Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring

Muhammad E.H. Chowdhury, Amith Khandakar, Khawla Alzoubi, Samar Mansoor, Anas M Tahir, Md. Mamun Ibne Reaz, Nasser Al-Emadi

Research output: Contribution to journalArticle

Abstract

One of the major causes of death all over the world is heart disease or cardiac dysfunction. These diseases could be identified easily with the variations in the sound produced due to the heart activity. These sophisticated auscultations need important clinical experience and concentrated listening skills. Therefore, there is an unmet need for a portable system for the early detection of cardiac illnesses. This paper proposes a prototype model of a smart digital-stethoscope system to monitor patient's heart sounds and diagnose any abnormality in a real-time manner. This system consists of two subsystems that communicate wirelessly using Bluetooth low energy technology: A portable digital stethoscope subsystem, and a computer-based decision-making subsystem. The portable subsystem captures the heart sounds of the patient, filters and digitizes, and sends the captured heart sounds to a personal computer wirelessly to visualize the heart sounds and for further processing to make a decision if the heart sounds are normal or abnormal. Twenty-seven t-domain, f-domain, and Mel frequency cepstral coefficients (MFCC) features were used to train a public database to identify the best-performing algorithm for classifying abnormal and normal heart sound (HS). The hyper parameter optimization, along with and without a feature reduction method, was tested to improve accuracy. The cost-adjusted optimized ensemble algorithm can produce 97% and 88% accuracy of classifying abnormal and normal HS, respectively.

Original languageEnglish
JournalSensors (Basel, Switzerland)
Volume19
Issue number12
DOIs
Publication statusPublished - 20 Jun 2019

Fingerprint

stethoscopes
Stethoscopes
heart diseases
Heart Sounds
Heart Diseases
Acoustic waves
acoustics
Monitoring
classifying
Auscultation
energy technology
Microcomputers
personal computers
abnormalities
decision making
Bluetooth
Cause of Death
death
Decision Making
Personal computers

Keywords

  • digital stethoscope
  • heart diseases
  • heart sound
  • machine learning
  • Mel frequency cepstral coefficients (MFCC) features

ASJC Scopus subject areas

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering

Cite this

Chowdhury, M. E. H., Khandakar, A., Alzoubi, K., Mansoor, S., M Tahir, A., Ibne Reaz, M. M., & Al-Emadi, N. (2019). Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring. Sensors (Basel, Switzerland), 19(12). https://doi.org/10.3390/s19122781

Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring. / Chowdhury, Muhammad E.H.; Khandakar, Amith; Alzoubi, Khawla; Mansoor, Samar; M Tahir, Anas; Ibne Reaz, Md. Mamun; Al-Emadi, Nasser.

In: Sensors (Basel, Switzerland), Vol. 19, No. 12, 20.06.2019.

Research output: Contribution to journalArticle

Chowdhury, MEH, Khandakar, A, Alzoubi, K, Mansoor, S, M Tahir, A, Ibne Reaz, MM & Al-Emadi, N 2019, 'Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring', Sensors (Basel, Switzerland), vol. 19, no. 12. https://doi.org/10.3390/s19122781
Chowdhury, Muhammad E.H. ; Khandakar, Amith ; Alzoubi, Khawla ; Mansoor, Samar ; M Tahir, Anas ; Ibne Reaz, Md. Mamun ; Al-Emadi, Nasser. / Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring. In: Sensors (Basel, Switzerland). 2019 ; Vol. 19, No. 12.
@article{3e35f951b2ca4bdfa1ec54175a6133d0,
title = "Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring",
abstract = "One of the major causes of death all over the world is heart disease or cardiac dysfunction. These diseases could be identified easily with the variations in the sound produced due to the heart activity. These sophisticated auscultations need important clinical experience and concentrated listening skills. Therefore, there is an unmet need for a portable system for the early detection of cardiac illnesses. This paper proposes a prototype model of a smart digital-stethoscope system to monitor patient's heart sounds and diagnose any abnormality in a real-time manner. This system consists of two subsystems that communicate wirelessly using Bluetooth low energy technology: A portable digital stethoscope subsystem, and a computer-based decision-making subsystem. The portable subsystem captures the heart sounds of the patient, filters and digitizes, and sends the captured heart sounds to a personal computer wirelessly to visualize the heart sounds and for further processing to make a decision if the heart sounds are normal or abnormal. Twenty-seven t-domain, f-domain, and Mel frequency cepstral coefficients (MFCC) features were used to train a public database to identify the best-performing algorithm for classifying abnormal and normal heart sound (HS). The hyper parameter optimization, along with and without a feature reduction method, was tested to improve accuracy. The cost-adjusted optimized ensemble algorithm can produce 97{\%} and 88{\%} accuracy of classifying abnormal and normal HS, respectively.",
keywords = "digital stethoscope, heart diseases, heart sound, machine learning, Mel frequency cepstral coefficients (MFCC) features",
author = "Chowdhury, {Muhammad E.H.} and Amith Khandakar and Khawla Alzoubi and Samar Mansoor and {M Tahir}, Anas and {Ibne Reaz}, {Md. Mamun} and Nasser Al-Emadi",
year = "2019",
month = "6",
day = "20",
doi = "10.3390/s19122781",
language = "English",
volume = "19",
journal = "Sensors (Switzerland)",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "12",

