Artificial neural networks for the prediction of response to interferon plus ribavirin treatment in patients with chronic hepatitis C

Brave New World of Artificial Intelligence: Its Use in Antimicrobial Stewardship-A Systematic Review

Antimicrobial resistance (AMR) is a growing public health problem in the One Health dimension. Artificial intelligence (AI) is emerging in healthcare, since it is helpful to deal with large amounts of data and as a prediction tool. This systematic review explores the use of AI in antimicrobial stewardship programs (ASPs) and summarizes the predictive performance of machine learning (ML) algorithms, compared with clinical decisions, in inpatients and outpatients who need antimicrobial prescriptions. This review includes eighteen observational studies from PubMed, Scopus, and Web of Science. The exclusion criteria comprised studies conducted only in vitro, not addressing infectious diseases, or not referencing the use of AI models as predictors. Data such as study type, year of publication, number of patients, study objective, ML algorithms used, features, and predictors were extracted from the included publications. All studies concluded that ML algorithms were useful to assist antimicrobial stewardship teams in multiple tasks such as identifying inappropriate prescribing practices, choosing the appropriate antibiotic therapy, or predicting AMR. The most extracted performance metric was AUC, which ranged from 0.64 to 0.992. Despite the risks and ethical concerns that AI raises, it can play a positive and promising role in ASP.

Artificial intelligence models for the diagnosis and management of liver diseases

With the development of more advanced methods for the diagnosis and treatment of diseases, the data required for medical care are becoming complex, and misinterpretation of information due to human error may result in serious consequences. Human error can be avoided with the support of artificial intelligence (AI). AI models trained with various medical data for diagnosis and management of liver diseases have been applied to hepatitis, fatty liver disease, liver cirrhosis, and liver cancer. Some of these models have been reported to outperform human experts in terms of performance, indicating their potential for supporting clinical practice given their high-speed output. This paper summarizes the recent advances in AI for liver disease and introduces the AI-aided diagnosis of liver tumors using B-mode ultrasonography.

Key use cases for artificial intelligence to reduce the frequency of adverse drug events: a scoping review

Adverse drug events (ADEs) represent one of the most prevalent types of health-care-related harm, and there is substantial room for improvement in the way that they are currently predicted and detected. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged to reduce the frequency of ADEs. We focused on modern machine learning techniques and natural language processing. 78 articles were included in the scoping review. Studies were heterogeneous and applied various AI techniques covering a wide range of medications and ADEs. We identified several key use cases in which AI could contribute to reducing the frequency and consequences of ADEs, through prediction to prevent ADEs and early detection to mitigate the effects. Most studies (73 [94%] of 78) assessed technical algorithm performance, and few studies evaluated the use of AI in clinical settings. Most articles (58 [74%] of 78) were published within the past 5 years, highlighting an emerging area of study. Availability of new types of data, such as genetic information, and access to unstructured clinical notes might further advance the field.

Artificial intelligence for hepatitis evaluation

Recently, increasing attention has been paid to the application of artificial intelligence (AI) to the diagnosis of diverse hepatic diseases, which comprises traditional machine learning and deep learning. Recent studies have shown the possible value of AI based data mining in predicting the incidence of hepatitis, classifying the different stages of hepatitis, diagnosing or screening for hepatitis, forecasting the progression of hepatitis, and predicting response to antiviral drugs in chronic hepatitis C patients. More importantly, AI based on radiology has been proven to be useful in predicting hepatitis and liver fibrosis as well as grading hepatocellular carcinoma (HCC) and differentiating it from benign liver tumors. It can predict the risk of vascular invasion of HCC, the risk of hepatic encephalopathy secondary to hepatitis B related cirrhosis, and the risk of liver failure after hepatectomy in HCC patients. In this review, we summarize the application of AI in hepatitis, and identify the challenges and future perspectives.

Machine learning algorithm outperforms fibrosis markers in predicting significant fibrosis in biopsy-confirmed NAFLD

BACKGROUND

The presence of significant liver fibrosis is a key determinant of long-term prognosis in non-alcoholic fatty liver disease (NAFLD). We aimed to develop a novel machine learning algorithm (MLA) to predict fibrosis severity in NAFLD and compared it with the most widely used non-invasive fibrosis biomarkers.

METHODS

We used a cohort of 553 adults with biopsy-proven NAFLD, who were randomly divided into a training cohort (n = 278) for the development of both logistic regression model (LRM) and MLA, and a validation cohort (n = 275). Significant fibrosis was defined as fibrosis stage F ≥ 2. MLA and LRM were derived from variables that were selected using a least absolute shrinkage and selection operator (LASSO) logistic regression algorithm.

