2021
DOI: 10.1101/2021.06.16.21258884
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Abstract: Prognostic prediction of prelabor rupture of membrane (PROM) lacks of sample size and external validation. We compared a statistical model, machine learning algorithms, and a deep-insight visible neural network (DI-VNN) for PROM and estimating the time of delivery. We selected visits, including PROM (n=23,791/170,730), retrospectively from a nationwide health insurance dataset. DI-VNN achieved the best prediction (area under receiver operating characteristics curve [AUROC] 0.73, 95% CI 0.72 to 0.75). Meanwhile… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

1
1
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 81 publications
1
1
0
Order By: Relevance
“…To our knowledge, this is the first study to use machine learning methods for quantitative analysis of EDCs with delivery time. We found the EDCs and EHs can also be used to predict the timing of a delivery event within a defined period approaching the labor events, and the accuracy of this prediction method was similar to the previous reported literature (AUROC of 0.7-0.9) [ 30 , 33 ]. In addition, our results can reflect the effect of environmental chemical exposure on human pregnancy.…”
Section: Discussionsupporting
confidence: 86%
“…To our knowledge, this is the first study to use machine learning methods for quantitative analysis of EDCs with delivery time. We found the EDCs and EHs can also be used to predict the timing of a delivery event within a defined period approaching the labor events, and the accuracy of this prediction method was similar to the previous reported literature (AUROC of 0.7-0.9) [ 30 , 33 ]. In addition, our results can reflect the effect of environmental chemical exposure on human pregnancy.…”
Section: Discussionsupporting
confidence: 86%
“…One of the pregnancy complications that motivates researchers to explore ML solutions is Prelabor Rupture of Membranes (PROM). Sufriyana et al [43] aimed to predict the likelihood of PROM and delivery time. There were five ML and statistical techniques compared: Ridge Regression (RR), Elastic Net Regression (ENR), RF, Gradient Boosting (GB) models, and the Deep-Insight Visible Neural Network (DI-VNN).…”
Section: Pretermmentioning
confidence: 99%