Meta-learning algorithm development to predict outcomes in patients with hepatitis C virus-related hepatocellular carcinoma.

BACKGROUND AND STUDY AIMS: Prediction of prognosis and treatment outcomes for patients with hepatocellular carcinoma (HCC) is complex for most patients. Machine learning predictive analysis can be used to explore the rich information in electronic health records to discover hidden patterns and relationships. We aimed to develop a noninvasive algorithm for predicting outcome treatment options for patients with HCC. PATIENTS AND METHODS: This cross-sectional study included 1298 patients with Hepatitis C virus-related HCC attending an HCC multidisciplinary clinic, Kasr Al-Aini Hospital, Cairo University, between 2009 and 2016. Using machine learning analysis, we constructed Reduced Error Pruning (REP) decision tree algorithms and applied Auto-WEKA to select the best classifier out of 39 algorithms. RESULTS: The REP-tree algorithm predicted HCC management outcomes with a recall (sensitivity) of 0.658 and a precision (specificity) of 0.653 using only routine data. 854 (65.8%) instances were correctly identified, and 444 (34.2%) instances were incorrectly classified. Out of 31 attributes, liver decompensation was selected by REP-tree as the best predictor of HCC outcome (root node). With Auto-WEKA, the random subspace classifier was chosen as the best predictive algorithm with a recall (sensitivity) of 0.750 and a precision (specificity) of 0.75. There were 974 (75%) correctly classified instances and 324 (25%) incorrectly classified instances, which was better than REP-tree. CONCLUSION: Machine learning analysis explores data to discover hidden patterns and trends and enables the development of models to predict HCC treatment outcomes utilizing simple laboratory data. The random subspace classifier predicted the outcome more accurately than REP-tree.

Validation of a machine learning approach using FIB-4 and APRI scores assessed by the metavir scoring system: A cohort study.

BACKGROUND AND STUDY AIM: The study aim was to improve and validate the accuracy of the fibrosis-4 (FIB-4) and aspartate aminotransferase-to-platelet ratio index (APRI) scores for use in a potential machine-learning (ML) method that accurately predicts the extent of liver fibrosis. PATIENTS AND METHODS: This retrospective multicenter study included 69,106 patients with chronic hepatitis C planned for antiviral therapy from January 2010-December 2014 with liver biopsy results. FIB-4 and APRI scores were calculated and their performance for predicting significant liver fibrosis (F3-F4) assessed against the Metavir scoring system. ML was used for feature selection and reduction to identify the most relevant attributes (CfsSubseteval/best first) for prediction. RESULTS: In this study, 57,492 (83.2%) patients were F0-F2, and 11,615 (16.8%) patients were F3-F4. The revalidation of FIB-4 and APRI showed lower accuracy and higher disagreement with the biopsy results, with AUCs of 0.68 and 0.58, respectively. FIB-4 diagnosed fewer (14%) F3-F4 patients, and the high specificity and negative predictive values of FIB-4 and APRI reflected the low prevalence of F3-F4 in the study population. Out of 15 attributes, age (>35 years), AFP (>6.5 ng/ml), and platelet count (<150,000/mm3) were the most relevant risk attributes, and patients with one or more of these risk factors were likely to be F3-F4, with a classification accuracy of ≤ 92% and receiver operating characteristics area of 0.74. CONCLUSION: FIB-4 and APRI scores were not very accurate and missed diagnosing most of the F3-F4 patients. ML implementation improved medical decisions and minimized the required clinical data to three risk factors.

Acoustic radiation forced impulse-based splenic prediction model using data mining for the noninvasive prediction of esophageal varices in hepatitis C virus advanced fibrosis.

