An imaging-based machine learning model outperforms clinical risk scores for prognosis of cirrhotic variceal bleeding

Applications of artificial intelligence in abdominal imaging

The rapid advancements in artificial intelligence (AI) carry the promise to reshape abdominal imaging by offering transformative solutions to challenges in disease detection, classification, and personalized care. AI applications, particularly those leveraging deep learning and radiomics, have demonstrated remarkable accuracy in detecting a wide range of abdominal conditions, including but not limited to diffuse liver parenchymal disease, focal liver lesions, pancreatic ductal adenocarcinoma (PDAC), renal tumors, and bowel pathologies. These models excel in the automation of tasks such as segmentation, classification, and prognostication across modalities like ultrasound, CT, and MRI, often surpassing traditional diagnostic methods. Despite these advancements, widespread adoption remains limited by challenges such as data heterogeneity, lack of multicenter validation, reliance on retrospective single-center studies, and the "black box" nature of many AI models, which hinder interpretability and clinician trust. The absence of standardized imaging protocols and reference gold standards further complicates integration into clinical workflows. To address these barriers, future directions emphasize collaborative multi-center efforts to generate diverse, standardized datasets, integration of explainable AI frameworks to existing picture archiving and communication systems, and the development of automated, end-to-end pipelines capable of processing multi-source data. Targeted clinical applications, such as early detection of PDAC, improved segmentation of renal tumors, and improved risk stratification in liver diseases, show potential to refine diagnostic accuracy and therapeutic planning. Ethical considerations, such as data privacy, regulatory compliance, and interdisciplinary collaboration, are essential for successful translation into clinical practice. AI's transformative potential in abdominal imaging lies not only in complementing radiologists but also in fostering precision medicine by enabling faster, more accurate, and patient-centered care. Overcoming current limitations through innovation and collaboration will be pivotal in realizing AI's full potential to improve patient outcomes and redefine the landscape of abdominal radiology.

Visualizing global progress and challenges in esophagogastric variceal bleeding

BACKGROUND

Esophageal and gastric variceal bleeding is a catastrophic complication of portal hypertension, most commonly caused by cirrhosis of various etiologies. Although a considerable body of research has been conducted in this area, the complexity of the disease and the lack of standardized treatment strategies have led to fragmented findings, insufficient information, and a lack of systematic investigation. Bibliometric analysis can help clarify research trends, identify core topics, and reveal potential future directions. Therefore, this study aims to use bibliometric methods to conduct an in-depth exploration of research progress in this field, with the expectation of providing new insights for both clinical practice and scientific research.

AIM

To evaluate research trends and advancements in esophagogastric variceal bleeding (EGVB) over the past twenty years.

METHODS

Relevant publications on EGVB were retrieved from the Web of Science Core Collection. VOSviewer, Pajek, CiteSpace, and the bibliometrix package were then employed to perform bibliometric visualizations of publication volume, countries, institutions, journals, authors, keywords, and citation counts.

RESULTS

The analysis focused on original research articles and review papers. From 2004 to 2023, a total of 2097 records on EGVB were retrieved. The number of relevant publications has increased significantly over the past two decades, especially in China and the United States. The leading contributors in this field, in terms of countries, institutions, authors, and journals, were China, Assistance Publique-Hôpitaux de Paris, Bosch Jaime, and World Journal of Gastroenterology, respectively. Core keywords in this field include portal hypertension, management, liver cirrhosis, risk, prevention, and diagnosis. Future research directions may focus on optimizing diagnostic methods, personalized treatment, and multidisciplinary collaboration.

CONCLUSION

Using bibliometric methods, this study reveals the developmental trajectory and trends in research on EGVB, underscoring risk assessment and diagnostic optimization as the core areas of current focus. The study provides an innovative and systematic perspective for this field, indicating that future research could center on multidisciplinary collaboration, personalized treatment approaches, and the development of new diagnostic tools. Moreover, this work offers practical research directions for both the academic community and clinical practice, driving continued advancement in this domain.

