Cardiotocography (CTG) is a standard tool for the assessment of fetal well-being during pregnancy and delivery. However, its interpretation is associated with high inter- and intra-observer variability. Since its introduction there have been numerous attempts to develop computerized systems assisting the evaluation of the CTG recording. Nevertheless these systems are still hardly used in a delivery ward. Two main approaches to computerized evaluation are encountered in the literature; the first one emulates existing guidelines, while the second one is more of a data-driven approach using signal processing and computational methods. The latter employs preprocessing, feature extraction/selection and a classifier that discriminates between two or more classes/conditions. These classes are often formed using the umbilical cord artery pH value measured after delivery. In this work an approach to Fetal Heart Rate (FHR) classification using pH is presented that could serve as a benchmark for reporting results on the unique open-access CTU-UHB CTG database, the largest and the only freely available database of this kind. The overall results using a very small number of features and a Least Squares Support Vector Machine (LS-SVM) classifier, are in accordance to the ones encountered in the literature and outperform the results of a baseline classification scheme proving the utility of using advanced data processing methods. Therefore the achieved results can be used as a benchmark for future research involving more informative features and/or better classification algorithms.

CIIRC Czech Technical University Prague Czech Republic Prague Czech Republic

Control Engineering Group Department of Computer Science Electrical and Space Engineering Luleå University of Technology SE 97187 Luleå Sweden

Laboratory of Knowledge and Intelligent Computing Department of Computer Engineering Technological Educational Institute of Epirus Arta Kostakioi Greece

Zobrazit více v PubMed

Amer-Wåhlin I, Maršál K. ST analysis of fetal electrocardiography in labor. Semin Fetal Neonatal Med. 2011;16(1):29–35. doi: 10.1016/j.siny.2010.09.004. PubMed DOI

Stout MJ, Cahill AG. Electronic fetal monitoring: past, present, and future. Clin Perinatol. 2011;38(1):127–142. doi: 10.1016/j.clp.2010.12.002. PubMed DOI

FIGO Guidelines for the use of fetal monitoring. Int J Gynaecol Obstet. 1986;25:159–167.

Bernardes J, Costa-Pereira A, Ayres-de-Campos D, Geijn HP, Pereira-Leite L. Evaluation of interobserver agreement of cardiotocograms. Int J Gynecol Obset. 1997;57(1):33–37. doi: 10.1016/S0020-7292(97)02846-4. PubMed DOI

Hruban L, Spilka J, Chudáček V, Janků P, Huptych M, Burša M, Hudec A, Kacerovský M, Kacerovský M, Koucký M, Procházka M, Korečko V, Seget’a J, Šimetka O, Měchurová A, Lhotská L. Agreement on intrapartum cardiotocogram recordings between expert obstetricians. J Eval Clin Pract. 2015;21:694–702. doi: 10.1111/jep.12368. PubMed DOI

Steer PJ. Has electronic fetal heart rate monitoring made a difference. Semin Fetal Neonatal Med. 2008;13(1):2–7. doi: 10.1016/j.siny.2007.09.005. PubMed DOI

Ayres-de-Campos D, Ugwumadu A, Banfield P, Lynch P, Amin P, Horwell D, Santos A, Bernardes J, Rosen K. A randomized clinical trial of intrapartum fetal monitoring with computer analysis and alerts versus previously available monitoring. BMC pregnancy and childbirth. 2010;10(1):71. doi: 10.1186/1471-2393-10-71. PubMed DOI PMC

Visser GH, Dawes GS, Redman CW. Numerical analysis of the normal human antenatal fetal heart rate. BJOG. 1981;88(8):792–802. doi: 10.1111/j.1471-0528.1981.tb01305.x. PubMed DOI

Ayres-de-Campos D, Bernardes J, Garrido A, Sa J, Pereira-Leite L. SisPorto 2.0: a program for automated analysis of cardiotocograms. J Matern Fetal Med. 2001;9(5):311–318. PubMed

Task-Force 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. Eur Heart J. 1996;17(3):354–381. doi: 10.1093/oxfordjournals.eurheartj.a014868. PubMed DOI

Magenes G, Signorini MG, Arduini D. Classification of cardiotocographic records by neural networks. Proceedings IEEE-INNS-ENNS, 2000. International Joint Conference on Neural Networks IJCNN. 2000;3:637–641.

