Application of Artificial Intelligence for the Diagnosis and Treatment of Liver Diseases

Machine-Learning-Based Identification of Key Feature RNA-Signature Linked to Diagnosis of Hepatocellular Carcinoma

Background

Hepatocellular carcinoma (HCC) is the third prime cause of malignancy-related mortality worldwide. Early and accurate identification of HCC is crucial for good prognosis, efficacy of therapy, and survival rates of the patients. We aimed to develop a machine-learning model incorporating differentially expressed RNA signatures with laboratory parameters to construct an RNA signature-based diagnostic model for HCC.

Methods

We have used five classifiers (KNN, RF, SVM, LGBM, and DNNs) to predict the liver disease (HCC). The classifiers were trained on 187 samples and then tested on 80 samples. The model included 22 features (age, sex, smoking, cirrhosis, non-cirrhosis, albumin, ALT, AST bilirubin (total and direct), INR, AFP, HBV Ag, HCV Abs, RQmiR-1298, RQmiR-1262, RQmiR-106b-3p, RQmRNARAB11A, and RQSTAT1, RQmRNAATG12, RQLnc-WRAP53, RQLncRNA- RP11-513I15.6).

Results

LGBM achieved the highest accuracy of 98.75% in predicting HCC among all models surpassing Random Forest (96.25%), DNN (91.25%), SVC (88.75%), and KNN (87.50%).

Conclusion

Our machine-learning model incorporating the expression data of RAB11A/STAT1/ATG12/miR-1262/miR-1298/miR-106b-3p/lncRNA-RP11-513I15.6/lncRNA-WRAP53 signature and clinical data represents a potential novel diagnostic model for HCC.

Optimizing time prediction and error classification in early melanoma detection using a hybrid RCNN-LSTM model

Skin cancer is a terrifying disorder that affects all individuals. Due to the significant increase in the rate of melanoma skin cancer, early detection of skin cancer is now more critical than ever before. Malignant melanoma is one of the most serious forms of skin cancer, and it is caused by abnormal melanocyte cell growth. In recent years, skin cancer predictive categorization has become more accurate and predictive due to multiple deep learning algorithms. Malignant melanoma is diagnosed using the Recurrent Convolution Neural Network-Long Short-Term Memory (RCNN-LSTM), which is one of the deep learning classification approaches. Using the International Skin Image Collection and the RCNN-LSTM, the data are categorized and analyzed to gain a better understanding of skin cancer. The method begins with data preprocessing, which prepares the dataset for classification. Additionally, the RCNN is employed to extract the features that are vital to the prediction process. The LSTM is accountable for the final step, classification. There are further factors to examine, such as the precision of 94.60%, the sensitivity of 95.67%, and the F1-score of 95.13%. Other benefits of the suggested study include shorter prediction durations of 95.314, 122.530, and 131.205 s and lower model loss of 0.25%, 0.19%, and 0.15% for input sizes 10, 15, and 20, respectively. Three datasets had a reduced categorization error of 5.11% and an accuracy of 95.42%. In comparison to previous approaches, the work discussed here produces superior outcomes. RESEARCH HIGHLIGHTS: Recurrent convolutional neural network (RCNN) deep learning approach for optimizing time prediction and error classification in early melanoma detection. It extracts a high number of specific features from the skin disease image, making the classification process easier and more accurate. To reduce classification errors in accurately detecting melanoma, context dependency is considered in this work. By accounting for context dependency, the deprivation state is avoided, preventing performance degradation in the model. To minimize melanoma detection model loss, a skin disease image augmentation or regularization process is performed in this work. This strategy improves the accuracy of the model when applied to fresh, previously unobserved data.

Novel approach exploring the correlation between presepsin and routine laboratory parameters using explainable artificial intelligence

Although presepsin, a crucial biomarker for the diagnosis and management of sepsis, has gained prominence in contemporary medical research, its relationship with routine laboratory parameters, including demographic data and hospital blood test data, remains underexplored. This study integrates machine learning with explainable artificial intelligence (XAI) to provide insights into the relationship between presepsin and these parameters. Advanced machine learning classifiers provide a multilateral view of data and play an important role in highlighting the interrelationships between presepsin and other parameters. XAI enhances analysis by ensuring transparency in the model's decisions, especially in selecting key parameters that significantly enhance classification accuracy. Utilizing XAI, this study successfully identified critical parameters that increased the predictive accuracy for sepsis patients, achieving a remarkable ROC AUC of 0.97 and an accuracy of 0.94. This breakthrough is possibly attributed to the comprehensive utilization of XAI in refining parameter selection, thus leading to these significant predictive metrics. The presence of missing data in datasets is another concern; this study addresses it by employing Extreme Gradient Boosting (XGBoost) to manage missing data, effectively mitigating potential biases while preserving both the accuracy and relevance of the results. The perspective of examining data from higher dimensions using machine learning transcends traditional observation and analysis. The findings of this study hold the potential to enhance patient diagnoses and treatment, underscoring the value of merging traditional research methods with advanced analytical tools.

Predicting the 28-day prognosis of acute-on-chronic liver failure patients based on machine learning

BACKGROUND

We aimed to establish a prognostic predictive model based on machine learning (ML) methods to predict the 28-day mortality of acute-on-chronic liver failure (ACLF) patients, and to evaluate treatment effectiveness.

METHODS

ACLF patients from six tertiary hospitals were included for analysis. Features for ML models' development were selected by LASSO regression. Models' performance was evaluated by area under the curve (AUC) and accuracy. Shapley additive explanation was used to explain the ML model.

RESULTS

Of the 736 included patients, 587 were assigned to a training set and 149 to an external validation set. Features selected included age, hepatic encephalopathy, total bilirubin, PTA, and creatinine. The eXtreme Gradient Boosting (XGB) model outperformed other ML models in the prognostic prediction of ACLF patients, with the highest AUC and accuracy. Delong's test demonstrated that the XGB model outperformed Child-Pugh score, MELD score, CLIF-SOFA, CLIF-C OF, and CLIF-C ACLF. Sequential assessments at baseline, day 3, day 7, and day 14 improved the predictive performance of the XGB-ML model and can help clinicians evaluate the effectiveness of medical treatment.

CONCLUSIONS

We established an XGB-ML model to predict the 28-day mortality of ACLF patients as well as to evaluate the treatment effectiveness.

