Table 1.

Machine learning performance metrics for validation data sets of (a) Near-Infrared (NIR), (b) Raman and (c and d) multimodal data using logistic regression (LR), stochastic gradient descent (SGD) and support vector machines (SVM), with combined “stack” (LR + SGD + SVM)

	AUC	Precision	Recall	Specificity
(a) NIR model
Logistic regression	0.980	0.944	0.933	0.967
SGD	0.550	0.281	0.400	0.700
SVM	0.840	0.806	0.800	0.900
Stack	0.933	0.794	0.800	0.900
(b) Raman model
Logistic regression	0.985	0.940	0.929	0.960
SGD	0.892	0.869	0.857	0.932
SVM	0.992	0.940	0.929	0.960
Stack	0.954	0.869	0.857	0.932
(c) MSS: multimodal (NIR + Raman) to detect DCM vs. IHD vs. normal patients
Logistic regression	0.975	0.841	0.828	0.917
SGD	0.847	0.803	0.793	0.899
SVM	0.971	0.853	0.828	0.917
Stack	0.961	0.853	0.828	0.917
(d) MSS: multimodal (NIR + Raman) to detect pathological vs. normal patients
Logistic regression	0.961	0.969	0.966	0.984
SGD	0.944	0.967	0.966	0.923
SVM	1.000	1.000	1.000	1.000
Stack	1.000	0.944	0.931	0.969

Bold values indicate values obtained from the stack algorithm and used for analyses