Skip to main content

Advertisement

SpringerLink
Log in

A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients

  • Original Article
  • Published:
Hepatology International Aims and scope Submit manuscript

Abstract

Background and aim

To develop and validate a novel machine learning-based radiomic model (RM) for diagnosing high bleeding risk esophageal varices (HREV) in patients with cirrhosis.

Methods

A total of 796 qualified participants were enrolled. In training cohort, 218 cirrhotic patients with mild esophageal varices (EV) and 240 with HREV RM were included to training and internal validation groups. Additionally, 159 and 340 cirrhotic patients with mild EV and HREV RM, respectively, were used for external validation. Interesting regions of liver, spleen, and esophagus were labeled on the portal venous-phase enhanced CT images. RM was assessed by area under the receiver operating characteristic curves (AUROC), sensitivity, specificity, calibration and decision curve analysis (DCA).

Results

The AUROCs for mild EV RM in training and internal validation were 0.943 and 0.732, sensitivity and specificity were 0.863, 0.773 and 0.763, 0.763, respectively. The AUROC, sensitivity, and specificity were 0.654, 0.773 and 0.632, respectively, in external validation. Interestingly, the AUROCs for HREV RM in training and internal validation were 0.983 and 0.834, sensitivity and specificity were 0.948, 0.916 and 0.977, 0.969, respectively. The related AUROC, sensitivity and specificity were 0.736, 0.690 and 0.762 in external validation. Calibration and DCA indicated RM had good performance. Compared with Baveno VI and its expanded criteria, HREV RM had a higher accuracy and net reclassification improvements that were as high as 49.0% and 32.8%.

Conclusion

The present study developed a novel non-invasive RM for diagnosing HREV in cirrhotic patients with high accuracy. However, this RM still needs to be validated by a large multi-center cohort.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Availability of data and material

The datasets used and analyzed during the current study are available from the corresponding author.

Abbreviations

ALB:

Albumin

ALT:

Alanine aminotransferase

AST:

Aspartate aminotransferase

AUROC:

Under the receiver operating characteristic curves

Cr:

Creatinine

CT:

Computed tomography

DCA:

Decision curve analysis

DCE:

Dynamic contrast enhancement

EV:

Esophageal varices

HOG:

Histogram of oriented gradient

HREV:

High-risk esophageal varices

HVPG:

Hepatic venous pressure gradient

INR:

International normalized ratio

NRI:

Net reclassification improvement

PCA:

Principal components analysis

PLT:

Platelets counts

PT:

Prothrombin time

PTA:

Prothrombin time activity

RM:

Radiomic model

ROI:

Regions of interest

SVM:

Support vector machine

TB:

Total bilirubin

References

  1. Roberts D, Best LM, Freeman SC, et al. Treatment for bleeding oesophageal varices in people with decompensated liver cirrhosis: a network meta-analysis. Cochrane Database Syst Rev. 2021. https://doi.org/10.1002/2021/013155

    Article  PubMed  PubMed Central  Google Scholar 

  2. Jia-Li Ma, Ling-Ling He, Ping Li, et al. Clinical features and outcomes of repeated endoscopic therapy for esophagogastric variceal hemorrhage in cirrhotic patients: ten-year real-world analysis. Gastroenterol Res Pract. 2020. https://doi.org/10.1155/2020/5747563

    Article  Google Scholar 

  3. Tripathi D, Stanley AJ, Hayes PC, et al. U.K. Guidelines on the management of variceal haemorrhage in cirrhotic patients. Gut. 2015;64:1680–1704

    Article  PubMed  Google Scholar 

  4. Garcia-Tsao G, Abraldes JG, Berzigotti A, et al. Portal hypertensive bleeding in cirrhosis: risk stratification, diagnosis, and management: 2016 practice guidance by the American Association for the study of liver diseases. Hepatology. 2017;65:310–335

