Prediction of occurrence of Periventricular Leukomalacia in neonates after heart surgery using a decision tree algorithm

This paper is concerned with the prediction of the occurrence of Periventricular Leukomalacia (PVL), a form of white-matter brain injury, in neonates after heart surgery. The data which is collected over a period of 12 hours after the cardiac surgery contains measurements with different resolutions. The fact that data is collected at different time scales makes the modeling approach impractical, if not impossible. Hence, the decision tree classification technique has been selected for its capacity for discovering rules and novel associations in the data. It classifies groups based on reducing uncertainty in the classified data. From a physiological point of view we know that there are several regulatory mechanisms responsible for fluctuation of the hemodynamic variables at different time scales. To discover the most important active physiological components which might lead to the occurrence of PVL, we focus on the variation in the data in 1 min, 20 min and 2 hour periods. We calculate the energy of continuous wavelet transform coefficients of vital data at these time scales as a measure of variation in the different time frames. Results obtained from developing decision tree classifiers show that among all variations in all the variables, 2 hour and 20 minute variations in the heart rate and also 1 minute and 20 minute variation in Oxygen saturation are the most important parameters to predict PVL occurrence.