Human Disease Prediction Based on Symptoms Using Novel Machine Learning

Ibukunoluwa Oluwabusayo Efunwoye, Mandar Gogate, Adeel Hussain, Bin Luo, Jinchang Ren, Fengling Jiang, Amir Hussain, Kia Dashtipour

Abstract: Nowadays, individuals are often preoccupied with their daily lives and may disregard minor illnesses they are experiencing. However, these seemingly insignificant diseases can sometimes escalate into more serious health problems. Therefore, in this paper, we propose a novel approach for the detection of various types of diseases using machine learning algorithms, such as Support Vector Machine (SVM), Naïve Bayes, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and others. The primary objective of this research is to develop a personalized health monitoring system that leverages an individual’s medical history and current health status, utilizing advanced machine learning techniques. The main aim of this study is to provide personalized health predictions based on individual’s medical and current health information. Through our proposed approach, we aim to create a robust and accurate disease prediction model that can effectively identify a wide range of ailments, including minor diseases. Our approach involves employing diverse machine learning algorithms to capture complex patterns and features in the data, enabling a comprehensive analysis of health conditions. The results of our machine learning experiments demonstrate the effectiveness of our proposed approach in detecting small diseases. By leveraging machine learning algorithms, we are able to provide timely and accurate disease predictions, enabling early identification of potential health issues. This proactive approach to disease detection has the potential to facilitate timely medical intervention, leading to improved health outcomes and overall well-being. Our research contributes to the field of personalized health monitoring and has implications for proactive disease prevention and management strategies. Further studies and validations are warranted to refine and optimize our approach for real-world clinical applications.