Classification Accuracy of Hepatitis C Virus Infection Outcome: Data Mining Approach.
Ontology highlight
ABSTRACT: Background
The dataset from genes used to predict hepatitis C virus outcome was evaluated in a previous study using a conventional statistical methodology.Objective
The aim of this study was to reanalyze this same dataset using the data mining approach in order to find models that improve the classification accuracy of the genes studied.Methods
We built predictive models using different subsets of factors, selected according to their importance in predicting patient classification. We then evaluated each independent model and also a combination of them, leading to a better predictive model.Results
Our data mining approach identified genetic patterns that escaped detection using conventional statistics. More specifically, the partial decision trees and ensemble models increased the classification accuracy of hepatitis C virus outcome compared with conventional methods.Conclusions
Data mining can be used more extensively in biomedicine, facilitating knowledge building and management of human diseases.
SUBMITTER: Frias M
PROVIDER: S-EPMC7946589 | biostudies-literature | 2021 Feb
REPOSITORIES: biostudies-literature
Publications
Classification Accuracy of Hepatitis C Virus Infection Outcome: Data Mining Approach.
Frias Mario M Moyano Jose M JM Rivero-Juarez Antonio A Luna Jose M JM Camacho Ángela Á Fardoun Habib M HM Machuca Isabel I Al-Twijri Mohamed M Rivero Antonio A Ventura Sebastian S
Journal of medical Internet research 20210224 2
<h4>Background</h4>The dataset from genes used to predict hepatitis C virus outcome was evaluated in a previous study using a conventional statistical methodology.<h4>Objective</h4>The aim of this study was to reanalyze this same dataset using the data mining approach in order to find models that improve the classification accuracy of the genes studied.<h4>Methods</h4>We built predictive models using different subsets of factors, selected according to their importance in predicting patient class ...[more]
Similar Datasets
Project description:There is little known of immunologic factors leading to the occurrence of occult HBV infection (OBI). Specific cellular immune response to hepatitis B virus (HBV) core/pol peptides was compared between blood donor populations, including 37 OBIs, 53 chronic HBV infections (CHB), 47 resolved infections, and 56 non-infected controls, respectively. The rate of CD4+/CD8+ T cell proliferation in OBI or CHB carriers was higher than in HBV resolved and non-infected individuals (P < 0.05). The intensity of IFN-γ-secretion T-cell response of OBI carriers was highest, followed by CHB and resolved infections, and non-infected individuals (P < 0.05). The frequency of intracellular IFN-γ and IL-17A CD4+/CD8+ and IL-21 CD4+ T-cell responses was significantly higher in resolved infections than in OBI or CHB carriers (P < 0.05), while the level of extracellular IL-17A of peripheral blood mononuclear cells (PBMCs) was higher in OBI and CHB carriers than in resolved infections (P < 0.01). The frequency of intracellular IL-10 CD4+ T-cell response in CHB, OBI, and resolved infections was higher than in HBV non-infected individuals (P < 0.01). Intracellular IL-10 CD8+ T cell and extracellular IL-10 T-cell responses were higher in CHB than in OBI (P = 0.012) or HBV resolved infections (P < 0.01). In conclusion, the higher level of effective T-cell response with IFN-γ, IL-17A, and IL-21 contributes to resolved infection outcome, while higher levels of suppressive T-cell response with IL-10 result in HBV chronicity. OBI is an intermediary status between HBV resolved and chronic infections, in which IL-21 effector and IL-10 suppressor T-cell responses play an important role in directing the outcome of HBV infection.
| S-EPMC9022031 | biostudies-literature
Project description:Infection by hepatitis C virus (HCV) leads to one of two outcomes; either the infection resolves within approximately 6 months or the virus can persist indefinitely. Host genetics are known to affect the likelihood of clearance or persistence. By contrast, the importance of the virus genotype in determining infection outcome is unknown, as quantifying this effect traditionally requires well-characterized transmission networks, which are rare. Extending phylogenetic approaches previously developed to estimate the virus control over set-point viral load in HIV-1 infections, we simulate inheritance of a binary trait along a phylogenetic tree, use this data to quantify how infection outcomes cluster and ascertain the effect of virus genotype on these. We apply our method to the Hepatitis C Incidence and Transmission Study in prisons (HITS-p) data set from Australia, as this cohort prospectively identified incident cases including viraemic subjects who ultimately clear the virus, thus providing us with a unique collection of sequences from clearing infections. We detect significant correlations between infection outcome and virus distance in the phylogeny for viruses of Genotype 1, with estimates lying at around 67%. No statistically significant estimates were obtained for viruses of Genotype 3a.
