Using nonlinear features for fetal heart rate classification

J 2012

Using nonlinear features for fetal heart rate classification

SPILKA, J.; V. CHUDÁČEK; M. KOUCKÝ; L. LHOTSKÁ; M. HUPTYCH et al.

Základní údaje

Originální název

Using nonlinear features for fetal heart rate classification

Autoři

SPILKA, J.; V. CHUDÁČEK; M. KOUCKÝ; L. LHOTSKÁ; M. HUPTYCH; Petr JANKŮ ; G. GEORGOULAS a C. STYLIOS

Vydání

Biomedical Signal Processing and Control, OXFORD, ELSEVIER SCI LTD, 2012, 1746-8094

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30214 Obstetrics and gynaecology

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Impakt faktor

Impact factor: 1.074

Označené pro přenos do RIV

Organizační jednotka

Lékařská fakulta

DOI

https://doi.org/10.1016/j.bspc.2011.06.008

UT WoS

000304843400005

Klíčová slova anglicky

Fetal heart rate; Cardiotocography; Nonlinear methods; Feature selection; Classification

Změněno: 22. 4. 2013 17:10, Ing. Mgr. Věra Pospíšilíková

Anotace

V originále

Fetal heart rate (FHR) is used to evaluate fetal well-being and enables clinicians to detect ongoing hypoxia during delivery. Routine clinical evaluation of intrapartum FHR is based on macroscopic morphological features visible to the naked eye. In this paper we evaluated conventional features and compared them to the nonlinear ones in the task of intrapartum FHR classification. The experiments were performed using a database of 217 FUR records with objective annotations, i.e. pH measurement. We have proven that the addition of nonlinear features improves accuracy of classification. The best classification results were achieved using a combination of conventional and nonlinear features with sensitivity of 73.4%, specificity of 76.3%, and F-measure of 71.9%. The best selected nonlinear features were: Lempel Ziv complexity, Sample entropy, and fractal dimension estimated by Higuchi method. Since the results of automatic signal evaluation are easily reproducible, the process of FHR evaluation can become more objective and may enable clinicians to focus on additional non-cardiotocography parameters influencing the fetus during delivery.

Citovat

SPILKA, J.; V. CHUDÁČEK; M. KOUCKÝ; L. LHOTSKÁ; M. HUPTYCH; Petr JANKŮ; G. GEORGOULAS a C. STYLIOS. Using nonlinear features for fetal heart rate classification. Biomedical Signal Processing and Control. OXFORD: ELSEVIER SCI LTD, 2012, roč. 7, č. 4, s. 350-357. ISSN 1746-8094. Dostupné z: https://doi.org/10.1016/j.bspc.2011.06.008.

@article{1088407,
   author = {Spilka, J. and Chudáček, V. and Koucký, M. and Lhotská, L. and Huptych, M. and Janků, Petr and Georgoulas, G. and Stylios, C.},
   article_location = {OXFORD},
   article_number = {4},
   doi = {https://doi.org/10.1016/j.bspc.2011.06.008},
   keywords = {Fetal heart rate; Cardiotocography; Nonlinear methods; Feature selection; Classification},
   language = {eng},
   issn = {1746-8094},
   journal = {Biomedical Signal Processing and Control},
   title = {Using nonlinear features for fetal heart rate classification},
   volume = {7},
   year = {2012}
}

TY  - JOUR
ID  - 1088407
AU  - Spilka, J. - Chudáček, V. - Koucký, M. - Lhotská, L. - Huptych, M. - Janků, Petr - Georgoulas, G. - Stylios, C.
PY  - 2012
TI  - Using nonlinear features for fetal heart rate classification
JF  - Biomedical Signal Processing and Control
VL  - 7
IS  - 4
SP  - 350-357
EP  - 350-357
PB  - ELSEVIER SCI LTD
SN  - 17468094
KW  - Fetal heart rate
KW  - Cardiotocography
KW  - Nonlinear methods
KW  - Feature selection
KW  - Classification
N2  - Fetal heart rate (FHR) is used to evaluate fetal well-being and enables clinicians to detect ongoing hypoxia during delivery. Routine clinical evaluation of intrapartum FHR is based on macroscopic morphological features visible to the naked eye. In this paper we evaluated conventional features and compared them to the nonlinear ones in the task of intrapartum FHR classification. The experiments were performed using a database of 217 FUR records with objective annotations, i.e. pH measurement. We have proven that the addition of nonlinear features improves accuracy of classification. The best classification results were achieved using a combination of conventional and nonlinear features with sensitivity of 73.4%, specificity of 76.3%, and F-measure of 71.9%. The best selected nonlinear features were: Lempel Ziv complexity, Sample entropy, and fractal dimension estimated by Higuchi method. Since the results of automatic signal evaluation are easily reproducible, the process of FHR evaluation can become more objective and may enable clinicians to focus on additional non-cardiotocography parameters influencing the fetus during delivery.
ER  -

SPILKA, J.; V. CHUDÁČEK; M. KOUCKÝ; L. LHOTSKÁ; M. HUPTYCH; Petr JANKŮ; G. GEORGOULAS a C. STYLIOS. Using nonlinear features for fetal heart rate classification. \textit{Biomedical Signal Processing and Control}. OXFORD: ELSEVIER SCI LTD, 2012, roč.~7, č.~4, s.~350-357. ISSN~1746-8094. Dostupné z: https://doi.org/10.1016/j.bspc.2011.06.008.

Přehled o publikaci