A New Method for Syndrome Classification of Non-Small-Cell Lung Cancer Based on Data of Tongue and Pulse with Machine Learning

Table 6

Performance of models for detecting Qi deficiency syndrome of NSCLC based on different datasets.

Datasets	Model	AUC	Sensitivity	Specificity	F1	Precision	Accuracy
Symptom	Neural network	0.9223	0.9063	0.8286	0.8657	0.8286	0.8657
	SVM	0.9321	0.8750	0.8857	0.8750	0.8750	0.8806
	Logistic regression	0.9000	0.8125	0.8286	0.8125	0.8125	0.8209
	Random forest	0.9116	0.7813	0.8571	0.8065	0.8333	0.8209
Tongue & pulse	Neural network	0.7677	0.6316	0.6897	0.6761	0.7273	0.6567
	SVM	0.7455	0.6842	0.6552	0.7027	0.7222	0.6716
	Logistic regression	0.8022	0.6842	0.8276	0.7536	0.8387	0.7463
	Random forest	0.7314	0.5263	0.8621	0.6452	0.8333	0.6716
Symptom & tongue & pulse	Neural network	0.9401	0.9310	0.8421	0.8710	0.8182	0.8806
	SVM	0.9328	0.6552	0.9737	0.7755	0.9500	0.8358
	Logistic regression	0.9301	0.7931	0.8684	0.8070	0.8214	0.8358
	Random forest	0.9229	0.8966	0.8421	0.8525	0.8125	0.8657