Development of Thai Picture Description Task for Alzheimer's Screening using Part-of-Speech Tagging

Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI) are among the most common health conditions in elderly patients. Currently, methods to diagnose AD and MCI are lengthy, costly and require specialized staff to operate. A picture description task was developed to speed up the diagnosis. It was designed to be suitable and relatable to the Thai culture. In this paper, we will be presenting two picture description tasks named Thais-at-Home and Thai Temple Fair. The developed picture set was presented to 90 participants (30 normals, 30 MCI patients, and 30 AD patients). Then, the recording in the form of spontaneous speech is converted to text. A Part-of-Speech (PoS) tagger is used to categorize words into 7 types (noun, pronoun, adjective, verb, conjunction, preposition, and interjection) according to the Office of the Royal Society of Thailand. Six machine learning algorithms were applied to train with the PoS patterns and their performances were compared. Results showed that the PoS can be used to classify patients (MCI and AD) and healthy controls using multilayer perceptron with 90.00% sensitivity, 80.00% specificity, and 86.67% accuracy. Moreover, the findings showed that healthy controls used more conjunctions and verbs but fewer pronouns than the patients.Clinical relevance- The picture description tasks using part-of-speech (PoS) to showed promising results in screening Alzheimer's patients.