Personalized medicine through AI: Enhancing tuberculosis forecasting with fuzzy neural models

Tuberculosis (TB) remains a major health challenge in Sabah, Malaysia, where accurate forecasting is crucial for disease control. Traditional methods struggle with complex epidemiological data, making Artificial Intelligence (AI) techniques like fuzzy logic and neural networks valuable. Fuzzy logic handles uncertainty, neural networks detect patterns, and their integration using fuzzy neural models and enhances TB forecasting accuracy. Personalized medicine benefits from AI- driven models incorporating demographic and regional trends. Fuzzy logic forecasting converts uncertain data into insights through fuzzification, rule application, and defuzzification. Triangular membership functions improve computational efficiency while maintaining interpretability. Case studies show that fuzzy neural models outperform traditional methods, leading to proactive health measures and better resource allocation. Further advancements in these models promise improved TB management, benefiting both public health and personalized medicine.

Text 127636.pdf Restricted to Repository staff only Download (300kB) Official URL or Download Paper: https://www.igi-global.com/book/applied-neural-net...

Actions (login required)

View Item