A predictive model of response to peginterferon ribavirin in chronic hepatitis C using classification and regression tree analysis

Simple algorithm to narrow down the candidates to receive echocardiography in patients with chronic liver disease for suspected pulmonary hypertension

Aims

Portopulmonary hypertension (PoPH) is a subtype of pulmonary arterial hypertension related to portal hypertension. The definitive diagnosis of PoPH is made by invasive right heart catheterization. Alternatively, pulmonary arterial hypertension may be recognized noninvasively from the tricuspid regurgitant pressure gradient (TRPG), measured by echocardiography. In this study, we aimed to establish a simple algorithm to identify chronic liver disease patients with a high TRPG value in order to narrow down the candidates to receive echocardiography.

Methods and Results

TRPG was measured by echocardiography in 152 patients with chronic liver disease. Factors predictive of TRPG >30 mmHg were investigated. There were 28 (18%) cases with TRPG >30 mmHg. Independent factors associated with a high TRPG were the presence of shortness of breath, high serum brain natriuretic peptide (BNP), and low serum albumin. Child–Pugh class or the presence of ascites, varices, or encephalopathy was not associated with TRPG. There was a correlation between the serum BNP and TRPG, and the optimal cutoff value of BNP by the Youden index was 122 pg/mL, and by 100% sensitivity was 50 pg/mL. A combination of these factors identified patients with a high probability of TRPG >30 mmHg (n = 12, positive predictive value [PPV] of 83%), no probability (n = 80, PPV 0%), and intermediate probability (n = 60, PPV 25–34%). This algorithm has reduced the number of patients needing echocardiography by 53%.

Conclusions

A simple algorithm using the presence of shortness of breath, serum BNP, and albumin levels can narrow down the candidates to receive echocardiography.

Attenuation coefficient (ATT) measurement for liver fat quantification in chronic liver disease

Liver fat is one of the main clinical features in chronic liver disease, and the number of fatty liver patients is increasing as the prevalence of obesity and metabolic syndrome increases globally. Noninvasive and quantitative assessment of liver fat content was made possible by recent technological advances. Attenuation coefficient (ATT) measurement is a noninvasive and quantitative liver fat measurement method used in clinical practice. The ATT value is significantly associated with histological steatosis grade. The diagnostic accuracy of ATT for histological steatosis grade is equivalent to controlled attenuation parameter (CAP), and ATT has a lower measurement failure rate than CAP because ATT can be measured on a B-mode image with the exact location of the region of interest. Furthermore, ATT measurement has high interobserver reproducibility. Since ATT measurement and other ultrasound-based modalities for liver fat quantification are easy to perform and inexpensive, these modalities are suitable for point-of-care and screening. Although emerging data suggest that quantitative liver fat content and its changes over time may be associated with disease progression in nonalcoholic fatty liver disease, the association between ATT and disease progression has not been evaluated yet. Therefore, further investigation and validation studies are necessary to strengthen the clinical significance of ATT measurement in chronic liver disease.

Potential value and impact of data mining and machine learning in clinical diagnostics

Data mining involves the use of mathematical sciences, statistics, artificial intelligence, and machine learning to determine the relationships between variables from a large sample of data. It has previously been shown that data mining can improve the prediction and diagnostic precision of type 2 diabetes mellitus. A few studies have applied machine learning to assess hypertension and metabolic syndrome-related biomarkers, as well as refine the assessment of cardiovascular disease risk. Machine learning methods have also been applied to assess new biomarkers and survival outcomes in patients with renal diseases to predict the development of chronic kidney disease, disease progression, and renal graft survival. In the latter, random forest methods were found to be the best for the prediction of chronic kidney disease. Some studies have investigated the prognosis of nonalcoholic fatty liver disease and acute liver failure, as well as therapy response prediction in patients with viral disorders, using decision tree models. Machine learning techniques, such as Sparse High-Order Interaction Model with Rejection Option, have been used for diagnosing Alzheimer's disease. Data mining techniques have also been applied to identify the risk factors for serious mental illness, such as depression and dementia, and help to diagnose and predict the quality of life of such patients. In relation to child health, some studies have determined the best algorithms for predicting obesity and malnutrition. Machine learning has determined the important risk factors for preterm birth and low birth weight. Published studies of patients with cancer and bacterial diseases are limited and should perhaps be addressed more comprehensively in future studies. Herein, we provide an in-depth review of studies in which biochemical biomarker data were analyzed using machine learning methods to assess the risk of several common diseases, in order to summarize the potential applications of data mining methods in clinical diagnosis. Data mining techniques have now been increasingly applied to clinical diagnostics, and they have the potential to support this field.

Therapeutic Outcomes and Prognostic Factors of Unresectable Intrahepatic Cholangiocarcinoma: A Data Mining Analysis

Prognosis of patients with intrahepatic cholangiocarcinoma (ICC) is unsatisfactory. Tumor, host, and treatment factors including hepatic arterial infusion chemotherapy (HAIC) are intricately involved in the progression of ICC. We aimed to identify profiles associated with disease control rate (DCR) and the prognosis of patients with unresectable ICC by decision tree analysis. We analyzed 31 consecutive patients with unresectable ICC (median age, 71 years; the male ratio was 58.1%). Stage IVB occupied 51.6% of patients, and 38.7% and 58.1% of patients were treated with gemcitabine plus cisplatin combination therapy and HAIC, respectively. Profiles associated with prognosis as well as DCR were investigated by decision tree analysis. The median survival time (MST) of the patients was 11.6 months, and the DCR was 70.9%. Multivariate correlation analysis showed that albumin levels and WBC levels were significantly correlated with survival time (albumin, ρ = 0.3572, p = 0.0485; WBC, ρ = -0.4008, p = 0.0280). In decision tree analysis, WBC level was selected as the initial split variable, and subjects with WBC levels of 6800/μL or less (45.1%) showed a long survival time (MST 476 days). We also demonstrated that the profile associated with the highest DCR was "less than 4.46 mg/dL of CRP levels and treatment with HAIC". We demonstrated a new prognostic profile for ICC patients, which consisted of WBC and CRP levels. Moreover, we demonstrated that HAIC was associated with better disease control in ICC patients with low CPR levels. Thus, these new profiles may be useful for the management of ICC patients.

Association of serum interferon-λ3 levels with hepatocarcinogenesis in chronic hepatitis C patients treated with direct-acting antiviral agents

AIM

Although the efficacy of hepatitis C virus (HCV) treatment is improved dramatically by direct-acting antiviral agents (DAAs), the assessment of hepatocellular carcinoma (HCC) remains important. Interferon lambda 3 (IFN-λ3) is associated with liver fibrosis and inflammation in chronic hepatitis C (CHC) patients, but its impact on carcinogenesis remains controversial and little is known about its effects after viral clearance. To determine the contribution of IFN-λ3 to hepatocarcinogenesis after HCV clearance, we analyzed IFNL3 genotypes and serial serum IFN-λ3 levels in CHC patients who achieved sustained virologic responses (SVR).

METHODS

This study comprised 201 CHC patients treated with DAAs. Serum samples were collected sequentially and IFN-λ3 levels were quantified by chemiluminescence enzyme immunoassay. The IFNL3 polymorphism (rs8099917) was genotyped in 195 patients.

RESULTS

One hundred and twenty-five patients were rs8099917 T/T and 70 were non-T/T. Serum IFN-λ3 levels did not differ significantly with IFNL3 genotype, dropped markedly by 1 week and remained low up to 24 weeks after the end of treatment. Interferon-λ3 levels were significantly higher after viral clearance in patients who developed HCC and were associated with a higher potential for hepatocarcinogenesis, such as a higher frequency of non-hypervascular hypointensive nodules (P = 0.046), higher stages of liver fibrosis (P < 0.001), and higher post-treatment levels of Wisteria floribunda agglutinin positive Mac-2 binding protein (P < 0.001) and alanine aminotransferase (P < 0.001).

CONCLUSIONS

Serum IFN-λ3 levels after HCV clearance are associated with the potential for HCC development. Interferon-λ3 could be helpful for elucidating the relationships among immunologic status, liver fibrosis, liver inflammation, and hepatocarcinogenesis, after achieving SVR.

C-reactive protein to albumin ratio is a key indicator in a predictive model for anastomosis leakage after esophagectomy: Application of classification and regression tree analysis

Background

Anastomotic leakage (AL), a serious complication after esophagectomy, might impair patient quality of life, prolong hospital stay, and even lead to surgery‐related death. The aim of this study was to show a novel decision model based on classification and regression tree (CART) analysis for the prediction of postoperative AL among patients who have undergone esophagectomy.

