Artificial intelligence, language and Neuropsychological measures in Alzheimer’s disease

Abstract

AbstractBackgroundOne of the current challenges in the field of Alzheimer’s disease (AD) is to identify patients with mild cognitive impairment (MCI) that will convert to AD. Artificial intelligence, in particular machine learning (ML), has established as one of more powerful approach to extract reliable predictors and to automatically classify different AD phenotypes. It is time to accelerate the translation of this knowledge in clinical practice, mainly by using low‐cost features originating from the language and neuropsychological assessment.MethodWe aim at performing a meta‐analytic evaluation of the contribution of ML and language/neuropsychological measures for the automated classification of AD and MCI patients and the prediction of MCIs’ conversion to AD‐type dementia. Specifically, we study, from the results reported by independent studies, whether ML algorithms, trained on a set of language and neuropsychological measures, could be used for the automatic diagnosis of MCI and AD‐type dementia. To tackle the issue of cross‐linguistic sensitivity, this work spans cohorts of speakers from widely different languages. The advantages and issues that should be taken under consideration for translating these approaches into reliable clinical studies are discussed.ResultAlthough a high heterogeneity was observed, this meta‐analysis shows that ML applied to language and neuropsychological measures can lead to a successful automatic classification, being more specific as screening rather than prognosis tool. Relevant categories of language and neuropsychological tests can be extracted by ML that maximize the classification accuracy.ConclusionML applied on language and neuropsychological measures can automatically classify AD patients, even at an early stage of the disease. This brings several advantages, such as the development of more objective and efficient language and neuropsychological batteries for improving the early diagnosis of AD. Future studies should empirically test the combination of methodological features necessary to improve patients’ classification also at the preclinical stages.