-
Frontiers in Artificial Intelligence 2023Hepatocellular carcinoma is a malignant neoplasm of the liver and a leading cause of cancer-related deaths worldwide. The multimodal data combines several modalities,...
BACKGROUND
Hepatocellular carcinoma is a malignant neoplasm of the liver and a leading cause of cancer-related deaths worldwide. The multimodal data combines several modalities, such as medical images, clinical parameters, and electronic health record (EHR) reports, from diverse sources to accomplish the diagnosis of liver cancer. The introduction of deep learning models with multimodal data can enhance the diagnosis and improve physicians' decision-making for cancer patients.
OBJECTIVE
This scoping review explores the use of multimodal deep learning techniques (i.e., combining medical images and EHR data) in diagnosing and prognosis of hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA).
METHODOLOGY
A comprehensive literature search was conducted in six databases along with forward and backward references list checking of the included studies. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping review guidelines were followed for the study selection process. The data was extracted and synthesized from the included studies through thematic analysis.
RESULTS
Ten studies were included in this review. These studies utilized multimodal deep learning to predict and diagnose hepatocellular carcinoma (HCC), but no studies examined cholangiocarcinoma (CCA). Four imaging modalities (CT, MRI, WSI, and DSA) and 51 unique EHR records (clinical parameters and biomarkers) were used in these studies. The most frequently used medical imaging modalities were CT scans followed by MRI, whereas the most common EHR parameters used were age, gender, alpha-fetoprotein AFP, albumin, coagulation factors, and bilirubin. Ten unique deep-learning techniques were applied to both EHR modalities and imaging modalities for two main purposes, prediction and diagnosis.
CONCLUSION
The use of multimodal data and deep learning techniques can help in the diagnosis and prediction of HCC. However, there is a limited number of works and available datasets for liver cancer, thus limiting the overall advancements of AI for liver cancer applications. Hence, more research should be undertaken to explore further the potential of multimodal deep learning in liver cancer applications.
PubMed: 37965284
DOI: 10.3389/frai.2023.1247195 -
Expert Review of Gastroenterology &... 2023The incidence of nonalcoholic fatty liver disease (NAFLD)-related hepatocellular carcinoma (HCC) is increasing globally. We aimed to assess the performance of... (Meta-Analysis)
Meta-Analysis Review
INTRODUCTION
The incidence of nonalcoholic fatty liver disease (NAFLD)-related hepatocellular carcinoma (HCC) is increasing globally. We aimed to assess the performance of alpha-fetoprotein (AFP), AFP-L3, des-gamma-carboxy prothrombin (DCP), and GALAD score in detecting NAFLD-related HCC.
METHODS
We searched the relevant literature in PubMed, Embase and Cochrane. Conventional and network meta-analyses were performed for sensitivity, specificity, Youden index (YI), and the area under the summary receiver operator characteristic curve (AUC).
RESULTS
Fifteen studies involving 2031 NAFLD participants were included in this meta-analysis. When detecting early-stage NAFLD-related HCC, GALAD score and DCP process excellent performance. The sensitivity and AUC of DCP (0.60, 0.74, respectively) were higher than AFP (0.34, 0.59, respectively). The network meta-analysis showed that DCP and GALAD score had similar performance. In detecting all-stage NAFLD-related HCC, GALAD score (sensitivity = 0.87; YI = 0.77) performed better than AFP (sensitivity = 0.56; YI = 0.50), AFP-L3 (sensitivity = 0.39; YI = 0.36) and DCP (sensitivity = 0.73; YI = 0.62). Network meta-analysis obtained consistent results with conventional meta-analysis.
CONCLUSIONS
Due to the lower cost-effectiveness, DCP was more suitable for detecting early NAFLD-related HCC. AFP could be used in detecting all-stage NAFLD-related HCC.
