The automatic recognition and counting of cough
Samantha J Barry1, Adrie D Dane, Alyn H Morice
1Department of Chemistry, Faculty of Science and the Environment, University of Hull, Cottingham Road, Hull, HU6 7RX, UK. s.j.barry@chem.hull.ac.uk
A new automated system, the Hull Automatic Cough Counter (HACC), accurately counts coughs in audio recordings. This significantly reduces analysis time, making cough frequency studies more efficient.
Area of Science:
- Medical Technology
- Digital Signal Processing
- Artificial Intelligence in Healthcare
Background:
- Traditional cough analysis is time-consuming and problematic due to the episodic nature of coughs.
- Manual analysis of prolonged cough recordings requires extensive real-time aural assessment.
- A need exists for automated methods to quantify cough frequency and temporal patterns.
Purpose of the Study:
- To develop and validate an automated system for recognizing and counting cough events in digital audio recordings.
- To assess the accuracy, efficiency, and reproducibility of the automated cough counting method.
Main Methods:
- The Hull Automatic Cough Counter (HACC) program utilizes digital signal processing (DSP) and a probabilistic neural network (PNN).
- HACC analyzes spectral coefficients of sound events to classify them as cough or non-cough.
- The system was tested on audio recordings from 33 subjects with chronic cough.
Main Results:
- HACC significantly reduced manual counting time by 97.5%, with an average analysis time of 1 minute 35 seconds per hour recording.
- The system demonstrated a sensitivity of 80% and a specificity of 96% for cough detection.
- Reproducibility of HACC analysis was found to be 100%.
Conclusions:
- An automated system for cough event analysis has been successfully developed.
- The Hull Automatic Cough Counter (HACC) offers high robustness and accuracy in quantifying coughs.
- This automated approach streamlines the analysis of cough frequency and temporal relationships.
Related Concept Videos
Respiratory Assessment: Purpose and Indications
Objectives and Importance:
The primary goal of respiratory assessment is to evaluate patients at early risk of clinical deterioration. Since respiratory distress often precedes other signs of declining health, breathing patterns and sounds become a...
Respiratory System Abnormal Finding II: Palpation and Auscultation
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities:
Common Respiratory Disorders
Upper respiratory disorders impact the airways above the vocal cords, encompassing areas like the nose, sinuses, and throat. Various conditions fall under this category, including the common cold and allergic rhinitis. These disorders can stem from several causes,...
Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
Physical Assessment of the Respiratory Tract II: Palpation
Thoracic Palpation
Thoracic palpation detects tenderness, masses, lesions, respiratory excursions, and vocal fremitus. The nurse assesses...
Cardiopulmonary Resuscitation II: ACLS Airway Management


