A Comparison of Discriminant Functions and Decision Tree Induction Techniques for Evaluation of Antenatal Fetal Risk Assessment

Abstract

In recent years, the family of methods suitable for classification problems has been extended to include a range of new techniques, such as discriminant functions and decision tree induction. Our purpose is to make a comparison of these classification techniques in antepartum fetal evaluation. The task is to investigate the doppler ultrasound measurements of umbilical artery (UA) to relate the health conditions of fetuses using discriminant functions such as linear discriminant analysis (LDA), multilayer perceptron (MLP) and decision trees (ID3, CART). We use the following UA blood flow velocity waveforms: pulsality index (PI), resistance index (RI) and systolic/diastolic ratio (S/D) in terms of weeks (week index: WI as a normalized value) to decide if there is hypoxia suspicion. With these indices, a specificity and sensitivity are 100% and 93%. It has also been demonstrated that MLP and CART are favorable medical aids to phycisians during intensive surveilance of fetuses.

7 Figures and Tables

Cite this paper

@inproceedings{Guler2010ACO, title={A Comparison of Discriminant Functions and Decision Tree Induction Techniques for Evaluation of Antenatal Fetal Risk Assessment}, author={Nilgun Guler and Olcay Taner Yıldız and Fikret S. Gurgen and Fusun Gulizar Varol and Ethem Alpaydın}, year={2010} }