ABSTRACT
BACKGROUND: Modified albumin-bilirubin (mALBI) grade has been established as a survival determinant in hepatocellular carcinoma (HCC) patients who receive locoregional and targeted therapies. AIM: To investigate whether mALBI could predict survival in unresectable HCC (uHCC) patients who were treated with atezolizumab plus bevacizumab (AB). METHODS: A single-center, retrospective cohort study enrolled uHCC patients who received AB treatment between September 2020 and April 2023 and were followed up until June 2023. An association between mALBI and patient survival was determined using Cox proportional hazards analysis. RESULTS: Of the 83 patients, 67 patients (80.7%) were male with the mean age of 60.6 years. Among them, 22 patients (26.5%) were classified as Barcelona Clinic Liver Cancer B, and 61 patients (73.5%) were classified as Barcelona Clinic Liver Cancer C. Cirrhosis was present in 76 patients (91.6%), with 58 patients classified as Child-Turcotte-Pugh (CTP) A and 18 as CTP B. The median overall survival (OS) and progression-free survival were 13.0 mo [95% confidence interval (CI): 5.2-20.8] and 9.0 mo (95%CI: 5.0-13.0), respectively. The patients were divided into two groups based on mALBI grades: 42 patients (50.6%) in the mALBI 1 + 2a group; and 41 patients (49.4%) in the mALBI 2b + 3 group. During the median follow-up period of 7.0 mo, the mALBI 1 + 2a group exhibited significantly better survival compared to the mALBI 2b + 3 group, with a median OS that was not reached vs 3.0 mo (95%CI: 0.1-6.0, P < 0.001). In a subgroup of patients with CTP A, the mALBI 1 + 2a group also showed significantly longer survival compared to the mALBI 2b + 3 group, with a median OS that was not reached vs 6.0 mo (95%CI: 3.4-8.6, P < 0.001). In the multivariate analysis, both CTP class and mALBI grade were independently associated with survival, with adjusted hazard ratios (95%CI) of 2.63 (1.19-5.78, P = 0.020) and 3.90 (1.71-8.90, P = 0.001), respectively. CONCLUSION: mALBI grades can determine survival of uHCC patients receiving AB treatment, particularly those who have mildly impaired liver function. This highlights the importance of assessing mALBI before initiating AB treatment to optimize therapeutic efficacy in clinical practice.
ABSTRACT
PURPOSE: Detection of hepatocellular carcinoma (HCC) is crucial during surveillance by ultrasound. We previously developed an artificial intelligence (AI) system based on convolutional neural network for detection of focal liver lesions (FLLs) in ultrasound. The primary aim of this study was to evaluate whether the AI system can assist non-expert operators to detect FLLs in real-time, during ultrasound examinations. METHOD: This single-center prospective randomized controlled study evaluated the AI system in assisting non-expert and expert operators. Patients with and without FLLs were enrolled and had ultrasound performed twice, with and without AI assistance. McNemar's test was used to compare paired FLL detection rates and false positives between groups with and without AI assistance. RESULTS: 260 patients with 271 FLLs and 244 patients with 240 FLLs were enrolled into the groups of non-expert and expert operators, respectively. In non-experts, FLL detection rate in the AI assistance group was significantly higher than the no AI assistance group (36.9 % vs 21.4 %, p < 0.001). In experts, FLL detection rates were not significantly different between the groups with and without AI assistance (66.7 % vs 63.3 %, p = 0.32). False positive detection rates in the groups with and without AI assistance were not significantly different in both non-experts (14.2 % vs 9.2 %, p = 0.08) and experts (8.6 % vs 9.0 %, p = 0.85). CONCLUSIONS: The AI system resulted in significant increase in detection of FLLs during ultrasound examinations by non-experts. Our findings may support future use of the AI system in resource-limited settings where ultrasound examinations are performed by non-experts. The study protocol was registered under the Thai Clinical Trial Registry (TCTR20201230003), which is part of the WHO ICTRP Registry Network. The registry can be accessed via the following URL: https://trialsearch.who.int/Trial2.aspx?TrialID=TCTR20201230003.