Predictive value of high-risk esophageal varices in cirrhosis based on dual-energy CT combined with clinical and serologic features

OBJECTIVE

To investigate the predictive value of dual-energy CT (DECT) in combination with clinical and serologic features for noninvasive assessment of high-risk esophageal variceal (EV) in cirrhosis patients.

DATA AND METHODS

120 patients who had undergone DECT and gastroscopy were retrospectively enrolled. They were categorized into low-risk variceal (LRV) and high-risk variceal (HRV) groups by gastroscopy (LRV: none, mild, HRV: moderate, severe). Clinical data, serologic and DECT parameters were recorded respectively. Multifactorial logistic regression analyses were conducted to develop clinical, serological, DECT, and combined models. AUC was utilized to assess the diagnostic performance. Non-parametric tests were employed to analyze differences in DECT parameters among different grading of EV.

RESULTS

In clinical model, ascites was the independent risk predictor, with 78.3% accuracy,50% sensitivity, 100% specificity, and an AUC of 0.693. The serological model revealed white blood cell count, hematocrit, alanine aminotransferase, and platelet count as predictors for HRV, demonstrating 83.3% accuracy, 90.9% sensitivity, 76.9% specificity, and an AUC of 0.784. The DECT model, identified liver normalized iodine volume (NIV-L) and spleen volume (V-S) as key predictors, with 84% accuracy, 72.7% sensitivity, 92.9% specificity, and an AUC of 0.84. The combined model, integrating NIV-L, V-S, and Ascites, demonstrated superior performance with 82.6% accuracy, 90% sensitivity, 76.9% specificity, and an AUC of 0.878, compared to the other models. Additionally, severe EV had higher V-S and NIV-S values than other grades (p < 0.05), with AUC of 0.874 and 0.864, respectively.

CONCLUSION

DECT-based NIV-L, V-S, and presence of ascites can predict high-risk esophageal varices.

CLINICAL RELEVANCE STATEMENT

Quantitative parameters of DECT can predict high-risk esophageal varices in cirrhotic patients, avoid gastroscopy, if possible, continue hierarchical management.

TRIAL REGISTRATION

retrospectively registered.

Identification of abdominal MRI features associated with histopathological severity and treatment response in autoimmune hepatitis

To identify abdominal contrast magnetic resonance imaging (MRI) features associated with histopathological severity, and treatment response in autoimmune hepatitis (AIH).

PATIENTS AND METHODS

AIH patients who had abdominal contrast MRI within 3 months of liver biopsy were retrospectively enrolled. Histopathological severity, liver volume, MRI features, laboratory tests, and treatment response were collected. MRI and serum models were constructed through stepwise univariate and multivariate logistic regression for diagnosing severe histopathology and predicting insufficient response (IR).

RESULTS

One hundred AIH patients were included (median age: 57.0 years, 79.0% female). For diagnosing severe portal inflammation, reticular fibrosis and volume ratio of segment V-VIII to total liver (SV-SVIII/TLV) achieved an area under the receiver operating characteristic curve (AUROC) of 0.765 (95% CI 0.670-0.860). Severe confluent necrosis was modeled using hepatic fissure widening, reticular fibrosis, and volume ratio of segment I-III to segments IV-VIII, achieving an AUROC of 0.796 (95% CI 0.708-0.885). Severe histological activity was modeled using ascites, and SV-SVIII/TLV achieved an AUROC of 0.748 (95% CI 0.649-0.847). To diagnose cirrhosis, ascites, reticular fibrosis, and the volume ratio of segment I to the total liver were employed, yielding an AUROC of 0.833 (95% CI 0.716-0.949); IR (transaminases and/or immunoglobulin G remaining unnormal after 6 months of immunosuppressive treatment) was modeled using ascites, gallbladder wall edema, and transient hepatic attenuation difference, achieving an AUROC of 0.796 (95% CI 0.691-0.902).

CONCLUSION

The MRI models demonstrated relatively good performance in evaluating histopathological severity and treatment response. Combining MRI and serum models could enhance diagnostic and prognostic efficacy.

