Spoken Language Derived Measures for Detecting Mild Cognitive Impairment

• Published in: IEEE transactions on audio, speech, and language processing Vol. 19; no. 7; pp. 2081 - 2090
• Main Authors: Roark, B., Mitchell, M., Hosom, J., Hollingshead, K., Kaye, J.
• Format: Journal Article
• Language: English
• Published: Piscataway, NJ IEEE 01.09.2011; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Biological and medical sciences; Complexity theory; Computerized, statistical medical data processing and models in biomedicine; Dementia; Exact sciences and technology; Forced alignment; Information, signal and communications theory; linguistic complexity; Manuals; Medical management aid. Diagnosis aid; Medical sciences; mild cognitive impairment (MCI); parsing; Pragmatics; Signal processing; Speech; Speech processing; spoken language understanding; Syntactics; Telecommunications and information theory; Human; Performance evaluation; Speech analysis; spoken language understanding; linguistic complexity; mild cognitive impairment (MCI); Syntactic analysis; Complexity measure; parsing; Statistical method; Forced alignment; Automatic measurement; Diagnostic aid; Elderly
• ISSN: 1558-7916; 1558-7924
• DOI: 10.1109/TASL.2011.2112351

Spoken responses produced by subjects during neuropsychological exams can provide diagnostic markers beyond exam performance. In particular, characteristics of the spoken language itself can discriminate between subject groups. We present results on the utility of such markers in discriminating between healthy elderly subjects and subjects with mild cognitive impairment (MCI). Given the audio and transcript of a spoken narrative recall task, a range of markers are automatically derived. These markers include speech features such as pause frequency and duration, and many linguistic complexity measures. We examine measures calculated from manually annotated time alignments (of the transcript with the audio) and syntactic parse trees, as well as the same measures calculated from automatic (forced) time alignments and automatic parses. We show statistically significant differences between clinical subject groups for a number of measures. These differences are largely preserved with automation. We then present classification results, and demonstrate a statistically significant improvement in the area under the ROC curve (AUC) when using automatic spoken language derived features in addition to the neuropsychological test scores. Our results indicate that using multiple, complementary measures can aid in automatic detection of MCI.