Methods

A total of 450 patients (training set: 356; test set: 94) with perioperative information were included. A decision tree model was established to identify the predictors of AL in the training set, which was validated in the test set. A receiver operating characteristic curve was also created to illustrate the diagnostic ability of the decision model.

Results

A total of 12.2% (55/450) of the 450 patients suffered AL, which was diagnosed at median postoperative day 7 (range: 6–16). The decision tree model, containing surgical duration, postoperative lymphocyte count, and postoperative C‐reactive protein to albumin ratio, was established by CART analysis. Among the three variables, the postoperative C‐reactive protein to albumin ratio was identified as the most important indicator in the CART model with normalized importance of 100%. According to the results validated in the test set, the sensitivity, specificity, positive and negative predictive value, and diagnostic accuracy of the prediction model were 80%, 98.8%, 88.9%, 97.6%, and 96.8%, respectively. Moreover, the area under the receiver operating characteristic curve was 0.95.

Conclusion

The decision model based on CART analysis presented good performance for predicting AL, and might allow the early identification of patients at high risk.

Prevalent vertebral fracture is dominantly associated with spinal microstructural deterioration rather than bone mineral density in patients with type 2 diabetes mellitus

BACKGROUND

An assessment of bone strength based on bone mineral density (BMD) underestimates the risk of fracture in patients with diabetes mellitus (T2DM). However, using the trabecular bone score (TBS) for estimating bone microarchitecture, previous studies showed that bone fragility is associated with deterioration of the microstructure concomitantly with decreased BMD. This study was conducted to clarify which of these skeletal-related factors had a more prominent relationship with bone fragility.

RESEARCH DESIGN AND METHODS

A retrospective cross-sectional study was performed at Shimane University Hospital. A total of 548 Japanese patients with T2DM [257 postmenopausal women and 291 men aged over 50 years] were included. TBS of the spine was computed from dual-energy X-ray absorptiometry images obtained from BMD measurements.

RESULTS

Vertebral fractures (VFs) were identified in 74 (28.8%) women and 115 (39.5%) men. A relationship between BMD and VFs was observed in the limited subgroup of women with a BMD T-score ≤-1.0. According to multivariate logistic regression analysis, low TBS was significantly correlated with prevalent VFs, independent of BMD in both genders, except for men with a BMD T-score > -1.0. The decision tree showed that the priority factor for determining VFs was TBS, not BMD.

CONCLUSION

Spinal microarchitecture represented by TBS was a more dominant skeletal factor for bone fragility than the decrease in bone mass, independent of BMD, in patients with T2DM. This observation suggests that loss of structural bone quality was crucial underlying pathogenesis for bone brittleness in these populations, regardless of gender. An integrated assessment of bone strength by BMD and TBS would help diagnose diabetic osteoporosis.

Factors improving the utility of antiviral therapy for chronic hepatitis B: A nationwide multicenter study in Japan

AIM

The consideration of patients' needs in terms of research outcomes is emphasized in research promotion to eradicate hepatitis B virus according to the Basic Act on Hepatitis Measures in Japan. This study analyzed patients' attitudes toward experienced antiviral therapies for chronic hepatitis B and their need for future therapies.

METHODS

A self-administered questionnaire comprising 124 questions was completed among patients with chronic hepatitis B from 61 core-center hospitals designated to implement and research policies on hepatitis in 47 prefectures from August 2013 to January 2014 (n = 3021, response rate = 51%).

RESULTS

In decision-tree models with 333 variables generated from the questionnaire data, patients' satisfaction with therapy and reduction in anxiety about therapy were dependent on favorable therapeutic effects, sufficient information provided by the physician, and fewer lifestyle disturbances. Medical expenses were not selected at a superior branch because subsidy for antiviral therapy started in 2010. In correspondence analysis of free text answers, patients' need for therapy and support mechanisms differed among their attributes, including a great need for novel therapy in older men, hope for avoidance of lifestyle disturbance in younger men, and alleviation of painful experience with the disease in women.

CONCLUSIONS

Continual provision of sufficient information is necessary to improve the utility of antiviral therapy for chronic hepatitis B as well as for favorable therapeutic effects. The patients believed that novel drugs and support would reduce the diverse burden of the disease on their lives.

A Data Mining-based Prognostic Algorithm for NAFLD-related Hepatoma Patients: A Nationwide Study by the Japan Study Group of NAFLD

The prognosis of patients with nonalcoholic fatty liver disease-related hepatocellular carcinoma (NAFLD-HCC) is intricately associated with various factors. We aimed to investigate the prognostic algorithm of NAFLD-HCC patients using a data-mining analysis. A total of 247 NAFLD-HCC patients diagnosed from 2000 to 2014 were registered from 17 medical institutions in Japan. Of these, 136 patients remained alive (Alive group) and 111 patients had died at the censor time point (Deceased group). The random forest analysis demonstrated that treatment for HCC and the serum albumin level were the first and second distinguishing factors between the Alive and Deceased groups. A decision-tree algorithm revealed that the best profile comprised treatment with hepatectomy or radiofrequency ablation and a serum albumin level ≥3.7 g/dL (Group 1). The second-best profile comprised treatment with hepatectomy or radiofrequency ablation and serum albumin levels <3.7 g/dL (Group 2). The 5-year overall survival rate was significantly higher in the Group 1 than in the Group 2. Thus, we demonstrated that curative treatment for HCC and serum albumin level >3.7 g/dL was the best prognostic profile for NAFLD-HCC patients. This novel prognostic algorithm for patients with NAFLD-HCC could be used for clinical management.

Daclatasvir and asunaprevir treatment in patients infected by genotype 1b of hepatitis C virus with no or subtle resistant associated substitutions (RAS) in NS5A-Y93

In this study, we investigated the real-world data of the first approved interferon-free regimen in Japan, daclatasvir and asunaprevir (DCV+ASV), in chronic hepatitis C patients infected HCV genotype 1b with no or subtle amount of baseline resistant associated substitutions (RAS). Among 924 patients registered in our multicenter study, 750 patients who were proven not to be infected with NS5A-Y93H RAS by direct sequencing and to have no or subtle amount (less than 20%) of NS5A-Y93H RAS by probe assays (Cycleave or PCR invader assay) were included in this study. We investigated the anti-viral effect and factors associated with SVR12. In statistical analysis, P < 0.05 was considered as significant. The SVR12 rate in this population was 92.1% (562/618). Factors associated with SVR12 were male (odds ratio: 2.128; 95%CI: 1.134-4.000, P = 0.019); lower serum γGTP (odds ratio: 1.007; 95%CI: 1.002-1.012, P = 0.006); lower HCV-RNA (odds ratio: 1.848; 95%CI: 1.087-3.145, P = 0.023), and RVR (odds ratio: 6.250; 95%CI: 2.445-15.873, P < 0.001). No patients with γGTP ≧ 80 IU/L without RVR showed SVR12 (0/4, 0%) and one patients with γGTP ≧ 20-< 80 IU/L and HCV-RNA ≧ 6.5 logIU/mL without RVR (5/10, 50%) and two female patients with RVR but γGTP ≧ 80 IU/L and HCV-RNA ≧ 6.5 logIU/mL (7/13, 53.8%) showed a low SVR12 rate. In the present study, we showed a good viral response with DCV-ASV treatment and identified four predictive factors associated with SVR12. These four markers could be a good predictive markers for the viral effect of this treatment regimen in patients with no or subtle amount of RAS in NS5A-Y93.

Daclatasvir and asunaprevir treatment in patients with severe liver fibrosis by hepatitis C virus genotype 1b infection: Real-world data

BACKGROUND AND AIM

In this study, we investigated the real-world data of the first approved interferon-free regimen in Japan: daclatasvir and asunaprevir in chronic hepatitis C patients with severe fibrosis.

METHODS

Among 924 patients registered in our multicenter study, 535 patients were defined as having severe fibrosis with Fib-4 index ≧ 3.25 and were included in this study. We investigated antiviral effect and factors associated with sustained viral response 12 (SVR12), and the additional effects on serum α-fetoprotein and albumin levels by eradicating virus in patients who attained SVR were investigated. In statistical analysis, P < 0.05 was considered as significant levels.

RESULTS

Antiviral effect was lower in patients with severe fibrosis at 8 and 12 weeks after start of the treatment (96.3%, 97.1% with severe fibrosis vs 99.5%, 99.2% without severe fibrosis, P = 0.002 and P = 0.036, respectively), and more early relapse (SVR4; 90.4% with severe fibrosis vs 95.4% without fibrosis, P = 0.008) was seen in patients with severe fibrosis; however, there were no differences in SVR12 and SVR24. In the safety profiles, discontinuation rate due to liver injury (2.8% with severe fibrosis vs 3.3% without severe fibrosis) or other causes of discontinuation was not different between two groups. Serum α-fetoprotein significantly decreased, and serum albumin levels significantly increased as early as 4 weeks after the start of treatment.

