Clinical informatics: Mining of pathological data by acoustic analysis

Zulfiqar Ali, Mansour Alsulaiman, Ghulam Muhammad, Ahmed Al-Nasheri, Awais Mahmood

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Data mining has a great potential in different areas of health informatics. Data mining in health industry can minimize the health cost as well as reduces the risk of life by informing a person at initial stage. An automatic classification system capable of mining pathological data may contribute in health informatics significantly. In this paper, an automatic system to differentiate between pathological and normal data is developed. The developed system mines the pathological data on the basis of an acoustic analysis. The purpose of the acoustic analysis is to estimate the auditory spectrum of a voice sample by using the principle of the human auditory system called as critical bandwidths. The estimated auditory spectrum simulates the behavior of a human ear and acts like an expert clinician who can identify a pathological voice by hearing. The pathological data used for this study is recorded from the people who are suffering from more than 100 different types of voice disorders. Voice of a disordered patient feels noisy, harsh, strain, breathy and unpleasant to ears. During the training phase of the proposed system, it takes labeled normal and pathological data to generate acoustic models by using the Gaussian mixture model. While in deployment phase, an unknown and unlabeled voice sample is given to the system to determine its type, i.e. normal or pathological. The best obtained accuracy of the system is 99.50%.

Conference

Conference2017 International Conference on Informatics, Health and Technology, ICIHT 2017
CountrySaudi Arabia
CityRiyadh
Period21/02/1723/02/17

Fingerprint

Medical Informatics
Acoustics
Data Mining
Informatics
Health
Data mining
Ear
Voice Disorders
Health Care Costs
Hearing
Audition
Industry
Bandwidth
Costs

Keywords

  • auditory spectrum
  • clinical data
  • data mining
  • Gaussian mixture model
  • Health informatics

Cite this

Ali, Z., Alsulaiman, M., Muhammad, G., Al-Nasheri, A., & Mahmood, A. (2017). Clinical informatics: Mining of pathological data by acoustic analysis. 1-8. Paper presented at 2017 International Conference on Informatics, Health and Technology, ICIHT 2017, Riyadh, Saudi Arabia. https://doi.org/10.1109/ICIHT.2017.7899136
Ali, Zulfiqar ; Alsulaiman, Mansour ; Muhammad, Ghulam ; Al-Nasheri, Ahmed ; Mahmood, Awais. / Clinical informatics : Mining of pathological data by acoustic analysis. Paper presented at 2017 International Conference on Informatics, Health and Technology, ICIHT 2017, Riyadh, Saudi Arabia.8 p.
@conference{e41891a8f0fc4ad9ad2b4563fe85b2d3,
title = "Clinical informatics: Mining of pathological data by acoustic analysis",
abstract = "Data mining has a great potential in different areas of health informatics. Data mining in health industry can minimize the health cost as well as reduces the risk of life by informing a person at initial stage. An automatic classification system capable of mining pathological data may contribute in health informatics significantly. In this paper, an automatic system to differentiate between pathological and normal data is developed. The developed system mines the pathological data on the basis of an acoustic analysis. The purpose of the acoustic analysis is to estimate the auditory spectrum of a voice sample by using the principle of the human auditory system called as critical bandwidths. The estimated auditory spectrum simulates the behavior of a human ear and acts like an expert clinician who can identify a pathological voice by hearing. The pathological data used for this study is recorded from the people who are suffering from more than 100 different types of voice disorders. Voice of a disordered patient feels noisy, harsh, strain, breathy and unpleasant to ears. During the training phase of the proposed system, it takes labeled normal and pathological data to generate acoustic models by using the Gaussian mixture model. While in deployment phase, an unknown and unlabeled voice sample is given to the system to determine its type, i.e. normal or pathological. The best obtained accuracy of the system is 99.50{\%}.",
keywords = "auditory spectrum, clinical data, data mining, Gaussian mixture model, Health informatics",
author = "Zulfiqar Ali and Mansour Alsulaiman and Ghulam Muhammad and Ahmed Al-Nasheri and Awais Mahmood",
year = "2017",
month = "4",
day = "13",
doi = "10.1109/ICIHT.2017.7899136",
language = "English",
pages = "1--8",
note = "2017 International Conference on Informatics, Health and Technology, ICIHT 2017 ; Conference date: 21-02-2017 Through 23-02-2017",

