基于贝叶斯网络原理的835例冠心病病例中医证候分类研究

Classification of TCM syndromes in 835 cases of coronary heart disease: on the basis of Bayesian networks principle

目的探讨客观有效的冠心病中医四诊信息融合模型。方法采用本课题组自行研制的中医心系问诊量表及舌面一体仪等收集835例冠心病患者的中医四诊证候信息,在专家辨证和先验知识的基础上,通过贝叶斯网络(Bayesian networks)对四诊证候信息进行分类识别研究。结果基于贝叶斯网络建立的融合模型对心气虚、心阳虚、心阴虚、血瘀、痰浊5个证型的识别率分别为69.34%、84.85%、65.12%、83.87%和65.12%。结论基于贝叶斯网络原理建立的四诊信息融合模型在冠心病中医证候分类客观化研究中具有较好的应用前景。

Objective To discuss the objective and effective information fusion model of coronary heart disease（CHD） based on the TCM four methods of diagnosis. Methods The information of TCM four methods of diagnosis was collected involving in 835 patients with CHD. On the basis of syndrome differentiation by experts and priori knowledge, we identified the classification of TCM syndromes in CHD by Bayesian networks. Results The recognition rate of fusion model was 69.34% in heart qi deficiency syndrome, 84.85% in heart yang deficiency syndrome, 65.12% in heart yin deficiency syndrome, 83.87% in blood stasis syndrome, 65.12% in phlegm turbid syndrome. Conclusion The information fusion model of four methods of diagnosis has better application prospect in classification of TCM syndromes in CHD.