Background/Aims: The performance of machine learning (ML) in predicting the outcomes of patients with hepatocellular carcinoma (HCC) remains uncertain. We aimed to develop risk scores using conventional methods and ML to categorize early-stage HCC patients into distinct prognostic groups. Methods: The study retrospectively enrolled 1,411 consecutive treatment-naïve patients with the Barcelona Clinic Liver Cancer (BCLC) stage 0 to A HCC from 2012 to 2021. The patients were randomly divided into a training cohort (n=988) and validation cohort (n=423). Two risk scores (CATS-IF and CATS-INF) were developed to predict overall survival (OS) in the training cohort using the conventional methods (Cox proportional hazards model) and ML-based methods (LASSO Cox regression), respectively. They were then validated and compared in the validation cohort. Results: In the training cohort, factors for the CATS-IF score were selected by the conventional method, including age, curative treatment, single large HCC, serum creatinine and alpha-fetoprotein levels, fibrosis-4 score, lymphocyte-tomonocyte ratio, and albumin-bilirubin grade. The CATS-INF score, determined by ML-based methods, included the above factors and two additional ones (aspartate aminotransferase and prognostic nutritional index). In the validation cohort, both CATS-IF score and CATS-INF score outperformed other modern prognostic scores in predicting OS, with the CATSINF score having the lowest Akaike information criterion value. A calibration plot exhibited good correlation between predicted and observed outcomes for both scores. Conclusions Both the conventional Cox-based CATS-IF score and ML-based CATS-INF score effectively stratified patients with early-stage HCC into distinct prognostic groups, with the CATS-INF score showing slightly superior performance.

INTRODUCTIONWe aimed to determine the prevalence and clinical manifestations of eosinophilic oesophagitis (EoE) in children who presented to a tertiary care hospital in Singapore.

METHODSWe conducted a retrospective review of all oesophageal biopsies taken during oesophagogastroduodenoscopy (OGD) from March 2010 to December 2011. The patients' demographics and clinical characteristics were collected. Biopsies were reviewed by a single pathologist who was blinded to the original reports, using the current consensus criteria for the histological diagnosis of EoE.

RESULTSOf the 88 children who had biopsies during OGD, 4 (4.5%) children (three boys, one girl; three Chinese, one Caucasian) were diagnosed with EoE. Their median age was 9.5 (range 4.0-12.0) years. The main clinical presentations were abdominal pain (in the three older children) and vomiting (in the youngest child). Three children had a history of atopy. Three children were diagnosed with EoE in the original histology reports, while one was diagnosed after the second review following histology demonstrating > 15 eosinophil granulocytes per high power field and microabscess formation. Endoscopy findings revealed oesophagitis in two children, one of whom was already on acid suppression therapy. Although three children were started on acid suppression therapy, they continued to be symptomatic. One child was also treated with swallowed fluticasone and two with food allergen avoidance, resulting in symptom improvement.

CONCLUSIONAlthough EoE is uncommon in Singapore, greater awareness is needed among family physicians and general paediatricians. Paediatric gastroenterologists should alert pathologists when sending biopsy specimens that are suspicious for EoE.