Liver functioning can affect a person’s metabolism, bile production and overall health. Diseases such as Jaundice, Hepatitis, Fatty Liver and Liver Cirrhosis can be life-threatening or cause permanent damages. AI can predict bile production, and through recent advances in computer vision and multimodal learning, abnormal growths can be detected early, alongside tracking of secondary symptoms on other parts of the body such as eyes, nails etc. It can also help predict causes such as excessive alcohol consumption.
This review article discusses the principles of applying AI on electronic health records, liver biopsy, and liver images. A few common AI approaches include logistic regression, decision tree, random forest, and XGBoost for data at a single time stamp, recurrent neural networks for sequential data, and deep neural networks for histology and images.
https://onlinelibrary.wiley.com/doi/abs/10.1111/jgh.15385
This work focuses on identifying jaundice from the sclera (yellowing of the eyes) using AI. A hybrid approach based on computer vision and classical machine learning is developed that can accurately determine the intensity of jaundice from the yellowness of the sclera. GANs are also used to develop synthetic data to make up for limited medical datasets for training.
https://www.sciencedirect.com/science/article/pii/S1877050923001114
AI based on radiology can 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. This review talks about the latest AI technology that can help with these applications.
https://pmc.ncbi.nlm.nih.gov/articles/PMC8473592/
Public health issues significantly affect the prevalence, diagnosis, treatment, and outcomes of liver diseases, particularly among racial/ethnic minorities, low-income populations, and those with limited access to healthcare. Structural racism and implicit bias, language barriers, Mistrust of the healthcare system, Geographic Public health issues and Immigration status all contribute to lack of appropriate treatment.
Rising rates of NAFLD and associated fibrosis have been observed in Hispanic persons, women aged > 50, and individuals experiencing food insecurity. Access to viral hepatitis screening and linkage to treatment are suboptimal for racial and ethnic minorities and individuals who are uninsured or underinsured, resulting in greater liver‐related mortality and later‐stage diagnoses of HCC as highlighted in this study.
The authors discuss that racial and ethnic minorities have lower rates of LT referral, more advanced liver disease at diagnosis, and are less likely to undergo living donor LT (LDLT). Gender-based Public health issues were observed in waitlist mortality and LT allocation. Women have lower LT rates after waitlisting. Medicaid insurance has been associated with higher rates of chronic liver disease and poor waitlist outcomes.
https://aasldpubs.onlinelibrary.wiley.com/doi/abs/10.1002/lt.25996
This article talks about stigmas associated with liver diseases and the opinions of healthcare providers. Specifically, over 30% felt that the use of the term “nonalcoholic” was stigmatizing to their patients as it potentially infers an association with alcohol use. Additionally, nearly 40% believed that the term “fatty liver” was stigmatizing due to its relation to obesity.
https://www.sciencedirect.com/science/article/pii/S0168827823052790
This is an emerging and critical area for improving population health while ensuring fairness in innovation. Liver diseases such as Hepatitis B/C, Non-Alcoholic Fatty Liver Disease (NAFLD), Alcohol-Associated Liver Disease (ALD), and Hepatocellular Carcinoma (HCC) disproportionately impact marginalized populations. Through early detection, screening, and personalized medicine, AI can help ensure fairer treatment across diverse populations.
There are several mechanisms through which AI/ML could contribute to health inequities in gastroenterology and hepatology, including diagnosis of liver transplantation, colorectal cancer screening and many others. This review adapts a framework for ethical AI/ML development and application to gastroenterology and hepatology such that clinical practice is advanced while minimising bias and optimising Public health issues.
https://gut.bmj.com/content/71/9/1909.abstract
This research aims to improve the accuracy of liver disease classification using Quantum Feature Engineering (QFE) and the Synthetic Minority Over-sampling Technique and Tomek Links (SMOTE-Tomek) data balancing technique to ensure all socioeconomic and demographically diverse populations have adequate dataset representation during training.
https://dl.futuretechsci.org/id/eprint/91/
The AEEH launched LiverAI as a specialized area focused on AI applications in hepatology, motivated by the need to improve knowledge and access to AI tools specifically designed for clinical practice and research in liver diseases. LiverAI has extensive scientific content related to the pathophysiology, diagnosis, treatment, and research of liver diseases. This can help educate minority populations encouraging them to seek treatment earlier.
https://www.sciencedirect.com/science/article/abs/pii/S021057052400075X