Related Experiment Video
Updated: Jul 26, 2026
Author Spotlight: Advancements in Multiplex Detection of Respiratory Viruses
Published on: November 10, 2023
Detecting acute respiratory diseases in the pediatric population using cough sound features and machine learning: A
Roneel V Sharan1, Hania Rahimi-Ardabili1
1Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, Australia.
Insights
Machine learning algorithms show promise in analyzing pediatric cough sounds for diagnosing acute respiratory diseases. This technology could improve diagnostic accuracy beyond human perception.
Area of Science:
- Pediatric respiratory medicine
- Artificial intelligence in healthcare
- Machine learning for diagnostics
Background:
- Acute respiratory diseases are a major cause of illness and death in children.
- Cough sounds can indicate specific respiratory conditions, but clinical assessment relies on subjective human perception.
- Objective analysis of cough sounds using AI offers potential for improved diagnosis.
Approach:
- A systematic review was conducted using Scopus, Medline, and Embase databases.
- Six studies met inclusion criteria, with quality assessed using a medical AI checklist.
- Machine learning algorithms, including deep learning, were analyzed for their ability to classify cough sounds.
Key Points:
- Algorithms utilized diverse cough sound features, sometimes combined with clinical data.
- Classification accuracy for common childhood respiratory illnesses ranged from 82-96% in most studies.
- Variability in input features and algorithms impacted diagnostic performance.
Conclusions:
- While the number of studies is limited, AI-powered cough sound analysis shows potential for diagnosing pediatric acute respiratory diseases.
- Further research is needed to refine algorithms and validate their predictive capabilities.
- This approach may enhance clinical decision-making for childhood respiratory conditions.
Background:
Acute respiratory diseases are a leading cause of morbidity and mortality in children. Cough is a common symptom of acute respiratory diseases and the sound of cough can be indicative of the respiratory disease. However, cough sound assessment in routine clinical practice is limited to human perception and the skills of the clinician. Objective cough sound evaluation has the potential to aid clinicians in acute respiratory disease diagnosis. In this systematic review, we assess and summarize the predictive ability of machine learning algorithms in analyzing cough sounds of acute respiratory diseases in the pediatric population.
Method:
Our systematic search of the Scopus, Medline, and Embase databases on 25 January 2023 identified six articles meeting the inclusion criteria. Quality assessment of the included studies was performed using the checklist for the assessment of medical artificial intelligence.
Results:
Our analysis shows variability in the input to the machine learning algorithms, such as the use of various cough sound features and combining cough sound features with clinical features. The use of the machine learning algorithms also varies from conventional algorithms, such as logistic regression and support vector machine, to deep learning techniques, such as convolutional neural networks. The classification accuracy for the detection of bronchiolitis, croup, pertussis, and pneumonia across five articles is in the range of 82-96%. However, a significant drop is observed in the detection accuracy for bronchiolitis and pneumonia in the remaining article.
Conclusion:
The number of articles is limited but, in general, the predictive ability of cough sound classification algorithms in childhood acute respiratory diseases shows promise.
Related Concept Videos
01:23Assessment of Respiration
Subjective Assessment: Nurses interview the patient to gather information directly during the subjective assessment. It includes questions about the individual's medical history, medications, and symptoms, focusing on past respiratory conditions like asthma or COPD,...
01:31Common 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,...
01:28Physical Assessment of the Respiratory Tract IV: Auscultation
Breath Sounds
Breath sounds are categorized into vesicular, bronchovesicular, and bronchial.
01:30Respiratory System Abnormal Finding I: Inspection and Percussion
Inspection Findings
During an inspection, several findings may suggest the presence of respiratory distress or disease. Pursed-lip breathing, where exhalation is slowed by...
01:31Respiratory System Abnormal Finding II: Palpation and Auscultation
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities:
01:29Respiratory Syncytial Virus Disease