• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于深度神经网络的胎儿体重估计：一项回顾性观察研究。

Fetal weight estimation based on deep neural network: a retrospective observational study.

机构信息

International Peace Maternity and Child Health Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, 200030, China.

Shanghai Key Laboratory of Embryo Original Diseases, Shanghai, 200030, China.

出版信息

BMC Pregnancy Childbirth. 2023 Aug 2;23(1):560. doi: 10.1186/s12884-023-05819-8.

DOI:10.1186/s12884-023-05819-8
PMID:37533038
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10394792/
Abstract

BACKGROUND

Improving the accuracy of estimated fetal weight (EFW) calculation can contribute to decision-making for obstetricians and decrease perinatal complications. This study aimed to develop a deep neural network (DNN) model for EFW based on obstetric electronic health records.

METHODS

This study retrospectively analyzed the electronic health records of pregnant women with live births delivery at the obstetrics department of International Peace Maternity & Child Health Hospital between January 2016 and December 2018. The DNN model was evaluated using Hadlock's formula and multiple linear regression.

RESULTS

A total of 34824 live births (23922 primiparas) from 49896 pregnant women were analyzed. The root-mean-square error of DNN model was 189.64 g (95% CI 187.95 g-191.16 g), and the mean absolute percentage error was 5.79% (95%CI: 5.70%-5.81%), significantly lower compared to Hadlock's formula (240.36 g and 6.46%, respectively). By combining with previously unreported factors, such as birth weight of prior pregnancies, a concise and effective DNN model was built based on only 10 parameters. Accuracy rate of a new model increased from 76.08% to 83.87%, with root-mean-square error of only 243.80 g.

CONCLUSIONS

Proposed DNN model for EFW calculation is more accurate than previous approaches in this area and be adopted for better decision making related to fetal monitoring.

摘要

背景

提高估计胎儿体重（EFW）计算的准确性有助于产科医生做出决策，并减少围产期并发症。本研究旨在基于产科电子健康记录开发一种用于 EFW 的深度神经网络（DNN）模型。

方法

本研究回顾性分析了 2016 年 1 月至 2018 年 12 月在国际和平妇幼保健院妇产科分娩的活产孕妇的电子健康记录。使用 Hadlock 公式和多元线性回归评估 DNN 模型。

结果

共分析了 49896 名孕妇的 34824 例活产（23922 例初产妇）。DNN 模型的均方根误差为 189.64g（95%CI 187.95g-191.16g），平均绝对百分比误差为 5.79%（95%CI：5.70%-5.81%），明显低于 Hadlock 公式（分别为 240.36g 和 6.46%）。通过结合先前未报告的因素，如先前妊娠的出生体重，仅基于 10 个参数构建了一个简洁有效的 DNN 模型。新模型的准确率从 76.08%提高到 83.87%，均方根误差仅为 243.80g。

结论

提出的用于 EFW 计算的 DNN 模型比该领域以前的方法更准确，可用于更好地做出与胎儿监测相关的决策。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/67a1ba7f6386/12884_2023_5819_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/6269031163f7/12884_2023_5819_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/2731269d4690/12884_2023_5819_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/4b68d4dd99ba/12884_2023_5819_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/4e05fcadea84/12884_2023_5819_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/cb3960bd7e0c/12884_2023_5819_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/8c1b6b80cfb0/12884_2023_5819_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/72cdd452f004/12884_2023_5819_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/67a1ba7f6386/12884_2023_5819_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/6269031163f7/12884_2023_5819_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/2731269d4690/12884_2023_5819_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/4b68d4dd99ba/12884_2023_5819_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/4e05fcadea84/12884_2023_5819_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/cb3960bd7e0c/12884_2023_5819_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/8c1b6b80cfb0/12884_2023_5819_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/72cdd452f004/12884_2023_5819_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7e6a/10394792/67a1ba7f6386/12884_2023_5819_Fig8_HTML.jpg

