Total views : 259

Various Medical Aspects of Liver Transplantation and its Survival Prediction using Machine Learning Techniques

Affiliations

  • Manonmaniam Sundaranar University, Tirunelveli – 627012, Tamil Nadu, India
  • Computer Center, University of Kerala, Thiruvananthapuram – 695034, Kerala, India

Abstract


Objective: Prognosis models play a significant role in forecasting the patient's survival in Organ transplantation. To review the impact of machine learning methods in predicting the of survival of patients who undergoes Liver Transplantation using a Multilayer Perceptron Artificial Neural Network model with an extensive discussion of all the medical aspects is the key objective of this paper. Methods/Analysis: Medical practitioners studied various parameters during pretransplantation for predicting the survival of a patient. This study considered those parameters and reviewed whether these parameters have any vital part in the survival rate of a patient after Liver Transplantation (LT). This study also compared various scores including Model for End Stage Liver Disease (MELD) score, Emory score and Child score that are used in survival prediction. Currently the medicinal specialists estimate the outcome of LT with MELD score. We employed a detailed learning about the health aspects of LT and various machine learning techniques used in this area. In order to perform the experimentation, the dataset was congregated from the United Network for Organ Sharing transplant database (n = 65534). With the three layer architecture, the model trains the attributes of donors, recipient and transplantation using back propagation algorithm. 10-fold cross validation was applied in each training and test set before training. During the training process, the appropriate donor-recipient pairs were found out and obtained the best liver patient survival in transplantation. Findings: We conducted a comprehensive study about LT for the liver patient survival prediction. We proposed a Multilayer Perceptron Artificial Neural Network model to predict the survival rate after LT with 99.74% accuracy using United Network Organ Sharing registry. We also compared the performance of proposed model with existing models and proved that proposed model produced more accuracy than other models. Novelty/Improvement: The multilayer perceptron model succeeded clinical scores in terms of high accuracy, sensitivity and specificity. Machine learning techniques show better performance than conservative numerical methods in donor, recipient and transplantation attributes which are used to predict the survival. Due to less expensive and producing reliable solutions with rich datasets, machine learning techniques have been succeeded the conventional statistical methods and medical scoring systems. The proposed model predicts a promising accuracy for the prediction of best survival rates after.

Keywords

Artificial Neural Networks, Liver Transplantation, Machine Learning, Multilayer Perceptron, Post-Liver Transplantation Survival Prediction.

Full Text:

 |  (PDF views: 126)

