Abstract
Background
Posthepatectomy liver failure is a worrisome complication after major hepatectomy
for hepatocellular carcinoma and is the leading cause of postoperative mortality.
Recommendations for hepatectomy for hepatocellular carcinoma are based on the risk
of severe posthepatectomy liver failure, and accurately predicting posthepatectomy
liver failure risk before undertaking major hepatectomy is of great significance.
Thus, herein, we aimed to establish and validate an artificial neural network model
to predict severe posthepatectomy liver failure in patients with hepatocellular carcinoma
who underwent hemihepatectomy.
Methods
Three hundred and fifty-three patients who underwent hemihepatectomy for hepatocellular
carcinoma were included. We randomly divided the patients into a development set (n = 265, 75%) and a validation set (n = 88, 25%). Multivariate logistic analysis facilitated identification of independent
variables that we incorporated into the artificial neural network model to predict
severe posthepatectomy liver failure in the development set and then verified in the
validation set.
Results
The morbidity of patients with severe posthepatectomy liver failure in the development
and validation sets was 24.9% and 23.9%, respectively. Multivariate analysis revealed
that platelet count, prothrombin time, total bilirubin, aspartate aminotransferase,
and standardized future liver remnant were all significant predictors of severe posthepatectomy
liver failure. Incorporating these factors, the artificial neural network model showed
satisfactory area under the receiver operating characteristic curve for the development
set of 0.880 (95% confidence interval, 0.836–0.925) and for the validation set of
0.876 (95% confidence interval, 0.801–0.950) in predicting severe posthepatectomy
liver failure and achieved well-fitted calibration ability. The predictive performance
of the artificial neural network model for severe posthepatectomy liver failure outperformed
the traditional logistic regression model and commonly used scoring systems. Moreover,
stratification into 3 risk groups highlighted significant differences between the
incidences and grades of posthepatectomy liver failure.
Conclusion
The artificial neural network model accurately predicted the risk of severe posthepatectomy
liver failure in patients with hepatocellular carcinoma who underwent hemihepatectomy.
Our artificial neural network model might help surgeons identify intermediate and
high-risk patients to facilitate earlier interventions.
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to SurgeryAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.CA Cancer J Clin. 2018; 68: 394-424
- AASLD guidelines for the treatment of hepatocellular carcinoma.Hepatology. 2018; 67: 358-380
- Asia-Pacific clinical practice guidelines on the management of hepatocellular carcinoma: a 2017 update.Hepatol Int. 2017; 11: 317-370
- European Association for the Study of the Liver. EASL Clinical Practice Guidelines: Management of hepatocellular carcinoma.J Hepatol. 2018; 69: 182-236
- The "50-50 criteria" on postoperative day 5: an accurate predictor of liver failure and death after hepatectomy.Ann Surg. 2005; 242 (discussion 828-829): 824-828
- Improving perioperative outcome expands the role of hepatectomy in management of benign and malignant hepatobiliary diseases: analysis of 1222 consecutive patients from a prospective database.Ann Surg. 2004; 240 (discussion 708-710): 698-708
- An ordinal model to predict the risk of symptomatic liver failure in patients with cirrhosis undergoing hepatectomy.J Hepatol. 2019; 71: 920-929
- Posthepatectomy liver failure: a definition and grading by the International Study Group of Liver Surgery (ISGLS).Surgery. 2011; 149: 713-724
- Risk factors for perioperative morbidity and mortality after extended hepatectomy for hepatocellular carcinoma.Br J Surg. 2003; 90: 33-41
- New perspectives in the assessment of future remnant liver.Dig Surg. 2014; 31: 255-268
- Assessment of the prognosis of cirrhosis: Child-Pugh versus MELD.J Hepatol. 2005; (42 Suppl(1):S100-S107)
- Transection of the oesophagus for bleeding oesophageal varices.Br J Surg. 1973; 60: 646-649
- A model to predict poor survival in patients undergoing transjugular intrahepatic portosystemic shunts.Hepatology. 2000; 31: 864-871
- Assessment of liver function in patients with hepatocellular carcinoma: a new evidence-based approach-the ALBI grade.J Clin Oncol. 2015; 33: 550-558
- Albumin-bilirubin versus Child-Pugh score as a predictor of outcome after liver resection for hepatocellular carcinoma.Br J Surg. 2016; 103: 725-734
- ALBI and PALBI grade predict survival for HCC across treatment modalities and BCLC stages in the MELD Era.J Gastroenterol Hepatol. 2017; 32: 879-886
- Platelet-albumin-bilirubin grade: Risk stratification of liver failure, prognosis after resection for hepatocellular carcinoma.Dig Liver Dis. 2019; 51: 1430-1437
- FIB-4: an inexpensive and accurate marker of fibrosis in HCV infection. comparison with liver biopsy and fibrotest.Hepatology. 2007; 46: 32-36
- Comparison of FIB-4 index and Child-Pugh score in predicting the outcome of hepatic resection for hepatocellular carcinoma.J Gastrointest Surg. 2020; 24: 823-831
- Performance of the aspartate aminotransferase-to-platelet ratio index for the staging of hepatitis C-related fibrosis: an updated meta-analysis.Hepatology. 2011; 53: 726-736
