Natural Language Processing and Automated Speech Recognition to Identify Older Adults with Cognitive Impairment

自然语言处理和自动语音识别可识别患有认知障碍的老年人

• 批准号: 10609461
• 负责人: Alex D Federman
• 金额: $ 81.52万
• 依托单位: ICAHN SCHOOL OF MEDICINE AT MOUNT SINAI
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-04-15 至 2025-03-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10609461
• 关键词: Acoustics; Acute; Address; Algorithms; Alzheimer' s disease related dementia; Caregivers; Chicago; Clinical; Clinical assessments; Code; Cognition; Cognitive; Data; Data Analyses; Data Element; Data Scientist; Data Set; Development; Diagnosis; Diagnostic; Dimensions; Documentation; Early Diagnosis; Elderly; Electronic Health Record; Health Services; Health system; Impaired cognition; Individual; Insurance Carriers; Machine Learning; Measures; Mental disorders; Methods; Natural Language Processing; Neurocognitive; New York City; Notification; Parkinson Disease; Patients; Persons; Physicians; Population; Positioning Attribute; Preventive care; Primary Care; Procedures; Provider; Psychiatric Diagnosis; Reference Standards; Research; Research Personnel; Resource Allocation; Risk Factors; Sampling; Semantics; Sensitivity and Specificity; Services; Signs and Symptoms; Speech; Structure; Study Subject; Technology; Testing; Text; Time; Training; United States; Validation; adverse event risk; aging population; automated speech recognition; care coordination; clinical encounter; cognitive function; cognitive testing; deep learning; demographics; diagnostic algorithm; electronic health data; electronic structure; falls; feature extraction; financial incentive; health care settings; improved; insurance claims; machine learning algorithm; machine learning classifier; mental state; mild cognitive impairment; multidisciplinary; prevent; primary care patient; primary care setting; primary care visit; recruit; risk mitigation; screening; secondary analysis; structured data; success; tool; treatment choice; unstructured data

Project Summary The purpose of this proposal is to develop two strategies, natural language processing (NLP) and automated speech analysis (ASA), to enable automated identification of patients with cognitive impairment (CI), from mild cognitive impairment (MCI) to Alzheimer’s Disease Related Dementias (ADRD) in clinical settings. The number of older adults in the United States with MCI and ADRD is increasing and yet the ability of clinicians and researchers to identify them at scale has advanced little over recent decades and screening with clinical assessments is done inconsistently. Alternative strategies using available data, like analysis of diagnostic codes in the clinical record or insurance claims, have very low sensitivity. NLP and ASA used with machine learning are technologies that could greatly increase ability to detect MCI and ADRD in clinical contexts. NLP automatically converts text in the electronic health record (EHR) into structured concepts suitable for analysis. Thus, clinicians’ documentation of signs and symptoms or orders of tests and services that reflect or address cognitive limitations can be efficiently captured, possibly long before the clinician uses an ADRD-related diagnostic code. ASA directly measures cognition by recognizing different features of cognition captured in speech. Extracting features through both NLP and ASA could thus provide a unique measure of cognition and its impact on the individual and their caregivers. Early detection of MCI and ADRD can help researchers identify appropriate patients for research and help clinicians and health systems target patients for preventive care and care coordination. For these reasons, more efficient, highly scalable strategies are needed to identify people with MCI and ADRD. The Specific Aims of this proposal are to (1) Develop and validate a ML algorithm using features extracted from the EHR with NLP to identify patients with CI, (2) Develop and validate a ML algorithm using features extracted from ASA of audio recordings of patient-provider encounters during routine primary care visits to identify patients with CI, (3) Develop and validate a ML algorithm using both NLP and ASA extracted features to create an integrated CI diagnostic algorithm. We will develop machine learning algorithms using NLP and ASA extracted features trained against neurocognitive assessment data on 800 primary care patients in New York City and validate them in an independent sample of 200 patients in Chicago. In secondary analyses we will train ML algorithms to identify MCI and its subtypes. This project will be the most rigorous development of NLP, ASA, and ML algorithms for CI yet performed, the first to test ASA in primary care settings, and the first to test NLP and ASA feature extraction strategies in combination. The multi-disciplinary team of clinicians, health services researchers, and neurocognitive and data scientists will apply machine learning to develop these highly scalable, automated technologies for identification of MCI and ADRD. 1

项目概要 该提案的目的是开发两种策略，自然语言处理（NLP）和自动化 语音分析 (ASA)，能够自动识别患有认知障碍 (CI) 的患者（从轻度到中度） 临床环境中认知障碍（MCI）到阿尔茨海默病相关痴呆（ADRD）的数量。 在美国，患有 MCI 和 ADRD 的老年人数量正在增加，但信徒和 ADRD 的能力 近几十年来，研究人员在大规模识别它们方面进展甚微，并且通过临床筛选 使用现有数据（例如诊断分析）进行的评估不一致。 临床记录或保险索赔中的代码，与机器一起使用的 NLP 和 ASA 的敏感性非常低。 学习技术可以极大地提高在临床环境中检测 MCI 和 ADRD 的能力。 自动将电子健康记录 (EHR) 中的文本转换为适合分析的结构化概念。 因此，人群对体征和症状的记录或反映或解决问题的测试和服务顺序 可能早在临床医生使用 ADRD 相关药物之前就可以有效地捕获认知限制 诊断代码。ASA 通过识别捕获的不同认知特征来直接测量认知。 因此，通过 NLP 和 ASA 提取特征可以提供一种独特的认知测量方法。 它对个人及其护理人员的影响。 早期检测 MCI 和 ADRD 可以帮助研究人员识别合适的患者进行研究并帮助 由于这些原因， 需要更有效、高度可扩展的策略来识别 MCI 和 ADRD 患者。 该提案的目的是 (1) 使用从 EHR 中提取的特征来开发和验证 ML 算法 NLP 识别 CI 患者，(2) 使用从 ASA 中提取的特征开发和验证 ML 算法 在日常初级保健就诊期间患者与提供者接触的录音，以识别患有 CI 的患者， (3) 使用 NLP 和 ASA 提取的特征来开发和验证 ML 算法，以创建集成 CI 我们将使用 NLP 和 ASA 提取的特征来开发机器学习算法。 根据纽约市 800 名初级保健患者的神经认知评估数据进行训练并进行验证 在芝加哥的 200 名患者的独立样本中，我们将训练 ML 算法。 识别 MCI 及其子类型 该项目将是 NLP、ASA 和 ML 的最严格的开发。 CI 算法尚未执行，是第一个在初级保健环境中测试 ASA 的算法，也是第一个测试 NLP 和 ASA 的算法 新人、健康服务多学科团队的特征提取策略相结合。 研究人员以及神经认知和数据科学家将应用机器学习来开发这些高度 用于识别 MCI 和 ADRD 的可扩展自动化技术。 1