Background: The GALAD score is a serum biomarkerbased model that predicts the probability of having hepatocellular carcinoma (HCC) in patients with chronic liver disease. We aimed to assess the performance of the GALAD score in comparison with liver ultrasound for detection of HCC.Methods: A single-center cohort of 111 HCC patients and 180 controls with cirrhosis or chronic hepatitis B and a multicenter cohort of 233 early HCC and 412 cirrhosis patients from the Early Detection Research Network (EDRN) phase II HCC Study were analyzed.Results: The area under the ROC curve (AUC) of the GALAD score for HCC detection was 0.95 [95% confidence interval (CI), 0.93-97], which was higher than the AUC of ultrasound (0.82, P <0.01). At a cutoff of À0.76, the GALAD score had a sensitivity of 91% and a specificity of 85% for HCC detection. The AUC of the GALAD score for early-stage HCC detection remained high at 0.92 (95% CI, 0.88-0.96; cutoff À1.18, sensitivity 92%, specificity 79%). The AUC of the GALAD score for HCC detection was 0.88 (95% CI, 0.85-0.91) in the EDRN cohort. The combination of GALAD and ultrasound (GALADUS score) further improved the performance of the GALAD score in the single-center cohort, achieving an AUC of 0.98 (95% CI, 0.96-0.99; cutoff À0.18, sensitivity 95%, specificity 91%). a For the calculation of AUC, the continuous GALAD score is used, whereas for sensitivity and specificity, we used the GALAD cutoff. b P value looking at difference in AUC between GALAD and ultrasound.Yang et al.