Drug-induced Liver Injury Classification Research Articles

Identification of reversible OATP1B1 and time-dependent CYP3A4 inhibition as the major risk factors for drug-induced cholestasis (DIC).

Hepatic bile acid regulation is a multifaceted process modulated by several hepatic transporters and enzymes. Drug-induced cholestasis (DIC), a main type of drug-induced liver injury (DILI), denotes any drug-mediated condition in which hepatic bile flow is impaired. Our ability in translating preclinical toxicological findings to human DIC risk is currently very limited, mainly due to important interspecies differences. Accordingly, the anticipation of clinical DIC with available in vitro or in silico models is also challenging, due to the complexity of the bile acid homeostasis. Herein, we assessed the in vitro inhibition potential of 47 marketed drugs with various degrees of reported DILI severity towards all metabolic and transport mechanisms currently known to be involved in the hepatic regulation of bile acids. The reported DILI concern and/or cholestatic annotation correlated with the number of investigated processes being inhibited. Furthermore, we employed univariate and multivariate statistical methods to determine the important processes for DILI discrimination. We identified time-dependent inhibition (TDI) of cytochrome P450 (CYP) 3A4 and reversible inhibition of the organic anion transporting polypeptide (OATP) 1B1 as the major risk factors for DIC among the tested mechanisms related to bile acid transport and metabolism. These results were consistent across multiple statistical methods and DILI classification systems applied in our dataset. We anticipate that our assessment of the two most important processes in the development of cholestasis will enable a risk assessment for DIC to be efficiently integrated into the preclinical development process.

Automatic text classification of drug-induced liver injury using document-term matrix and XGBoost.

Regulatory agencies generate a vast amount of textual data in the review process. For example, drug labeling serves as a valuable resource for regulatory agencies, such as U.S. Food and Drug Administration (FDA) and Europe Medical Agency (EMA), to communicate drug safety and effectiveness information to healthcare professionals and patients. Drug labeling also serves as a resource for pharmacovigilance and drug safety research. Automated text classification would significantly improve the analysis of drug labeling documents and conserve reviewer resources. We utilized artificial intelligence in this study to classify drug-induced liver injury (DILI)-related content from drug labeling documents based on FDA's DILIrank dataset. We employed text mining and XGBoost models and utilized the Preferred Terms of Medical queries for adverse event standards to simplify the elimination of common words and phrases while retaining medical standard terms for FDA and EMA drug label datasets. Then, we constructed a document term matrix using weights computed by Term Frequency-Inverse Document Frequency (TF-IDF) for each included word/term/token. The automatic text classification model exhibited robust performance in predicting DILI, achieving cross-validation AUC scores exceeding 0.90 for both drug labels from FDA and EMA and literature abstracts from the Critical Assessment of Massive Data Analysis (CAMDA). Moreover, the text mining and XGBoost functions demonstrated in this study can be applied to other text processing and classification tasks.

Drug-induced liver injury: diagnosis of exclusion

Drug-induced liver injury (DILI) is a relevant issue in clinical practice and is still a diagnosis of exclusion. Despite the low incidence in the general population, DILI is the cause of most cases of acute hepatic injury and has a mortality rate of up to 50%. Despite many reports in the medical literature about the DILI mechanisms, a clear causal relationship between them, drugs, and risk factors has not been established. Current clinical practice is based on a combination of a thorough study of a history of risk factors, the timing of drug and dietary supplements' administration, and the analysis of laboratory and instrumental tests. It aligns with the international criteria of the Rousell Uclaf Causality Assessment Method (RUCAM), which is considered one of the main diagnostic algorithms for DILI. The article addresses current DILI classification, risk factors, diagnostic algorithms, causalities, clinical evaluation, promising liver function biomarkers, and specific treatment.

Drug-induced liver injury: a comprehensive review.

Drug-induced liver injury (DILI) remains a challenge in clinical practice and is still a diagnosis of exclusion. Although it has a low incidence amongst the general population, DILI accounts for most cases of acute liver failure with a fatality rate of up to 50%. While multiple mechanisms of DILI have been postulated, there is no clear causal relationship between drugs, risk factors and mechanisms of DILI. Current best practice relies on a combination of high clinical suspicion, thorough clinical history of risk factors and timeline, and extensive hepatological investigations as supported by the international Roussel Uclaf Causality Assessment Method criteria, the latter considered a key diagnostic algorithm for DILI. This review focuses on DILI classification, risk factors, clinical evaluation, future biomarkers and management, with the aim of facilitating physicians to correctly identify DILI early in presentation.

