Applications of fuzzy theory on health care: an example of depression disorder classification based on FCM

The purpose of this study is to apply fuzzy theory on health care. To achieve this goal, Beck Depression Inventory (BDI)-II was adopted as the instrument and outpatients of a psychiatric clinic were recruited as samples and undergraduates as non-clinical sample as well. To elicit the membership degree, we asked the subjects are free to choose more than one alternative for each item listed in BDI and, in turn, assign percentages on the chosen alternatives. Moreover, the sum of percentages of the chosen categories is restricted to 100%. We performed the possibility- based (fuzzy c-means, FCM) and probability-based classification (Wald's method and k-means) to classification of severity of depression. The scoring of BDI of subjects were analyzed by clustering analysis while the diagnose of depression-severity by a psychiatrist was used as the criterion to evaluate classification accuracy. The percentage of correct classification among FCM, Wald's method and k-means were compared. The analytical results show the Kendall's τ coefficient of FCM, Wald's method and k-means were .549, .316, and .395, respectively. That is, FCM exhibited a higher association between the original and classified membership than did Wald's and k-means methods. We concluded that FCM identified the data structure more accurately than the two crisp clustering methods. It is also suggested that considerable cost concerning prevention and cure of depression might be reduced via FCM.