Deep learning models for predicting the survival of patients with hepatocellular carcinoma based on a surveillance, epidemiology, and end results (SEER) database analysis

Hepatocellular carcinoma (HCC) is a common malignancy with poor survival and requires long-term follow-up. Hence, we collected information on patients with Primary Hepatocellular Carcinoma in the United States from the Surveillance, Epidemiology, and EndResults (SEER) database. We used this information to establish a deep learning with a multilayer neural network (the NMTLR model) for predicting the survival rate of patients with Primary Hepatocellular Carcinoma. HCC patients pathologically diagnosed between January 2011 and December 2015 in the SEER (Surveillance, Epidemiology, and End Results) database of the National Cancer Institute of the United States were selected as study subjects. We utilized two deep learning-based algorithms (DeepSurv and Neural Multi-Task Logistic Regression [NMTLR]) and a machine learning-based algorithm (Random Survival Forest [RSF]) for model training. A multivariable Cox Proportional Hazards (CoxPH) model was also constructed for comparison. The dataset was randomly divided into a training set and a test set in a 7:3 ratio. The training dataset underwent hyperparameter tuning through 1000 iterations of random search and fivefold cross-validation. Model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). The accuracy of predicting 1-year, 3-year, and 5-year survival rates was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Area Under the Curve (AUC). The primary outcomes were the 1-year, 3-year, and 5-year overall survival rates. Models were developed using DeepSurv, NMTLR, RSF, and Cox Proportional Hazards regression. Model differentiation was evaluated using the C-index, calibration with concordance plots, and risk stratification capability with the log-rank test. The study included 2197 HCC patients, randomly divided into a training cohort (70%, n = 1537) and a testing cohort (30%, n = 660). Clinical characteristics between the two cohorts showed no significant statistical difference (p > 0.05). The deep learning models outperformed both RSF and CoxPH models, with C-indices of 0.735 (NMTLR) and 0.731 (DeepSurv) in the test dataset. The NMTLR model demonstrated enhanced accuracy and well-calibrated survival estimates, achieving an Area Under the Curve (AUC) of 0.824 for 1-year survival predictions, 0.813 for 3-year, and 0.803 for 5-year survival rates. This model's superior calibration and discriminative ability enhance its utility for clinical prognostication in Primary Hepatocellular Carcinoma. We deployed the NMTLR model as a web application for clinical practice. The NMTLR model have potential advantages over traditional linear models in prognostic assessment and treatment recommendations. This novel analytical approach may provide reliable information on individual survival and treatment recommendations for patients with primary liver cancer.

Radiomics Analysis of Preprocedural CT Imaging for Outcome Prediction after Transjugular Intrahepatic Portosystemic Shunt Creation

PURPOSE

To evaluate the role of radiomics in preoperative outcome prediction in cirrhotic patients who underwent transjugular intrahepatic portosystemic shunt (TIPS) using "controlled expansion covered stents".

MATERIALS AND METHODS

This retrospective institutional review board-approved study included cirrhotic patients undergoing TIPS with controlled expansion covered stent placement. From preoperative CT images, the whole liver was segmented into Volumes of Interest (VOIs) at the unenhanced and portal venous phase. Radiomics features were extracted, collected, and analyzed. Subsequently, receiver operating characteristic (ROC) curves were drawn to assess which features could predict patients' outcomes. The endpoints studied were 6-month overall survival (OS), development of hepatic encephalopathy (HE), grade II or higher HE according to West Haven Criteria, and clinical response, defined as the absence of rebleeding or ascites. A radiomic model for outcome prediction was then designed.

RESULTS

A total of 76 consecutive cirrhotic patients undergoing TIPS creation were enrolled. The highest performances in terms of the area under the receiver operating characteristic curve (AUROC) were observed for the "clinical response" and "survival at 6 months" outcome with 0.755 and 0.767, at the unenhanced and portal venous phase, respectively. Specifically, on basal scans, accuracy, specificity, and sensitivity were 66.42%, 63.93%, and 73.75%, respectively. At the portal venous phase, an accuracy of 65.34%, a specificity of 62.38%, and a sensitivity of 74.00% were demonstrated.

CONCLUSIONS

A pre-interventional machine learning-based CT radiomics algorithm could be useful in predicting survival and clinical response after TIPS creation in cirrhotic patients.

Accurate Liver Fibrosis Detection Through Hybrid MRMR-BiLSTM-CNN Architecture with Histogram Equalization and Optimization

The early detection and accurate diagnosis of liver fibrosis, a progressive and potentially serious liver condition, are crucial for effective medical intervention. Invasive methods like biopsies for diagnosis can be risky and expensive. This research presents a novel computer-aided diagnosis model for liver fibrosis using a hybrid approach of minimum redundancy maximum relevance (MRMR) feature selection, bidirectional long short-term memory (BiLSTM), and convolutional neural networks (CNN). The proposed model involves multiple stages, including image acquisition, preprocessing, feature representation, fibrous tissue identification, and classification. Notably, histogram equalization is employed to enhance image quality by addressing variations in brightness levels. Performance evaluation encompasses a range of metrics such as accuracy, precision, sensitivity, specificity, F1 score, and error rate. Comparative analyses with established methods like DCNN, ANN-FLI, LungNet22, and SDAE-GAN underscore the efficacy of the proposed model. The innovative integration of hybrid MRMR-BiLSTM-CNN architecture and the horse herd optimization algorithm significantly enhances accuracy and F1 score, even with small datasets. The model tackles the complexities of hyperparameter optimization through the IHO algorithm and reduces training time by leveraging MRMR feature selection. In practical application, the proposed hybrid MRMR-BiLSTM-CNN method demonstrates remarkable performance with a 97.8% accuracy rate in identifying liver fibrosis images. It exhibits high precision, sensitivity, specificity, and minimal error rate, showcasing its potential for accurate and non-invasive diagnosis.

Predictive modeling of deep vein thrombosis risk in hospitalized patients: A Q-learning enhanced feature selection model

Deep vein thrombosis (DVT) represents a critical health concern due to its potential to lead to pulmonary embolism, a life-threatening complication. Early identification and prediction of DVT are crucial to prevent thromboembolic events and implement timely prophylactic measures in high-risk individuals. This study aims to examine the risk determinants associated with acute lower extremity DVT in hospitalized individuals. Additionally, it introduces an innovative approach by integrating Q-learning augmented colony predation search ant colony optimizer (QL-CPSACO) into the analysis. This algorithm, then combined with support vector machines (SVM), forms a bQL-CPSACO-SVM feature selection model dedicated to crafting a clinical risk prognostication model for DVT. The effectiveness of the proposed algorithm's optimization and the model's accuracy are assessed through experiments utilizing the CEC 2017 benchmark functions and predictive analyses on the DVT dataset. The experimental results reveal that the proposed model achieves an outstanding accuracy of 95.90% in predicting DVT. Key parameters such as D-dimer, normal plasma prothrombin time, prothrombin percentage activity, age, previously documented DVT, leukocyte count, and thrombocyte count demonstrate significant value in the prognostication of DVT. The proposed method provides a basis for risk assessment at the time of patient admission and offers substantial guidance to physicians in making therapeutic decisions.

Insights into ALD and AUD diagnosis and prognosis: Exploring AI and multimodal data streams

The rapid evolution of artificial intelligence and the widespread embrace of digital technologies have ushered in a new era of clinical research and practice in hepatology. Although its potential is far from realization, these significant strides have generated new opportunities to address existing gaps in the delivery of care for patients with liver disease. In this review, we discuss how artificial intelligence and opportunities for multimodal data integration can improve the diagnosis, prognosis, and management of alcohol-associated liver disease. An emphasis is made on how these approaches will also benefit the detection and management of alcohol use disorder. Our discussion encompasses challenges and limitations, concluding with a glimpse into the promising future of these advancements.