Goncalves H, Rocha AP, Campos DA, Bernardes J. Linear and non linear fetal heart rate analysis of normal and acidemic fetuses in the minutes preceding delivery. Med Biol Eng Comput. 2006;44(10):847–855. doi: 10.1007/s11517-006-0105-6. PubMed DOI

Spilka J, Chudáček V, Koucký M, Lhotská L, Huptych M, Janků P, Georgoulas G, Stylios C. Using nonlinear features for fetal heart rate classification. Biomedical Signal Processing Control. 2012;7(4):350–357. doi: 10.1016/j.bspc.2011.06.008. DOI

Georgoulas G, Stylios C, Groumpos P. Feature extraction and classification of fetal heart rate using wavelet analysis and support vector machines. International Journal Artificial Intelligence Tools. 2006;15(03):411–432. doi: 10.1142/S0218213006002746. DOI

Krupa N, Mohd AM, Zahedi E, Ahmed S, Hassan FM. Antepartum fetal heart rate feature extraction and classification using empirical mode decomposition and support vector machine. Biomed Eng Online. 2011; doi:10.1186/1475-925X-10-6. PubMed PMC

Georgoulas G, Gavrilis D, Tsoulos I, Stylios C, Bernardes J, Groumpos P. Novel approach for fetal heart rate classification introducing grammatical evolution. Biomedical Signal Processing Control. 2007;2(2):69–79. doi: 10.1016/j.bspc.2007.05.003. DOI

Warrick PA, Hamilton EF, Precup D, Kearney RE. Classification of normal and hypoxic fetuses from systems modeling of intrapartum cardiotocography. IEEE Trans Biomed Eng. 2010;57(4):771–779. doi: 10.1109/TBME.2009.2035818. PubMed DOI

Georgoulas G, Stylios C, Groumpos P. Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines. IEEE Trans Biomed Eng. 2006;53(5):875–884. doi: 10.1109/TBME.2006.872814. PubMed DOI

Xu L, Redman CW, Payne SJ, Georgieva A. Feature selection using genetic algorithms for fetal heart rate analysis. Physiol Meas. 2014;35(7):1357–1371. doi: 10.1088/0967-3334/35/7/1357. PubMed DOI

Czabanski R, Jezewski J, Wrobel J, Horoba K. Predicting the risk of low-fetal birth weight from cardiotocographic signals using ANBLIR system with deterministic annealing and-insensitive learning. IEEE Trans Inf Technology Biomedicine. 2010;14(4):1062–1074. doi: 10.1109/TITB.2009.2039644. PubMed DOI

Georgieva A, Payne SJ, Moulden M, Redman CW. Artificial neural networks applied to fetal monitoring in labour. Neural Comput & Applic. 2013;22(1):85–93. doi: 10.1007/s00521-011-0743-y. DOI

Jezewski M, Wrobel J, Labaj P, Leski J, Henzel N, Horoba K, et al. Some practical remarks on neural networks approach to fetal cardiotocograms classification. Proceedings 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon: August 2007. p. 5170–3. PubMed

Dash S, Quirk JG, Djuric PM. Fetal heart rate classification using generative models. IEEE Trans Biomed Eng. 2014;61(11):2796–2805. doi: 10.1109/TBME.2014.2330556. PubMed DOI

Czabanski R, Jezewski J, Matonia A, Jezewski M. Computerized analysis of fetal heart rate signals as the predictor of neonatal academia. Expert Syst Appl. 2012;39(15):11846–11860. doi: 10.1016/j.eswa.2012.01.196. DOI

Czabanski R, Wrobel J, Jezewski J, Jezewski M. Two-step analysis of the fetal heart rate signal as a predictor of distress. Proceedings 4th Asian conference intelligent information and database systems. 2012b. pp 431–8.

Georgoulas G, Stylios CD, Nokas G, Groumpos P. Classification of fetal heart rate during labour using hidden Markov models. Proceedings IEEE International Joint Conference on Neural Networks. 2004;3:2471–2475.

Costa MD, Schnettler WT, Amorim-Costa C, Bernardes J, Costa A, Goldberger AL, Ayres-de-Campos D. Complexity-loss in fetal heart rate dynamics during labor as a potential biomarker of academia. Early Hum Dev. 2014;90(1):67–71. doi: 10.1016/j.earlhumdev.2013.10.002. PubMed DOI PMC

Georgieva A, Papageorghiou AT, Payne SJ, Moulden M, Redman CWG. Phase-rectified signal averaging for intrapartum electronic fetal heart rate monitoring is related to acidaemia at birth. BJOG. 2014;121(7):889–894. doi: 10.1111/1471-0528.12568. PubMed DOI

Costa A, Ayres-de-Campos D, Costa F, Santos C, Bernardes J. Prediction of neonatal acidemia by computer analysis of fetal heart rate and ST event signals. Am J Obstet Gynecol. 2009;201(5):464–4e1. doi: 10.1016/j.ajog.2009.04.033. PubMed DOI

Keith RD, Beckley S, Garibaldi JM, Westgate JA, Ifeachor EC, Greene KR. A multicentre comparative study of 17 experts and an intelligent computer system for managing labour using the cardiotocogram. BJOG. 1995;102(9):688–700. doi: 10.1111/j.1471-0528.1995.tb11425.x. PubMed DOI

Georgieva A, Moulden M, Redman CWG. Umbilical cord gases in relation to the neonatal condition: the EveREst plot. Eur J Obstet Gynecol Reprod Biol. 2013;168(2):155–160. doi: 10.1016/j.ejogrb.2013.01.003. PubMed DOI

Spilka J. Complex approach to fetal heart rate analysis: a hierarchical classification model. PhD Thesis, at Czech Technical University in Prague Department of Cybernetics. 2013.

