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

Table 4 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 training cohort

	AUC (95%CI)	Optimal cut-off	Sensitivity (%)	Specificity (%)	PPV (%)	NPV (%)	Accuracy (%)
mLPaM	0.855 (0.809-0.901)	0.135	91.3	66.4	36.09	97.35	70.68
MELD	0.752 (0.688-0.817)	7.662	80.0	61.4	31.25	93.33	54.75
ALBI	0.776 (0.717-0.835)	-2.557	76.3	67.9	37.67	91.85	69.90
PTAR	0.728 (0.664-0.791)	0.150	73.8	71.8	42.11	90.79	72.24
LSM (kPa)	0.733 (0.672-0.794)	1.50	78.8	67.9	37.67	92.86	70.05
sLPaM	0.872 (0.823-0.921)	0.046	96.8	64.6	14.83	99.69	66.53
MELD	0.786 (0.687-0.886)	9.380	71.0	85.2	35.45	96.25	83.74
ALBI	0.798 (0.706-0.890)	-2.220	64.5	87.4	39.81	95.01	84.78
PTAR	0.731 (0.644-0.818)	0.150	80.6	65.5	15.33	97.76	66.59
LSM (kPa)	0.706 (0.618-0.795)	1.50	80.6	60.6	12.79	97.76	61.94

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.