Skip to main content

Table 3 Sensitivity, specificity and area-under-the-curve (AUC) of AI-assisted ultrasonography, AI-assisted elastography, and AI-assisted clinical data for the diagnosis of liver cirrhosis (F4), advanced fibrosis (F3–4) and significant liver fibrosis (F2–4)

From: Application of artificial intelligence in chronic liver diseases: a systematic review and meta-analysis

Analysis

AI-assisted ultrasonography

AI-assisted elastography

AI-assisted clinical data

Transient elastography [41, 42]

Real-time elastography [43]

APRI [44]

FIB-4 [44]

Cirrhosis (F4)

(Cut-off 2.0)

(Cut-off 1.62–2.65)

 Sensitivity

0.79 (0.73–0.84)

0.87 (0.50–0.98)

0.65 (0.58–0.72)

0.83 (0.79–0.86)

0.74 (0.63–0.82)

0.31 (0.13–0.63)

0.64 (0.39–0.77)

 Specificity

0.93 (0.90–0.95)

0.88 (0.85–0.91)

0.91 (0.74–0.97)

0.89 (0.87–0.91)

0.84 (0.79–0.88)

0.89 (0.81–0.96)

0.86 (0.75–0.98)

 AUC

0.95

0.89

0.68

0.94

0.72

0.72

0.78

Advanced fibrosis (F3–4)

(Cut-off 0.5)

(Cut-off 1.45)

 Sensitivity

–

0.84 (0.74–0.91)

0.87 (0.79–0.92)

0.82 (0.78–0.86)

0.82 (0.75–0.88)

0.73 (0.63–0.83)

0.63 (0.50–0.71)

 Specificity

–

0.94 (0.77–0.99)

0.82 (0.79–0.85)

0.86 (0.82–0.89)

0.81 (0.72–0.88)

0.55 (0.37–0.72)

0.56 (0.14–0.80)

 AUC

–

0.93

0.86

0.89

0.86

0.76

0.80

Significant fibrosis (F2–4)

(Cut-off 0.5)

(Cut-off 1.45)

 Sensitivity

0.90 (0.87–0.93)

0.73 (0.68–0.77)

0.96 (0.94–0.98)

0.79 (0.74–0.82)

0.79 (0.75–0.83)

0.70 (0.35–0.97)

0.65 (0.52–0.87)

 Specificity

0.82 (0.77–0.85)

0.87 (0.82–0.90)

0.78 (0.72–0.83)

0.78 (0.72–0.83)

0.76 (0.68–0.82)

60 (0.34–0.87)

0.74 (0.65–0.85)

 AUC

0.92

0.85

0.86

0.84

0.69

0.72

0.76

  1. Pooled sensitivity, specificity and AUC of transient elastography, real-time elastography, AST to Platelet Ratio Index (APRI) and Fibrosis-4 (FIB-4) for diagnosis of liver fibrosis from previous meta-analyses [41,42,43,44] are also shown