| S-EPMC4055175 | biostudies-literature
Project description:Current serologic tests provide the foundation for diagnosis of hepatitis A and hepatitis A virus (HAV) infection. Recent advances in methods to identify and characterize nucleic acid markers of viral infections have provided the foundation for the field of molecular epidemiology and increased our knowledge of the molecular biology and epidemiology of HAV. Although HAV is primarily shed in feces, there is a strong viremic phase during infection which has allowed easy access to virus isolates and the use of molecular markers to determine their genetic relatedness. Molecular epidemiologic studies have provided new information on the types and extent of HAV infection and transmission in the United States. In addition, these new diagnostic methods have provided tools for the rapid detection of food-borne HAV transmission and identification of the potential source of the food contamination.
| S-EPMC1360271 | biostudies-literature
Project description:Several studies have demonstrated that chronic hepatitis delta virus (HDV) infection is associated with a worsening of hepatitis B virus (HBV) infection and increased risk of hepatocellular carcinoma (HCC). However, there is limited data on the role of HDV in the oncogenesis of HCC. This study is aimed at assessing the potential mechanisms of HDV-associated hepatocarcinogenesis, especially to screen and identify key genes and pathways possibly involved in the pathogenesis of HCC. We selected three microarray datasets: GSE55092 contains 39 cancer specimens and 81 paracancer specimens from 11 HBV-associated HCC patients, GSE98383 contains 11 cancer specimens and 24 paracancer specimens from 5 HDV-associated HCC patients, and 371 HCC patients with the RNA-sequencing data combined with their clinical data from the Cancer Genome Atlas (TCGA). Afterwards, 948 differentially expressed genes (DEGs) closely related to HDV-associated HCC were obtained using the R package and filtering with a Venn diagram. We then performed gene ontology (GO) annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis to determine the biological processes (BP), cellular component (CC), molecular function (MF), and KEGG signaling pathways most enriched for DEGs. Additionally, we performed Weighted Gene Coexpression Network Analysis (WGCNA) and protein-to-protein interaction (PPI) network construction with 948 DEGs, from which one module was identified by WGCNA and three modules were identified by the PPI network. Subsequently, we validated the expression of 52 hub genes from the PPI network with an independent set of HCC dataset stored in the Gene Expression Profiling Interactive Analysis (GEPIA) database. Finally, seven potential key genes were identified by intersecting with key modules from WGCNA, including 3 reported genes, namely, CDCA5, CENPH, and MCM7, and 4 novel genes, namely, CDC6, CDC45, CDCA8, and MCM4, which are associated with nucleoplasm, cell cycle, DNA replication, and mitotic cell cycle. The CDCA8 and stage of HCC were the independent factors associated with overall survival of HDV-associated HCC. All the related findings of these genes can help gain a better understanding of the role of HDV in the underlying mechanism of HCC carcinogenesis.
| S-EPMC7867452 | biostudies-literature
Project description:Primary hepatitis C virus infection might be spontaneously cleared or become chronic. Polymorphisms in immune regulatory genes might influence the outcome. The aim of this study was to determine the frequency of genotypes and alleles of PD-1.3 and PD-1.5 gene loci in HCV infected patients and their association with the disease outcome. In this study 167 patients with chronic hepatic C and 42 individuals whose infection was spontaneously cleared, and a healthy control group comprising of 300 participants were included. The presence of chronic or spontaneously cleared infection amongst the participants was determined in advance by serologic and molecular methods. Genomic DNA was extracted using salting out method. PD-1 gene polymorphisms assay was performed using PCR-RFLP method. The frequency of alleles of PD-1.3 gene locus was significantly higher in the spontaneously cleared HCV infected group (P = 0.03) as well as the healthy control group (P = 0.04) in comparison to the chronic infected participants. In the case of PD-1.5 locus, there was no association between the frequency of inherited genotype or alleles and HCV infection outcome amongst the three groups. Haplotype analysis showed no statistically significant differences in the frequencies of different haplotypes between the three studied groups. Our finding collectively inferred that individuals with A allele at PD-1.3 locus might clear HCV infection more frequently than those with T allele. Instead, polymorphisms at PD-1.5 locus as well as haplotypes emerged from PD-1.3 G/A and PD-1.5 C/T might not be significant in the HCV infection outcome.
