Lung Function Estimation from a Monosyllabic Voice Segment Captured Using Smartphones

Saleheen, Nazir; Ahmed, Tousif; Rahman, Mahbubur; Nemati, Eghlim; Nathan, Viswam; Vatanparvar, Korosh; Blackstock, Erin; Kuang, Jilong

doi:10.1145/3379503.3403543

Cited by 9 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Saleheen et al extracted the "A-vowel" segments from the voice sound and then extracted features from the 'A-vowel' sounds and predicted lung function in terms of the FEV1/FVC ratio. 18 Due to the lack of the FVC values in this study, the results are not directly comparable. Chun et al developed models to predict lung function in terms of the FEV1/FVC ratio and FEV1%.…”

Section: Normal Vs Abnormal Lung Function Prediction (Model3)mentioning

confidence: 79%

See 1 more Smart Citation

Predicting pulmonary function from the analysis of voice: a machine learning approach

Alam

Billantino

et al. 2021

Preprint

View full text Add to dashboard Cite

Providing proper timely treatment of asthma, self-monitoring can play a vital role in disease control. Existing methods (such as peak flow meter, smart spirometer) requires special equipment and are not always used by the patient. Using voice recording as surrogate measures of lung function can be used to assess asthma, which has good potential to self-monitor asthma and could be integrated into telehealth platforms. This study aims to apply machine learning approach to predict lung functions from recorded voice for asthma patients. A threshold-based mechanism was designed to separate speech and breathing from recordings (323 recordings from 26 participants) and features extracted from these were combined with biological attributes and lung function (percentage predicted forced expiratory volume in 1 second, FEV1%). Three predictive models were developed: (a) regression models to predict lung function, (b) multi-class classification models to predict the severity, and (c) binary classification models to predict abnormality. Random Forest (RF), Support Vector Machine (SVM), and Linear Regression (LR) algorithms were implemented to develop these predictive models. Training and test samples were separated (70%:30% using balanced portioning). Features were normalised and 10-fold cross-validation used to measure the model's training performances on the training samples. Models were then run on the test samples to measure the final performances. The RF based regression model performed better with lowest root mean square error = 10.86, and mean absolute score = 11.47, as compared to other models. In predicting the severity of lung function, the SVM based model performed better with 73.20% accuracy. The RF based model performed better in binary classification models for predicting abnormality of lung function (accuracy = 0.85, F1-score = 0.84, and area under the receiver operating characteristic curve = 0.88). The proposed machine learning approach can predict lung function (in terms of FEV1%), from the recorded voice files, better than other published approaches. These models can be extended to predict both the severity and abnormality of lung function with reasonable accuracies. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

show abstract

Section: Normal Vs Abnormal Lung Function Prediction (Model3)mentioning

confidence: 79%

“…Saleheen et al proposed a convenient mobile-based approach that utilises a monosyllabic voice segment called A-vowel' sound or 'Aaaa...' sound from voice to estimate lung function. 18 Chun et. al.…”

Section: Introductionmentioning

confidence: 99%

Predicting pulmonary function from the analysis of voice: a machine learning approach

Alam

Billantino

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Only two recent studies have used voice sounds to predict lung function. Saleheen et al extracted the “A-vowel” segments from the voice sound and then extracted features from the ‘A-vowel' sounds and predicted lung function in terms of the FEV 1 /FVC ratio ( 18 ). Due to the unavailability of FVC values in this study, it is not possible to directly compare results.…”

Section: Discussionmentioning

confidence: 99%

“…To date, only two studies have utilised machine learning techniques to predict lung function from the recorded voice. Saleheen et al proposed a convenient mobile-based approach that utilises a monosyllabic voice segment called “A-vowel” sound or “Aaaa…” sound from voice to estimate lung function ( 18 ). Chun et al proposed two algorithms for passive assessment of pulmonary conditions: one for detection of obstructive pulmonary disease and the other for estimation of the pulmonary function in terms of ratio of forced expiratory volume in 1 s (FEV 1 ) and forced vital capacity (FVC) also denoted as FEV 1 /FVC and percentage predicted FEV 1 (FEV 1 %) ( 19 ).…”

