Table 4.

Performance comparison of PIP-EL with other machine learning-based methods on the same benchmarking dataset.

Method	Matthews’ correlation coefficient (MCC)	Accuracy	Sensitivity	Specificity	AUC	P-value
PIP-EL	0.435	0.717	0.701	0.727	0.786	–
Extremely randomized trees (ERT)	0.423	0.712	0.714	0.709	0.775	0.538
Support vector machine (SVM)	0.298	0.649	0.618	0.679	0.697	<0.000003
ProInflam	0.580	0.778	0.936	0.620	0.880	–

The first column represents the methods developed in this study. The column 2–6 respectively represent the MCC, accuracy, sensitivity, specificity, and AUC value. The last column represents a pairwise comparison of AUC between PIP-EL and the other methods using a two-tailed t-test. P ≤ 0.05 indicates a statistically meaningful difference between PIP-EL and the selected composition (shown in bold). For comparison, we have also included ProInflam CV performance.