| S-EPMC6295627 | biostudies-literature
Project description:BackgroundIn Uzbekistan, routine serologic testing has not been available to differentiate etiologies of acute viral hepatitis (AVH). To determine the age groups most affected by hepatitis E virus (HEV) during documented AVH epidemics, trends in AVH-associated mortality rate (MR) per 100,000 over a 15-year period and reported incidence of AVH over a 35-year period were examined.MethodsReported AVH incidence data from 1971 to 2005 and AVH-associated mortality data from 1981 to 1995 were examined. Serologic markers for infection with hepatitis viruses A, B, D, and E were determined from a sample of hospitalized patients with AVH from an epidemic period (1987) and from a sample of pregnant women with AVH from a non-epidemic period (1992).ResultsTwo multi-year AVH outbreaks were identified: one during 1975-1976, and one during 1985-1987. During 1985-1987, AVH-associated MRs were 12.3-17.8 per 100,000 for the general population. Highest AVH-associated MRs occurred among children in the first 3 years of life (40-190 per 100,000) and among women aged 20-29 (15-21 per 100,000). During 1988-1995 when reported AVH morbidity was much lower in the general population, AVH-associated MRs were markedly lower among these same age groups. In 1988, AVH-associated MRs were higher in rural (21 per 100,000) than in urban (8 per 100,000) populations (RR 2.6; 95% CI 1.16-5.93; p < 0.05). Serologic evidence of acute HEV infection was found in 280 of 396 (71%) patients with AVH in 1987 and 12 of 99 (12%) pregnant patients with AVH in 1992.ConclusionIn the absence of the availability of confirmatory testing, inferences regarding probable hepatitis epidemic etiologies can sometimes be made using surveillance data, comparing AVH incidence with AVH-associated mortality with an eye to population-based viral hepatitis control measures. Data presented here implicate HEV as the probable etiology of high mortality observed in pregnant women and in children less than 3 years of age in Uzbekistan during 1985-1987. High mortality among pregnant women but not among children less than 3 years has been observed in previous descriptions of epidemic hepatitis E. The high mortality among younger children observed in an AVH outbreak associated with hepatitis E merits corroboration in future outbreaks.
| S-EPMC2671511 | biostudies-literature
Project description:The use of mobile health applications (apps) especially in the area of lifestyle behaviors has increased, thus providing unprecedented opportunities to develop health programs that can engage people in real-time and in the real-world. Yet, relatively little is known about which factors relate to the engagement of commercially available apps for health behaviors. This exploratory study examined behavioral engagement with a weight loss app, Lose It! and characterized higher versus lower engaged groups. Cross-sectional, anonymized data from Lose It! were analyzed (n = 12,427,196). This dataset was randomly split into 24 subsamples and three were used for this study (total n = 1,011,008). Classification and regression tree methods were used to identify subgroups of user engagement with one subsample, and descriptive analyses were conducted to examine other group characteristics associated with engagement. Data mining validation methods were conducted with two separate subsamples. On average, users engaged with the app for 29 days. Six unique subgroups were identified, and engagement for each subgroup varied, ranging from 3.5 to 172 days. Highly engaged subgroups were primarily distinguished by the customization of diet and exercise. Those less engaged were distinguished by weigh-ins and the customization of diet. Results were replicated in further analyses. Commercially-developed apps can reach large segments of the population, and data from these apps can provide insights into important app features that may aid in user engagement. Getting users to engage with a mobile health app is critical to the success of apps and interventions that are focused on health behavior change.
