FOOD ALLERGY DETECTION USING MACHINE LEARNING APPROACH

Abstract

Food allergy is one of the diseases that is on the rise. More and more people are diagnosed with food allergies. There are around 8% of adults and 3-5% of children and adolescents suffering from food allergies around the world. These numbers are only increasing every year. According to the recent research papers and data sets, there are now at least 20 foods that are causing allergies. Among these foods, children are often allergic to peanuts, shell fish and tree nuts. Whereas, in the case of adults these foods mostly include shell fish, tree nut, peanut and milk. The first step to any treatment is the timely and accurate diagnosis. In the case of food allergies, the traditional diagnosis involves tests such as the skin prick test which are time consuming and also some of these tests are even inefficient in terms of cost. The solution to this predicament is the involvement of the most recent and the most advanced technologies for the diagnosis. This research paper explores the application of machine learning for the detection of food allergy. This study explores the application of different machine learning algorithms for the detection of allergens causing food allergies. The machine learning programs and algorithms discussed in this study for the detection of food allergy include the prediction model, allerStat, and a clinical decision support system (CDSS). These machine learning programs and algorithms are applied for the diagnosis of food allergies in this research study.