CONCLUSION

Although the antiviral effect was slightly lower in patients with severe fibrosis compared with those without, treatment with daclatasvir and asunaprevir is basically an effective and well-tolerable treatment in these populations.

Impact of PNPLA3 and IFNL3 polymorphisms on hepatic steatosis in Asian patients with chronic hepatitis C

BACKGROUND AND AIMS

A recent meta-analysis revealed that the genotype PNPLA3 rs738409 GG is associated with a higher risk of hepatic steatosis (HS) in Caucasian patients with chronic hepatitis C (CHC). However, controversial results were found regarding Asian populations. Furthermore, previous studies have shown a negative association between interferon lambda 3 (IFNL3) rs12979860 CC and HS in Caucasian CHC patients, but there have been no reports indicating any such association in Asian populations. In this study, then, we investigated the association of PNPLA3 and IFNL3 polymorphisms with HS in Asian CHC patients.

METHODS

We enrolled consecutive CHC patients who underwent liver biopsy prior to antiviral therapy. We excluded those patients with decompensated liver disease, any co-existing chronic liver disease, or HIV or HBV co-infection.

RESULTS

1080 CHC patients were enrolled, and HS was found in 453 (41.9%) patients. The frequency distribution of the G allele was significantly associated with HS (P<0.001), and this conferred a higher risk to G allele homozygotes (OR: 2.06, 95% CI: 1.46-2.88, P <0.001) than to G allele carriers (OR: 1.98, 95% CI: 1.52-2.58, P<0.001). There was a borderline significant difference in the prevalence of HS in rs12979860 CC versus non-CC (40.8% versus 49.3%, P = 0.059). After adjustment for age, sex, body mass index, diabetes, and excessive alcohol intake, the rs738409 G allele homozygote carriers still carried a higher risk for HS (OR: 1.93, 95% CI: 1.35-2.77, P = 0.003).

CONCLUSION

The PNPLA3 rs738409 GG genotype is positively associated with HS, while the IFNL3 rs 12979860 CC genotype may be negatively associated with HS, in Asian CHC patients.

Single focus on breast magnetic resonance imaging: diagnosis based on kinetic pattern and patient age

Background Because of its small size, a focus in breast magnetic resonance imaging (MRI) must be evaluated on the basis of characteristics other than morphologic features. Patient-related factors including patient age, in conjunction with lesion-related factors, could be useful for decision-making. Purpose To assess the probability of malignant foci based on both lesion- and patient-related factors, and to propose a relevant decision-making method. Material and Methods Foci in our breast MRI database dating from April 2006 to June 2013 were retrospectively identified and analyzed. A Fisher's exact test or a Mann-Whitney U test were performed for univariate analyses, and factors that showed a significant association with outcome in the univariate analyses were subjected to multivariate analysis using a logistic regression model. A decision tree was then drawn using the significant predictors confirmed by multivariate analysis. Results In total, 184 foci (168 benign, 16 malignant) in 184 patients were analyzed in our study. The presence of a washout pattern and older age were found to be significant predictors of malignancy ( P < 0.0001; odds ratio [OR], 17.8; P = 0.021; OR, 1.1, respectively). The main decisive node on the decision tree was the presence of a washout pattern, followed by whether the patient's age was >63 years. Conclusion An enhancing focus showing a washout pattern, especially in older patients, may warrant immediate biopsy rather than short-interval follow-up.

Predictors of Virological Response in 3,235 Chronic HCV Egyptian Patients Treated with Peginterferon Alpha-2a Compared with Peginterferon Alpha-2b Using Statistical Methods and Data Mining Techniques

Despite the appearance of new oral antiviral drugs, pegylated interferon (PEG-IFN)/RBV may remain the standard of care therapy for some time, and several viral and host factors are reported to be correlated with therapeutic effects. This study aimed to reveal the independent variables associated with failure of sustained virological response (SVR) to PEG-IFN alpha-2a versus PEG-IFN alpha-2b in treatment of naive chronic hepatitis C virus (HCV) Egyptian patients using both statistical methods and data mining techniques. This retrospective cohort study included 3,235 chronic hepatitis C patients enrolled in a large Egyptian medical center: 1,728 patients had been treated with PEG-IFN alpha-2a plus ribavirin (RBV) and 1,507 patients with PEG-IFN alpha-2b plus RBV between 2007 and 2011. Both multivariate analysis and Reduced Error Pruning Tree (REPTree)-based model were used to reveal the independent variables associated with treatment response. In both treatment types, alpha-fetoprotein (AFP) >10 ng/mL and HCV viremia >600 × 10(3) IU/mL were the independent baseline variables associated with failure of SVR, while male gender, decreased hemoglobin, and thyroid-stimulating hormone were the independent variables associated with good response (P < 0.05). Using REPTree-based model showed that low AFP was the factor of initial split (best predictor) of response for either PEG-IFN alpha-2a or PEG-IFN alpha-2b (cutoff value 8.53, 4.89 ng/mL, AUROC = 0.68 and 0.61, P = 0.05). Serum AFP >10 ng/mL and viral load >600 × 10(3) IU/mL are variables associated with failure of response in both treatment types. REPTree-based model could be used to assess predictors of response.

Application of data mining techniques to explore predictors of HCC in Egyptian patients with HCV-related chronic liver disease

BACKGROUND

Hepatocellular carcinoma (HCC) is the second most common malignancy in Egypt. Data mining is a method of predictive analysis which can explore tremendous volumes of information to discover hidden patterns and relationships. Our aim here was to develop a non-invasive algorithm for prediction of HCC. Such an algorithm should be economical, reliable, easy to apply and acceptable by domain experts.

METHODS

This cross-sectional study enrolled 315 patients with hepatitis C virus (HCV) related chronic liver disease (CLD); 135 HCC, 116 cirrhotic patients without HCC and 64 patients with chronic hepatitis C. Using data mining analysis, we constructed a decision tree learning algorithm to predict HCC.

RESULTS

The decision tree algorithm was able to predict HCC with recall (sensitivity) of 83.5% and precession (specificity) of 83.3% using only routine data. The correctly classified instances were 259 (82.2%), and the incorrectly classified instances were 56 (17.8%). Out of 29 attributes, serum alpha fetoprotein (AFP), with an optimal cutoff value of ≥50.3 ng/ml was selected as the best predictor of HCC. To a lesser extent, male sex, presence of cirrhosis, AST>64U/L, and ascites were variables associated with HCC.

CONCLUSION

Data mining analysis allows discovery of hidden patterns and enables the development of models to predict HCC, utilizing routine data as an alternative to CT and liver biopsy. This study has highlighted a new cutoff for AFP (≥50.3 ng/ml). Presence of a score of >2 risk variables (out of 5) can successfully predict HCC with a sensitivity of 96% and specificity of 82%.

Genotype 3 and higher low-density lipoprotein levels are predictors of good response to treatment of recurrent hepatitis C following living donor liver transplantation

BACKGROUND

Treatment of recurrent hepatitis C after liver transplantation is associated with poor sustained virological response (SVR) in genotype 1, and data on genotype 3 is limited to small numbers. We report one of the largest series of genotype 3 patients treated for recurrent hepatitis C following living donor liver transplantation (LDLT).

METHODS

From January 2002 to November 2013, of 1349 transplants, 359 patients had hepatitis C. Patients with histological recurrence were treated with pegylated interferon in escalating dose regimen for 48 weeks and weight-based ribavirin. Virological response was defined as rapid virological response (RVR-4 weeks), early virological response (EVR-12 weeks), end of treatment response (ETR-48 weeks), and SVR (24 weeks after end of treatment). SVR and no-SVR groups were compared for age, sex, body mass index (BMI), diabetes, total cholesterol, low-density lipoprotein (LDL), high-density lipoprotein (HDL), triglycerides, ferritin, genotype, and hepatitis C virus (HCV) RNA levels before initiation of treatment.

RESULTS

The study included 67 patients who had at least 18 months of follow up after treatment initiation (45 males), aged 51 ± 6.3 years. Treatment was started after 16 months (median); baseline median RNA was 2.7 × 10(6) IU/mL. There was no significant difference between the SVR and no-SVR groups regarding age, sex ratio, follow up period, total cholesterol, triglycerides, HDL, BMI, prevalence of diabetes, HCV RNA, and ferritin levels. Genotype 3, RVR, EVR, ETR, and higher LDL levels were significantly associated with SVR. Genotype 3 had a significantly higher SVR rate of 71 % as compared to an SVR rate of only 14 % in genotype 1, p = 0.0003. Absence of RVR and EVR predicted treatment failure with a specificity of 88 % and 92 %, respectively.

