Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
September 19th, 2025
This study effectively accomplished the automated classification of two distinct categories by acquiring cough sound data from patients diagnosed with chronic obstructive pulmonary disease (COPD) and respiratory tract infections (RTI), utilizing an integration of speech signal processing techniques and machine learning algorithms.
This research focuses on acoustic diagnostics, utilizing voice signal analysis and machine learning to extract distinctive voice features for non-invasive early classification of chronic obstructive pulmonary disease and respiratory tract infections. The recent developments in this field include AI-driven voice analysis, machine learning techniques such as convolutional neural networks and support vector machines, signal processing tools like MFCCs, and variable acoustic sensors for detecting disease-related patterns in sound signals. One of the main challenges in the clinical translation of voice-based diagnostic is data scarcity.
Other challenges include limited model generalization, privacy ethics, conflicts, and barriers to interpretability. After assembling the vocal feature indicator database, open SPSS and load the appropriate data file. From the menu bar, select Analyze, then choose Nonparametric Tests, followed by Legacy Dialogues, and click on 2 Independent Samples.
In the pop-up dialogue box, select the observed variables to be compared under the Test Variable List section. Then, under Grouping Variable, select the variable that will be used for grouping. Click the Define Groups button and enter the identifiers for the two groups in the pop-up window.
Under Test Type, select the Mann-Whitney U test. Click OK to run the test and allow SPSS to automatically generate the output. For principal component analysis, ensure that the data is collated, saved in Excel or CSV format, and imported into SPSS version 20.0.
To open the file, select File, then choose Open, followed by Data, and select the appropriate file. To initiate principal component analysis, click Analyze, then choose Dimension Reduction, and select Factor. In the dialogue box, add all continuous variables used in principal component analysis into the Variables field.
Click the Extraction button and select the Principal components method as the extraction technique. Select Eigenvalues greater than 1 as the criterion for retaining principal components. Select the rotation method and click Rotation to choose either Varimax or Promax.
Under Options, check both Scree plot and Coefficient matrix to include the gravel diagram and the matrix of coefficients in the output for evaluating retained variants. After completing all the settings, click OK to execute the analysis and allow SPSS to generate the output. Interpret the principal component loading matrix to assess the relationship between the principal components and the original variables.
Identify variables with higher loading values, as these contribute more significantly to component changes. Use the Total Variance Explained table to evaluate how much variance each principal component accounts for. Identify the principal components with large variance proportions, as they typically capture most of the data variation.
Refer to the scree plot to determine which components to retain. Locate the inflection point and keep all components to the left of this point. If principal component scores are required, check Save as variables before running the analysis.
SPSS will add the scores for each sample as new variables in the dataset. Principal component analysis identified six major components which together accounted for 76.8%of the total variance. The logistic regression model demonstrated stable performance across three validation folds, with AUC values of 0.71, 0.74, and 0.88, yielding a mean AUC of 0.77.
In contrast, the random forest model exhibited greater variability, with fold AUC scores of 0.69, 0.52, and 0.83, and a lower mean AUC of 0.68. The logistic regression model achieved 100%correct predictions for COPD and six out of seven correct for respiratory tract infections, as shown in the confusion matrix, indicating high classification accuracy. The random forest model misclassified one COPD and two respiratory tract infection cases, resulting in lower classification accuracy compared to the logistic regression model.
On the test dataset, the logistic regression model yielded excellent classification performance, achieving an AUC value of 0.95. The random forest model showed lower test performance with an AUC value of 0.76.
View the full transcript and gain access to thousands of scientific videos
Overview
This research focuses on acoustic diagnostics, utilizing voice signal analysis and machine learning to extract distinctive voice features for non-invasive early classification of chronic obstructive pulmonary disease and respiratory tract infections. The study highlights the integration of advanced techniques in speech signal processing and machine learning algorithms.