BACKGROUND: Esophageal varices (EV) are serious complications of hepatitis C virus (HCV) cirrhosis. Endoscopic screening is expensive, invasive, and uncomfortable. Accordingly, noninvasive methods are mandatory to avoid unnecessary endoscopy. Acoustic radiation forced impulse (ARFI) imaging using point shear wave elastography as demonstrated with virtual touch quantification is a possible noninvasive EV predictor. We aimed to validate the reliability of liver stiffness (LS) and spleen stiffness (SS) by an ARFI-based study together with other noninvasive parameters for EV prediction in HCV patients. Also, we aimed to evaluate the diagnostic performance of a new simple prediction model (incorporating SS) using data mining analysis. PATIENTS AND METHODS: This cross-sectional study included 200 HCV patients with advanced fibrosis. Labs, endoscopic, ultrasonographic, LS, and SS data were collected. Their accuracy in diagnosing EV was assessed and a data mining analysis was carried out. RESULTS: Ninety patients (22/46% of F3/F4 patients) had EV (39/30/18/3 patients had grade I/II/III/IV, respectively). LS and SS by ARFI showed high significance in differentiating not only patients with/without EV (P = 0.000 for both) but also correlated with the grading of varices (R = 0.31 and 0.45, respectively; P = 0.000 for both). Spleen longitudinal diameter (SD), splenic vein diameter (SVD), platelets to spleen diameter ratio, LOK index, and FIB-4 score were the best ultrasonographic and biochemical predictors for the prediction of EV [area under receiver operating characteristic (AUROC) 0.79, 0.76, 0.76, 0.74, and 0.71, respectively]. SS (using ARFI) had better diagnostic performance than LS for the prediction of EV (AUROC = 0.76 and 0.70, respectively). The diagnostic performance increased using data mining to construct a simple prediction model: high probability for EV if [(SD cm) × 0.17 + (SVD mm) × 0.06 + (SS) × 0.97] more than 6.35 with AUROC 0.85. CONCLUSION: SS by ARFI represents a reliable noninvasive tool for the prediction of EV in HCV patients, especially when incorporated into a new data mining-based prediction model.

Diagnostic accuracy of acoustic radiation force impulse elastography (ARFI) in comparison to other non-invasive modalities in staging of liver fibrosis in chronic HCV patients: single-center experience.

PURPOSE: To evaluate the reliability of ARFI elastography for liver fibrosis staging and compare it to other non-invasive assessment of hepatic fibrosis (FIB-4 and APRI) in chronic HCV (CHC) patients. METHODS: A single-center, prospective study included 2103 CHC patients. Liver stiffness (LS) was evaluated by TE and ARFI elastography. FIB-4 and APRI were calculated. The area under the receiver-operating characteristic curve (AUROCs) was used to assess the diagnostic performance of ARFI elastography for staging of liver fibrosis using TE as a reference standard. RESULTS: The best cut off values of ARFI elastography for diagnosis of ≥ F2, ≥ F3and F4 were 1.36 m/s, 1.45 m/s, and 1.7 m/s with AUROCs of 0.89, 0.94 and 0.95, respectively. ARFI elastography cut offs are lower in patients with normal ALT level compared to those with ALT level (1.1-< 3 ULN) and those with ALT level ≥ 3ULN (1.35 m/s vs 1.39 m/s vs 1.54 for F ≥ 2, 1.44 m/s vs 1.58 m/s vs 1.6 m/s for F3, 1.69 m/s, 1.84 m/s, 1.86 m/s for F4). FIB-4 (0.82-0.86) and APRI (0.78-0.82) yielded lower AUC in prediction of significant fibrosis and cirrhosis than ARFI elastography (0.89-0.95). CONCLUSION: ARFI elastography is a reliable method for non-invasive staging of liver fibrosis in CHC patients when compared to TE with a good diagnostic performance comparable to FIB-4 and APRI scores for the prediction of significant fibrosis and cirrhosis.

Data Mining and Machine Learning Algorithms Using IL28B Genotype and Biochemical Markers Best Predicted Advanced Liver Fibrosis in Chronic Hepatitis C.

