Automated Machine Learning Diagnostic Support System as a Computational Biomarker for Detecting Drug-Induced Liver Injury Patterns in Whole Slide Liver Pathology Images

Drug-induced liver injury (DILI) is a challenging disease to diagnose, a leading cause of acute liver failure, and responsible for drug withdrawal from the market. There is no symptom, no biomarker or test for detection, no therapy, but discontinuation of the drug. Pharmaceutical companies spend huge money, time, and scientific research efforts to test DILI effects and drug efficacy. A preclinical diagnostic support system is designed and proposed for DILI detection and classification on liver biopsy histopathology images. Heterogeneity features and automated machine learning (AutoML) models were tested to classify DILI injury patterns on whole slide image. Fractal and lacunarity values were used to detect hepatocellular necrotic injury patterns caused on a rat liver (in vivo) by 10 drugs at four dose levels. Correlations between fractal and lacunarity values were statistically analyzed for the 10 drugs; the Pearson correlation (r = 0.9809), p-value (1.6612E-06), and R2 (0.9582) were found to be high in the case of carbon tetrachloride. The AutoML model was tested to understand the injury patterns on a subset of 1,277 histology images. The AutoML algorithm was able to classify necrotic injury patterns accurately with an average precision of 98.6% on a score threshold of 0.5.

MEDICAL COMORBIDITY AND COMPLICATIONS

Like their peers in the general youth population, youth with chronic medical conditions (YCMC) are at risk for substance use, including nonmedical use of prescription medications. However, given dangerous disease-substance interactions, the stakes for detecting and intervening on substance use are perhaps even higher for YCMC. Given the risk for nonadherence with chronic disease management, it is incumbent on primary care providers, specialty providers, and behavioral health specialists to be vigilant in asking about substance use and providing brief counseling and referral to substance use treatment when appropriate.

Drug-induced acute liver failure and gastrointestinal complications

The objective of this article is to describe adverse drug events related to the liver and gastrointestinal tract in critically ill patients. PubMed and other resources were used to identify information related to drug-induced acute liver failure, gastrointestinal hypomotility, constipation, diarrhea, gastrointestinal bleeding, and pancreatitis in critically ill patients. This information was reviewed, and data regarding pathophysiology, common drug causes, and guidelines for prevention and management were collected and summarized. In cases in which data in critically ill patients were unavailable, data were extrapolated from other patient populations. Drug-induced acute liver failure can be caused by many drugs routinely used in the intensive care unit and may be associated with significant morbidity and mortality. Drug-related hypomotility and constipation and drug-related diarrhea are reported with many drugs, and these are common adverse drug events in critically ill patients that can substantially complicate the care of these patients. Drug-induced gastrointestinal bleeding and drug-induced pancreatitis occur less frequently, can range in disease severity, and can be associated with morbidity and mortality. Many drugs used in critically ill patients are associated with adverse drug events related to the liver and gastrointestinal tract. Critical care clinicians should be aware of common drug causes of drug-induced acute liver failure, gastrointestinal hypomotility, constipation, diarrhea, gastrointestinal bleeding, and pancreatitis, and should be familiar with the prevention and management of these diverse conditions.