Key Study Components
Area of Science
- Neuroscience
- Machine Learning
- Acoustic Diagnostics
Background
- Utilization of voice signal analysis for disease classification.
- Challenges in clinical translation due to data scarcity and model generalization.
- Ethical considerations regarding privacy and interpretability.
- Recent advancements in AI-driven voice analysis.
Purpose of Study
- To automate the classification of COPD and RTI using cough sound data.
- To explore the effectiveness of machine learning techniques in acoustic diagnostics.
- To address challenges in implementing voice-based diagnostics in clinical settings.
Methods Used
- Acquisition of cough sound data from patients.
- Application of machine learning algorithms such as convolutional neural networks and support vector machines.
- Use of signal processing tools like MFCCs.
- Development of a vocal feature indicator database.
Main Results
- Successful classification of distinct categories of cough sounds.
- Identification of disease-related patterns in sound signals.
- Insights into the effectiveness of AI in early diagnosis.
- Discussion of challenges faced in data interpretation and model generalization.
Conclusions
- The study demonstrates the potential of voice analysis in diagnosing respiratory diseases.
- Highlights the need for addressing data scarcity and ethical issues.
- Encourages further research into machine learning applications in healthcare.
Frequently Asked Questions
Executive Industry Relevance
Machine learning-based cough tone classification offers a non-invasive, data-driven approach for differentiating chronic obstructive pulmonary disease (COPD) from respiratory tract infections (RTI), addressing a critical diagnostic inflection point in respiratory disease management. By leveraging quantitative voice feature analysis and robust statistical validation, this workflow enhances predictive confidence and supports risk-adjusted triage in early discovery and translational research. The approach demonstrates enterprise value by enabling scalable, reproducible, and interpretable diagnostics that can be integrated into broader R&D pipelines.
Strategic Applications in Biopharma R&D
Early Discovery & Target Validation
- Enables interrogation of disease-specific acoustic biomarkers for mechanistic de-risking.
- Supports functional target validation through statistically significant voice feature differentiation.
- Facilitates portfolio triage by providing quantitative evidence for disease classification.
Screening & Assay Development
- Prepares validated voice feature datasets for downstream machine learning model development.
- Standardizes feature extraction and statistical testing for reproducible assay outputs.
- Enables scalable screening of patient-derived acoustic data for model training and evaluation.
Translational & Preclinical Research
- Aligns acoustic biomarkers with disease-relevant phenotypes for translational continuity.
- Supports risk-adjusted advancement by quantifying model performance across validation folds.
- Provides a foundation for integrating non-invasive diagnostics into preclinical workflows.
Pipeline & Workflow Integration
This method bridges early discovery and translational research by transforming raw acoustic data into validated, quantitative features for machine learning-based disease classification.
- Discovery Biology: Facilitates hypothesis testing and pathway clarification through statistical analysis of voice features.
- Screening: Delivers reproducible, quantitative outputs for model training and evaluation.
- Analytics: Provides AUC, confusion matrix, and principal component outputs for robust model comparison.
- Translational Research: Connects non-invasive biomarker discovery to preclinical validation of diagnostic tools.
- Enterprise Reuse: Establishes a scalable workflow for future respiratory disease classification initiatives.
Operational & Enterprise Impact
- Scientific Value: Increases predictive confidence and reduces mechanistic ambiguity in respiratory disease differentiation.
- Operational Value: Standardizes feature extraction, statistical testing, and model evaluation for reproducibility.
- Strategic Value: Enables data-driven go/no-go decisions and capital-efficient diagnostic development.
- Portfolio Impact: Supports risk-adjusted prioritization of diagnostic candidates and workflow scalability.
Implementation Considerations
- Requires expertise in acoustic signal processing and statistical analysis.
- Needs access to machine learning infrastructure and SPSS for data analysis.
- Demands standardized data collection and feature extraction protocols across teams.
- Must address model generalization and interpretability for broader application.
- Limited by data scarcity and privacy considerations in patient-derived datasets.