Artificial Intelligence in Liver Diseases: Recent Advances

Liver diseases cause a significant burden on public health worldwide. In spite of great advances during recent years, there are still many challenges in the diagnosis and treatment of liver diseases. During recent years, artificial intelligence (AI) has been widely used for the diagnosis, risk stratification, and prognostic prediction of various diseases based on clinical datasets and medical images. Accumulative studies have shown its performance for diagnosing patients with nonalcoholic fatty liver disease and liver fibrosis and assessing their severity, and for predicting treatment response and recurrence of hepatocellular carcinoma, outcomes of liver transplantation recipients, and risk of drug-induced liver injury. Herein, we aim to comprehensively summarize the current evidence regarding diagnostic, prognostic, and/or therapeutic role of AI in these common liver diseases.

Development of a machine learning-based model to predict hepatic inflammation in chronic hepatitis B patients with concurrent hepatic steatosis: a cohort study

Background

With increasingly prevalent coexistence of chronic hepatitis B (CHB) and hepatic steatosis (HS), simple, non-invasive diagnostic methods to accurately assess the severity of hepatic inflammation are needed. We aimed to build a machine learning (ML) based model to detect hepatic inflammation in patients with CHB and concurrent HS.

Methods

We conducted a multicenter, retrospective cohort study in China. Treatment-naive CHB patients with biopsy-proven HS between April 2004 and September 2022 were included. The optimal features for model development were selected by SHapley Additive explanations, and an ML algorithm with the best accuracy to diagnose moderate to severe hepatic inflammation (Scheuer's system ≥ G3) was determined and assessed by decision curve analysis (DCA) and calibration curve. This study is registered with ClinicalTrials.gov (NCT05766449).

Findings

From a pool of 1,787 treatment-naive patients with CHB and HS across eleven hospitals, 689 patients from nine of these hospitals were chosen for the development of the diagnostic model. The remaining two hospitals contributed to two independent external validation cohorts, comprising 509 patients in validation cohort 1 and 589 in validation cohort 2. Eleven features regarding inflammation, hepatic and metabolic functions were identified. The gradient boosting classifier (GBC) model showed the best performance in predicting moderate to severe hepatic inflammation, with an area under the receiver operating characteristic curve (AUROC) of 0.86 (95% CI 0.83-0.88) in the training cohort, and 0.89 (95% CI 0.86-0.92), 0.76 (95% CI 0.73-0.80) in the first and second external validation cohorts, respectively. A publicly accessible web tool was generated for the model.

Interpretation

Using simple parameters, the GBC model predicted hepatic inflammation in CHB patients with concurrent HS. It holds promise for guiding clinical management and improving patient outcomes.

Funding

This research was supported by the National Natural Science Foundation of China (No. 82170609, 81970545), Natural Science Foundation of Shandong Province (Major Project) (No. ZR2020KH006), Natural Science Foundation of Jiangsu Province (No.BK20231118), Tianjin Key Medical Discipline (Specialty), Construction Project, TJYXZDXK-059B, Tianjin Health Science and Technology Project key discipline special, TJWJ2022XK034, and Research project of Chinese traditional medicine and Chinese traditional medicine combined with Western medicine of Tianjin municipal health and Family Planning Commission (2021022).

Algorithms for Early Detection of Silent Liver Fibrosis in the Primary Care Setting

More than one-third of the adult world population has steatotic liver disease (SLD), with a few percent of individuals developing cirrhosis after decades of silent liver fibrosis accumulation. Lack of systematic early detection causes most patients to be diagnosed late, after decompensation, when treatment has limited effect and survival is poor. Unfortunately, no isolated screening test in primary care can sufficiently predict advanced fibrosis from SLD. Recent efforts, therefore, combine several parameters into screening algorithms, to increase diagnostic accuracy. Besides patient selection, for example, by specific characteristics, algorithms include nonpatented or patented blood tests and liver stiffness measurements using elastography-based techniques. Algorithms can be composed as a set of sequential tests, as recommended by most guidelines on primary care pathways. Future use of algorithms that are easy to interpret, cheap, and semiautomatic will improve the management of patients with SLD, to the benefit of global health care systems.

MELD 3.0 in Advanced Chronic Liver Disease

The MELD (model for end-stage liver disease) 3.0 score was developed to replace the MELD-Na score that is currently used to prioritize liver allocation for cirrhotic patients awaiting liver transplantation in the United States. The MELD 3.0 calculator includes new inputs from patient sex and serum albumin levels and has new weights for serum sodium, bilirubin, international normalized ratio, and creatinine levels. It is expected that use of MELD 3.0 scores will reduce overall waitlist mortality modestly and improve access for female liver transplant candidates. The utility of MELD 3.0 and PELDcre (pediatric end-stage liver disease, creatinine) scores for risk stratification in cirrhotic patients undergoing major abdominal surgery, placement of a transjugular intrahepatic portosystemic shunt, and other interventions requires further study. This article reviews the background of the MELD score and the rationale to create MELD 3.0 as well as potential implications of using this newer risk stratification tool in clinical practice.

Recent Advances in the Pathogenesis and Clinical Evaluation of Portal Hypertension in Chronic Liver Disease

In chronic liver disease, hepatic stellate cell activation and degeneration of liver sinusoidal endothelial cells lead to structural changes, which are secondary to fibrosis and the presence of regenerative nodules in the sinusoids, and to functional changes, which are related to vasoconstriction. The combination of such changes increases intrahepatic vascular resistance and causes portal hypertension. The subsequent increase in splanchnic and systemic hyperdynamic circulation further increases the portal blood flow, thereby exacerbating portal hypertension. In clinical practice, the hepatic venous pressure gradient is the gold-standard measure of portal hypertension; a value of ≥10 mm Hg is defined as clinically significant portal hypertension, which is severe and is associated with the risk of liver-related events. Hepatic venous pressure gradient measurement is somewhat invasive, so evidence on the utility of risk stratification by elastography and serum biomarkers is needed. The various stages of cirrhosis are associated with different outcomes. In viral hepatitis-related cirrhosis, viral suppression or elimination by nucleos(t)ide analog or direct-acting antivirals results in recompensation of liver function and portal pressure. However, careful follow-up should be continued, because some cases have residual clinically significant portal hypertension even after achieving sustained virologic response. In this study, we reviewed the current and future prospects for portal hypertension.

Application of Machine Learning Based on Structured Medical Data in Gastroenterology

The era of big data has led to the necessity of artificial intelligence models to effectively handle the vast amount of clinical data available. These data have become indispensable resources for machine learning. Among the artificial intelligence models, deep learning has gained prominence and is widely used for analyzing unstructured data. Despite the recent advancement in deep learning, traditional machine learning models still hold significant potential for enhancing healthcare efficiency, especially for structured data. In the field of medicine, machine learning models have been applied to predict diagnoses and prognoses for various diseases. However, the adoption of machine learning models in gastroenterology has been relatively limited compared to traditional statistical models or deep learning approaches. This narrative review provides an overview of the current status of machine learning adoption in gastroenterology and discusses future directions. Additionally, it briefly summarizes recent advances in large language models.

A Systematic Review of the Barriers to the Implementation of Artificial Intelligence in Healthcare

Artificial intelligence (AI) is expected to improve healthcare outcomes by facilitating early diagnosis, reducing the medical administrative burden, aiding drug development, personalising medical and oncological management, monitoring healthcare parameters on an individual basis, and allowing clinicians to spend more time with their patients. In the post-pandemic world where there is a drive for efficient delivery of healthcare and manage long waiting times for patients to access care, AI has an important role in supporting clinicians and healthcare systems to streamline the care pathways and provide timely and high-quality care for the patients. Despite AI technologies being used in healthcare for some decades, and all the theoretical potential of AI, the uptake in healthcare has been uneven and slower than anticipated and there remain a number of barriers, both overt and covert, which have limited its incorporation. This literature review highlighted barriers in six key areas: ethical, technological, liability and regulatory, workforce, social, and patient safety barriers. Defining and understanding the barriers preventing the acceptance and implementation of AI in the setting of healthcare will enable clinical staff and healthcare leaders to overcome the identified hurdles and incorporate AI technologies for the benefit of patients and clinical staff.

NASH drug treatment development: challenges and lessons

Non-alcoholic fatty liver disease (NAFLD) has become the most common chronic liver disease worldwide. Although NAFLD is tightly linked to obesity and type 2 diabetes, this liver disease also affects individuals who do not have obesity. NAFLD increases the risk of developing cardiovascular disease, chronic kidney disease, and certain extrahepatic cancers. There is currently no licensed pharmacotherapy for NAFLD, despite numerous clinical trials in the past two decades. Currently, the reason so few drugs have been successful in the treatment of NAFLD in a trial setting is not fully understood. As cardiovascular disease is the predominant cause of mortality in people with NAFLD, future pharmacotherapies for NAFLD must consider associated cardiometabolic risk factors. The successful use of glucose-lowering drugs in the treatment of type 2 diabetes in patients with NAFLD indicates that this strategy is important, and worth developing further. Greater public awareness of NAFLD is needed because collaboration between all stakeholders is vital to enable a holistic approach to successful treatment.

Clinical decision support and electronic interventions to improve care quality in chronic liver diseases and cirrhosis

Significant quality gaps exist in the management of chronic liver diseases and cirrhosis. Clinical decision support systems-information-driven tools based in and launched from the electronic health record-are attractive and potentially scalable prospective interventions that could help standardize clinical care in hepatology. Yet, clinical decision support systems have had a mixed record in clinical medicine due to issues with interoperability and compatibility with clinical workflows. In this review, we discuss the conceptual origins of clinical decision support systems, existing applications in liver diseases, issues and challenges with implementation, and emerging strategies to improve their integration in hepatology care.

A Practical Model for Predicting Esophageal Variceal Rebleeding in Patients with Hepatitis B-Associated Cirrhosis

Background

Variceal rebleeding is a significant and potentially life-threatening complication of cirrhosis. Unfortunately, currently, there is no reliable method for stratifying high-risk patients. Liver stiffness measurements (LSM) have been shown to have a predictive value in identifying complications associated with portal hypertension, including first-time bleeding. However, there is a lack of evidence to confirm that LSM is reliable in predicting variceal rebleeding. The objective of our study was to evaluate the ability of generating a extreme gradient boosting (XGBoost) algorithm model to improve the prediction of variceal rebleeding.

Methods

This retrospective analysis examined a cohort of 284 patients with hepatitis B-related cirrhosis. XGBoost models were developed using laboratory data, LSM, and imaging data to predict the risk of rebleeding in the patients. In addition, we compared the XGBoost models with traditional logistic regression (LR) models. We evaluated and compared the two models using the area under the receiver operating characteristic curve (AUROC) and other model performance parameters. Lastly, we validated the models using nomograms and decision curve analysis (DCA).

Results

During a median follow-up of 66.6 weeks, 72 patients experienced rebleeding, including 21 (7.39%) and 61 (21.48%) patients who rebleed within 6 weeks and 1 year, respectively. In brief, the AUC of the LR models in predicting rebleeding at 6 weeks and 1 year was 0.828 (0.759-0.897) and 0.799 (0.738-0.860), respectively. In contrast, the accuracy of the XGBoost model in predicting rebleeding at 6 weeks and 1 year was 0.985 (0.907-0.731) and 0.931 (0.806-0.935), respectively. LSM and high-density lipoprotein (HDL) levels differed significantly between the rebleeding and nonrebleeding groups, with LSM being a reliable predictor in those models. The XGBoost models outperformed the LR models in predicting rebleeding within 6 weeks and 1 year, as demonstrated by the ROC and DCA curves.

Conclusion

The XGBoost algorithm model can achieve higher accuracy than the LR model in predicting rebleeding, making it a clinically beneficial tool. This implies that the XGBoost model is better suited for predicting the risk of esophageal variceal rebleeding in patients.

Large-scale identification of undiagnosed hepatic steatosis using natural language processing

Background

Nonalcoholic fatty liver disease (NAFLD) is a major cause of liver-related morbidity in people with and without diabetes, but it is underdiagnosed, posing challenges for research and clinical management. Here, we determine if natural language processing (NLP) of data in the electronic health record (EHR) could identify undiagnosed patients with hepatic steatosis based on pathology and radiology reports.

Methods

A rule-based NLP algorithm was built using a Linguamatics literature text mining tool to search 2.15 million pathology report and 2.7 million imaging reports in the Penn Medicine EHR from November 2014, through December 2020, for evidence of hepatic steatosis. For quality control, two independent physicians manually reviewed randomly chosen biopsy and imaging reports (n = 353, PPV 99.7%).

Findings

After exclusion of individuals with other causes of hepatic steatosis, 3007 patients with biopsy-proven NAFLD and 42,083 patients with imaging-proven NAFLD were identified. Interestingly, elevated ALT was not a sensitive predictor of the presence of steatosis, and only half of the biopsied patients with steatosis ever received an ICD diagnosis code for the presence of NAFLD/NASH. There was a robust association for PNPLA3 and TM6SF2 risk alleles and steatosis identified by NLP. We identified 234 disorders that were significantly over- or underrepresented in all subjects with steatosis and identified changes in serum markers (e.g., GGT) associated with presence of steatosis.

Interpretation

This study demonstrates clear feasibility of NLP-based approaches to identify patients whose steatosis was indicated in imaging and pathology reports within a large healthcare system and uncovers undercoding of NAFLD in the general population. Identification of patients at risk could link them to improved care and outcomes.

Funding

The study was funded by US and German funding sources that did provide financial support only and had no influence or control over the research process.

Deep learning nomogram based on Gd-EOB-DTPA MRI for predicting early recurrence in hepatocellular carcinoma after hepatectomy

OBJECTIVES

The accurate prediction of post-hepatectomy early recurrence in patients with hepatocellular carcinoma (HCC) is crucial for decision-making regarding postoperative adjuvant treatment and monitoring. We aimed to explore the feasibility of deep learning (DL) features derived from gadoxetate disodium (Gd-EOB-DTPA) MRI, qualitative features, and clinical variables for predicting early recurrence.