Topics: Humans; Carcinoma, Hepatocellular; alpha-Fetoproteins; Network Meta-Analysis; Non-alcoholic Fatty Liver Disease; Liver Neoplasms; Protein Precursors; Prothrombin; Biomarkers; Biomarkers, Tumor
PubMed: 37929312
DOI: 10.1080/17474124.2023.2279175 -
Updates in Surgery Dec 2023Anal fistula (AF) is a common disease with high prevalence and surgical operations are effective treatments in clinical work. There exist many well-known surgical... (Meta-Analysis)
Meta-Analysis Review
Anal fistula (AF) is a common disease with high prevalence and surgical operations are effective treatments in clinical work. There exist many well-known surgical techniques treating complex anal fistula (CAF), however, none is ideal. To compare the superiority of Anal fistula plug (AFP) and Endoanal advancement flap repair (EAFR) for complex anal fistula. We searched worldwide databases including Pubmed, Embase, Cochrane Library, Web of Science, CNKI, WanFang, VIP, and SinoMed from their inception to March 2023. Studies comparing the outcomes of AFP and EAFR were included according to the PICO principles. The indicators of the healing rate, recurrence rate, wound infection rate, and complication rate, et al. were extracted and compared between different surgical methods. 5 RCTS and 7 non-RCTs were included in the meta-analysis with a total of 847 patients (341 patients conducted with AFP and 506 patients with EAFR). By combining the total effect of the 12 articles, we found that there was a statistical difference reporting the healing rate of AFP 48.3% and EAFR 64.4% treating the CAF (OR 0.68, 95% CI 0.30,1.55, P = 0.03), and EAFR has a better healing rate. However, there was no significant difference in terms of the recurrence rate (OR 1.68, 95% CI 0.80,3.54, P = 0.17), the wound infection rate (OR 1.82, 95% CI 0.95,3.52, P = 0.07), and the complication rate (OR 1.06, 95% CI 0.70,1.61, P = 0.77) either in the 12 articles or in the subgroup. The meta-analysis indicated that the EAFR was superior to AFP in terms of the healing rate treating the CAF, however, there were no significant differences between the two groups when it came to the recurrence rate, the wound infection rate, and the complication rate. EAFR might be one initial treatment for the complex cryptoglandular anal fistulas compared with AFP.
Topics: Humans; alpha-Fetoproteins; Rectal Fistula; Treatment Outcome; Surgical Flaps; Fecal Incontinence; Wound Infection; Anal Canal
PubMed: 37882975
DOI: 10.1007/s13304-023-01674-6 -
Expert Review of Molecular Diagnostics 2023Early and non-invasive detection of hepatocellular carcinoma (HCC), which is usually asymptomatic, can improve overall survival outcomes. The objective of this... (Meta-Analysis)
Meta-Analysis Review
INTRODUCTION
Early and non-invasive detection of hepatocellular carcinoma (HCC), which is usually asymptomatic, can improve overall survival outcomes. The objective of this systematic review and meta-analysis was to evaluate the diagnostic accuracy of serum-derived exosomes for diagnosing HCC.
METHODS
PubMed, Web of Science, and Scopus databases were searched for relevant studies up to April 2023. The quality of included studies was assessed using the QUADAS-2 checklist, and data were extracted. Statistical analysis was performed on 18 studies from 3,993 records, and a diagnostic meta-analysis was conducted. Biomarkers were categorized into four groups based on their type (exosomal miRNAs, exosomal RNAs, alpha-fetoprotein (AFP), and exosomal RNAs+AFP panel), and a meta-analysis was conducted for each category separately.
RESULTS
The highest pooled sensitivity was 0.86 for exosomal miRNAs, and exosomal RNAs+AFP had the highest pooled specificity; (0.89). Furthermore, exosomal RNAs+AFP had the highest pooled positive likelihood ratio; (7.55), the highest pooled diagnostic odds ratio (35.96) and the highest pooled area under the curve (0.93). Exosomal miRNAs had the lowest pooled negative likelihood ratio; (0.17).
CONCLUSIONS
The diagnostic accuracy of exosomal biomarkers is superior to that of AFP, and combining the two in a panel yields the better results.
Topics: Humans; Carcinoma, Hepatocellular; alpha-Fetoproteins; Liver Neoplasms; Exosomes; Biomarkers; MicroRNAs; Biomarkers, Tumor
PubMed: 37715364
DOI: 10.1080/14737159.2023.2260306 -
Journal of Ethnopharmacology Jan 2024Transcatheter arterial chemoembolization (TACE) is recommended as the first-line therapy for unresected primary liver cancer (PLC), but only partial patients could... (Meta-Analysis)
Meta-Analysis
ETHNOPHARMACOLOGICAL RELEVANCE
Transcatheter arterial chemoembolization (TACE) is recommended as the first-line therapy for unresected primary liver cancer (PLC), but only partial patients could benefit from TACE due to the serious adverse reactions. Clearing heat and resolving toxin (CHRT), one of most critical traditional Chinese medicine (TCM) therapeutic principles, has been widely used in the treatment of PLC patients especially after TACE. However, there is no enough clinical evidence to confirm the efficacy and safety of the combined therapy.
