Title
Using data mining techniques in monitoring diabetes care. The simpler the better?
Abstract
We aim at evaluating how data-mining statistical techniques can be applied on medical records and administrative data of diabetes and how they differ in terms of capabilities of predicting outcomes (e.g. death). Data on 3,892 outpatient patients with a diagnosis of type 2 diabetes from the San Giovanni Battista Hospital in Torino. Six statistical classifiers were applied: Logistic regression (LR), Generalized Additive Model (GAM), Projection pursuit Regression (PPR), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Artificial Neural Networks (ANN). All models selected the same subset of covariates. ANN is the model performing worse, whereas simpler models, like LR, GAM and LDA seem to perform better. GAM is associated with a very small misclassification rate. The agreement in predicting individual outcomes among models is 0.23 (SE 0.06, Kappa). Monitoring on the basis of patients' characteristics is highly dependent from the statistical properties of the chosen statistical model.
Year
DOI
Venue
2011
10.1007/s10916-009-9363-9
J. Medical Systems
Keywords
Field
DocType
monitoring diabetes care,quadratic discriminant analysis,data-mining statistical technique,statistical classifier,artificial neural networks,data mining.diabetescare.mortality. administrative data.clinical predictions,linear discriminant analysis,simpler model,data mining techniques,statistical property,administrative data,generalized additive model,statistical model,medical records,projection pursuit regression,data mining,model selection,logistic regression,artificial neural network
Data mining,Computer science,Artificial intelligence,Artificial neural network,Logistic regression,Covariate,Projection pursuit regression,Statistical model,Linear discriminant analysis,Statistics,Generalized additive model,Machine learning,Quadratic classifier
Journal
Volume
Issue
ISSN
35
2
0148-5598
Citations 
PageRank 
References 
1
0.34
5
Authors
7
Name
Order
Citations
PageRank
Dario Gregori162.20
Michele Petrinco210.68
Simona Bo310.34
Rosalba Rosato410.34
Eva Pagano510.68
Paola Berchialla660.85
Franco Merletti710.68