Can Machine Learning Predict Favorable Outcome After Radiofrequency Ablation of Hepatocellular Carcinoma?

PURPOSE: The standard practice for limited-stage hepatocellular carcinoma (HCC) is the resection or the use of local ablative techniques, such as radiofrequency ablation (RFA). The outcome after RFA depends on a complex interaction between the patient's general condition, hepatic function, and disease stage. In this study, we aimed to explore using a machine learning model to predict the response. PATIENTS AND METHODS: A retrospective study was conducted for patients with RFA for a localized HCC between 2018 and 2022. The collected clinical, radiologic, and laboratory data were explored using Python and XGBoost. They were split into a training set (70%) and a validation set (30%). The primary end point of this study was to predict the probability of achieving favorable outcomes 12 months after RFA. Favorable outcomes were defined as the patient was alive and HCC was controlled. RESULTS: One hundred and eleven patients were eligible for the study. Males were 78 (70.3%) with a median age of 57 (range of 43-81) years. Favorable outcome was seen in 62 (55.9%) of the patients. The 1-year survival rate and control rate were 94.6%, and 61.3%, respectively. The final model harbored an accuracy and an AUC of 90.6% and 0.95, respectively, for the training set, while they were 78.9% and 0.80, respectively, for the validation set. CONCLUSION: Machine learning can be a predictive tool for the outcome after RFA in patients with HCC. Further validation by a larger study is necessary.

Clinical characteristics, risk factors and diagnostic outcomes of patients presented with indeterminate biliary stricture: A multicenter study.

Background and aim: Indeterminate biliary stricture (IBS) is a frequently encountered clinical problem. In this study, we aimed to highlight the clinical characteristics, risk factors and diagnostic outcomes of patients presented with indeterminate biliary stricture. Method: A Retrospective multicenter study included all patients diagnosed with IBS in the participating centers between 2017 and 2021. Data regarding IBS such as presentations, patient characteristics, diagnostic and therapeutic modalities were collected from the patients' records and then were analyzed. Results: Data of 315 patients with IBS were retrospectively collected from 7 medical centers with mean age: 62.6 ± 11 years, females: 40.3% and smokers: 44.8%. For diagnosing stricture; Magnetic resonance imaging/Magnetic resonance cholangiopancreatography (MRI/MRCP) was the most frequently requested imaging modality in all patients, Contrast enhanced computerized tomography (CECT) in 85% and endoscopic ultrasound (EUS) in 23.8%. Tissue diagnosis of cholangiocarcinoma was achieved in 14% only. The used therapeutic modalities were endoscopic retrograde cholangiopancreatography (ERCP)/stenting in 70.5%, percutaneous trans-hepatic biliary drainage (PTD): 17.8%, EUS guided drainage: 0.3%, and surgical resection in 8%. The most frequent type of strictures was distal stricture in 181 patients, perihilar in 128 and intrahepatic in 6. Distal strictures had significant male predominance, with higher role for EUS for diagnosis and higher role for ERCP/stenting for drainage, while in the perihilar strictures, there was higher role for CECT and MRI/MRCP for diagnosis and more frequent use of PTD for drainage. Conclusion: Indeterminate biliary stricture is a challenging clinical problem with lack of tissue diagnosis in most of cases mandates an urgent consensus diagnostic and treatment guidelines.