相似文献

1
Fetal weight estimation based on deep neural network: a retrospective observational study.基于深度神经网络的胎儿体重估计：一项回顾性观察研究。
BMC Pregnancy Childbirth. 2023 Aug 2;23(1):560. doi: 10.1186/s12884-023-05819-8.
2
Estimating fetal weight in gastroschisis: A 10 year audit of outcomes at the National Maternity Hospital.估算先天性腹壁裂胎儿体重：国家妇产医院 10 年的结局回顾。
Int J Gynaecol Obstet. 2024 Sep;166(3):1198-1202. doi: 10.1002/ijgo.15525. Epub 2024 Apr 4.
3
Ultrasonographic fetal thigh measurement in the estimation of fetal weight based on Isobe's formula in women with an engaged fetal head in the pelvis: a comparative study.经耻骨联合上方胎儿头测量超声股骨长度估计胎儿体重的比较研究：基于 Isobe 公式。
J Ultrasound. 2022 Dec;25(4):805-814. doi: 10.1007/s40477-022-00662-7. Epub 2022 Apr 17.
4
Fetal growth restriction and intra-uterine growth restriction: guidelines for clinical practice from the French College of Gynaecologists and Obstetricians.胎儿生长受限与宫内生长受限：法国妇产科医师学院临床实践指南
Eur J Obstet Gynecol Reprod Biol. 2015 Oct;193:10-8. doi: 10.1016/j.ejogrb.2015.06.021. Epub 2015 Jul 2.
5
[Accuracy of ultrasound estimated fetal weight at term].[超声估计足月胎儿体重的准确性]
Gynecol Obstet Fertil. 2016 Jul-Aug;44(7-8):391-5. doi: 10.1016/j.gyobfe.2016.05.005. Epub 2016 Jul 15.
6
Reliability of sonographic fetal weight estimation in triplet pregnancies: a retrospective cohort study.超声估计三胎妊娠胎儿体重的可靠性：一项回顾性队列研究。
Arch Gynecol Obstet. 2018 Jun;297(6):1441-1447. doi: 10.1007/s00404-018-4746-0. Epub 2018 Mar 17.
7
Greater estimated fetal weight and birth weight in IVF/ICSI pregnancy after frozen-thawed vs fresh blastocyst transfer: prospective cohort study with novel unified modeling methodology.冻融后与新鲜囊胚移植相比，体外受精/卵胞浆内单精子注射妊娠中估计胎儿体重和出生体重更大：采用新型统一建模方法的前瞻性队列研究。
Ultrasound Obstet Gynecol. 2022 Jul;60(1):76-85. doi: 10.1002/uog.24806.
8
The birth weight of macrosomia influence the accuracy of ultrasound estimation of fetal weight at term.巨大儿的出生体重会影响足月时超声估计胎儿体重的准确性。
J Clin Ultrasound. 2022 Sep;50(7):967-973. doi: 10.1002/jcu.23236. Epub 2022 Jun 18.
9
Impact of chemotherapy during pregnancy on fetal growth.孕期化疗对胎儿生长的影响。
J Matern Fetal Neonatal Med. 2022 Dec;35(26):10314-10323. doi: 10.1080/14767058.2022.2128645. Epub 2022 Oct 6.
10
Limitations of clinical and sonographic estimates of birth weight: experience with 1034 parturients.临床及超声估计出生体重的局限性：1034例产妇的经验
Obstet Gynecol. 1998 Jan;91(1):72-7. doi: 10.1016/s0029-7844(97)00590-5.

