Clinical value of predictive models based on liver stiffness measurement in predicting liver reserve function of compensated chronic liver disease

Table 5 Comparison of the predictive performance of the new constructed models (mLPaM and sLPaM) and other models in the assessment of impaired liver reserve function in the prospective validation cohort

	AUC (95%CI)	Optimal cut-off	Sensitivity (%)	Specificity (%)	PPV (%)	NPV (%)	Accuracy (%)
mLPaM	0.869 (0.810-0.929)	0.240	89.1	74.4	60.85	93.86	78.94
MELD	0.729 (0.633-0.824)	9.743	43.5	96.5	93.65	59.01	67.74
ALBI	0.824 (0.749-0.900)	-2.315	78.3	76.7	63.78	87.09	77.25
PTAR	0.672 (0.580-0.765)	1.500	89.1	45.3	30.70	93.86	54.66
LSM (kPa)	0.782 (0.702-0.862)	1.500	91.3	65.1	49.93	95.15	72.33
sLPaM	0.876 (0.812-0.940)	0.073	92.9	68.3	49.94	95.15	72.33
MELD	0.803 (0.701-0.904)	9.187	64.3	85.6	61.54	87.00	79.98
ALBI	0.836 (0.743-0.929)	-1.897	71.4	88.5	67.44	90.27	84.22
PTAR	0.666 (0.566-0.767)	1.500	92.9	59.6	28.43	97.98	64.50
LSM (kPa)	0.743 (0.653-0.833)	1.500	92.9	55.8	25.37	97.98	60.96

MELD: Model for end-stage liver disease; ALBI: Albumin-bilirubin grade; PTAR: Prothrombin time international normalized ratio to albumin ratio; LSM: Liver stiffness measurement; AUC: Area under the cure; CI: Confidence interval; NPV: Negative predictive value; PPV: Positive predictive value; mLPaM: Mildly impaired liver reserve function model; sLPaM: Severely impaired liver reserve function model.