基于BP神经网络的骨折愈合强度仿真初探

A Primary Study on Simulation of Fracture Strength Based on BP Neural Networks

目的探索用BP神经网络建立应力刺激与愈合骨强度之间的关系模型,为临床上准确预测骨折愈合程度提供理论基础.方法将兔双侧胫骨干横形截骨后,分别以应力松弛接骨板和传统坚硬接骨板固定,观察术后2～48周应力遮挡率和愈合骨弯曲强度变化.构造BP神经网络模型,用应力松弛接骨板组的实验数据进行训练,然后用训练好的网络对两组实验进行仿真,根据骨折部位的应力预测愈合骨强度.结果当输入已学习过的样本时,该模型能够准确地预测出愈合骨强度随应力的变化曲线,但对未学习过的样本,模型的预测误差较大.结论 BP神经网络可用来定量地研究各种因素对骨折愈合的影响,预测骨愈合程度,但仍需要进一步完善以提高其预测的准确性.

Objective To model the relationship between stimulating stress and fracture strength using BP neural networks, and to provide a theoretical basis for accurate prediction of the rate of fracture healing. Methods The bilateral tibiae in New Zealand rabbits were osteotomized and fixed by stress-relaxation plate（SRP） and rigid plate（RP）, respectively. The stress shielding rate and bending strength of the healing fractures were measured at 2 to 48 weeks postoperatively. A BP neural network was constructed and trained using the experimental data of the stress-relaxation group. Then the trained network was used for simulation to predict fracture strength of the two groups from the stress at the fracture site. Results With the input of the data that has been used to train the network, fracture strength similar to those measured in experiment was calculated from the BP neural network. However, poor results were obtained with the input of new data. Conclusion BP neural network can be used to investigate the influence of various factors on fracture healing quantitatively, and to predict the rate of healing. However, the model still needs to be perfected. More experimental or clinical data are needed to train the network for improving the accuracy of prediction.