Establishment of Automated Technique of FHR Baseline and Variability Detection Using CTG: Statistical Comparison with Expert’s Analysis

The most widely accepted method of monitoring the fetal heart rate and uterine activity of the mother is using Cardiotocograph (CTG). It simultaneously captures these two signals and correlate them to find the status of the fetus. This method is preferred by obstetricians since it is non-invasive as well as cost-effective. Though used widely, the specificity and predictive precision has not been undisputable. The main reason behind this is due to the contradiction in clinicians opinions. The two main components of CTG are Baseline and Variability which provide a thorough idea about the state of the fetal-health when CTG signals are inspected visually. These parameters are indicative of the oxygen saturation level in the fetal blood. Automated detection and analysis of these parameters is necessary for early and accurate detection of hypoxia, thus avoiding further compromise. Results of the proposed algorithm were compared with the visual assessment performed by three clinicians in this field using various statistical techniques like Confidence Interval (CI), paired sample t-test and Bland-Altman plot. The agreement between the proposed method and the clinicians’ evaluation is strong.

[1]  G. Dawes,et al.  Numerical analysis of the human fetal heart rate: the quality of ultrasound records. , 1981, American journal of obstetrics and gynecology.

[2]  D. Gavrilis,et al.  Classification of fetal heart rate using grammatical evolution , 2005, IEEE Workshop on Signal Processing Systems Design and Implementation, 2005..

[3]  D. Altman,et al.  Measuring agreement in method comparison studies , 1999, Statistical methods in medical research.

[4]  Amparo Alonso-Betanzos,et al.  The NST-EXPERT project: the need to evolve , 1995, Artif. Intell. Medicine.

[5]  Janusz Jezewski,et al.  Baseline and Acceleration Episodes - Clinically Significant Nonstationarities in FHR Signal: Part II. Indirect Comparison , 2005, CORES.

[6]  Janusz Jezewski,et al.  Baseline and Acceleration Episodes - Clinically Significant Nonstationarities in FHR Signal: Part I. Coefficients of Inconsistency , 2005, CORES.

[7]  Edwin Chandraharan,et al.  Prevention of birth asphyxia: responding appropriately to cardiotocograph (CTG) traces. , 2007, Best practice & research. Clinical obstetrics & gynaecology.

[8]  C. Spong,et al.  The 2008 National Institute of Child Health and Human Development workshop report on electronic fetal monitoring: update on definitions, interpretation, and research guidelines. , 2008, Journal of obstetric, gynecologic, and neonatal nursing : JOGNN.

[9]  Kaushik Roy,et al.  Fuzzy Membership Estimation Using ANN: A Case Study in CTG Analysis , 2014, FICTA.

[10]  Diogo Ayres-de-Campos,et al.  Human factors affecting the interpretation of fetal heart rate tracings: an update , 2012, Current opinion in obstetrics & gynecology.

[11]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[12]  Douglas G. Altman,et al.  Measurement in Medicine: The Analysis of Method Comparison Studies , 1983 .

[13]  Diogo Ayres-de-Campos,et al.  Omniview-SisPorto 3.5 - a central fetal monitoring station with online alerts based on computerized cardiotocogram+ST event analysis. , 2008, Journal of perinatal medicine.

[14]  Kaushik Roy,et al.  A novel approach for extraction and analysis of variability of baseline , 2011, 2011 International Conference on Recent Trends in Information Systems.

[15]  Manuela Ferrario,et al.  Improving the fetal cardiotocographic monitoring by advanced signal processing , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[16]  Amparo Alonso-Betanzos,et al.  Empirical evaluation of a hybrid intelligent monitoring system using different measures of effectiveness , 2002, Artif. Intell. Medicine.