• 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

开发和验证一种自然语言处理工具,以识别与虐待相关的婴儿损伤。

Development and Validation of a Natural Language Processing Tool to Identify Injuries in Infants Associated With Abuse.

机构信息

Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.

Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.

出版信息

Acad Pediatr. 2022 Aug;22(6):981-988. doi: 10.1016/j.acap.2021.11.004. Epub 2021 Nov 12.

DOI:10.1016/j.acap.2021.11.004
PMID:34780997
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9095755/
Abstract

OBJECTIVES

Medically minor but clinically important findings associated with physical child abuse, such as bruises in pre-mobile infants, may be identified by frontline clinicians yet the association of these injuries with child abuse is often not recognized, potentially allowing the abuse to continue and even to escalate. An accurate natural language processing (NLP) algorithm to identify high-risk injuries in electronic health record notes could improve detection and awareness of abuse. The objectives were to: 1) develop an NLP algorithm that accurately identifies injuries in infants associated with abuse and 2) determine the accuracy of this algorithm.

METHODS

An NLP algorithm was designed to identify ten specific injuries known to be associated with physical abuse in infants. Iterative cycles of review identified inaccurate triggers, and coding of the algorithm was adjusted. The optimized NLP algorithm was applied to emergency department (ED) providers' notes on 1344 consecutive sample of infants seen in 9 EDs over 3.5 months. Results were compared with review of the same notes conducted by a trained reviewer blind to the NLP results with discrepancies adjudicated by a child abuse expert.

RESULTS

Among the 1344 encounters, 41 (3.1%) had one of the high-risk injuries. The NLP algorithm had a sensitivity and specificity of 92.7% (95% confidence interval [CI]: 79.0%-98.1%) and 98.1% (95% CI: 97.1%-98.7%), respectively, and positive and negative predictive values were 60.3% and 99.8%, respectively, for identifying high-risk injuries.

CONCLUSIONS

An NLP algorithm to identify infants with high-risk injuries in EDs has good accuracy and may be useful to aid clinicians in the identification of infants with injuries associated with child abuse.

摘要

目的

与身体虐待相关的医学上轻微但临床上重要的发现,如婴幼儿期的瘀伤,可能被一线临床医生发现,但这些损伤与虐待的关联常常未被识别,这可能导致虐待继续甚至升级。一种准确的自然语言处理(NLP)算法,可以识别电子健康记录中的高风险损伤,从而提高虐待的检测和意识。目的是:1)开发一种能够准确识别与虐待相关的婴儿损伤的 NLP 算法,2)确定该算法的准确性。

方法

设计了一种 NLP 算法来识别已知与婴儿身体虐待相关的十种特定损伤。通过反复审查,确定不准确的触发因素,并调整算法的编码。优化后的 NLP 算法应用于 9 家急诊室在 3.5 个月内连续观察的 1344 例婴儿的急诊室医生记录。结果与对同一记录进行的由一名接受过培训的评审员进行的审查进行了比较,该评审员对 NLP 结果不知情,差异由虐待儿童专家进行裁决。

结果

在 1344 次就诊中,有 41 次(3.1%)出现了一种高风险损伤。NLP 算法的敏感性和特异性分别为 92.7%(95%置信区间[CI]:79.0%-98.1%)和 98.1%(95% CI:97.1%-98.7%),阳性和阴性预测值分别为 60.3%和 99.8%,用于识别高风险损伤。

