TY - GEN
T1 - Prediction of occurrence of Periventricular Leukomalacia in neonates after heart surgery using a decision tree algorithm
AU - Jalali, Ali
AU - Nataraj, C.
N1 - Copyright:
Copyright 2013 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84884624249&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84884624249&partnerID=8YFLogxK
U2 - 10.1115/DETC2012-71301
DO - 10.1115/DETC2012-71301
M3 - Conference contribution
AN - SCOPUS:84884624249
SN - 9780791845004
T3 - Proceedings of the ASME Design Engineering Technical Conference
SP - 217
EP - 222
BT - ASME 2012 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2012
T2 - ASME 2012 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2012
Y2 - 12 August 2012 through 12 August 2012
ER -