BERT-Based Natural Language Processing of Drug Labeling Documents: A Case Study for Classifying Drug-Induced Liver Injury Risk.

Background & Aims: The United States Food and Drug Administration (FDA) regulates a broad range of consumer products, which account for about 25% of the United States market. The FDA regulatory activities often involve producing and reading of a large number of documents, which is time consuming and labor intensive. To support regulatory science at FDA, we evaluated artificial intelligence (AI)-based natural language processing (NLP) of regulatory documents for text classification and compared deep learning-based models with a conventional keywords-based model. Methods: FDA drug labeling documents were used as a representative regulatory data source to classify drug-induced liver injury (DILI) risk by employing the state-of-the-art language model BERT. The resulting NLP-DILI classification model was statistically validated with both internal and external validation procedures and applied to the labeling data from the European Medicines Agency (EMA) for cross-agency application. Results: The NLP-DILI model developed using FDA labeling documents and evaluated by cross-validations in this study showed remarkable performance in DILI classification with a recall of 1 and a precision of 0.78. When cross-agency data were used to validate the model, the performance remained comparable, demonstrating that the model was portable across agencies. Results also suggested that the model was able to capture the semantic meanings of sentences in drug labeling. Conclusion: Deep learning-based NLP models performed well in DILI classification of drug labeling documents and learned the meanings of complex text in drug labeling. This proof-of-concept work demonstrated that using AI technologies to assist regulatory activities is a promising approach to modernize and advance regulatory science.

Predicting Drug-Induced Liver Injury Using Machine Learning on a Diverse Set of Predictors.

A major challenge in drug development is safety and toxicity concerns due to drug side effects. One such side effect, drug-induced liver injury (DILI), is considered a primary factor in regulatory clearance. The Critical Assessment of Massive Data Analysis (CAMDA) 2020 CMap Drug Safety Challenge goal was to develop prediction models based on gene perturbation of six preselected cell-lines (CMap L1000), extended structural information (MOLD2), toxicity data (TOX21), and FDA reporting of adverse events (FAERS). Four types of DILI classes were targeted, including two clinically relevant scores and two control classifications, designed by the CAMDA organizers. The L1000 gene expression data had variable drug coverage across cell lines with only 247 out of 617 drugs in the study measured in all six cell types. We addressed this coverage issue by using Kru-Bor ranked merging to generate a singular drug expression signature across all six cell lines. These merged signatures were then narrowed down to the top and bottom 100, 250, 500, or 1,000 genes most perturbed by drug treatment. These signatures were subject to feature selection using Fisher’s exact test to identify genes predictive of DILI status. Models based solely on expression signatures had varying results for clinical DILI subtypes with an accuracy ranging from 0.49 to 0.67 and Matthews Correlation Coefficient (MCC) values ranging from -0.03 to 0.1. Models built using FAERS, MOLD2, and TOX21 also had similar results in predicting clinical DILI scores with accuracy ranging from 0.56 to 0.67 with MCC scores ranging from 0.12 to 0.36. To incorporate these various data types with expression-based models, we utilized soft, hard, and weighted ensemble voting methods using the top three performing models for each DILI classification. These voting models achieved a balanced accuracy up to 0.54 and 0.60 for the clinically relevant DILI subtypes. Overall, from our experiment, traditional machine learning approaches may not be optimal as a classification method for the current data.

Drug-induced liver injury and liver injury during pregnancy: pathogenesis, diagnosis and treatment

