Department of Pediatrics (M Shum, A Hsiao, A Asnes, and G Tiyyagura), Yale University School of Medicine, New Haven, Conn.
Department of Pediatrics (M Shum, A Hsiao, A Asnes, and G Tiyyagura), Yale University School of Medicine, New Haven, Conn.
Acad Pediatr. 2024 Jan-Feb;24(1):92-96. doi: 10.1016/j.acap.2023.08.015. Epub 2023 Aug 29.
We aimed to refine a natural language processing (NLP) algorithm that identified injuries associated with child abuse and identify areas in which integration into a real-time clinical decision support (CDS) tool may improve clinical care.
We applied an NLP algorithm in "silent mode" to all emergency department (ED) provider notes between July 2021 and December 2022 (n = 353) at 1 pediatric and 8 general EDs. We refined triggers for the NLP, assessed adherence to clinical guidelines, and evaluated disparities in degree of evaluation by examining associations between demographic variables and abuse evaluation or reporting to child protective services.
Seventy-three cases falsely triggered the NLP, often due to errors in interpreting linguistic context. We identified common false-positive scenarios and refined the algorithm to improve NLP specificity. Adherence to recommended evaluation standards for injuries defined by nationally accepted clinical guidelines was 63%. There were significant demographic differences in evaluation and reporting based on presenting ED type, insurance status, and race and ethnicity.
Analysis of an NLP algorithm in "silent mode" allowed for refinement of the algorithm and highlighted areas in which real-time CDS may help ED providers identify and pursue appropriate evaluation of injuries associated with child physical abuse.
我们旨在改进一种自然语言处理（NLP）算法，以识别与儿童虐待相关的伤害，并确定将其整合到实时临床决策支持（CDS）工具中可能改善临床护理的领域。
我们在 2021 年 7 月至 2022 年 12 月期间，在 1 家儿科和 8 家综合急诊科的所有急诊部（ED）医护人员记录中以“静默模式”应用 NLP 算法（n=353）。我们改进了 NLP 的触发因素，评估了对临床指南的遵守情况，并通过检查人口统计学变量与虐待评估或向儿童保护服务机构报告之间的关联，评估评估或报告程度的差异。
73 例病例错误触发了 NLP，这通常是由于对语言环境的解释错误所致。我们确定了常见的假阳性场景，并改进了算法以提高 NLP 的特异性。对符合国家认可的临床指南定义的伤害进行推荐评估标准的遵守率为 63%。根据就诊 ED 类型、保险状况以及种族和民族，在评估和报告方面存在显著的人口统计学差异。
在“静默模式”下分析 NLP 算法，可以改进算法，并突出实时 CDS 可能有助于 ED 提供者识别和进行与儿童身体虐待相关的伤害适当评估的领域。
