Remaining challenges for the noninvasive diagnosis of esophageal varices in liver cirrhosis

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.

Shear wave elastography measured liver stiffness-spleen size-to-platelet ratio for the prediction of high-risk oesophageal varices: a meta-analysis

OBJECTIVES

The potential predictive role of shear wave elastography (SWE) measured liver stiffness-spleen size-to-platelet ratio score (LSPS) for high-risk oesophageal varices (HREV) in patients with cirrhosis remains controversial. A systematic review and meta-analysis was performed to investigate the diagnostic efficacy of SWE-measured LSPS for HREV.

METHODS

Relevant studies were retrieved by searching PubMed, Embase, Web of Science, Wanfang, and CNKI databases. Only studies comparing the diagnostic efficacy of SWE-measured LSPS with oesophagogastroduodenoscopy for HREV in patients with cirrhosis were included. Pooled sensitivity and specificity were calculated with a random-effect model.

RESULTS

Overall, eight cohorts were included. Four of them used point SWE (pSWE) and the other four used 2D-SWE. Pooled results showed that a high LSPS measured by pSWE and 2D-SWE were both associated with satisfying diagnostic efficacy for endoscopic-evidenced HREV, with pooled sensitivity, specificity, diagnostic odds ratio, and pooled area under receiver operating characteristic curve of 0.86, 0.86, 39.36, and 0.92 for pSWE-derived LSPS, and 0.77, 0.86, 20.64, and 0.89 for 2D-SWE-derived LSPS. No significant difference was observed in the diagnostic efficacy between pSWE- and 2D-SWE-derived LSPS ( P all > 0.05). Significant heterogeneity was observed. However, further subgroup and meta-regression analysis failed to show that differences in study design, sex, diagnosis (compensated or overall cirrhosis), or LPSP cutoffs may lead to heterogeneity ( P for subgroup difference > 0.05).

CONCLUSION

A high LSPS with liver stiffness measured by pSWE or 2D-SWE shows satisfying predictive accuracy for HREV in patients with cirrhosis.

Clinical-radiomics nomogram for predicting esophagogastric variceal bleeding risk noninvasively in patients with cirrhosis

BACKGROUND

Esophagogastric variceal bleeding (EGVB) is a serious complication of patients with decompensated cirrhosis and is associated with high mortality and morbidity. Early diagnosis and screening of cirrhotic patients at risk for EGVB is crucial. Currently, there is a lack of noninvasive predictive models widely available in clinical practice.

AIM

To develop a nomogram based on clinical variables and radiomics to facilitate the noninvasive prediction of EGVB in cirrhotic patients.

METHODS

A total of 211 cirrhotic patients hospitalized between September 2017 and December 2021 were included in this retrospective study. Patients were divided into training (n = 149) and validation (n = 62) groups at a 7:3 ratio. Participants underwent three-phase computed tomography (CT) scans before endoscopy, and radiomic features were extracted from portal venous phase CT images. The independent sample t-test and least absolute shrinkage and selection operator logistic regression were used to screen out the best features and establish a radiomics signature (RadScore). Univariate and multivariate analyses were performed to determine the independent predictors of EGVB in clinical settings. A noninvasive predictive nomogram for the risk of EGVB was built using independent clinical predictors and RadScore. Receiver operating characteristic, calibration, clinical decision, and clinical impact curves were applied to evaluate the model’s performance.

RESULTS

Albumin (P = 0.001), fibrinogen (P = 0.001), portal vein thrombosis (P = 0.002), aspartate aminotransferase (P = 0.001), and spleen thickness (P = 0.025) were selected as independent clinical predictors of EGVB. RadScore, constructed with five CT features of the liver region and three of the spleen regions, performed well in training (area under the receiver operating characteristic curve (AUC) = 0.817) as well as in validation (AUC = 0.741) cohorts. There was excellent predictive performance in both the training and validation cohorts for the clinical-radiomics model (AUC = 0.925 and 0.912, respectively). Compared with the existing noninvasive models such as ratio of aspartate aminotransferase to platelets and Fibrosis-4 scores, our combined model had better predictive accuracy with the Delong's test less than 0.05. The Nomogram had a good fit in the calibration curve (P > 0.05), and the clinical decision curve further supported its clinical utility.

CONCLUSION

We designed and validated a clinical-radiomics nomogram able to noninvasively predict whether cirrhotic patients will develop EGVB, thus facilitating early diagnosis and treatment.

Can Location of Stiffness Measurement Impact Spleen 2-Dimensional Shear Wave Elastography Measurement?

ABSTRACT

Ultrasound-based spleen elastography is a promising surrogate to predict portal hypertension noninvasively. In contrast to defined standards for liver stiffness measurement, the standardized examination procedures for 2-dimensional (2D) shear wave elastography spleen elastography have not been established yet. The aim was to investigate the impact of location of stiffness measurement on 2D shear wave elastography spleen stiffness measurement (SSM). Patients with splenomegaly were enrolled. Both B-mode ultrasound and elastography of spleen were performed. For SSM, 3 regions were chosen for spleen measurement: lower pole region, central region, and the region between lower pole and center. Mean SSM value, success rate, and reliability predicators (standard deviation, standard deviation/mean, size of region of interest) were assessed. A total of 124 patients were included. For mean SSM value, there were no significant differences among 3 regions. Spleen stiffness measurement success rate in lower pole region, central region, and the region between them was 63.7% (79), 91.1% (113), and 78.2% (97), respectively. The success rate in the central region was significantly higher than that in the other 2 regions (P < 0.05). Reliability in the central region was also highest among the 3 regions. Location of stiffness measurement has a limited effect on SSM. Changing location of measurement will not influence mean stiffness value in spleen.