引用本文的文献

1
Application of artificial intelligence in VSD prenatal diagnosis from fetal heart ultrasound images.人工智能在胎儿心脏超声图像 VSD 产前诊断中的应用。
BMC Pregnancy Childbirth. 2024 Nov 16;24(1):758. doi: 10.1186/s12884-024-06916-y.
2
Identifying First-Trimester Risk Factors for SGA-LGA Using Weighted Inheritance Voting Ensemble Learning.使用加权遗传投票集成学习法识别小于胎龄儿-大于胎龄儿的孕早期风险因素。
Bioengineering (Basel). 2024 Jun 27;11(7):657. doi: 10.3390/bioengineering11070657.
3
Prediction of Alzheimer's Disease Based on 3D Genome Selected circRNA.

本文引用的文献

1
Association Between Maternal Fasting Plasma Glucose Value and Fetal Weight Among Singletons of Mothers with Gestational Diabetes Mellitus.妊娠期糖尿病母亲单胎妊娠中母亲空腹血糖值与胎儿体重之间的关联
Diabetes Metab Syndr Obes. 2022 Dec 10;15:3799-3807. doi: 10.2147/DMSO.S391253. eCollection 2022.
2
Measuring intrauterine growth in healthy pregnancies using quantitative magnetic resonance imaging.应用定量磁共振成像技术测量健康妊娠的宫内胎儿生长情况。
J Perinatol. 2022 Jul;42(7):860-865. doi: 10.1038/s41372-022-01340-6. Epub 2022 Feb 23.
3
Accuracy of Fetal Weight Estimation by Ultrasonographic Evaluation in a Northeastern Region of India.
基于 3D 基因组选择的 circRNA 预测阿尔茨海默病。
J Prev Alzheimers Dis. 2024;11(4):1055-1062. doi: 10.14283/jpad.2024.52.
印度东北地区超声评估胎儿体重估计的准确性
Int J Biomater. 2021 Dec 20;2021:9090338. doi: 10.1155/2021/9090338. eCollection 2021.
4
Scikit-Dimension: A Python Package for Intrinsic Dimension Estimation.Scikit-Dimension：一个用于本征维度估计的Python包。
Entropy (Basel). 2021 Oct 19;23(10):1368. doi: 10.3390/e23101368.
5
Third trimester ultrasound estimated fetal weight for increasing prenatal prediction of small-for-gestational age newborns in low-risk pregnant women.孕晚期超声评估胎儿体重，以提高对低风险孕妇中小于胎龄新生儿的产前预测。
J Matern Fetal Neonatal Med. 2022 Dec;35(25):6721-6726. doi: 10.1080/14767058.2021.1920915. Epub 2021 May 23.
6
Abnormal Fetal Growth: Small for Gestational Age, Fetal Growth Restriction, Large for Gestational Age: Definitions and Epidemiology.异常胎儿生长：小于胎龄儿、胎儿生长受限、大于胎龄儿：定义和流行病学。
Obstet Gynecol Clin North Am. 2021 Jun;48(2):267-279. doi: 10.1016/j.ogc.2021.02.002.
7
Maternal Obesity and Risk of Low Birth Weight, Fetal Growth Restriction, and Macrosomia: Multiple Analyses.母亲肥胖与低出生体重、胎儿生长受限和巨大儿的风险：多项分析。
Nutrients. 2021 Apr 7;13(4):1213. doi: 10.3390/nu13041213.
8
Building and Interpreting Artificial Neural Network Models for Biological Systems.构建和解释生物系统的人工神经网络模型。
Methods Mol Biol. 2021;2190:185-194. doi: 10.1007/978-1-0716-0826-5_8.
9
Influence of Sonographic Fetal Weight Estimation Inaccuracies in Macrosomia on Perinatal Outcome.超声胎儿体重估计不准确对巨大儿围产结局的影响。
Ultraschall Med. 2022 Oct;43(5):e56-e64. doi: 10.1055/a-1205-0191. Epub 2020 Aug 6.
10
Significant deviations in sonographic fetal weight estimation: causes and implications.超声胎儿体重估计的显著偏差：原因与意义。
Arch Gynecol Obstet. 2020 Dec;302(6):1339-1344. doi: 10.1007/s00404-020-05732-x. Epub 2020 Aug 3.