Investigation of Machine Learning Models for Foodborne Disease Classification

Abstract

Foodborne disease is highly prevalent in low- and middle-income countries worldwide. There are many people affected by foodborne disease in Ethiopia, due to various causes. There are high rate of infections; the control of most foodborne diseases in Ethiopia is low due to a lack of knowledge, medication and support to healthcare professionals for better diagnoses. Machine learning applications in the healthcare and biomedical domain are popular for the early detection of diseases and help to make a better diagnosis. Machine learning models can learn from past data, identify patterns and make decisions with a minimal human intervention. Though there are studies that apply machine learning to medical diagnosis and other fields, there is a lack of studies that classify the foodborne diseases common in Ethiopia. This study focuses on foodborne diseases by selecting some of the prevalent foodborne illnesses in Ethiopia including Typhoid fever, Giardiasis, and Amoebiasis in consultation with medical experts. To achieve the objective of the study the researcher used an experimental research design. Data is collected from two Hospitals. After preprocessing the collected data, the researcher trained the developed model using state-of- art machine learning algorithms including Decision Tree, Random Forest, XGBoost and Stacking ensemble learning method. Based on the experiment conducted, the Stacking ensemble learning method model outperforms the others with an accuracy of 98.06% (98.1%), followed by Random Forest, XGBoost, and Decision Tree with accuracy of 97.5%, 96.9%, and 96.5% respectively. The result obtained by the study depicts that, the Stacking ensemble learning model is suitable for diseases classification.