A novel radiomics-platelet nomogram for the prediction of gastroesophageal varices needing treatment in cirrhotic patients

BACKGROUND AND AIMS

Highly accurate noninvasive methods for predicting gastroesophageal varices needing treatment (VNT) are desired. Radiomics is a newly emerging technology of image analysis. This study aims to develop and validate a novel noninvasive method based on radiomics for predicting VNT in cirrhosis.

METHODS

In this retrospective-prospective study, a total of 245 cirrhotic patients were divided as the training set, internal validation set and external validation set. Radiomics features were extracted from portal-phase computed tomography (CT) images of each patient. A radiomics signature (Rad score) was constructed with the least absolute shrinkage and selection operator algorithm and tenfold cross-validation in the training set. Combined with independent risk factors, a radiomics nomogram was built with a multivariate logistic regression model.

RESULTS

The Rad score, consisting of 14 features from the gastroesophageal region and 5 from the splenic hilum region, was effective for VNT classification. The diagnostic performance was further improved by combining the Rad score with platelet counts, achieving an AUC of 0.987 (95% CI 0.969-1.00), 0.973 (95% CI 0.939-1.00) and 0.947 (95% CI 0.876-1.00) in the training set, internal validation set and external validation set, respectively. In efficacy and safety assessment, the radiomics nomogram could spare more than 40% of endoscopic examinations with a low risk of missing VNT (< 5%), and no more than 8.3% of unnecessary endoscopic examinations still be performed.

CONCLUSIONS

In this study, we developed and validated a novel, diagnostic radiomics-based nomogram which is a reliable and noninvasive method to predict VNT in cirrhotic patients.

CLINICAL TRIALS REGISTRATION

NCT04210297.

Screening varices in patients with HBV-related cirrhosis on antiviral therapy: Platelet alone or together with LSM

BACKGROUND & AIMS

Non-invasive assessment criteria to rule out high-risk varices (HRV) in compensated hepatitis B virus (HBV) cirrhosis on antiviral therapy remains unclear.

METHODS

HBV-related compensated cirrhotic patients who underwent screening endoscopy during antiviral therapy were enrolled and randomly divided into the derivation and validation sets. HRV were defined as medium to large varices or small varices with red signs. Univariate and multivariate logistic analysis were used to determine the parameters associated with HRV.

RESULTS

A total of 436 HBV-related compensated cirrhotic patients screened for varices were enrolled, the median duration of antiviral therapy was 4 years (IQR: 2.5-5.5 years). In the derivation set (N = 290, 17.2% with HRV), only platelet (PLT) count (OR = 0.972, 95% CI 0.961-0.984, P < .05) was independently associated with HRV, whereas liver stiffness measurement was not associated with the presence of HRV. With a PLT count cut-off value of 105 × 10⁹ /L, unnecessary endoscopies could be spared in 56.9% patients, with a 3.6%. risk of missing HRV. In the validation cohort (N = 146, 16.4% with HRV), the proportion of patients that could safely spare endoscopies (61.0%) identified by this PLT count cut-off value was higher than that obtained by using Baveno VI criteria (34.9%), with an acceptable risk of missing HRV (3.4%).

CONCLUSION

Compared with the 'Baveno VI criteria or beyond' criteria, PLT count higher than 105 × 10⁹ /L could safely spare more screening endoscopies without increasing the risk of missing HRV in patients with HBV-related compensated cirrhosis on antiviral therapy.

Noninvasive markers for esophageal varices in children with cirrhosis

BACKGROUND

The diagnosis of esophageal varices (EV) is based on the findings of esophagogastroduodenoscopy (EGD), biopsy, and serum markers. Thus, noninvasive cost-effective tests through which high-risk EV children can be diagnosed are needed.

PURPOSE

This cross-sectional study aimed to identify the noninvasive markers for EV in children with liver cirrhosis.

METHODS

A total of 98 children with liver cirrhosis were evaluated in this study. The spleen size, platelet count, serum albumin, liver function test results, and risk scores were evaluated prior to endoscopy. The endoscopic investigations aimed to identify the presence of EV and red signs, and determine varices sizes.

RESULTS

Endoscopy revealed varices in 43 subjects (43.9%). The spleen size, platelet count, international normalized ratio, aspartate aminotransferase to platelet ratio index (APRI), platelet count to spleen size ratio, and risk score differed significantly between patients with and without EV on univariate analysis; however, the logistic regression analysis showed no differences, indicating that none of these parameters were independently associated with the presence of EV.

CONCLUSION

Platelet count, risk score, platelet count to spleen size, and APRI can be useful tools for the identification of highrisk patients with EV and might reduce the need for invasive methods like EGD.