Prediction of cirrhosis in patients with chronic hepatitis C infection by artificial neural network analysis of virus and clinical factors

Hybrid model for precise hepatitis-C classification using improved random forest and SVM method

Hepatitis C Virus (HCV) is a viral infection that causes liver inflammation. Annually, approximately 3.4 million cases of HCV are reported worldwide. A diagnosis of HCV in earlier stages helps to save lives. In the HCV review, the authors used a single ML-based prediction model in the current research, which encounters several issues, i.e., poor accuracy, data imbalance, and overfitting. This research proposed a Hybrid Predictive Model (HPM) based on an improved random forest and support vector machine to overcome existing research limitations. The proposed model improves a random forest method by adding a bootstrapping approach. The existing RF method is enhanced by adding a bootstrapping process, which helps eliminate the tree's minor features iteratively to build a strong forest. It improves the performance of the HPM model. The proposed HPM model utilizes a 'Ranker method' to rank the dataset features and applies an IRF with SVM, selecting higher-ranked feature elements to build the prediction model. This research uses the online HCV dataset from UCI to measure the proposed model's performance. The dataset is highly imbalanced; to deal with this issue, we utilized the synthetic minority over-sampling technique (SMOTE). This research performs two experiments. The first experiment is based on data splitting methods, K-fold cross-validation, and training: testing-based splitting. The proposed method achieved an accuracy of 95.89% for k = 5 and 96.29% for k = 10; for the training and testing-based split, the proposed method achieved 91.24% for 80:20 and 92.39% for 70:30, which is the best compared to the existing SVM, MARS, RF, DT, and BGLM methods. In experiment 2, the analysis is performed using feature selection (with SMOTE and without SMOTE). The proposed method achieves an accuracy of 41.541% without SMOTE and 96.82% with SMOTE-based feature selection, which is better than existing ML methods. The experimental results prove the importance of feature selection to achieve higher accuracy in HCV research.

Artificial Intelligence in Hepatology: A Narrative Review

There has been a tremendous growth in data collection in hepatology over the last decade. This wealth of "big data" lends itself to the application of artificial intelligence in the development of predictive and diagnostic models with potentially greater accuracy than standard biostatistics. As processing power of computing systems has improved and data are made more accessible through the large databases and electronic health record, these more contemporary techniques for analyzing and interpreting data have garnered much interest in the field of medicine. This review highlights the current evidence base for the use of artificial intelligence in hepatology, focusing particularly on the areas of diagnosis and prognosis of advanced chronic liver disease and hepatic neoplasia.

Computer-Aided Prediction of Long-Term Prognosis of Patients with Ulcerative Colitis after Cytoapheresis Therapy

Cytoapheresis (CAP) therapy is widely used in ulcerative colitis (UC) patients with moderate to severe activity in Japan. The aim of this study is to predict the need of operation after CAP therapy of UC patients on an individual level using an artificial neural network system (ANN). Ninety UC patients with moderate to severe activity were treated with CAP. Data on the patients' demographics, medication, clinical activity index (CAI) and efficacy of CAP were collected. Clinical data were divided into training data group and validation data group and analyzed using ANN to predict individual outcomes. The sensitivity and specificity of predictive expression by ANN were 0.96 and 0.97, respectively. Events of admission, operation, and use of immunomodulator, and efficacy of CAP were significantly correlated to the outcome. Requirement of operation after CAP therapy was successfully predicted by using ANN. This newly established ANN strategy would be used as powerful support of physicians in the clinical practice.

An MLP classifier for prediction of HBV-induced liver cirrhosis using routinely available clinical parameters

Background. Liver cirrhosis (LC) is the final stage of most of chronic liver diseases and is almost caused by chronic hepatitis B (CHB) in China. Liver biopsy is the reference method for the evaluation of liver cirrhosis. However, it is an invasive procedure with inherent risk. The aim of this study was to construct a new classifier based on the routine clinical markers for the prediction of HBV-induced LC. Subjects and Methods. We collected routine clinical parameters from 124 LC patients with CHB and 115 with CHB. Training set (n = 120) and test set (n = 119) were built for model construction and evaluation, respectively. Results. We describe a new classifier, MLP, for prediction of LC with CHB. MLP was built with seven routinely available clinical parameters, including age, ALT, AST, PT, PLT, HGB, and RDW. With optimal cutoff, we obtained a sensitivity of 95.2%, a specificity of 84.2%, and an overall accuracy of 89.9% on an independent test set, which were superior to those of FIB-4 and APRI. Conclusions. Our study suggests that the MLP classifier can be implemented for discriminating LC and non-LC cohorts by using machine learning method based on the routine available clinical parameters. It could be used for clinical practice in HBV-induced LC assessment.