References


  • Azzam A. History and evolution of LT. INTECH Open Access Publisher; 2012 Feb 15. p.1–17.
  • Schaubel DE, Sima CS, Goodrich NP, Feng S, Merion RM. The survival benefit of deceased donor LT as a function of candidate disease severity and donor quality. American Journal of Transplantation. 2008 Feb 1; 8(2):419–25. Crossref
  • Schaubel DE, Guidinger MK, Biggins SW, Kalbfleisch JD, Pomfret EA, Sharma P, Merion RM. Survival benefit-based deceased-donor liver allocation. American Journal of Transplantation. 2009 Apr 1; 9(42):970–81. Crossref
  • Kamath PS, Wiesner RH, Malinchoc M, Kremers W, Therneau TM, Kosberg CL, D'Amico G, Dickson ER, Kim W. A model to predict survival in patients with end-stage liver disease. Hepatology. 2001 Feb 1; 33(2):464–70. Crossref
  • Waljee AK, Higgins PD. Machine learning in medicine: a primer for physicians. The American Journal of Gastroenterology. 2010 Jun 1; 105(6):1224–6. Crossref
  • Laker MF. Liver function tests. BMJ. 1990 Aug 4; 301(6746):250–1. Crossref
  • Chouker A, Martignoni A, Dugas M, Eisenmenger W, Schauer R, Kaufmann I, Schelling G, Löhe F, Jauch KW, Peter K, Thiel M. Estimation of liver size for LT: the impact of age and gender. Liver Transplantation. 2004 May 1; 10(5):678–85.
  • Nair S, Vanatta JM, Arteh J, Eason JD. Effects of obesity, diabetes, and prior abdominal surgery on resource utilization in LT: a single-center study. Liver Transplantation. 2009 Nov 1; 15(11):1519–24.
  • Chalasani N, Clark WS, Martin LG, Kamean J, Khan MA, Patel NH, Boyer TD. Determinants of mortality in patients with advanced cirrhosis after transjugular intrahepatic portosystemic shunting. Gastroenterology. 2000 Jan 31; 118(1):138–44. Crossref
  • Astegiano M, Sapone N, Demarchi B, Rossetti S, Bonardi R, Rizzetto M. Laboratory evaluation of the patient with liver disease. European review for Medical and Pharmacological Sciences. 2004; 8(1):3–10.
  • Sallie R, Michael Tredger J, Williams R. Drugs and the liver Part 1: testing liver function. Biopharmaceutics and Drug Disposition. 1991 May 1; 12(4):251–9. Crossref
  • Markmann JF, Markmann JW, Markmann DA, Bacquerizo A, Singer J, Holt CD, Gornbein J, Yersiz H, Morrissey M, Lerner SM, McDiarmid SV. Preoperative factors associated with outcome and their impact on resource use in 1148 consecutive primary liver transplants. Transplantation. 2001 Sep 27; 72(6):1113–22. Crossref
  • Brölsch CE, Stevens LH, Whitington PF. The use of reducedsize liver transplants in children, including split livers and living related liver transplants. European Journal of Pediatric Surgery. 1991 Jun; 1(3):166–71.
  • Strong RW. Living-donor LT: an overview. Journal of HepatoBiliary-Pancreatic Surgery. 2006 Sep 1; 13(5):370–7. Crossref
  • Strong RW, Lynch SV, Ong TH, Matsunami H, Koido Y, Balderson GA. Successful LT from a living donor to her son. New England Journal of Medicine. 1990 May 24; 322(21):1505–7. Crossref
  • Busuttil RW, Goss JA. Split LT. Annals of surgery. 1999 Mar; 229(3):1–313.
  • de Boer MT, Molenaar IQ, Hendriks HG, Slooff MJ, Porte RJ. Minimizing blood loss in LT: progress through research and evolution of techniques. Digestive surgery. 2005 Oct; 22(4):265–75. Crossref
  • Parikh MC, Maradia KG. Comparative analysis of motion base image segmentation using machine learning techniques. Indian Journal of Science and Technology. 2016 Mar; 9(9):1–9.
  • Jeon H, Lee SG. Living donor LT. Current Opinion in Organ Transplantation. 2010 Jun 1; 15(3):283–7. Crossref
  • Marcos A. Right lobe living donor LT: a review. Liver Transplantation. 2000 Jan 1; 6(1):3–20.