IL28B single nucleotide polymorphism (rs12979860) is an etiology-independent predictor of hepatitis C virus (HCV)-related hepatic fibrosis. Data mining is a method of predictive analysis which can explore tremendous volumes of information from health records to discover hidden patterns and relationships. The current study aims to evaluate and compare the prediction accuracy of scoring system like aspartate aminotransferase-to-platelet ratio index (APRI) and fibrosis-4 (FIB-4) index versus data mining for the prediction of HCV-related advanced fibrosis. This retrospective study included 427 patients with chronic hepatitis C. We used data mining analysis to construct a decision tree by reduced error (REP) technique, followed by Auto-WEKA tool to select the best classifier out of 39 algorithms to predict advanced fibrosis. APRI and FIB-4 had sensitivity-specificity parameters of 0.523-0.831 and 0.415-0.917, respectively. REPTree algorithm was able to predict advanced fibrosis with sensitivity of 0.749, specificity of 0.729, and receiver operating characteristic (ROC) area of 0.796. Out of the 16 attributes, IL28B genotype was selected by the REPTree as the best predictor for advanced fibrosis. Using Auto-WEKA, the multilayer perceptron (MLP) neural model was selected as the best predictive algorithm with sensitivity of 0.825, specificity of 0.811, and ROC area of 0.880. Thus, MLP is better than APRI, FIB-4, and REPTree for predicting advanced fibrosis for patients with chronic hepatitis C.

Data mining of routine laboratory tests can predict liver disease progression in Egyptian diabetic patients with hepatitis C virus (G4) infection: a cohort study of 71 806 patients.

OBJECTIVES: Hepatitis C virus (HCV) and diabetes mellitus (DM) are prevalent diseases worldwide, associated with significant morbidity, mortality, and mutual association. The aims of this study were as follows: (i) find the prevalence of DM among 71 806 Egyptian patients with chronic HCV infection and its effect on liver disease progression and (ii) using data mining of routine tests to predict hepatic fibrosis in diabetic patients with HCV infection. PATIENTS AND METHODS: A retrospective multicentered study included laboratory and histopathological data of 71 806 patients with HCV infection collected by Egyptian National Committee for control of viral hepatitis. Using data mining analysis, we constructed decision tree algorithm to assess predictors of fibrosis progression in diabetic patients with HCV. RESULTS: Overall, 12 018 (16.8%) patients were diagnosed as having diabetes [6428: fasting blood glucose ≥126 mg/dl (9%) and 5590: fasting blood glucose ≥110-126 mg/dl (7.8%)]. DM was significantly associated with advanced age, high BMI and α-fetoprotein (AFP), and low platelets and serum albumin (P≤0.001). Advanced liver fibrosis (F3-F4) was significantly correlated with DM (P≤0.001) irrespective of age. Of 16 attributes, decision tree model for fibrosis showed AFP was most decisive with cutoff of 5.25 ng/ml as starting point of fibrosis. AFP level greater than cutoff in patients was the first important splitting attribute; age and platelet count were second important splitting attributes. CONCLUSION: (i) Chronic HCV is significantly associated with DM (16.8%). (ii) Advanced age, high BMI and AFP, low platelets count and albumin show significant association with DM in HCV. (iii) AFP cutoff of 5.25 is a starting point of fibrosis development and integrated into mathematical model to predict development of liver fibrosis in diabetics with HCV (G4) infection.

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.

IP-10 Serum Level in Chronic Hepatitis C Virus Patients: Relation to Fibrosis and Response to Combined Interferon/Ribavirin Therapy.

Despite the appearance of the direct acting antiviral drugs, pegylated interferon/ribavirin (PEG-IFN/RBV) still has a place in the standard of care (SOC) therapy for chronic HCV4. Studies were conducted to find an accurate prediction in response to SOC therapy. Pretreatment serum interferon-γ-inducible protein-10 (IP-10) is an independent predictive factor of sustained virological response (SVR) in HCV1-infected patients. To assess whether the pretreatment serum level of IP-10 influences hepatic fibrosis and PEG-IFN/RBV therapy response, a study was conducted on 88 chronic Hepatitis C virus (HCV) patients who received PEG-IFN/RBV. Patients were subjected to a pretreatment routine laboratory evaluation, liver biopsy, and serum IP-10 assessment. They were followed up for 6 months after cessation of therapy (week 72). Patients were classified into 3 groups according to their response; nonresponders, relapsers, or sustained virological responders. The relation of pretreatment IP-10 with fibrosis and response was assessed. The studied groups were matched regarding their demographic data. There was no statistically significant association between the pretreatment IP-10 level and fibrosis (P=0.86) and no relation to response was found at week 12, 24, 48, and 72 (P=0.58, 0.8, 0.47, and 0.43, respectively). Pretreatment IP-10 could not predict either fibrosis or response to PEG-IFN/RIB therapy in chronic HCV Egyptian patients.

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%.

Peginterferon alpha-2a versus peginterferon alpha-2b for chronic hepatitis C.

BACKGROUND: A combination of weekly pegylated interferon (peginterferon) alpha and daily ribavirin still represents standard treatment of chronic hepatitis C infection in the majority of patients. However, it is not established which of the two licensed peginterferon products, peginterferon alpha-2a or peginterferon alpha-2b, is the most effective and has a better safety profile. OBJECTIVES: To systematically evaluate the benefits and harms of peginterferon alpha-2a versus peginterferon alpha-2b in head-to-head randomised clinical trials in patients with chronic hepatitis C. SEARCH METHODS: We searched the Cochrane Hepato-Biliary Group Controlled Trials Register, the Cochrane Central Register of Controlled Trials (CENTRAL) in The Cochrane Library, MEDLINE, EMBASE, Science Citation Index Expanded, and LILACS until October 2013. We also searched conference abstracts, journals, and grey literature. SELECTION CRITERIA: We included randomised clinical trials comparing peginterferon alpha-2a versus peginterferon alpha-2b given with or without co-intervention(s) (for example, ribavirin) for chronic hepatitis C. Quasi-randomised studies and observational studies as identified by the searches were also considered for assessment of harms. Our primary outcomes were all-cause mortality, liver-related morbidity, serious adverse events, adverse events leading to treatment discontinuation, other adverse events, and quality of life. The secondary outcome was sustained virological response in the blood serum. DATA COLLECTION AND ANALYSIS: Two authors independently used a standardised data collection form. We meta-analysed data with both the fixed-effect and the random-effects models. For each outcome we calculated the relative risk (RR) with 95% confidence interval (CI) based on intention-to-treat analysis. We used domains of the trials to assess the risk of systematic errors (bias) and trial sequential analyses to assess the risks of random errors (play of chance). Intervention effects on the outcomes were assessed according to GRADE. MAIN RESULTS: We included 17 randomised clinical trials which compared peginterferon alpha-2a plus ribavirin versus peginterferon alpha-2b plus ribavirin in 5847 patients. All trials had a high risk of bias. Very few trials reported data on very few patients for the patient-relevant outcomes all-cause mortality, liver-related morbidity, serious adverse events, and quality of life. Accordingly, we were unable to conduct meta-analyses on all-cause mortality, liver-related morbidity, and quality of life. Twelve trials reported on adverse events leading to discontinuation of treatment without clear evidence of a difference between the two peginterferons (197/2171 (9.1%) versus 311/3169 (9.9%); RR 0.84, 95% CI 0.57 to 1.22; I2 = 44%; low quality evidence). A trial sequential analysis showed that we could exclude a relative risk reduction of 20% or more on this outcome. Peginterferon alpha-2a significantly increased the number of patients who achieved a sustained virological response in the blood serum compared with peginterferon alpha-2b (1069/2099 (51%) versus 1327/3075 (43%); RR 1.12, 95% CI 1.06 to 1.18; I2= 0%, 12 trials; moderate quality evidence). Trial sequential analyses supported this result. Subgroup analyses based on risk of bias, viral genotype, and treatment history yielded similar results. Trial sequential analyses supported the results in patients with genotypes 1 and 4, but not in patients with genotypes 2 and 3. AUTHORS' CONCLUSIONS: There is lack of evidence on patient-important outcomes and paucity of evidence on adverse events. Moderate quality evidence suggests that peginterferon alpha-2a is associated with a higher sustained virological response in serum than with peginterferon alpha-2b. This finding may be affected by the high risk of bias of the included studies . The clinical consequences of peginterferon alpha-2a versus peginterferon alpha-2b are unknown, and we cannot translate an effect on sustained virological response into comparable clinical effects because sustained virological response is still an unvalidated surrogate outcome for patient-important outcomes. The lack of evidence on patient-important outcomes and the paucity of evidence on adverse events means that we are unable to draw any conclusions about the effects of one peginterferon over the other.

Peginterferon plus ribavirin versus interferon plus ribavirin for chronic hepatitis C.

BACKGROUND: Pegylated interferon (peginterferon) plus ribavirin is the recommended treatment for patients with chronic hepatitis C, but systematic assessment of the effect of this treatment compared with interferon plus ribavirin is needed. OBJECTIVES: To systematically evaluate the benefits and harms of peginterferon plus ribavirin versus interferon plus ribavirin for patients with chronic hepatitis C. SEARCH METHODS: We searched the Cochrane Hepato-Biliary Group Controlled Trials Register, the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, EMBASE, Science Citation Index-Expanded, and LILACS. We also searched conference abstracts, journals, and grey literature. The last searches were conducted in September 2013. SELECTION CRITERIA: We included randomised clinical trials comparing peginterferon plus ribavirin versus interferon plus ribavirin with or without co-intervention(s) (e.g., other antiviral drugs) for chronic hepatitis C. Quasi-randomised and observational studies retrieved through the searches for randomised clinical trials were also considered for reports of harms. Our primary outcomes were liver-related morbidity, all-cause mortality, serious adverse events, adverse events leading to treatment discontinuation, other adverse events, and quality of life. Our secondary outcome was sustained virological response in serum, that is, undetectable hepatitis C virus RNA in serum by sensitive tests six months after the end of treatment. DATA COLLECTION AND ANALYSIS: Two review authors independently used a standardised data collection form. We meta-analysed data with both fixed-effect and random-effects models. For each outcome, we calculated the odds ratio (OR) (for liver-related morbidity or all-cause mortality) or the risk ratio (RR) along with 95% confidence interval (CI) based on intention-to-treat analysis. We used domains of the trials to assess the risk of systematic errors (bias) and trial sequential analyses to assess the risk of random errors (play of chance).For each outcome, we calculated the RR with 95% CI based on intention-to-treat analysis. Effects of interventions on outcomes were assessed according to GRADE. MAIN RESULTS: We included 27 randomised trials with 5938 participants. All trials had high risk of bias. We considered that the risk of bias did not impact on the quality of evidence for liver-related mortality and adverse event outcomes, but it did for virological response. All trials compared peginterferon alpha-2a or peginterferon alpha-2b plus ribavirin versus interferon plus ribavirin for participants with chronic hepatitis C. Three trials administered co-interventions (amantadine hydrochloride 200 mg daily to both intervention groups), and 24 trials were conducted without co-interventions. The effect observed between the two intervention groups regarding liver-related morbidity plus all-cause mortality (5/907 (0.55%) versus 4/882 (0.45%) was imprecise: OR 1.14 ( 95% CI 0.38 to 3.42; five trials; low quality of evidence), as was the risk of adverse events leading to treatment discontinuation (332/2692 (12.3%) versus 409/2176 (18.8%); RR 0.86, 95% CI 0.68 to 1.09; 15 trials; low quality of evidence) or regarding adverse events leading to treatment discontinuation (332/2692 (12.3%) versus 409/2176 (18.8%); RR 0.86, 95% CI 0.66 to 1.12; 17 trials; low quality of evidence). However, peginterferon plus ribavirin versus interferon plus ribavirin significantly increased the risk of neutropenia (332/2202 (15.1%) versus 117/1653 (7.1%); RR 2.15, 95% CI 1.76 to 2.61; 13 trials), thrombocytopenia (65/1113 (5.8%) versus 23/1082 (2.1%); RR 2.63, 95% CI 1.68 to 4.11; 10 trials), arthralgia (517/1740 (29.7%) versus 282/1194 (23.6%); RR 1.19, 95% CI 1.05 to 1.35; four trials), injection site reaction (627/1168 (53.7%) versus 186/649 (28.7%); RR 1.71, 95% CI 1.50 to 1.93; four trials), and nausea (606/1784 (34.0%) versus 354/1239 (28.6%); RR 1.13, 95% CI 1.01 to 1.26; four trials). The most frequent adverse event was fatigue, which occurred in 57% of participants (2024/3608). No significant difference was noted between peginterferon plus ribavirin versus interferon plus ribavirin in terms of fatigue (1177/2062 (57.1%) versus 847/1546 (54.8%); RR 1.01, 95% CI 0.96 to 1.07; 12 trials). No significant differences were reported between the two treatment groups regarding anaemia, headache, rigours, myalgia, pyrexia, weight loss, asthenia, depression, insomnia, irritability, alopecia, pruritus, skin rash, thyroid malfunction, decreased appetite, or diarrhoea. We were unable to identify any data on quality of life. Peginterferon plus ribavirin versus interferon plus ribavirin seemed to significantly increase the number of participants achieving sustained virological response (1673/3300 participants (50.7%) versus 1081/2804 patients (36.7%); RR 1.39, 95% CI 1.25 to 1.56; I2 = 64%; 27 trials; very low quality of evidence). However, the risk of bias in the 13/27 (48.1%) trials reporting on this outcome was high and was considered only 'lower' in the remainder. Because the conventional meta-analysis did not reach its required information size (n = 14,486 participants), we used trial sequential analysis to control for risks of random errors. Again, in this analysis, the estimated effect was statistically significant in favour of peginterferon. Subgroup analyses according to risk of bias, viral genotype, baseline viral load, past treatment history, and type of intervention yielded similarly significant results favouring peginterferon over interferon on the outcome of sustained virological response. AUTHORS' CONCLUSIONS: Peginterferon plus ribavirin versus interferon plus ribavirin seems to significantly increase the proportion of patients with sustained virological response, as well as the risk of certain adverse events. However, we have insufficient evidence to recommend or reject peginterferon plus ribavirin for liver-related morbidity plus all-cause mortality compared with interferon plus ribavirin. The clinical consequences of achieved sustained virological response are unknown, as sustained virological response is still an unvalidated surrogate outcome. We found no evidence of the potential benefits on quality of life in patients with achieved sustained virological response. Further high-quality research is likely to have an important impact on our confidence in the estimate of patient-relevant outcomes and is likely to change our estimates.There is very low quality evidence that peginterferon plus ribavirin increases the proportion of patients with sustained virological response in comparison with interferon plus ribavirin. There is evidence that it also increases the risk of certain adverse events.

