Abstract:Based on the statistics and collection of historical data, 18 surface characteristics of patients with pelvic fractures were selected. Bayesian network based on K2 algorithm was used to mine the causal relationship between the 18 surface characteristics, also between the surface characteristics and the pelvic fracture types. Different node ordering strategies were designed to analyze the influence on algorithm performance. Based on the stability of the pelvis, pelvic fracture was divided into A, B and C 3 types. Then found the features associated with each type of pelvic fracture, which was the basis of judgment. Based on the analysis of surface characteristics and pelvic fracture types, preliminary classification were made by means of early observation and simple examination.
