Prediction of periventricular leukomalacia. Part II: Selection of hemodynamic features using computational intelligence

  • Authors:

  • Biswanath Samanta;Geoffrey L. Bird;Marijn Kuijpers;Robert A. Zimmerman;Gail P. Jarvik;Gil Wernovsky;Robert R. Clancy;Daniel J. Licht;J. William Gaynor;Chandrasekhar Nataraj

  • Affiliations:

  • Department of Mechanical Engineering, Villanova University, 800 Lancaster Avenue, Villanova, PA 19085, USA;Division of Critical Care Medicine and Cardiology, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA;Academic Medical Center, University of Amsterdam, Department of Anesthesiology, Amsterdam, Netherlands;Division of Neuroradiology, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA;Department of Medicine (Medical Genetics), University of Washington, Seattle, WA 98195, USA;Division of Critical Care Medicine and Cardiology, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA;Division of Neurology, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA;Division of Neurology, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA;Division of Cardiothoracic Surgery, Children's Hospital of Philadelphia, Philadelphia, PA 19104, USA;Department of Mechanical Engineering, Villanova University, 800 Lancaster Avenue, Villanova, PA 19085, USA

  • Venue:
  • Artificial Intelligence in Medicine
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Objective: The objective of Part II is to analyze the dataset of extracted hemodynamic features (Case 3 of Part I) through computational intelligence (CI) techniques for identification of potential prognostic factors for periventricular leukomalacia (PVL) occurrence in neonates with congenital heart disease. Methods: The extracted features (Case 3 dataset of Part I) were used as inputs to CI based classifiers, namely, multi-layer perceptron (MLP) and probabilistic neural network (PNN) in combination with genetic algorithms (GA) for selection of the most suitable features predicting the occurrence of PVL. The selected features were next used as inputs to a decision tree (DT) algorithm for generating easily interpretable rules of PVL prediction. Results: Prediction performance for two CI based classifiers, MLP and PNN coupled with GA are presented for different number of selected features. The best prediction performances were achieved with 6 and 7 selected features. The prediction success was 100% in training and the best ranges of sensitivity (SN), specificity (SP) and accuracy (AC) in test were 60-73%, 74-84% and 71-74%, respectively. The identified features when used with the DT algorithm gave best SN, SP and AC in the ranges of 87-90% in training and 80-87%, 74-79% and 79-82% in test. Among the variables selected in CI, systolic and diastolic blood pressures, and pCO"2 figured prominently similar to Part I. Decision tree based rules for prediction of PVL occurrence were obtained using the CI selected features. Conclusions: The proposed approach combines the generalization capability of CI based feature selection approach and generation of easily interpretable classification rules of the decision tree. The combination of CI techniques with DT gave substantially better test prediction performance than using CI and DT separately.