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的一部分，有助于长期（HEL）倡议结束成瘾，以加快对国家阿片类药物公共卫生危机的科学解决方案。 NIH Heal Heal Initiative Bolsters跨NIH的研究，以改善阿片类药物滥用和成瘾的治疗方法。及时，准确地估计过量（OD）事件速率是一种必不可少的监视成分，可以减轻正在进行的OD流行的损失。快速更新非致命的ODS对于减少OD死亡的进一步升级至关重要。传统的OD监视方法目前依赖CDC的综合征监视系统和汇总急诊科（ED）计费数据。但是，全国一级的估计受到重大延误的困扰。因此，越来越多的推动力监视（子）状态级数据集，包括ED和紧急医疗服务（EMS）记录。同时，叙事数据在这些记录中的作用被认为为导致其提供的OD和药物提供了完整的信号，因为现有的基于诊断的OD定义显示出较低的召回率（敏感性）。即使是基于规则的定义，在叙述中搜索术语的定义也缺少叙事数据中的顺序语义上下文。为了解决这些简短的信息，我们建议使用深层神经网络（DNN）设计和实施最先进的自然语言处理（NLP）模型，以进行OD分类和对导致OD的药物术语的细粒度识别。为此，我们将首先使用ED和EMS叙述来创建和传播这些任务的公共金标准手工标记数据集。我们的注册笔记将用于构建DNN模型，也将是 公开向更广泛的OD监视社区共享。我们的模型有望大大改善召回率，并及时导致更好的非致命OD监视。我们还将开发域适应方法，以增强从站点到数据集开发的模型的应用，从其他站点到数据集。全面的， 我们的项目将为OD监视社区创建新颖的公共资源（数据，代码，模型），以利用NLP方法中的最新进展。