The swift diagnosis and treatment of mild cognitive impairment (MCI), as a pre-stage of dementia, are important to reduce the enormous costs of dementia treatment. The aim of this paper is to investigate the potential features in human sleep stage to facilitate the early diagnosis of amnestic MCI. In order to extract specific features from sleep logs, we collected data of sleep logs using Fitbit's wrist band worn day and night from 8 subjects, for 12 week each. These data were analyzed using the SPSS(Statistical Package for Social Science) for verification and 8 total numbers of the significant features are extracted, further these features used for classification based on artificial neural networks (ANNs). ANNs with 10 input neurons (extracted features), 10 hidden neurons, and output neurons (diagnosis) were used to classify the patients. The results indicate that sleep logs based ANNs classifier have a good capacity (Mean AUC=0.84土0.08) to discriminate amnestic MCI patients from healthy controls.
Research Interests
Digital Phenotyping; Data Mining & Machine Learning for Text & Multimedia; Brain-Sense-ICTConvergence Computing; Computational Olfaction Measurement; Simulation&Modeling