Objective: This study presents a novel approach for early detection of cognitive impairment in the elderly. The approach incorporates the use of speech sound analysis, multivariate statistics, and data-mining techniques. We have developed a speech prosody-based cognitive impairment rating (SPCIR) that can distinguish between cognitively normal controls and elderly people with mild Alzheimer's disease (mAD) or mild cognitive impairment (MCI) using prosodic signals extracted from elderly speech while administering a questionnaire. Two hundred and seventy-three Japanese subjects (73 males and 200 females between the ages of 65 and 96) participated in this study. The authors collected speech sounds from segments of dialogue during a revised Hasegawa's dementia scale (HDS-R) examination and talking about topics related to hometown, childhood, and school. The segments correspond to speech sounds from answers to questions regarding birthdate (T1), the name of the subject's elementary school (T2), time orientation (Q2), and repetition of three-digit numbers backward (Q6). As many prosodic features as possible were extracted from each of the speech sounds, including fundamental frequency, formant, and intensity features and mel-frequency cepstral coefficients. They were refined using principal component analysis and/or feature selection. The authors calculated an SPCIR using multiple linear regression analysis.
Conclusion: In addition, this study proposes a binary discrimination model of SPCIR using multivariate logistic regression and model selection with receiver operating characteristic curve analysis and reports on the sensitivity and specificity of SPCIR for diagnosis (control vs. MCI/mAD). The study also reports discriminative performances well, thereby suggesting that the proposed approach might be an effective tool for screening the elderly for mAD and MCI.