Towards the Early Diagnosis of Alzheimer’s Disease via a Multicriteria Classification Model

摘要: The very early detection of Alzheimer's disease (AD) has been deeply investigated in numerous studies the past years. These have demonstrated that pathology usually arises decades before clinical diagnosis is effectively made, and so a reliable identification AD its earliest stages one major challenges clinicians researchers face nowadays. In present study, we introduce new approach developed upon specific Multicriteria Decision Aid (MCDA) classification method to assist process. MCDA centered on concept prototypes, is, alternatives serve as class representatives related given problem, performance index dependent choice values some control parameters. such regard, two techniques, based ELECTRE IV methodology other customized genetic algorithm, are employed order select prototypes calibrate parameters automatically. Moreover, database designed taking reference both functional cognitive recommendations Scientific Department Cognitive Neurology Aging Brazilian Academy neuropsychological battery exams made available by well-known Consortium Establish Registry for Disease (CERAD). Various experiments performed over this manner either fine-tune components model or compare level with exhibited state-of-the-art algorithms.