RESULTS

In the training cohort, the variables selected by LASSO algorithm were body mass index, pro-collagen type III, collagen type IV, aspartate aminotransferase and albumin-to-globulin ratio. The diagnostic accuracy of MLA showed the highest values of area under the receiver operator characteristic curve (AUROC: 0.902, 95% CI 0.869-0.904) for identifying fibrosis F ≥ 2. The LRM AUROC was 0.764, 95% CI 0.710-0.816 and significantly better than the AST-to-Platelet ratio (AUROC 0.684, 95% CI 0.605-0.762), FIB-4 score (AUROC 0.594, 95% CI 0.503-0.685) and NAFLD Fibrosis Score (AUROC 0.557, 95% CI 0.470-0.644). In the validation cohort, MLA also showed the highest AUROC (0.893, 95% CI 0.864-0.901). The diagnostic accuracy of MLA outperformed that of LRM in all subgroups considered.

CONCLUSIONS

Our newly developed MLA algorithm has excellent diagnostic performance for predicting fibrosis F ≥ 2 in patients with biopsy-confirmed NAFLD.

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

BACKGROUND

Machine learning (ML) is a growing field in medicine. This narrative review describes the current body of literature on ML for clinical decision support in infectious diseases (ID).

OBJECTIVES

We aim to inform clinicians about the use of ML for diagnosis, classification, outcome prediction and antimicrobial management in ID.

SOURCES

References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, biorXiv, ACM Digital Library, arXiV and IEEE Xplore Digital Library up to July 2019.

CONTENT

We found 60 unique ML-clinical decision support systems (ML-CDSS) aiming to assist ID clinicians. Overall, 37 (62%) focused on bacterial infections, 10 (17%) on viral infections, nine (15%) on tuberculosis and four (7%) on any kind of infection. Among them, 20 (33%) addressed the diagnosis of infection, 18 (30%) the prediction, early detection or stratification of sepsis, 13 (22%) the prediction of treatment response, four (7%) the prediction of antibiotic resistance, three (5%) the choice of antibiotic regimen and two (3%) the choice of a combination antiretroviral therapy. The ML-CDSS were developed for intensive care units (n = 24, 40%), ID consultation (n = 15, 25%), medical or surgical wards (n = 13, 20%), emergency department (n = 4, 7%), primary care (n = 3, 5%) and antimicrobial stewardship (n = 1, 2%). Fifty-three ML-CDSS (88%) were developed using data from high-income countries and seven (12%) with data from low- and middle-income countries (LMIC). The evaluation of ML-CDSS was limited to measures of performance (e.g. sensitivity, specificity) for 57 ML-CDSS (95%) and included data in clinical practice for three (5%).

IMPLICATIONS

Considering comprehensive patient data from socioeconomically diverse healthcare settings, including primary care and LMICs, may improve the ability of ML-CDSS to suggest decisions adapted to various clinical contexts. Currents gaps identified in the evaluation of ML-CDSS must also be addressed in order to know the potential impact of such tools for clinicians and patients.

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.

Optimization of paclitaxel-loaded poly (d,l-lactide-co-glycolide-N-p-maleimido benzoic hydrazide) nanoparticles size using artificial neural networks

The aim of this study was to find a model using artificial neural networks (ANNs) to predict PLGA-PMBH nanoparticles (NPs) size in preparation by modified nanoprecipitation. The input variables were polymer content, drug content, power of sonication and ratio of organic/aqueous phase (i.e. acetone/water), while the NPs size of PLGA-PMBH was assumed as the output variable. Forty samples of PLGA-PMBH NPs containing anticancer drug (i.e. paclitaxel) were synthesized by changing the variable factors in the experiments. The data modeling were performed using ANNs. The effects of input variables (namely, polymer content, drug content, power of sonication and ratio of acetone/water) on the output variables were evaluated using the 3D graphs obtained after modeling. Contrasting the 3D graphs from the generated model revealed that the amount of polymer (PLGA-PMBH) and drug content (PTX) have direct relation with the size of polymeric NPs in the process. In addition, it was illustrated that the ratio of acetone/water was the most important factor affecting the particle size of PLGA-PMBH NPs provided by solvent evaporation technique. Also, it was found that increasing the sonication power (up to a certain amount) indirectly affects the polymeric NPs size however it was directly affected in higher values.

Machine learning algorithms outperform conventional regression models in predicting development of hepatocellular carcinoma

OBJECTIVES

Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine-learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine-learning algorithms.

METHODS

We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine-learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared with the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis, and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics.

RESULTS

After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95% confidence interval (CI) 0.56-0.67), whereas the machine-learning algorithm had a c-statistic of 0.64 (95% CI 0.60-0.69) in the validation cohort. The HALT-C model had a c-statistic of 0.60 (95% CI 0.50-0.70) in the validation cohort and was outperformed by the machine-learning algorithm. The machine-learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (P<0.001) and integrated discrimination improvement (P=0.04).