Chudáček V, Spilka J, Burša M, Janků P, Hruban L, Huptych M, Lhotská L. Open access intrapartum CTG database. BMC Pregnancy and Childbirth. 2014;14:16. doi: 10.1186/1471-2393-14-16. PubMed DOI PMC

Spilka J, Georgoulas G, Karvelis P, Oikonomou V, Chudáček V, Stylios C, et al. Automatic evaluation of FHR recordings from CTU-UHB CTG database. In: Information technology in bio-and medical informatics; 2013. p. 47–61.

Ayres-de-Campos D, Rei M, Nunes I, Sousa P, Bernardes J. SisPorto 4.0–computer analysis following the 2015 FIGO guidelines for intrapartum fetal monitoring. J Matern Fetal Neonatal Med. 2016 doi:10.3109/14767058.2016.1161750. PubMed

Oikonomou VP, Spilka J, Stylios CD, Lhotská L. An adaptive method for the recovery of missing samples from FHR time series. Proceedings CBMS; 2013. p 337–42.

Krupa BN, Ali MM, Zahedi E. The application of empirical mode decomposition for the enhancement of cardiotocograph signals. Physiol Meas. 2009;30(8):729. doi: 10.1088/0967-3334/30/8/001. PubMed DOI

deHaan J, Bemmel J, Versteeg B, Veth A, Stolte L, Janssens J, Eskes T. Quantitative evaluation of fetal heart rate patterns: I. Processing methods. Eur J Obstet Gynecol Reprod Biol. 1971;1(3):95–102. doi: 10.1016/0028-2243(71)90056-6. DOI

Yeh SY, Forsythe A, Hon EH. Quantification of fetal heart beat-to-beat interval differences. Obstet Gynecol. 1973;41(3):355–363. PubMed

Pardey J, Moulden J, Redman C. A computer system for the numerical analysis of nonstress tests. Am J Obstet Gynecol. 2002;186(5):1095–1103. doi: 10.1067/mob.2002.122447. PubMed DOI

Signorini MG, Magenes G, Cerutti S, Arduini D. Linear and nonlinear parameters for the analysis of fetal heart rate signal from cardiotocographic recordings. IEEE Trans Biomed Eng. 2003;50(3):365–374. doi: 10.1109/TBME.2003.808824. PubMed DOI

Kinsner W. Batch and real-time computation of a fractal dimension based on variance of a time series. Technical report. Department of Electrical & Computer Engineering, University of Manitoba, Winnipeg. 1994.

Sevcik C. A procedure to estimate the fractal dimension of waveforms. Complex Int. 1998;5:1–19. http://arxiv.org/pdf/1003.5266.pdf.

Higuchi T. Approach to an irregular time series on the basis of the fractal theory. Phys D. 1988;31(2):277–283. doi: 10.1016/0167-2789(88)90081-4. DOI

Peng CK, Havlin S, Stanley HE, Goldberger AL. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos. 1995;5(1):82–87. doi: 10.1063/1.166141. PubMed DOI

Pincus S. Approximate entropy (ApEn) as a complexity measure. Chaos. 1995;5(1):110–117. doi: 10.1063/1.166092. PubMed DOI

Richman JS, Moorman JR. Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol. 2000;278(6):2039–2049. PubMed

Lempel A, Ziv J. On the complexity of finite sequences. IEEE Trans Information Theory. 1976;22(1):75–81. doi: 10.1109/TIT.1976.1055501. DOI

Chudáček V, Spilka J, Janků P, Koucký M, Lhotská L, Huptych M. Automatic evaluation of intrapartum fetal heart rate recordings: a comprehensive analysis of useful features. Physiol Meas. 2011;32(8):1347–1360. doi: 10.1088/0967-3334/32/8/022. PubMed DOI

Bernardes J, Moura C, de Sa JP, Leite LP. The Porto system for automated cardiotocographic signal analysis. J Perinat Med. 1991;19:61–65. doi: 10.1515/jpme.1991.19.1-2.61. PubMed DOI

Theodoridis S, Koutroumbas K. Pattern recognition. 4th ed London: Academic Press; 2009.

