Statin, aspirin and metformin use and risk of hepatocellular carcinoma related outcomes following liver transplantation: A retrospective study

BACKGROUND Liver transplantation(LT)is a potentially curative therapy for patients with hepatocellular carcinoma(HCC).HCC-recurrence following LT is associated with reduced survival.There is increasing interest in chemoprophylaxis to improve HCC-related outcomes post-LT.AIM To investigate whether there is any benefit for the use of drugs with proposed chemoprophylactic properties against HCC,and patient outcomes following LT.METHODS This was a retrospective study of adult patients who received Deceased Donor LT for HCC from 2005-2022,from a single Australian centre.Drug use was defined as statin,aspirin or metformin therapy for≥29 days,within 24 months post-LT.A cox proportional-hazards model with time-dependent covariates was used for survival analysis.Outcome measures were the composite-endpoint of HCC-recurrence and all-cause mortality,HCC-recurrence and HCC-related mortality.Sensitivity analysis was performed to account for immortality time bias and statin dosing.RESULTS Three hundred and five patients were included in this study,with 253(82.95%)males with a median age of 58.90 years.Aetiologies of liver disease were 150(49.18%)hepatitis C,73(23.93%)hepatitis B(HBV)and 33(10.82%)non-alcoholic fatty liver disease(NAFLD).56(18.36%)took statins,51(16.72%)aspirin and 50(16.39%)metformin.During a median follow-up time of 59.90 months,34(11.15%)developed HCC-recurrence,48(15.74%)died,17(5.57%)from HCC-related mortality.Statin,aspirin or metformin use was not associated with statistically significant differences in the composite endpoint of HCC-recurrence or all-cause mortality[hazard ratio(HR):1.16,95%CI:0.58-2.30;HR:1.21,95%CI:0.28-5.27;HR:0.61,95%CI:0.27-1.36],HCC-recurrence(HR:0.52,95%CI:0.20-1.35;HR:0.51,95%CI:0.14-1.93;HR 1.00,95%CI:0.37-2.72),or HCC-related mortality(HR:0.32,95%CI:0.033-3.09;HR:0.71,95%CI:0.14-3.73;HR:1.57,95%CI:0.61-4.04)respectively.Statin dosing was not associated with statist-ically significant differences in HCC-related outcomes.CONCLUSION Statin,metformin or aspirin use was not associated with improved HCC-related outcomes post-LT,in a largely historical cohort of Australian patients with a low proportion of NAFLD.Further prospective,multicentre studies are required to clarify any potential benefit of these drugs to improve HCC-related outcomes.

Deep learning vs conventional learning algorithms for clinical prediction in Crohn's disease: A proof-of-concept study

BACKGROUND Traditional methods of developing predictive models in inflammatory bowel diseases(IBD)rely on using statistical regression approaches to deriving clinical scores such as the Crohn's disease(CD)activity index.However,traditional approaches are unable to take advantage of more complex data structures such as repeated measurements.Deep learning methods have the potential ability to automatically find and learn complex,hidden relationships between predictive markers and outcomes,but their application to clinical prediction in CD and IBD has not been explored previously.AIM To determine and compare the utility of deep learning with conventional algorithms in predicting response to anti-tumor necrosis factor(anti-TNF)therapy in CD.METHODS This was a retrospective single-center cohort study of all CD patients who commenced anti-TNF therapy(either adalimumab or infliximab)from January 1,2010 to December 31,2015.Remission was defined as a C-reactive protein(CRP)<5 mg/L at 12 mo after anti-TNF commencement.Three supervised learning algorithms were compared:(1)A conventional statistical learning algorithm using multivariable logistic regression on baseline data only;(2)A deep learning algorithm using a feed-forward artificial neural network on baseline data only;and(3)A deep learning algorithm using a recurrent neural network on repeated data.Predictive performance was assessed using area under the receiver operator characteristic curve(AUC)after 10×repeated 5-fold cross-validation.RESULTS A total of 146 patients were included(median age 36 years,48%male).Concomitant therapy at anti-TNF commencement included thiopurines(68%),methotrexate(18%),corticosteroids(44%)and aminosalicylates(33%).After 12 mo,64%had CRP<5 mg/L.The conventional learning algorithm selected the following baseline variables for the predictive model:Complex disease behavior,albumin,monocytes,lymphocytes,mean corpuscular hemoglobin concentration and gamma-glutamyl transferase,and had a cross-validated AUC of 0.659,95%confidence interval(CI):0.562-0.756.A feed-forward artificial neural network using only baseline data demonstrated an AUC of 0.710(95%CI:0.622-0.799;P=0.25 vs conventional).A recurrent neural network using repeated biomarker measurements demonstrated significantly higher AUC compared to the conventional algorithm(0.754,95%CI:0.674-0.834;P=0.036).CONCLUSION Deep learning methods are feasible and have the potential for stronger predictive performance compared to conventional model building methods when applied to predicting remission after anti-TNF therapy in CD.