Fast and fine: NLP methods for near real-time and fine-grained overdose surveillance

快速而精细：用于近实时和细粒度过量监测的 NLP 方法

• 批准号: 10590000
• 负责人: Venkata Naga Ramakanth Kavuluru
• 金额: $ 134.47万
• 依托单位: UNIVERSITY OF KENTUCKY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-30 至 2025-09-29
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10590000
• 关键词: Accident and Emergency department; Address; Benchmarking; COVID-19 pandemic; Centers for Disease Control and Prevention (U.S.); Classification; Clinical; Code; Collaborations; Communities; Computer software; County; Data; Data Set; Death Certificates; Diagnosis; Docking; Drug usage; Emergency department visit; Emergency medical service; Epidemic; Evaluation; Event; Goals; Gold; Grain; Hand; Health; Helping to End Addiction Long-term; Human; Information Retrieval; International Statistical Classification of Diseases and Related Health Problems, Tenth Revision (ICD-10); Kentucky; Label; Lead; Learning; Letters; Life; Linear Models; Logistic Regressions; Machine Learning; Manuscripts; Methods; Modeling; Monitor; Naloxone; Names; Natural Language Processing; Neural Network Simulation; Non-linear Models; Opiate Addiction; Opioid; Overdose; Performance; Pharmaceutical Preparations; Prevention Research; Public Health; Records; Recurrence; Reporting; Research; Research Personnel; Resource Allocation; Resource-limited setting; Resources; Role; Semantics; Service delivery model; Signal Transduction; Site; Source; Speed; Spottings; Structure; Substance abuse problem; Supervision; System; Time; Training; Triage; United States National Institutes of Health; Universities; Update; Work; base; billing data; care delivery; dashboard; data modeling; data reuse; deep neural network; design; disability; experimental study; improved; injury prevention; insight; learning strategy; machine learning method; neural model; novel; open source; opioid misuse; opioid use disorder; overdose death; random forest; relating to nervous system; stem; supervised learning; syndromic surveillance; tool; transfer learning

This study is part of the NIH’s Helping to End Addiction Long-term (HEAL) initiative to speed scientific solutions to the national opioid public health crisis. The NIH HEAL Initiative bolsters research across NIH to improve treatment for opioid misuse and addiction. Timely and accurate estimation of overdose (OD) event rates is an indispensable surveillance component to mit-igate the toll of the ongoing OD epidemic. Getting fast updates for nonfatal ODs is crucial in decreasing further escalations in OD deaths. Traditional approaches to OD surveillance currently rely on CDC's syndromic surveil-lance system and aggregated emergency department (ED) billing data. However national level estimates are plagued by substantial delays. Hence, there is an increasing push to monitor (sub)state level datasets including ED and emergency medical service (EMS) records. Meanwhile, the role of narrative data in these records is being recognized to offer complementary signal for ODs and drugs leading to them because existing diagnosis code based OD definitions are shown to have lower recall (sensitivity). Even rule-based definitions that search for terms in narratives are missing the sequential semantic context in narrative data. To address these shortcom-ings, we propose to design and implement state-of-the-art natural language processing (NLP) models using deep neural networks (DNNs) for OD classification and fine-grained recognition of drug terms leading to ODs. To this end, we will first create and disseminate the first of their kind public gold standard hand-labeled datasets for these tasks using ED and EMS narratives. Our de-identified notes will be used to build DNN models that will also be shared publicly to the wider OD surveillance community. Our models are expected to improve recall substantially and lead to better nonfatal OD surveillance in a timely manner. We will also develop domain adaption methods to enhance the application of models developed with data from a site to datasets from a different site. Overall, our project will create novel public resources (data, code, models) for the OD surveillance community to leverage latest advances in NLP methods.

这项研究是NIH帮助结束长期成瘾（HEAL）计划的一部分，旨在加速科学解决国家阿片类药物公共卫生危机。NIH HEAL倡议支持整个NIH的研究，以改善阿片类药物滥用和成瘾的治疗。及时、准确地估计药物过量（OD）事件发生率是减少持续OD流行的一个不可或缺的监测组成部分。快速更新非致命性OD对于减少OD死亡的进一步升级至关重要。OD监测的传统方法目前依赖于CDC的症状监测系统和汇总的急诊科（艾德）账单数据。然而，国家一级的估计数受到严重拖延的困扰。因此，越来越多地推动监测包括艾德和紧急医疗服务（EMS）记录的（子）州级数据集。与此同时，这些记录中的叙述性数据的作用被认为是为OD和导致OD的药物提供补充信号，因为现有的基于诊断代码的OD定义具有较低的召回率（敏感性）。即使是基于规则的定义，在叙述中搜索术语，也缺少叙述数据中的顺序语义上下文。为了解决这些缺点，我们建议使用深度神经网络（DNN）设计和实现最先进的自然语言处理（NLP）模型，用于OD分类和导致OD的药物术语的细粒度识别。为此，我们将首先使用艾德和EMS叙述为这些任务创建和传播第一个公共黄金标准手工标记数据集。我们的去识别艾德笔记将用于构建DNN模型， 公开分享给更广泛的OD监测社区。我们的模型有望大大提高召回率，并及时进行更好的非致命性OD监测。我们还将开发领域自适应方法，以增强模型的应用程序开发的数据从一个网站到数据集从不同的网站。总的来说， 我们的项目将为OD监测社区创建新的公共资源（数据，代码，模型），以利用NLP方法的最新进展。