CONCLUSION

Genotype 3 and higher LDL levels predict SVR in patients treated for hepatitis C recurrence following LDLT, whereas absence of RVR and EVR strongly predict treatment failure.

A novel approach to identify candidate prognostic factors for hepatitis C treatment response integrating clinical and viral genetic data

The combined therapy of pegylated interferon (IFN) plus ribavirin (RBV) has been for a long time the standard treatment for patients infected with hepatitis C virus (HCV). In the case of genotype 1, only 38%–48% of patients have a positive response to the combined treatment. In previous studies, viral genetic information has been occasionally included as a predictor. Here, we consider viral genetic variation in addition to 11 clinical and 19 viral populations and evolutionary parameters to identify candidate baseline prognostic factors that could be involved in the treatment outcome. We obtained potential prognostic models for HCV subtypes la and lb in combination as well as separately. We also found that viral genetic information is relevant for the combined treatment assessment of patients, as the potential prognostic model of joint subtypes includes 9 viral-related variables out of 11. Our proposed methodology fully characterizes viral genetic information and finds a combination of positions that modulate inter-patient variability.

Stratifying the risk of lymph node metastasis in undifferentiated-type early gastric cancer

AIM: To study how lymph node metastasis (LNM) risk is stratified in undifferentiated-type early gastric cancer (undiff-EGC) dependent on combinations of risk factors.

METHODS: Five hundred and sixty-seven cases with undiff-EGC undergoing gastrectomy with lymphadenectomy were examined retrospectively. Using clinicopathological factors of patient age, location, size, an endoscopic macroscopic tumor form, ulceration, depth, histology, lymphatic involvement (LI) and venous involvement (VI), LNM risk was examined and stratified by conventional statistical analysis and data-mining analysis.

RESULTS: LNM was positive in 44 of 567 cases (7.8%). Univariate analysis revealed > 2 cm, protrusion, submucosal (sm), mixed type, LI and VI as significant prognostic factors and > 2 cm and LI-positive were independent factors by multivariate analysis. In preoperatively evaluable factors excluding LVI, sm and > 2 cm were independent factors. According to the depth and size, cases were categorized into the low-risk group [m and ≤ 2 cm, 0% (LNM incidence)], the moderate-risk group (m and > 2 cm, 5.6%; and sm and ≤ 2 cm, 6.0%), and the high-risk group (sm and > 2 cm, 19.3%). On the other hand, LNM occurred in 1.4% in all LI-negative cases, greatly lower than 28.2% in all LI-positive cases, and LNM incidence was low in LI-negative cases even in the moderate- and high-risk groups.

CONCLUSION: LNM-related factors in undiff-EGC were depth and size preoperatively while those were LI and size postoperatively. Among these factors, LI was the most significantly correlated factor.

A framework for prediction of response to HCV therapy using different data mining techniques

Hepatitis C which is a widely spread disease all over the world is a fatal liver disease caused by Hepatitis C Virus (HCV). The only approved therapy is interferon plus ribavirin. The number of responders to this treatment is low, while its cost is high and side effects are undesirable. Treatment response prediction will help in reducing the patients who suffer from the side effects and high costs without achieving recovery. The aim of this research is to develop a framework which can select the best model to predict HCV patients' response to the treatment of HCV from clinical information. The framework contains three phases which are preprocessing phase to prepare the data for applying Data Mining (DM) techniques, DM phase to apply different DM techniques, and evaluation phase to evaluate and compare the performance of the built models and select the best model as the recommended one. Different DM techniques had been applied which are associative classification, artificial neural network, and decision tree to evaluate the framework. The experimental results showed the effectiveness of the framework in selecting the best model which is the model built by associative classification using histology activity index, fibrosis stage, and alanine amino transferase.

Serum albumin level is a notable profiling factor for non-B, non-C hepatitis virus-related hepatocellular carcinoma: A data-mining analysis

AIM

Various factors are underlying for the onset of non-B, non-C hepatitis virus-related hepatocellular carcinoma (NBNC-HCC). We aimed to investigate the independent risk factors and profiles associated with NBNC-HCC using a data-mining technique.

METHODS

We conducted a case-control study and enrolled 223 NBNC-HCC patients and 669 controls from a health checkup database (n = 176 886). Multivariate analysis, random forest analysis and a decision-tree algorithm were employed to examine the independent risk factors, factors distinguishing between the case and control groups, and to identify profiles for the incidence of NBNC-HCC, respectively.

RESULTS

In multivariate analysis, besides γ-glutamyltransferase (GGT) levels and the Brinkman index, albumin level was an independent negative risk factor for the incidence of NBNC-HCC (odds ratio = 0.67; 95% confidence interval = 0.60-0.70; P < 0.0001). In random forest analysis, serum albumin level was the highest-ranked variable for distinguishing between the case and control groups (98 variable importance). A decision-tree algorithm was created for albumin and GGT levels, the aspartate aminotransferase-to-platelet ratio index (APRI) and the Brinkman index. The serum albumin level was selected as the initial split variable, and 82.5% of the subjects with albumin levels of less than 4.01 g/dL were found to have NBNC-HCC.

CONCLUSION

Data-mining analysis revealed that serum albumin level is an independent risk factor and the most distinguishable factor associated with the incidence of NBNC-HCC. Furthermore, we created an NBNC-HCC profile consisting of albumin and GGT levels, the APRI and the Brinkman index. This profile could be used in the screening strategy for NBNC-HCC.

The impact of interleukin 28b gene polymorphism on the virological response to combined pegylated interferon and ribavirin therapy in chronic HCV genotype 4 infected egyptian patients using data mining analysis

BACKGROUND

Chronic HCV represents one of the common causes of chronic liver disease worldwide with Egypt having the highest prevalence, namely genotype 4. Interleukin IL-28B gene polymorphism has been shown to relate to HCV treatment response, mainly in genotype1.

OBJECTIVES

We aim to evaluate the predictive power of the rs12979860 IL28B SNP and its protein for treatment response in genotype 4 Egyptian patients by regression analysis and decision tree analysis.

PATIENTS AND METHODS

The study included 263 chronic HCV Egyptian patients receiving peg-interferon and ribavirin therapy. Patients were classified into 3 groups; non responders (83patients), relapsers (76patients) and sustained virological responders (104 patients). Serum IL 28 B was performed, DNA was extracted and analyzed by direct sequencing of the SNP rs 12979860 of IL28B gene.

RESULTS

CT, CC and TT represented 56 %, 25 % and 19% of the patients, respectively. Absence of C allele (TT genotype) was significantly correlated with the early failure of response while CC was associated with sustained virological response. The decision tree showed that baseline alpha fetoprotein (AFP ≤ 2.68 ng/ml) was the variable of initial split (the strongest predictor of response) confirmed by regression analysis. Patients with TT genotype had the highest probability of failure of response.

CONCLUSIONS

Absence of the C allele was significantly associated with failure of response. The presence of C allele was associated with a favorable outcome. AFP is a strong baseline predictor of HCV treatment response. A decision tree model is useful for predicting the probability of response to therapy.

Factors affecting length of stay in the pediatric emergency department

BACKGROUND

A large volume of visits can cause an emergency department (ED) to become overcrowded, resulting in a longer length of stay (LOS). The objective of this study was to analyze factors affecting the LOS in the pediatric ED.

METHODS

Records of all visits to the pediatric ED of the study hospital, from July 1, 2006 to June 31, 2007, were retrospectively retrieved. Data were collected from the hospital's computerized records system. Eta-squared correlation ratio and Cramer's V test evaluated the associations between variables. Two-thirds of the database was randomized for the classification and regression tree (CART) model-building dataset, and one-third was used for the validation dataset.

RESULTS

A total of 29,035 patients visited the pediatric ED during the evaluation period. Of the total visits, 61.1% were due to complaints of fever. The mean LOS was 2.6 ± 4.67 hours, and 74.3% of visits had an LOS of shorter than 2 hours. The CART analysis selected five factors (waiting time for hospitalization, laboratory tests, door-to-physician time, gastrointestinal symptoms, and patient outcome) to produce a total of nine subgroups of patients. The mean LOS of the model-building dataset closely correlated with that of the validation dataset (r(2) = 0.999).