KEY POINTS

Question Abdominal contrast MRI may help clinicians better evaluate the histopathological severity and treatment response of autoimmune hepatitis (AIH), but there is currently limited research. Findings Models based on MRI features perform well in diagnosing severe portal inflammation, confluent necrosis, histological activity, and cirrhosis, as well as predicting insufficient response. Clinical relevance Abdominal contrast MRI, combined with serological parameters, provides a new and stronger noninvasive method for clinically assessing AIH progression and treatment.

AI in Hepatology: Revolutionizing the Diagnosis and Management of Liver Disease

The integration of artificial intelligence (AI) into hepatology is revolutionizing the diagnosis and management of liver diseases amidst a rising global burden of conditions like metabolic-associated steatotic liver disease (MASLD). AI harnesses vast datasets and complex algorithms to enhance clinical decision making and patient outcomes. AI's applications in hepatology span a variety of conditions, including autoimmune hepatitis, primary biliary cholangitis, primary sclerosing cholangitis, MASLD, hepatitis B, and hepatocellular carcinoma. It enables early detection, predicts disease progression, and supports more precise treatment strategies. Despite its transformative potential, challenges remain, including data integration, algorithm transparency, and computational demands. This review examines the current state of AI in hepatology, exploring its applications, limitations, and the opportunities it presents to enhance liver health and care delivery.

Development of a non-invasive diagnostic model for high-risk esophageal varices based on radiomics of spleen CT

PURPOSE

To evaluate the diagnostic performance of radiomics models derived from multi-phase spleen CT for high-risk esophageal varices (HREV) in cirrhotic patients.

METHODS

We retrospectively selected cirrhotic patients with esophageal varices from two hospitals from September 2019 to September 2023. Patients underwent non-contrast and contrast-enhanced CT scans and were categorized into HREV and non-HREV groups based on endoscopic evaluations. Radiomics features were extracted from spleen CT images in non-contrast, arterial, and portal venous phases, with feature selection via lasso regression and Pearson's correlation. Ten machine learning models were developed to diagnose HREV, evaluated by area under the curve (AUC). The AUC values of the three groups of models were statistically compared by the Kruskal-Wallis H test and Bonferroni-corrected Mann-Whitney U test. A p-value less than 0.05 was considered statistically significant.

RESULTS

Among 233 patients, 11, 6, and 11 features were selected from non-contrast, arterial, and portal venous phases, respectively. Significant differences in AUC values were observed across phases (p < 0.05), and the arterial phase models showed the highest AUC values. The best model in arterial phase was the logical regression model, whose AUC value was 0.85, sensitivity was 83.3%, specificity was 80% and F1 score was 0.81.

CONCLUSION

Radiomics models based on spleen CT, especially the arterial phase models, demonstrate high diagnostic accuracy for HREV, offering the potential for early detection and intervention.

Comprehensive approach to esophageal variceal bleeding: From prevention to treatment

Esophageal variceal bleeding is a severe complication often associated with portal hypertension, commonly due to liver cirrhosis. Prevention and treatment of this condition are critical for patient outcomes. Preventive strategies focus on reducing portal hypertension to prevent varices from developing or enlarging. Primary prophylaxis involves the use of non-selective beta-blockers, such as propranolol or nadolol, which lower portal pressure by decreasing cardiac output and thereby reducing blood flow to the varices. Endoscopic variceal ligation (EVL) may also be employed as primary prophylaxis to prevent initial bleeding episodes. Once bleeding occurs, immediate treatment is essential. Initial management includes hemodynamic stabilization followed by pharmacological therapy with vasoactive drugs such as octreotide or terlipressin to control bleeding. Endoscopic intervention is the cornerstone of treatment, with techniques such as EVL or sclerotherapy applied to directly manage the bleeding varices. In cases where bleeding is refractory to endoscopic treatment, transjugular intrahepatic portosystemic shunt may be considered to effectively reduce portal pressure. Long-term management after an acute bleeding episode involves secondary prophylaxis using beta-blockers and repeated EVL sessions to prevent rebleeding, complemented by monitoring and managing liver function to address the underlying disease. In light of new scientific evidence, including the findings of the study by Peng et al, this editorial aims to review available strategies for the prevention and treatment of esophageal varices.