- Preoperative aspartate aminotransferase-to-platelet-ratio index as a predictor of posthepatectomy liver failure for resectable hepatocellular carcinoma.Cancer Manag Res. 2019; 11: 1401-1414
- A simple noninvasive index can predict both significant fibrosis and cirrhosis in patients with chronic hepatitis C.Hepatology. 2003; 38: 518-526
- Predictive value of indocyanine green retention test and indocyanine green clearance in Child-Pugh class A patients.Hepatology. 2015; 61: 2112-2113
- and the Liver Cancer Study Group of Japan. JSH Consensus-Based Clinical Practice Guidelines for the Management of Hepatocellular Carcinoma: 2014 Update by the Liver Cancer Study Group of Japan.Liver Cancer. 2014; 3: 458-468
- Liver planning software accurately predicts postoperative liver volume and measures early regeneration.J Am Coll Surg. 2014; 219: 199-207
- Virtual hepatic resection using three-dimensional reconstruction of helical computed tomography angioportograms.Ann Surg. 2001; 233: 221-226
- Volumetric analysis and indocyanine green retention rate at 15 min as predictors of post-hepatectomy liver failure.HPB (Oxford). 2015; 17: 159-167
- Combining albumin-bilirubin score with future liver remnant predicts post-hepatectomy liver failure in HBV-associated HCC patients.Liver Int. 2018; 38: 494-502
- Three hundred and one consecutive extended right hepatectomies: evaluation of outcome based on systematic liver volumetry.Ann Surg. 2009; 250: 540-548
- Edinburgh Liver Surgery and Transplantation Experimental Research Group (eLISTER). The value of residual liver volume as a predictor of hepatic dysfunction and infection after major liver resection.Gut. 2005; 54: 289-296
- Artificial neural networks and prostate cancer--tools for diagnosis and management.Nat Rev Urol. 2013; 10: 174-182
- A novel approach for accurate prediction of spontaneous passage of ureteral stones: support vector machines.Kidney Int. 2006; 69: 157-160
- Neural network and regression predictions of 5-year survival after colon carcinoma treatment.Cancer. 2001; 91: 1673-1678
- Portal hypertension and the outcome of surgery for hepatocellular carcinoma in compensated cirrhosis: a systematic review and meta-analysis.Hepatology. 2015; 61: 526-536
- Development and validation of a nomogram to preoperatively estimate post-hepatectomy liver dysfunction risk and long-term survival in patients with hepatocellular carcinoma.Ann Surg. 2020; (Available from:)https://doi.org/10.1097/sla.0000000000003803
- Combining aspartate aminotransferase-to-platelet ratio index with future liver remnant to assess preoperative hepatic functional reserve in patients with hepatocellular carcinoma.J Gastrointest Surg. 2020; (Available from:)https://doi.org/10.1007/s11605-020-04575-w
- X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization.Clin Cancer Res. 2004; 10: 7252-7259
- Comparison between dynamic gadoxetate-enhanced MRI and 99m Tc-mebrofenin hepatobiliary scintigraphy with SPECT for quantitative assessment of liver function.Eur Radiol. 2019; 29: 5063-5072
- The BARD score and the NAFLD fibrosis score in the assessment of advanced liver fibrosis in nonalcoholic fatty liver disease.Med Sci Monit. 2012; 18: CR735-CR740
- Platelet count is more useful for predicting posthepatectomy liver failure at surgery for hepatocellular carcinoma than indocyanine green clearance test.J Surg Oncol. 2016; 113: 565-569
- The gastroenterologist's guide to management of the post-liver transplant patient.Am J Gastroenterol. 2018; 113: 819-828
- Predictive power of prothrombin time and serum total bilirubin for postoperative mortality after major hepatectomy with extrahepatic bile duct resection.Surgery. 2014; 155: 504-511
- Increased liver markers are associated with higher risk of type 2 diabetes.World J Gastroenterol. 2015; 21: 7478-7487
- Mitochondrial injury, oxidative stress, and antioxidant gene expression are induced by hepatitis C virus core protein.Gastroenterology. 2002; 122: 366-375
Article info
Publication history
Published online: August 11, 2020
Accepted:
June 23,
2020
Footnotes
Rong-yun Mai and Hua-ze Lu contributed equally to this work.
RYM, LQL, and JZY conceived the study and revised the manuscript critically for important intellectual content. RYM, HZL, and TB made significant contributions to its design, acquisition, analyses, and interpretation of data. RL, YL, LM, BDX, and GBW participated in the design, acquisition, analyses, and interpretation of information. All authors read and approved the final manuscript.
Identification
Copyright
© 2020 Elsevier Inc. All rights reserved.
ScienceDirect
Access this article on ScienceDirectLinked Article
- Re: Artificial neural network model for preoperative prediction of severe liver failure after hemihepatectomy in patients with hepatocellular carcinomaSurgeryVol. 169Issue 4
- PreviewWe read the manuscript entitled “Artificial neural network model for preoperative prediction of severe liver failure after hemihepatectomy in patients with hepatocellular carcinoma” with great interest.1 The authors deserve appreciation for their effort. We agree with the authors that logistic regression models do not have the ability to detect all possible interactions between predictor variables. Compared with logistic regression models, the artificial neural network (ANN) is superior to logistic regression.
- Full-Text
- Preview
