A Comprehensive Review of Human Disease Prediction Models using Machine Learning and Data Analytics

The medical domain is currently dealing with a significant problem of diagnosing the human disease at the early stages. Micro-organism evolution started spreading various diseases, which grow in the human body without showing any significant symptoms. Physicians rely on technology to diagnose human disease at an early stage. In this continuity, physicians employed Digital Image processing techniques and later employed Deep Learning (DL) algorithms to diagnose human diseases. To overcome the limitations in image processing and DL methods, Machine Learning (ML) algorithms are employed currently. Machine Learning (ML) is gaining popularity as a method for analyzing massive datasets and developing predictive modeling or pattern recognition. Physicians could manage patients who were sick using the information presented if they had a thorough understanding of the disease. As a result, diseases are sometimes misconstrued and undertreated. Using an existing statistical model, researchers educate the system to predict the likelihood of an individual's disease based on the symptoms the doctor provides. ML is the most rapidly growing area of computer science, yet health informatics is quite challenging. Machine learning aims to create predictive algorithms that improve with experience. Machine learning benefits many industries, including healthcare. Its alert and decision-making technologies improve patient safety and healthcare quality. This manuscript performs a detailed analysis of human disease prediction models based on Deep Learning and Machine Learning algorithms to determine the pros and cons of the existing methodologies.