A Comprehensive Analysis of Artificial Intelligence Techniques for the Prediction and Prognosis of Lifestyle Diseases

Artificial intelligence is the fastest growing data-driven technology and is currently used in all major fields and reduces the work of humans. Artificial intelligence can analyse extensive data from Electronic Health Records, clinical trials, patient’s medical history, X-rays, CT scans and contribute to the healthcare field by explicitly detecting and predicting lifestyle diseases such as Alzheimer, Arthritis, Asthma, Atherosclerosis, COPD, Depression, Obesity, Osteoporosis, Metabolic Syndrome and PCOS. Lifestyle diseases are diseases related to the daily habits or routines of individuals such as smoking, excessive consumption of alcohol, physical inactivity, overeating etc. Common techniques used by AI to diagnose these diseases are Decision Tree, Random Forest, ANN, SVM, Regression, Naïve Bayes and deep learning models such as Convolutional Neural Network, Recurrent Neural Network, and Natural Language Processing. A common framework is presented in this paper to carry forward the research to add significant value. This paper presents an extensive overview of the diseases, their symptoms and associated illnesses, risk factors, datasets suitable for developing predictive models, challenges encountered by researchers, and significant contributions made in this area.