METHODS

In this bicentric study, 285 patients with HCC who underwent Gd-EOB-DTPA MRI before resection were divided into training (n = 195) and validation (n = 90) sets. DL features were extracted from contrast-enhanced MRI images using VGGNet-19. Three feature selection methods and five classification methods were combined for DL signature construction. Subsequently, an mp-MR DL signature fused with multiphase DL signatures of contrast-enhanced images was constructed. Univariate and multivariate logistic regression analyses were used to identify early recurrence risk factors including mp-MR DL signature, microvascular invasion (MVI), and tumor number. A DL nomogram was built by incorporating deep features and significant clinical variables to achieve early recurrence prediction.

RESULTS

MVI (p = 0.039), tumor number (p = 0.001), and mp-MR DL signature (p < 0.001) were independent risk factors for early recurrence. The DL nomogram outperformed the clinical nomogram in the training set (AUC: 0.949 vs. 0.751; p < 0.001) and validation set (AUC: 0.909 vs. 0.715; p = 0.002). Excellent DL nomogram calibration was achieved in both training and validation sets. Decision curve analysis confirmed the clinical usefulness of DL nomogram.

CONCLUSION

The proposed DL nomogram was superior to the clinical nomogram in predicting early recurrence for HCC patients after hepatectomy.

KEY POINTS

• Deep learning signature based on Gd-EOB-DTPA MRI was the predominant independent predictor of early recurrence for hepatocellular carcinoma (HCC) after hepatectomy. • Deep learning nomogram based on clinical factors and Gd-EOB-DTPA MRI features is promising for predicting early recurrence of HCC. • Deep learning nomogram outperformed the conventional clinical nomogram in predicting early recurrence.

Conventional and artificial intelligence-based computed tomography and magnetic resonance imaging quantitative techniques for non-invasive liver fibrosis staging

Chronic liver disease (CLD) ultimately develops into liver fibrosis and cirrhosis and is a major public health problem globally. The assessment of liver fibrosis is important for patients with CLD for prognostication, treatment decisions, and surveillance. Liver biopsies are traditionally performed to determine the stage of liver fibrosis. However, the risks of complications and technical limitations restrict their application to screening and sequential monitoring in clinical practice. CT and MRI are essential for evaluating cirrhosis-associated complications in patients with CLD, and several non-invasive methods based on them have been proposed. Artificial intelligence (AI) techniques have also been applied to stage liver fibrosis. This review aimed to explore the values of conventional and AI-based CT and MRI quantitative techniques for non-invasive liver fibrosis staging and summarized their diagnostic performance, advantages, and limitations.

Artificial Intelligence-Based Opportunities in Liver Pathology-A Systematic Review

BACKGROUND

Artificial Intelligence (AI)-based Deep Neural Networks (DNNs) can handle a wide range of applications in image analysis, ranging from automated segmentation to diagnostic and prediction. As such, they have revolutionized healthcare, including in the liver pathology field.

OBJECTIVE

The present study aims to provide a systematic review of applications and performances provided by DNN algorithms in liver pathology throughout the Pubmed and Embase databases up to December 2022, for tumoral, metabolic and inflammatory fields.

RESULTS

42 articles were selected and fully reviewed. Each article was evaluated through the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool, highlighting their risks of bias.

CONCLUSIONS

DNN-based models are well represented in the field of liver pathology, and their applications are diverse. Most studies, however, presented at least one domain with a high risk of bias according to the QUADAS-2 tool. Hence, DNN models in liver pathology present future opportunities and persistent limitations. To our knowledge, this review is the first one solely focused on DNN-based applications in liver pathology, and to evaluate their bias through the lens of the QUADAS2 tool.

Machine learning can guide suitability of consultation and patient referral through telemedicine for hepatobiliary diseases

BACKGROUND AND AIM

Telemedicine is an evolving tool to provide health-care services. We evaluated the suitability of telemedicine to deliver effective consultation for hepatobiliary disorders.

METHODS

In this prospective study spanning over a year, we interviewed hepatologists delivering the teleconsultations through a pre-validated questionnaire. A consult was deemed suitable based on the physician's judgment in the absence of unplanned hospitalization. We evaluated factors determining the suitability through inferential statistics and machine learning models, namely, extreme gradient boosting (XGB) and decision tree (DT).

RESULTS

Of 1118 consultations, 917 (82.0%) were deemed suitable. On univariable analysis, patients with skilled occupation, higher education, out-of-pocket expenses, and diseases such as chronic hepatitis B, C, and non-alcoholic fatty liver disease (NAFLD) without cirrhosis were associated with suitability (P < 0.05). Patients with cirrhosis (compensated or decompensated), acute-on-chronic liver failure (ACLF), and biliary obstruction were likely unsuitable (P < 0.05). XGB and DT models predicted suitability with an area under the receiver operating curve of 0.808 and 0.780, respectively. DT demonstrated that compensated cirrhosis with higher education or skilled occupation with age < 55 years had 78% chance of suitability whereas hepatocellular carcinoma, decompensated cirrhosis, and ACLF patients were unsuitable with a 60-95% probability. In non-cirrhotic liver diseases, hepatitis B, C, and NAFLD were suitable, with a probability of 89.7%. Biliary obstruction and previous failure of teleconsultation were unsuitable, with a probability of 70%. Non-cirrhotic portal fibrosis, dyspepsia, and dysphagia not requiring intervention were suitable (probability: 88%).

CONCLUSION

A simple decision tree can guide the referral of unsuitable and the management of suitable patients with hepatobiliary diseases through telemedicine.

Acute on chronic liver failure: prognostic models and artificial intelligence applications

Critically ill patients presenting with acute on chronic liver failure (ACLF) represent a particularly vulnerable population due to various considerations surrounding the syndrome definition, lack of robust prospective evaluation of outcomes, and allocation of resources such as organs for transplantation. Ninety-day mortality related to ACLF is high and patients who do leave the hospital are frequently readmitted. Artificial intelligence (AI), which encompasses various classical and modern machine learning techniques, natural language processing, and other methods of predictive, prognostic, probabilistic, and simulation modeling, has emerged as an effective tool in various areas of healthcare. These methods are now being leveraged to potentially minimize physician and provider cognitive load and impact both short-term and long-term patient outcomes. However, the enthusiasm is tempered by ethical considerations and a current lack of proven benefits. In addition to prognostic applications, AI models can likely help improve the understanding of various mechanisms of morbidity and mortality in ACLF. Their overall impact on patient-centered outcomes and countless other aspects of patient care remains unclear. In this review, we discuss various AI approaches being utilized in healthcare and discuss the recent and expected future impact of AI on patients with ACLF through prognostic modeling and AI-based approaches.

APASL-ACLF Research Consortium-Artificial Intelligence (AARC-AI) model precisely predicts outcomes in acute-on-chronic liver failure patients

BACKGROUND AND AIMS

We hypothesized that artificial intelligence (AI) models are more precise than standard models for predicting outcomes in acute-on-chronic liver failure (ACLF).

