Multimodal Disease Prediction Using Hybrid Machine Learning Algorithms

Abstract

Machine learning (ML) and deep learning (DL) are derivatives of artificial intelligence (AI) that have proven effective in various fields, including healthcare, and are now routinely integrated into patients' daily activities. Machine learning techniques are increasingly used to improve disease prediction. In this paper, we propose a multi-disease prediction system that uses ML and DL algorithms to predict the probability of several common diseases. Although there are many algorithms and techniques for predicting diseases, there are not enough systems that can identify multiple diseases in a single system. Therefore, this paper focuses on the prediction of various diseases using ML and DL algorithms. Our goal is to build a model that effectively predicts diseases such as kidney, heart, diabetes, and malaria using ML and DL algorithms. This helps to better predict disease. For accurate predictions, we will use stacking and assembling models, which helps improve model accuracy. We will implement all these models in a Flask web application.