Section: Introductionmentioning

confidence: 99%

Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach

Alam

Brillantino

et al. 2022

Front. Digit. Health

View full text Add to dashboard Cite

IntroductionTo self-monitor asthma symptoms, existing methods (e.g. peak flow metre, smart spirometer) require special equipment and are not always used by the patients. Voice recording has the potential to generate surrogate measures of lung function and this study aims to apply machine learning approaches to predict lung function and severity of abnormal lung function from recorded voice for asthma patients.MethodsA threshold-based mechanism was designed to separate speech and breathing from 323 recordings. Features extracted from these were combined with biological factors to predict lung function. Three predictive models were developed using Random Forest (RF), Support Vector Machine (SVM), and linear regression algorithms: (a) regression models to predict lung function, (b) multi-class classification models to predict severity of lung function abnormality, and (c) binary classification models to predict lung function abnormality. Training and test samples were separated (70%:30%, using balanced portioning), features were normalised, 10-fold cross-validation was used and model performances were evaluated on the test samples.ResultsThe RF-based regression model performed better with the lowest root mean square error of 10·86. To predict severity of lung function impairment, the SVM-based model performed best in multi-class classification (accuracy = 73.20%), whereas the RF-based model performed best in binary classification models for predicting abnormal lung function (accuracy = 85%).ConclusionOur machine learning approaches can predict lung function, from recorded voice files, better than published approaches. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

show abstract

“…A support vector machine model was used to classify the severity of four kinds of pulmonary function, and the accuracy was 73.20%, and an accuracy of 85% was achieved to judge whether the subjects had abnormal pulmonary function through the random forest classification model. In addition, Nazir ( 18 ) adopted mobile devices for the diagnosis of chronic respiratory diseases, and 201 subjects were enrolled to collect “A-vowel” sound or “AAAA...” sound to assess the pulmonary function parameter FEV1/FVC by using the multi-layer regression model, and it achieved an MAE of 7.4%. Moreover, keuml ( 19 ) used mobile phones to collect the speech sound signals of 59 subjects and proposed two algorithms for passive evaluation of pulmonary function: the first one used a random forest classifier model to distinguish whether the subjects were healthy or had obstructive respiratory disease, and obtained an accuracy of 78.6%; the latter one used the 7-dimension features of speech sounds by neural network model to assess FEV1/FVC pulmonary function parameters, and achieved an MAE of 12.5%.…”

Section: Related Workmentioning

confidence: 99%

A forced cough sound based pulmonary function assessment method by using machine learning

He²,

Chen³

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

Pulmonary function testing (PFT) has important clinical value for the early detection of lung diseases, assessment of the disease severity, causes identification of dyspnea, and monitoring of critical patients. However, traditional PFT can only be carried out in a hospital environment, and it is challenging to meet the needs for daily and frequent evaluation of chronic respiratory diseases. In this study, we propose a novel method for accurately assessing pulmonary function by analyzing recorded forced cough sounds by mobile device without time and location restrictions. In the experiment, 309 clips of cough sound segments were separated from 133 patients who underwent PFT by using Audacity software. There are 247 clips of training samples and 62 clips of testing samples. Totally 52 features were extracted from the dataset, and principal component analysis (PCA) was used for feature reduction. Combined with biological attributes, the normalized features were regressed by using machine learning models with pulmonary function parameters (i.e., FEV1, FVC, FEV1/FVC, FEV1%, and FVC%). And a 5-fold cross-validation was applied to evaluate the performance of the regression models. As described in the experimental result, the result of coefficient of determination (R2) indicates that the support vector regression (SVR) model performed best in assessing FVC (0.84), FEV1% (0.61), and FVC% (0.62) among these models. The gradient boosting regression (GBR) model performs best in evaluating FEV1 (0.86) and FEV1/FVC (0.54). The result confirmed that the proposed method was capable of accurately assessing pulmonary function with forced cough sound. Besides, the cough sound sampling by a smartphone made it possible to conduct sampling and assess pulmonary function frequently in the home environment.

show abstract

Lung Function Estimation from a Monosyllabic Voice Segment Captured Using Smartphones

Cited by 9 publications

References 35 publications

Predicting pulmonary function from the analysis of voice: a machine learning approach

Predicting pulmonary function from the analysis of voice: a machine learning approach

Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach

A forced cough sound based pulmonary function assessment method by using machine learning

Contact Info

Product

Resources

About