Prediction of knee osteoarthritis progression using radiological descriptors obtained from bone texture analysis and Siamese neural networks: data from OAI and MOST cohorts

Table 3 Summary of AUC values of the 8 models: data from OAI and MOST datasets

	Model_1	Model_2	Model_3	Model_4	Model_5	Model_6	Model_7	Model_8
OAI-QC
CR	0.58	0.69	0.71	0.63	0.69	0.72	0.72	0.75
RG	0.50	0.73	0.68	0.60	0.67	0.67	0.75	0.75
RGCR	0.56	0.69	0.71	0.63	0.69	0.69	0.72	0.74
OAI-nonQC
CR	0.58	0.69	0.70	0.63	0.68	0.72	0.72	0.73
RG	0.55	0.72	0.68	0.63	0.67	0.74	0.74	0.75
RGCR	0.58	0.68	0.70	0.63	0.68	0.72	0.72	0.73
MOST-QC
CR	0.56	0.75	0.74	0.64	0.68	0.78	0.78	0.79
RG	0.58	0.80	0.74	0.65	0.68	0.80	0.80	0.81
RGCR	0.57	0.75	0.75	0.65	0.68	0.78	0.78	0.79
MOST-nonQC
CR	0.56	0.74	0.72	0.62	0.67	0.77	0.77	0.78
RG	0.58	0.77	0.74	0.65	0.71	0.79	0.79	0.80
RGCR	0.57	0.75	0.74	0.64	0.69	0.78	0.78	0.79

ISSN: 1478-6362