Utilización de escalas no invasivas en la detección de varices esofágicas en pacientes con trombosis venosa portal / Use of non-invasive scales for detecting esophageal varices in paediatric patients with portal vein thrombosis

Introducción La trombosis portal (TVP) es la causa más frecuente de hipertensión portal en población pediátrica. El Consenso de Baveno VI considera la ligadura endoscópica de varices como segunda opción terapéutica tras el meso-Rex-bypass (shunt quirúrgico). Objetivo Analizar la rentabilidad diagnóstica de escalas no invasivas para predecir el riesgo de varices esofágicas en niños con TVP. Material y métodos Estudio descriptivo retrospectivo donde se incluyeron endoscopias digestivas altas (EDA) en pacientes<15 años con TVP no cirróticos. Se dividieron según la presencia de varices esofágicas y se estudiaron sexo, etiología, edad, hemorragia digestiva o tratamientos previos, resultados de EDA y las escalas (Regla Predicción Clínica-CPR, Regla Predicción Varices-VPR, King's Variceal Prediction Score-K-VaPS y ratio plaquetas/bazo-RPB). Las variables cualitativas se expresaron mediante frecuencia absoluta y porcentaje, y las cuantitativas mediante mediana y rango intercuartílico. Para las comparaciones se emplearon los test U de Mann-Whitney y Hanley-McNeil. Resultados Se realizaron 45 EDA. Un 80%(n=36) presentaron varices esofágicas: mediana de 3(2 – 3) y un 33,3%(n=12) precisó ligadura endoscópica de varices. Se demostraron diferencias estadísticamente significativas entre ambos grupos: CPR (142,39 [132,22 - 166,53] vs. 122,75 [115,24 – 133,15] p=0,003), VPR (9,91 [9,36 – 11,75] vs. 5,6 [3,34 – 8,39] p=0,001), K-VaPS (117,86 [99,66 - 126,58] vs. 99,64 [94,88 - 110,18] p=0,019), RPB (2384,62 [1902,22 - 3201,63] vs. 1252,5 [579,6 - 2144,42] p=0,05), con un área bajo la curva>75%, sin demostrarse diferencias entre escalas. Conclusiones En pacientes pediátricos con TVP no cirróticos se pueden emplear escalas no invasivas como herramienta para predecir la presencia de VE y plantear con ello la indicación de EDA. (AU)

Introduction Portal vein thrombosis (PVT) is the most frequent cause of portal hypertension in paediatric population. Baveno VI Consensus considers endoscopic variceal ligation as the second therapeutic option after meso-Rex bypass (surgical shunt). Aim Analyse the diagnostic profitability of non-invasive scales in order to predict the risk of oesophageal varices (OV) in children with PVT. Material and methods Descriptive retrospective study where every upper gastrointestinal endoscopy (UGE) carried on patients <15 years old with non-cirrhotic PVT were included. There were divided according to the presence of OV and sex, cause, age, previous gastrointestinal bleeding or treatments, results of UGE and scales (Clinical Prediction Rule – CPR), Varices Prediction Rule – VPR), King's Variceal Prediction Score – K-VaPS) and Platelet count/Spleen diameter Ratio – PSR). Qualitative variables were expressed as absolute frequency and percentage, and quantitative variables as median and interquartile range. U Mann–Whitney and Hanley–McNeil tests were used for comparisons. Results Forty-five UGE were analysed. 80% (n=36) presented OV: median of 3 (2–3) and 33.3% (n=12) required endoscopic variceal ligation. Statistical differences were demonstrated between both groups: CPR (142.39 [132.22-166.53] vs. 122.75 [115.24-133.15]; p=0.003), VPR (9.91 [9.36-11.75] vs. 5.6 [3.34-8.39]; p=0.001), K-VaPS (117.86 [99.66-126.58] vs. 99.64 [94.88-10.18]; p=0.019), PSR (2384.62 [1902.22-3201.63] vs. 1252.5 [579.6-2144.42]; p=0.05), with and area under the curve AUROC>75%, without statistical differences between scales. ConclusionsIn paediatric patients with non-cirrotic PVT non-invasive scales can be used as a tool to predict the presence of OV and raise the indication of UGE. (AU)

Screening for exclusion of high-risk bleeding features of esophageal varices in cirrhosis through CT and MRI.

