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

Abstract

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.

A Pervasive Pulmonary Function Estimation System with Six-Minute Walking Test

“…Many other portable sensing devices for pulmonary function were reported in [ 20 , 21 , 22 ]. They had the features of low cost and easy use.…”

“…Larson et al [ 20 ] use a microphone on a mobile phone to diagnose varying degrees of obstructive lung ailments with a low FVC accuracy rate. Alam et al [ 21 ] predict lung functions from recorded voice and enable patients to achieve improved symptom control. Nevertheless, it is not able to utilize a feature engineering method to identify informative features.…”

Current state and prospects of artificial intelligence in allergy

“…Another study applied ML to analyze the sounds of asthma inhalers to predict adequate usage and drug actuations 149 . Recorded sound on mobile devices has also been proposed to monitor lung function in asthmatics 150 . While requiring further validation, these techniques could be used to develop future telehealth solutions including smartphone‐based applications, which have the potential to aid decision‐making and self‐monitoring in asthma.…”

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

“…Other than being a reliable means to non-empirically quantify voice impairment in diseases that affect phonatory production, voice analysis is also a completely non-invasive, low-cost and pseudo-real-time solution for deploying telemedicine assessments. Voice-based AI solutions have been successfully experimentally investigated and employed in other medical fields such as dysphonia [ 31 , 32 , 33 ], COVID-19 and pulmonary diseases [ 20 , 22 , 34 , 35 ], and even emotion and stress recognition [ 24 , 36 ].…”