You could be reading the full-text of this article now if you...

If you have access to this article through your institution,
you can view this article in

Predicting Survival in Patients With Brain Metastases Treated With Radiosurgery Using Artificial Neural Networks

Oermann, Eric K. BS*,‡; Kress, Marie-Adele S. MD; Collins, Brian T. MD; Collins, Sean P. MD, PhD; Morris, David MD§; Ahalt, Stanley C. PhD¶,║; Ewend, Matthew G. MD*

Neurosurgery:
doi: 10.1227/NEU.0b013e31828ea04b
Research-Human-Clinical Studies
Press Release
Abstract

BACKGROUND: Artificial neural networks (ANNs) excel at analyzing challenging data sets and can be exceptional tools for decision support in clinical environments. The present study pilots the use of ANNs for determining prognosis in neuro-oncology patients.

OBJECTIVE: To determine whether ANNs perform better at predicting 1-year survival in a group of patients with brain metastasis compared with traditional predictive tools.

METHODS: ANNs were trained on a multi-institutional data set of radiosurgery patients to predict 1-year survival on the basis of several input factors. A single ANN, an ensemble of 5 ANNs, and logistic regression analyses were compared for efficacy. Sensitivity analysis was used to identify important variables in the ANN model.

RESULTS: A total of 196 patients were divided up into training, testing, and validation data sets consisting of 98, 49, and 49 patients, respectively. Patients surviving at 1 year tended to be female (P = .001) and of good performance status (P = .01) and to have favorable primary tumor histology (P = .001). The pooled voting of 5 ANNs performed significantly better than the multivariate logistic regression model (P = .02), with areas under the curve of 84% and 75%, respectively. The ensemble also significantly outperformed 2 commonly used prognostic indexes. Primary tumor subtype and performance status were identified on sensitivity analysis to be the most important variables for the ANN.

CONCLUSION: ANNs outperform traditional statistical tools and scoring indexes for predicting individual patient prognosis. Their facile implementation, robustness in the presence of missing data, and ability to continuously learn make them excellent choices for use in complicated clinical environments.

ABBREVIATIONS: ANN, artificial neural network

AUC, area under the curve

GPA, Graded Prognostic Assessment

GGS, Golden Grading Scale

MLP, multilayer perceptron

NPV, negative predictive value

PPV, positive predictive value

ROC, receiver-operating characteristic

WBRT, whole-brain radiation therapy

Author Information

*Department of Neurosurgery and the Lineberger Comprehensive Cancer Center;

§Department of Radiation Oncology, and;

Department of Computer Science, University of North Carolina School of Medicine, Chapel Hill, North Carolina;

Department of Radiation Medicine, Georgetown University Hospital, Washington, DC;

Renaissance Computing Institute, Chapel Hill, North Carolina

Correspondence: Matthew Ewend, MD, FACS, Professor and Chair, Department of Neurosurgery, University of North Carolina School of Medicine, PO Box 2151, CB 7060, 170 Manning Dr, Chapel Hill, NC 27599. E-mail: ewend@med.unc.edu

Received August 17, 2012

Accepted February 04, 2012

Copyright © by the Congress of Neurological Surgeons