Predictive Modeling of Diseases with Explainable Artificial Intelligence Using LightGBM
DOI:
https://doi.org/10.59287/as-ijanser.10Keywords:
Disease Prediction, Machine Learning, AI-Driven Healthcare, SHAP, Decision Support SystemsAbstract
The continuous exploration of the intricate connections among symptoms, patient attributes, and diseases within the intricate landscape of human health represents an ongoing pursuit. Data-driven methodologies have ushered in novel opportunities for comprehending these intricate relationships. Especially with the COVID-19 pandemic, the paradigms of disease understanding, diagnosis, and treatment management have assumed unprecedented significance. This study, powered by LightGBM and SHAP, has the potential to provide invaluable support to experts in decision support systems, early diagnosis of diseases, personalized treatment plan applications, strengthening medical interventions with case-oriented treatment predictions by producing advanced diagnosis and treatment strategies at demographic scales and analyzing risk factors, developing evidence-based public health policies and proactive health services, researchers. Furthermore, this research can be effectively leveraged in epidemiological investigations to ascertain the correlations and emerging trends between various diseases and the influencing health determinants all with an impressive 81% accuracy.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 International Journal of Advanced Natural Sciences and Engineering Researches (IJANSER)
This work is licensed under a Creative Commons Attribution 4.0 International License.