Key result
An electronic nose combined with machine learning classified exhaled breath for tuberculosis with an accuracy of up to 94.87% using an Artificial Neural Network.
Why the study?
Does an electronic nose combined with machine learning accurately classify exhaled breath for tuberculosis detection compared to chest x-ray confirmation?
Cross-Sectional
Does an electronic nose combined with machine learning accurately classify exhaled breath for tuberculosis detection compared to chest x-ray confirmation?
An electronic nose combined with machine learning, particularly ANN, shows high accuracy in non-invasively classifying exhaled breath for tuberculosis detection.
May support non-invasive TB screening; leaves open large prospective validation before clinical adoption.
This research aims to apply an electronic nose (e-Nose) identifying TB through exhaled breath combined with machine learning methods. For the e-Nose system, participants breath normally into the e-Nose chamber. The e-Nose classified the exhaled breath into Tuberculosis Suspect (TBS) and Healthy Person (HP). The dataset was created by collecting directly after pulmonologist confirmed by using chest x-ray images. The machine learning methods were used to train and classify the exhaled breath. E-Nose models were created by using Support Vector Machine (SVM), Random Forest, and XGBoost. Based on experiments, the exhaled breath accuracy is 92 % for SVM, 88.24% for XGBoost, 94.87% for ANN, and 84.24% for the random forest.
No takes yet. Share an insight, caveat, or question.
Hendrick et al. (2021) conducted a cross-sectional in Tuberculosis. Electronic nose (e-Nose) with machine learning vs. Healthy persons was evaluated on Classification accuracy (Accuracy 94.87% for ANN). An electronic nose combined with machine learning classified exhaled breath for tuberculosis with an accuracy of up to 94.87% using an Artificial Neural Network.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: