Machine-Learning-Based Clinical Biomarker Using Cell-Free DNA for Hepatocellular Carcinoma (HCC)

Programmed Death 1 and Cytotoxic T-Lymphocyte-Associated Protein 4 Gene Expression in Peripheral Blood Mononuclear Cells Can Serve as Prognostic Biomarkers for Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is a highly aggressive form of liver cancer with poor prognosis. The lack of reliable biomarkers for early detection and accurate diagnosis and prognosis poses a significant challenge to its effective clinical management. In this study, we investigated the diagnostic and prognostic potential of programmed cell death protein 1 (PD-1) and cytotoxic T-lymphocyte-associated protein 4 (CTLA-4) expression in peripheral blood mononuclear cells (PBMCs) in HCC. PD-1 and CTLA-4 gene expression was analyzed comparatively using PBMCs collected from HCC patients and healthy individuals. The results revealed higher PD-1 gene expression levels in patients with multifocal tumors, lymphatic invasion, or distant metastasis than those in their control counterparts. However, conventional serum biomarkers of liver function do not exhibit similar correlations. In conclusion, PD-1 gene expression is associated with OS and PFS and CTLA-4 gene expression is associated with OS, whereas the serum biomarkers analyzed in this study show no significant correlation with survival in HCC. Hence, PD-1 and CTLA-4 expressed in PBMCs are considered potential prognostic biomarkers for patients with HCC that can facilitate prediction of malignancy, response to currently available HCC treatments, and overall survival.

Value of GPR, APPRI and FIB-4 in the early diagnosis of hepatocellular carcinoma: a prospective cohort study

OBJECTIVE

There is an urgent need for novel biomarkers that are inexpensive, effective and easily accessible to complement the early diagnosis of hepatocellular carcinoma. This study aimed to analyze the relationship between serum gamma-glutamate-transpeptidase to platelet ratio, alkaline phosphatase-to-platelet ratio index, fibrosis index based on four factors and the risk of hepatocellular carcinoma, and to determine the optimal cut-offs for predicting hepatocellular carcinoma.

METHODS

Based on a prospective cohort study, 44 215 participants who were cancer-free at baseline (2011-13) were included in the study. Cox proportional hazard models and receiver operating characteristics curves were used to analyze the diagnostic value and optimal cut-off value of gamma-glutamyl-transpeptidase to platelet ratio, alkaline phosphatase-to-platelet ratio index and fibrosis index based on four factors in predicting hepatocellular carcinoma patients.

RESULTS

Gamma-glutamyl-transpeptidase to platelet ratio, alkaline phosphatase-to-platelet ratio index and fibrosis index based on four factors can be used as early independent predictors of hepatocellular carcinoma risk. The risk of hepatocellular carcinoma in the fourth quantile of gamma-glutamyl-transpeptidase to platelet ratio and alkaline phosphatase-to-platelet ratio index was 4.04 times (hazard ratio = 4.04, 95% confidence interval: 2.09, 7.80) and 2.59 times (hazard ratio = 2.59, 95% confidence interval: 1.45, 4.61), respectively, compared with the first quantile. With fibrosis index based on four factors first quantile as a reference, fibrosis index based on four factors fourth quantile had the highest risk (hazard ratio = 18.58, 95% confidence interval: 7.55, 45.72). Receiver operating characteristic results showed that fibrosis index based on four factors had a stronger ability to predict the risk of hepatocellular carcinoma (area under curve = 0.81, 95% confidence interval: 0.80, 0.81), and similar results were shown for gender stratification. In the total population, the optimal cut-off values of gamma-glutamyl-transpeptidase to platelet ratio, alkaline phosphatase-to-platelet ratio index and fibrosis index based on four factors were 0.208, 0.629 and 1.942, respectively.

CONCLUSIONS

Gamma-glutamyl-transpeptidase to platelet ratio, alkaline phosphatase-to-platelet ratio index and fibrosis index based on four factors were independent predictors of hepatocellular carcinoma risk. Amongst them, fibrosis index based on four factors shows a stronger predictive ability for hepatocellular carcinoma risk, and gamma-glutamyl-transpeptidase to platelet ratio and alkaline phosphatase-to-platelet ratio index can be used as complementary indicators.

Cell-Free DNA: Unveiling the Future of Cancer Diagnostics and Monitoring

As we conclude this Special Issue of 21 published articles dedicated to cell-free DNA (cfDNA) as a prognostic and predictive biomarker in solid cancers, we find ourselves gazing at a vibrant landscape of research on cfDNA [...].