AIM OF THE STUDY
To comprehensively evaluate the efficacy and safety of the combined CHRT-CHF with TACE in the treatment of PLC.
MATERIALS AND METHODS
7 databases were searched from their inception until February 1, 2023. The primary outcomes included survival rate (1-, 2-year), objective response rate (ORR) and disease control rate (DCR), liver function indicators (AST, ALT), adverse reactions including fever, upper digestive tract side and myelosuppression, AFP were selected as the secondary outcomes. RevMan5.4 software was used to evaluate the quality of included studies; meta-analysis, subgroup analysis, meta-regression analysis, publication bias and trial sequential analyses (TSA) was conducted by Stata software 12.0.
RESULTS
There were 40 RCTs involving 3649 patients. Patients treated with TACE plus CHRT-CHF showed significantly better 1-, 2-year survival (respectively: OR, 2.23 [1.67-2.97]; OR, 2.13 [1.56-2.92]), ORR (OR, 2.14 [1.82-2.52]), DCR (OR, 2.13 [1.73-2.62]) compared with TACE alone. There was a decreased incidence of aspartate transaminase (AST), alanine transaminase (ALT), alpha-fetoprotein (AFP) and postembolization syndrome (PES) in patients receiving the combined TACE with CHRT-CHF compared with TACE alone. Subgroup analysis found that lower proportion (20-30%) of CHRT-CHF significantly enhanced survival rate and DCR, higher proportion (≥40%) of CHRT-CHF reduced PES after TACE treatment.
CONCLUSION
The efficacy and safety of the combined CHRT-CHF with TACE were validated in this meta-analysis, the optimal proportion of CHRT-CHF in enhancing the efficacy may be 20-30%; Additionally, higher proportion (≥40%) of CHRT-CHF appears to reduce PES after TACE treatment. The potential role of combined relative proportion of CHRT-CHF with TACE should be emphasized in clinic.
Topics: Humans; Carcinoma, Hepatocellular; Liver Neoplasms; alpha-Fetoproteins; Chemoembolization, Therapeutic; Hot Temperature; Treatment Outcome
PubMed: 37625603
DOI: 10.1016/j.jep.2023.117072 -
Journal of Clinical Medicine Research Jul 2023Protein induced by vitamin K absence or antagonist-II (PIVKA-II) and α-fetoprotein (AFP) are promising tumor markers for the diagnosis of hepatocellular carcinoma...
BACKGROUND
Protein induced by vitamin K absence or antagonist-II (PIVKA-II) and α-fetoprotein (AFP) are promising tumor markers for the diagnosis of hepatocellular carcinoma (HCC). Yet, their diagnostic performance differs throughout HCC investigations. The aim of this meta-analysis was to assess the effectiveness of PIVKA-II and AFP in the diagnosis of HCC.
METHODS
A systematic literature search was performed to identify relevant studies from eight databases, which were published up to February 2023, in order to compare the diagnostic performance of PIVKA-II and AFP for HCC. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic (SROC) curve was performed to assess the diagnostic accuracy of each biomarker.
RESULTS
Fifty-three studies were identified. The pooled sensitivity (95% confidence interval (CI)) of PIVKA-II and AFP was 0.71 (0.70 - 0.72) and 0.64 (0.63 - 0.65), respectively in diagnosis of HCC, and the corresponding pooled specificity (95% CI) was 0.90 (0.89 - 0.90) and 0.87 (0.87 - 0.88), respectively. The area under the ROC curve (AUC) of PIVKA-II and AFP was 0.89 (0.88 - 0.90) and 0.78 (0.77 - 0.79), respectively. Subgroup analysis demonstrated that PIVKA-II presented higher AUC values compared to AFP in terms of ethnic group (African, European, Asian, and American patients), etiology (mixed-type HCC, hepatitis C virus (HCV)-related, and hepatitis B virus (HBV)-related) and sample size of cases (≤ 100 and > 100).
CONCLUSION
This study reveals that PIVKA-II is a promising biomarker for identifying and tracking HCC, exhibiting greater accuracy than AFP. Our findings indicate that PIVKA-II outperforms AFP in detecting HCC across diverse racial groups and sample sizes, as well as in cases of HBV-related, HCV-related, or mixed-etiology HCC.
PubMed: 37575350
DOI: 10.14740/jocmr4951 -
Heliyon Aug 2023Traditional Chinese medicine and radiofrequency ablation are becoming increasingly important in the treatment of primary liver cancer. However, the clinical outcome of...