CONCLUSION

Patients who were waiting for hospitalization for less than 8 hours or were not admitted, those without any laboratory tests, those having door-to-physician time less than 60 minutes, and those without any gastrointestinal symptoms had the shortest LOS. Patients who waited for hospitalization for more than 16 hours had the longest LOS.

The assessment of data mining for the prediction of therapeutic outcome in 3719 Egyptian patients with chronic hepatitis C

INTRODUCTION

Decision-tree analysis; a core component of data mining analysis can build predictive models for the therapeutic outcome to antiviral therapy in chronic hepatitis C virus (HCV) patients.

AIM

To develop a prediction model for the end virological response (ETR) to pegylated interferon PEG-IFN plus ribavirin (RBV) therapy in chronic HCV patients using routine clinical, laboratory, and histopathological data.

PATIENTS AND METHODS

Retrospective initial data (19 attributes) from 3719 Egyptian patients with chronic HCV presumably genotype-4 was assigned to model building using the J48 decision tree-inducing algorithm (Weka implementation of C4.5). All patients received PEG-IFN plus RBV at Cairo-Fatemia Hospital, Cairo, Egypt in the context of the national treatment program. Factors predictive of ETR were explored and patients were classified into seven subgroups according to the different rates of ETR. The universality of the decision-tree model was subjected to a 10-fold cross-internal validation in addition to external validation using an independent dataset collected of 200 chronic HCV patients.

RESULTS

At week 48, overall ETR was 54% according to intention to treat protocol. The decision-tree model included AFP level (<8.08 ng/ml) which was associated with high probability of ETR (73%) followed by stages of fibrosis and Hb levels according to the patients' gender followed by the age of patients.

CONCLUSION

In a decision-tree model for the prediction for antiviral therapy in chronic HCV patients, AFP level was the initial split variable at a cutoff of 8.08 ng/ml. This model could represent a potential tool to identify patients' likelihood of response among difficult-to-treat presumably genotype-4 chronic HCV patients and could support clinical decisions regarding the proper selection of patients for therapy without imposing any additional costs.

Association of γ-glutamyl transferase (GGT) activity with treatment and clinical outcomes in chronic hepatitis C (HCV)

Increased γ-glutamyl transferase (GGT) activity is associated with liver injury and with mortality in the general population. Less is known about its association with chronic hepatitis C (HCV) outcomes. We examined GGT as a predictor of both virological response to treatment and long-term clinical outcomes in the Hepatitis C Anti-viral Treatment Against Cirrhosis Trial (HALT-C). HALT-C enrolled patients with advanced liver disease (Ishak fibrosis score ≥3) in two phases: a lead-in to establish lack of sustained viral response with full dose pegylated interferon (IFN) and ribavirin followed by a 3.5-year randomized trial with low-dose IFN. Low-dose IFN did not prevent liver disease progression, and patients were then followed for up to an additional 5 years off therapy. Analyses were performed for 1,319 patients who had GGT measured prior to initiation of treatment. Increases in risk with each increase in quintile of GGT (10-57, 58-89, 90-139, 140-230, 231-2,000 IU/L) were determined by logistic regression for treatment response or Cox regression for clinical outcomes. Baseline GGT was associated with male sex, nonwhite ethnicity, diabetes and insulin resistance, interleukin (IL)28B rs12979860 CT and TT genotypes, and numerous markers of liver disease injury and severity. In the lead-in phase, increasing GGT was strongly associated with diminished week 20 response, end of treatment response, and sustained virological response in both univariate and multivariate analyses controlling for factors known to be associated with treatment response (P < 0.0001). GGT was also associated with all clinical outcomes in univariate and multivariate analysis (P < 0.05) except for hepatocellular carcinoma (P = 0.46 in multivariate analysis).

CONCLUSION

GGT is an independent predictor of both virological response and clinical outcomes among patients with advanced liver disease due to HCV.

Lipid profile is associated with the incidence of cognitive dysfunction in viral cirrhotic patients: A data-mining analysis

AIM

  Cognitive dysfunction (CD) is frequently observed in cirrhotic patients. However, the biochemical profiles associated with CD remain unclear. We investigated the biochemical profiles associated with the incidence of CD in cirrhotic patients by using multivariate analyses, including a decision-tree algorithm.

METHODS

  In this study, 27 viral cirrhotic patients were enrolled. All subjects underwent neuropsychiatric tests; two or more abnormal results were defined as CD. A logistic regression model was used for multivariate stepwise analysis. A decision-tree algorithm was constructed, and the categorical differences based on the decision-tree model were analyzed by χ(2) -tests.

RESULTS

  Multivariate stepwise analysis showed the levels of total bilirubin, triglycerides and free fatty acids (FFA) as independent bioparameters associated with the incidence of CD in cirrhotic patients. The decision-tree algorithm showed that among patients with FFA of 514 mEq/L or more, 77.8% had CD. Meanwhile, among patients with FFA of less than 514 mEq/L and triglycerides of 106 mg/dL or more, 20.0% had CD. The sensitivity, specificity and accuracy for the incidence of CD using the lipid profile (FFA >514 mEq/L or triglycerides <106 mg/dL) were 85.7% (12/14), 61.5% (8/13) and 74.1% (20/27), respectively.

CONCLUSION

  The levels of total bilirubin, FFA and triglycerides are independently associated with the incidence of CD in cirrhotic patients. In addition, a decision-tree algorithm revealed that FFA of more than 514 mEq/L or triglycerides of less than 106 mg/dL is a profile associated with the incidence of CD. Thus, this lipid profile could be a possible screening bioparameter for CD in cirrhotic patients.

Model incorporating the ITPA genotype identifies patients at high risk of anemia and treatment failure with pegylated-interferon plus ribavirin therapy for chronic hepatitis C

This study aimed to develop a model for predicting anemia using the inosine triphosphatase (ITPA) genotype and to evaluate its relationship with treatment outcome. Patients with genotype 1b chronic hepatitis C (n = 446) treated with peg-interferon alpha and ribavirin (RBV) for 48 weeks were genotyped for the ITPA (rs1127354) and IL28B (rs8099917) genes. Data mining analysis generated a predictive model for anemia (hemoglobin (Hb) concentration <10 g/dl); the CC genotype of ITPA, baseline Hb <14.0 g/dl, and low creatinine clearance (CLcr) were predictors of anemia. The incidence of anemia was highest in patients with Hb <14.0 g/dl and CLcr <90 ml/min (76%), followed by Hb <14.0 g/dl and ITPA CC (57%). Patients with Hb ≥ 14.0 g/dl and ITPA AA/CA had the lowest incidence of anemia (17%). Patients with two predictors (high-risk) had a higher incidence of anemia than the others (64% vs. 28%, P < 0.0001). At baseline, the IL28B genotype was a predictor of a sustained virological response [adjusted odds ratio 9.88 (95% confidence interval 5.01-19.48), P < 0.0001]. In patients who achieved an early virological response, the IL28B genotype was not associated with a sustained virological response, while a high risk of anemia was a significant negative predictor of a sustained virological response [0.47 (0.24-0.91), P = 0.026]. For high-risk patients with an early virological response, giving >80% of the planned RBV dose increased sustained virological responses by 24%. In conclusion, a predictive model incorporating the ITPA genotype could identify patients with a high risk of anemia and reduced probability of sustained virological response.

Fish to meat intake ratio and cooking oils are associated with hepatitis C virus carriers with persistently normal alanine aminotransferase levels

AIM

  Dietary habits are involved in the development of chronic inflammation; however, the impact of dietary profiles of hepatitis C virus carriers with persistently normal alanine transaminase levels (HCV-PNALT) remains unclear. The decision-tree algorithm is a data-mining statistical technique, which uncovers meaningful profiles of factors from a data collection. We aimed to investigate dietary profiles associated with HCV-PNALT using a decision-tree algorithm.

METHODS

  Twenty-seven HCV-PNALT and 41 patients with chronic hepatitis C were enrolled in this study. Dietary habit was assessed using a validated semiquantitative food frequency questionnaire. A decision-tree algorithm was created by dietary variables, and was evaluated by area under the receiver operating characteristic curve analysis (AUROC).

RESULTS

  In multivariate analysis, fish to meat ratio, dairy product and cooking oils were identified as independent variables associated with HCV-PNALT. The decision-tree algorithm was created with two variables: a fish to meat ratio and cooking oils/ideal bodyweight. When subjects showed a fish to meat ratio of 1.24 or more, 68.8% of the subjects were HCV-PNALT. On the other hand, 11.5% of the subjects were HCV-PNALT when subjects showed a fish to meat ratio of less than 1.24 and cooking oil/ideal bodyweight of less than 0.23 g/kg. The difference in the proportion of HCV-PNALT between these groups are significant (odds ratio 16.87, 95% CI 3.40-83.67, P = 0.0005). Fivefold cross-validation of the decision-tree algorithm showed an AUROC of 0.6947 (95% CI 0.5656-0.8238, P = 0.0067).

