TB Prediction and Personalized Diet Planning

Tuberculosis (TB) remains a significant global health concern, impacting millions annually. Early diagnosis and intervention are crucial in controlling its spread, yet detecting TB in its early stages remains challenging. This project, titled "TB Prediction and Personalized Diet Planning," leverages machine learning to predict the likelihood of TB in patients based on their medical records. Using the "Comprehensive Tuberculosis Patient Classification Dataset," which includes demographic information, clinical symptoms, and diagnostic results, the system is designed to provide healthcare professionals with an efficient diagnostic tool. In addition to TB prediction, the system also integrates personalized diet planning, suggesting customized dietary plans tailored to each patient’s health condition and TB diagnosis. The backend of the system is developed using Python and Flask, while the frontend uses HTML, CSS, and JavaScript for user interface development. The primary objective of the system is to assist healthcare providers in the early detection of TB and offer actionable recommendations for diet adjustments, aiding in the recovery process. Through predictive analytics and personalized interventions, this project aims to improve patient outcomes and optimize healthcare practices in the management of tuberculosis.

Keywords: Tuberculosis, prediction, personalized diet, machine learning, Flask, health prediction, clinical symptoms, diagnostic results, patient data, healthcare system, early diagnosis, dietary interventions, recovery.