BACKGROUND & AIMS
Traditional Chinese medicine and radiofrequency ablation are becoming increasingly important in the treatment of primary liver cancer. However, the clinical outcome of traditional Chinese medicine plus radiofrequency ablation is contentious. This study aimed to conduct a meta-analysis of randomized controlled clinical trials to address this gap.
METHODS
Short-term efficacy, alpha-fetoprotein level, immune function, liver function, and quality of life outcomes in patients with primary liver cancer treated with Chinese herbal medicine adjuvant radiofrequency ablation were systematically reviewed.
RESULTS
Eighteen randomized controlled clinical trials with 1488 patients with primary liver cancer were included. The combination treatment significantly increased the objective remission rate and quality of patient survival compared to the control group. Combination treatment significantly improved immunity and liver function factors, including CD3, CD4, CD4/CD8, alanine aminotransferase, aspartate aminotransferase, total bilirubin, and albumin levels. However, there were no statistical differences in CD8 levels across treatments. Trial sequential analysis showed that the cumulative Z-curve of the Objective response rate crossed the conventional and test sequence monitoring boundaries; however, it did not cross the required information size line.
CONCLUSIONS
Traditional Chinese medicine combined with radiofrequency ablation for primary liver cancer can effectively reduce alpha-fetoprotein and improve clinical efficacy, immune function, liver function, as well as the quality of life.
PubMed: 37554780
DOI: 10.1016/j.heliyon.2023.e18591 -
Acta Obstetricia Et Gynecologica... Apr 2024Hepatocellular carcinoma (HCC) is the most frequent primary malignant liver tumor and typically develops in the context of chronic liver disease, such as liver cirrhosis... (Review)
Review
INTRODUCTION
Hepatocellular carcinoma (HCC) is the most frequent primary malignant liver tumor and typically develops in the context of chronic liver disease, such as liver cirrhosis or chronic hepatitis B virus infection. Ultrasound evaluation, CT scan, and MRI are used to detect HCC. α-fetoprotein (AFP) is a common marker used to detect HCC in the non-pregnant population, which notoriously increases in pregnant women in relation to gestational age. Treatment is driven by the extent of the disease and the severity of underlying liver disease. Pregnancy may represent an obstacle to diagnosis and appropriate treatment of HCC. The aim of this descriptive systematic review was to describe the clinical features and maternal and neonatal outcomes of HCC in pregnancy.
MATERIAL AND METHODS
We performed a systematic review of the literature about HCC diagnosed in pregnancy and the postpartum period, with signs or symptoms arising in pregnancy. We included case reports and case series describing the clinical features of women diagnosed with HCC, fibrolamellar variant of HCC, and mixed HCC and cholangiocarcinoma during pregnancy or the postpartum period (with onset of symptoms during pregnancy), from inception to March 2023. The study protocol was registered with the PROSPERO database (Registration number: ID CRD42021275584).
RESULTS
We identified 180 records. The articles included in this systematic review were 47 case reports and 5 case series, for a total of 63 pregnancies. The two most frequent predisposing conditions were hepatitis B virus infection (30/63; 47%) and liver cirrhosis (14/63; 22%). Ultrasound evaluation was the most used technique to detect HCC. AFP was higher than normal in 28/46 patients tested (61%). Surgical treatment was the most used therapy, both during pregnancy and after delivery. Twenty-six patients (26/63; 42%) died within 6 months of diagnosis. Survival >24 months was 9% (4/46) in symptomatic and 29% (5/17) in asymptomatic women. No patient with cirrhotic liver survived more than 12 months. Thirty-eight newborns were alive at 28 days of age (38/63; 61%).
CONCLUSIONS
Hepatocellular carcinoma in pregnancy is associated with a high risk of maternal and neonatal mortality. Diagnosis in asymptomatic high-risk women or following abnormal maternal serum AFP screening is associated with better maternal outcomes.
Topics: Infant, Newborn; Humans; Female; Pregnancy; Carcinoma, Hepatocellular; alpha-Fetoproteins; Liver Neoplasms; Hepatitis B, Chronic; Liver Cirrhosis
PubMed: 37533304
DOI: 10.1111/aogs.14640 -
Frontiers in Immunology 2023To identify the risk factors associated with prognosis in patients with hepatocellular carcinoma (HCC) treated with immune checkpoint inhibitors (ICI) via meta-analysis.... (Meta-Analysis)
Meta-Analysis
Development and validation of prognostic risk prediction models for hepatocellular carcinoma patients treated with immune checkpoint inhibitors based on a systematic review and meta-analysis of 47 cohorts.