}

TY - JOUR

T1 - Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring

AU - Chowdhury, Muhammad E.H.

AU - Khandakar, Amith

AU - Alzoubi, Khawla

AU - Mansoor, Samar

AU - M Tahir, Anas

AU - Ibne Reaz, Md. Mamun

AU - Al-Emadi, Nasser

PY - 2019/6/20

Y1 - 2019/6/20

N2 - One of the major causes of death all over the world is heart disease or cardiac dysfunction. These diseases could be identified easily with the variations in the sound produced due to the heart activity. These sophisticated auscultations need important clinical experience and concentrated listening skills. Therefore, there is an unmet need for a portable system for the early detection of cardiac illnesses. This paper proposes a prototype model of a smart digital-stethoscope system to monitor patient's heart sounds and diagnose any abnormality in a real-time manner. This system consists of two subsystems that communicate wirelessly using Bluetooth low energy technology: A portable digital stethoscope subsystem, and a computer-based decision-making subsystem. The portable subsystem captures the heart sounds of the patient, filters and digitizes, and sends the captured heart sounds to a personal computer wirelessly to visualize the heart sounds and for further processing to make a decision if the heart sounds are normal or abnormal. Twenty-seven t-domain, f-domain, and Mel frequency cepstral coefficients (MFCC) features were used to train a public database to identify the best-performing algorithm for classifying abnormal and normal heart sound (HS). The hyper parameter optimization, along with and without a feature reduction method, was tested to improve accuracy. The cost-adjusted optimized ensemble algorithm can produce 97% and 88% accuracy of classifying abnormal and normal HS, respectively.

AB - One of the major causes of death all over the world is heart disease or cardiac dysfunction. These diseases could be identified easily with the variations in the sound produced due to the heart activity. These sophisticated auscultations need important clinical experience and concentrated listening skills. Therefore, there is an unmet need for a portable system for the early detection of cardiac illnesses. This paper proposes a prototype model of a smart digital-stethoscope system to monitor patient's heart sounds and diagnose any abnormality in a real-time manner. This system consists of two subsystems that communicate wirelessly using Bluetooth low energy technology: A portable digital stethoscope subsystem, and a computer-based decision-making subsystem. The portable subsystem captures the heart sounds of the patient, filters and digitizes, and sends the captured heart sounds to a personal computer wirelessly to visualize the heart sounds and for further processing to make a decision if the heart sounds are normal or abnormal. Twenty-seven t-domain, f-domain, and Mel frequency cepstral coefficients (MFCC) features were used to train a public database to identify the best-performing algorithm for classifying abnormal and normal heart sound (HS). The hyper parameter optimization, along with and without a feature reduction method, was tested to improve accuracy. The cost-adjusted optimized ensemble algorithm can produce 97% and 88% accuracy of classifying abnormal and normal HS, respectively.

KW - digital stethoscope

KW - heart diseases

KW - heart sound

KW - machine learning

KW - Mel frequency cepstral coefficients (MFCC) features

UR - http://www.scopus.com/inward/record.url?scp=85068575583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068575583&partnerID=8YFLogxK

U2 - 10.3390/s19122781

DO - 10.3390/s19122781

M3 - Article

VL - 19

JO - Sensors (Switzerland)

JF - Sensors (Switzerland)

SN - 1424-8220

IS - 12

ER -