Artificial Intelligence to Assist Clinical Diagnosis in Medicine

Abstract

Medicine is one of the elds of knowledge that would most bene t from a closer interaction with Computer studies and Mathematics by optimizing complex, imperfect processes such as differential diagnosis; this is the domain of Machine Learning, a branch of Arti cial Intelligence that builds and studies systems capable of learning from a set of training data, in order to optimize classi cation and prediction processes. In Mexico during the last few years, progress has been made on the implementation of electronic clinical records, so that the National Institutes of Health already have accumulated a wealth of stored data. For those data to become knowledge, they need to be processed and analyzed through complex statistical methods, as it is already being done in other countries, employing: case-based reasoning, artificial neural networks, Bayesian classi ers, multivariate logistic regression, or support vector machines, among other methodologies; to assist the clinical diagnosis of acute appendicitis, breast cancer and chronic liver disease, among a wide array of maladies. In this review we sift through concepts, antecedents, current examples and methodologies of machine learning-assisted clinical diagnosis.