Integrating bioinformatics and machine learning methods to analyze diagnostic biomarkers for HBV-induced hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) is a malignant tumor. It is estimated that approximately 50-80% of HCC cases worldwide are caused by hepatitis b virus (HBV) infection, and other pathogenic factors have been shown to promote the development of HCC when coexisting with HBV. Understanding the molecular mechanisms of HBV-induced hepatocellular carcinoma (HBV-HCC) is crucial for the prevention, diagnosis, and treatment of the disease. In this study, we analyzed the molecular mechanisms of HBV-induced HCC by combining bioinformatics and deep learning methods. Firstly, we collected a gene set related to HBV-HCC from the GEO database, performed differential analysis and WGCNA analysis to identify genes with abnormal expression in tumors and high relevance to tumors. We used three deep learning methods, Lasso, random forest, and SVM, to identify key genes RACGAP1, ECT2, and NDC80. By establishing a diagnostic model, we determined the accuracy of key genes in diagnosing HBV-HCC. In the training set, RACGAP1(AUC:0.976), ECT2(AUC:0.969), and NDC80 (AUC: 0.976) showed high accuracy. They also exhibited good accuracy in the validation set: RACGAP1(AUC:0.878), ECT2(AUC:0.731), and NDC80(AUC:0.915). The key genes were found to be highly expressed in liver cancer tissues compared to normal liver tissues, and survival analysis indicated that high expression of key genes was associated with poor prognosis in liver cancer patients. This suggests a close relationship between key genes RACGAP1, ECT2, and NDC80 and the occurrence and progression of HBV-HCC. Molecular docking results showed that the key genes could spontaneously bind to the anti-hepatocellular carcinoma drugs Lenvatinib, Regorafenib, and Sorafenib with strong binding activity. Therefore, ECT2, NDC80, and RACGAP1 may serve as potential biomarkers for the diagnosis of HBV-HCC and as targets for the development of targeted therapeutic drugs.

Etiology and Outcomes of Patients with Extreme Hyperbilirubinemia in Korea: A Retrospective Cohort Study.

Background/Aim: Extreme hyperbilirubinemia is occasionally observed in intensive care unit (ICU) and non-ICU settings. This study examined the etiologies of extreme hyperbilirubinemia (bilirubin level ≥12 mg/dL) and the factors associated with the 30-day mortality. Methods: This retrospective observational cohort study identified 439 patients with extreme hyperbilirubinemia at the Gyeongsang National University Changwon Hospital between 2016 and 2020. The patients were classified into three groups and 11 diseases according to their etiology. The risk factors associated with 30-day mortality at the baseline were investigated using the Cox proportional hazards model. Results: Of 439 patients with extreme hyperbilirubinemia, 287, 78, and 74 were in the liver cirrhosis/malignancy group, the ischemic injury group, and the benign hepatobiliary-pancreatic etiological group, respectively, with corresponding 30-day mortality rates of 42.9%, 76.9%, and 17.6%. The most common disease leading to hyperbilirubinemia was a pancreatobiliary malignancy (28.7%), followed by liver cirrhosis (17.3%), hepatocellular carcinoma (10.9%), and liver metastases (8.4%). The etiologies of hyperbilirubinemia, obstructive jaundice, infection, albumin level, creatinine level, and prothrombin time-international normalized ratio were independently associated with the 30-day mortality. Conclusions: This study suggests three etiologies of extreme hyperbilirubinemia in the ICU and non-ICU settings. The prognosis of patients with extreme hyperbilirubinemia depends largely on the etiology and the presence of obstructive jaundice.

An efficient DNAzyme-locked leakless enzyme-free amplification system for alpha-foetoprotein detection in liver cancer and breast cancer.

Alpha-foetoprotein (AFP) is taken as a diagnostic tumor marker for the screening and diagnosis of cancer. Nucleic acid-based isothermal amplification strategies are emerging as a potential technology in early screening and clinical diagnosis of AFP. The leakages between hairpins dramatically increase the background and reduce the sensitivity. Thus, it is necessary to develop some strategies to reduce the leakage for isothermal amplification strategies. A DNAzyme-locked leakless enzyme-free amplification system was developed for AFP detection in liver cancer and breast cancer. AFP could open the apt-hairpin and initiate the catalytic hairpin assembly (CHA) reaction to produce a Y-shaped duplex. Two tails of a Y-shaped duplex cleaved the two kinds of leakless hairpins. Then, the third tail of the Y-shaped duplex catalyzed the second CHA between the cleaved leakless hairpins to recover the fluorescent intensity. The limit of detection reached 5 fg/mL by the two levels of signal amplifications. Importantly, the leakless hairpin design effectively reduced leakage between hairpins and weakened the background. In addition, it also showed a great promising potential for AFP detection in early screening and clinical diagnosis.

