English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Objective: The automatic discrimination between the coughing sounds producedby patients with tuberculosis (TB) and those produced by patients with otherlung ailments.  Approach: We present experiments based on a dataset of 1358 forced coughrecordings obtained in a developing-world clinic from 16 patients withconfirmed active pulmonary TB and 35 patients suffering from respiratoryconditions suggestive of TB but confirmed to be TB negative. Using nestedcross-validation, we have trained and evaluated five machine learningclassifiers: logistic regression (LR), support vector machines (SVM), k-nearestneighbour (KNN), multilayer perceptrons (MLP) and convolutional neural networks(CNN).  Main Results: Although classification is possible in all cases, the bestperformance is achieved using LR. In combination with feature selection bysequential forward selection (SFS), our best LR system achieves an area underthe ROC curve (AUC) of 0.94 using 23 features selected from a set of 78high-resolution mel-frequency cepstral coefficients (MFCCs). This systemachieves a sensitivity of 93\% at a specificity of 95\% and thus exceeds the90\% sensitivity at 70\% specificity specification considered by the WorldHealth Organisation (WHO) as a minimal requirement for a community-based TBtriage test.  Significance: The automatic classification of cough audio sounds, whenapplied to symptomatic patients requiring investigation for TB, can meet theWHO triage specifications for the identification of patients who should undergoexpensive molecular downstream testing. This makes it a promising and viablemeans of low cost, easily deployable frontline screening for TB, which canbenefit especially developing countries with a heavy TB burden.

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