Fig 1.
The workflow of feature categorization according to frequency, intensity, and mixed groups.
Table 1.
List of cough sound features subjected to analysis.
Table 2.
Baseline characteristics of whole ALS patient’s population (n = 60), and controls (N = 40).
Fig 2.
Support vector machine (SVM) analysis of all cough sound samples.
Receiver operating characteristic curves (ROC) were calculated with a SVM to differentiate ALS patients and controls for the three different groups of cough sound features. One of the five model’s iterations is demonstrated (settings: k_features = ‘best’; forward = ‘False’; scoring = ‘accuracy’; cv = ‘5’; random_state = ‘41’).
Fig 3.
An example of the analysis of sound waves in voluntary coughing of a healthy control (upper row) and an ALS patient (lower row).
Each column of the image depicts different features of the three distinct groups of features. The first column highlights the frequency features associated with the repetition rate of one event, such as the number of times that the signal passes the zero line or the number of positive turning points. The second column emphasizes the intensity features, such as the signal amplitude or peak distance. Lastly, the third column shows features that provide information on both frequency and intensity, such as the signal power and entropy. The main differences were observed in the frequency group. To note that these cough signals did not undergo pre-processing procedures.
Table 3.
F values from regression analyses contributing of control vs. ALS classification to performance on each voice sound variable.
Fig 4.
Analysis of sound waves in voluntary coughing: Comparison between patients in different disease states.
The left image represents the cough sound of one patient in a better functional state (Female; 60> years old; ALSFRS-R total score of 39) versus the right image, which represents the cough sound of one patient in a worse functional state (Female; 60> years old; ALSFRS-R total score of 20). The main differences are presented in the intensity-related group of features. (Signal without pre-processing).
Table 4.
Correlations between the ALSFRS-R total score and different cough sound features.
Results are adjusted for age and gender.
Table 5.
F values from regression analyses contributing of with respiratory vs. without respiratory dysfunction classification to performance on each voice sound variable.
Table 6.
Correlations between the FVC (%), MIP (%), MEP (%), and CPF (L/min), and different cough sound features.
Table 7.
F values from regression analyses contributing of with bulbar vs. without bulbar dysfunction classification to performance on each voice sound variable.
Table 8.
Classification results based on the different groups of cough sound features.
Only the highest sensitivity and specificity scores from the best random seeds are presented.
Table 9.
Summary of all correlations undertaken in this study.
The symbol ‘*’ denotes statistical significance, α = 0.05 was considered. The ‘+’ and ‘-‘ symbols indicate positive and negative associations, respectively, between related sound analysis features clinical variable. This pertains to the classification of controls vs. ALS patients; patients with bulbar symptoms vs. without; patients with respiratory symptoms vs. without.