Published January 1, 2026 | Version v1

Post-TB Lung Risk Forecaster: A Real-Time Clinical Decision Support System.

Description

Post-tuberculosis (post-TB) lung disease has emerged as a significant cause of long-term respiratory impairment, especially in regions with high TB prevalence. Detecting individuals at risk of developing chronic pulmonary complications—such as fibrosis, persistent airflow obstruction, and recurrent infections—remains a critical gap in clinical practice. This paper presents a Post-TB Lung Risk Forecaster, a real-time clinical decision support system aimed at predicting the likelihood of adverse lung outcomes in patients previously treated for tuberculosis. The system leverages machine learning techniques to analyze integrated data, including patient demographics, medical history, imaging results, lung function tests, and treatment responses, to produce personalized risk assessments. Its intuitive interface allows healthcare providers to obtain actionable insights during routine clinical workflows, supporting early intervention and tailored patient management. The model is developed and validated using longitudinal clinical datasets, showing strong predictive performance and practical relevance. By promoting early detection and preventive care, this system can help reduce long-term complications, enhance patient outcomes, and support efficient use of healthcare resources, contributing to improved post-TB care strategies.

 

Files

1775651120_IJSRET_V12_issue2_314.pdf

Files (518.3 kB)

Name Size
md5:da55e82ac20dd43d9e93d492be2d156d
518.3 kB Preview Download

Additional details