    Article  PubMed  Google Scholar 

  5. Chinese Portal Study Group (CHESS). Chinese Society of Gastroenterology. Consensus on clinical application of hepatic venous pressure gradient in China. Zhonghzua Gan Zang Bing Za Zhi. 2018;26:801–812

    Google Scholar 

  6. Xie W, Chen FX, Zhu LY, et al. Risk assessment of first upper gastrointestinal bleeding using computerized tomoscanning in esophageal varices patients with cirrhosis and portal hypertension. Medicine (Baltimore). 2020;99:e18923

    Article  Google Scholar 

  7. Han X, An W, Cao Q, et al. Noninvasive evaluation of esophageal varices in cirrhotic patients based on spleen hemodynamics: a dual-energy CT study. Eur Radiol. 2020;30:3210–3216

    Article  PubMed  Google Scholar 

  8. Inokuchi Y, Uematsu M, Takashina T. Diagnostic accuracy of the attenuation value in abdominal contrast enhanced dynamic multi-detector-row computed tomography for esophageal varices in patients with liver cirrhosis. Eur J Radiol Open. 2021;2021: 100347. https://doi.org/10.1016/2021/100347

    Article  Google Scholar 

  9. Li Y, Li L, Weng HL, Liebe R, Ding HG. Computed tomography vs liver stiffness measurement and magnetic resonance imaging in evaluating esophageal varices in cirrhotic patients: a systematic review and meta-analysis. World J Gastroenterol. 2020;26(18):2247–2267

    Article  PubMed  PubMed Central  Google Scholar 

  10. Ji GW, Zhu FP, Xu Q, et al. Radiomic features at contrast-enhanced CT predict recurrence in early stage hepatocellular carcinoma: a multi-institutional study. Radiology. 2020;294:568–579

    Article  PubMed  Google Scholar 

  11. Xiao-Yuan Xu, Hui-Guo D, Wen-Gang Li, et al. Chinese guidelines on the management of Liver cirrhosis(abbreviated version). World J Gastroenterol. 2020;26(45):7088–7103

    Article  Google Scholar 

  12. Shiha G, Ibrahim A, Helmy A, et al. Asian-Pacific Association for the Study of the Liver (APASL) consensus guidelines on invasive and non-invasive assessment of hepatic fibrosis: a 2016 update. Hepatol Int. 2017;11(1):1–30

    Article  PubMed  Google Scholar 

  13. Crabb DW, Lm GY, Szabo G, et al. Diagnosis and treatment of alcohol-associated liver diseases: 2019 practice guidance from the American Association for the Study of Liver Diseases. Hepatology. 2020;71(1):306–333

    Article  PubMed  Google Scholar 

  14. Mack CL, Adams D, Assis DN, et al. Diagnosis and management of autoimmune hepatitis in adults and children: 2019 practice guidance and guidelines from the American Association for the Study of Liver Diseases. Hepatology. 2020;72(2):671–722

    Article  PubMed  Google Scholar 

  15. Mohammed E, Shiv SK, Wong VWS, et al. The Asian Pacific Association for the study of the liver clinical practice guidelines for the diagnosis and management of metabolic associated fatty liver disease. Hepatol Int. 2020;14(6):889–919

    Article  Google Scholar 

  16. Chinese Society of Hepatology, Chinese Society of Gastroenterology and Endoscopy. Guidelines for the diagnosis and treatment of esophageal and gastric variceal bleeding in cirrhotic portal hypertension. Zhonghua Nei Ke Za Zhi. 2016;55:57–72

    Google Scholar 

  17. Tajiri T, Yoshida H, Obara K, et al. General rules for recording endoscopic findings of esophagogastric varices (2nd edition). Dig Endosc. 2010;22(1):1–9

    Article  PubMed  Google Scholar 

  18. De Franchis R. Expanding consensus in portal hypertension: report of the Baveno VI consensus workshop: stratifying risk and individualizing care for portal hypertension. J Hepatol. 2015;63:743–752

    Article  PubMed  Google Scholar 

  19. Kravetz D, Bildozola M, Argonz J, et al. Patients with ascites have higher variceal pressure and wall tension than patients without ascites. Am J Gastroenterol. 2000;95:1770–1775

    Article  CAS  PubMed  Google Scholar 

  20. S Augustin, M Pons, JB Maurice, et al. Expanding the Baveno VI criteria for the screening of varices in patients with compensated advanced chronic liver disease. Hepatology 2017; 66(6):1980–1988.