CONCLUSIONS

Machine-learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing 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.

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.

Case-based reasoning support for liver disease diagnosis

OBJECTIVES

In Taiwan, as well as in the other countries around the world, liver disease has reigned over the list of leading causes of mortality, and its resistance to early detection renders the disease even more threatening. It is therefore crucial to develop an auxiliary system for diagnosing liver disease so as to enhance the efficiency of medical diagnosis and to expedite the delivery of proper medical treatment.

METHODS

The study accordingly integrated the case-based reasoning (CBR) model into several common classification methods of data mining techniques, including back-propagation neural network (BPN), classification and regression tree, logistic regression, and discriminatory analysis, in an attempt to develop a more efficient model for early diagnosis of liver disease and to enhance classification accuracy. To minimize possible bias, this study used a ten-fold cross-validation to select a best model for more precise diagnosis results and to reduce problems caused by false diagnosis.

RESULTS

Through a comparison of five single models, BPN and CBR emerged to be the top two methods in terms of overall performance. For enhancing diagnosis performance, CBR was integrated with other methods, and the results indicated that the accuracy and sensitivity of each CBR-added hybrid model were higher than those of each single model. Of all the CBR-added hybrid models, the BPN-CBR method took the lead in terms of diagnosis capacity with an accuracy rate of 95%, a sensitivity of 98%, and a specificity of 94%.

CONCLUSIONS

After comparing the five single and hybrid models, the study found BPN-CBR the best model capable of helping physicians to determine the existence of liver disease, achieve an accurate diagnosis, diminish the possibility of a false diagnosis being given to sick people, and avoid the delay of clinical treatment.

Prediction of survival and complications after percutaneous endoscopic gastrostomy in an individual by using clinical factors with an artificial neural network system

BACKGROUND

The demand for percutaneous endoscopic gastrostomy (PEG) has increased because it is safe and a technically easy method, but it has risks of severe complications including death and a high mortality rate within 30 days. At present, we cannot predict survival or the incidence of complications before tube placement in an individual. Earlier 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.

AIMS

We predicted the survival and complications before PEG placement in an individual by using artificial neural network (ANN) system, which can assess the nonlinear relationship.

METHODS

We studied 100 patients who underwent PEG at the Kitasato Medical Institute Hospital from 1997 to 2005. Clinical data and laboratory data were used as input data. Complications related to PEG placement and survival dates were historically and prospectively measured. From the clinical data and laboratory data, we examined the prediction of outcome in individual patients using multiple logistic regression analysis and an ANN.

RESULTS

The correct answer rate of survival by multiple logistic regression analysis was 67.9%. In contrast, using the ANN, we correctly predicted the survival date and aspiration pneumonia in 75 and 89% of patients, respectively. There was a nonlinear relationship among input factors and survival and complications.

CONCLUSION

We correctly predicted the outcome and complications of individual patients with PEG with a high correct answer rate. Our data show the potential of an ANN as a powerful tool in daily clinical use to individualize treatment ('tailor-made medicine') for PEG and reduce costs.

Gene-gene and gene-environment interactions in interferon therapy for chronic hepatitis C

INTRODUCTION

In studies of pharmacogenomics, it is essential to address gene-gene and gene-environment interactions to describe complex traits involving pharmacokinetic and pharmacodynamic mechanisms. In this work, our goal is to detect gene-gene and gene-environment interactions resulting from an analysis of chronic hepatitis C patients' clinical factors including SNPs, viral genotype, viral load, age and gender.

MATERIALS & METHODS

We collected blood samples from 523 chronic hepatitis C patients who had received interferon and ribavirin combination therapy. Based on the treatment strategy for chronic hepatitis C patients, we focused our search for candidate genes involved in pathways related to interferon signaling and immunomodulation. To investigate gene-gene and gene-environment interactions, we implemented an artificial neural network-based method for identifying significant interactions between clinical factors with the fivefold crossvalidation method and permutation tests. The artificial neural network model was trained by an algorithm with an adaptive momentum and learning rate.

RESULTS

A total of 20 SNPs were selected from six candidate genes including adenosine deaminase-RNA-specific (ADAR), caspase 5 (CASP5), interferon consensus sequence binding protein 1 (ICSBP1), interferon-induced protein 44 (IFI44), phosphoinositide-3-kinase catalytic gamma polypeptide (PIK3CG), and transporter 2 ATP-binding cassette subfamily B (TAP2) genes. By applying our artificial neural network-based approach, IFI44 was found in the significant two-locus, three-locus and four-locus gene-gene effect models, as well as in the significant two-factor and three-factor gene-environment effect models. Furthermore, viral genotype remained in the best two-factor, three-factor and four-factor gene-environment models. These results support the hypothesis that IFI44 and viral genotype may play a role in the pharmacogenomics of interferon treatment. In addition, our approach identified a panel of ten clinical factors that may be more significant than the others for further study.

