User's mentality classification method using self-organising feature map on healthcare intelligent system for diabetic patients

摘要

Diabetes is a metabolic disorder characterised by the elevation of blood glucose. Glysemic control can delay the onset and slow the progression of vascular complications. Lifestyle modification including weight reduction can contribute significantly to glycemic control. The health support intelligent system for diabetic patients (HSISD) can provide guideline-based decision support (GDS) for lifestyle modifications in the treatment of diabetes. HSISD also provides opportunities for telecounselling (TC) with the use of mobile devices and the internet. The TC phase inquires about the patient's condition and the patient answers in a questionnaire, which includes a free-answer style question. However, physicians may not have enough time to read all text carefully. We propose a method to analyse text data from the patients and classify them into five anxiety types automatically. Related to the classified anxiety types, the method can analyse the patient's inner emotion to guess serious and emergency degree. Self-organising feature map is trained by the distribution of feature words (morphemes) in the input text and also classify anxiety type and emotion type simultaneously.