Clinical Data Mining of Phenotypic Network in Angina Pectoris of Coronary Heart Disease

Table 4

The computational performance of the four MI-based algorithms.

Syndrome	Algorithm	Sensitivity	Specificity	Accuracy
Qi deficiency syndrome	1	0.911497105	0.634958383	0.79804878
	2	0.819699499	0.498826291	0.686341463
	3	0.829592685	0.514757969	0.699512195
	4	0.804898649	0.473441109	0.664878049
Blood stasis syndrome	1	0.8408	0.595	0.744878049
	2	0.909171861	0.618122977	0.777560976
	3	0.828371278	0.52753304	0.695121951
	4	0.900179856	0.601279318	0.763414634
Yin deficiency syndrome	1	0.843273232	0.87434161	0.863414634
	2	0.80112835	0.845637584	0.830243902
	3	0.773049645	0.828996283	0.809756098
	4	0.812849162	0.855322339	0.840487805
Tan-Zhuo syndrome	1	0.806451613	0.877769836	0.855121951
	2	0.781701445	0.853538893	0.831707317
	3	0.806299213	0.869964664	0.850243902
	4	0.793333333	0.848275862	0.832195122
Yang deficiency syndrome	1	0.724233983	0.922531047	0.887804878
	2	0.710144928	0.914369501	0.88
	3	0.630985915	0.890962099	0.854634146
	4	0.690625	0.901734104	0.868780488
Qi stagnation syndrome	1	0.707964602	0.958333333	0.930731707
	2	0.7	0.948108108	0.923902439
	3	0.731707317	0.953387534	0.931219512
	4	0.641025641	0.940161725	0.911707317
Spleen deficiency syndrome	1	0.757575758	0.967602592	0.947317073
	2	0.773333333	0.950526316	0.937560976
	3	0.752808989	0.959401709	0.941463415
	4	0.703703704	0.949152542	0.929756098