Developing an advanced diagnostic model for hepatocellular carcinoma through multi-omics integration leveraging diverse cell-death patterns.

Introduction: Hepatocellular carcinoma (HCC), representing more than 80% of primary liver cancer cases, lacks satisfactory etiology and diagnostic methods. This study aimed to elucidate the role of programmed cell death-associated genes (CDRGs) in HCC by constructing a diagnostic model using single-cell RNA sequencing (scRNA-seq) and RNA sequencing (RNA-seq) data. Methods: Six categories of CDRGs, including apoptosis, necroptosis, autophagy, pyroptosis, ferroptosis, and cuproptosis, were collected. RNA-seq data from blood-derived exosomes were sourced from the exoRBase database, RNA-seq data from cancer tissues from the TCGA database, and scRNA-seq data from the GEO database. Subsequently, we intersected the differentially expressed genes (DEGs) of the HCC cohort from exoRBase and TCGA databases with CDRGs, as well as DEGs obtained from single-cell datasets. Candidate biomarker genes were then screened using clinical indicators and a machine learning approach, resulting in the construction of a seven-gene diagnostic model for HCC. Additionally, scRNA-seq and spatial transcriptome sequencing (stRNA-seq) data of HCC from the Mendeley data portal were used to investigate the underlying mechanisms of these seven key genes and their association with immune checkpoint blockade (ICB) therapy. Finally, we validated the expression of key molecules in tissues and blood-derived exosomes through quantitative Polymerase Chain Reaction (qPCR) and immunohistochemistry experiments. Results: Collectively, we obtained a total of 50 samples and 104,288 single cells. Following the meticulous screening, we established a seven-gene diagnostic model for HCC, demonstrating high diagnostic efficacy in both the exoRBase HCC cohort (training set: AUC = 1; testing set: AUC = 0.847) and TCGA HCC cohort (training set: AUC = 1; testing set: AUC = 0.976). Subsequent analysis revealed that HCC cluster 3 exhibited a higher stemness index and could serve as the starting point for the differentiation trajectory of HCC cells, also displaying more abundant interactions with other cell types in the microenvironment. Notably, key genes TRIB3 and NQO1 displayed elevated expression levels in HCC cells. Experimental validation further confirmed their elevated expression in both tumor tissues and blood-derived exosomes of cancer patients. Additionally, stRNA analysis not only substantiated these findings but also suggested that patients with high TRIB3 and NQO1 expression might respond more favorably to ICB therapy. Conclusions: The seven-gene diagnostic model demonstrated remarkable accuracy in HCC screening, with TRIB3 emerging as a promising diagnostic tool and therapeutic target for HCC.

Beyond pixels: Graph filtration learning unveils new dimensions in hepatocellular carcinoma imaging.

This editorial explores the emerging role of Graph Filtration Learning (GFL) in revolutionizing Hepatocellular carcinoma (HCC) imaging analysis. As traditional pixel-based methods reach their limits, GFL offers a novel approach to capture complex topological features in medical images. By representing imaging data as graphs and leveraging persistent homology, GFL unveils new dimensions of information that were previously inaccessible. This paradigm shift holds promise for enhancing HCC diagnosis, treatment planning, and prognostication. We discuss the principles of GFL, its potential applications in HCC imaging, and the challenges in translating this innovative technique into clinical practice.

Tumor detection by analysis of both symmetric- and hemi-methylation of plasma cell-free DNA.

Aberrant DNA methylation patterns have been used for cancer detection. However, DNA hemi-methylation, present at about 10% CpG dinucleotides, has been less well studied. Here we show that a majority of differentially hemi-methylated regions (DHMRs) in liver tumor DNA or plasma cells free (cf) DNA do not overlap with differentially methylated regions (DMRs) of the same samples, indicating that DHMRs could serve as independent biomarkers. Furthermore, we analyzed the cfDNA methylomes of 215 samples from individuals with liver or brain cancer and individuals without cancer (controls), and trained machine learning models using DMRs, DHMRs or both. The models incorporated with both DMRs and DHMRs show a superior performance compared to models trained with DMRs or DHMRs, with AUROC being 0.978, 0.990, and 0.983 in distinguishing control, liver and brain cancer, respectively, in a validation cohort. This study supports the potential of utilizing both DMRs and DHMRs for multi-cancer detection.

