PROJECT TITLE :
Improving Reliability of Monitoring Background EEG Dynamics in Asphyxiated Infants
The goal of this study is to develop an automatic algorithm to quantify background electroencephalography (EEG) dynamics in term neonates with hypoxic ischemic encephalopathy. The recorded EEG signal is adaptively segmented and the segments with low amplitudes are detected. Next, relying on the spatial distribution of the low-amplitude segments, the primary half of the algorithm detects (dynamic) interburst intervals (dIBIs) and performs well on the comparatively artifact-free EEG periods and well-defined burst-suppression EEG periods. But, on testing the algorithm on EEG recordings of more than forty eight h per neonate, a important range of misclassified and dubious detections were encountered. So, as the subsequent step, we have a tendency to applied machine learning classifiers to differentiate between definite dIBI detections and misclassified ones. The developed algorithm achieved a true positive detection rate of ninety eight%, ninety seven%, 88%, and 95% for four period-connected dIBI groups that we tend to subsequently outlined. We tend to benchmarked our algorithm with an expert diagnostic interpretation of EEG periods (one h long) and demonstrated its effectiveness in clinical apply. We tend to show that the detection algorithm effectively discriminates challenging cases encountered inside mild and moderate background abnormalities. The dIBI detection algorithm improves identification of neonates with sensible clinical outcome as compared to the classification primarily based on the classical burst-suppression interburst interval.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here