Stability and robustness of human metabolic phenotypes in response to sequential food challenges

High-resolution spectroscopic profiles of biofluids can define metabolic phenotypes, providing a window onto the impact of diet on health to reflect gene-environment interactions. (1)H NMR spectroscopic profiling was used to characterize the effect of nutritional intervention on the stability of the metabolic phenotype of 7 individuals following a controlled 7 day dietary protocol. Inter-individual metabolic differences influenced proportionally more of the spectrum than dietary modulation, with certain individuals displaying a greater stability of metabolic phenotypes than others. Correlation structures between urinary metabolites were identified and used to map inter-individual pathway differences. Choline degradation was the pathway most affected by the individual, suggesting that the gut microbiota influence host metabolic phenotypes. This influence was further emphasized by the highly correlated excretion of the microbial-mammalian co-metabolites phenylacetylglutamine, 4-cresylsulfate (r = 0.87), and indoxylsulfate (r = 0.67) across all individuals. Above the background of inter-individual differences, clear biochemical effects of single type dietary interventions, animal protein, fruit and wine intake, were observed; for example, the spectral variance introduced by fruit ingestion was attributed to the metabolites tartrate, proline betaine, hippurate, and 4-hydroxyhippurate. This differential metabolic baseline and response to selected dietary challenges highlights the importance of understanding individual differences in metabolism and provides a rationale for evaluating dietary interventions and stratification of individuals with respect to guiding nutrition and health programmes.

Prediction of effect of pegylated interferon alpha-2b plus ribavirin combination therapy in patients with chronic hepatitis C infection

Treatment with pegylated interferon alpha-2b (PEGIFN) plus ribavirin (RBV) is standard therapy for patients with chronic hepatitis C. Although the effectiveness, patients with high titres of group Ib hepatitis C virus (HCV) respond poorly compared to other genotypes. At present, we cannot predict the effect in an individual. Previous studies have used traditional statistical analysis by assuming a linear relationship between clinical features, but most phenomena in the clinical situation are not linearly related. The aim of this study is to predict the effect of PEG IFN plus RBV therapy on an individual patient level using an artificial neural network system (ANN). 156 patients with HCV group 1b from multiple centres were treated with PEGIFN (1.5 µg/kg) plus RBV (400–1000 mg) for 48 weeks. Data on the patients' demographics, laboratory tests, PEGIFN, and RBV doses, early viral responses (EVR), and sustained viral responses were collected. Clinical data were randomly divided into training data set and validation data set and analyzed using multiple logistic regression analysis (MLRs) and ANN to predict individual outcomes. The sensitivities of predictive expression were 0.45 for the MLRs models and 0.82 for the ANNs and specificities were 0.55 for the MLR and 0.88 for the ANN. Non-linear relation analysis showed that EVR, serum creatinine, initial dose of Ribavirin, gender and age were important predictive factors, suggesting non-linearly related to outcome. In conclusion, ANN was more accurate than MLRs in predicting the outcome of PEGIFN plus RBV therapy in patients with group 1b HCV.

Prediction of metabolic syndrome using artificial neural network system based on clinical data including insulin resistance index and serum adiponectin

OBJECTIVE

This study aimed to predict the 6-year incidence of metabolic syndrome (MetS) using an artificial neural network (ANN) system and multiple logistic regression (MLR) analysis based on clinical factors, including the insulin resistance index calculated by homeostasis model assessment (HOMA-IR).

DESIGN

Subjects were recruited from participants in annual health check-ups in both 2000 and 2006. A total of 410 Japanese male teachers and other workers at Keio University, 30-59 years of age at baseline, participated in this retrospective cohort study.

MEASUREMENTS

Clinical parameters were randomly divided into a training dataset and a validation dataset, and the ANN system and MLR analysis were applied to predict individual incidences. The leave some out cross validation method was used for validation.

RESULTS

The sensitivity of the prediction was 0.27 for the MLR model and 0.93 for the ANN system, while specificities were 0.95 and 0.91, respectively. Sensitivity analysis employing the ANN system identified BMI, age, diastolic blood pressure, HDL-cholesterol, LDL-cholesterol and HOMA-IR as important predictors, suggesting these factors to be non-linearly related to the outcome.

