Cover Image

Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor

Objective To investigate the performance of the machine learning (ML) model in predicting small-for-gestational-age (SGA) at birth, using second-trimester data. Methods Retrospective data of 347 patients, consisting of maternal demographics and ultrasound parameters collected between the 20th and 25...

Full description

Saved in:
Bibliographic Details
Main Authors: Saw, Shier Nee, Biswas, Arijit, Mattar, Citra Nurfarah Zaini, Lee, Hwee Kuan, Yap, Choon Hwai
Format: Article
Published: Wiley 2021
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.um.edu.my/27997/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.27997
record_format eprints
spelling my.um.eprints.279972022-07-06T02:35:31Z http://eprints.um.edu.my/27997/ Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor Saw, Shier Nee Biswas, Arijit Mattar, Citra Nurfarah Zaini Lee, Hwee Kuan Yap, Choon Hwai QA75 Electronic computers. Computer science Objective To investigate the performance of the machine learning (ML) model in predicting small-for-gestational-age (SGA) at birth, using second-trimester data. Methods Retrospective data of 347 patients, consisting of maternal demographics and ultrasound parameters collected between the 20th and 25th gestational weeks, were studied. ML models were applied to different combinations of the parameters to predict SGA and severe SGA at birth (defined as 10th and third centile birth weight). Results Using second-trimester measurements, ML models achieved an accuracy of 70% and 73% in predicting SGA and severe SGA whereas clinical guidelines had accuracies of 64% and 48%. Uterine PI (Ut PI) was found to be an important predictor, corroborating with existing literature, but surprisingly, so was nuchal fold thickness (NF). Logistic regression showed that Ut PI and NF were significant predictors and statistical comparisons showed that these parameters were significantly different in disease. Further, including NF was found to improve ML model performance, and vice versa. Conclusion ML could potentially improve the prediction of SGA at birth from second-trimester measurements, and demonstrated reduced NF to be an important predictor. Early prediction of SGA allows closer clinical monitoring, which provides an opportunity to discover any underlying diseases associated with SGA. Wiley 2021-03 Article PeerReviewed Saw, Shier Nee and Biswas, Arijit and Mattar, Citra Nurfarah Zaini and Lee, Hwee Kuan and Yap, Choon Hwai (2021) Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor. Prenatal Diagnosis, 41 (4). pp. 505-516. ISSN 0197-3851, DOI https://doi.org/10.1002/pd.5903 <https://doi.org/10.1002/pd.5903>. 10.1002/pd.5903
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Saw, Shier Nee
Biswas, Arijit
Mattar, Citra Nurfarah Zaini
Lee, Hwee Kuan
Yap, Choon Hwai
Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
description Objective To investigate the performance of the machine learning (ML) model in predicting small-for-gestational-age (SGA) at birth, using second-trimester data. Methods Retrospective data of 347 patients, consisting of maternal demographics and ultrasound parameters collected between the 20th and 25th gestational weeks, were studied. ML models were applied to different combinations of the parameters to predict SGA and severe SGA at birth (defined as 10th and third centile birth weight). Results Using second-trimester measurements, ML models achieved an accuracy of 70% and 73% in predicting SGA and severe SGA whereas clinical guidelines had accuracies of 64% and 48%. Uterine PI (Ut PI) was found to be an important predictor, corroborating with existing literature, but surprisingly, so was nuchal fold thickness (NF). Logistic regression showed that Ut PI and NF were significant predictors and statistical comparisons showed that these parameters were significantly different in disease. Further, including NF was found to improve ML model performance, and vice versa. Conclusion ML could potentially improve the prediction of SGA at birth from second-trimester measurements, and demonstrated reduced NF to be an important predictor. Early prediction of SGA allows closer clinical monitoring, which provides an opportunity to discover any underlying diseases associated with SGA.
format Article
author Saw, Shier Nee
Biswas, Arijit
Mattar, Citra Nurfarah Zaini
Lee, Hwee Kuan
Yap, Choon Hwai
author_facet Saw, Shier Nee
Biswas, Arijit
Mattar, Citra Nurfarah Zaini
Lee, Hwee Kuan
Yap, Choon Hwai
author_sort Saw, Shier Nee
title Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
title_short Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
title_full Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
title_fullStr Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
title_full_unstemmed Machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
title_sort machine learning improves early prediction of small-for-gestational-age births and reveals nuchal fold thickness as unexpected predictor
publisher Wiley
publishDate 2021
url http://eprints.um.edu.my/27997/
_version_ 1738510685592092672
score 13.2353115

Similar Items