结论

一种用于识别急诊科高风险损伤的婴儿的 NLP 算法具有良好的准确性,可能有助于临床医生识别与虐待相关的损伤的婴儿。

相似文献

1
Development and Validation of a Natural Language Processing Tool to Identify Injuries in Infants Associated With Abuse.开发和验证一种自然语言处理工具,以识别与虐待相关的婴儿损伤。
Acad Pediatr. 2022 Aug;22(6):981-988. doi: 10.1016/j.acap.2021.11.004. Epub 2021 Nov 12.
2
Natural Language Processing - A Surveillance Stepping Stone to Identify Child Abuse.自然语言处理——识别儿童虐待的监控踏脚石。
Acad Pediatr. 2024 Jan-Feb;24(1):92-96. doi: 10.1016/j.acap.2023.08.015. Epub 2023 Aug 29.
3
Initial development of tools to identify child abuse and neglect in pediatric primary care.儿科初级保健中识别儿童虐待和忽视工具的初步开发。
BMC Med Inform Decis Mak. 2023 Nov 17;23(1):266. doi: 10.1186/s12911-023-02361-7.
4
Harnessing the Power of Machine Learning and Electronic Health Records to Support Child Abuse and Neglect Identification in Emergency Department Settings.利用机器学习和电子健康记录的力量支持急诊科儿童虐待和忽视的识别。
Stud Health Technol Inform. 2024 Aug 22;316:1652-1656. doi: 10.3233/SHTI240740.
5
A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records.一种基于自然语言处理和深度学习的方法,用于从儿科电子病历中识别儿童虐待。
PLoS One. 2021 Feb 26;16(2):e0247404. doi: 10.1371/journal.pone.0247404. eCollection 2021.
6
Use of Natural Language Processing Tools to Identify and Classify Periprosthetic Femur Fractures.使用自然语言处理工具识别和分类股骨假体周围骨折。
J Arthroplasty. 2019 Oct;34(10):2216-2219. doi: 10.1016/j.arth.2019.07.025. Epub 2019 Jul 24.
7
Building a Natural Language Processing Tool to Identify Patients With High Clinical Suspicion for Kawasaki Disease from Emergency Department Notes.构建一个自然语言处理工具,用于从急诊科记录中识别高度怀疑患有川崎病的患者。
Acad Emerg Med. 2016 May;23(5):628-36. doi: 10.1111/acem.12925. Epub 2016 Apr 13.
8
The use of natural language processing to identify vaccine-related anaphylaxis at five health care systems in the Vaccine Safety Datalink.利用自然语言处理技术在疫苗安全数据链中的五个医疗系统中识别与疫苗相关的过敏反应。
Pharmacoepidemiol Drug Saf. 2020 Feb;29(2):182-188. doi: 10.1002/pds.4919. Epub 2019 Dec 3.
9
Using natural language processing to identify child maltreatment in health systems.利用自然语言处理技术在卫生系统中识别儿童虐待。
Child Abuse Negl. 2023 Apr;138:106090. doi: 10.1016/j.chiabu.2023.106090. Epub 2023 Feb 8.
10
Natural Language Processing for Asthma Ascertainment in Different Practice Settings.不同实践环境下的哮喘确定的自然语言处理。
J Allergy Clin Immunol Pract. 2018 Jan-Feb;6(1):126-131. doi: 10.1016/j.jaip.2017.04.041. Epub 2017 Jun 19.

引用本文的文献

1
Screening tools used by paediatric healthcare providers to identify child maltreatment by parents or caregivers: a systematic review.儿科医疗服务提供者用于识别父母或照顾者对儿童虐待行为的筛查工具:一项系统综述。
BMJ Open. 2025 Aug 4;15(8):e101721. doi: 10.1136/bmjopen-2025-101721.
2
Leveraging AI to Investigate Child Maltreatment Text Narratives: Promising Benefits and Addressable Risks.利用人工智能研究虐待儿童文本叙述:潜在益处与可应对风险
JMIR Pediatr Parent. 2025 Jul 24;8:e73579. doi: 10.2196/73579.
3
Identifying Risk Factors of Children Who Suffered Physical Abuse: A Systematic Review.识别遭受身体虐待儿童的风险因素:一项系统综述
J Am Acad Orthop Surg Glob Res Rev. 2025 Jan 16;9(1). doi: 10.5435/JAAOSGlobal-D-24-00163. eCollection 2025 Jan 1.
4
Estimating the Prevalence of Child Abuse and Neglect Among Adolescents in Primary Care Through Diagnoses Codes and Free-Text EHR Clinical Notes.通过诊断编码和自由文本电子健康记录临床笔记估算初级保健中青少年遭受虐待和忽视的患病率
J Pediatr Health Care. 2025 Mar-Apr;39(2):189-197. doi: 10.1016/j.pedhc.2024.10.016. Epub 2024 Nov 22.
5
Developing and Testing the Usability of a Novel Child Abuse Clinical Decision Support System: Mixed Methods Study.开发和测试新型儿童虐待临床决策支持系统的可用性:混合方法研究。
J Med Internet Res. 2024 Mar 29;26:e51058. doi: 10.2196/51058.
6
Artificial Intelligence and Child Abuse and Neglect: A Systematic Review.人工智能与虐待及忽视儿童:一项系统综述。
Children (Basel). 2023 Oct 6;10(10):1659. doi: 10.3390/children10101659.
7
Natural Language Processing - A Surveillance Stepping Stone to Identify Child Abuse.自然语言处理——识别儿童虐待的监控踏脚石。
Acad Pediatr. 2024 Jan-Feb;24(1):92-96. doi: 10.1016/j.acap.2023.08.015. Epub 2023 Aug 29.

