Machine learning, medical diagnosis, and biomedical engineering research - commentary
Top Cited Papers
Open Access
- 1 January 2014
- journal article
- review article
- Published by Springer Science and Business Media LLC in BioMedical Engineering OnLine
- Vol. 13 (1), 94
- https://doi.org/10.1186/1475-925x-13-94
Abstract
A large number of papers are appearing in the biomedical engineering literature that describe the use of machine learning techniques to develop classifiers for detection or diagnosis of disease. However, the usefulness of this approach in developing clinically validated diagnostic techniques so far has been limited and the methods are prone to overfitting and other problems which may not be immediately apparent to the investigators. This commentary is intended to help sensitize investigators as well as readers and reviewers of papers to some potential pitfalls in the development of classifiers, and suggests steps that researchers can take to help avoid these problems. Building classifiers should be viewed not simply as an add-on statistical analysis, but as part and parcel of the experimental process. Validation of classifiers for diagnostic applications should be considered as part of a much larger process of establishing the clinical validity of the diagnostic technique.Keywords
This publication has 9 references indexed in Scilit:
- Classification And Regression TreesPublished by Taylor & Francis Ltd ,2017
- Assessment of significance of features acquired from thyroid ultrasonograms in Hashimoto's diseaseBioMedical Engineering OnLine, 2012
- Pitfalls of supervised feature selectionBioinformatics, 2009
- Statistical strategies for avoiding false discoveries in metabolomics and related experimentsMetabolomics, 2006
- Internal and external validation of predictive models: A simulation study of bias and precision in small samplesJournal of Clinical Epidemiology, 2003
- The Boosting Approach to Machine Learning: An OverviewPublished by Springer Science and Business Media LLC ,2003
- Selective sampling to overcome skewed a priori probabilities with neural networks.2000
- A simulation study of the number of events per variable in logistic regression analysisJournal of Clinical Epidemiology, 1996
- Evaluation of new imaging procedures for breast cancer: proper processAmerican Journal of Roentgenology, 1983