Machine Learning in Medicine - a Complete Overview

Abstract

The amount of data stored in the world’s databases doubles every 20 months, as estimated by Usama Fayyad, one of the founders of machine learning and co-author of the book Advances in Knowledge Discovery and Data Mining (ed. by the American Association for Artifi cial Intelligence, Menlo Park, CA, USA, 1996), and clinicians, familiar with traditional statistical methods, are at a loss to analyze them. Traditional methods have, indeed, diffi culty to identify outliers in large datasets, and to fi nd patterns in big data and data with multiple exposure/outcome variables. In addition, analysis-rules for surveys and questionnaires, which are currently com- mon methods of data collection, are, essentially, missing. Fortunately, the new dis- cipline, machine learning, is able to cover all of these limitations. So far, medical professionals have been rather reluctant to use machine learning. Ravinda Khattree, co-author of the book Computational Methods in Biomedical Research (ed. by Chapman & Hall, Baton Rouge, LA, USA, 2007) suggests that there may be historical reasons: technological (doctors are better than computers (?)), legal, cultural (doctors are better trusted). Also, in the fi eld of diagnosis mak- ing, few doctors may want a computer checking them, are interested in collabora- tion with a computer or with computer engineers.