Automatic Classification of Intrapartal Fetal Heart-Rate Recordings - Can It Compete with Experts?

Fetal heart rate (fHR) is used to evaluate the fetal well-being during the delivery. It provides information of fetal status and allows doctors to detect ongoing hypoxia. Routine clinical evaluation of intrapartal fHR is based on description of macroscopic morphological features of its baseline. In this paper we show, that by using additional features for description of the fHR recordings, we can improve the classification accuracy. Additionally since results of automatic signal evaluation are easily reproducible we can objectify the whole process, thus enabling us to focus on the underlying reasons for high expert inter-observer and intra-observer variability.

[1]  David Ruelle,et al.  Deterministic chaos: the science and the fiction , 1995 .

[2]  G. Magenes,et al.  Identification of fetal sufferance antepartum through a multiparametric analysis and a support vector machine , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  E. Blix,et al.  Inter‐observer variation in assessment of 845 labour admission tests: comparison between midwives and obstetricians in the clinical setting and two experts , 2003, BJOG : an international journal of obstetrics and gynaecology.

[4]  G. Breithardt,et al.  Heart rate variability: standards of measurement, physiological interpretation and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. , 1996 .

[5]  Z. J. Yang,et al.  The prediction of fetal acidosis at birth by computerised analysis of intrapartum cardiotocography , 1995, British journal of obstetrics and gynaecology.

[6]  A. Malliani,et al.  Heart rate variability. Standards of measurement, physiological interpretation, and clinical use , 1996 .

[7]  Ana Paula Rocha,et al.  Linear and nonlinear fetal heart rate analysis of normal and acidemic fetuses in the minutes preceding delivery , 2006, Medical and Biological Engineering and Computing.

[8]  Chrysostomos D. Stylios,et al.  Feature Extraction and Classification of Fetal Heart Rate Using Wavelet Analysis and Support Vector Machines , 2006, Int. J. Artif. Intell. Tools.

[9]  P. Steer.  Has electronic fetal heart rate monitoring made a difference. , 2008, Seminars in fetal & neonatal medicine.

[10]  Arnold Neumaier,et al.  Introduction to Numerical Analysis , 2001 .

[11]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

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

[13]  E. Ifeachor,et al.  A Comparative Study of Fetal Heart Rate Variability Analysis Techniques , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[14]  Chrysostomos D. Stylios,et al.  Novel approach for fetal heart rate classification introducing grammatical evolution , 2007, Biomed. Signal Process. Control..

[15]  Maria G. Signorini,et al.  Classification of cardiotocographic records by neural networks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[16]  R D Keith,et al.  The prediction of fetal acidosis at birth by computerised analysis of intrapartum cardiotocography , 1996, British journal of obstetrics and gynaecology.

[17]  H. Stanley,et al.  Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. , 1995, Chaos.

[18]  Tiina Luukkaala,et al.  Intrapartum cardiotocography – the dilemma of interpretational variation , 2006, Journal of Perinatal Medicine.

[19]  Amparo Alonso-Betanzos,et al.  Intelligent analysis and pattern recognition in cardiotocographic signals using a tightly coupled hybrid system , 2002, Artif. Intell..

[20]  J. V. van Laar,et al.  Spectral analysis of fetal heart rate variability for fetal surveillance: review of the literature , 2008, Acta obstetricia et gynecologica Scandinavica.

[21]  Abraham Lempel,et al.  On the Complexity of Finite Sequences , 1976, IEEE Trans. Inf. Theory.

[22]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[23]  J. P. Marques de Sá,et al.  The Porto system for automated cardiotocographic signal analysis , 1991, Journal of perinatal medicine.

[24]  L. Lhotska,et al.  Assessment of non-linear features for intrapartal fetal heart rate classification , 2009, 2009 9th International Conference on Information Technology and Applications in Biomedicine.

[25]  J. M. Swartjes,et al.  Computer analysis of antepartum fetal heart rate: 2. Detection of accelerations and decelerations. , 1990, International journal of bio-medical computing.

[26]  J. Bernardes,et al.  Evaluation of interobserver agreement of cardiotocograms , 1997, International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics.

[27]  D. Ayres-de- Campos,et al.  SisPorto 2.0: a program for automated analysis of cardiotocograms. , 2000, The Journal of maternal-fetal medicine.

[28]  T. Higuchi.  Approach to an irregular time series on the basis of the fractal theory , 1988 .

[29]  Steven M. Pincus,et al.  Approximate Entropy: A Regularity Measure for Fetal Heart Rate Analysis , 1992, Obstetrics and gynecology.

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

[31]  Ian Witten,et al.  Data Mining , 2000 .

[32]  S. Pincus.  Approximate entropy (ApEn) as a complexity measure. , 1995, Chaos.

[33]  S. Cerutti,et al.  Complexity analysis of 24 hours heart rate variability time series , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[34]  D. Koutsouris,et al.  Computerised intrapartum diagnosis of fetal hypoxia based on fetal heart rate monitoring and fetal pulse oximetry recordings utilising wavelet analysis and neural networks , 2002, BJOG : an international journal of obstetrics and gynaecology.

[35]  D. Percival,et al.  Physiological time series: distinguishing fractal noises from motions , 2000, Pflügers Archiv.

[36]  Chrysostomos D. Stylios,et al.  Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines , 2006, IEEE Transactions on Biomedical Engineering.

[37]  George J. Vachtsevanos,et al.  A comparison of fractal dimension algorithms using synthetic and experimental data , 1999, ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349).

[38]  K. Maršál,et al.  Fetal heart rate patterns and ECG ST segment changes preceding metabolic acidaemia at birth , 2005, BJOG : an international journal of obstetrics and gynaecology.

[39]  J. Sprott.  Chaos and time-series analysis , 2001 .

[40]  J. Stoer,et al.  Introduction to Numerical Analysis , 2002 .

[41]  Pincus Sm,et al.  Approximate Entropy: A Regularity Measure for Fetal Heart Rate Analysis , 1992, Obstetrics and gynecology.