Detecting paroxysmal coughing from pertussis cases using voice recognition technology

Danny Parker; Joseph Picone; Amir Harati; Shuang Lu; Marion H Jenkyns; Philip M Polgreen

doi:10.1371/journal.pone.0082971

Back

Detecting paroxysmal coughing from pertussis cases using voice recognition technology

Journal article

Open access

Peer reviewed

Detecting paroxysmal coughing from pertussis cases using voice recognition technology

Danny Parker, Joseph Picone, Amir Harati, Shuang Lu, Marion H Jenkyns and Philip M Polgreen

PloS one, Vol.8(12), pp.e82971-e82971

2013

DOI: 10.1371/journal.pone.0082971

PMCID: PMC3876998

PMID: 24391730

Files and links (1)

url

https://doi.org/10.1371/journal.pone.0082971View

Published (Version of record) Open Access

Abstract

Pertussis is highly contagious; thus, prompt identification of cases is essential to control outbreaks. Clinicians experienced with the disease can easily identify classic cases, where patients have bursts of rapid coughing followed by gasps, and a characteristic whooping sound. However, many clinicians have never seen a case, and thus may miss initial cases during an outbreak. The purpose of this project was to use voice-recognition software to distinguish pertussis coughs from croup and other coughs. We collected a series of recordings representing pertussis, croup and miscellaneous coughing by children. We manually categorized coughs as either pertussis or non-pertussis, and extracted features for each category. We used Mel-frequency cepstral coefficients (MFCC), a sampling rate of 16 KHz, a frame Duration of 25 msec, and a frame rate of 10 msec. The coughs were filtered. Each cough was divided into 3 sections of proportion 3-4-3. The average of the 13 MFCCs for each section was computed and made into a 39-element feature vector used for the classification. We used the following machine learning algorithms: Neural Networks, K-Nearest Neighbor (KNN), and a 200 tree Random Forest (RF). Data were reserved for cross-validation of the KNN and RF. The Neural Network was trained 100 times, and the averaged results are presented. After categorization, we had 16 examples of non-pertussis coughs and 31 examples of pertussis coughs. Over 90% of all pertussis coughs were properly classified as pertussis. The error rates were: Type I errors of 7%, 12%, and 25% and Type II errors of 8%, 0%, and 0%, using the Neural Network, Random Forest, and KNN, respectively. Our results suggest that we can build a robust classifier to assist clinicians and the public to help identify pertussis cases in children presenting with typical symptoms.

Acoustics

Algorithms

Artificial Intelligence

Child

Cough - diagnosis

Cough - physiopathology

Diagnosis, Computer-Assisted - methods

Diagnosis, Differential

Humans

Neural Networks, Computer

Speech Recognition Software

Whooping Cough - diagnosis

Whooping Cough - physiopathology

Details

Title: Subtitle: Detecting paroxysmal coughing from pertussis cases using voice recognition technology
Creators: Danny Parker - GTD Unlimited (United States)
Joseph Picone - Temple University
Amir Harati - Temple University
Shuang Lu - Temple University
Marion H Jenkyns - Jenkyns Oxford High School, Oxford, United Kindgom.
Philip M Polgreen - University of Iowa
Resource Type: Journal article
Publication Details: PloS one, Vol.8(12), pp.e82971-e82971
DOI: 10.1371/journal.pone.0082971
PMID: 24391730
PMCID: PMC3876998
NLM abbreviation: PLoS One
ISSN: 1932-6203
eISSN: 1932-6203
Grant note: K01 AI75089 / NIAID NIH HHS K01 AI075089 / NIAID NIH HHS
Language: English
Date published: 2013
Academic Unit: Infectious Diseases; Epidemiology; Injury Prevention Research Center; Internal Medicine
Record Identifier: 9984360055102771

Metrics

11 Record Views

20 Times Cited - Web of Science

See more details