Guyon I, Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res. 2003;3:1157–1182.

Liu H, Motoda H. Computational methods of feature selection. Boca Raton: CRC Press; 2010.

Wasikowski M, Xue-wen C. Combating the small sample class imbalance problem using feature selection. IEEE Trans Knowledge Data Engineering. 2010;22(10):1388–1400. doi: 10.1109/TKDE.2009.187. DOI

DeLong E, DeLong D, Clarke-Peterson D. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1998;44:837–845. doi: 10.2307/2531595. PubMed DOI

Maloof M. Learning when data sets are imbalanced and when costs are unequal and unknown. In: Workshop on Learning from Imbalanced Data Sets II ICML; 2003.

Joachims T. Text categorization with support vector machines: learning with many relevant features, Poceedings ECML-98. 1998; p. 137–42.

Suykens JAK, Vandewalle J. Least Squares support vector machine classifiers. Neural Process Lett. 1999;9:293–300. doi: 10.1023/A:1018628609742. DOI

Ding LZ, Liao S. Approximate model selection for large scale LSSVM. Proceedings ACML. 2011. p. 165–80.

Osuna EE, Freund R, Girosi F. Support vector machines: training and applications, MIT, A.I. Memo. no. 1602. 1997.

Luts J, Ojeda F, Van de Plas R, De Moor B, Van Huffel S, Suykens JA. A tutorial on support vector machine-based methods for classification problems in chemometrics. Anal Chim Acta. 2010;665(2):129–145. doi: 10.1016/j.aca.2010.03.030. PubMed DOI

Tan P, Steinbach M, Kumar V. Introduction to data mining. Reading: Addison-Wesley; 2006.

Yanmin S, Kamel M, Wong A, Wang Y. Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn. 2007;40(12):3358–3378. doi: 10.1016/j.patcog.2007.04.009. DOI

Matthews BW. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA) - Protein Structure. 1975;405(2):442–451. doi: 10.1016/0005-2795(75)90109-9. PubMed DOI

Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority oversampling technique. J Artif Intell Res. 2002;16:321–357.

van der Maaten LJ, Postma EO, van den Herik HJ. Dimensionality reduction: a comparative review. J Mach Learn Res. 2009;10:66–71.

Hand DJ. Classifier technology and the illusion of progress. Stat Sci. 2006;21(1):1–14. doi: 10.1214/088342306000000060. PubMed DOI

Ayres-de-Campos D, Sousa P, Costa A, Bernardes J. Omniview-SisPorto® 3.5–a central fetal monitoring station with online alerts based on computerized cardiotocogram+ ST event analysis. J Perinat Med. 2008;36(3):260–264. doi: 10.1515/JPM.2008.030. PubMed DOI

Rotariu C, Pasarica A, Costin H, Nemescu D. Spectral analysis of fetal heart rate variability associated with fetal acidosis and base deficit values. Proceedings IEEE International Conference on Development and Application Systems (DAS). 2014a. p. 210–13.

Rotariu C, Pasarica A, Andruseac G, Costin H, Nemescu D. Automatic analysis of the fetal heart rate variability and uterine contractions. Proceedigns international conference and exposition on Electrical and Power Engineering (EPE). 2014b. p. 553–56.

Warmerdam GJJ, Vullings R, Van Laar J, Bergmans JWM, Schmitt L, Oei SG. Using uterine activity to improve fetal heart rate variability analysis for detection of asphyxia during labor. Physiol Meas. 2016;37(3):387. doi: 10.1088/0967-3334/37/3/387. PubMed DOI

Gonçalves H, Pinto P, Silva M, Ayres-de-Campos D, Bernardes J. Toward the improvement in fetal monitoring during labor with the inclusion of maternal heart rate analysis. Med Biol Eng Comput. 2015; doi:10.1007/s11517-015-1359-7. PubMed

Spilka J, Chudáček V, Janků P, Hruban L, Burša M, Huptych M, Zach L, Lhotská L. Analysis of obstetricians’ decision making on CTG recordings. J Biomed Inform. 2014;51:72–79. doi: 10.1016/j.jbi.2014.04.010. PubMed DOI

Georgoulas G, Spilka J, Karvelis P, Chudáček V, Stylios C, Lhotská L. A three class treatment of the FHR classification problem using latent class analysis labeling. Proceedings 36th IEEE Engineering in Medicine and Biology Society Conference (EMBC). 2014. p. 46–9. PubMed

Karvelis P, Spilka J, Georgoulas G, Chudáček V, Stylios CD, Lhotská L. Combining latent class analysis labeling with multiclass approach for fetal heart rate categorization. Physiol Meas. 2015;36(5):1001–1024. doi: 10.1088/0967-3334/36/5/1001. PubMed DOI