Mortality risk after liver transplantation in hepatocellular carcinoma recipients: a nonlinear predictive model.

BACKGROUND The balanced application of a model for the estimate of outcomes of liver transplantation, in concert with assessment of disease severity, would not only improve transplant outcomes and maximize patient benefit from transplantation, but also facilitate informed decision making by patients and their relatives when considering transplantation. So far, however, linear discriminating methods have failed to attain sufficient power to predict post-transplant prognosis. Therefore, our aim was to develop a cancer-specific prognostic model by a nonlinear methodology based on pretransplant characteristics. METHODS With data collected retrospectively from 290 liver transplant recipients with HCC from February 1999 to August 2009, a multilayer perceptron (MLP) neural network was constructed to predict mortality risk after transplantation. Its predictive performances at posttransplant 1-, 2-, and 5-year intervals were evaluated using a receiver operating characteristic curve. RESULTS By the forward stepwise selection in MLP network, donor age, donor body mass index, recipient hemoglobin, serum concentrations of total bilirubin, alkaline phosphatase, creatinine, aspartate aminotransferase, international normalized ratio of prothrombin time, and Na(+); alpha fetoprotein categorization, total diameter, number of tumor lesions, presence of imaging macrovascular invasion, and lobe distribution of the tumor were identified to be the optimal input features. The MLP, employing 24 inputs and 7 hidden neurons, yielded c-statistics of 0.909 (P < .001) in the 1-year, 0.888 (P < .001), in the 2-year, and 0.845 (P < .001) in the 5-year prediction. CONCLUSION Post-transplant prognosis is a multidimensional, nonlinear problem, and the specific MLP can achieve high accuracy in the prediction of posttransplant mortality risk for HCC recipients. The pattern recognition methodologies like MLP hold promise for solving outcome prediction after liver transplantation.

[1]  G. McNatt,et al.  The Economic Impact of MELD on Liver Transplant Centers , 2005, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[2]  J. Fung,et al.  Liver transplantation in China , 2007, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[3]  D. E. Schaubela,et al.  The Survival Benefit of Deceased Donor Liver Transplantation as a Function of Candidate Disease Severity and Donor Quality , 2008 .

[4]  R. Wiesner,et al.  Model for end-stage liver disease (MELD) and allocation of donor livers. , 2003, Gastroenterology.

[5]  R. Wiesner.  Patient selection in an era of donor liver shortage: current US policy , 2005, Nature Clinical Practice Gastroenterology &Hepatology.

[6]  Hyunjin Park,et al.  Method for quantifying volumetric lesion change in interval liver CT examinations , 2003, IEEE Transactions on Medical Imaging.

[7]  S Mitchell,et al.  Early death or retransplantation in adults after orthotopic liver transplantation. Can outcome be predicted? , 1994, Transplantation.

[8]  B. Daniele,et al.  Design and Endpoints of Clinical Trials in Hepatocellular Carcinoma , 2008 .

[9]  C. Sabin,et al.  3-month and 12-month mortality after first liver transplant in adults in Europe: predictive models for outcome , 2006, The Lancet.

[10]  Liver-cell cancer and transplantation. , 2009, The Lancet. Oncology.

[11]  Patrick van der Smagt,et al.  Introduction to neural networks , 1995, The Lancet.

[12]  Sammy Saab,et al.  Pretransplant Model to Predict Posttransplant Survival in Liver Transplant Patients , 2002, Annals of surgery.

[13]  N D Heaton,et al.  Artificial neural network is superior to MELD in predicting mortality of patients with end-stage liver disease , 2006, Gut.

[14]  Yeong-Seok Im,et al.  Hyponatremia and Mortality among Patients on the Liver-Transplant Waiting List , 2009 .

[15]  S Mitchell,et al.  Predicting Outcomes After Liver Transplantation A Connectionist Approach , 1994, Annals of surgery.

[16]  T M Therneau,et al.  A model to predict survival in patients with end‐stage liver disease , 2001, Hepatology.

[17]  Riccardo Lencioni,et al.  Design and endpoints of clinical trials in hepatocellular carcinoma. , 2008, Journal of the National Cancer Institute.

[18]  R. Wolfe,et al.  The Survival Benefit of Liver Transplantation , 2005, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[19]  G. Ioannou,et al.  Development and validation of a model predicting graft survival after liver transplantation , 2006, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[20]  M. Ramundo,et al.  Artificial neural network predicts CT scan abnormalities in pediatric patients with closed head injury. , 2001, The Journal of trauma.

[21]  E. Trulock,et al.  The new lung allocation system and its impact on waitlist characteristics and post-transplant outcomes. , 2008, Seminars in Thoracic and Cardiovascular Surgery.

[22]  R. Wiesner,et al.  Resource Utilization in Liver Transplantation: Effects of Patient Characteristics and Clinical Practice , 2000 .

[23]  Minyou Chen,et al.  Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. , 2003, Clinical cancer research : an official journal of the American Association for Cancer Research.

[24]  J. Gong,et al.  Quantitative estimation of the degree of hepatic macrovesicular steatosis in a disease‐free population: A single‐center experience in mainland China , 2009, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[25]  W. Washburn,et al.  Impact of Recipient MELD Score on Resource Utilization , 2006, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[26]  J. Trotter,et al.  MELD scores of liver transplant recipients according to size of waiting list: impact of organ allocation and patient outcomes. , 2004, JAMA.

[27]  U. Ghoshal,et al.  Predicting mortality in patients with cirrhosis of liver with application of neural network technology , 2003, Journal of gastroenterology and hepatology.

[28]  P. Lapuerta,et al.  Neural networks as predictors of outcomes in alcoholic patients with severe liver disease , 1997, Hepatology.

[29]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[30]  J. Emond,et al.  Survival Outcomes Following Liver Transplantation (SOFT) Score: A Novel Method to Predict Patient Survival Following Liver Transplantation , 2008, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[31]  R. Freeman.  Predicting the future? , 2007, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[32]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[33]  J. Kalbfleisch,et al.  Survival Benefit‐Based Deceased‐Donor Liver Allocation , 2009, American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons.

[34]  T. Starzl,et al.  Liver transplantation for hepatocellular carcinoma: a proposal of a prognostic scoring system. , 2000, Journal of the American College of Surgeons.

[35]  Q. Ye,et al.  A decade’s studies on metastasis of hepatocellular carcinoma , 2004, Journal of Cancer Research and Clinical Oncology.

[36]  F. Piscaglia,et al.  Assessment of donor steatosis in liver transplantation: is it possible without liver biopsy? , 2009, Clinical transplantation.

[37]  Alexander Gimson,et al.  Systematic review and validation of prognostic models in liver transplantation , 2005, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[38]  S. Biggins.  Beyond the numbers: Rational and ethical application of outcome models for organ allocation in liver transplantation , 2007, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[39]  J. Lewsey,et al.  Developing a Prognostic Model for 90-day Mortality After Liver Transplantation Based on Pretransplant Recipient Factors , 2006, Transplantation.

[40]  E. Hill.  With the WHO in China , 1948 .

[41]  Rajasvaran Logeswaran,et al.  Cholangiocarcinoma—An Automated Preliminary Detection System Using MLP , 2009, Journal of Medical Systems.

[42]  H. Yoo,et al.  A model to predict survival at one month, one year, and five years after liver transplantation based on pretransplant clinical characteristics , 2003, Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society.

[43]  Bert A. Mobley,et al.  Predictions of coronary artery stenosis by artificial neural network , 2000, Artif. Intell. Medicine.