}

Ali, Z, Alsulaiman, M, Muhammad, G, Al-Nasheri, A & Mahmood, A 2017, 'Clinical informatics: Mining of pathological data by acoustic analysis' Paper presented at 2017 International Conference on Informatics, Health and Technology, ICIHT 2017, Riyadh, Saudi Arabia, 21/02/17 - 23/02/17, pp. 1-8. https://doi.org/10.1109/ICIHT.2017.7899136

Clinical informatics : Mining of pathological data by acoustic analysis. / Ali, Zulfiqar; Alsulaiman, Mansour; Muhammad, Ghulam; Al-Nasheri, Ahmed; Mahmood, Awais.

2017. 1-8 Paper presented at 2017 International Conference on Informatics, Health and Technology, ICIHT 2017, Riyadh, Saudi Arabia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Clinical informatics

T2 - Mining of pathological data by acoustic analysis

AU - Ali, Zulfiqar

AU - Alsulaiman, Mansour

AU - Muhammad, Ghulam

AU - Al-Nasheri, Ahmed

AU - Mahmood, Awais

PY - 2017/4/13

Y1 - 2017/4/13

N2 - Data mining has a great potential in different areas of health informatics. Data mining in health industry can minimize the health cost as well as reduces the risk of life by informing a person at initial stage. An automatic classification system capable of mining pathological data may contribute in health informatics significantly. In this paper, an automatic system to differentiate between pathological and normal data is developed. The developed system mines the pathological data on the basis of an acoustic analysis. The purpose of the acoustic analysis is to estimate the auditory spectrum of a voice sample by using the principle of the human auditory system called as critical bandwidths. The estimated auditory spectrum simulates the behavior of a human ear and acts like an expert clinician who can identify a pathological voice by hearing. The pathological data used for this study is recorded from the people who are suffering from more than 100 different types of voice disorders. Voice of a disordered patient feels noisy, harsh, strain, breathy and unpleasant to ears. During the training phase of the proposed system, it takes labeled normal and pathological data to generate acoustic models by using the Gaussian mixture model. While in deployment phase, an unknown and unlabeled voice sample is given to the system to determine its type, i.e. normal or pathological. The best obtained accuracy of the system is 99.50%.

AB - Data mining has a great potential in different areas of health informatics. Data mining in health industry can minimize the health cost as well as reduces the risk of life by informing a person at initial stage. An automatic classification system capable of mining pathological data may contribute in health informatics significantly. In this paper, an automatic system to differentiate between pathological and normal data is developed. The developed system mines the pathological data on the basis of an acoustic analysis. The purpose of the acoustic analysis is to estimate the auditory spectrum of a voice sample by using the principle of the human auditory system called as critical bandwidths. The estimated auditory spectrum simulates the behavior of a human ear and acts like an expert clinician who can identify a pathological voice by hearing. The pathological data used for this study is recorded from the people who are suffering from more than 100 different types of voice disorders. Voice of a disordered patient feels noisy, harsh, strain, breathy and unpleasant to ears. During the training phase of the proposed system, it takes labeled normal and pathological data to generate acoustic models by using the Gaussian mixture model. While in deployment phase, an unknown and unlabeled voice sample is given to the system to determine its type, i.e. normal or pathological. The best obtained accuracy of the system is 99.50%.

KW - auditory spectrum

KW - clinical data

KW - data mining

KW - Gaussian mixture model

KW - Health informatics

UR - http://www.scopus.com/inward/record.url?scp=85019171085&partnerID=8YFLogxK

U2 - 10.1109/ICIHT.2017.7899136

DO - 10.1109/ICIHT.2017.7899136

M3 - Paper

SP - 1

EP - 8

ER -

Ali Z, Alsulaiman M, Muhammad G, Al-Nasheri A, Mahmood A. Clinical informatics: Mining of pathological data by acoustic analysis. 2017. Paper presented at 2017 International Conference on Informatics, Health and Technology, ICIHT 2017, Riyadh, Saudi Arabia. https://doi.org/10.1109/ICIHT.2017.7899136