Mitotic catastrophe heterogeneity: implications for prognosis and immunotherapy in hepatocellular carcinoma.

Background and aims: The mitotic catastrophe (MC) pathway plays an important role in hepatocellular carcinoma (HCC) progression and tumor microenvironment (TME) regulation. However, the mechanisms linking MC heterogeneity to immune evasion and treatment response remain unclear. Methods: Based on 94 previously published highly correlated genes for MC, HCC patients' data from the Cancer Genome Atlas (TCGA) and changes in immune signatures and prognostic stratification were studied. Time and spatial-specific differences for MCGs were assessed by single-cell RNA sequencing and spatial transcriptome (ST) analysis. Multiple external databases (GEO, ICGC) were employed to construct an MC-related riskscore model. Results: Identification of two MC-related subtypes in HCC patients from TCGA, with clear differences in immune signatures and prognostic risk stratification. Spatial mapping further associates low MC tumor regions with significant immune escape-related signaling. Nomogram combining MC riskscore and traditional indicators was validated great effect for early prediction of HCC patient outcomes. Conclusion: MC heterogeneity enables immune escape and therapy resistance in HCC. The MC gene signature serves as a reliable prognostic indicator for liver cancer. By revealing clear immune and spatial heterogeneity of HCC, our integrated approach provides contextual therapeutic strategies for optimal clinical decision-making.

CDKL3 is a promising biomarker for diagnosis and prognosis prediction in patients with hepatocellular carcinoma.

Cyclin-dependent kinase-like 3 (CDKL3) has been identified as an oncogene in certain types of tumors. Nonetheless, its function in hepatocellular carcinoma (HCC) is poorly understood. In this study, we conducted a comprehensive analysis of CDKL3 based on data from the HCC cohort of The Cancer Genome Atlas (TCGA). Our analysis included gene expression, diagnosis, prognosis, functional enrichment, tumor microenvironment and metabolic characteristics, tumor burden, mRNA expression-based stemness, alternative splicing, and prediction of therapy response. Additionally, we performed a cell counting kit-8 assay, TdT-mediated dUTP nick-end Labeling staining, migration assay, wound healing assay, colony formation assay, and nude mouse experiments to confirm the functional relevance of CDKL3 in HCC. Our findings showed that CDKL3 was significantly upregulated in HCC patients compared to controls. Various bioinformatic analyses suggested that CDKL3 could serve as a potential marker for HCC diagnosis and prognosis. Furthermore, CDKL3 was found to be involved in various mechanisms linked to the development of HCC, including copy number variation, tumor burden, genomic heterogeneity, cancer stemness, and alternative splicing of CDKL3. Notably, CDKL3 was also closely correlated with tumor immune cell infiltration and the expression of immune checkpoint markers. Additionally, CDKL3 was shown to independently function as a risk predictor for overall survival in HCC patients by multivariate Cox regression analysis. Furthermore, the knockdown of CDKL3 significantly inhibited cell proliferation in vitro and in vivo, indicating its role as an oncogene in HCC. Taken together, our findings suggest that CDKL3 shows promise as a biomarker for the detection and treatment outcome prediction of HCC patients.

Dual Enzyme-Locked Activation Reporter for Accurate Liver Cancer Surveillance.

Activatable probes with a higher signal-to-background ratio and accuracy are essential for monitoring liver cancer as well as intraoperative fluorescence navigation. However, the presence of only one biomarker is usually not sufficient to meet the high requirement of a signal-to-background ratio in cancer surveillance, leading to the risk of misdiagnosis. In this work, a dual-locked activation response probe, Si-NTR-LAP, for nitroreductase and leucine aminopeptidase was reported. This dual-locked probe provides better tumor recognition and a higher signal-to-noise ratio than that of single-locked probes (Si-LAP and Si-NTR). In both the subcutaneous tumor model and the more complex orthotopic hepatocellular carcinoma model, the probe was able to identify tumor tissue with high specificity and accurately differentiate the boundaries between tumor tissue and normal tissue. Therefore, the dual-locked probe may provide a new and practical strategy for applying to real patient tumor tissue samples.

