<![CDATA[Multi-drug resistant tuberculosis (MDR-TB) is caused by Mycobacterium tuberculosis strains that resist at least two first-line anti-TB drugs. This disease presents a major global health challenge, particularly affecting middle to lower income countries where affordable and rapid diagnostic tools are urgently needed. To address this, researchers are exploring the combination of whole genome sequencing and machine learning for drug resistance predictions. Using Mycobacterium tuberculosis genomic data from databases, both Logistic Regression (LR) and Convolutional Neural Network (CNN) models were trained to predict drug resistance. Performance evaluation revealed that CNN slightly outperformed LR in accuracy and specificity for Rifampicin and Pyrazinamide predictions, while LR showed better results for Isoniazid and Ethambutol. In terms of sensitivity, LR demonstrated superior performance for most drugs, except Ethambutol where CNN excelled. Though computational complexity assessment was incomplete due to hardware limitations, both models showed distinct advantages in predicting first-line anti-TB drug resistance.]]>
Copyrights © 2025