  • Thuluvath PJ, Yoo HY. Graft and patient survival after adult live donor LT compared to a matched cohort who received a deceased donor transplantation. Liver Transplantation. 2004 Oct 1; 10(10):1263–8.
  • Dreiseitl S, Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. Journal of Biomedical Informatics. 2002 Oct 31; 35(5):352–9. Crossref
  • Freise CE, Gillespie BW, Koffron AJ, Lok AS, Pruett TL, Emond JC, Fair JH, Fisher RA, Olthoff KM, Trotter JF, Ghobrial RM. Recipient morbidity after living and deceased donor LT: findings from the A2ALL retrospective cohort study. American Journal of Transplantation. 2008 Dec 1; 8(12):2569–79. Crossref
  • Todo S, Furukawa H, Japanese Study Group on Organ Transplantation. Living donor LT for adult patients with hepatocellular carcinoma: experience in Japan. Annals of surgery. 2004 Sep 1; 240(3):451–61.
  • Busuttil RW, Tanaka K. The utility of marginal donors in LT. Liver Transplantation. 2003 Jul 1; 9(7):651–63.
  • Mor E, Klintmalm GB, Gibbs JF, Watemberg I, Goldstein RM, Husberg BS. The use of marginal donors for LTA retrospective study of 365 liver donors 1, 2. Transplantation. 1992 Feb 1; 53(2):383–6. Crossref
  • Busquets J, Xiol X, Figueras J, Jaurrieta E, Torras J, Ramos E, Rafecas A, Fabregat J, Lama C, Iba-ez L, Llado L. The impact of donor age on LT: influence of donor age on early liver function and on subsequent patient and graft survival. Transplantation. 2001 Jun 27; 71(12):1765–71. Crossref
  • Raji CG, Vinod Chandra SS. Artificial neural networks in prediction of patient survival after LT. Journal Health and Medical Informatics. 2016 Feb 5; 215:1–2.
  • Lai JC, Feng S, Roberts JP, Terrault NA. Gender differences in liver donor quality are predictive of graft loss. American Journal of Transplantation. 2011 Feb 1; 11(2):296–302. Crossref
  • Rustgi VK, Marino G, Halpern MT, Johnson LB, Umana WO, Tolleris C. Role of gender and race mismatch and graft failure in patients undergoing LT. Liver Transplantation. 2002 Jun 1; 8(6):514–8.
  • Burra P, Martin ED, Gitto S, Villa E. Influence of age and gender before and after LT. Liver Transplantation. 2013 Feb 1; 19(2):122–34.
  • Feng S, Goodrich NP, Bragg-Gresham JL, Dykstra DM, Punch JD, DebRoy MA, Greenstein SM, Merion RM. Characteristics associated with liver graft failure: the concept of a donor risk index. American Journal of Transplantation. 2006 Apr 1; 6(4):783–90. Crossref
  • Gordon RD, Iwatsuki S, Esquivel CO, Tzakis A, Todo S, Starzl TE. LT across ABO blood groups. Surgery. 1986 Aug 1; 100(2):342–8.
  • Calle EE, Thun MJ, Petrelli JM, Rodriguez C, Heath Jr CW. Body-mass index and mortality in a prospective cohort of US adults. New England Journal of Medicine. 1999 Oct 7; 341(15):1097–105. Crossref
  • Pelletier SJ, Schaubel DE, Wei G, Englesbe MJ, Punch JD, Wolfe RA, Port FK, Merion RM. Effect of body mass index on the survival benefit of LT. Liver Transplantation. 2007 Dec 1; 13(12):1678–83.
  • Nair S, Verma S, Thuluvath PJ. Obesity and its effect on survival in patients undergoing orthotopic LT in the United States. Hepatology. 2002 Jan 1; 35(1):105–9. Crossref
  • Pi-Sunyer FX. NHLBI obesity education initiative expert panel on the identification, evaluation, and treatment of overweight and obesity in adults-The evidence report. Obesity Research. 1998 Sep 1; 6:51–209.
  • Reuben A. Long-term management of the liver transplant patient: diabetes, hyperlipidemia, and obesity. Liver Transplantation. 2001 Nov 1; 7(11):13–21.
  • Rodriguez RA, Mendelson M, O'Hare AM, Hsu LC, Schoenfeld P. Determinants of survival among HIV-infected chronic dialysis patients. Journal of the American Society of Nephrology. 2003 May 1; 14(5):1307–13. Crossref