OBJECTIVE
To identify the risk factors associated with prognosis in patients with hepatocellular carcinoma (HCC) treated with immune checkpoint inhibitors (ICI) via meta-analysis. And to construct prediction models to aid in the prediction and improvement of prognosis.
METHODS
We searched PubMed, Embase, Web of Science and Cochrane Library for relevant studies from inception to March 29, 2023. After completing literature screening and data extraction, we performed meta-analysis, sensitivity analysis, and subgroup analysis to identify risk factors associated with OS and PFS. Using the pooled hazard ratio value for each risk factor, we constructed prediction models, which were then validated using datasets from 19 centers in Japan and two centers in China, comprising a total of 204 patients.
RESULTS
A total of 47 studies, involving a total of 7649 ICI-treated HCC patients, were included in the meta-analysis. After analyzing 18 risk factors, we identified AFP, ALBI, NLR, ECOG performance status, Child-Pugh stage, BCLC stage, tumor number, vascular invasion and combination therapy as predictors for OS prediction model, while AFP, ALBI, NLR, ECOG performance status, Child-Pugh stage, BCLC stage, tumor number and vascular invasion were selected as predictors for PFS model. To validate the models, we scored two independent cohorts of patients using both prediction models. Our models demonstrated good performance in these cohorts. In addition, in the pooled cohort of 204 patients, Our models also showed good performance with area under the curve (AUC) values of 0.712, 0.753, and 0.822 for the OS prediction model at 1-year, 2-year, and 3-year follow-up points, respectively, and AUC values of 0.575, 0.749 and 0.691 for the PFS prediction model Additionally, the calibration curve, decision curve analysis, and Kaplan-Meier curves in the pooled cohort all supported the validity of both models.
CONCLUSION
Based on the meta-analysis, we successfully constructed the OS and PFS prediction models for ICI-treated HCC patients. We also validated the models externally and observed good discrimination and calibration. The model's selected indicators are easily obtainable, making them suitable for further application in clinical practice.
Topics: Humans; Carcinoma, Hepatocellular; Prognosis; Immune Checkpoint Inhibitors; Liver Neoplasms; alpha-Fetoproteins
PubMed: 37520554
DOI: 10.3389/fimmu.2023.1215745 -
EBioMedicine Jul 2023Various studies have reported cell-free RNAs (cfRNAs) as noninvasive biomarkers for detecting hepatocellular carcinoma (HCC). However, they have not been independently...
BACKGROUND
Various studies have reported cell-free RNAs (cfRNAs) as noninvasive biomarkers for detecting hepatocellular carcinoma (HCC). However, they have not been independently validated, and some results are contradictory. We provided a comprehensive evaluation of various types of cfRNA biomarkers and a full mining of the biomarker potential of new features of cfRNA.
METHODS
We first systematically reviewed reported cfRNA biomarkers and calculated dysregulated post-transcriptional events and cfRNA fragments. In 3 independent multicentre cohorts, we further selected 6 cfRNAs using RT-qPCR, built a panel called HCCMDP with AFP using machine learning, and internally and externally validated HCCMDP's performance.
FINDINGS
We identified 23 cfRNA biomarker candidates from a systematic review and analysis of 5 cfRNA-seq datasets. Notably, we defined the cfRNA domain to describe cfRNA fragments systematically. In the verification cohort (n = 183), cfRNA fragments were more likely to be verified, while circRNA and chimeric RNA candidates were neither abundant nor stable as qPCR-based biomarkers. In the algorithm development cohort (n = 287), we build and test the panel HCCMDP with 6 cfRNA markers and AFP. In the independent validation cohort (n = 171), HCCMDP can distinguish HCC patients from control groups (all: AUC = 0.925; CHB: AUC = 0.909; LC: AUC = 0.916), and performs well in distinguishing early-stage HCC patients (all: AUC = 0.936; CHB: AUC = 0.917; LC: AUC = 0.928).
INTERPRETATION
This study comprehensively evaluated full-spectrum cfRNA biomarker types for HCC detection, highlighted the cfRNA fragment as a promising biomarker type in HCC detection, and provided a panel HCCMDP.
FUNDING
National Natural Science Foundation of China, and The National Key Basic Research Program (973 program).
Topics: Humans; Carcinoma, Hepatocellular; Liver Neoplasms; alpha-Fetoproteins; Cell-Free Nucleic Acids; Biomarkers, Tumor; ROC Curve; MicroRNAs
PubMed: 37315449
DOI: 10.1016/j.ebiom.2023.104645