A5060977321- Artificial Intelligence in Healthcare
- Liver Disease Diagnosis and Treatment
- Hepatocellular Carcinoma Treatment and Prognosis
- Radiomics and Machine Learning in Medical Imaging
- Ferroptosis and cancer prognosis
- Systemic Sclerosis and Related Diseases
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Cancer Mechanisms and Therapy
- Hepatitis C virus research
- Colorectal Cancer Treatments and Studies
Catholic University of Korea
2022-2025
St. Vincent's Hospital
2024-2025
Abstract Purpose: Given its heterogeneity and diverse clinical outcomes, precise subclassification of Barcelona Clinic Liver Cancer stage C (BCLC-C) hepatocellular carcinoma (HCC) is required for appropriately determining patient prognosis selecting treatment. Experimental Design: We recruited 2,626 patients with BCLC-C HCC from multiple centers, comprising training/test (n = 1,693) validation cohorts 933). The XGBoost model was chosen maximum performance among the machine learning (ML)...
/Aims: This study aimed to evaluate the performance of Model for End-Stage Liver Disease (MELD) 3.0 predicting mortality and liver-related complications compared with Child-Pugh classification, albumin-bilirubin (ALBI) grade, MELD, MELD sodium (MELDNa) score. We evaluated a multicenter retrospective cohort incorporated patients cirrhosis between 2013 2019. conducted comparisons area under receiver operating characteristic curve (AUROC) MELD3.0 other models 3-month mortality. Additionally, we...
Hepatocellular carcinoma (HCC) is a cytotoxic chemotherapy-resistant tumor and most HCCs arise in background of liver cirrhosis various causes. Although the IMBrave150 trial showed remarkable advancements treatment unresectable HCC with atezolizumab plus bevacizumab (AteBeva), therapeutic outcomes were unsatisfactory more than half patients. Accordingly, many ongoing trials combine conventional modalities new drugs such as immune checkpoint inhibitors for better outcomes, they are expected...
<div>AbstractPurpose:<p>Given its heterogeneity and diverse clinical outcomes, precise subclassification of Barcelona Clinic Liver Cancer stage C (BCLC-C) hepatocellular carcinoma (HCC) is required for appropriately determining patient prognosis selecting treatment.</p>Experimental Design:<p>We recruited 2,626 patients with BCLC-C HCC from multiple centers, comprising training/test (<i>n</i> = 1,693) validation cohorts 933). The XGBoost model was chosen...
<p>Application to the patients with first-line and later-line systemic chemotherapy in propensity-score matched cohort.</p>
<p>A study flow chart presents machine learning modeling and risk stratification.</p>
<p>Kaplan–Meier curves examining the survival differences of three representative modalities in each risk subgroup by CLAM-C.</p>
<p>A KNIME workflow evaluates the performance of each machine learning algorithm using a derivation cohort.</p>
<p>Application to each treatment subgroup in terms of progression-free survival.</p>
<p>Flow chart of the analysis for first-line systemic chemotherapy.</p>
<p>Diagrams presenting the relative feature importance of XGBoost model predicting 1-year survival patients with BCLC-C HCC.</p>
<p>A KNIME workflow presents the backward elimination feature selection.</p>
<p>Kaplan–Meier curves represent the OS according to previously reported subclassifications.</p>
<div>AbstractPurpose:<p>Given its heterogeneity and diverse clinical outcomes, precise subclassification of Barcelona Clinic Liver Cancer stage C (BCLC-C) hepatocellular carcinoma (HCC) is required for appropriately determining patient prognosis selecting treatment.</p>Experimental Design:<p>We recruited 2,626 patients with BCLC-C HCC from multiple centers, comprising training/test (<i>n</i> = 1,693) validation cohorts 933). The XGBoost model was chosen...
<p>A study flow chart presents machine learning modeling and risk stratification.</p>
<p>SHAP values of each clinical parameter predicting 1-year survival using CLAM-C.</p>
<p>Kaplan–Meier curves represent the OS according to previously reported subclassifications.</p>
<p>A KNIME workflow evaluates the performance of each machine learning algorithm using a derivation cohort.</p>