BACKGROUND
Alzheimer's disease is the most common form of dementia, and it is a disease that makes it difficult for patients and their families due to various symptoms. For these reasons, early detection is very important, and after early detection, symptoms can be alleviated through medication and treatment.
OBJECTIVE
Since Alzheimer's disease strongly induces language disorders, our research goal is detecting Alzheimer's disease quickly and easily through the analysis of language characteristics.
METHODS
Using the Mini-Mental State Examination for Dementia Screening (MMSE-DS), which is the most used in Korean public health centers, negative answers were obtained according to the questionnaire. Among the acquired voices, significant questionnaires and answers were selected, spectrogrammed, and converted into MFCC. After accumulating significant answers, training data was created, augmented, and then trained on various deep learning models and the results were observed.
RESULTS
Due to the lack of data, the results of the five-fold cross validation were more significant than the holdout method. the accuracy of separating AD patients from the control group using Densnet121 was 91.25%.
CONCLUSIONS
In this regard, the potential for remote health care can be increased by simplifying the AD screening process. By facilitating remote health care, the proposed method is expected to enhancing the accessibility of AD screening and increase the rate of early AD detection.
CLINICALTRIAL
IRB No. CNUH2019-02-068