Identification of New Biomarker for Prediction of Hepatocellular Carcinoma Development in Early-Stage Cirrhosis Patients

Revisiting artificial intelligence diagnosis of hepatocellular carcinoma with DIKWH framework

Hepatocellular carcinoma (HCC) is the most common type of liver cancer with a high morbidity and fatality rate. Traditional diagnostic methods for HCC are primarily based on clinical presentation, imaging features, and histopathology. With the rapid development of artificial intelligence (AI), which is increasingly used in the diagnosis, treatment, and prognosis prediction of HCC, an automated approach to HCC status classification is promising. AI integrates labeled clinical data, trains on new data of the same type, and performs interpretation tasks. Several studies have shown that AI techniques can help clinicians and radiologists be more efficient and reduce the misdiagnosis rate. However, the coverage of AI technologies leads to difficulty in which the type of AI technology is preferred to choose for a given problem and situation. Solving this concern, it can significantly reduce the time required to determine the required healthcare approach and provide more precise and personalized solutions for different problems. In our review of research work, we summarize existing research works, compare and classify the main results of these according to the specified data, information, knowledge, wisdom (DIKW) framework.

Classification and survival prediction in early-stage cirrhosis by gene expression profiling

Liver cirrhosis has been increasingly diagnosed at an early stage owing to the non-invasive diagnostic techniques. However, it is difficult to identify patients at high risk of disease progression. Screening cirrhotic patients with poor prognosis who are most in need of surveillance is still challenging. Gene expression data GSE15654 and GSE14520 were downloaded for performing unsupervised clustering analysis. The prognostic differences between the different clusters were explored by Cox regression. Integrative analysis of gene expression signature, immune cell enrichments and clinical characterization was performed for different clusters. Two distinctive subclasses were identified in HCV-related GSE15654, and Kaplan-Meier analysis indicated that subtype 2 had lower survival rates than subtype 1 (p = 0.0399). Further analysis revealed subtype 2 had a higher density of follicular T helper cells, resting natural killer cells and M0, M2 macrophages while subtype 1 with a higher fraction of naive B cells, memory B cells, resting memory CD 4 T cells, activated natural killer cells and monocytes. 226 differentially expressed genes were identified between the two subtypes, and Reactome analysis showed the mainly enriched pathways were biological oxidations and fatty acid metabolism. Five hub genes (AKT1, RPS16, CDC42, CCND1 and PCBP2) and three significant modules were extracted from the PPI network. The results were validated in HBV-related GSE14520 cohort. We identified two subtypes of patients with different prognosis for hepatitis C-related early-stage liver cirrhosis. Bioinformatics analysis of the gene expression and immune cell profile may provide fresh insight into understanding the prognosis difference.