Development and internal validation of prediction model for rebleeding within one year after endoscopic treatment of cirrhotic varices: consideration from organ-based CT radiomics signature

BACKGROUND

Rebleeding after endoscopic treatment for esophagogastric varices (EGVs) in cirrhotic patients remains a significant clinical challenge, with high mortality rates and limited predictive tools. Current methods, relying on clinical indicators, often lack precision and fail to provide personalized risk assessments. This study aims to develop and validate a novel, non-invasive prediction model based on CT radiomics to predict rebleeding risk within one year of treatment, integrating radiomic features from key organs and clinical data.

METHODS

123 patients were enrolled and divided into rebleeding (n = 44) and non-bleeding group (n = 79) within 1 year after endoscopic treatment of EGVs. The liver, spleen, and the lower part of the esophagus were segmented and the extracted radiomics features were selected to construct liver/spleen/esophagus radiomics signatures based on logistic regression. Clinic-radiomics combined models and multi-organ combined radiomics models were constructed based on independent model scores using logistic regression. The model performance was evaluated by ROC analysis, calibration and decision curves. The continuous net reclassification improvement (NRI) and integrated discrimination improvement (IDI) indices were analyzed.

RESULTS

The clinical-liver combined model had the highest AUC of 0.931 (95% CI: 0.887-0.974), which was followed by the liver-based model with AUC of 0.891 (95% CI: 0.835-0.74). The decision curves also showed that the clinical-liver combined model afforded a greater net benefit compared to other models within the threshold probability of 0.45 to 0.80. Significant improvements in discrimination (IDI, P < 0.05) and reclassification (NRI, P < 0.05) were obtained for clinical-liver combined model compared with the independent ones.

CONCLUSION

The independent and combined liver-based CT radiomics models performed well in predicting rebleeding within 1 year after endoscopic treatment of EGVs.

Computed tomography-based multi-organ radiomics nomogram model for predicting the risk of esophagogastric variceal bleeding in cirrhosis

BACKGROUND

Radiomics has been used in the diagnosis of cirrhosis and prediction of its associated complications. However, most current studies predict the risk of esophageal variceal bleeding (EVB) based on image features at a single level, which results in incomplete data. Few studies have explored the use of global multi-organ radiomics for non-invasive prediction of EVB secondary to cirrhosis.

AIM

To develop a model based on clinical and multi-organ radiomic features to predict the risk of first-instance secondary EVB in patients with cirrhosis.

METHODS

In this study, 208 patients with cirrhosis were retrospectively evaluated and randomly split into training (n = 145) and validation (n = 63) cohorts. Three areas were chosen as regions of interest for extraction of multi-organ radiomic features: The whole liver, whole spleen, and lower esophagus-gastric fundus region. In the training cohort, radiomic score (Rad-score) was created by screening radiomic features using the inter-observer and intra-observer correlation coefficients and the least absolute shrinkage and selection operator method. Independent clinical risk factors were selected using multivariate logistic regression analyses. The radiomic features and clinical risk variables were combined to create a new radiomics-clinical model (RC model). The established models were validated using the validation cohort.

RESULTS

The RC model yielded the best predictive performance and accurately predicted the EVB risk of patients with cirrhosis. Ascites, portal vein thrombosis, and plasma prothrombin time were identified as independent clinical risk factors. The area under the receiver operating characteristic curve (AUC) values for the RC model, Rad-score (liver + spleen + esophagus), Rad-score (liver), Rad-score (spleen), Rad-score (esophagus), and clinical model in the training cohort were 0.951, 0.930, 0.801, 0.831, 0.864, and 0.727, respectively. The corresponding AUC values in the validation cohort were 0.930, 0.886, 0.763, 0.792, 0.857, and 0.692.

CONCLUSION

In patients with cirrhosis, combined multi-organ radiomics and clinical model can be used to non-invasively predict the probability of the first secondary EVB.

Applications of Artificial Intelligence-Based Systems in the Management of Esophageal Varices

BACKGROUND

Esophageal varices, dilated submucosal veins in the lower esophagus, are commonly associated with portal hypertension, particularly due to liver cirrhosis. The high morbidity and mortality linked to variceal hemorrhage underscore the need for accurate diagnosis and effective management. The traditional method of assessing esophageal varices is esophagogastroduodenoscopy (EGD), which, despite its diagnostic and therapeutic capabilities, presents limitations such as interobserver variability and invasiveness. This review aims to explore the role of artificial intelligence (AI) in enhancing the management of esophageal varices, focusing on its applications in diagnosis, risk stratification, and treatment optimization.