CONCLUSION

We successfully predicted the 6-year incidence of MetS using an ANN system based on clinical data, including HOMA-IR and serum adiponectin, in Japanese male subjects.

Proteomic approaches in the search for biomarkers of liver fibrosis

Chronic liver diseases (CLDs) can cause progressive hepatic fibrosis culminating in cirrhosis. Fibrosis staging requires liver biopsy, which is invasive, expensive and frequently poorly tolerated by patients. Serum-based panels of fibrosis biomarkers have been developed as alternatives to biopsy. Recent advances in high-throughput proteomic methods have the potential to optimise combinations of biomarkers for the diagnosis of liver fibrosis. Here, we review the key recent developments in the field of proteomics and their application to this important clinical question. We critically discuss the challenges and priorities for future research that are of critical importance to clinical hepatology.

Systematic review: non-invasive methods of fibrosis analysis in chronic hepatitis C

BACKGROUND

Accurate determination of the presence and degree of liver fibrosis is essential for prognosis and for planning treatment of patients with chronic hepatitis C virus (HCV). Non-invasive methods of assessing fibrosis have been developed to reduce the need for biopsy.

AIM

To perform a review of these non-invasive measures and their ability to replace biopsy for assessing hepatic fibrosis in patients with chronic HCV.

METHODS

A systematic review of PUBMED and EMBASE was performed through 2008 using the following search terms: HCV, liver, elastography, hepatitis, Fibroscan, SPECT, noninvasive liver fibrosis, ultrasonography, Doppler, MRI, Fibrotest, Fibrosure, Actitest, APRI, Forns and breath tests, alone or in combination.

RESULTS

We identified 151 studies: 87 using biochemical, 57 imaging and seven breath tests either alone or in combination.

CONCLUSIONS

Great strides are being made in the development of accurate non-invasive methods for determination of fibrosis. Although no single non-invasive test or model developed to date can match that information obtained from actual histology (i.e. inflammation, fibrosis, steatosis), combinations of two modalities of non-invasive methods can reliably differentiate between minimal and significant fibrosis, and thereby avoid liver biopsy in a significant percentage of patients.

Prediction of asymptomatic cirrhosis in chronic hepatitis C patients: accuracy of artificial neural networks compared with logistic regression models

OBJECTIVE

Models based on logistic regression analysis are proposed as noninvasive tools to predict cirrhosis in chronic hepatitis C (CHC) patients. However, none showed to be sufficiently accurate to replace liver biopsy. Artificial neural networks (ANNs), providing a prediction based on nonlinear algorithms, can improve the diagnosis of cirrhosis, a syndrome characterized by complex, nonlinear biological alterations. We compared ANNs with two logistic regression analysis-based models in predicting CHC histologically proven cirrhosis.

METHODS

Liver biopsy was obtained in CHC patients of two different cohorts (an internal cohort including 244 patients and an external cohort including 220 patients). One hundred and forty-four patients from the internal cohort served as a training set to construct ANNs and a logistic regression model (LOGIT). These two models and the aspartate aminotransferase-to-platelet ratio index (APRI) were tested in the remaining 100 patients (internal validation set) and in the external cohort (external validation set). Diagnostic performances were evaluated by standard indices of accuracy.

RESULTS

In the internal validation set, ANNs, LOGIT, and APRI showed similar discrimination powers (0.88, 0.87, and 0.87 respectively). However, ANNs showed the best positive predictive value (0.86 vs. 0.67 and 0.56) and positive likelihood ratio (40.2 vs. 13.4 and 8.4). In the external validation set, the discrimination power of ANNs (0.76) was significantly higher than those of LOGIT (0.67) and APRI (0.67).

CONCLUSION

Compared to conventional models, ANNs performance in predicting CHC cirrhosis is slightly better and more reproducible.

