Automating Assessment of Asthma Care Quality

描述(由申请人提供)：为了解决共识质量标准与实际提供给符合条件的人的医疗服务之间的巨大差异，医学研究所呼吁采取新的质量倡议，并已将哮喘确定为其优先领域之一。每年，数以千计的可预防的死亡被归因于哮喘。与哮喘相关的健康负担在脆弱人群中尤为明显。提高哮喘护理质量的机会取决于全面和定期评估实际提供给哮喘患者的护理的能力。目前的质量测量研究需要广泛的临床图表审查，在公共卫生规模上是不划算的。医疗保健信息技术(Health IT)可以通过实现自动化质量评估产生重大影响。电子病历(EMR)系统捕获临床信息，使全面、经济高效的质量评估成为可能。然而，许多相关信息(以及可能50%或更多的必要数据)驻留在自由文本临床记录中，这对自动化质量评估提出了重大挑战。本研究旨在开发、验证、应用和评估一种可扩展的方法，用于常规和全面测量门诊哮喘护理质量。为此，我们将扩展MediClass(一种“医疗分类器”)，这是一项成熟的技术，可从EMR中的编码数据和自由文本临床记录中提取医疗质量数据。这项研究将对两个不同的医疗系统的电子病历数据进行回顾性分析：一个中等规模的医疗保健组织(Kaiser Permanente Northwest，KPNW)和一个公共医疗诊所联盟(俄勒冈社区健康信息网络)，包括太平洋西北地区的患者、提供者和医疗保健实践的不同样本。该项目利用健康信息技术来评估和改善该地区参保和贫困、未参保和参保不足人群的护理质量。我们建议使用来自最初的兰德质量评估工具项目的门诊哮喘护理质量(ACQ)测量集。我们将首先使用最新的临床指南和5岁以上哮喘患者的门诊诊断、治疗和管理的共识标准来完善ACQ措施。接下来，我们将开发并验证一种自动方法，用于将这些措施应用于全面的电子病历数据。在每个研究地点，MediClass系统将提取编码数据，并在自由文本临床记录上使用自然语言处理(NLP)来识别电子病历中与ACQ相关的临床事件。然后，我们将应用ACQ措施来评估两个卫生系统目前的哮喘护理质量水平。最后，我们将使用KPNW研究站点提供的广泛的纵向患者数据来评估推荐哮喘治疗的ACQ测量与实际临床结果之间的关联。

DESCRIPTION (provided by the applicant): To address the large discrepancy between consensus quality standards and healthcare services actually delivered to those eligible, the Institute of Medicine has called for new quality initiatives and has identified asthma as one if its priority areas. Each year, thousands of preventable deaths are attributed to asthma. The asthma-related health burden is especially pronounced in vulnerable populations. Opportunities to improve asthma care quality hinge on the capacity to comprehensively and routinely assess the care that is actually delivered to asthma patients. Current quality measurement studies require extensive clinical chart review and are not cost-effective on a public health scale. Healthcare information technology (Health IT) could have a big impact by enabling automated quality assessments. Electronic medical record (EMR) systems capture clinical information that could make comprehensive, cost effective quality assessment possible. However, much relevant information (and perhaps 50% or more of the necessary data) resides in free-text clinical notes, which presents a significant challenge to automated quality assessment. This research aims to develop, validate, apply, and evaluate a scalable method for routine and comprehensive measurement of outpatient asthma care quality. To accomplish this, we will extend MediClass (a "Medical Classifier"), which is a proven technology for extracting care quality data from both coded data and free-text clinical notes in the EMR. This research will perform retrospective analysis of EMR data from two distinct health systems: a mid-sized HMO (Kaiser Permanente Northwest, KPNW) and a consortium of public health clinics (Oregon Community Health Information Network) including a diverse sample of patients, providers, and health care practices of the Pacific Northwest. This project leverages Health IT to assess and improve quality of care for both insured and the indigent, uninsured, and underinsured populations of this region. We propose to use an outpatient Asthma Care Quality (ACQ) measure set derived from the original RAND Quality Assessment Tools Project. We will first refine the ACQ measures using up-to-date clinical guidelines and consensus standards for outpatient diagnosis, treatment and management of asthma in patients older than 5 years. Next, we will develop and validate an automated method for applying these measures to comprehensive EMR data. At each study site, the MediClass system will extract coded data and use natural language processing (NLP) on free-text clinical notes to identify ACQ-relevant clinical events in the electronic medical record. Then, we will apply the ACQ measures to assess current levels of asthma care quality in the two health systems. Finally, we will evaluate the association between ACQ measures of recommended asthma care and actual clinical outcomes using extensive longitudinal patient data available at the KPNW study site.