LRFNet: A deep learning model for the assessment of liver reserve function based on Child-Pugh score and CT image

The ARH score, a practical guide to decision-making for retreatment with hepatic arterial infusion chemotherapy in hepatocellular carcinoma patients

BACKGROUND

Hepatic arterial infusionchemotherapy (HAIC) is a promising option for large unresectable hepatocellular carcinoma (HCC). Identifying patients who could benefit from continuous HAIC remains a challenge. We aimed to establish an objective model to guide the decision for retreatment with HAIC.

METHODS

Between 2015 and 2020, the data of patients with large unresectable HCC without macrovascular invasion or extrahepatic spread undergoing multiple HAIC cycles from 3 different centers were retrieved. We investigated the basic tumor parameters and the effect of HAIC on liver function and tumor response, and their impact on overall survival (OS). A point score (ARH, Assessment for Retreatment with HAIC) was built by using a stepwise Cox regression model in the training cohort (n = 112) and was validated in an independent validation cohort (n = 71).

RESULTS

The high α-fetoprotein before the second cycle of HAIC, an increase in Child-Pugh score, and undesirable radiologic tumor responses remained independent negative prognostic factors and were used to create the ARH score. The prognosis of HCC patients deteriorated significantly with the increase in ARH score. The median OS of patients with ARH score 0-2 points and ≥ 2.5 points were 19.37 months and 11.60 months (P < 0.001). All of these results had been confirmed in the external validation cohort and demonstrated significance across multiple subgroups.

CONCLUSIONS

The ARH score makes an excellent prediction of the prognosis of HCC patients who received retreatment of HAIC. Patients with an ARH score ≥ 2.5 prior to the second cycle of HAIC may not profit from further sessions.

Risk evaluation of ampicillin/sulbactam-induced liver injury based on albumin-bilirubin score

BACKGROUND

Drug-induced liver injury (DILI) is an adverse reaction caused by ampicillin/sulbactam (ABPC/SBT). The albumin-bilirubin (ALBI) score is an index of hepatic functional reserve. However, the relationship between ABPC/SBT-induced DILI and ALBI score remains unknown; therefore, we aimed to elucidate the risk of ABPC/SBT-induced DILI based on the ALBI score.

METHODS

This was a single-center, retrospective, case-control study using electronic medical records. A total of 380 patients were enrolled in the present study, and the primary outcome was ABPC/SBT-induced DILI. The ALBI score was calculated using serum albumin and total bilirubin levels. In addition, we performed COX regression analysis using age ≥75 years, dose ≥9 g/day, alanine aminotransferase (ALT) ≥21 IU/L, and ALBI score ≥-2.00 as covariates. We also performed 1:1 propensity score matching between non-DILI and DILI groups.

RESULTS

The incidence of DILI was 9.5% (36/380). According to COX regression analysis, the adjusted hazard ratio for ABPC/SBT-induced DILI with an ALBI score ≥-2.00 was 2.55 (95% confidence interval: 1.256-5.191, P = 0.010), suggesting that patients with baseline ALBI score ≥-2.00 may be at high risk for ABPC/SBT-induced DILI. However, significant differences were not observed in cumulative risk for DILI between non-DILI and DILI patients regarding an ALBI score ≥-2.00 after propensity score matching (P = 0.146).

CONCLUSION

These findings suggest that ALBI score may be a simple and potentially useful index for predicting ABPC/SBT-induced DILI. In patients with an ALBI score ≥-2.00, frequent liver function monitoring should be considered to prevent ABPC/SBT-induced DILI.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.