BACKGROUND & AIM: Esophageal varices (EV) screening guidelines have evolved with improved risk stratification to avoid unnecessary esophagogastroduodenoscopy (EGD) in individuals with low bleeding risks. However, uncertainties persist in the recommendations for certain patient groups, particularly those with hepatocellular carcinoma (HCC) and/or receiving non-selective beta-blockers (NSBB) without prior endoscopy. This study assessed the efficacy of imaging in ruling out EVs and their high-risk features associated with bleeding in patients with cirrhosis and with HCC. We also evaluated the impact of NSBB on the detection of these characteristics. METHODS: A total of 119 patients undergoing EGD with CT and/or MRI within 90 days of the procedure were included. 87 patients had HCC. A new imaging grading system was developed utilizing the size of EVs and the extent of their protrusion into the esophagus lumen. The negative predictive value (NPV) of EVimaging(-) versus EVimaging (+) (grades 1-3) in ruling out the presence of EV and/or high-risk features by EGD was calculated. The predictive performance of imaging was determined by logistic regression. RESULTS: The NPV of imaging for detecting EV and high-risk features was 81 % and 92 %, respectively. Among HCC patients, the NPV for EV and high-risk features was 80 % and 64 %, respectively. Being on NSBB didn't statistically impact the imaging detection of EV. Imaging was a better predictor of high-risk EGD findings than Child-Turcotte-Pugh scores. CONCLUSIONS: Our results suggest that imaging can effectively rule out the presence of EV and high-risk features during EGD, even in patients with HCC and/or receiving NSBB.

Diagnostic value of liver stiffness measurement combined with risk scores for esophagogastric variceal bleeding in patients with hepatitis B cirrhosis.

PURPOSE: To assess the predictive value of liver stiffness measurement (LSM) and three bleeding risk scoring systems for esophagogastric varices bleeding (EGVB) in patients with hepatitis B cirrhosis during hospitalization. METHODS: In this study, 210 patients who had hepatitis B cirrhosis were selected as the subjects. They were categorized into two groups based on whether EGVB occurred during hospitalization: a bleeding group (70 cases) and a non-bleeding group (140 cases). Logistic regression was used to analyze the factors related to the occurrence of EGVB, and the diagnostic performance was evaluated using a receiver operating characteristic (ROC) curve. RESULTS: Significant differences were observed between the two groups in systolic blood pressure, platelet count, albumin, urea nitrogen, LSM, pre-endoscopic Rockall score (PRS), Glasgow-Blatchford score (GBS), and AIMS65 score (P < 0.05). The correlation analysis showed that LSM had significant positive relationship with PRS, GBS and AIMS65 score. Logistic regression analysis revealed that LSM and GBS score were independent risk factors for EGVB occurrence during hospitalization. ROC curve analysis showed that the combined prediction model of LSM and GBS score had the best prediction performance for EGVB occurrence, with an ROC curve area of 0.811, which was significantly better than the three risk scoring systems (P < 0.05), but similar to the predicted value of LSM (P = 0.335). CONCLUSIONS: The combination of LSM and GBS score can significantly improve the predictive efficacy of EGVB occurrence in patients with hepatitis B cirrhosis during hospitalization, which has important clinical significance for patients' prognosis.

Application of Indian ink markers for locating gastric varices under endoscopic ultrasonography.

