The study explores machine learning's role in predicting TB treatment outcomes using tabular data sourced from NIKSHAY. It transforms the prediction task into a binary classification problem, achieving high recall and AUC-ROC score. Various ML algorithms like random forest and SVM are used to analyze patient information for accurate predictions. The study highlights the potential of ML in customizing treatments based on individual profiles, aiding in early detection and contact tracing. By combining different models and encoding techniques, robust predictions are made for TB treatment outcomes. The research aims to improve public health interventions and contribute to TB eradication efforts.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by SeshaSai Nat... at arxiv.org 03-15-2024
https://arxiv.org/pdf/2403.08834.pdfDeeper Inquiries