METHODS

We recruited ACLF patients between 2009 and 2020 from APASL-ACLF Research Consortium (AARC). Their clinical data, investigations and organ involvement were serially noted for 90-days and utilized for AI modelling. Data were split randomly into train and validation sets. Multiple AI models, MELD and AARC-Model, were created/optimized on train set. Outcome prediction abilities were evaluated on validation sets through area under the curve (AUC), accuracy, sensitivity, specificity and class precision.

RESULTS

Among 2481 ACLF patients, 1501 in train set and 980 in validation set, the extreme gradient boost-cross-validated model (XGB-CV) demonstrated the highest AUC in train (0.999), validation (0.907) and overall sets (0.976) for predicting 30-day outcomes. The AUC and accuracy of the XGB-CV model (%Δ) were 7.0% and 6.9% higher than the standard day-7 AARC model (p < .001) and 12.8% and 10.6% higher than the day 7 MELD for 30-day predictions in validation set (p < .001). The XGB model had the highest AUC for 7- and 90-day predictions as well (p < .001). Day-7 creatinine, international normalized ratio (INR), circulatory failure, leucocyte count and day-4 sepsis were top features determining the 30-day outcomes. A simple decision tree incorporating creatinine, INR and circulatory failure was able to classify patients into high (~90%), intermediate (~60%) and low risk (~20%) of mortality. A web-based AARC-AI model was developed and validated twice with optimal performance for 30-day predictions.

CONCLUSIONS

The performance of the AARC-AI model exceeds the standard models for outcome predictions in ACLF. An AI-based decision tree can reliably undertake severity-based stratification of patients for timely interventions.

Machine Learning to Predict the Response to Lenvatinib Combined with Transarterial Chemoembolization for Unresectable Hepatocellular Carcinoma

BACKGROUND

Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data.

METHODS

Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4-12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model.

RESULTS

A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61-0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level.

CONCLUSIONS

A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

Deep-learning based approach to identify substrates of human E3 ubiquitin ligases and deubiquitinases

E3 ubiquitin ligases (E3s) and deubiquitinating enzymes (DUBs) play key roles in protein degradation. However, a large number of E3 substrate interactions (ESIs) and DUB substrate interactions (DSIs) remain elusive. Here, we present DeepUSI, a deep learning-based framework to identify ESIs and DSIs using the rich information present in protein sequences. Utilizing the collected golden standard dataset, key hyperparameters in the process of model training, including the ones relevant to data sampling and number of epochs, have been systematically assessed. The performance of DeepUSI was thoroughly evaluated by multiple metrics, based on internal and external validation. Application of DeepUSI to cancer-associated E3 and DUB genes identified a list of druggable substrates with functional implications, warranting further investigation. Together, DeepUSI presents a new framework for predicting substrates of E3 ubiquitin ligases and deubiquitinates.

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.

Artificial Intelligence in Hepatology- Ready for the Primetime

Artificial Intelligence (AI) is a mathematical process of computer mediating designing of algorithms to support human intelligence. AI in hepatology has shown tremendous promise to plan appropriate management and hence improve treatment outcomes. The field of AI is in a very early phase with limited clinical use. AI tools such as machine learning, deep learning, and 'big data' are in a continuous phase of evolution, presently being applied for clinical and basic research. In this review, we have summarized various AI applications in hepatology, the pitfalls and AI's future implications. Different AI models and algorithms are under study using clinical, laboratory, endoscopic and imaging parameters to diagnose and manage liver diseases and mass lesions. AI has helped to reduce human errors and improve treatment protocols. Further research and validation are required for future use of AI in hepatology.

The potential role of machine learning in modelling advanced chronic liver disease

The use of artificial intelligence is rapidly increasing in medicine to support clinical decision making mostly through diagnostic and prediction models. Such models derive from huge databases (big data) including a large variety of health-related individual patient data (input) and the corresponding diagnosis and/or outcome (labels). Various types of algorithms (e.g. neural networks) based on powerful computational ability (machine), allow to detect the relationship between input and labels (learning). More complex algorithms, like recurrent neural network can learn from previous as well as actual input (deep learning) and are used for more complex tasks like imaging analysis and personalized (bespoke) medicine. The prompt availability of big data makes that artificial intelligence can provide rapid answers to questions that would require years of traditional clinical research. It may therefore be a key tool to overcome several major gaps in the model of advanced chronic liver disease, mostly transition from mild to clinically significant portal hypertension, the impact of acute decompensation and the role of further decompensation and treatment efficiency. However, several limitations of artificial intelligence should be overcome before its application in clinical practice. Assessment of the risk of bias, understandability of the black boxes developing the models and models' validation are the most important areas deserving clarification for artificial intelligence to be widely accepted from physicians and patients.

A researcher's guide to preclinical mouse NASH models

Non-alcoholic fatty liver disease (NAFLD) and its inflammatory form, non-alcoholic steatohepatitis (NASH), have quickly risen to become the most prevalent chronic liver disease in the Western world and are risk factors for the development of hepatocellular carcinoma (HCC). HCC is not only one of the most common cancers but is also highly lethal. Nevertheless, there are currently no clinically approved drugs for NAFLD, and NASH-induced HCC poses a unique metabolic microenvironment that may influence responsiveness to certain treatments. Therefore, there is an urgent need to better understand the pathogenesis of this rampant disease to devise new therapies. In this line, preclinical mouse models are crucial tools to investigate mechanisms as well as novel treatment modalities during the pathogenesis of NASH and subsequent HCC in preparation for human clinical trials. Although, there are numerous genetically induced, diet-induced and toxin-induced models of NASH, not all of these models faithfully phenocopy and mirror the human pathology very well. In this Perspective, we shed some light onto the most widely used mouse models of NASH and highlight some of the key advantages and disadvantages of the various models with an emphasis on 'Western diets', which are increasingly recognized as some of the best models in recapitulating the human NASH pathology and comorbidities.

Artificial intelligence model with deep learning in nonalcoholic fatty liver disease diagnosis: genetic based artificial neural networks

Nonalcoholic fatty liver disease (NAFLD) is one of the most common causes of chronic liver disease in the world. The NAFLD spectrum includes simple steatosis, steatohepatitis, fibrosis, cirrhosis, and hepatocellular carcinoma (HCC). Genetic, nutritional factors, obesity, insulin resistance, gut microbiota are among the risk factors for NAFLD. The genetic variant Patatin-like phospholipase domain-containing protein 3 (PNPLA3) plays an important role in the development of a number of liver diseases ranging from steatosis, chronic hepatitis, cirrhosis and HCC. Due to the increase in the prevalence of NAFLD, new models are being developed with machine learning, deep learning, artificial neural network (ANN) algorithms in the field of artificial intelligence (AI) to determine low-cost, noninvasive diagnostic methods. Models developed with ANN from AI modules are important in order to examine biochemical and genomic information in detail in the diagnosis of NAFLD. The aim of this study is to develop a simple ANN model using biochemical and genotypic parameters in the diagnosis of NAFLD. A total of 300 patients followed up with the diagnosis of NAFLD and 100 controls were included in the study. The data set was divided into two as training and test set. Genotyping of PNPLA3 (CC, CG, GG) as genomic analysis was performed with real time PCR device. The algorithm used for the diagnosis of NAFLD was designed using age, body mass index (BMI), mean platelet volume (MPV), insulin resistance (IR), alanine aminotransferase (ALT), genotype PNPLA3 (CC, CG, GG) parameters. MLP Classifier algorithm from ANN was used in the development of the model. ANN algorithms are used in python programming language. Statistical analyzes were made in SPSS program. Percent accuracy, area under the ROC curve, confusion matrix, Positive (PPV) and Negative Predicted Value (NPV) values, precision, recall, and f1-score results were determined. The accuracy percentage was determined as 0.979 in the train set and 0.970 in the test set. The Log Loss value was set to 0.09. The developed neural network achieved an accuracy percentage of 97.0% during testing, with an area under the ROC curve value of 0.95. We think that the ANN model developed with genomic and biochemical parameters can be used as a cost-effective, noninvasive new predictive diagnostic model in clinical practice in the diagnosis of NAFLD.