  21. Ferraioli G, Wong VW, Castera L, et al. Liver Ultrasound Elastography: an update to the world federation for ultrasound in medicine and biology guidelines and recommendations. Ultrasound Med Biol. 2018;44:2419–2440

    Article  PubMed  Google Scholar 

  22. Li H, Chen TW, Li ZL, et al. Albumin and magnetic resonance imaging-liver volume to identify hepatitis B-related cirrhosis and esophageal varices. World J Gastroenterol. 2015;21:988–996

    Article  PubMed  PubMed Central  Google Scholar 

  23. Jhang ZE, Wu KL, Chen CB, et al. Diagnostic value of spleen stiffness by magnetic resonance elastography for prediction of esophageal varices in cirrhotic patients. Abdom Radiol (NY). 2021;46(2):526–533

    Article  Google Scholar 

  24. Son JH, Lee SS, Lee Y, et al. Assessment of liver fibrosis severity using computed tomography-based liver and spleen volumetric indices in patients with chronic liver disease. Eur Radiol. 2020;30:3486–3496

    Article  PubMed  Google Scholar 

  25. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–1358

    Article  PubMed  Google Scholar 

  26. Sousa M, Fernandes S, Proenca L, et al. The Baveno VI criteria for predicting esophageal varices: validation in real life practice. Rev Esp Enferm Dig. 2017;109:704–707

    PubMed  Google Scholar 

Download references

Funding

This study was supported by the State Key Projects Specialized on Infectious Diseases (No. 2017ZX10203202-004), Digestive Medical Coordinated Development Center of Beijing Hospitals Authority (No. XXT24 and XXZ0801) and Sino-German Cooperation Group (No. GZ1517).

Author information

Author notes

  1. Yijie Yan, Yue Li, Chunlei Fan equally contributed to this manuscript.

Authors and Affiliations

  1. Department of Gastroenterology and Hepatology, Beijing You’an Hospital Affiliated With Capital Medical University, Beijing, 100069, China

    Yijie Yan, Yue Li, Chunlei Fan, Yuening Zhang, Shibin Zhang, Lei Li & Huiguo Ding

  2. Department of Gastroenterology, The Fourth Affiliated Hospital of Harbin Medical University, Harbin, 150001, Heilongjiang, China

    Yue Li

  3. Blot Info & Tech (Beijing) Co. Ltd, Beijing, 101200, China

    Zhi Wang & Tehui Huang

  4. Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China

    Zhenjia Ding

  5. Division of Gastroenterology and Hepatology, University of California, Irvine, School of Medicine, Orange, CA, USA

    Keqin Hu

Authors
  1. Yijie Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yue Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chunlei Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yuening Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shibin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Zhi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Tehui Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Zhenjia Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Keqin Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Lei Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Huiguo Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

YY, YL and CF were contributed equally to collecting the data, development and validation RM. HD designed the project and was in charge of the manuscript. ZD and KH performed the language polishing and scientific editing. LL and HD were contributed equally to writing and editing. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Lei Li or Huiguo Ding.

Ethics declarations

Conflict of interest

Yijie Yan, Yue Li, Chunlei Fan, Yuening Zhang, Shibin Zhang, Zhi Wang, Tehui Huang, Zhenjia Ding, Keqin Hu, Lei Li, and Huiguo Ding declare no conflict of interest.

Ethics statements

All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1975, as revised in 2008.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yan, Y., Li, Y., Fan, C. et al. A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients. Hepatol Int 16, 423–432 (2022). https://doi.org/10.1007/s12072-021-10292-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12072-021-10292-6

Keywords

Search

Navigation