  • Schaeffer DF, Yoshida EM, Buczkowski AK, Chung SW, Steinbrecher UP, Erb SE, Scudamore CH. Surgical morbidity in severely obese liver transplant recipients–a single Canadian centre experience. Ann Hepatol. 2009 Jan 1; 8(1):38–40.
  • Dare A, Jiang Y, Harrison B, Gane E, Orr D, Phillips A, Plank L, Bartlett A. The additive effect of pre-transplant obesity, diabetes and cardiovascular risk factors on outcome after LT: a 10-year national experience. Intransplant International. 2014; 20(1):281–90.
  • Murakami T, Mochizuki K, Nakamura H. Imaging evaluation of the cirrhotic liver. InSeminars in liver disease. 2001 May; 21(2):213–24.
  • Llovet JM, Schwartz M, Mazzaferro V. Resection and LT for hepatocellular carcinoma. InSeminars in liver disease. 2004 Dec; 25(2):181–200.
  • Mazzaferro V, Llovet JM, Miceli R, Bhoori S, Schiavo M, Mariani L, Camerini T, Roayaie S, Schwartz ME, Grazi GL, Adam R. Predicting survival after LT in patients with hepatocellular carcinoma beyond the Milan criteria: a retrospective, exploratory analysis. The LANCET oncology. 2009 Jan 31; 10(1):35–43. Crossref
  • Schepke M, Roth F, Fimmers R, Brensing KA, Sudhop T, Schild HH, Sauerbruch T. Comparison of MELD, ChildPugh, and Emory model for the prediction of survival in patients undergoing transjugular intrahepatic portosystemic shunting. The American Journal of Gastroenterology.
  • ; 98(5):1167–74. Crossref
  • Durand F, Valla D. Assessment of the prognosis of cirrhosis: Child–Pugh versus MELD. Journal of Hepatology. 2005 Apr 30; 42(1):S100–7. Crossref
  • Testa G, Malago M, Broelsch CE. Living-donor LT in adults. Langenbeck's Archives of Surgery. 1999 Dec 1; 384(6):536– 43. Crossref
  • Bak T, Wachs M, Trotter J, Everson G, Trouillot T, Kugelmas M, Steinberg T, Kam I. Adult-to-adult living donor LT using right-lobe grafts: Results and lessons learned from a single-center experience. Liver Transplantation. 2001 Aug 1; 7(8):680–6.
  • Tector AJ, Mangus RS, Chestovich P, Vianna R, Fridell JA, Milgrom ML, Sanders C, Kwo PY. Use of extended criteria livers decreases wait time for LT without adversely impacting post transplant survival. Annals of surgery. 2006 Sep 1; 244(3):439–50.
  • Selzner M, Clavien PA. Fatty liver in LT and surgery. InSeminars in liver disease 2000 Dec; 21(1):105–13.
  • Durand F, Renz JF, Alkofer B, Burra P, Clavien PA, Porte RJ, Freeman RB, Belghiti J. Report of the Paris consensus meeting on expanded criteria donors in LT. Liver Transplantation. 2008 Dec 1; 14(12):1694–707.
  • Lee S, Park K, Hwang S, Lee Y, Choi D, Kim K, Koh K, Han S, Choi K, Hwang K, Makuuchi M. Congestion of right liver graft in living donor LT. Transplantation. 2001 Mar 27; 71(6):812–4.
  • Kiuchi T, Kasahara M, Uryuhara K, Inomata Y, Uemoto S, Asonuma K, Egawa H, Fujita S, Hayashi M, Tanaka K. Impact of graft size mismatching on graft prognosis in LT from living donors1, 2. Transplantation. 1999 Jan 27; 67(2):321–7. Crossref
  • Lo CM, Fan ST, Liu CL, Chan JK, Lam BK, Lau GK, Wei WI, Wong J. Minimum graft size for successful living donor LT. Transplantation. 1999 Oct 27; 68(8):1112–6. Crossref
  • Gridelli B, Remuzzi G. Strategies for making more organs available for transplantation. New England Journal of Medicine. 2000 Aug 10; 343(6):404–10. Crossref
  • Moreno R, Berenguer M. Post-LT medical complications. Ann Hepatol. 2006 Apr; 5(2):77–85.
  • Motschman TL, Taswell HF, Brecher ME, Rakela J, Grambsch PM, Larson-Keller JJ, Rettke SR, Krom RA. Intraoperative blood loss and patient and graft survival in orthotopic LT: their relationship to clinical and laboratory data. In Mayo Clinic proceedings. 1989 Mar 31; 64(3):346– 55. Crossref
