<![CDATA[This study aimed to develop TB-Guard, a HealthTech startup that provides an early tuberculosis (TB) screening system based on the Gradient Boosting Machine (GBM) algorithm to support early detection among correctional inmates. The novelty of this study lies in integrating physiological parameters, including body temperature, oxygen saturation (SpO₂), pulse rate, blood pressure, and respiratory rate, into a predictive model with the potential to be transformed into a digital health product. An analytical observational study was conducted involving 70 correctional inmates selected through purposive sampling. Data were processed through preprocessing, feature selection, GBM model development, and performance evaluation using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC). The proposed model achieved a testing accuracy of 92.86% with an AUC of 0.947, demonstrating excellent classification performance for early TB risk prediction. These findings indicate that TB-Guard offers a rapid, objective, and cost-effective screening solution while demonstrating strong potential for commercialization as a HealthTech startup supporting tuberculosis control programs]]>
Copyrights © 2026