METHODS

This systematic review focuses on the capabilities of AI algorithms to analyze clinical scores, laboratory data, endoscopic images, and imaging modalities like CT scans.

RESULTS

AI-based systems, particularly machine learning (ML) and deep learning (DL) algorithms, have demonstrated the ability to improve risk stratification and diagnosis of esophageal varices, analyzing vast amounts of data, identifying patterns, and providing individualized recommendations. However, despite these advancements, clinical scores based on laboratory data still show low specificity for esophageal varices, often requiring confirmatory endoscopic or imaging studies.

CONCLUSIONS

AI integration in managing esophageal varices offers significant potential for advancing diagnosis, risk assessment, and treatment strategies. While promising, AI systems should complement rather than replace traditional methods, ensuring comprehensive patient evaluation. Further research is needed to refine these technologies and validate their efficacy in clinical practice.

Age and mean platelet volume-based nomogram for predicting the therapeutic efficacy of metoprolol in Chinese pediatric patients with vasovagal syncope

BACKGROUND

Vasovagal syncope (VVS) is the most common type of orthostatic intolerance in children. We investigated whether platelet-related factors related to treatment efficacy in children suffering from VVS treated with metoprolol.

METHODS

Metoprolol-treated VVS patients were recruited. The median duration of therapy was three months. Patients were followed and divided into two groups, treament-effective group and treatment-ineffective group. Logistic and least absolute shrinkage selection operator regressions were used to examine treatment outcome variables. Receiver-operating characteristic (ROC) curves, precision-recall (PR) curves, calibration plots, and decision curve analyses were used to evaluate the nomogram model.

RESULTS

Among the 72 patients who complete the follow-up, treatment-effective group and treatment-ineffective group included 42 (58.3%) and 30 (41.7%) cases, respectively. The patients in the treatment-effective group exhibited higher mean platelet volume (MPV) [(11.0 ± 1.0) fl vs. (9.8 ± 1.0) fl, P < 0.01] and platelet distribution width [12.7% (12.3%, 14.3%) vs. 11.3% (10.2%, 12.2%), P < 0.01] than those in the treatment-ineffective group. The sex ratio was significantly different (P = 0.046). A fit model comprising age [odds ratio (OR) = 0.766, 95% confidence interval (CI) = 0.594-0.987] and MPV (OR = 5.613, 95% CI = 2.297-13.711) might predict therapeutic efficacy. The area under the curve of the ROC and PR curves was computed to be 0.85 and 0.9, respectively. The P value of the Hosmer-Lemeshow test was 0.27. The decision curve analysis confirmed that managing children with VVS based on the predictive model led to a net advantage ranging from 0.01 to 0.58. The nomogram is convenient for clinical applications.

CONCLUSION

A novel nomogram based on age and MPV can predict the therapeutic benefits of metoprolol in children with VVS.

Computed tomography for the prediction of oesophageal variceal bleeding: A surrogate or complementary to the gold standard?

In this editorial we comment on the in-press article in the World Journal of Gastrointestinal endoscopy about the role of computed tomography (CT) for the prediction of esophageal variceal bleeding. The mortality and morbidity are much increased in patients with chronic liver diseases when complicated with variceal bleeding. Predicting the patient at a risk of bleeding is extremely important and receives a great deal of attention, paving the way for primary prophylaxis either using medical treatment including carvedilol or propranolol, or endoscopic band ligation. Endoscopic examination and the hepatic venous pressure gradient are the gold standards in the diagnosis and prediction of variceal bleeding. Several non-invasive laboratory and radiological examinations are used for the prediction of variceal bleeding. The contrast-enhanced multislice CT is a widely used non-invasive, radiological examination that has many advantages. In this editorial we briefly comment on the current research regarding the use of CT as a non-invasive tool in predicting the variceal bleeding.