Monocyte distribution width as a promising biomarker for differential diagnosis of chronic hepatitis, cirrhosis, and hepatocellular carcinoma.

Objective: We aimed to investigate the association and diagnostic value of monocyte distribution width (MDW) for chronic hepatitis B (CHB), liver cirrhosis (LC), and hepatocellular carcinoma (HCC). Methods: MDW levels were measured in 483 individuals (103 CHB, 77 LC, 153 HCC, and 150 controls). MDW was detected using UniCel Dx900 for specific cell volume parameters and the distribution of cell volumes. Results: Our findings revealed a dynamic upward change in MDW levels across different stages of chronic liver disease, from CHB to LC and HCC. In CHB, MDW levels were highest among HBeAg-positive CHB patients and exhibited a negative correlation with HBV markers while positively correlating with ALT levels. In LC, MDW showed a positive association with the pathological progression of LC, demonstrating consistency with CP scores. MDW proved to be equally effective as traditional detection for diagnosing LC. In HCC, MDW was positively correlated with HCC occurrence and development, with higher levels observed in the high MDW group, which also exhibited elevated AFP levels, MELD scores, and 90-day mortality rates. MDW surpassed predictive models in its effectiveness for diagnosing HCC, as well as CHB and LC, with respective areas under the curve of 0.882, 0.978, and 0.973. Furthermore, MDW emerged as an independent predictor of HCC. Conclusion: MDW holds significant diagnostic efficacy in identifying CHB, LC, and HCC. These findings suggest that MDW could serve as a promising biomarker for predicting the severity of liver diseases and aid in rational clinical treatment strategies.

Hepatocellular carcinoma outcomes and potential implications for surveillance in elderly patients.

International liver societies recommend hepatocellular carcinoma (HCC) surveillance for those at high-risk of developing HCC. While previous studies have shown the benefits of surveillance for middle-aged patients, but its necessity for elderly patients is unclear. This study aimed to assess the benefits of HCC surveillance in the elderly by comparing diagnosis mode of HCC. Consecutive, elderly patients aged 75 years or older who were newly diagnosed with HCC were screened at our institution between January 2009 and December 2021. Patients were grouped into those who were diagnosed with HCC during surveillance (n = 235, surveillance group) and those who were diagnosed with HCC due to symptoms (n = 184, symptomatic group). The study outcome was overall survival. It was compared in the overall cohort and a propensity score (PS)-matched cohort. Early-stage diagnosis was more frequent in the surveillance group than in the symptomatic group (mUICC stage I/II: 72.3% vs. 39.1%, p < 0.001). The overall survival rate was better in the surveillance group than in the symptomatic group (median 4.4 vs. 2.1 years, log-rank p < 0.001). In multivariable-adjusted models, the hazard ratio (HR) of mortality of the surveillance group compared to the symptomatic group was 0.64 (95% confidence interval (CI): 0.47-0.87). However, further adjustment for the tumor stage markedly attenuated this association, which was no longer statistically significant (adjusted HR = 0.75; 95% CI: 0.54-1.02). In the PS-matched cohort analysis, outcomes were similar when the PS matching variables included the tumor stage. In contrast, when PS matching variables did not include the tumor stage, outcomes were better for the surveillance group. The surveillance group of elderly patients showed better survival than the symptomatic group, which was largely explained by earlier tumor stage at diagnosis. This suggests that the overall outcome of elderly HCC patients could be improved by increasing surveillance-detected cases compared to symptom-driven cases.

Myxoinflammatory fibroblastic sarcoma of the liver: Case report and literature review.

RATIONALE: Myxoinflammatory fibroblastic sarcoma (MIFS) is a rare low-grade malignant soft tissue sarcoma that primarily affects the distal extremities in adults, with the highest incidence in patients in their 40s and 50s. It has a high local recurrence rate and a low metastasis rate. Although MIFSs have been documented in other sites, an MIFS in the liver is highly unusual. Herein, we present a case of a patient with hepatic MIFS. PATIENT CONCERNS: The patient was a 58-year-old Chinese man with abdominal pain as the primary symptom. Abdominal computed tomography and magnetic resonance imaging revealed a mass in the right posterior lobe of the liver. The patient underwent surgical excision, and the excised specimen was identified as MIFS. Three years later, the patient returned to our hospital for abdominal pain. Computed tomography and magnetic resonance imaging revealed a mass in liver segments 2/3/4. DIAGNOSIS: Postoperative pathological examination of the tumor revealed the recurrence of MIFS. INTERVENTIONS: The patient underwent surgical resection of the MIFS. OUTCOMES: The patient received multiple pirarubicin-based chemotherapy treatments and an ALK inhibitor (anlotinib) within 6 months after surgery, but the tumor recurred. LESSONS: MIFS can not only occur in the proximal limbs, trunk, head, and neck but can also affect the abdominal organs. Surgical resection remains the primary treatment option for MIFS in the absence of any contraindications. Because the recurrence rate of MIFS is high, meticulous long-term monitoring is required.