  • Deschênes M, Belle SH, Krom RA, Zetterman RK, Lake JR. Early allograft dysfunction after LT: a definition and predictors of outcome1. Transplantation. 1998 Aug 15; 66(3):302– 10. Crossref
  • Navasa M, Bustamante J, Marroni C, González E, Andreu H, Esmatjes E, García-Valdecasas JC, Grande L, Cirera I, Rimola A, Rodés J. Diabetes mellitus after LT: prevalence and predictive factors. Journal of Hepatology. 1996 Jul 31; 25(1):64–71. Crossref
  • Demetris AJ. Central venulitis in liver allografts: considerations of differential diagnosis. Hepatology. 2001 May 1; 33(5):1329–30. Crossref
  • Correia IM, Rego LO, Lima AS. Post-liver transplant obesity and diabetes. Current Opinion in Clinical Nutrition and Metabolic Care. 2003 Jul 1; 6(4):457–60. Crossref, Crossref
  • Moser MA, Wall WJ. Management of biliary problems after LT. Liver Transplantation. 2001 Nov 1; 7(11B):13–21.
  • Song AT, Avelino-Silva VI, Pecora RA, Pugliese V, D'Albuquerque LA, Abdala E. LT: fifty years of experience. World Journal of Gastroenterology (WJG). 2014 May 14; 20(18):5363. Crossref
  • Jain A, Reyes J, Kashyap R, Dodson SF, Demetris AJ, Ruppert K, Abu-Elmagd K, Marsh W, Madariaga J, Mazariegos G, Geller D. Long-term survival after LT in 4,000 consecutive patients at a single center. Annals of surgery. 2000 Oct 1; 232(4):490–500. Crossref
  • Calne RY, Rolles K, Thiru S, McMaster P, Craddock GN, Aziz S, White DJ, Evans DB, Dunn DC, Henderson RG, Lewis P. Cyclosporin a initially as the only immunosup pressant in 34 recipients of cadaveric organs: 32 kidneys, 2 pancreases, and 2 livers. The LANCET. 1979 Nov 17; 314(8151):1033–6. Crossref
  • Yao FY, Ferrell L, Bass NM, Watson JJ, Bacchetti P, Venook A, Ascher NL, Roberts JP. LT for hepatocellular carcinoma: expansion of the tumor size limits does not adversely impact survival. Hepatology. 2001 Jun 1; 33(6):1394–403. Crossref
  • Kiuchi T, Kasahara M, Uryuhara K, Inomata Y, Uemoto S, Asonuma K, Egawa H, Fujita S, Hayashi M, Tanaka K. Impact of graft size mismatching on graft prognosis in LT from living donors1, 2. Transplantation. 1999 Jan 27; 67(2):321–7. Crossref
  • Fawcett T. An introduction to ROC analysis. Pattern Recognition Letters. 2006 Jun 30; 27(8):861–74. Crossref
  • Cruz-Ramírez M, Hervás-Martínez C, Fernandez JC, Briceno J, De La Mata M. Predicting patient survival after LT using evolutionary multi-objective artificial neural networks. Artificial Intelligence in Medicine. 2013 May 31; 58(1):37–49. Crossref
  • Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge university press; 2000 Mar 23.
  • Godara S, Singh R. Evaluation of predictive machine learning techniques as expert systems in medical diagnosis. Indian Journal of Science and Technology. 2016 Mar; 9(10):1–4.
  • Rizwan JM, Krishnan PN, Karthikeyan R, Kumar SR. Multi layer perception type artificial neural network based traffic control. Indian Journal of Science and Technology. 2016 Feb; 9(5):1–6. Crossref
  • Ohno-Machado L. Modeling medical prognosis: survival analysis techniques. Journal of Biomedical Informatics. 2001 Dec 31; 34(6):428–39. Crossref
  • Doyle HR, Marino IR, Jabbour N, Zetti G, McMichael J, Mitchell S, Fung J, Starzl TE. Early death or retransplantation in adults after orthotopic LT: can outcome be predicted? 1. Transplantation. 1994 Apr 15; 57(7):1028. Crossref
  • Doyle HR, Marino IR, Jabbour N, Zetti G, McMichael J, Mitchell S, Fung J, Starzl TE. Early death or retransplantation in adults after orthotopic LT: can outcome be predicted? 1. Transplantation. 1994 Apr 15; 57(7):1028. Crossref