本文引用的文献

1
Validation of a Clinical Decision Rule to Predict Abuse in Young Children Based on Bruising Characteristics.基于瘀伤特征预测幼儿虐待的临床决策规则的验证。
JAMA Netw Open. 2021 Apr 1;4(4):e215832. doi: 10.1001/jamanetworkopen.2021.5832.
2
Improving the Care of Abused Children Presenting to Community Emergency Departments: The Evolving Landscape.改善前往社区急诊科就诊的受虐儿童的护理:不断演变的形势。
Acad Pediatr. 2021 Mar;21(2):221-222. doi: 10.1016/j.acap.2020.09.008. Epub 2020 Sep 19.
3
Child Protection Team Consultation for Injuries Potentially Due to Child Abuse in Community Emergency Departments.社区急诊中疑似儿童虐待所致伤害的儿童保护团队会诊。
Acad Emerg Med. 2021 Jan;28(1):70-81. doi: 10.1111/acem.14132. Epub 2020 Oct 9.
4
Integration of physical abuse clinical decision support at 2 general emergency departments.将身体虐待临床决策支持整合到 2 家综合急诊部。
J Am Med Inform Assoc. 2019 Oct 1;26(10):1020-1029. doi: 10.1093/jamia/ocz069.
5
Machine Learning in Relation to Emergency Medicine Clinical and Operational Scenarios: An Overview.机器学习与急诊医学临床和操作场景的关系:概述。
West J Emerg Med. 2019 Mar;20(2):219-227. doi: 10.5811/westjem.2019.1.41244. Epub 2019 Feb 14.
6
Impact of Child Abuse Clinical Pathways on Skeletal Survey Performance in High-Risk Infants.儿童虐待临床路径对高危婴儿骨骼筛查表现的影响。
Acad Pediatr. 2020 Jan-Feb;20(1):39-45. doi: 10.1016/j.acap.2019.02.012. Epub 2019 Mar 14.
7
Early Involvement of the Child Protection Team in the Care of Injured Infants in a Pediatric Emergency Department.儿童保护团队在儿科急诊科对受伤婴儿护理中的早期介入。
J Emerg Med. 2019 Jun;56(6):592-600. doi: 10.1016/j.jemermed.2019.01.030. Epub 2019 Mar 14.
8
Oral injuries in children less than 24 months of age in a pediatric emergency department.儿科急诊中 24 个月以下儿童的口腔损伤。
Child Abuse Negl. 2019 Mar;89:70-77. doi: 10.1016/j.chiabu.2019.01.006.
9
Implementation of routine electronic health record-based child abuse screening in General Emergency Departments.在综合急诊部门实施基于常规电子健康记录的儿童虐待筛查。
Child Abuse Negl. 2018 Nov;85:58-67. doi: 10.1016/j.chiabu.2018.08.008. Epub 2018 Aug 28.
10
Racial and Ethnic Disparities and Bias in the Evaluation and Reporting of Abusive Head Trauma.种族和民族差异以及在虐待性头部创伤评估和报告中的偏见。
J Pediatr. 2018 Jul;198:137-143.e1. doi: 10.1016/j.jpeds.2018.01.048. Epub 2018 Mar 29.