Efficient fetal size classification combined with artificial neural network for estimation of fetal weight

Yueh Chin Cheng, Gwo Lang Yan, Yu Hsien Chiu, Fong Ming Chang, Chiung Hsin Chang, Kao Chi Chung

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Objectives: A novel analysis was undertaken to select a significant ultrasonographic parameter (USP) for classifying fetuses to support artificial neural network (ANN), and thus to enhance the accuracy of fetal weight estimation. Methods: In total, 2127 singletons were examined by prenatal ultrasound within 3 days before delivery. First, correlation analysis was used to determine a significant USP for fetal grouping. Second, K-means algorithm was utilized for fetal size classification based on the selected USP. Finally, stepwise regression analysis was used to examine input parameters of the ANN model. Results: The estimated fetal weight (EFW) of the new model showed mean absolute percent error (MAPE) of 5.26 ± 4.14% and mean absolute error (MAE) of 157.91 ± 119.90 g. Comparison of EFW accuracy showed that the new model significantly outperformed the commonly-used EFW formulas (all p < 0.05). Conclusion: We proved the importance of choosing a specific grouping parameter for ANN to improve EFW accuracy.

Original languageEnglish
Pages (from-to)545-553
Number of pages9
JournalTaiwanese Journal of Obstetrics and Gynecology
Volume51
Issue number4
DOIs
Publication statusPublished - 2012 Dec

All Science Journal Classification (ASJC) codes

  • Obstetrics and Gynaecology

Fingerprint Dive into the research topics of 'Efficient fetal size classification combined with artificial neural network for estimation of fetal weight'. Together they form a unique fingerprint.

Cite this