Liquid biopsy for early detection of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is a highly prevalent and lethal cancer globally. Over 90% of HCC cases arise in the context of liver cirrhosis, and the severity of the underlying liver disease or advanced tumor stage at diagnosis significantly limits treatment options. Early diagnosis is crucial, and all guidelines stress the importance of screening protocols for HCC early detection as a public health objective. As serum biomarkers are not optimal for early diagnosis, liquid biopsy has emerged as a promising tool for diagnosis, prognostication, and patients' stratification for personalized therapy in various solid tumors, including HCC. While circulating tumor cells (CTCs) are better suited for personalized therapy and prognosis, cell-free DNA (cfDNA) and extracellular vesicle-based technologies show potential for early diagnosis, HCC screening, and surveillance protocols. Evaluating the added value of liquid biopsy genetic and epigenetic biomarkers for HCC screening is a key goal in translational research. Somatic mutations commonly found in HCC can be investigated in cfDNA and plasma exosomes as genetic biomarkers. Unique methylation patterns in cfDNA or cfDNA fragmentome features have been suggested as innovative tools for early HCC detection. Likewise, extracellular vesicle cargo biomarkers such as miRNAs and long non-coding RNAs may serve as potential biomarkers for early HCC detection. This review will explore recent findings on the utility of liquid biopsy for early HCC diagnosis. Combining liquid biopsy methods with traditional serological biomarkers could improve the overall diagnostic accuracy for early HCC detection.

Advances in novel strategies for isolation, characterization, and analysis of CTCs and ctDNA

Over the past decade, the detection and analysis of liquid biopsy biomarkers such as circulating tumor cells (CTCs) and circulating tumor DNA (ctDNA) have advanced significantly. They have received recognition for their clinical usefulness in detecting cancer at an early stage, monitoring disease, and evaluating treatment response. The emergence of liquid biopsy has been a helpful development, as it offers a minimally invasive, rapid, real-time monitoring, and possible alternative to traditional tissue biopsies. In resource-limited settings, the ideal platform for liquid biopsy should not only extract more CTCs or ctDNA from a minimal sample volume but also accurately represent the molecular heterogeneity of the patient's disease. This review covers novel strategies and advancements in CTC and ctDNA-based liquid biopsy platforms, including microfluidic applications and comprehensive analysis of molecular complexity. We discuss these systems' operational principles and performance efficiencies, as well as future opportunities and challenges for their implementation in clinical settings. In addition, we emphasize the importance of integrated platforms that incorporate machine learning and artificial intelligence in accurate liquid biopsy detection systems, which can greatly improve cancer management and enable precision diagnostics.

The Role of Artificial Intelligence in the Detection and Implementation of Biomarkers for Hepatocellular Carcinoma: Outlook and Opportunities

Liver cancer is a leading cause of cancer-related death worldwide, and its early detection and treatment are crucial for improving morbidity and mortality. Biomarkers have the potential to facilitate the early diagnosis and management of liver cancer, but identifying and implementing effective biomarkers remains a major challenge. In recent years, artificial intelligence has emerged as a promising tool in the cancer sphere, and recent literature suggests that it is very promising in facilitating biomarker use in liver cancer. This review provides an overview of the status of AI-based biomarker research in liver cancer, with a focus on the detection and implementation of biomarkers for risk prediction, diagnosis, staging, prognostication, prediction of treatment response, and recurrence of liver cancers.

Serological indices and ultrasound variables in predicting the staging of hepatitis B liver fibrosis: A comparative study based on random forest algorithm and traditional methods

Objective

To compare the diagnostic efficacy of serological indices and ultrasound (US) variables in hepatitis B virus (HBV) liver fibrosis staging using random forest algorithm (RFA) and traditional methods.

Methods

The demographic and serological indices and US variables of patients with HBV liver fibrosis were retrospectively collected and divided into serology group, US group, and serology + US group according to the research content. RFA was used for training and validation. The diagnostic efficacy was compared to logistic regression analysis (LRA) and APRI and FIB-4 indices.

Results

For the serology group, the diagnostic performance of RFA was significantly higher than that of APRI and FIB-4 indices. The diagnostic accuracy of RFA in the four classifications (S0S1/S2/S3/S4) of the hepatic fibrosis stage was 79.17%. The diagnostic accuracy for significant fibrosis (≥S2), advanced fibrosis (≥S3), and cirrhosis (S4) was 87.99%, 90.69%, and 92.40%, respectively. The area under the curve (AUC) values were 0.945, 0.959, and 0.951, respectively. For the US group, there was no significant difference in diagnostic performance between RFA and LRA. The diagnostic performance of RFA in the serology + US group was significantly better than that of LRA. The diagnostic accuracy of the four classifications (S0S1/S2/S3/S4) of the hepatic fibrosis stage was 77.21%. The diagnostic accuracy for significant fibrosis (≥S2), advanced fibrosis (≥S3), and cirrhosis (S4) was 87.50%, 90.93%, and 93.38%, respectively. The AUC values were 0.948, 0.959, and 0.962, respectively.

