RESUMO
Objective: Tuberculosis remains a major global health challenge, with delayed diagnosis contributing to increased transmission and disease burden. While microbiological tests are the gold standard for confirming active tuberculosis, many cases lack microbiological evidence, necessitating additional clinical and laboratory data for diagnosis. The complete blood count (CBC), an inexpensive and widely available test, could provide a valuable tool for tuberculosis diagnosis by analyzing disturbances in blood parameters. This study aimed to develop and evaluate a machine learning (ML)-based web application, TubIAgnosis, for diagnosing active tuberculosis using CBC data. Methods: We conducted a retrospective case-control study using data from 449 tuberculosis patients and 1200 healthy controls in Oran, Algeria, from January 2016 to April 2023. Eight ML algorithms were trained on 18 CBC parameters and demographic data. Model performance was evaluated using balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC). Results: The best-performing model, Extreme Gradient Boosting (XGB), achieved a balanced accuracy of 83.3%, AUC of 89.4%, sensitivity of 83.3%, and specificity of 83.3% on the testing dataset. Platelet-to-lymphocyte ratio was the most influential parameter in this ML predictive model. The best performing model (XGB) was made available online as a web application called TubIAgnosis, which is available free of charge at https://yh5f0z-ghermi-mohamed.shinyapps.io/TubIAgnosis/. Conclusions: TubIAgnosis, a ML-based web application utilizing CBC data, demonstrated promising performance for diagnosing active tuberculosis. This accessible and cost-effective tool could complement existing diagnostic methods, particularly in resource-limited settings. Prospective studies are warranted to further validate and refine this approach.