| S-EPMC5526821 | biostudies-other
Project description:BackgroundHepatitis delta virus (HDV) coinfects with hepatitis B virus (HBV) causing the most severe form of viral hepatitis. However, its exact global disease burden remains largely obscure. We aim to establish the global epidemiology, infection mode-stratified disease progression, and clinical outcome of HDV infection.MethodsWe conducted a meta-analysis with a random-effects model and performed data synthesis.ResultsThe pooled prevalence of HDV is 0.80% (95% confidence interval [CI], 0.63-1.00) among the general population and 13.02% (95% CI, 11.96-14.11) among HBV carriers, corresponding to 48-60 million infections globally. Among HBV patients with fulminant hepatitis, cirrhosis, or hepatocellular carcinoma, HDV prevalence is 26.75% (95% CI, 19.84-34.29), 25.77% (95% CI, 20.62-31.27), and 19.80% (95% CI, 10.97-30.45), respectively. The odds ratio (OR) of HDV infection among HBV patients with chronic liver disease compared with asymptomatic controls is 4.55 (95% CI, 3.65-5.67). Hepatitis delta virus-coinfected patients are more likely to develop cirrhosis than HBV-monoinfected patients with OR of 3.84 (95% CI, 1.79-8.24). Overall, HDV infection progresses to cirrhosis within 5 years and to hepatocellular carcinoma within 10 years, on average.ConclusionsFindings suggest that HDV poses a heavy global burden with rapid progression to severe liver diseases, urging effective strategies for screening, prevention, and treatment.
| S-EPMC7184909 | biostudies-literature
Project description:BackgroundInterferon and ribavirin therapy for chronic hepatitis C virus (HCV) infection yields sustained virological response (SVR) rates of 50-80%. Several factors such as non-1 genotype, beneficial IL28B genetic variants, low baseline IP-10, and the functionality of HCV-specific T cells predict SVR. With the pending introduction of new therapies for HCV entailing very rapid clearance of plasma HCV RNA, the importance of baseline biomarkers likely will increase in order to tailor therapy. CD26 (DPPIV) truncates the chemokine IP-10 into a shorter antagonistic form, and this truncation of IP-10 has been suggested to influence treatment outcome in patients with chronic HCV infection patients. In addition, previous reports have shown CD26 to be a co-stimulator for T cells. The aim of the present study was to assess the utility of CD26 as a biomarker for treatment outcome in chronic hepatitis C and to define its association with HCV-specific T cells.MethodsBaseline plasma from 153 genotype 1 and 58 genotype 2/3 infected patients enrolled in an international multicenter phase III trial (DITTO-HCV) and 36 genotype 1 infected patients participating in a Swedish trial (TTG1) were evaluated regarding baseline soluble CD26 (sCD26) and the functionality of HCV-specific CD8(+) T cells.ResultsGenotype 1 infected patients achieving SVR in the DITTO (P?=?0.002) and the TTG1 (P?=?0.02) studies had lower pretreatment sCD26 concentrations compared with non-SVR patients. Sixty-five percent of patients with sCD26 concentrations below 600 ng/mL achieved SVR compared with 39% of the patients with sCD26 exceeding 600 ng/mL (P?=?0.01). Patients with sCD26 concentrations below 600 ng/mL had significantly higher frequencies of HCV-specific CD8(+) T cells (P?=?0.02).ConclusionsLow baseline systemic concentrations of sCD26 predict favorable treatment outcome in chronic HCV infection and may be associated with higher blood counts of HCV-specific CD8(+) T cells.
| S-EPMC3577643 | biostudies-literature
Project description:Hepatitis C virus (HCV) and hepatitis B virus (HBV) co-infection can be encountered in either virus endemic countries. Co-infection can also be found in populations at risk of parenteral transmission. Previous studies demonstrated a high risk of liver disease progression in patients with HCV/HBV co-infection; thus, they should be treated aggressively. Previous evidence recommended therapy combining peginterferon (pegIFN) alfa and ribavirin for co-infected patients with positive HCV RNA. Recent trials further advise using direct-acting antivirals (DAAs) for the clearance of HCV in the co-infected patients. Reactivation of HBV has been observed in patients post-intervention, with higher risks and earlier onset in those having had HCV cured by DAA- versus pegIFN-based therapy. The mechanism of HBV reactivation is an interesting but unsolved puzzle. Our recent study revealed that in vitro HBV replication was suppressed by HCV co-infection; HBV suppression was attenuated when interferon signaling was blocked. In vivo, the HBV viremia, initially suppressed by the presence of HCV super-infection, rebounded following HCV clearance by DAA treatment and was accompanied by a reduced hepatic interferon response. In summary, major achievements in the treatment of HCV/HBV co-infection have been accomplished over the past 20 years. Future clinical trials should address measures to reduce or prevent HBV reactivation post HCV cure.
| S-EPMC7412310 | biostudies-literature