Artificial neural network prediction of clozapine response with combined pharmacogenetic and clinical data

Although one third to one half of refractory schizophrenic patients responds to clozapine, however, there are few evidences currently that could predict clozapine response before the use of the medication. The present study aimed to train and validate artificial neural networks (ANN), using clinical and pharmacogenetic data, to predict clozapine response in schizophrenic patients. Five pharmacogenetic variables and five clinical variables were collated from 93 schizophrenic patients taking clozapine, including 26 responders. ANN analysis was carried out by training the network with data from 75% of cases and subsequently testing with data from 25% of unseen cases to determine the optimal ANN architecture. Then the leave-one-out method was used to examine the generalization of the models. The optimal ANN architecture was found to be a standard feed-forward, fully-connected, back-propagation multilayer perceptron. The overall accuracy rate of ANN was 83.3%, which is higher than that of logistic regression (LR) (70.8%). By using the area under the receiver operating characteristics curve as a measure of performance, the ANN outperformed the LR (0.821+/-0.054 versus 0.579+/-0.068; p<0.001). The ANN with only genetic variables outperformed the ANN with only clinical variables (0.805+/-0.056 versus 0.647+/-0.066; p=0.046). The gene polymorphisms should play an important role in the prediction. Further validation of ANN analysis is likely to provide decision support for predicting individual response.

1H NMR metabonomics of plasma lipoprotein subclasses: elucidation of metabolic clustering by self-organising maps

(1)H NMR spectra of plasma are known to provide specific information on lipoprotein subclasses in the form of complex overlapping resonances. A combination of (1)H NMR and self-organising map (SOM) analysis was applied to investigate if automated characterisation of subclass-related metabolic interactions can be achieved. To reliably assess the intrinsic capability of (1)H NMR for resolving lipoprotein subclass profiles, sum spectra representing the pure lipoprotein subclass part of actual plasma were simulated with the aid of experimentally derived model signals for 11 distinct lipoprotein subclasses. Two biochemically characteristic categories of spectra, representing normolipidaemic and metabolic syndrome status, were generated with corresponding lipoprotein subclass profiles. A set of spectra representing a metabolic pathway between the two categories was also generated. The SOM analysis, based solely on the aliphatic resonances of these simulated spectra, clearly revealed the lipoprotein subclass profiles and their changes. Comparable SOM analysis in a group of 69 experimental (1)H NMR spectra of serum samples, which according to biochemical analyses represented a wide range of lipoprotein lipid concentrations, corroborated the findings based on the simulated data. Interestingly, the choline-N(CH(3))(3) region seems to provide more resolved clustering of lipoprotein subclasses in the SOM analyses than the methyl-CH(3) region commonly used for subclass quantification. The results illustrate the inherent suitability of (1)H NMR metabonomics for automated studies of lipoprotein subclass-related metabolism and demonstrate the power of SOM analysis in an extensive and representative case of (1)H NMR metabonomics.

Support Vector Machine-Based Feature Selection for Classification of Liver Fibrosis Grade in Chronic Hepatitis C

Although liver biopsy is currently regarded as the gold standard for staging liver fibrosis in chronic hepatitis C, it is a costly invasive procedure and carries a small risk for complication. Our aim in this study was to construct a simple model to distinguish between patients with no or mild fibrosis (METAVIR F0-F1) versus those with clinically significant fibrosis (METAVIR F2-F4). We retrospectively studied 204 consecutive CHC patients. Thirty-four serum markers with age, gender, duration of infection were assessed to classify fibrosis with a classifier known as the support vector machine (SVM). The method of feature selection known as sequential forward floating selection (SFFS) was introduced before the performance of SVM. When four serum markers were extracted with SFFS-SVM, F2-F4 could be predicted accurately in 96%. Our study showed that application of this model could identify CHC patients with clinically significant fibrosis with a high degree of accuracy and may decrease the need for liver biopsy.

[Use of an artificial neural network for detecting excess deaths due to cholera in Ceará, Brazil]

OBJECTIVE

To evaluate recurrent neural networks as a predictive technique for time-series in the health field.

METHODS

The study was carried out during a cholera epidemic which took place in 1993 and 1994 in the state of Ceará, northeastern Brazil, and was based on excess deaths having 'poorly defined intestinal infections' as the underlying cause (ICD-9). The monthly number of deaths with due to this cause between 1979 and 1995 in the state of Ceará was obtained from the Ministry of Health's Mortality Information System (SIM). A network comprising two neurons in the input layer, twelve in the hidden layer, one in the output layer, and one in the memory layer was trained by backpropagation using the fist 150 observations, with 0.01 learning rate and 0.9 momentum. Training was ended after 22,000 epochs. We compare the results with those of a negative binomial regression.

RESULTS

ANN forecasting was adequate. Excessive mortality (number of deaths above the upper limit of the confidence interval) was detected in December 1993 and October/November 1994. However, negative binomial regression detected excess mortality from March 1992 onwards.

