论文信息 - Radial Basis Networks and Logistic Regression Method for Prediction of Broncho Pulmonary Dysplasia

Radial Basis Networks and Logistic Regression Method for Prediction of Broncho Pulmonary Dysplasia

The main goal of this paper is prediction of Bronchopulmonary Dysplasia among newborn children. Static and dynamic parameters obtained from hospital database and medical data monitoring system were used to build logistic regression and radial basis function neural networks (RBFN) models.

[1] J. Ribeiro,et al. Risk factors for bronchopulmonary dysplasia in very low birth weight newborns treated with mechanical ventilation in the first week of life. , 2005, Journal of tropical pediatrics.

[2] Tom Fawcett,et al. ROC Graphs: Notes and Practical Considerations for Data Mining Researchers , 2003 .

[3] F. Girosi,et al. Networks for approximation and learning , 1990, Proc. IEEE.

[4] Andrew P. Bradley,et al. The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[5] Matthias Schroder,et al. Logistic Regression: A Self-Learning Text , 2003 .

[6] David W. Hosmer,et al. Applied Logistic Regression , 1991 .

[7] Wieslaw Wajs,et al. Bronchopulmonary Dysplasia Prediction using Logistic Regression , 2006, Sixth International Conference on Intelligent Systems Design and Applications.

[8] John Moody,et al. Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[9] J. Hanley,et al. The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[10] C. Grandi,et al. Bronchopulmonary dysplasia: incidence, risk factors and resource utilization in a population of South American very low birth weight infants. , 2006, Jornal de pediatria.