From data to decisions: Statistical tools and Artificial Intelligence in tuberculosis Operational Research

Abstract

Background: Tuberculosis (TB) remains a major public health challenge, especially in low- and middle-income countries. Operational Research (OR), supported by robust statistical methods, plays a critical role in optimizing TB control strategies.

Objective: This review highlights the statistical tools applied in TB Operational Research, their applications, and the emerging role of Artificial Intelligence (AI) in strengthening data-driven decision-making.

Methods: We examine classical statistical approaches alongside predictive modeling, cost-effectiveness analysis, and AI-based frameworks. Case examples from diverse settings illustrate their practical impact.

Findings: Statistical methods underpin surveillance, diagnosis, treatment evaluation, and policy modeling in TB programs. AI-driven techniques, such as machine learning and deep learning, are expanding the analytical landscape by enhancing prediction, identifying high-risk populations, and enabling real-time program monitoring.

Conclusion: Statistical tools from traditional inference to AI-modeling are essential for advancing TB control. Strengthening methodological rigor, reporting standards and interdisciplinary collaboration will be pivotal in harnessing data for effective TB elimination strategies.

Keywords: Artificial intelligence; Modeling; Operational research; Statistical tools; Tuberculosis.