OBJECTIVE: The present study aimed to investigate the accuracy of endoscopic ultrasonography (EUS) combined with Indian ink in locating target vessels of gastric varices (GVs) compared with conventional endoscopic techniques. Additionally, the characteristics of GVs under conventional endoscopy were also explored. METHODS: All 50 cirrhotic patients with GVs between August 2021 and December 2022 were included in the study. Firstly, conventional endoscopy was employed to identify GVs and to record the expected injection sites. Subsequently, EUS was used to locate the perforated vessel and the injection site was them marked with India ink followed by injection with cyanoacrylate (CYA). Finally, conventional endoscopy was used to examine GVs, to identify the marker points of Indian ink and to compare whether the injection points under conventional endoscopy were consistent with those marked with Indian ink. Furthermore, patients with consistent and inconsistent distribution of endoscopic markers and injection sites were divided into two groups. RESULTS: EUS could detect the perforating vessels in real time and intuitively. The distribution of markers using EUS was significantly different compared with the injection points obtained by conventional endoscopy (P < 0.001). Therefore, 20 cases were allocated to the consistent group and 30 cases to the non-consistent group. 16 patients who showed red wale signs were obtained in the consistent group and 11 patients in the non-consistent group (P = 0.048). The diameter of the largest GVs was 13.5 (10-15) mm in the consistent group compared with 10 (7.5-10) mm in the non-consistent group (P = 0.006). CONCLUSION: EUS could provide the exact location of GVs, thus more accurately describing the endoscopic characteristics of the GVs. Furthermore, the red wale signs and diameter of the largest GVs obtained using conventional endoscopy were helpful in determining the location of target GVs.

Endovascular management of sinistral portal hypertension-related variceal hemorrhage: a multicenter retrospective study.

PURPOSE: This study aimed to assess the safety and efficacy of endovascular managements, including splenic vein recanalization (SVR), partial splenic embolization (PSE), and percutaneous transsplenic gastric varices embolization combined with PSE (PSE+GVE), for management of SPH-related variceal hemorrhage (VH). METHODS: A total of 61 patients with SPH-related VH from three hospitals were enrolled and classified into three groups: the SVR group (Group 1, n=24), the PSE+GVE group (Group 2, n=17), and the PSE group (Group 3, n=20). Baseline characteristics and clinical outcomes were compared among the groups. RESULTS: The technical success rates for transhepatic and transsplenic SVR were 27.8% and 34.6%, respectively. No major complications were observed during any of the procedures. The median follow-up period was 53.2 months. The 2-year GI rebleeding rates for Group 1, 2, and 3 were 0%, 5.9%, and 35%, respectively. Groups 1 and 2 have a lower GI rebleeding rate (p = 0.002, p = 0.048, respectively) and better results of the degree of GV (p = 0.003, p = 0.044, respectively) compared to Group 3. No significant differences were found in 2-year GI rebleeding rates and the degree of GV between Group 1 and 2 (p = 0.415, p = 0.352, respectively). CONCLUSION: SVR, PSE+GVE, and PSE seem safe and effective for management of SPH-related VH. SVR appears to be the superior treatment option. Transsplenic access may further increase the SVR success rate. PSE+GVE seems to have comparable outcomes in GV control and GI rebleeding rates compared to SVR, while superior to PSE.

Role of Interventional Radiology (IR) in vascular emergencies among cirrhotic patients.

