Badal Varsha D, Tran Caitlyn, Brown Haze, Glorioso Danielle K, Daly Rebecca, Molina Anthony J A, Moore Alison A, Bilal Erhan, Lee Ellen E, Depp Colin A
Department of Psychiatry, University of California San Diego, San Diego, CA, United States.
Stein Institute for Research on Aging, University of California San Diego, San Diego, CA, United States.
Front Psychiatry. 2025 Jul 1;16:1596132. doi: 10.3389/fpsyt.2025.1596132. eCollection 2025.
Psycho-linguistic and audio data derived from speech may be useful in screening and monitoring cognitive aging. However, there are gaps in understanding the predictive value of different prompts (e.g., open ended or structured) and the relationship of features to subjective versus objective cognition.
To advance understanding of method variation in speech-analysis based psychometry, we evaluated targeted prompts for classification of impaired cognition and cognitive complaints.
A sample of 49 older participants (mean age: 76.9, SD: 8.5) completed short interview questions and cognitive assessments. Acoustic and Linguistic Inquiry through Word Counting i.e., LIWC (verbal content-based) features were derived from answers to open ended questions about aging (AG) and the Cookie Theft task (CT). Outcomes were objective cognitive ability measured using Telephone Interview for Cognitive Status (TICS-m), and subjective cognition using Cognitive Failures Questionnaire (CFQ).
A combined feature set including acoustic and LIWC (verbal content) yielded excellent classification results for both CFQ and TICS-m. The F1, precision and recall for CFQ elevation was 0.83, 0.85 and 0.82, and for TICS-m cutoff was 0.92, 0.92 and 0.92 respectively (using single learners). Features derived from CT task were of greater relevance to TICS-m classification, while the features from the AG task were of greater relevance to the CFQ classification.
Acoustic and psycholinguistic features are relevant to assessment of cognition and subjective cognitive complaints, with combined features performing best. However, subjective and objective cognitions were predicted to differing extents by the different tasks, and the feature sets.
源自言语的心理语言学和音频数据可能有助于认知衰老的筛查和监测。然而，在理解不同提示（例如开放式或结构化）的预测价值以及特征与主观认知和客观认知之间的关系方面仍存在差距。
为了加深对基于言语分析的心理测量方法差异的理解，我们评估了用于受损认知和认知主诉分类的针对性提示。
49名老年参与者（平均年龄：76.9，标准差：8.5）的样本完成了简短的访谈问题和认知评估。通过词频统计进行声学和语言探究，即LIWC（基于言语内容）特征，来自关于衰老（AG）和饼干失窃任务（CT）的开放式问题的答案。结果指标为使用认知状态电话访谈（TICS-m）测量的客观认知能力，以及使用认知失误问卷（CFQ）测量的主观认知。
包括声学和LIWC（言语内容）的组合特征集在CFQ和TICS-m上均产生了出色的分类结果。CFQ升高的F1值、精确率和召回率分别为0.83、0.85和0.82，TICS-m临界值的F1值、精确率和召回率分别为0.92、0.92和0.92（使用单一学习器）。源自CT任务的特征与TICS-m分类的相关性更大，而源自AG任务的特征与CFQ分类的相关性更大。
声学和心理语言学特征与认知评估及主观认知主诉相关，组合特征表现最佳。然而，不同任务和特征集对主观认知和客观认知的预测程度不同。
