Automated identification of abnormal fetuses using fetal ECG and Doppler ultrasound signals

Ahsan H. Khandoker, Y. Kimura, M. Palaniswami

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

In this study, we propose an automated algorithm (support vector machines, SVM) to recognize the abnormal fetus using the timings of fetal cardiac events on the basis of analysis of simultaneously recorded fetal ECG (FECG) and Doppler ultrasound (DUS) signal. FECG and DUS signals from 29 fetuses [21 normal and 8 abnormal] were analyzed. Multiresolution wavelet analysis was used to link the frequency contents of the Doppler signals with the opening(o) and closing(c) of the heart's valves [Aortic (A) and Mitral(M)]. Five types of feature, namely 1) R-R intervals, 2) time intervals from R-wave of QRS complex of FECG to opening and closing of aortic valve, i.e. R-Ao 3) R-Ac 4) for the mitral valve R-Mc and 5) R-Mo were extracted from 60 beats and used as inputs to the SVM. Using leave-one-fetus out cross validation technique, an SVM with polynomial kernel (d=3, C=10) correctly recognized 8 abnormal (heart anomalies) fetuses out of 29 fetuses.

Original languageBritish English
Title of host publicationComputers in Cardiology 2009, CinC 2009
Pages709-712
Number of pages4
StatePublished - 2009
Event36th Annual Conference of Computers in Cardiology, CinC 2009 - Park City, UT, United States
Duration: 13 Sep 200916 Sep 2009

Publication series

NameComputers in Cardiology
Volume36
ISSN (Print)0276-6574

Conference

Conference36th Annual Conference of Computers in Cardiology, CinC 2009
Country/TerritoryUnited States
CityPark City, UT
Period13/09/0916/09/09

Fingerprint

Dive into the research topics of 'Automated identification of abnormal fetuses using fetal ECG and Doppler ultrasound signals'. Together they form a unique fingerprint.

Cite this