Two Models for Outcome Prediction - a Comparison of Logistic Regression and Neural Networks

TitelTwo Models for Outcome Prediction - a Comparison of Logistic Regression and Neural Networks
Publication TypeJournal Article
Year of Publication2006
AuthorsLinder R., König I.R., Weimar C., Diener H.C., Pöppl S.J., Ziegler A.
JournalMethods of information in medicine
Volume45
Issue5
Pages536-40
Date Published2006
Publication Languageeng
ISSN0026-1270
SchlüsselwörterAged, Aged, 80 and over, Benchmarking, Disease Progression, Female, Forecasting, Germany, Humans, Logistic Models, Male, Middle Aged, Models, Theoretical, Neural Networks (Computer), Outcome Assessment (Health Care), Stroke
Abstract

OBJECTIVES: Accurately predicting disease progress from a set of predictive variables is an important aspect of clinical work. For binary outcomes, the classical approach is to develop prognostic logistic regression (LR) models. Alternatively, machine learning algorithms were proposed with artificial neural networks (ANN) having become popular over the last decades. Although some studies have compared predictive accuracies of LR and ANN models, some concerns regarding their methodological quality have been voiced. Our comparison has the advantage of being based on two large independent data sets allowing for elaborate model development and independent validation.

METHODS: From the German Stroke Database, a learning data set including 1754 prospectively recruited patients with acute ischemic stroke was used. Utilizing LR and ANN, two prognostic models were developed predicting restitution of functional independence and survival after 100 days. The resulting models were applied to classify 1470 patients with acute ischemic stroke; this test data set was collected independently from the learning data. Error fractions in the test data were determined, and differences in error fractions between the algorithms were calculated with 95% confidence intervals.

RESULTS: For most prognostic models, error fractions in the test data were below 40%. There was no difference between the algorithms except for the model predicting completely versus incompletely restituted or deceased patients (difference in error fractions = 4.01% [2.10-5.96%], p = 0.0001).

CONCLUSIONS: The conscientiously applied LR remains the gold standard for prognostic modelling; however, ANN can be an alternative automated "quick and easy" multivariate analysis.

PubMed Link

http://www.ncbi.nlm.nih.gov/pubmed/17019508?dopt=Abstract

Alternate JournalMethods Inf Med
Erstellt am 2. November 2012 - 17:55 von Kulbe.

Anschrift

Institutssekretariat
Susanne Petersen

Tel+49 451 3101 5601
Fax+49 451 3101 5604


Gebäude 64 (Informatik)

Ratzeburger Allee 160
23538 Lübeck
Deutschland