Artificial intelligence for precision medicine in autoimmune liver disease

Autoimmune liver diseases (AiLDs) are rare autoimmune conditions of the liver and the biliary tree with unknown etiology and limited treatment options. AiLDs are inherently characterized by a high degree of complexity, which poses great challenges in understanding their etiopathogenesis, developing novel biomarkers and risk-stratification tools, and, eventually, generating new drugs. Artificial intelligence (AI) is considered one of the best candidates to support researchers and clinicians in making sense of biological complexity. In this review, we offer a primer on AI and machine learning for clinicians, and discuss recent available literature on its applications in medicine and more specifically how it can help to tackle major unmet needs in AiLDs.

The Role of Praziquantel in the Prevention and Treatment of Fibrosis Associated with Schistosomiasis: A Review

Schistosomiasis remains a major global public health concern. Currently, the control of this neglected tropical disease still depends on chemotherapy to reduce the prevalence and intensity of the parasite infection. It has been widely accepted that praziquantel is highly effective against all species of Schistosoma, and this agent is virtually the only drug of choice for the treatment of human schistosomiasis. Mass drug administration (MDA) with praziquantel has been shown to be effective in greatly reducing the prevalence and morbidity due to schistosomiasis worldwide. In addition to antischistosomal activity, a large number of experiential and clinical evidence has demonstrated the action of praziquantel against fibrosis caused by S. mansoni and S. japonicum infections through decreasing the expression of fibrotic biomarkers such as α-smooth muscle actin (α-SMA), collagen, matrix metalloproteinase (MMP), and tissue inhibitor of metalloproteinase (TIMP), and inhibiting the expression of proinflammatory cytokines such as interleukin (IL)-6, tumor necrosis factor (TNF)-α, and transforming growth factor (TGF)-β, as well as chemokines, and similar antifibrotic activity was observed in mouse models of fibrosis induced by carbon tetrachloride (CCl4) and concanavalin A (Con-A). In this review, we discuss the role of praziquantel in the prevention and treatment of fibrosis associated with schistosomiasis and the possible mechanisms. We call for randomized, controlled clinical trials to evaluate the efficacy and safety of praziquantel in the treatment of schistosomiasis-induced hepatic fibrosis, and further studies to investigate the potential of praziquantel against fibrosis associated with alcohol consumption, viruses, and toxins seem justified.

Liver Function-How to Screen and to Diagnose: Insights from Personal Experiences, Controlled Clinical Studies and Future Perspectives

Acute and chronic liver disease is a relevant problem worldwide. Liver function plays a crucial role in the course of liver diseases not only in estimating prognosis but also with regard to therapeutic interventions. Within this review, we discuss and evaluate different tools from screening to diagnosis and give insights from personal experiences, controlled clinical studies and future perspectives. Finally, we offer our novel diagnostic algorithm to screen patients with presumptive acute or chronic liver disease in the daily clinical routine.

Digital Technologies: Advancing Individualized Treatments through Gene and Cell Therapies, Pharmacogenetics, and Disease Detection and Diagnostics

Digital technologies are shifting the paradigm of medicine in a way that will transform the healthcare industry. Conventional medical approaches focus on treating symptoms and ailments for large groups of people. These approaches can elicit differences in treatment responses and adverse reactions based on population variations, and are often incapable of treating the inherent pathophysiology of the medical conditions. Advances in genetics and engineering are improving healthcare via individualized treatments that include gene and cell therapies, pharmacogenetics, disease detection, and diagnostics. This paper highlights ways that artificial intelligence can help usher in an age of personalized medicine.

Registered Trials of Artificial Intelligence Conducted on Chronic Liver Disease: A Cross-Sectional Study on ClinicalTrials.gov

Background

Artificial intelligence (AI) has been widely applied in the diagnosis and therapy of chronic liver disease (CLD), but there is currently little insight into the trials registered on ClinicalTrials.gov. Thus, this cross-sectional study was focused on analyzing the progress in the use of AI in CLD.

Methods

Registered trials of AI applied in CLD on ClinicalTrials.gov were searched firstly. All available information was downloaded to Excel (Microsoft Excel, Rong, Rong, China), and duplicates were removed. We extracted the data of the included trials, then analyzed the characteristics of them finally.

Results

Up to the 27th of May 2021, 6835 trials were identified following an initial search, and 20 registered trials were included after screening for inclusion and exclusion criteria. Among those trials, hepatocellular carcinoma (HCC, 40.0%) and nonalcoholic fatty liver disease (NAFLD, 20.0%) were the most widely applied CLDs for AI. Trials started in 2013 until 2021, with 17 trials (85%) registered after 2016. There was a large trend in trial enrolment, with 40% of them including samples more than 500. Five trials (25%) have been completed, but only one of these had available results. The most frequent sponsors and collaborators were both hospitals at 55%, followed by universities at 35% and institutes at 11%, respectively. Of the 20 trials included, 35% (7 trials) were interventional trials and 65% (13 trials) were observational trials. Among 7 interventional trials, most trials were for diagnosis purpose (42.86%, 3 trials); 4 trials (57.14%) were randomized; 3 trials (42.86%) applied behavioral intervention, 1 trial (14.29%) was in device intervention, 2 trials (28.57%) were in diagnostic test, and 1 trial intervention was unknown. Among 13 observational trials, 8 (61.54%) were cohort studies; 6 (46.15%) were prospective studies, 4 (30.77%) were retrospective studies, 2 (15.38%) were cross-sectional studies, and 1 (7.69%) did not involve a temporal perspective.

Conclusion

The study is the first to focus on AI registration trials in CLD, which will aid relevant scholars in understanding the current state of the subject. This study demonstrates that additional research on AI used in the diagnosis and treatment of CLD is required, and timely publication of accessible results from registered trials is essential.

Artificial intelligence in gastroenterology and hepatology: how to advance clinical practice while ensuring health equity

Artificial intelligence (AI) and machine learning (ML) systems are increasingly used in medicine to improve clinical decision-making and healthcare delivery. In gastroenterology and hepatology, studies have explored a myriad of opportunities for AI/ML applications which are already making the transition to bedside. Despite these advances, there is a risk that biases and health inequities can be introduced or exacerbated by these technologies. If unrecognised, these technologies could generate or worsen systematic racial, ethnic and sex disparities when deployed on a large scale. There are several mechanisms through which AI/ML could contribute to health inequities in gastroenterology and hepatology, including diagnosis of oesophageal cancer, management of inflammatory bowel disease (IBD), 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 health equity.