CONCLUSION

  The decision-tree algorithm disclosed that fish to meat ratio and cooking oil/ideal bodyweight were associated with HCV-PNALT.

IL28B polymorphism is associated with fatty change in the liver of chronic hepatitis C patients

BACKGROUND

Several single nucleotide polymorphisms (SNPs) within the interleukin 28B (IL28B) locus are associated with sustained viral response in chronic hepatitis C (HCV) patients who were treated with pegylated interferon (PEG-IFN) plus ribavirin (RBV) combination therapy. Recently, an association between γ-GTP level and IL28B genotype was identified. In this study, the relationship between IL28B genotype and liver steatosis was analyzed.

METHODS

One hundred fifty-three patients who underwent liver biopsy before PEG-IFN plus RBV combination therapy were enrolled. The level of liver steatosis was measured using a BIOREVO BZ-9000 microscope, and the proportion of fatty change and clear cell change were calculated using Dynamic cell count BZ-H1C software. IL28B SNP genotype (rs8099917) was determined using the Invader Assay.

RESULTS

Vesicular change was significantly associated with body mass index (BMI), HCV RNA titer, serum aspartate aminotransferase, γ-GTP, IL28B genotype and liver fibrosis level (P < 0.05). Clear cell change was significantly associated with serum aspartate aminotransferase, γ-GTP and IL28B genotype by univariate logistic regression analysis (P < 0.05). Under multiple logistic regression, IL28B genotype (OR(adj) = 8.158; 95% CI 2.412-27.589), liver fibrosis (OR(adj) = 2.541; 95% CI 1.040-6.207) and BMI (OR(adj) = 1.147; 95% CI 1.011-1.301) were significant independent factors for vesicular change and IL28B genotype (OR(adj) = 3.000; 95% CI 1.282-7.019) for clear cell change.

CONCLUSION

In this study, a new quantitative method to objectively evaluate hepatic steatosis was described. IL28B genotypes were significantly associated with both vesicular and clear cell changes of livers in chronic hepatitis C patients.

LDLr genotype modifies the impact of IL28B on HCV viral kinetics after the first weeks of treatment with PEG-IFN/RBV in HIV/HCV patients

OBJECTIVE

To evaluate the effect of low-density lipoprotein receptor (LDLr) and IL28B genotypes on hepatitis C virus (HCV) viral kinetics in the first 4 weeks of treatment with pegylated-interferon (PEG-IFN)/ribavirin (RBV) in HIV patients co-infected with HCV genotype 1.

METHODS

HIV patients co-infected with HCV genotype 1 and naïve to PEG-IFN/RBV treatment were enrolled in a prospective study. HCV RNA viral loads were measured at baseline and at weeks 1, 2 and 4 after start of therapy. Differences in viral load decline were evaluated for IL28B (CC versus non-CC) and LDLr (CC versus non-CC) genotypes between baseline and weeks 1, 2 and 4. Additionally, the effect of LDLr genotype on HCV viral decline in IL28B CC genotype patients (CC/CC versus CC/non-CC) was analyzed.

RESULTS

Eighty-seven HIV/HCV genotype 1 co-infected patients were included in the study. Patients carrying the LDLr-CC or IL28B-CC genotypes showed greater HCV viral decline than those with IL28B non-CC or LDLr non-CC genotypes at every time-point analyzed. CC/CC patients had higher rapid virological response (RVR) rates than CC/non-CC patients (41.2 versus 13.3%; P < 0.001). Moreover, at all time points, the CC/CC pattern was associated with greater HCV viral decline than the CC/non-CC genotype (week 1: 1.18 ± 0.51 versus 0.31 ± 0.29, P = 0.041; week 2: 1.55 ± 0.81 versus 0.93 ± 0.73, P = 0.032; week 4: 2.23 ± 1.1 versus 1.5 ± 0.94, P = 0.039).

CONCLUSION

The LDLr genotype impacts on viral kinetics during the first days of starting treatment with PEG-IFN/RBV in HIV/HCV genotype 1 co-infected patients, and modifies the impact of IL28B on HCV viral decay.

Data mining model using simple and readily available factors could identify patients at high risk for hepatocellular carcinoma in chronic hepatitis C

BACKGROUND & AIMS

Assessment of the risk of hepatocellular carcinoma (HCC) development is essential for formulating personalized surveillance or antiviral treatment plan for chronic hepatitis C. We aimed to build a simple model for the identification of patients at high risk of developing HCC.

METHODS

Chronic hepatitis C patients followed for at least 5 years (n=1003) were analyzed by data mining to build a predictive model for HCC development. The model was externally validated using a cohort of 1072 patients (472 with sustained virological response (SVR) and 600 with nonSVR to PEG-interferon plus ribavirin therapy).

RESULTS

On the basis of factors such as age, platelet, albumin, and aspartate aminotransferase, the HCC risk prediction model identified subgroups with high-, intermediate-, and low-risk of HCC with a 5-year HCC development rate of 20.9%, 6.3-7.3%, and 0-1.5%, respectively. The reproducibility of the model was confirmed through external validation (r(2)=0.981). The 10-year HCC development rate was also significantly higher in the high-and intermediate-risk group than in the low-risk group (24.5% vs. 4.8%; p<0.0001). In the high-and intermediate-risk group, the incidence of HCC development was significantly reduced in patients with SVR compared to those with nonSVR (5-year rate, 9.5% vs. 4.5%; p=0.040).

CONCLUSIONS

The HCC risk prediction model uses simple and readily available factors and identifies patients at a high risk of HCC development. The model allows physicians to identify patients requiring HCC surveillance and those who benefit from IFN therapy to prevent HCC.

Toward the establishment of a prediction system for the personalized treatment of chronic hepatitis C

BACKGROUND

Although several direct-acting antivirals (DAAs) are now available, the therapy regimen for chronic hepatitis C will continue to include pegylated interferon and ribavirin for the foreseeable future. Despite their improved rate of sustained virological response (SVR), DAAs pose increased risks of side effects and selection for antiviral resistance. Not all patients require DAA to achieve SVR, whereas others are unlikely to respond even to triple therapy. Therefore, a personalized approach to candidate selection is necessary.

METHODS

In this retrospective study, data from 640 Japanese patients who were treated for chronic hepatitis C genotype 1, 2, or 3 with pegylated interferon plus ribavirin combination therapy was compiled to identify robust pretreatment predictive factors for SVR.

RESULTS

A logistic regression model for personalized therapy was developed based on age, viral genotype, initial viral load, aspartate aminotransferase/alanine aminotransferase ratio, α-fetoprotein levels, and IL28B single-nucleotide polymorphism genotype. The area under the receiver-operating characteristic curve (AUC) was 0.85. The mean AUC following 10 rounds of 10-fold cross validation was 0.82, with a true positive rate of 78.2%.

CONCLUSIONS

A personalized approach to therapy may better inform treatment decisions and reduce incidence of side effects and antiviral resistance.

Treatment of chronic hepatitis C genotype 1 patients at an academic center in Europe involved in prospective, controlled trials: is there a selection bias?

Pegylated interferon-alpha2/ribavirin (peg-IFN/RBV) is the standard of care (SOC) for patients with chronic hepatitis C (CHC) infection. Currently, direct-acting antiviral agents (DAAs) are evaluated in clinical trials. The aim of this study was to compare baseline characteristics and sustained virologic response (SVR) rates in patients included in clinical trials to those receiving SOC. Medical records of all 503 treatment-naïve patients with CHC, genotype (GT) 1, referred over a 4-year period (January 2006-December 2009) were reviewed. Only 310 of 503 (62%) patients received antiviral therapy, 141 were enrolled in randomized, controlled trials ("study patients"; 101 in DAA studies), and 169 received SOC. At baseline, viral load and platelet count were higher and bilirubin was lower in study patients than in SOC patients. History of psychiatric disorders was more common in SOC patients (43 [25%] versus study patients with 18 [13%]; P < 0.01). Liver biopsy was obtained in 98% of study patients, but only in 59% of SOC patients. Twenty-nine (21%) and 40 (40%) study and SOC patients, respectively, had advanced fibrosis (F3/4; P = 0.001). By intent-to-treat analysis, SVR rates were higher in DAAs (64%; 95% confidence interval [CI]: 53.4-74.4) than in SOC patients (46%; 95% CI: 37.9-53.7; P < 0.01), but not different when calculated on a treated-per-protocol (TPP) basis. Interleukin (IL)28B GT was equally distributed in both cohorts. By chance, more patients treated with IFN/RBV had rs12979860 C/C-GT (up to 44%) than DAA-treated patients. If analyzed according to the IL28B polymorphism, TPP SVR rates did not reach statistically significant differences among study and SOC patients.

