Exploring the assessment of post-cardiac valve surgery pulmonary complication risks through the integration of wearable continuous physiological and clinical data

Table 3 Comparison of model performance for different feature combinations

Model	Feature combination	AUC	ACC	F 1	Precision	P-Value^a
XGB	Physiological	0.69 ± 0.15	0.79 ± 0.06	0.73 ± 0.07	0.74 ± 0.14	0.01*
	Clinical	0.78 ± 0.08	0.77 ± 0.03	0.68 ± 0.03	0.61 ± 0.04	0.05*
	Both	0.82 ± 0.08	0.80 ± 0.01	0.74 ± 0.0	0.75 ± 0.10	/
LR	Physiological	0.60 ± 0.08	0.75 ± 0.05	0.67 ± 0.02	0.60 ± 0.02	0.17
	Clinical	0.75 ± 0.11	0.78 ± 0.03	0.70 ± 0.04	0.66 ± 0.11	0.65
	Both	0.77 ± 0.09	0.75 ± 0.05	0.69 ± 0.06	0.65 ± 0.09	/
RF	Physiological	0.63 ± 0.07	0.76 ± 0.04	0.67 ± 0.04	0.61 ± 0.04	0.00*
	Clinical	0.73 ± 0.03	0.77 ± 0.05	0.71 ± 0.03	0.69 ± 0.09	0.08
	Both	0.80 ± 0.10	0.80 ± 0.04	0.75 ± 0.04	0.77 ± 0.10	/
SVM	Physiological	0.64 ± 0.15	0.77 ± 0.05	0.68 ± 0.05	0.61 ± 0.05	0.82
	Clinical	0.54 ± 0.29	0.76 ± 0.04	0.67 ± 0.04	0.61 ± 0.04	0.45
	Both	0.77 ± 0.17	0.78 ± 0.03	0.68 ± 0.04	0.61 ± 0.04	/
KNN	Physiological	0.42 ± 0.08	0.72 ± 0.06	0.65 ± 0.04	0.60 ± 0.04	0.00*
	Clinical	0.66 ± 0.13	0.71 ± 0.02	0.68 ± 0.02	0.65 ± 0.03	0.96
	Both	0.70 ± 0.10	0.75 ± 0.06	0.73 ± 0.06	0.74 ± 0.08	/

Notes: AUC, ACC, F1, and precision values were expressed as mean ± standard deviation of five-fold cross-validation. AUC, the area under the ROC curve; ACC, accuracy; F1, F1 score; XGB, XGBoost; LR, Logistic Regression; RF, Random Forests; SVM, Support Vector Machine; KNN, k-Nearest Neighbor
a. The p-value indicates the significance of performance differences between the model based on the both dataset against those using the clinical or physiological dataset individually, as evaluated by the DeLong test
* p < 0.05

ISSN: 1472-6947