# Automatic Cough Classification for Tuberculosis Screening in a Real-World Environment

arXiv: https://arxiv.org/abs/2103.13300 · HTML: https://mlsanity.com/paper/2103.13300/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 103 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 4 of 4)

- [Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data](https://mlsanity.com/paper/2006.05919/) (2020)
- [Coswara -- A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis](https://mlsanity.com/paper/2005.10548/) (2020)
- [COVID-19 Cough Classification using Machine Learning and Global Smartphone Recordings](https://mlsanity.com/paper/2012.01926/) (2020)
- [Deep Neural Network based Cough Detection using Bed-mounted Accelerometer Measurements](https://mlsanity.com/paper/2102.04997/) (2021)

## Built on by (most cited first, 17 of 17)

- [HeAR -- Health Acoustic Representations](https://mlsanity.com/paper/2403.02522/) (2024)
- [COVID-19 Detection in Cough, Breath and Speech using Deep Transfer Learning and Bottleneck Features](https://mlsanity.com/paper/2104.02477/) (2021)
- [Towards using Cough for Respiratory Disease Diagnosis by leveraging Artificial Intelligence: A Survey](https://mlsanity.com/paper/2309.14383/) (2023)
- [Automatic non-invasive Cough Detection based on Accelerometer and Audio Signals](https://mlsanity.com/paper/2109.00103/) (2021)
- [Predicting Tuberculosis from Real-World Cough Audio Recordings and Metadata](https://mlsanity.com/paper/2307.04842/) (2023)
- [TB or not TB? Acoustic cough analysis for tuberculosis classification](https://mlsanity.com/paper/2209.00934/) (2022)
- [Wake-Cough: cough spotting and cougher identification for personalised long-term cough monitoring](https://mlsanity.com/paper/2110.03771/) (2021)
- [Automatic Tuberculosis and COVID-19 cough classification using deep learning](https://mlsanity.com/paper/2205.05480/) (2022)
- [Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals](https://mlsanity.com/paper/2309.05843/) (2023)
- [Accelerometer-based Bed Occupancy Detection for Automatic, Non-invasive Long-term Cough Monitoring](https://mlsanity.com/paper/2202.03936/) (2022)
- [On the link between generative semi-supervised learning and generative open-set recognition](https://mlsanity.com/paper/2303.11702/) (2023)
- [Towards reliable respiratory disease diagnosis based on cough sounds and vision transformers](https://mlsanity.com/paper/2408.15667/) (2024)
- [Tuberculosis Screening from Cough Audio: Baseline Models, Clinical Variables, and Uncertainty Quantification](https://mlsanity.com/paper/2601.07969/) (2026)
- [Fused Audio Instance and Representation for Respiratory Disease Detection](https://mlsanity.com/paper/2204.10581/) (2022)
- [Leveraging cough sounds to optimize chest x-ray usage in low-resource settings](https://mlsanity.com/paper/2402.08789/) (2024)
- [Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data](https://mlsanity.com/paper/2402.10100/) (2024)
- [Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening](https://mlsanity.com/paper/2608.25846/) (2026)

## Abstract (arXiv)

Objective: The automatic discrimination between the coughing sounds produced by patients with tuberculosis (TB) and those produced by patients with other lung ailments. Approach: We present experiments based on a dataset of 1358 forced cough recordings obtained in a developing-world clinic from 16 patients with confirmed active pulmonary TB and 35 patients suffering from respiratory conditions suggestive of TB but confirmed to be TB negative. Using nested cross-validation, we have trained and evaluated five machine learning classifiers: logistic regression (LR), support vector machines (SVM), k-nearest neighbour (KNN), multilayer perceptrons (MLP) and convolutional neural networks (CNN). Main Results: Although classification is possible in all cases, the best performance is achieved using LR. In combination with feature selection by sequential forward selection (SFS), our best LR system achieves an area under the ROC curve (AUC) of 0.94 using 23 features selected from a set of 78 high-resolution mel-frequency cepstral coefficients (MFCCs). This system achieves a sensitivity of 93% at a specificity of 95% and thus exceeds the 90% sensitivity at 70% specificity specification considered by the World Health Organisation (WHO) as a minimal requirement for a community-based TB triage test. Significance: The automatic classification of cough audio sounds, when applied to symptomatic patients requiring investigation for TB, can meet the WHO triage specifications for the identification of patients who should undergo expensive molecular downstream testing. This makes it a promising and viable means of low cost, easily deployable frontline screening for TB, which can benefit especially developing countries with a heavy TB burden.