CONCLUSIONS

Baseline characteristics slightly favored study patients, but IL28B GT and treatment adherence were the most important factors determining outcome. Thus, the applicability of the results of controlled studies has to be tested in a "real-world" setting.

Sequences in the interferon sensitivity-determining region and core region of hepatitis C virus impact pretreatment prediction of response to PEG-interferon plus ribavirin: data mining analysis

The aim of the present study was to clarify the significance of viral factors for pretreatment prediction of sustained virological response to pegylated-interferon (PEG-IFN) plus ribavirin (RBV) therapy for chronic hepatitis C using data mining analysis. Substitutions in the IFN sensitivity-determining region (ISDR) and at position 70 of the HCV core region (Core70) were determined in 505 patients with genotype 1b chronic hepatitis C treated with PEG-IFN plus RBV. Data mining analysis was used to build a predictive model of sustained virological response in patients selected randomly (n = 304). The reproducibility of the model was validated in the remaining 201 patients. Substitutions in ISDR (odds ratio = 9.92, P < 0.0001) and Core70 (odds ratio = 1.92, P = 0.01) predicted sustained virological response independent of other covariates. The decision-tree model revealed that the rate of sustained virological response was highest (83%) in patients with two or more substitutions in ISDR. The overall rate of sustained virological response was 44% in patients with a low number of substitutions in ISDR (0-1) but was 83% in selected subgroups of younger patients (<60 years), wild-type sequence at Core70, and higher level of low-density lipoprotein cholesterol (LDL-C) (≥ 120 mg/dl). Reproducibility of the model was validated (r(2) = 0.94, P < 0.001). In conclusion, substitutions in ISDR and Core70 of HCV are significant predictors of response to PEG-IFN plus RBV therapy. A decision-tree model that includes these viral factors as predictors could identify patients with a high probability of sustained virological response.

Beneficial IL28B genotype associated with lower frequency of hepatic steatosis in patients with chronic hepatitis C

BACKGROUND & AIMS

IL28B polymorphisms have been associated with both treatment induced and spontaneous clearance of hepatitis C virus (HCV). We previously found that LDL cholesterol levels were higher in chronic hepatitis C (CHC) patients with the CC genotype at the rs12979860 polymorphism, located proximal to the IL28 gene. Here we analyzed the association of steatosis with IL28B genotype in treatment naïve patients with CHC.

METHODS

Two independent cohorts of 145 genotype 1 infected patients from an antifibrotic study and 180 genotype 1 patients from Duke were analyzed for the presence and severity of steatosis in relation to the rs12979860 polymorphism at the IL28B locus. TaqMan assay based genotyping classified three groups CC, CT, and TT.

RESULTS

CC genotype was associated with a lower prevalence of steatosis. In the antifibrotic study, steatosis was found in 47.6% (50/105) of IL28B non-CC vs. 22.5% (9/40; p=0.008) in CC patients. Similarly, steatosis was found in 67.4% (89/132) of non-CC patients compared to only 39.6% (19/48; p=0.001) of CC patients in the Duke cohort.

CONCLUSIONS

IL28B CC genotype is associated with less pronounced disturbances of lipid metabolism, as reflected both in serum lipoprotein levels and hepatic steatosis, in HCV infection.

Prediction of severe acute pancreatitis using classification and regression tree analysis

BACKGROUND

The available prognostic scoring systems for acute pancreatitis have limitations that restrict their clinical value.

AIMS

To develop a decision model based on classification and regression tree (CART) analysis for the prediction of severe acute pancreatitis (SAP).

METHODS

A total of 420 patients with acute pancreatitis were enrolled. Study participants were randomly assigned to the training sample and test sample in a 2:1 ratio. First, univariate analysis and logistic regression analysis were used to identify predictors associated with SAP in the training sample. Then, CART analysis was carried out to develop a simple tree model for the prediction of SAP. A receiver operating characteristic (ROC) curve was constructed in order to assess the performance of the model. The prediction model was then applied to the test sample.

RESULTS

Four variables (systemic inflammatory response syndrome [SIRS], pleural effusion, serum calcium, and blood urea nitrogen [BUN]) were identified as important predictors of SAP by logistic regression analysis. A tree model (which consisted of pleural effusion, serum calcium, and BUN) that was developed by CART analysis was able to early identify among cohorts at high (79.03%) and low (7.80%) risk of developing SAP. The area under the ROC curve of the tree model was higher than that of the APACHE II score (0.84 vs. 0.68; P < 0.001). The predicted accuracy of the tree model was validated in the test sample with an area under the ROC curve of 0.86.

CONCLUSIONS

A decision tree model that consists of pleural effusion, serum calcium, and BUN may be useful for the prediction of SAP.

Pretreatment prediction of anemia progression by pegylated interferon alpha-2b plus ribavirin combination therapy in chronic hepatitis C infection: decision-tree analysis

BACKGROUND

This study aimed to develop a model to predict the development of severe anemia during pegylated interferon alpha-2b plus ribavirin combination therapy.

METHODS

Data were collected from 1081 genotype 1b chronic hepatitis C patients who were treated at 6 hospitals in Japan. These patients were randomly assigned to a model-building group (n = 691) or an internal validation group (n = 390). Factors predictive of severe anemia (hemoglobin, Hb < 8.5 g/dl) were explored using data-mining analysis.

RESULTS

Hb values at baseline, creatinine clearance (Ccr), and an Hb concentration decline by 2 g/dl at week 2 were used to build a decision-tree model, in which the patients were divided into 5 subgroups based on variable rates of severe anemia ranging from 0.4 to 11.8%. The reproducibility of the model was confirmed by the internal validation group (r² = 0.96). The probability of severe anemia was high in patients whose Hb value was <14 g/dl before treatment (6.5%), especially (a) in those whose Ccr was <80 ml/min (11.8%) and (b) those whose Ccr was ≥ 80 ml/min but whose Hb concentration decline at week 2 was ≥ 2 g/dl (11.5%). The probability of severe anemia was low in the other patients (0.4-2.5%).

CONCLUSIONS

The decision-tree model that included Hb values at baseline, Ccr, and an Hb concentration decline by 2 g/dl at week 2 was useful for predicting the probability of severe anemia, and has the potential to support clinical decisions regarding early dose reduction of ribavirin.

Redefining baseline demographics: the role of genetic testing in hepatitis C virus infection

The current standard of care for hepatitis C virus (HCV) infection is pegylated interferon and ribavirin. Unfortunately, treatment cures at best only 40% to 50% of patients infected with genotype 1 HCV, the most common HCV genotype in Western countries. Treatment is also expensive and is often poorly tolerated. Therefore, the identification of patients most likely to benefit from treatment is clinically important. Genome-wide association studies have recently identified genetic variants, most notably IL28B and ITPA, which will enhance the ability of clinicians to personalize antiviral therapy for HCV infection.

Cholesterol and chronic hepatitis C virus infection

Cholesterol is an essential molecule for the life cycle of the hepatitis C virus (HCV). This review focuses on the roles of cholesterol in HCV infection and introduces HCV events related to cholesterol metabolism and applications for cholesterol metabolism as a therapeutic target. HCV appears to alter host lipid metabolism into its preferable state, which is clinically recognized as steatosis and hypocholesterolemia. While hepatic fatty acid and triglyceride syntheses are upregulated in chronic hepatitis C patients, no direct evidence of increased hepatic de novo cholesterol biosynthesis has been obtained. Impaired VLDL secretion from hepatocytes is suggested to increase intracellular cholesterol concentrations, which may lead to hypocholesterolemia. Clinically, lower serum cholesterol levels are associated with lower rates of sustained virological responses (SVR) to pegylated-interferon plus ribavirin therapy, but the reason remains unclear. Clinical trials targeting HMG-CoA reductase, the rate-limiting enzyme in the cholesterol biosynthetic pathway, are being conducted using statins. Anti-HCV actions by statins appear to be caused by the inhibition of geranylgeranyl pyrophosphate synthesis rather than their cholesterol lowering effects. Other compounds that block various steps of cholesterol metabolic pathways have also been studied to develop new strategies for the complete eradication of this virus.

