Table 2.

Lung function values from body plethysmography and the predicted lung function values from all algorithms used with their standard deviation.

Lung Function Values from Body Plethysmorgraphy and Predicted Lung Function Values
		Measured Values	Mean Prediction	Median Prediction	kNN	Polynomial Regression	Neural Network	XGBoost	p-Value
inspiration	%FEV1	56 ± 6	56 ± 0.3	48 ± 0.1	56 ± 6	55 ± 13	55 ± 13	56 ± 16	0.0024
	%FEV1/VC	55 ± 7	56 ± 0.1	54 ± 0.1	55 ± 7	56 ± 7	56 ± 7	56 ± 10	0.732
	RV/TLC	59 ± 6	60 ± 0.2	61 ± 0.5	59 ± 6	60 ± 10	60 ± 11	59 ± 11	0.96
expiration	%FEV1	53 ± 12	56 ± 0.3	48 ± 0.1	53 ± 12	56 ± 14	55 ± 14	56 ± 16	0.0078
	%FEV1/VC	55 ± 8	56 ± 0.1	54 ± 0.1	55 ± 8	56 ± 8	56 ± 8	56 ± 11	0.6
	RV/TLC	61 ± 9	60 ± 0.2	61 ± 0.5	61 ± 9	59 ± 11	59 ± 12	59 ± 12	0.7996
delta	%FEV1	56 ± 13	56 ± 0.3	48 ± 0.1	56 ± 13	56 ± 14	49 ± 27	56 ± 16	0.002
	%FEV1/VC	55 ± 8	56 ± 0.1	54 ± 0.1	55 ± 8	56 ± 8	49 ± 25	56 ± 11	0.0005
	RV/TLC	59 ± 8	60 ± 0.2	61 ± 0.5	59 ± 8	59 ± 8	54 ± 26	58 ± 13	0.0522

Measured lung function values from the body plethysmography and predicted lung function values from the mathematical models, both with their standard deviation. For k-nearest neigbours and the polynomial regression, only the best performing ks and degrees are shown (see Table 1). The p-values of the ANOVA are shown in the right column. FEV1: forced expiratory volume in one second; VC: vital capacity; RV: residual volume; TLC: total lung capacity; kNN: k-nearest neighbour.