Establishment of diagnostic model and identification of diagnostic markers between liver cancer and cirrhosis based on multi-chip and machine learning.

OBJECTIVE: Most cases of hepatocellular carcinoma (HCC) arise as a consequence of cirrhosis. In this study, our objective is to construct a comprehensive diagnostic model that investigates the diagnostic markers distinguishing between cirrhosis and HCC. METHODS: Based on multiple GEO datasets containing cirrhosis and HCC samples, we used lasso regression, random forest (RF)-recursive feature elimination (RFE) and receiver operator characteristic analysis to screen for characteristic genes. Subsequently, we integrated these genes into a multivariable logistic regression model and validated the linear prediction scores in both training and validation cohorts. The ssGSEA algorithm was used to estimate the fraction of infiltrating immune cells in the samples. Finally, molecular typing for patients with cirrhosis was performed using the CCP algorithm. RESULTS: The study identified 137 differentially expressed genes (DEGs) and selected five significant genes (CXCL14, CAP2, FCN2, CCBE1 and UBE2C) to construct a diagnostic model. In both the training and validation cohorts, the model exhibited an area under the curve (AUC) greater than 0.9 and a kappa value of approximately 0.9. Additionally, the calibration curve demonstrated excellent concordance between observed and predicted incidence rates. Comparatively, HCC displayed overall downregulation of infiltrating immune cells compared to cirrhosis. Notably, CCBE1 showed strong correlations with the tumour immune microenvironment as well as genes associated with cell death and cellular ageing processes. Furthermore, cirrhosis subtypes with high linear predictive scores were enriched in multiple cancer-related pathways. CONCLUSION: In conclusion, we successfully identified diagnostic markers distinguishing between cirrhosis and hepatocellular carcinoma and developed a novel diagnostic model for discriminating the two conditions. CCBE1 might exert a pivotal role in regulating the tumour microenvironment, cell death and senescence.

ACG Clinical Guideline: Focal Liver Lesions.

Focal liver lesions (FLLs) have become an increasingly common finding on abdominal imaging, especially asymptomatic and incidental liver lesions. Gastroenterologists and hepatologists often see these patients in consultation and make recommendations for management of multiple types of liver lesions, including hepatocellular adenoma, focal nodular hyperplasia, hemangioma, and hepatic cystic lesions including polycystic liver disease. Malignancy is important to consider in the differential diagnosis of FLLs, and healthcare providers must be familiar with the diagnosis and management of FLLs. This American College of Gastroenterology practice guideline uses the best evidence available to make diagnosis and management recommendations for the most common FLLs.

Misdiagnosis Based on Neoplastic Markers-Extremely High Alpha-Fetoprotein in Patients with Intrahepatic Cholangiocarcinoma with Literature Review of the Published Cases.

Background: Alpha-fetoprotein (AFP) and carbohydrate antigen 19-9 (CA 19-9) are two tumor markers that are widely used in the differential diagnosis in patients with primary liver tumors. Very high levels of AFP are sporadically observed in patients with intrahepatic cholangiocarcinoma (ICC) and may cause an incorrect initial diagnosis of hepatocellular carcinoma (HCC). Methods: Two cases of tumors in cirrhotic livers were described, in which the initial diagnosis, based on very high AFP levels (Patient I: 10,464 ng/mL, Patient II: 2212 ng/mL, reference range: ≤8.04 ng/mL) was HCC. In addition, the PubMed database was searched for cases of ICC with elevated AFP. Discussion: In both individuals, liver cirrhosis was diagnosed, but there was no typical rapid "washout" in the contrast-enhanced computed tomography. Based on the histological assessment of samples obtained in the core biopsies, the initially assumed diagnosis of HCC was changed to ICC in both cases. Only nine cases of patients with ICC and high AFP levels were found in the PubMed database. The AFP levels ranged from slightly elevated to over 16,000 ng/mL. Conclusions: A very high AFP level does not necessarily correlate with the presence of HCC. Therefore, the diagnosis has to be verified histologically, when the radiological imaging is uncertain in patients with liver cirrhosis.