Gastrointestinal hemorrhage remains one of the most common causes of morbidity and mortality among patients with liver cirrhosis. Mostly, these patients bleed from the gastroesophageal varices. However, nonvariceal bleeding is also more likely to occur in these patients. Because of frequent co-existing coagulopathy, cirrhotics are more prone to bleed from a minor vascular injury while performing percutaneous interventions. Ultrasound-guided bedside vascular access is an essential procedure in liver critical care units. Transjugular portosystemic shunts (TIPS) with/without variceal embolization is a life-saving measure in patients with refractory variceal bleeding. Whenever feasible, balloon-assisted retrograde transvenous obliteration (BRTO) is an alternative to TIPS in managing gastric variceal bleeding, but without a risk of hepatic encephalopathy. In cases of failed or unfeasible endotherapy, transarterial embolization using various embolic agents remains the cornerstone therapy in patients with nonvariceal bleeding such as ruptured hepatocellular carcinoma, gastroduodenal ulcer bleeding, and procedure-related hemorrhagic complications. Among various embolic agents, N-butyl cyanoacrylate (NBCA) enables better vascular occlusion in cirrhotics, even in coagulopathy, making it a more suitable embolic agent in an expert hand. This article briefly entails the different interventional radiological procedures in vascular emergencies among patients with liver cirrhosis.

Simple Scoring System for Esophagogastric Varices Prediction in Hepatocellular Carcinoma Patients without Liver Stiffness Evaluation.

INTRODUCTION: For predicting esophagogastric varices (EGVs), the Virtual Baveno VII Consensus Workshop has proposed a combination of liver stiffness determination and platelet count measurement using a FibroScan®. However, FibroScan® is not available at all institutions. The present study aimed to develop a simple method to predict development of EGV using only general blood examination results. MATERIALS AND METHODS: A total of 1,090 hepatocellular carcinoma patients were enrolled, after excluding 956 with major portal vein tumor thrombus (Vp3/Vp4) or without upper gastrointestinal endoscopy examination results available. Those with EGV (≥ grade F2) or a history of treatment for the condition were defined as positive for significant EGV, and then clinical factors were retrospectively evaluated to determine indicators of occurrence. RESULTS: Logistic multivariate analysis showed platelet count (≤12 × 104/µL) (odds ratio [OR] 3.79, p < 0.001), mALBI grade 2a (OR 1.52, p = 0.036), and mALBI 2b or 3 (OR 3.46, p < 0.001) as significant predictive factors. Based on the OR values, platelet count (≤12 × 104/µL) and mALBI grade 2b/3 were each assigned 2 points and mALBI 2a was given 1 point, with the result termed recommendation for EGV screening (REGS) score. Significant EGV occurrence was noted in 2.9% (9/311) of the patients with a REGS score 0, 11.0% (13/118) with a score 1, 19.3% (53/274) with a score 2, 29.5% (39/132) with a score 3, and 38.0% (97/255) with a score 4 (p < 0.001). CONCLUSION: The findings indicate that REGS score can provide useful predictive information for development of significant EGV without the need for special equipment such as a FibroScan®.

Predicting the risk of early bleeding following endoscopic variceal ligation in cirrhotic patients with computed tomography.

BACKGROUND: Life-threatening bleeding following endoscopic variceal ligation (EVL) in patients with cirrhosis rarely can occur. The present study aimed to evaluate the performance of computed tomography (CT) in predicting the risk of early bleeding following EVL in cirrhotic patients. METHODS: We retrospectively investigated 285 cirrhotic patients who had undergone EVL. EVL was performed for prophylaxis or acute variceal bleeding. The patients were classified into 2 groups: early bleeding (< 14 days after EVL) and non-early bleeding. We compared baseline characteristics including CT findings between the patient groups. RESULTS: Among the 285 patients who underwent EVL treatment, 19 patients (6.7%) experienced early bleeding. On average, these bleeding occurred 9.3 ± 3.5 days after the EVL, with a range of 3 to 13 days. Patients who experience early bleeding had a higher six-week bleeding-related mortality rate compared to those in the non-early bleeding group (31.6% vs. 10.2%; p = 0.014). There was a correlation between the grade of esophageal varix observed during endoscopy and the diameter of esophageal varix observed on CT (p < 0.001). The diameter of esophageal varix on CT was identified as the only significant predictive factor for early bleeding (p = 0.005). CONCLUSION: A larger esophageal varix diameter observed on CT is associated with an increased risk of early bleeding after EVL treatment. Early identification of this high-risk group can provide a change of treatment strategies to improve patient outcomes.

