Use of prenatal ultrasound findings to predict postnatal outcome in fetuses with lower urinary tract obstruction.

IF 6.1 1区 医学 Q1 ACOUSTICS
J Richter, S Shinar, L Erdman, H Good, J K Kim, J Dos Santos, A Khondker, M Chua, T Van Mieghem, A J Lorenzo, M Rickard
{"title":"Use of prenatal ultrasound findings to predict postnatal outcome in fetuses with lower urinary tract obstruction.","authors":"J Richter, S Shinar, L Erdman, H Good, J K Kim, J Dos Santos, A Khondker, M Chua, T Van Mieghem, A J Lorenzo, M Rickard","doi":"10.1002/uog.29129","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Lower urinary tract obstruction (LUTO) is a chronic condition with a spectrum of outcomes. It is usually suspected prenatally based on ultrasound features (USFs). Given the unknown postnatal trajectory and the potential for significant morbidity and mortality, many families choose termination of pregnancy (TOP), often based on USFs alone. Herein, we sought to develop a tool that can be used to predict postnatal outcome based on combinations of USFs, which can aid prenatal counseling and parental decision-making.</p><p><strong>Methods: </strong>This was a retrospective study of cases with suspected fetal LUTO that were seen at a high-risk fetal center and a tertiary pediatric center in Canada. Data were collected on USFs, prenatal/postnatal death and postnatal need for transplantation and/or dialysis. USFs from pregnancies with a gestational age of 13-26 weeks on initial ultrasound at the high-risk fetal center that underwent TOP were collected and matched to fetuses with comparable prenatal USFs that were not terminated, which had a known postnatal outcome, to build a random forest model. The random forest model was fitted for each outcome (death, dialysis or transplantation) and tested for accuracy using leave-one-out cross-validation. Each predictor was assessed independently with combined importance when accounting for other predictors. The model was used to predict the most likely postnatal outcomes for cases of TOP had the pregnancy been continued.</p><p><strong>Results: </strong>USF data from 85 cases of TOP and 125 cases of expectantly managed pregnancy with prenatally suspected LUTO were retrieved. For expectantly managed cases, there was a median follow-up duration of 5.7 (interquartile range, 0.2-14.5) years among the liveborn infants. There were 14 prenatal and 22 postnatal deaths in the expectantly managed cohort. The random forest model demonstrated the highest predictive accuracy for transplantation (77% accuracy, 50% sensitivity, 80% specificity), followed by death (72% accuracy, 83% sensitivity, 67% specificity) and dialysis (71% accuracy, 70% sensitivity, 71% specificity). For the TOP cohort, had the pregnancies been continued, the model predicted transplantation and dialysis in 21/85 (25%) and 37/85 (44%) cases, respectively; pre- or postnatal death was predicted in 69/85 (81%) cases.</p><p><strong>Conclusions: </strong>Our data suggest that it is possible to predict death and postnatal transplantation and/or dialysis from USFs in fetuses with suspected LUTO with acceptable accuracy. Predictive accuracy will improve with continued follow-up of more patients, enabling more personalized prenatal counseling and more informed decision-making for families. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.</p>","PeriodicalId":23454,"journal":{"name":"Ultrasound in Obstetrics & Gynecology","volume":"64 6","pages":"768-775"},"PeriodicalIF":6.1000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11610651/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ultrasound in Obstetrics & Gynecology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/uog.29129","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ACOUSTICS","Score":null,"Total":0}
引用次数: 0

Abstract

Objective: Lower urinary tract obstruction (LUTO) is a chronic condition with a spectrum of outcomes. It is usually suspected prenatally based on ultrasound features (USFs). Given the unknown postnatal trajectory and the potential for significant morbidity and mortality, many families choose termination of pregnancy (TOP), often based on USFs alone. Herein, we sought to develop a tool that can be used to predict postnatal outcome based on combinations of USFs, which can aid prenatal counseling and parental decision-making.

Methods: This was a retrospective study of cases with suspected fetal LUTO that were seen at a high-risk fetal center and a tertiary pediatric center in Canada. Data were collected on USFs, prenatal/postnatal death and postnatal need for transplantation and/or dialysis. USFs from pregnancies with a gestational age of 13-26 weeks on initial ultrasound at the high-risk fetal center that underwent TOP were collected and matched to fetuses with comparable prenatal USFs that were not terminated, which had a known postnatal outcome, to build a random forest model. The random forest model was fitted for each outcome (death, dialysis or transplantation) and tested for accuracy using leave-one-out cross-validation. Each predictor was assessed independently with combined importance when accounting for other predictors. The model was used to predict the most likely postnatal outcomes for cases of TOP had the pregnancy been continued.

Results: USF data from 85 cases of TOP and 125 cases of expectantly managed pregnancy with prenatally suspected LUTO were retrieved. For expectantly managed cases, there was a median follow-up duration of 5.7 (interquartile range, 0.2-14.5) years among the liveborn infants. There were 14 prenatal and 22 postnatal deaths in the expectantly managed cohort. The random forest model demonstrated the highest predictive accuracy for transplantation (77% accuracy, 50% sensitivity, 80% specificity), followed by death (72% accuracy, 83% sensitivity, 67% specificity) and dialysis (71% accuracy, 70% sensitivity, 71% specificity). For the TOP cohort, had the pregnancies been continued, the model predicted transplantation and dialysis in 21/85 (25%) and 37/85 (44%) cases, respectively; pre- or postnatal death was predicted in 69/85 (81%) cases.

Conclusions: Our data suggest that it is possible to predict death and postnatal transplantation and/or dialysis from USFs in fetuses with suspected LUTO with acceptable accuracy. Predictive accuracy will improve with continued follow-up of more patients, enabling more personalized prenatal counseling and more informed decision-making for families. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
12.30
自引率
14.10%
发文量
891
审稿时长
1 months
期刊介绍: Ultrasound in Obstetrics & Gynecology (UOG) is the official journal of the International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) and is considered the foremost international peer-reviewed journal in the field. It publishes cutting-edge research that is highly relevant to clinical practice, which includes guidelines, expert commentaries, consensus statements, original articles, and systematic reviews. UOG is widely recognized and included in prominent abstract and indexing databases such as Index Medicus and Current Contents.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信