ObjectiveTo understand the inpatient classification and influence factors of hospitalization expenses, so as to provide basis for hospital management. MethodsThe diagnosis and treatment data of inpatients in a grade A tertiary hospital in 2013 were collected, the percentile method were used to describe the expenses distribution, the K-means clustering method was applied to classify the inpatients, the rank-sum test was utilized to analyze the differences of the costs among different groups, ICD-10 was applied to analyze the diseases distribution, and the median regression was used to analyze the influence factors. ResultsThere were 175 333 inpatients in total. The median of the expenses was 10 016.31 yuan RMB. The inpatients might be classified into seven groups with different expenses (P=0.0001). For inpatients who had no "blood transfusion cost", the top three factors of cost category were operation, laboratory test, examination; for who had "blood transfusion cost", the top three factors of cost category were blood transfusion, laboratory test, examination. There were 2 147, 2 182, 1 499, 1 301, 2 059, 22 and 14 kinds of diseases (ICD-10 four-digit code) respectively among the seven groups. The influence factors could be summarized into patient-related and diagnosis & treatment-related ones. ConclusionThe costs of operation, blood transfusion, laboratory test, and examination affect the inpatients classification greatly. The results could be of help to inform the admission of patients, the expense control and the disease management.
It's common that general rules exist in a certain classification. The general rules of expense classification enable us to judge the category of a patient as soon as possible and to curb the expense. Theory of rough set helps us reach the best reduction of attributes. Based on the core attributes, classification rules are put forward by value reduction. The results show that 10 core attributes remain in 21 attributes of 1527 inpatients' information and 76 classification rules are founded. All of 76 rules guide classification of the patients. 44 of the 76 rules define the only category of a patient, the other 32 rules defines the potential catagories of a patient. Meanwhile, equal attributes of the same category are summerized to guide the cost control of patients. The results indicate that the theory of rough set is effective in attributes reduction and rule generalization of patient expense classification, and it has important significance on medical practice.