  • Matis S, Doyle H, Marino I, Mural R, Uberbacher E. Use of neural networks for prediction of graft failure following LT. In the Proceedings of the Eighth Institute of Electrical and Electronics Engineers (IEEE) Symposium on ComputerBased Medical Systems, USA; 1995 Jun 9. p. 133–40.
  • Parmanto B, Doyle HR. Recurrent neural networks for predicting outcomes after LT: representing temporal sequence of clinical observations. Methods Archive. 2001; 40(5):386– 91.
  • Cucchetti A, Vivarelli M, Heaton ND, Phillips S, Piscaglia F, Bolondi L, La Barba G, Foxton MR, Rela M, O'Grady J, Pinna AD. Artificial neural network is superior to MELD in predicting mortality of patients with end-stage liver disease. Gut. 2007 Feb 1; 56(2):253–8. Crossref
  • Marsh JW, Dvorchik I, Subotin M, Balan V, Rakela J, Popechitelev EP, Subbotin V, Casavilla A, Carr BI, Fung JJ, Iwatsuki S. The prediction of risk of recurrence and time to recurrence of hepatocellular carcinoma after orthotopic LT: a pilot study. Hepatology. 1997 Aug 1; 26(2):444–50. Crossref
  • Rajanayagam J, Frank E, Shepherd RW, Lewindon PJ. Artificial neural network is highly predictive of outcome in paediatric acute liver failure. Pediatric Transplantation. 2013 Sep 1; 17(6):535–42. Crossref
  • Raji CG, Chandra SSV. Graft survival prediction in LT using artificial neural network models. Journal of Computational Science. 2016 Sep; 30(16):72–8. Crossref
  • Raji CG, Chandra SSV. Predicting the survival of graft following LT using a nonlinear model. Journal of Public Health. 2016 Oct 1; 24(5):443–52. Crossref
  • Raji CG, Chandra SSV. Long-term forecasting the survival in LT using multilayer perceptron networks. Institute of Electrical and Electronics Engineers (IEEE) Transactions on Systems, Man, and Cybernetics: Systems. 2017 Feb 22; PP(99):1–12. Crossref
  • Raji CG, Chandra SSV. Prediction and survival analysis of patients after LT using RBF networks. In the International Conference on Data Mining and Big Data, Springer International Publishing; 2016 Jun 25. p.147–55.
  • VinodChandra S.S, Girijadevi R, Nair AS, Pillai SS, Pillai RM. MTar: a computational micro RNA target prediction architecture for human transcriptome. BMC Bioinformatics. 2010 Jan 18; 11(S1):s1–S2.
  • Yao FY, Ferrell L, Bass NM, Watson JJ, Bacchetti P, Venook A, Ascher NL, Roberts JP. LT for hepatocellular carcinoma: expansion of the tumor size limits does not adversely impact survival. Hepatology. 2001 Jun 1; 33(6):1394–403. Crossref
  • Yersiz H, Renz JF, Hisatake G, Reichert PR, Feduska NJ, Lerner S, Farmer DG, Ghobrial RM, Geevarghese S, Baquerizo A, Chen P. Technical and logistical considerations of in situ split-LT for two adults: part II, creation of left segment I-IV and right segment V-VIII grafts. Liver Transplantation. 2002 Jan 1; 8(1):78–81.
  • Zhang M, Yin F, Chen B, Li YP, Yan LN, Wen TF, Li B. Pre-transplant prediction of post-transplant survival for liver recipients with benign end-stage liver diseases: a nonlinear model. PLOS one. 2012 Mar 1; 7(3):31256. Crossref
  • Iba-ez V, Pareja E, Serrano AJ, Vila JJ, Perez S, Martin JD, Sanjuan F, Lopez R, Mir J. Predicting early transplant failure: neural network versus logistic regression. Open Transplantation Journal. 2009 May 18; 3:14–21. Crossref
  • Khosravi B, Pourahmad S, Bahreini A, Nikeghbalian S, Mehrdad G. Five years survival of patients after LT and its effective factors by neural network and Cox poroportional hazard regression models. Hepatitis monthly. 2015 Sep; 15(9):e2516. Crossref

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.