Predicting outcome on admission and post-admission for acetaminophen-induced acute liver failure using classification and regression tree models
Jaime Lynn Speiser, William M Lee, Constantine J Karvellas, US Acute Liver Failure Study Group, William M Lee, Anne M Larson, Iris Liou, Timothy Davern, Oren Fix, Michael Schilsky, Timothy McCashland, J Eileen Hay, Natalie Murray, A Obaid S Shaikh, Andres Blei, Daniel Ganger, Atif Zaman, Steven H B Han, Robert Fontana, Brendan McGuire, Raymond T Chung, Alastair Smith, Robert Brown, Jeffrey Crippin, Edwin Harrison, Adrian Reuben, Santiago Munoz, Rajender Reddy, R Todd Stravitz, Lorenzo Rossaro, Raj Satyanarayana, Tarek Hassanein, James Hanje, Jody Olson, Ram Subramanian, Constantine J Karvellas, Grace Samuel, Ezmina Lalani, Carla Pezzia, Corron Sanders, Nahid Attar, Linda S Hynan, Valerie Durkalski, Wenle Zhao, Jaime Speiser, Catherine Dillon, Holly Battenhouse, Michelle Gottfried, Jaime Lynn Speiser, William M Lee, Constantine J Karvellas, US Acute Liver Failure Study Group, William M Lee, Anne M Larson, Iris Liou, Timothy Davern, Oren Fix, Michael Schilsky, Timothy McCashland, J Eileen Hay, Natalie Murray, A Obaid S Shaikh, Andres Blei, Daniel Ganger, Atif Zaman, Steven H B Han, Robert Fontana, Brendan McGuire, Raymond T Chung, Alastair Smith, Robert Brown, Jeffrey Crippin, Edwin Harrison, Adrian Reuben, Santiago Munoz, Rajender Reddy, R Todd Stravitz, Lorenzo Rossaro, Raj Satyanarayana, Tarek Hassanein, James Hanje, Jody Olson, Ram Subramanian, Constantine J Karvellas, Grace Samuel, Ezmina Lalani, Carla Pezzia, Corron Sanders, Nahid Attar, Linda S Hynan, Valerie Durkalski, Wenle Zhao, Jaime Speiser, Catherine Dillon, Holly Battenhouse, Michelle Gottfried
Abstract
Background/aim: Assessing prognosis for acetaminophen-induced acute liver failure (APAP-ALF) patients often presents significant challenges. King's College (KCC) has been validated on hospital admission, but little has been published on later phases of illness. We aimed to improve determinations of prognosis both at the time of and following admission for APAP-ALF using Classification and Regression Tree (CART) models.
Methods: CART models were applied to US ALFSG registry data to predict 21-day death or liver transplant early (on admission) and post-admission (days 3-7) for 803 APAP-ALF patients enrolled 01/1998-09/2013. Accuracy in prediction of outcome (AC), sensitivity (SN), specificity (SP), and area under receiver-operating curve (AUROC) were compared between 3 models: KCC (INR, creatinine, coma grade, pH), CART analysis using only KCC variables (KCC-CART) and a CART model using new variables (NEW-CART).
Results: Traditional KCC yielded 69% AC, 90% SP, 27% SN, and 0.58 AUROC on admission, with similar performance post-admission. KCC-CART at admission offered predictive 66% AC, 65% SP, 67% SN, and 0.74 AUROC. Post-admission, KCC-CART had predictive 82% AC, 86% SP, 46% SN and 0.81 AUROC. NEW-CART models using MELD (Model for end stage liver disease), lactate and mechanical ventilation on admission yielded predictive 72% AC, 71% SP, 77% SN and AUROC 0.79. For later stages, NEW-CART (MELD, lactate, coma grade) offered predictive AC 86%, SP 91%, SN 46%, AUROC 0.73.
Conclusion: CARTs offer simple prognostic models for APAP-ALF patients, which have higher AUROC and SN than KCC, with similar AC and negligibly worse SP. Admission and post-admission predictions were developed.