CONCLUSION

We demonstrated that our artificial neural network-based approach is a promising method to assess the gene-gene and gene-environment interactions for interferon and ribavirin combination treatment in chronic hepatitis C patients by using clinical factors such as SNPs, viral genotype, viral load, age and gender.

International experience on the use of artificial neural networks in gastroenterology

In this paper, we reconsider the scientific background for the use of artificial intelligence tools in medicine. A review of some recent significant papers shows that artificial neural networks, the more advanced and effective artificial intelligence technique, can improve the classification accuracy and survival prediction of a number of gastrointestinal diseases. We discuss the 'added value' the use of artificial neural networks-based tools can bring in the field of gastroenterology, both at research and clinical application level, when compared with traditional statistical or clinical-pathological methods.

An artificial neural network approach to the drug efficacy of interferon treatments

INTRODUCTION

Interferon taken alone or in combination with ribavirin can be used for the treatment of persons with chronic hepatitis C. It is highly desirable, both clinically and economically, to establish tools to distinguish responders from nonresponders and to predict possible outcomes of the treatments. In this work, our goal is to develop a prediction model resulting from the analysis of chronic hepatitis C patients' single nucleotide polymorphisms, viral genotype, viral load, age and gender, to predict the responsiveness of interferon combination treatment.

MATERIALS AND METHODS

We collected blood samples from 523 chronic hepatitis C patients that had received interferon and ribavirin combination therapy. Based on the current treatment strategy for chronic hepatitis C patients, we focused our search for candidate genes involved in pathways related to interferon signaling and immunomodulation. With artificial neural network algorithms, we then developed pattern recognition methodologies to achieve predictions among the patients. The artificial neural network model was trained by an algorithm with an adaptive momentum and learning rate.

RESULTS

There were seven single nucleotide polymorphisms selected from six candidate genes including adenosine deaminase-RNA-specific, caspase 5, interferon consensus sequence binding protein 1, interferon-induced protein 44, phosphoinositide-3-kinase catalytic gamma polypeptide and transporter 2 ATP-binding cassette subfamily B genes. We further applied the artificial neural network algorithms with these seven single nucleotide polymorphisms, viral genotype, viral load, age and gender information to build tools for predicting the responsiveness of interferon. Based on the fivefold cross-validation method to evaluate the performance, the model achieved a high success rate of prediction.

CONCLUSION

We demonstrated that a trained artificial neural network model is a promising method for providing the inference from factors such as single nucleotide polymorphisms, viral genotype, viral load, age and gender to the responsiveness of interferon.

Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency room

Introduction

Neural networks are new methodological tools based on nonlinear models. They appear to be better at prediction and classification in biological systems than do traditional strategies such as logistic regression. This paper provides a practical example that contrasts both approaches within the setting of suspected sepsis in the emergency room.

Methods

The study population comprised patients with suspected bacterial infection as their main diagnosis for admission to the emergency room at two University-based hospitals. Mortality within the first 28 days from admission was predicted using logistic regression with the following variables: age, immunosuppressive systemic disease, general systemic disease, Shock Index, temperature, respiratory rate, Glasgow Coma Scale score, leucocyte counts, platelet counts and creatinine. Also, with the same input and output variables, a probabilistic neural network was trained with an adaptive genetic algorithm. The network had three neurone layers: 10 neurones in the input layer, 368 in the hidden layer and two in the output layer. Calibration was measured using the Hosmer-Lemeshow goodness-of-fit test and discrimination was determined using receiver operating characteristic curves.

Results

A total of 533 patients were recruited and overall 28-day mortality was 19%. The factors chosen by logistic regression (with their score in parentheses) were as follows: immunosuppressive systemic disease or general systemic disease (2), respiratory rate 24–33 breaths/min (1), respiratory rate ≥ 34 breaths/min (3), Glasgow Come Scale score ≤12 (3), Shock Index ≥ 1.5 (2) and temperature <38°C (2). The network included all variables and there were no significant differences in predictive ability between the approaches. The areas under the receiver operating characteristic curves were 0.7517 and 0.8782 for the logistic model and the neural network, respectively (P = 0.037).

Conclusion

A predictive model would be an extremely useful tool in the setting of suspected sepsis in the emergency room. It could serve both as a guideline in medical decision-making and as a simple way to select or stratify patients in clinical research. Our proposed model and the specific development method – either logistic regression or neural networks – must be evaluated and validated in an independent population.