. 2022 Nov 21;13(2):572–584. doi: 10.21037/qims-22-531

Table 1. Classification performance of different models.

Models	Hyper-parameters	Features	Accuracy (mean ± SD)	RSD (%)	P value
Decision Tree	criterion=‘gini’, min_samples_split=2, min_samples_leaf=1	DLR	0.842±0.006	0.69	<0.0001
Decision Tree	criterion=‘gini’, min_samples_split=2, min_samples_leaf=1	DLR + ARF	0.854±0.007	0.84	<0.0001
Random Forest	n_estimators=100, criterion=‘gini’	DLR	0.904±0.003	0.40	<0.0001
Random Forest	n_estimators=100, criterion=‘gini’	DLR + ARF	0.910±0.003	0.40	<0.0001
LinearSVC	penalty=‘l1’, loss=‘squared_hinge’, max_iter=10000	DLR	0.867±0.001	0.10	<0.0001
LinearSVC	penalty=‘l1’, loss=‘squared_hinge’, max_iter=10000	DLR + ARF	0.881±0.001	0.11	<0.0001
Multilayer Perceptron	hidden_layer_sizes=(100) activation=‘relu’, solver=‘adam’	DLR	0.908±0.004	0.47	<0.0001
Multilayer Perceptron	hidden_layer_sizes=(100) activation=‘relu’, solver=‘adam’	DLR + ARF	0.911±0.004	0.42	<0.0001

SVC, support vector classification; DLR, deep learning latent representation; ARF, attentional lung region radiomics features; RSD, relative standard deviation.