Detecting and classifying non-fluent speech in aphasia using machine learning

使用机器学习对失语症患者的不流利言语进行检测和分类

• 批准号: 10647054
• 负责人: Claire Elizabeth Cordella
• 金额: $ 0.25万
• 依托单位: BOSTON UNIVERSITY (CHARLES RIVER CAMPUS)
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-01 至
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10647054
• 关键词: Acoustics; Affect; American; Aphasia; Articulation; Clinical; Code; Cognitive; Communication; Databases; Diagnostic; Feeling; Functional disorder; Future; Goals; Impaired cognition; Impairment; Individual; Intervention; Language; Life; Light; Linear Regressions; Linguistics; Long-Term Effects; Machine Learning; Measures; Mental Depression; Modeling; Monitor; Motor; Output; Patients; Persons; Population; Predictive Value; Proxy; Research; Sampling; Scheme; Social isolation; Source; Speech; Standardization; Surface; Techniques; Testing; Time; Training; Validation; Work; accurate diagnosis; cognitive function; cohort; disability; experience; functional outcomes; indexing; inter-individual variation; interest; language impairment; lexical retrieval; machine learning classifier; novel; novel diagnostics; novel strategies; post stroke; predictive modeling; prospective; recruit; social; stroke-induced aphasia; supervised learning; syntax; treatment planning; treatment response

PROJECT SUMMARY Among the approximately 2 million Americans living with post-stroke aphasia, many experience difficulties with verbal expression that render everyday communication effortful, inefficient, and stressful.1,32 For persons with aphasia (PWA), speech non-fluency is often experienced as a visible disability with significant social consequences.36,37 Given this functional salience, speech fluency is an important construct to assess, monitor, and treat. It is, however, a longstanding clinical challenge to index fluency in a way that is comprehensive, interpretable, and efficient,7 and current approaches rely on either expert clinician ratings or time-intensive linguistic analyses using detailed coding. Temporal acoustic measures, by contrast, are objective measures that can be automatically or semi-automatically derived from connected speech. Prior research has demonstrated that the rate and rhythm of speech output reflect underlying impairments in both speech and language (e.g., motor speech, lexical retrieval), suggesting the utility of temporal acoustic measures to index non-fluency in PWA. The goal of the current study is to investigate the feasibility of using automated temporal acoustic features to identify non-fluent aphasia and to better understand the latent speech, language, and cognitive constructs underlying these surface speech features. To achieve this goal, we leverage machine learning techniques as part of a predictive modeling approach to identify speech features whose clinical utility can be generalized to inform future assessment of fluency in aphasia. In Aim 1, we will investigate whether temporal acoustic features accurately predict fluency status using a supervised machine learning approach (Aim 1a), and which features are most important to clinical distinctions of interest (fluent v. non-fluent; present v. absent motor speech impairment; Aim 1b). In Aim 2, we will determine the underlying speech, language, and cognitive contributors to inter-individual variability in temporal acoustic measures, thereby augmenting the explanatory power of study results. These aims are a first step toward an interpretable and automatable predictive model of fluency in PWA that can be generalized to novel diagnostic situations. Results of this research will help clinicians identify important features for efficient assessment of and treatment planning for patients as well as provide a mechanistic understanding of surface level features by mapping those features to explanatory clinical sub-constructs.

项目概要 在大约 200 万患有中风后失语症的美国人中，许多人都遇到了困难 言语表达使日常沟通变得费力、低效且充满压力。1,32 失语症（PWA），言语不流利通常被视为一种明显的残疾，具有严重的社交障碍 36,37 鉴于这种功能显着性，言语流畅性是评估、监控、 并治疗。然而，以全面的方式索引流畅性是一个长期的临床挑战。 可解释、高效7，当前的方法依赖于专家临床医生的评级或时间密集型 使用详细编码进行语言分析。相比之下，时间声学测量是客观测量 可以自动或半自动地从连接的语音中导出。先前的研究有 证明言语输出的速率和节奏反映了言语和语言的潜在障碍 语言（例如，运动语音、词汇检索），建议使用时间声学测量来索引 PWA 不流利。当前研究的目标是调查使用自动时间 声学特征可识别不流利的失语症并更好地理解潜在的言语、语言和 这些表面语音特征背后的认知结构。为了实现这一目标，我们利用机器 学习技术作为预测建模方法的一部分来识别语音特征，其临床实用性 可以概括为未来失语流畅性评估提供信息。在目标 1 中，我们将调查是否 使用监督机器学习方法，时间声学特征准确预测流利度状态 （目标 1a），以及哪些特征对于感兴趣的临床区别最重要（流利与非流利；目前 v. 不存在运动性言语障碍；目标 1b)。在目标 2 中，我们将确定潜在的语音、语言和 认知因素对时间声学测量的个体间差异有贡献，从而增强了 研究结果的解释力。这些目标是迈向可解释和自动化的第一步 PWA 流畅度的预测模型，可以推广到新的诊断情况。结果 研究将帮助临床医生确定重要特征，以便有效评估和制定治疗计划 患者以及通过将这些特征映射到表面水平特征来提供对表面特征的机械理解 解释性临床子结构。