A symptom-driven medical diagnosis support model based on machine learning techniques

Abstract

Medicine is a human science that is constantly evolving, and this evolution generates a large mass of data that needs to be exploited with the multitude of IT resources available to guarantee and maintain this scientific progress. Some diseases share most symptoms, whereas others could have a low probability of being identified in an early stage. Thus, when facing a such situation, an inexperienced doctor may have difficulty making the right diagnosis or may test different cases, which will be a big waste of time. In this paper, we are going to make this embarrassing situation less complex by giving practitioners every probable disease, and even the least probable ones according to the given symptoms. Indeed, this work will push the diagnosis deeper to reveal hidden symptoms and pathogenesis, to help practitioners make the right decisions. To develop such a solution, the data is organized by matching each disease with its known symptoms, then we used naive Bayes as a classification model, and different metrics to evaluate the performance of this experiment. This work proves that machine learning has become very effective in the medical sector, especially when we notice that the accuracy exceeds 90% in the detection of diseases.