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.

Clinical, biochemical and pathological profiles of 5464 Egyptian chronic hepatitis C-infected patients.

BACKGROUND/AIMS: In Egypt, hepatitis C virus (HC is highly endemic with at least 91% are genotype-4. However, HCV-specific burden data for Egypt are scarce. The study aims to identify clinical, biochemical and pathological features of chronic HCV population in Egypt. METHODOLOGY: We analyzed retrospective data of 5,464 HCV-antibody and PCR positive patients attending pre-treatment assessment at one of the National Treatment Centers, Cairo, Egypt. RESULTS: Chronic HCV patients were males (81.4%) in their productive age, mean body mass index (BMI): 28 kg/m2. Laboratory profile demonstrated mean platelet count 214 x 10(3)/µ L with only 14% having thrombocytopenia, amino-transferases were mildly elevated: mean AST, ALT were 56 and 63 respectively,low viraemia: 50% had viral load <100 (x 10(3)) IU/mL,and median AFP level 3.3 ng/mL. Liver biopsy revealed ≤A2 in 92% of patients; 80% had ≤F2 and 7.3 % had F4 according to the METAVIR score. Meta regression demonstrated that advanced stages of fibrosis were significantly correlated with platelet count, AST/ALT ratio, AFP levels and BMI (p <0.001). However there was no correlation with viral load. CONCLUSIONS: To our knowledge, this is the first study on nationwide scale that provided the demographic, biochemical,and histological characteristics for this number of chronic HCV patients presumably genotype-4.