Deep learning to predict esophageal variceal bleeding based on endoscopic images.

OBJECTIVE: Esophageal varix (EV) bleeding is a particularly serious complications of cirrhosis. Prediction of EV bleeding requires extensive endoscopy experience; it remains unreliable and inefficient. This retrospective cohort study evaluated the feasibility of using deep learning (DL) to predict the 12-month risk of EV bleeding based on endoscopic images. METHODS: Six DL models were trained to perform binary classification of endoscopic images of EV bleeding. The models were subsequently validated using an external test dataset, then compared with classifications performed by two endoscopists. RESULTS: In the validation dataset, EfficientNet had the highest accuracy (0.910), followed by ConvMixer (0.898) and Xception (0.875). In the test dataset, EfficientNet maintained the highest accuracy (0.893), which was better than the endoscopists (0.800 and 0.763). Notably, one endoscopist displayed higher recall (0.905), compared with EfficientNet (0.870). When their predictions were assisted by artificial intelligence, the accuracies of the two endoscopists increased by 17.3% and 19.0%. Moreover, statistical agreement among the models was dependent on model architecture. CONCLUSIONS: This study demonstrated the feasibility of using DL to predict the 12-month risk of EV bleeding based on endoscopic images. The findings suggest that artificial intelligence-aided diagnosis will be a useful addition to cirrhosis management.

Spleen stiffness: a new tool to predict high-risk varices in cirrhotic patients.

INTRODUCTION: Cirrhosis is one of the major causes of morbidity and mortality worldwide. Portal hypertension is the major contributor of cirrhosis-related complications and is defined as a hepatic venous pressure gradient (HVPG) > 5 mmHg. Measurement of HVPG is an invasive, difficult, and costly procedure. Therefore, it is only performed in specialized centers. Liver stiffness measured with transient elastography is one of the most studied noninvasive markers of portal hypertension, and spleen elastography has recently emerged as an important adjuvant tool. The development of a new probe (100 Hz) that more reliably reflect the grade of portal hypertension evaluated by spleen stiffness measurement has improved the accuracy of this technique. The aim of this work was to evaluate the accuracy of spleen stiffness with the new dedicated probe to predict the presence of high-risk varices, as well as to determine the ideal cutoff to predict it. METHODS: Prospective study of cirrhotic patients admitted to upper endoscopy that were also submitted to liver and spleen elastography with the 100-Hz probe by the same blinded operator in a tertiary center. RESULTS: We included 209 cirrhotic patients, with mean age of 61.9 years (±9.9), 77.0% male. The most common etiology was alcoholic liver disease (72.7%). The median value of liver elastography was 25.3 [4.5-75] kPa, and the median value of spleen elastography was 42.4 [7.6-100] kPa. At the cutoff of 53.25 kPa, we obtained sensitivity of 100% and specificity of 72.6% to predict high-risk varices, and, according to this cutoff, 133/175 of esophagogastroduodenoscopy could have been spared (76.0%), while according to Baveno guidelines, only 51/175 would have been spared (29.1%). CONCLUSION: In the era of noninvasive exams, spleen elastography with the 100-Hz probe emerges as an excellent tool for prediction of presence of high-risk varices. At the cutoff of 53.25 kPa, spleen elastography avoids upper endoscopy for screening for high-risk varices, promising to be become part of the hepatologists' daily routine.

Endoscopic ultrasonography-guided injection of cyanoacrylate in the treatment of gastroesophageal varices type 1: a single-center randomized study.