Pink-on-pink: hepatocellular carcinoma metastatic to oncocytic carcinoma of the thyroid.

Hepatocellular carcinoma typically metastasizes within the liver and may involve extrahepatic sites such as the lungs, adrenal glands, and bones at advanced stages. However, hepatocellular carcinoma metastasis to the thyroid is very uncommon and tumor-to-tumor metastasis from a hepatocellular cancer to a thyroid neoplasm is extremely rare. In this report, we present a case of a 70-year-old man with a hepatocellular carcinoma metastasizing to oncocytic thyroid carcinoma, emphasizing the importance of clinical history and of a multidisciplinary approach, as well as the usefulness of site-specific immunohistochemical markers, in diagnosing and managing cases of Rosai's metastasis, especially when donor and recipient neoplasms share similar histologic features.

A paradigm shift in diagnosis and treatment innovation for mucinous cystic neoplasms of the liver.

This study comprehensively explores the clinical characteristics, diagnostic approaches, and treatment methods for liver mucinous cystic neoplasms (MCN). A retrospective analysis was conducted on seven individuals diagnosed with MCN, admitted to the Fifth Medical Center of the PLA General Hospital between October 2016 and May 2023. Preoperative AFP was negative, while CA19-9 was elevated in two cases. Surgical resection was performed for all patients. The patients showed favorable postoperative recovery. Follow-up revealed an excellent overall survival rate, except for one case of invasive carcinoma resulting in tumor recurrence and metastasis 6 months after surgery. MCN poses a diagnostic challenge due to the absence of distinct clinical and radiological features, leading to potential misdiagnosis and inappropriate treatment. Patients with suspected liver cystic diseases should consider the possibility of MCN. Surgical resection has proven to be a practical approach with satisfactory therapeutic outcomes.

Exploring Glypican-3 as a Molecular Target in Hepatocellular Carcinoma: Perspectives on Diagnosis and Precision Immunotherapy Strategies.

Liver cancer, primarily hepatocellular carcinoma (HCC), is the second leading cause of cancer-related deaths globally. It is typically characterized by rapid progression, poor prognosis, and high mortality rates. Given these challenges, the search for molecular targets aiding early diagnosis and targeted therapy remains imperative. Glypican 3 (GPC3), a cell-surface glycoprotein, emerges as a promising candidate for addressing HCC Overexpressed in HCC tissues; GPC3 is a credible immunohistochemical marker for liver cancer diagnosis and a potential marker for liquid biopsy through soluble GPC3 in serum. Various immunotherapies targeting GPC3 have been developed, including vaccines, anti-GPC3 immunotoxins, and chimeric antigen receptor-modified cells. This review comprehensively covers the structure, physicochemical properties, biological functions, and clinical applications of GPC3. It explores diagnostic and treatment strategies centered around GPC3, offering hope for improved early detection and targeted therapies in the challenging landscape of HCC.

Identification and quantification of serum KIN17 protein based on ELISA assay and exploring its clinical diagnostic value in liver cancer.

It has been well-elaborated that KIN17 protein is closely related to the expression, development and prognosis of liver cancer; however, till date, there has been no study about detecting the KIN17 protein in serum, which is important to developing clinical applications. The objective of this work is to detect serum KIN17 protein by the ELISA method and to explore the diagnostic significance of the KIN17 protein in liver cancer. First, we verified the ELISA method for serum KIN17 measurement according to five aspects: accuracy, precision, specificity, stability and detection limit. Results illustrate that the recovery rate of the ELISA method can be controlled between 90% and 110%, the variation coefficient of intra-assay can be controlled within 16%, and the variation coefficient of inter-assay can be controlled within 10%. There is no non-specific reaction with common tumor markers, and the detection limit can reach 0.125 ng mL-1. The results show that the KIN17 protein can be detected by ELISA, and there is a significant rise in KIN17 concentration in a liver cancer group compared with a healthy group, whose average concentrations are 1.730 ng mL-1 and 0.3897 ng mL-1, respectively. On this basis, we hypothesize that the serum KIN17 protein can serve as a potential biomarker of liver cancer and be measurable with the verified ELISA system after specific ultrafiltration and centrifugation, which is of great significance for the diagnosis and treatment of liver cancer.