An Intelligent Clinical Decision Support System for Patient-Specific Predictions to Improve Cervical Intraepithelial Neoplasia Detection

Table 16

Diagnostic performance of cytology, biomarkers, and the CDSS to identify high-grade cervical intraepithelial neoplasia or cancer (CIN2+).

Histology endpoint CIN2+	Sensitivity (%)	Specificity (%)	PPV (%)	NPV (%)	Youden’s index
Pap test (cut-off ASCUS+)	98.1	45.3	33.3	98.9	0.43
Pap test (cut-off LSIL+)	89.4	67.0	43.0	96.0	0.56
Pap test (cut-off HSIL+)	71.4	95.3	81.0	92.3	0.67
HPV DNA test	91.9	61.5	39.9	96.5	0.53
HR-HPV DNA	89.4	67.4	43.2	95.8	0.57
NASBA E6/E7 HPV mRNA test	77.0	90.2	68.5	93.4	0.67
Flow cytometric E6/E7 HPV mRNA assay	93.2	81.9	58.8	97.7	0.75
p16	58.4	92.9	69.6	88.9	0.51
CDSS	89.4	97.1	89.4	97.1	0.87

Statistical measures have been calculated using all the cases of the dataset (Table 1). Histology endpoint is CIN2+ for all cases. Definition of positivity of each medical test is presented in Table 15. For the CDSS, positivity was defined as a classification result of CIN2/3 or cancer. CIN2+: cervical intraepithelial neoplasia grade 2 or worse, PPV: positive predictive value, and NPV: negative predictive value.