This projects studies statistical learning machines as applied to biomedical and clinical prediction, probabilitiy assignment, regresssion, and ranking problems. The algorithms involved include support vector machines (SVMs), neural networks (NNs), and variations of the boosting algorithm (Freund and Schapire, 1995). These are all recently developed techniques orginally constructed by the machine learning community, and which are only now starting to see applications in biomedical problems. As the methods were not designed through statistical reasoning or applied to data collected by clinicians or biomedical researchers, these new techniques require modifications and enhancements appropriate to data collected from these alternate sources. In particular, we address the problem of (1) greatly unbalanced data sets, where the researcher typically has only a handful of positive cases and a great many negative cases, (2) the issue of accurate estimates of prediction error rates, where the researcher typically has a relatively small data set upon which to do both model fitting and testing, and (3) the interpretation of the means by which the prediction engine operates and the development of practical prognostic factors. These three problems are essential questions facing the use of modern prediction engines, such as SVMs, NNs, and boosting methods, but have been only lightly studied by the machine learning community. We are in the process of preparing an invited review and tutorial article for the journal Statistics in Medicine, in an effort to introduce, explain and promote these methods for the biostatistical community. We have applied these statistical learning machine methods to (1) a data set involving ischemic stroke six-month functional outcomes (in collaboration with Dr. Andreas Ziegler, University of Luebeck, Germany) and (2) data collected to develop prognostic factors in systemic lupus erythematosus (in collaboration with Dr. Michael Ward, MD, NIAMS/NIH). Research papers are in preparation for both studies. Results include significant improvements in sensitivity and specificity using SVMs and boosting, when compared to conventional logistic regression followed by parameter shrinkage.

Agency
National Institute of Health (NIH)
Institute
Center for Information Technology (CIT)
Type
Intramural Research (Z01)
Project #
1Z01CT000271-01
Application #
6828448
Study Section
(MSCL)
Project Start
Project End
Budget Start
Budget End
Support Year
1
Fiscal Year
2003
Total Cost
Indirect Cost
Name
Computer Research and Technology
Department
Type
DUNS #
City
State
Country
United States
Zip Code
Nicodemus, Kristin K; Malley, James D (2009) Predictor correlation impacts machine learning algorithms: implications for genomic studies. Bioinformatics 25:1884-90
Konig, I R; Malley, J D; Weimar, C et al. (2007) Practical experiences on the necessity of external validation. Stat Med 26:5499-511
Paul, Scott M; Siegel, Karen Lohmann; Malley, James et al. (2007) Evaluating interventions to improve gait in cerebral palsy: a meta-analysis of spatiotemporal measures. Dev Med Child Neurol 49:542-9
Ward, Michael M; Pajevic, Sinisa; Dreyfuss, Jonathan et al. (2006) Short-term prediction of mortality in patients with systemic lupus erythematosus: classification of outcomes using random forests. Arthritis Rheum 55:74-80
O'Hanlon, Terrance P; Carrick, Danielle Mercatante; Targoff, Ira N et al. (2006) Immunogenetic risk and protective factors for the idiopathic inflammatory myopathies: distinct HLA-A, -B, -Cw, -DRB1, and -DQA1 allelic profiles distinguish European American patients with different myositis autoantibodies. Medicine (Baltimore) 85:111-27
O'Hanlon, Terrance P; Rider, Lisa G; Mamyrova, Gulnara et al. (2006) HLA polymorphisms in African Americans with idiopathic inflammatory myopathy: allelic profiles distinguish patients with different clinical phenotypes and myositis autoantibodies. Arthritis Rheum 54:3670-81
Mamyrova, Gulnara; O'Hanlon, Terrance P; Monroe, Jason B et al. (2006) Immunogenetic risk and protective factors for juvenile dermatomyositis in Caucasians. Arthritis Rheum 54:3979-87
O'Hanlon, Terrance P; Carrick, Danielle Mercatante; Arnett, Frank C et al. (2005) Immunogenetic risk and protective factors for the idiopathic inflammatory myopathies: distinct HLA-A, -B, -Cw, -DRB1 and -DQA1 allelic profiles and motifs define clinicopathologic groups in caucasians. Medicine (Baltimore) 84:338-49
Jerebko, Anna K; Malley, James D; Franaszek, Marek et al. (2005) Support vector machines committee classification method for computer-aided polyp detection in CT colonography. Acad Radiol 12:479-86
O'Hanlon, Terrance; Koneru, Bhanu; Bayat, Elham et al. (2004) Immunogenetic differences between Caucasian women with and those without silicone implants in whom myositis develops. Arthritis Rheum 50:3646-50

Showing the most recent 10 out of 12 publications