This article is a literature review on drug-induced liver injury (DILI). The authors revealed the role of liver tissue in biotransformation of drugs, and the mechanisms of hepatocytes injury under the influence of their metabolites (direct lesion of hepatocytes structure and idiosyncratic hypersensitivity). Separation of drugs into true and facultative hepatotoxins is explained. Opinion of patients and doctors of various majors about the most hepatotoxic drugs is presented. DILI classification depending on the dominant pathogenetic mechanism is given. Nuances of clinical and laboratory diagnostics and drug treatment of DILI are revealed. Advantages of ademetionine, ursodeoxycholic acid and glucocorticoids prescription are analyzed, indications for their application are listed, and the optimal therapeutic dosages of these drugs are given. Expediency of prescribing plant hepatoprotector chophytol and myotropic spasmolytic hymecromone is considered.
 Pathogenesis of liver injury during pregnancy is described, occurrence of hepatological pathology in this cohort of patients is briefly characterized, nuances of diagnostics and course of intrahepatic cholestasis of pregnancy, acute fatty liver dystrophy of pregnancy, HELLP-syndrome are considered. Peculiarities of the course of pregnancy on the background of the previous liver disease (viral hepatitis A, B, C, autoimmune hepatitis, primary biliary cirrhosis, Wilson’s disease) are revealed. The most effective conservative (ademetionine, ursodeoxycholic acid) and operative techniques (early delivery) of correction of liver injury of pregnancy are listed.

Automated Integration of Structural, Biological and Metabolic Similarities to Sustain Read-Across

Read-across (RAX) is a popular data-gap filling technique that uses category and analogue approaches to predict toxicological endpoints for a target. Despite its increasing relevance, RAX relies on human expert judgement and lacks a reproducible and automated protocol. It also only relies on structural similarity for identifying the analogues, while other aspects are often neglected. In this paper, we propose an automated procedure for the selection of analogues for data gap-filling. Analogues were identified with a decision algorithm that integrates three similarity metrics, each considering different toxicologically relevant aspects (i.e., structural, biological and metabolic similarity). Structural filters based on the presence of maximum common substructures (MCS) and common functional groups were applied to narrow the chemical space for the analogues search. The procedure has been implemented as a workflow in KNIME and is freely available. The workflow provides informative tabular and graphical outputs to support toxicologists and risk assessors in drawing conclusion based on the RAX approach. The procedure has been validated for its predictive power on two datasets related to high-tier in vivo toxicological endpoints, i.e. human hepatotoxicity and drug-induced liver injury (DILI). The validation results gave good accuracy values (i.e., up to 0.79 for the binary hepatotoxicity classification and up to 0.67 for the three-class DILI classification) that were higher than those returned by RAX based on the sole use of structural similarity. Results confirmed the suitability of the procedure as a source of data to support regulatory decision-making.

A proposed pathologic sub-classification of drug-induced liver injury.

The aim of this study was to establish a new pathologic sub-classification of drug-induced liver injury (DILI) in combination with serum chemistry parameters and clinical observations. From 777 DILI cases diagnosed in China-Japan Friendship Hospital from 2003 to 2014, 590 cases without other concomitant liver diseases were selected for the study. Pathological classification was established. Pathology and serum biochemical correlation analyses in 208 acute cases with complete biochemical data and prognostic information were conducted. We established a pathological classification of DILI according to the target cells of the liver (hepatocytes, bile duct epithelial cells, liver vascular and sinusoidal endothelial cells). In the 590 cases of DILI analyzed, hepatocyte injury accounted for 67.0%, bile duct epithelial injury (including cholestasis and mixed type of injury) 23.9%, and vascular injury 8.8%; about half of them were caused by the administration of traditional Chinese herbal medicines. Acute hepatocyte injury (lobular hepatitis) is further divided into mild, moderate and severe subtypes, while the mixed type of injury is categorized as cholestatic hepatitis and mixed hepatitis. The dynamic liver enzyme curves were established between lobular hepatitis and mixed-type hepatitis based on the combined consideration of histopathology and serum chemistry data. We proved that R value > 5 with cholestasis is a special feature of mixed hepatitis, which clarified the suspicion of the previous clinical classification of R value. Greater attention should be paid to drug-induced bile duct vanishing syndrome and drug-induced vascular injury. The pathological classification is simple to adopt and practically useful, which demonstrates the consistency between clinical features and liver pathology. The correlation between pathology and clinical biochemistry is an important way to acquire further understanding of DILI.