Data mining reveals complex interactions of risk factors and clinical feature profiling associated with the staging of non-hepatitis B virus/non-hepatitis C virus-related hepatocellular carcinoma

AIM

  Non-hepatitis B virus/non-hepatitis C virus-related hepatocellular carcinoma (NBNC-HCC) is often detected at an advanced stage, and the pathology associated with the staging of NBNC-HCC remains unclear. Data mining is a set of statistical techniques which uncovers interactions and meaningful patterns of factors from a large data collection. The aims of this study were to reveal complex interactions of the risk factors and clinical feature profiling associated with the staging of NBNC-HCC using data mining techniques.

METHODS

  A database was created from 663 patients with NBNC-HCC at 20 institutions. The Milan criteria were used as staging of HCC. Complex associations of variables and clinical feature profiling with the Milan criteria were analyzed by graphical modeling and decision tree algorithm methods, respectively.

RESULTS

  Graphical modeling identified six factors independently associated with the Milan criteria: diagnostic year of HCC; diagnosis of liver cirrhosis; serum aspartate aminotransferase (AST); alanine aminotransferase (ALT); α-fetoprotein (AFP); and des-γ-carboxy prothrombin (DCP) levels. The decision trees were created with five variables to classify six groups of patients. Sixty-nine percent of the patients were within the Milan criteria, when patients showed an AFP level of 200 ng/mL or less, diagnosis of liver cirrhosis and an AST level of less than 93 IU/mL. On the other hand, 18% of the patients were within the Milan criteria, when patients showed an AFP level of more than 200 ng/mL and ALT level of 20 IU/mL or more.

CONCLUSION

  Data mining disclosed complex interactions of the risk factors and clinical feature profiling associated with the staging of NBNC-HCC.

Factors predictive of sustained virological response following 72 weeks of combination therapy for genotype 1b hepatitis C

BACKGROUND

Treatment of genotype 1b chronic hepatitis C virus (HCV) infection has been improved by extending peg-interferon plus ribavirin combination therapy to 72 weeks, but predictive factors are needed to identify those patients who are likely to respond to long-term therapy.

METHODS

We analyzed amino acid (aa) substitutions in the core protein and the interferon sensitivity determining region (ISDR) of nonstructural protein (NS) 5A in 840 genotype 1b chronic hepatitis C patients with high viral load. We used logistic regression and classification and regression tree (CART) analysis to identify predictive factors for sustained virological response (SVR) for patients undergoing 72 weeks of treatment.

RESULTS

When patients were separately analyzed by treatment duration using multivariate logistic regression, several factors, including sex, age, viral load, and core aa70 and ISDR substitutions (P = 0.0003, P = 0.02, P = 0.01, P = 0.0001, and P = 0.0004, respectively) were significant predictive factors for SVR with 48 weeks of treatment, whereas age, previous interferon treatment history, and ISDR substitutions (P = 0.03, P = 0.01, and P = 0.02, respectively) were the only significant predictive factors with 72 weeks of treatment. Using CART analysis, a decision tree was generated that identified age, cholesterol, sex, treatment length, and aa70 and ISDR substitutions as the most important predictive factors. The CART model had a sensitivity of 69.2% and specificity of 60%, with a positive predictive value of 68.4%.

CONCLUSIONS

Complementary statistical and data mining approaches were used to identify a subgroup of patients likely to benefit from 72 weeks of therapy.

Pre-treatment prediction of response to pegylated-interferon plus ribavirin for chronic hepatitis C using genetic polymorphism in IL28B and viral factors

BACKGROUND & AIMS

Pegylated interferon and ribavirin (PEG-IFN/RBV) therapy for chronic hepatitis C virus (HCV) genotype 1 infection is effective in 50% of patients. Recent studies revealed an association between the IL28B genotype and treatment response. We aimed to develop a model for the pre-treatment prediction of response using host and viral factors.

METHODS

Data were collected from 496 patients with HCV genotype 1 treated with PEG-IFN/RBV at five hospitals and universities in Japan. IL28B genotype and mutations in the core and IFN sensitivity determining region (ISDR) of HCV were analyzed to predict response to therapy. The decision model was generated by data mining analysis.

RESULTS

The IL28B polymorphism correlated with early virological response and predicted null virological response (NVR) (odds ratio=20.83, p<0.0001) and sustained virological response (SVR) (odds ratio=7.41, p<0.0001) independent of other covariates. Mutations in the ISDR predicted relapse and SVR independent of IL28B. The decision model revealed that patients with the minor IL28B allele and low platelet counts had the highest NVR (84%) and lowest SVR (7%), whereas those with the major IL28B allele and mutations in the ISDR or high platelet counts had the lowest NVR (0-17%) and highest SVR (61-90%). The model had high reproducibility and predicted SVR with 78% specificity and 70% sensitivity.

CONCLUSIONS

The IL28B polymorphism and mutations in the ISDR of HCV were significant pre-treatment predictors of response to PEG-IFN/RBV. The decision model, including these host and viral factors may support selection of optimum treatment strategy for individual patients.

Pretreatment prediction of response to peginterferon plus ribavirin therapy in genotype 1 chronic hepatitis C using data mining analysis

BACKGROUND

This study aimed to develop a model for the pre-treatment prediction of sustained virological response (SVR) to peg-interferon plus ribavirin therapy in chronic hepatitis C.

METHODS

Data from 800 genotype 1b chronic hepatitis C patients with high viral load (>100,000 IU/ml) treated by peg-interferon plus ribavirin at 6 hospitals in Japan were randomly assigned to a model building (n = 506) or an internal validation (n = 294). Data from 524 patients treated at 29 hospitals in Japan were used for an external validation. Factors predictive of SVR were explored using data mining analysis.

RESULTS

Age (<50 years), alpha-fetoprotein (AFP) (<8 ng/mL), platelet count (≥ 120 × 10(9)/l), gamma-glutamyltransferase (GGT) (<40 IU/l), and male gender were used to build the decision tree model, which divided patients into 7 subgroups with variable rates of SVR ranging from 22 to 77%. The reproducibility of the model was confirmed by the internal and external validation (r (2) = 0.92 and 0.93, respectively). When reconstructed into 3 groups, the rate of SVR was 75% for the high probability group, 44% for the intermediate probability group and 23% for the low probability group. Poor adherence to drugs lowered the rate of SVR in the low probability group, but not in the high probability group.

CONCLUSIONS

A decision tree model that includes age, gender, AFP, platelet counts, and GGT is useful for predicting the probability of response to therapy with peg-interferon plus ribavirin and has the potential to support clinical decisions regarding the selection of patients for therapy.

Prediction of large esophageal varices in cirrhotic patients using classification and regression tree analysis

OBJECTIVES

Recent guidelines recommend that all cirrhotic patients should undergo endoscopic screening for esophageal varices. That identifying cirrhotic patients with esophageal varices by noninvasive predictors would allow for the restriction of the performance of endoscopy to patients with a high risk of having varices. This study aimed to develop a decision model based on classification and regression tree analysis for the prediction of large esophageal varices in cirrhotic patients.

METHODS

309 cirrhotic patients (training sample, 187 patients; test sample 122 patients) were included. Within the training sample, the classification and regression tree analysis was used to identify predictors and prediction model of large esophageal varices. The prediction model was then further evaluated in the test sample and different Child-Pugh classes.

RESULTS

The prevalence of large esophageal varices in cirrhotic patients was 50.8%. A tree model that was consisted of spleen width, portal vein diameter and prothrombin time was developed by classification and regression tree analysis achieved a diagnostic accuracy of 84% for prediction of large esophageal varices. When reconstructed into two groups, the rate of varices was 83.2% for high-risk group and 15.2% for low-risk group. Accuracy of the tree model was maintained in the test sample and different Child-Pugh classes.

CONCLUSIONS

A decision tree model that consists of spleen width, portal vein diameter and prothrombin time may be useful for prediction of large esophageal varices in cirrhotic patients.

Predictors of virological response to a combination therapy with pegylated interferon plus ribavirin including virus and host factors

A combination therapy with pegylated interferon (PEG-IFN) plus ribavirin (RBV) has made it possible to achieve a sustained virological response (SVR) of 50% in refractory cases with genotype 1b and high levels of plasma HCVRNA. Several factors including virus mutation and host factors such as age, gender, fibrosis of the liver, lipid metabolism, innate immunity, and single nucleotide polymorphism (SNPs) are reported to be correlated to therapeutic effects. However, it is difficult to determine which factor is the most important predictor for an individual patient. Data mining analysis is useful for combining all these together to predict the therapeutic effects. It is important to analyze blood tests and to predict therapeutic effects prior to initiating treatment. Since new anti-HCV agents are under development, it will be necessary in the future to select the patients who have a high possibility of achieving SVR if treatment is performed with standard regimen.