BACKGROUND AND AIM: First, it has been demonstrated that endoscopic ultrasonography (EUS)-guided cyanoacrylate (CYA) injection (EUS-CYA) has greater efficacy than direct endoscopic injection of cyanoacrylate (DEI-CYA) for treating type 1-isolated gastric varices. However, it is necessary to conduct further studies to determine whether EUS has any advantage over the current guidelines for treating gastroesophageal varices type 1 (GOV1). Second, liver function is an important prognostic factor in patients with liver cirrhosis. Therefore, we evaluated the liver function of patients treated with EUS-CYA. METHODS: In a single-center study, a prospective cohort from February 2021 to September 2022 involving 89 patients with cirrhosis with GOV1 were assigned to undergo EUS-CYA (n = 45) or DEI-CYA (n = 44). The success rate of CYA injection, the rate of overall rebleeding, the rate of reintervention, the complications during the follow-up period, and the liver function were compared. RESULTS: In both groups, 100% of the operations were successful. The follow-up time of the two groups was 290 (153-398) days and 267 (177-416) days, respectively. In the EUS group, the perforating veins had an average diameter of 7.0 ± 2.7 mm, and they had a 100% occlusion rate. A statistically significant difference was found between the two groups regarding the number of sessions needed to eradicate GV (p = 0.005, pairwise comparisons were conducted using the Bonferroni correction method.), the late rebleeding rate after EUS-CYA [n = 3 (6.7%) vs n = 10 (22.7%); p = 0.032], and the incidence of postinjection ulcers [n = 4 (8.9%) vs n = 12 (27.3); p = 0.023)]. Following EUS or DEI-CYA treatment, the patient's liver function did not show any significant deterioration or decline. CONCLUSION: EUS-CYA has a higher eradication success rate and fewer complications, recurrences, and rebleeding episodes than DEI-CYA used for GOV1 treatment. In addition, EUS-CYA did not impair liver function.

Endoscopic Ultrasound-Guided Transgastric Shunt Obliteration for Recurrent Hepatic Encephalopathy.

INTRODUCTION: Occlusion of spontaneous portosystemic shunts (SPSSs) in patients with cirrhosis may be required in recurrent or refractory hepatic encephalopathy. We describe a novel method for occlusion of SPSS using endoscopic ultrasound (EUS). METHODS: EUS-guided transgastric shunt obliteration was performed by injecting glue and coils directly into SPSS. RESULTS: EUS-guided transgastric shunt obliteration was performed for 7 patients in 9 sessions. Complete cessation of Doppler flow was achieved in 6/7 cases. Adequate clinical response was observed in 6/7 patients. No procedure-related severe adverse events were seen. DISCUSSION: This novel technique is a potentially effective and efficient method for shunt obliteration.

Gastric variceal bleeding as a form of presentation of a pancreatic neuroendocrine tumor.

NETs (neuroendocrine tumors) constitute a heterogeneous group of epithelial-type neoplasms with a predominantly neuroendocrine differentiation. Although the most common locations are the pancreas, digestive tract, and lung, this type of neoplasm can arise in virtually any organ in the body. They are rare tumors with a wide variety of clinical presentations. Symptomatic tumors are more frequent in younger patients and present at more advanced pathological stages. We present the case of a 42-year-old male with idiopathic splenomegaly and bicytopenia (anaemia and thrombocytopenia) under study by haematology department who was admitted due to an episode of melena and hemoglobin of 4.5 mg/dl. Isolated gastric varices (IGV1) with red spots were confirmed at gastroscopy and endoscopic variceal obturation using cyanoacrylate was performed in two sessions. An endoscopic ultrasonography was performed, showing thrombosis of the splenic vein extending towards the splenoportal confluence with anechoic serpiginous structures outside and inside the gastric wall suggestive of collateral circulation with gastric varices (GV). An increase in portal caliber was observed, with no signs of liver cirrhosis. Computed tomography confirms the findings. Two months/week/days later he was readmitted with rebleeding signs after starting anticoagulant treatment, so it was decided to perform a splenectomy due to failure of the endoscopic treatment. Histology revealed infiltration of the spleen by a well-differentiated neuroendocrine tumor (NET). Gallium PET/CT and Octreotid scan showed uptake in the body and tail of the pancreas with positivity for somatostatin receptors previously undetected by other means. Finally, treatment was completed with distal pancreatectomy and splenoportal axis trombectomy with vascular esplenic resection and the patient was discharged from hospital.