Health-related quality of life in Egyptian patients after liver transplantation.

UNLABELLED: INTRODUCTION-AIM: Health-Related Quality of Life (HRQOL) has become an important focus of patient care and clinical outcomes research with the improvement in patient and graft survival after liver transplantation (LT). The current study was designed to evaluate the post-transplant HRQOL profiles using the Liver Disease Quality of Life 1.0 (LDQOL 1.0) Questionnaire and demonstrate the possible effect of peri-transplant clinical covariates on these profiles. MATERIAL AND METHODS: Participants included pre-transplant group (waiting-list patients n = 50) and post-transplant group (mean 5 ± 4 years after deceased or living donor LT n = 103) who were recruited from 3 specialized centers in Egypt. We applied the LDQOL 1.0 questionnaire; a 111-item containing the Short Form-36 version 2.0 (SF-36v2) as a generic component supplemented by 75 disease-specific items. The etiology of cirrhosis, co-morbidities, model for end-stage liver disease (MELD), Child-Pugh class and post-operative complications were analyzed. RESULTS: All recipients had significant higher HRQOL scores than patients in waiting-list using both questionnaire components. Recipients with pre-LT MELD ≥ 15, Child-Pugh class C, history of hepatocellular carcinoma (HCC) demonstrated low HRQOL scores. Recipients without post-operative surgical complications had a statistically better HRQOL using the disease-specific, but not the SF-36v2 component. On the other hand, both components demonstrated non-significant lower scores in recipients with rejection episodes, cytomegalovirus (CMV) infection and hepatitis C recurrence had compared to those without medical complications. CONCLUSION: Generally HRQOL improves dramatically after LT as assessed by LDQOL questionnaire. Moreover, combined questionnaires can provide accurate information about the possible impaired HRQOL post-LT due to pre-transplant disease severity and post-operative complications.

Peginterferon alpha-2a is associated with higher sustained virological response than peginterferon alfa-2b in chronic hepatitis C: systematic review of randomized trials.

UNLABELLED: A combination of weekly pegylated interferon (peginterferon) alpha and daily ribavirin represents the standard of care for the treatment of chronic hepatitis C according to current guidelines. It is not established which of the two licensed products (peginterferon alpha-2a or peginterferon alfa-2b) is most effective. We performed a systematic review of head-to-head randomized trials to assess the benefits and harms of the two treatments. We searched the Cochrane Central Register of Controlled Trials, MEDLINE, EMBASE, and LILACS through July 2009. Using standardized forms, two reviewers independently extracted data from each eligible trial report. We statistically combined data using a random effects meta-analysis according to the intention-to-treat principle. We identified 12 randomized clinical trials, including 5,008 patients, that compared peginterferon alpha-2a plus ribavirin versus peginterferon alfa-2b plus ribavirin. Overall, peginterferon alpha-2a significantly increased the number of patients who achieved a sustained virological response (SVR) versus peginterferon alfa-2b (47% versus 41%; risk ratio 1.11, 95% confidence interval 1.04-1.19; P = 0.004 [eight trials]). Subgroup analyses of risk of bias, viral genotype, and treatment history yielded similar results. The meta-analysis of adverse events leading to treatment discontinuation included 11 trials and revealed no significant differences between the two peginterferons. CONCLUSION: Current evidence suggests that peginterferon alpha-2a is associated with higher SVR than peginterferon alfa-2b. However, the paucity of evidence on adverse events curbs the decision to definitively recommend one peginterferon over the other, because any potential benefit must outweigh the risk of harm.

Hepatitis C intervention research - Where are we now and where should we be heading?

In this paper we outline some of the major pending research questions that lie ahead in hepatitis C intervention research. We argue why these should be answered with randomised clinical trials and we stress how Egypt and other Arab countries can play an important role in this context. We delineate a number of design issues relevant to recent and future hepatitis C randomised clinical trials and provide insights on how and why randomised clinical trial designed in a pragmatic and evidence-based framework will efficiently answer pending research questions.