Zeeshan Syed, PhD,1,2 Adam Wolfberg, MD, MPH,3,4 John Guttag, PhD.1
1Massachusetts Institute of Technology, 2University of Michigan, 3Tufts Medical Center, 4Children’s Hospital, Boston
To evaluate the use of fetal ECG entrophy to predict fetal inflammation.
Fetal EKG data were recorded during labor using a GE Corometric 120® fetal
monitor from six women who had a scalp electrode placed for a clinical indication at term. We measured the morphologic entropy of the fetal ECG
signal using an unsupervised
The algorithm first partitioned heart beats into classes of activity based on their morphology, and then computed the entropy of the symbolic sequence
obtained by replacing each beat in the original signal with a label
corresponding to its morphologic class.
Interleukin-6 (IL-6), IL-8, and neuron-specific enolase (NSE) levels were measurd in the umbilical cord serum.
Morphologic entrophy showed
a statistically significant linear accociation (p<0.05) with IL-6, IL-8, and NSE levels.
There was no association observed between heart-rate variability and any of the measured serum levels.
Morphologic entrophy of the fetal ECG signal may provide a noninvasive means to detect inflammation prior to the development of chorioamnionitis.
Acknowledgement: Center for the Integration of Medicine and Innovative Technology (CIMIT). Industrial Technology Research Institute Taiwan. Texas Instruments, Obstetrix, Research Grant.
© 2017-2018 Mindchild Medical, Inc. | 1600 Osgood Street | Suite 2017 | North Andover, MA 01845 | firstname.lastname@example.org | 978.566.9880