Treatment of colonic varices and gastrointestinal bleeding by recanalization and stenting of splenic-vein-thrombosis: A case report and literature review.

BACKGROUND: Splenic vein thrombosis is a known complication of pancreatitis. It can lead to increased blood flow through mesenteric collaterals. This segmental hypertension may result in the development of colonic varices (CV) with a high risk of severe gastrointestinal bleeding. While clear guidelines for treatment are lacking, splenectomy or splenic artery embolization are often used to treat bleeding. Splenic vein stenting has been shown to be a safe option. CASE SUMMARY: A 45-year-old female patient was admitted due to recurrent gastrointestinal bleeding. She was anemic with a hemoglobin of 8.0 g/dL. As a source of bleeding, CV were identified. Computed tomography scans revealed thrombotic occlusion of the splenic vein, presumably as a result of a severe acute pancreatitis 8 years prior. In a selective angiography, a dilated mesenterial collateral leading from the spleen to enlarged vessels in the right colonic flexure and draining into the superior mesenteric vein could be confirmed. The hepatic venous pressure gradient was within normal range. In an interdisciplinary board, transhepatic recanalization of the splenic vein via balloon dilatation and consecutive stenting, as well as coiling of the aberrant veins was discussed and successfully performed. Consecutive evaluation revealed complete regression of CV and splenomegaly as well as normalization of the red blood cell count during follow-up. CONCLUSION: Recanalization and stenting of splenic vein thrombosis might be considered in patients with gastrointestinal bleeding due to CV. However, a multidisciplinary approach with a thorough workup and discussion of individualized therapeutic strategies is crucial in these difficult to treat patients.

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

OBJECTIVES: To develop and validate a machine learning model based on contrast-enhanced CT to predict the risk of occurrence of the composite clinical endpoint (hospital-based intervention or death) in cirrhotic patients with acute variceal bleeding (AVB). METHODS: This retrospective study enrolled 330 cirrhotic patients with AVB between January 2017 and December 2020 from three clinical centers. Contrast-enhanced CT and clinical data were collected. Centers A and B were divided 7:3 into a training set and an internal test set, and center C served as a separate external test set. A well-trained deep learning model was applied to segment the liver and spleen. Then, we extracted 106 original features of the liver and spleen separately based on the Image Biomarker Standardization Initiative (IBSI). We constructed the Liver-Spleen (LS) model based on the selected radiomics features. The performance of LS model was evaluated by receiver operating characteristics and calibration curves. The clinical utility of models was analyzed using decision curve analyses (DCA). RESULTS: The LS model demonstrated the best diagnostic performance in predicting the composite clinical endpoint of AVB in patients with cirrhosis, with an AUC of 0.782 (95% CI 0.650-0.882) and 0.789 (95% CI 0.674-0.878) in the internal test and external test groups, respectively. Calibration curves and DCA indicated the LS model had better performance than traditional clinical scores. CONCLUSION: A novel machine learning model outperforms previously known clinical risk scores in assessing the prognosis of cirrhotic patients with AVB CLINICAL RELEVANCE STATEMENT: The Liver-Spleen model based on contrast-enhanced CT has proven to be a promising tool to predict the prognosis of cirrhotic patients with acute variceal bleeding, which can facilitate decision-making and personalized therapy in clinical practice. KEY POINTS: • The Liver-Spleen machine learning model (LS model) showed good performance in assessing the clinical composite endpoint of cirrhotic patients with AVB (AUC ≥ 0.782, sensitivity ≥ 80%). • The LS model outperformed the clinical scores (AUC ≤ 0.730, sensitivity ≤ 70%) in both internal and external test cohorts.