Can Machine Learning Be Used to Recognize and Diagnose Coughs?

  title={Can Machine Learning Be Used to Recognize and Diagnose Coughs?},
  author={Charles Bales and Charles N. John and Hasan Farooq and Usama Masood and Muhammad Nabeel and Ali Shariq Imran},
  journal={2020 International Conference on e-Health and Bioengineering (EHB)},
Emerging wireless technologies, such as 5G and beyond, are bringing new use cases to the forefront, one of the most prominent being machine learning empowered health care. One of the notable modern medical concerns that impose an immense worldwide health burden are respiratory infections. Since cough is an essential symptom of many respiratory infections, an automated system to screen for respiratory diseases based on raw cough data would have a multitude of beneficial research and medical… 

Figures and Tables from this paper

Cough Audio Analysis for COVID-19 Diagnosis

Results show that Multilayer Perceptron was able to distinguish between positive and negative COVID-19 coughs by a robust feature embedding technique, which is scalable and less time consuming.

Automatic Creation of Masks for Marking Histological Images of the Epithelium of the Paranasal Sinuses

The article discusses the approach to solving the problem of reducing time spent on the preparation of medical images for teaching neural networks, by reducing the time of creating masks for images, by proposing a software solution.

Quantum Machine Learning for Audio Classification with Applications to Healthcare

A hybrid quantum neural network (QNN) model for COVID-19 cough classification is developed and the design of the QNN simulation architecture is described and results are given with and without quantum noise.

Sound-Based Cough Detection System using Convolutional Neural Network

A precise cough identification and monitoring system utilising a convolutional neural network as a feature extraction algorithm and classification system, suggesting that this can be a successful cough detection method for future medical applications and devices, such as potential respiratory system condition diagnostic tool.

COVID-19 Detection from Respiratory Sounds with Hierarchical Spectrogram Transformers

A novel deep learning approach is introduced to distinguish patients with COVID-19 from healthy controls given audio recordings of cough or breathing sounds, and it is shown that HST outperforms competing methods, achieving over 97% area under the receiver operating characteristic curve (AUC) in detecting CO VID-19 cases.

Making cough count in tuberculosis care

An overview of recent advances in acoustic epidemiology is presented and how cough assessment, if validated, could support public health programs at various stages of the TB care cascade is described.

Changes in Cough Airflow and Acoustics After Injection Laryngoplasty

We explored the following hypotheses in a cohort of patients undergoing injection laryngoplasty: (1) glottic insufficiency affects voluntary cough airflow dynamics and restoring glottic competence

Project Achoo: A Practical Model and Application for COVID-19 Detection From Recordings of Breath, Voice, and Cough

A machine learning method is proposed to quickly detect COVID-19 using audio recordings made on consumer devices that combines signal processing and noise removal methods with an ensemble of fine-tuned deep learning networks and enables COVID detection on coughs.

Past and Trends in Cough Sound Acquisition, Automatic Detection and Automatic Classification: A Comparative Review

The field of cough sound acquisition, automatic detection in longer audio sequences and automatic classification of the nature or disease shows a remarkable dynamic, boosted by the research on COVID-19 diagnosis, and a perfect adaptation to mobile health.



ESC: Dataset for Environmental Sound Classification

A new annotated collection of 2000 short clips comprising 50 classes of various common sound events, and an abundant unified compilation of 250000 unlabeled auditory excerpts extracted from recordings available through the Freesound project are presented.

Deep Neural Networks for Identifying Cough Sounds

Experimental results show both network architectures outperform traditional methods for cough detection and the effect of the network size parameters and the impact of long-term signal dependencies in cough classifier performance is explored.

Freesound technical demo

This demo wants to introduce Freesound to the multimedia community and show its potential as a research resource.

Adam: A Method for Stochastic Optimization

This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

librosa/librosa: 0.6.0

A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children

The results indicate that this technology has a role as a high-level diagnostic aid in the assessment of common childhood respiratory disorders, including asthma, pneumonia and bronchiolitis.

Comparison and Analysis of SampleCNN Architectures for Audio Classification

SampleCNN is scrutinized further by comparing it with spectrogram-based CNN and changing the subsampling operation in three different audio domains and shows that the excitation in the first layer is sensitive to the loudness, which is an acoustic characteristic that distinguishes different genres of music.

Novel feature extraction method for cough detection using NMF

To find the difference of cough and other audios in a more compact representation, non-negative matrix factorisation (NMF) is exploited to extract the spectral structure from signals and demonstrates that NMF-based feature extraction method has considerable potential in improving performance for cough detection.

Deep Convolutional Neural Network with Mixup for Environmental Sound Classification

A novel deep convolutional neural network is proposed to be used for environmental sound classification (ESC) tasks that uses stacked Convolutional and pooling layers to extract high-level feature representations from spectrogram-like features.