Exploring Tree-Based Machine Learning for Multi-Illness Prediction
Rapid advancements in machine learning techniques have opened new avenues for innovative healthcare strategies, particularly in disease prediction. The healthcare sector confronts escalating challenges due to the surge in diseases and population growth. Despite society's heavy reliance on the i...
Saved in:
Published in | 2024 International Conference on Knowledge Engineering and Communication Systems (ICKECS) Vol. 1; pp. 1 - 6 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
18.04.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Rapid advancements in machine learning techniques have opened new avenues for innovative healthcare strategies, particularly in disease prediction. The healthcare sector confronts escalating challenges due to the surge in diseases and population growth. Despite society's heavy reliance on the internet, physical health often receives inadequate attention. Minor health concerns are neglected, leading to the development of more severe illnesses over time. This paper thoroughly investigates machine learning algorithms for predicting multiple illnesses. The proposed model undergoes rigorous evaluation using a comprehensive dataset encompassing 41 distinct disorders characterized by 132 symptoms, totaling 4920 records. Tree-based Machine Learning models such as Decision Tree, Random Forest, XGBoost, AdaBoost, and LightGBM are employed to examine and assess the efficacy of disease prediction. The Django framework is employed to construct graphical user interface for users. The proposed XGBoost model demonstrates superior performance, achieving an accuracy of \mathbf{9 8 \%} compared to other tree-based models in the prediction of multiple diseases. These research findings underscore the potential of machine learning in predicting various diseases and emphasize its significant impact on public health. |
---|---|
DOI: | 10.1109/ICKECS61492.2024.10616981 |