Drug-Induced Liver Injury

Drug-induced liver injury (DILI) refers to liver damage caused by over-the-counter and prescription drugs as well as herbal and dietary supplements. Hepatocytes, the main factory cells of the liver, are the primary targets of drug-related injury. During hepatocyte injury, loss of cell integrity results in a leak of liver contents, including a variety of enzymes, into the circulation. Currently, more than 1,000 drugs and herbal products have recognized hepatotoxic properties, with acetaminophen (APAP) being the most common cause of acute liver failure in the United States and amoxicillin-clavulanate the most common cause of severe liver injury worldwide. This review of DILI addresses the epidemiology, classification, pathophysiology, clinical manifestations, diagnosis, common idiosyncratic drug reactions, unusual drug reactions, treatment, and prognosis, with special sections on APAP hepatotoxicity and the approval of prescription drugs by the Food and Drug Administration. Figures show histologic features of DILI, mechanisms of liver injury, genome-wide association study results for lumiracoxib, APAP metabolism, and the Rumack-Matthew nomogram. Tables list classification of DILI, features of idiosyncratic drug reactions, histologic patterns of DILI, haplotypes associated with specific drug-related disorders, and the Roussel-Uclaf causality assessment method. This review contains 5 highly rendered figures, 5 tables, and 54 references.

Current Challenges and Controversies in Drug-Induced Liver Injury

Current key challenges and controversies encountered in the identification of potentially hepatotoxic drugs and the assessment of drug-induced liver injury (DILI) are covered in this article. There is substantial debate over the classification of DILI itself, including the definition and validity of terms such as 'intrinsic' and 'idiosyncratic'. So-called idiosyncratic DILI is typically rare and requires one or more susceptibility factors in individuals. Consequently, it has been difficult to reproduce in animal models, which has limited the understanding of its underlying mechanisms despite numerous hypotheses. Advances in predictive models would also help to enable preclinical elimination of drug candidates and development of novel biomarkers. A small number of liver laboratory tests have been routinely used to help identify DILI, but their interpretation can be limited and confounded by multiple factors. Improved preclinical and clinical biomarkers are therefore needed to accurately detect early signals of liver injury, distinguish drug hepatotoxicity from other forms of liver injury, and differentiate mild from clinically important liver injury. A range of potentially useful biomarkers are emerging, although so far most have only been used preclinically, with only a few validated and used in the clinic for specific circumstances. Advances in the development of genomic biomarkers will improve the prediction and detection of hepatic injury in future. Establishing a definitive clinical diagnosis of DILI can be difficult, since it is based on circumstantial evidence by excluding other aetiologies and, when possible, identifying a drug-specific signature. DILI signals based on standard liver test abnormalities may be affected by underlying diseases such as hepatitis B and C, HIV and cancer, as well as the concomitant use of hepatotoxic drugs to treat some of these conditions. Therefore, a modified approach to DILI assessment is justified in these special populations and a suggested framework is presented that takes into account underlying disease when evaluating DILI signals in individuals. Detection of idiosyncratic DILI should, in some respects, be easier in the postmarketing setting compared with the clinical development programme, since there is a much larger and more varied patient population exposure over longer timeframes. However, postmarketing safety surveillance is currently limited by the quantity and quality of information available to make an accurate diagnosis, the lack of a control group and the rarity of cases. The pooling of multiple healthcare databases, which could potentially contain different types of patient data, is advised to address some of these deficiencies.

Drug-induced liver injury: present and future

Liver injury due to prescription and nonprescription medications is a growing medical, scientific, and public health problem. Worldwide, the estimated annual incidence rate of drug-induced liver injury (DILI) is 13.9-24.0 per 100,000 inhabitants. DILI is one of the leading causes of acute liver failure in the US. In Korea, the annual extrapolated incidence of cases hospitalized at university hospital is 12/100,000 persons/year. Most cases of DILI are the result of idiosyncratic metabolic responses or unexpected reactions to medication. There is marked geographic variation in relevant agents; antibiotics, anticonvulsants, and psychotropic drugs are the most common offending agents in the West, whereas in Asia, 'herbs' and 'health foods or dietary supplements' are more common. Different medical circumstances also cause discrepancy in definition and classification of DILI between West and Asia. In the concern of causality assessment, the application of the Roussel Uclaf Causality Assessment Method (RUCAM) scale frequently undercounts the cases caused by 'herbs' due to a lack of previous information and incompatible time criteria. Therefore, a more objective and reproducible tool that could be used for the diagnosis of DILI caused by 'herbs' is needed in Asia. In addition, a reporting system similar to the Drug-Induced Liver Injury Network (DILIN) in the US should be established as soon as possible in Asia.