Effects of asthma on breathing during reading aloud

Breathing better: A tech-monitored study of positive expiratory pressure and reading aloud for chronic obstructive pulmonary disease

BACKGROUND

Breathing exercises, such as diaphragmatic breathing and positive expiratory pressure (PEP), relieve breathlessness in people with chronic obstructive pulmonary disease (COPD).

AIM

This study aimed to investigate the effects of breathing exercises with PEP and reading aloud on vital signs, fatigue level, severity of dyspnoea and respiratory function parameters in patients with COPD.

DESIGN

The study followed a randomized controlled trial of COPD patients from a single hospital in eastern Turkey.

METHODS

The study included 103 patients who were randomly assigned to receive pre-reading exercises, breathing exercises with a PEP device or no intervention for 8 weeks.

RESULTS

The use of a PEP device improved oxygen saturation, forced expiratory volume in 1 s (FEV1 ) and FEV1 /forced vital capacity (FVC) values and reduced fatigue and dyspnoea severity. Reading aloud lowered the mean arterial pressure and reduced fatigue and dyspnoea severity.

CONCLUSION

The study concludes that PEP devices and reading aloud can improve respiratory function in patients with COPD. Additionally, reading aloud is an accessible, easy-to-implement and economically feasible method for treating COPD symptoms.

Utilizing Deep Learning on Limited Mobile Speech Recordings for Detection of Obstructive Pulmonary Disease

Passive assessment of obstructive pulmonary disease has gained substantial interest over the past few years in the mobile and wearable computing communities. One of the promising approaches is speech-based pulmonary assessment wherein spontaneous or scripted speech is used to evaluate an individual's pulmonary condition. Recent approaches in this regard heavily rely on accurate speech activity segmentation and specific, hand-crafted features. In this paper, we present an end-to-end deep learning approach for detecting obstructive pulmonary disease. We leveraged transfer learning using a network pre-trained for a different audio-based task, and employed our own additional shallow network on top as a binary classifier to indicate if a given speech recording belongs to an asthma or COPD patient. The additional network was a fully connected neural net with 2 hidden layers, and this was evaluated on two real-world datasets. We demonstrated that the system can identify subjects with obtructive pulmonary disease using their speech with 88.3 % precision, 88.8 % recall and 88.3% F-1 score using 10-fold cross-validation. The system showed improved performance in identifying the most severely affected subgroup of patients in the dataset, with an average 93.6 % accuracy.

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

Introduction

To 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.

Methods

A 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.

Results

The 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%).

Conclusion

Our 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.

Changes in asthma severity in the first year of school and difficulty learning to read

Objective: Asthma is a risk factor for poor early reading in children, for reasons that are unclear. This analysis examines the relationship between changes in asthma severity during the first year of school and being in the lowest quartile of reading achievement after 1 year of school.Methods: We used previously unreported data from our cohort study. Parent interviews and teacher questionnaires enquired about asthma and covariates of achievement at school entry (T1) and 12 months later (T2). Asthma severity scores at T1 and T2 showed that in 27 of 51 children with asthma, symptoms improved over the year, whereas in 24, symptoms persisted or worsened. Word and story reading were assessed at T1 and T2. We compared reading achievement at both timepoints between children with asthma and children who had no reported respiratory symptoms between birth and T2 (controls, N = 74), and between those with persistent versus improved symptoms.Results: More children with asthma than controls were in the lowest quartiles for reading. Further, significantly more children in the persistent group compared to the improved group were in the lowest quartiles for word reading (58 versus 30%, respectively) and story reading (54 versus 26%, respectively). School absences, increased behavior problems, stressful life events or parental mental health were not associated with the differences in either comparison. Logistic regression modeling identified persistent asthma as the most important variable associated with being in the lowest quartile of reading after 1 year in school.Conclusions: Active asthma symptoms during early school may influence early reading achievement.