning scenario, respectively. Finally, we utilize the explainable AI framework to identify those ECG features that get affected due to smoking. This work is aligned with the sustainable development goals 3 and 10 of the United Nations which aim to provide low-cost but quality healthcare solutions to the unprivileged. This work also finds its applications in the broad domain of forensic science.
Paper Structure (25 sections, 7 figures, 5 tables)

This paper contains 25 sections, 7 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Vascular ageing estimation methods
  4. Effect of smoking on ECG
  5. The Methodology and the Measurement Equipment
  6. The Proposed Framework
  7. The Low-cost Single-Lead ECG Module
  8. Data Collection, Data Pre-Processing and Feature Extraction
  9. Data Collection
  10. Data Pre-Processing
  11. Creation of 2nd Dataset via Segmentation
  12. Feature Extraction
  13. Machine, Deep and Transfer Learning Models Implemented
  14. Machine and deep learning models
  15. Transfer learning
  16. ...and 10 more sections

Figures (7)

  • Figure 1: The proposed method for vascular ageing prediction and for studying smoking-induced changes in single-lead ECG.
  • Figure 2: The three electrodes are placed such that together they form the einthoven triangle to acquire the lead I of the ECG (left subplot). The right subplot shows a snippet from our data collection campaign.
  • Figure 3: One cardiac cycle of a typical ECG signal annotated with many intervals (features) that have clinical significance.
  • Figure 4: Explainable AI based feature correlation analysis. (target variable is age).
  • Figure 5: Error Distribution of our ML, DL and TL models.
  • ...and 2 more figures