Exploring pathological signatures for predicting the recurrence of early-stage hepatocellular carcinoma based on deep learning

Background

Postoperative recurrence impedes the curability of early-stage hepatocellular carcinoma (E-HCC). We aimed to establish a novel recurrence-related pathological prognosticator with artificial intelligence, and investigate the relationship between pathological features and the local immunological microenvironment.

Methods

A total of 576 whole-slide images (WSIs) were collected from 547 patients with E-HCC in the Zhongshan cohort, which was randomly divided into a training cohort and a validation cohort. The external validation cohort comprised 147 Tumor Node Metastasis (TNM) stage I patients from The Cancer Genome Atlas (TCGA) database. Six types of HCC tissues were identified by a weakly supervised convolutional neural network. A recurrence-related histological score (HS) was constructed and validated. The correlation between immune microenvironment and HS was evaluated through extensive immunohistochemical data.

Results

The overall classification accuracy of HCC tissues was 94.17%. The C-indexes of HS in the training, validation and TCGA cohorts were 0.804, 0.739 and 0.708, respectively. Multivariate analysis showed that the HS (HR= 4.05, 95% CI: 3.40-4.84) was an independent predictor for recurrence-free survival. Patients in HS high-risk group had elevated preoperative alpha-fetoprotein levels, poorer tumor differentiation and a higher proportion of microvascular invasion. The immunohistochemistry data linked the HS to local immune cell infiltration. HS was positively correlated with the expression level of peritumoral CD14+ cells (p= 0.013), and negatively with the intratumoral CD8+ cells (p&lt; 0.001).

Conclusions

The study established a novel histological score that predicted short-term and long-term recurrence for E-HCCs using deep learning, which could facilitate clinical decision making in recurrence prediction and management.

Artificial intelligence to identify harmful alcohol use after early liver transplant for alcohol-associated hepatitis

Early liver transplantation (LT) for alcohol-associated hepatitis (AH) is the fastest growing indication for LT, but prediction of harmful alcohol use post-LT remains limited. Among 10 ACCELERATE-AH centers, we examined psychosocial evaluations from consecutive LT recipients for AH from 2006 to 2017. A multidisciplinary panel used content analysis to develop a maximal list of psychosocial variables. We developed an artificial intelligence model to predict post-LT harmful alcohol use. The cohort included training (N = 91 among 8 centers) and external validation (N = 25 among 2 centers) sets, with median follow-up of 4.4 (IQR 3.0-6.0) years post-LT. In the training set, AUC was 0.930 (95%CI 0.862-0.998) with positive predictive value of 0.891 (95%CI 0.620-1.000), internally validated through fivefold cross-validation. In the external validation set, AUC was 0.692 (95%CI 0.666-0.718) with positive predictive value of 0.82 (95%CI 0.625-1.000). The model identified specific variables related to social support and substance use as highly important to predict post-LT harmful alcohol use. We retrospectively developed and validated a model that identified psychosocial profiles at LT predicting harmful alcohol use post-LT for AH. This preliminary model may inform selection and post-LT management for AH and warrants prospective evaluation in larger studies among all alcohol-associated liver disease being considered for early LT.

Machine Learning Techniques Differentiate Alcohol-Associated Hepatitis From Acute Cholangitis in Patients With Systemic Inflammation and Elevated Liver Enzymes

OBJECTIVE

To develop machine learning algorithms (MLAs) that can differentiate patients with acute cholangitis (AC) and alcohol-associated hepatitis (AH) using simple laboratory variables.

METHODS

A study was conducted of 459 adult patients admitted to Mayo Clinic, Rochester, with AH (n=265) or AC (n=194) from January 1, 2010, to December 31, 2019. Ten laboratory variables (white blood cell count, hemoglobin, mean corpuscular volume, platelet count, aspartate aminotransferase, alanine aminotransferase, alkaline phosphatase, total bilirubin, direct bilirubin, albumin) were collected as input variables. Eight supervised MLAs (decision tree, naive Bayes, logistic regression, k-nearest neighbor, support vector machine, artificial neural networks, random forest, gradient boosting) were trained and tested for classification of AC vs AH. External validation was performed with patients with AC (n=213) and AH (n=92) from the MIMIC-III database. A feature selection strategy was used to choose the best 5-variable combination. There were 143 physicians who took an online quiz to distinguish AC from AH using the same 10 laboratory variables alone.

RESULTS

The MLAs demonstrated excellent performances with accuracies up to 0.932 and area under the curve (AUC) up to 0.986. In external validation, the MLAs showed comparable accuracy up to 0.909 and AUC up to 0.970. Feature selection in terms of information-theoretic measures was effective, and the choice of the best 5-variable subset produced high performance with an AUC up to 0.994. Physicians did worse, with mean accuracy of 0.790.

CONCLUSION

Using a few routine laboratory variables, MLAs can differentiate patients with AC and AH and may serve valuable adjunctive roles in cases of diagnostic uncertainty.

Developing a New qFIBS Model Assessing Histological Features in Pediatric Patients With Non-alcoholic Steatohepatitis

Background

The evolution of pediatric non-alcoholic fatty liver disease (NAFLD) to non-alcoholic steatohepatitis (NASH) is associated with unique histological features. Pathological evaluation of liver specimen is often hindered by observer variability and diagnostic consensus is not always attainable. We investigated whether the qFIBS technique derived from adult NASH could be applied to pediatric NASH.

Materials and Methods

102 pediatric patients (<18 years old) with liver biopsy-proven NASH were included. The liver biopsies were serially sectioned for hematoxylin-eosin and Masson trichrome staining for histological scoring, and for second harmonic generation (SHG) imaging. qFIBS-automated measure of fibrosis, inflammation, hepatocyte ballooning, and steatosis was estabilshed by using the NASH CRN scoring system as the reference standard.

Results

qFIBS showed the best correlation with steatosis (r = 0.84, P < 0.001); with ability to distinguish different grades of steatosis (AUROCs 0.90 and 0.98, sensitivity 0.71 and 0.93, and specificity 0.90 and 0.90). qFIBS correlation with fibrosis (r = 0.72, P < 0.001) was good with high AUROC values [qFibrosis (AUC) > 0.85 (0.85–0.95)] and ability to distinguish different stages of fibrosis. qFIBS showed weak correlation with ballooning (r = 0.38, P = 0.028) and inflammation (r = 0.46, P = 0.005); however, it could distinguish different grades of ballooning (AUROCs 0.73, sensitivity 0.36, and specificity 0.92) and inflammation (AUROCs 0.77, sensitivity 0.83, and specificity 0.53).

Conclusion

It was demonstrated that when qFIBS derived from adult NASH was performed on pediatric NASH, it could best distinguish the various histological grades of steatosis and fibrosis.