Format

Send to

Choose Destination
See comment in PubMed Commons below
Taiwan J Obstet Gynecol. 2012 Dec;51(4):545-53. doi: 10.1016/j.tjog.2012.09.009.

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

Author information

1
Department of Biomedical Engineering, National Cheng Kung University, Tainan, Taiwan.

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.

PMID:
23276557
DOI:
10.1016/j.tjog.2012.09.009
[Indexed for MEDLINE]
Free full text
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Support Center