摘要：Alzheimer's disease (AD) and other dementias have become the fifth leading cause of death worldwide. Accurate early detection of the disease and its precursor, Mild Cognitive Impairment (MCI), is crucial to alleviate the burden on the healthcare system. While most of the existing work in the literature applied neural networks directly together with several data pre-processing techniques, we proposed in this paper a screening system that is to perform classification based on automatic processing of the transcripts of speeches from the subjects undertaking a neuropsychological test. Our system is also shown applicable to different datasets and languages, suggesting that our system holds a high potential to be deployed widely in hospitals across regions. We conducted comprehensive experiments on two different languages datasets, the Pitt dataset and the NTUHV dataset, to validate our study. The results showed that our proposed system significantly outperformed the previous works on both datasets, with the score of the area under the receiver operating characteristic curve (AUROC) of classifying AD and healthy control (HC) being as high as 0.92 on the Pitt dataset and 0.97 on the NTUHV dataset. The performance on classifying MCI and HC remained promising, with the AUROC being 0.83 on the Pitt dataset and 0.88 on the NTUHV dataset.
