Explainable machine learning methods and respiratory oscillometry for the diagnosis of respiratory abnormalities in sarcoidosis

Table 5 Fuzzy features with significant changes between groups. Note that Control versu s Sarcoidosis (altered) presents 33 features distributed in two columns

Control versus Sarcoidosis (normal)		Control versus sarcoidosis (altered)
Feature	p-value	Feature	p-value	Feature	p-value
Ax_low	0.00007	Ax_low	0.0000068	C_high	0.0036
Ax_medium	0.00007	Fr_low	0.000012	Rp_low	0.0039
Rt_low	0.00024	Ax_medium	0.000065	Rm_low	0.0042
Cdyn_low	0.0015	Rt_low	0.00014	S_high	0.006
Rt_medium	0.0023	Fr_high	0.0003	Rm_high	0.0077
Z4_low	0.003	Cdyn_low	0.00056	R4-R20_medium	0.0084
Z4_medium	0.0035	Z4_low	0.00068	Rt_medium	0.009
Fr_low	0.0067	Z4_high	0.00069	Z4_medium	0.011
Cdyn_medium	0.0072	Xm_high	0.0011	Xm_low	0.012
R_low	0.019	R0_low	0.0016	R4_high	0.015
Fr_medium	0.022	R4_low	0.0019	R4-R20_high	0.016
R0_low	0.028	Rt_high	0.0023	I_high	0.016
R4_low	0.028	C_low	0.0025	S_low	0.016
C_low	0.039	R0_high	0.003	R_low	0.017
C_medium	0.049	Cdyn_medium	0.0031	C_medium	0.029
		Rp_medium	0.0032	Fr_medium	0.034
		R4-R20_low	0.0034

ISSN: 1472-6947