TITLE:
Prediction of the Knowledge Level of Tuberculosis
AUTHORS:
Yazid Hambally Yacouba, Amadou Diabagaté, Hafizatou Sani Yanoussa, Adama Coulibaly, Abdellah Azmani
KEYWORDS:
Machine Learning, Knowledge of Tuberculosis, Health Education, Artificial Intelligence, Decision Support
JOURNAL NAME:
Open Journal of Applied Sciences,
Vol.15 No.11,
October
31,
2025
ABSTRACT: Predicting knowledge of tuberculosis (TB) could imply several significant changes in the management, control and prevention of this disease. These would be based on advanced technological and organizational approaches, with benefits for both the detection, treatment, and prevention of tuberculosis. The use of predictive models based on artificial intelligence (AI) and machine learning to analyze clinical, epidemiological and biological data of patients could contribute to improving screening. Assessing the level of knowledge about tuberculosis is essential to improve prevention, diagnosis and treatment of this disease. It allows for the design of targeted programs to reduce stigma and strengthen health systems. The approach adopted is to conduct a semidirected questionnaire to assess the level of knowledge of tuberculosis through multiple choice, true/false or short answer questions. The data collected is then processed by machine learning algorithms to obtain results that will be analyzed. The collection and analysis of socioeconomic, geographic and demographic data make it possible to identify the most vulnerable populations and geographic areas at high risk of spread. Machine learning can be used to predict knowledge levels based on variables such as education, geography, access to information and health behaviors.