Conclusion

RFA can significantly improve the diagnostic performance of HBV liver fibrosis staging. RFA based on serological indices has a good ability to predict liver fibrosis staging. RFA can help clinicians accurately judge liver fibrosis staging and reduce unnecessary biopsies.

Screening of Hub Genes in Hepatocellular Carcinoma Based on Network Analysis and Machine Learning

Hepatocellular carcinoma (LIHC) is the fifth common cancer worldwide, and it requires effective diagnosis and treatment to prevent aggressive metastasis. The purpose of this study was to construct a machine learning-based diagnostic model for the diagnosis of liver cancer. Using weighted correlation network analysis (WGCNA), univariate analysis, and Lasso-Cox regression analysis, protein-protein interactions network analysis is used to construct gene networks from transcriptome data of hepatocellular carcinoma patients and find hub genes for machine learning. The five models, including gradient boosting, random forest, support vector machine, logistic regression, and integrated learning, were to identify a multigene prediction model of patients. Immunological assessment, TP53 gene mutation and promoter methylation level analysis, and KEGG pathway analysis were performed on these groups. Potential drug molecular targets for the corresponding hepatocellular carcinomas were obtained by molecular docking for analysis, resulting in the screening of 2 modules that may be relevant to the survival of hepatocellular carcinoma patients, and the construction of 5 diagnostic models and multiple interaction networks. The modes of action of drug-molecule interactions that may be effective against hepatocellular carcinoma core genes CCNA2, CCNB1, and CDK1 were investigated. This study is expected to provide research ideas for early diagnosis of hepatocellular carcinoma.

Current and Future Perspectives of Cell-Free DNA in Liquid Biopsy

A liquid biopsy is a minimally invasive or non-invasive method to analyze a range of tumor material in blood or other body fluids, including circulating tumor cells (CTCs), cell-free DNA (cfDNA), messenger RNA (mRNA), microRNA (miRNA), and exosomes, which is a very promising technology. Among these cancer biomarkers, plasma cfDNA is the most widely used in clinical practice. Compared with a tissue biopsy of traditional cancer diagnosis, in assessing tumor heterogeneity, a liquid biopsy is more reliable because all tumor sites release cfDNA into the blood. Therefore, a cfDNA liquid biopsy is less invasive and comprehensive. Moreover, the development of next-generation sequencing technology makes cfDNA sequencing more sensitive than a tissue biopsy, with higher clinical applicability and wider application. In this publication, we aim to review the latest perspectives of cfDNA liquid biopsy clinical significance and application in cancer diagnosis, treatment, and prognosis. We introduce the sequencing techniques and challenges of cfDNA detection, analysis, and clinical applications, and discuss future research directions.

Bimodal liquid biopsy for cancer immunotherapy based on peptide engineering and nanoscale analysis

Despite its high potential, PD-L1 expressed by tumors has not been successfully utilized as a biomarker for estimating treatment responses to immunotherapy. Circulating tumor cells (CTCs) and tumor-derived exosomes that express PD-L1 can potentially be used as biomarkers; however, currently available assays lack clinically significant sensitivity and specificity. Here, a novel peptide-based capture surface is developed to effectively isolate PD-L1-expressing CTCs and exosomes from human blood. For the effective targeting of PD-L1, this study integrates peptide engineering strategies to enhance the binding strength and specificity of a β-hairpin peptide derived from PD-1 (pPD-1). Specifically, this study examines the effect of poly(ethylene glycol) spacers, the secondary peptide structure, and modification of peptide sequences (e.g., removal of biologically redundant amino acid residues) on capture efficiency. The optimized pPD-1 configuration captures PD-L1-expressing tumor cells and tumor-derived exosomes with 1.5-fold (p = 0.016) and 1.2-fold (p = 0.037) higher efficiencies, respectively, than their whole antibody counterpart (aPD-L1). This enhanced efficiency is translated into more clinically significant detection of CTCs (1.9-fold increase; p = 0.035) and exosomes (1.5-fold increase; p = 0.047) from patients' baseline samples, demonstrating stronger correlation with patients' treatment responses. Additionally, we confirmed that the clinical accuracy of our system can be further improved by co-analyzing the two biomarkers (bimodal CTC/exosome analysis). These data demonstrate that pPD-1-based capture is a promising approach for capturing PD-L1-expressing CTCs and exosomes, which can be used as a reliable biomarker for cancer immunotherapy.