Artificial intelligence models for the diagnosis and management of liver diseases

Advancements in Artificial Intelligence-Enhanced Imaging Diagnostics for the Management of Liver Disease—Applications and Challenges in Personalized Care

Liver disease can significantly impact life expectancy, making early diagnosis and therapeutic intervention critical challenges in medical care. Imaging diagnostics play a crucial role in diagnosing and managing liver diseases. Recently, the application of artificial intelligence (AI) in medical imaging analysis has become indispensable in healthcare. AI, trained on vast datasets of medical images, has sometimes demonstrated diagnostic accuracy that surpasses that of human experts. AI-assisted imaging diagnostics are expected to contribute significantly to the standardization of diagnostic quality. Furthermore, AI has the potential to identify image features that are imperceptible to humans, thereby playing an essential role in clinical decision-making. This capability enables physicians to make more accurate diagnoses and develop effective treatment strategies, ultimately improving patient outcomes. Additionally, AI is anticipated to become a powerful tool in personalized medicine. By integrating individual patient imaging data with clinical information, AI can propose optimal plans for treatment, making it an essential component in the provision of the most appropriate care for each patient. Current reports highlight the advantages of AI in managing liver diseases. As AI technology continues to evolve, it is expected to advance personalized diagnostics and treatments and contribute to overall improvements in healthcare quality.

Prognostic models in acute liver failure-historic evolution and newer updates "prognostic models in acute liver failure"

Acute liver failure (ALF) is a rare and dynamic syndrome occurring as a sequela of severe acute liver injury (ALI). Its mortality ranges from 50% to 75% based on the aetiology, patients age and severity of encephalopathy at admission. With improvement in intensive care techniques, transplant-free survival in ALF has improved over time. Timely recognition of patients who are unlikely to survive with medical intervention alone is crucial since these individuals may rapidly develop multiorgan failure and render liver transplantation futile. Various predictive models, biomarkers and AI-based models are currently used in clinical practice, each with its fallacies. The King's College Hospital criteria (KCH) were initially established in 1989 to identify patients with acute liver failure (ALF) caused by paracetamol overdose or other causes who are unlikely to improve with conventional treatment and would benefit from a liver transplant. Since then, various models have been developed and validated worldwide. Most models include age, aetiology of liver disease, encephalopathy grade, and liver injury markers like INR, lactate, factor V level, factor VIII/V ratio and serum bilirubin. But none of the currently available models are dynamic and lack accuracy in predicting transplant free survival. There is an increasing interest in developing prognostic serum biomarkers that when used alone or in combination with clinical models enhance the accuracy of predicting outcomes in ALF. Genomics, transcriptomics, proteomics, and metabolomics as well as machine learning and artificial intelligence (AI) algorithms are areas of interest for developing higher-precision predictive models. Overall, the future of prognostic models in ALF is promising, with ongoing research paving the way for more accurate, personalized, and dynamic risk assessment tools that can potentially save lives in this challenging condition. This article summarizes the history of prognostic models in ALF and future trends.

Proceedings of the 5th Meeting of Translational Hepatology, organized by the Spanish Association for the Study of the Liver (AEEH)

This is the summary report of the 5th Translational Hepatology Meeting, endorsed by the Spanish Association for the Study of the Liver (AEEH) and held in Seville, Spain, in October 2023. The meeting aimed to provide an update on the latest advances in the field of basic and translational hepatology, covering different molecular, cellular, and pathophysiological aspects of the most relevant clinical challenges in liver pathologies. This includes the identification of novel biomarkers and diagnostic tools, the understanding of the relevance of immune response and inflammation in liver diseases, the characterization of current medical approaches to reverse liver diseases, the incorporation of novel molecular insights through omics techniques, or the characterization of the impact of toxic and metabolic insults, as well as other organ crosstalk, in liver pathophysiology.

Physiological network approach to prognosis in cirrhosis: A shifting paradigm

Decompensated liver disease is complicated by multi-organ failure and poor prognosis. The prognosis of patients with liver failure often dictates clinical management. Current prognostic models have focused on biomarkers considered as individual isolated units. Network physiology assesses the interactions among multiple physiological systems in health and disease irrespective of anatomical connectivity and defines the influence or dependence of one organ system on another. Indeed, recent applications of network mapping methods to patient data have shown improved prediction of response to therapy or prognosis in cirrhosis. Initially, different physical markers have been used to assess physiological coupling in cirrhosis including heart rate variability, heart rate turbulence, and skin temperature variability measures. Further, the parenclitic network analysis was recently applied showing that organ systems connectivity is impaired in patients with decompensated cirrhosis and can predict mortality in cirrhosis independent of current prognostic models while also providing valuable insights into the associated pathological pathways. Moreover, network mapping also predicts response to intravenous albumin in patients hospitalized with decompensated cirrhosis. Thus, this review highlights the importance of evaluating decompensated cirrhosis through the network physiologic prism. It emphasizes the limitations of current prognostic models and the values of network physiologic techniques in cirrhosis.

Hybrid Quantum Image Classification and Federated Learning for Hepatic Steatosis Diagnosis

In the realm of liver transplantation, accurately determining hepatic steatosis levels is crucial. Recognizing the essential need for improved diagnostic precision, particularly for optimizing diagnosis time by swiftly handling easy-to-solve cases and allowing the expert time to focus on more complex cases, this study aims to develop cutting-edge algorithms that enhance the classification of liver biopsy images. Additionally, the challenge of maintaining data privacy arises when creating automated algorithmic solutions, as sharing patient data between hospitals is restricted, further complicating the development and validation process. This research tackles diagnostic accuracy by leveraging novel techniques from the rapidly evolving field of quantum machine learning, known for their superior generalization abilities. Concurrently, it addresses privacy concerns through the implementation of privacy-conscious collaborative machine learning with federated learning. We introduce a hybrid quantum neural network model that leverages real-world clinical data to assess non-alcoholic liver steatosis accurately. This model achieves an image classification accuracy of 97%, surpassing traditional methods by 1.8%. Moreover, by employing a federated learning approach that allows data from different clients to be shared while ensuring privacy, we maintain an accuracy rate exceeding 90%. This initiative marks a significant step towards a scalable, collaborative, efficient, and dependable computational framework that aids clinical pathologists in their daily diagnostic tasks.