Early Screening and Monitoring of Heart Diseases based on the Fusion of Electrical and Mechanical Sensors: (HEART)

Home Early Screening and Monitoring of Heart Diseases based on the Fusion of Electrical and Mechanical Sensors: (HEART)

Early Screening and Monitoring of Heart Diseases based on the Fusion of Electrical and Mechanical Sensors: (HEART), PI: Mohamed Trabelsi, Funder: KFAS, Award Amount: 9000 KWD, Start: Jan 2021, End: July 2023

Funded by KFAS

Dr. Mohamed Trabelsi
Jan 2021

Award Amount: 
9000 KWD
PI: Dr. Mohamed Trabelsi

Start date: Jan 2021
End date: July 2023
Status: Completed

Research Theme: 

  • Biomedical Engineering
  • Internet of Things (IoT), Sensors, and Networking 
  • Artificial Intelligence (AI) and Robotics

Impact (SDG): 
Good health and well-being (SDG3)

Collaborators:

  • Prof. Mohamed Trabelsi, Lead PI, Kuwait College of Science and Technology, Kuwait
  • Dr. Ernest Kamavuako, Co-PI, Department of Engineering, King’s College London, United Kingdom
  • Dr. Ines CHIHI, Consultant, University of Luxembourg, Luxembourg

Description:

Cardiovascular diseases (CVDs) are the leading cause of death worldwide. In Kuwait, coronary heart disease is the major cause of mortality (30% of deaths) and CVDs are estimated to cause 46.0% of all mortalities. Adequate knowledge about CVD risk factors among individuals will help decrease their risk since many risk factors are adjustable and thus if the disease is screened and detected early, its progression can be controlled and thus prevent death. It is well-known that the detection of structural CVD depends highly on the ability of the physician to listen to cardiac murmurs, phonocardiogram (PCG) and rhythmic CVD on the electrocardiogram (ECG), before the patient is referred to a specialized ward for further investigations (imaging), which can be costly. Nevertheless, current research on low-cost devices has mainly focused on using one signal modality creating a gap in methods for early screening of CVDs. Thus, the overarching aim of this project is to initially design a world-first wearable system for early detection and monitoring of CVDs (HEART) using multiple PCG and ECG sensors coupled with advanced detection algorithms. The scientific method consists of a software part, which focuses on a hybrid approach that combines classical machine learning, deep learning, and mathematical modeling. The hardware part uses a user co-creation approach to assess the system usability and acceptance that will guide the creation of the design. The expected outcome of the project is the delivery of robust and reliable methods for CVD screening, detection, and monitoring together with circuit design and sensor identification. We expect that impact activities with users and stakeholders will help increase awareness for the benefit of the general population and public health with long-term reduction in cost.

Outcome publications: 

  1. Ghada Ben Othman, Atal Anil Kumar, Faten Ben Hassine, Dana Copot, Lilia Sidhom, Ernest N. Kamavuako, Mohamed Trabelsi, Clara Mihaela Ionescu, Inès Chihi, Sustainability and predictive accuracy evaluation of gel and embroidered electrodes for ECG monitoring, Biomedical Signal Processing and Control, Volume 96, Part A, 2024, https://doi.org/10.1016/j.bspc.2024.106632.
  2. Xinqi Bao, Yujia Xu, Hak-Keung Lam, Mohamed Trabelsi, Ines Chihi, Lilia Sidhom, Ernest N. Kamavuako, Time-Frequency distributions of heart sound signals: A Comparative study using convolutional neural networks, Biomedical Engineering Advances, Volume 5, 2023, 100093, ISSN 2667-0992, https://doi.org/10.1016/j.bea.2023.100093.
  3. Sidhom, L.; Chihi, I.; Barhoumi, M.; Ben Afia, N.; Kamavuako, E.N.; Trabelsi, M. Smart ECG Biosensor Design with an Improved ANN Performance Based on the Taguchi Optimizer. Bioengineering 2022, 9, 482. https://www.mdpi.com/2306-5354/9/9/482.
  4. G. Ben Othman, L. Sidhom, I. Chihi, E. Kamavuako, M. Trabelsi, "ECG Data Forecasting Based on Linear Models Approach: a Comparative Study," 2023 20th International Multi-Conference on Systems, Signals & Devices (SSD), Mahdia, Tunisia, 2023, pp. 339-344, doi: 10.1109/SSD58187.2023.10411269.
  5. X. Bao, F. Hu, Y. Xu, M. Trabelsi, and E. Kamavuako, “Paroxysmal Atrial Fibrillation Detection by Combined Recurrent Neural Network and Feature Extraction on ECG Signals”, International Conference on Bio-inspired Systems and Signal Processing, Biosignals 2022, February 2022, DOI:10.5220/0010987300003123.