CONCLUSIONS

The artificial neural network showed good predictive ability, especially in the initial period, and was able to detect alterations concomitant and a subsequent to the cholera epidemic. However, it was less precise that the binomial regression model, which was more sensitive to abnormal data concomitant with cholera circulation.

Historical features are poor predictors of liver fibrosis in Canadian patients with chronic hepatitis C

The progression of fibrosis in chronic hepatitis C infection (HCV) is related to host factors including age, gender and alcohol consumption. Due to the morbidity and potential mortality of liver biopsy, a noninvasive method of assessing hepatic fibrosis is needed. The aim of this study was to assess the utility of historical features in predicting fibrosis using published rates of fibrosis progression. The charts of 239 untreated patients with HCV were reviewed; patients who had a liver biopsy and whose duration of infection could be estimated (n=106) were categorized according to gender, age at infection (< or = or > 40 years) and peak alcohol consumption (< or > or = 50 g/day). Estimates of fibrosis were calculated using the product of the interval between infection and biopsy and published rates of fibrosis progression. Estimates were compared with liver biopsies staged according to the Metavir system (F0-F4; F0=no fibrosis; F4= cirrhosis). The mean age of patients was 42 +/- 8 years, 61% were male and 36% consumed > 50 g of alcohol daily. The mean duration of infection was 19 +/- 9 years (range, 1-40) and ALT was elevated > 1.5 times upper normal in 63%. When patients were classified into those with mild (F0-F2) and severe (F3-F4) fibrosis, the sensitivity, specificity, positive predictive value and negative predictive value of an estimate of mild fibrosis was 60%, 55%, 78% and 34%, respectively. An estimate of severe fibrosis had a sensitivity of 55%, specificity of 60%, positive predictive value of 34% and negative predictive value of 78%. Agreement between fibrosis estimates and actual histological stages was poor (kappa = 0.13, P=0.08). The prediction of hepatic fibrosis in HCV infection using historical features and published rates of fibrosis progression is poor in a Canadian clinical practice setting. Alternate noninvasive methods of predicting hepatic fibrosis are needed.

Application of self-organizing maps in conformational analysis of lipids

The characteristics of lipid assemblies are important for the functions of biological membranes. This has led to an increasing utilization of molecular dynamics simulations for the elucidation of the structural features of biomembranes. We have applied the self-organizing map (SOM) to the analysis of the complex conformational data from a 1-ns molecular dynamics simulation of PLPC phospholipids in a membrane assembly. Mapping of 1.44 million molecular conformations to a two-dimensional array of neurons revealed, without human intervention, the main conformational features in hours. Both the whole molecule and the characteristics of the unsaturated fatty acid chains were analyzed. All major structural features were easily distinguished, such as the orientational variability of the headgroup, the mainly trans state dihedral angles of the sn-1 chain, and both straight and bent conformations of the unsaturated sn-2 chain. Furthermore, presentation of the trajectory of an individual lipid molecule on the map provides information on conformational dynamics. The present results suggest that the SOM method provides a powerful tool for routinely gaining rapid insight to the main molecular conformations as well as to the conformational dynamics of any simulated molecular assembly without the requirement of a priori knowledge.

The HCV National Register: towards informing the natural history of hepatitis C infection in the UK

The aim of this paper is to describe the development of a national hepatitis C register and the completeness of the data it contains. This is a descriptive report of the structure and function of the register, including case definitions, registration and follow-up procedures, and methods used to maximize data quality and to obtain comparative data sources. The register contains data on HCV-infected individuals who acquired their infections on a known date and by a known route; to date all are transfusion recipients identified during the UK lookback exercise, who tested positive or indeterminate for anti-HCV after receiving 'infected' blood issued before the introduction of routine testing of the blood supply for anti-HCV. By 31 December 1999, 871 (87%) of 996 eligible transfusion recipients had been registered, and 984 (99%) flagged in the NHS Central Registers. Registered patients had been infected for an average of 11.1 years (SEM 0.1); around half were being cared for by clinicians with a specialist interest in liver disease. Except for the information on tobacco use, current alcohol use, and hepatitis B status, data were more than 80% complete, and for most variables, more than 90% complete. The consistency of data abstraction was found to be 98% (SEM 0.5). In conclusion, the Register contains high quality anonymised data on one of the largest cohorts of individuals with HCV infections acquired on a known date and by a known route. It could serve as a model for other chronic disease registers; developers may find the structure, design, and methodological issues addressed useful.