Key points: • Prognostication in acetaminophen-induced acute liver failure (APAP-ALF) is challenging beyond admission • Little has been published regarding the use of King's College Criteria (KCC) beyond admission and KCC has shown limited sensitivity in subsequent studies • Classification and Regression Tree (CART) methodology allows the development of predictive models using binary splits and offers an intuitive method for predicting outcome, using processes familiar to clinicians • Data from the ALFSG registry suggested that CART prognosis models for the APAP population offer improved sensitivity and model performance over traditional regression-based KCC, while maintaining similar accuracy and negligibly worse specificity • KCC-CART models offered modest improvement over traditional KCC, with NEW-CART models performing better than KCC-CART particularly at late time points.
Trial registration: ClinicalTrials.gov NCT00518440.
Conflict of interest statement
Competing Interests: The authors have declared that no competing interests exist.
Figures
References
- Fagan E, Wannan G. Reducing paracetamol overdoses. BMJ. 1996;313(7070):1417–8. .
- Larson AM, Polson J, Fontana RJ, Davern TJ, Lalani E, Hynan LS, et al. Acetaminophen-induced acute liver failure: results of a United States multicenter, prospective study. Hepatology. 2005;42(6):1364–72. .
- Karvellas CJ, Safinia N, Auzinger G, Heaton N, Muiesan P, O'Grady J, et al. Medical and psychiatric outcomes for patients transplanted for acetaminophen-induced acute liver failure: a case-control study. Liver international: official journal of the International Association for the Study of the Liver. 2010;30(6):826–33. 10.1111/j.1478-3231.2010.02243.x .
- Bernal W, Auzinger G, Dhawan A, Wendon J. Acute liver failure. Lancet. 2010;376(9736):190–201. Epub 2010/07/20. 10.1016/S0140-6736(10)60274-7 .
- Reddy KR, Schilsky M, Stravitz RT, Eberle C, Durkalski V, Fontana RJ, et al. Liver transplantation for Acute Liver Failure: Results from the NIH Acute Liver Failure Study Group. Hepatology. 2012;56(4(Suppl)):246A.
- Simpson KJ, Bates CM, Henderson NC, Wigmore SJ, Garden OJ, Lee A, et al. The utilization of liver transplantation in the management of acute liver failure: comparison between acetaminophen and non-acetaminophen etiologies. Liver Transpl. 2009;15(6):600–9. 10.1002/lt.21681 .
- Stravitz RT, Kramer AH, Davern T, Shaikh AO, Caldwell SH, Mehta RL, et al. Intensive care of patients with acute liver failure: recommendations of the U.S. Acute Liver Failure Study Group. Critical care medicine. 2007;35(11):2498–508. Epub 2007/09/29. 10.1097/01.CCM.0000287592.94554.5F .
- Antoniades CG, Berry PA, Wendon JA, Vergani D. The importance of immune dysfunction in determining outcome in acute liver failure. J Hepatol. 2008;49(5):845–61. Epub 2008/09/20. 10.1016/j.jhep.2008.08.009 .
- O'Grady JG, Alexander GJ, Hayllar KM, Williams R. Early indicators of prognosis in fulminant hepatic failure. Gastroenterology. 1989;97(2):439–45. Epub 1989/08/01. .
- Bernuau J. [Fulminant and subfulminant viral hepatitis]. Rev Prat. 1990;40(18):1652–5. Epub 1990/06/21. .
- Pauwels A, Mostefa-Kara N, Florent C, Levy VG. Emergency liver transplantation for acute liver failure. Evaluation of London and Clichy criteria. J Hepatol. 1993;17(1):124–7. .
- Schmidt LE, Dalhoff K. Serum phosphate is an early predictor of outcome in severe acetaminophen-induced hepatotoxicity. Hepatology. 2002;36(3):659–65. 10.1053/jhep.2002.35069 .
- Schmidt LE, Larsen FS. MELD score as a predictor of liver failure and death in patients with acetaminophen-induced liver injury. Hepatology. 2007;45(3):789–96. 10.1002/hep.21503 .
- Bernal W, Donaldson N, Wyncoll D, Wendon J. Blood lactate as an early predictor of outcome in paracetamol-induced acute liver failure: a cohort study. Lancet. 2002;359(9306):558–63. 10.1016/S0140-6736(02)07743-7 .
- Shakil AO, Kramer D, Mazariegos GV, Fung JJ, Rakela J. Acute liver failure: clinical features, outcome analysis, and applicability of prognostic criteria. Liver Transpl. 2000;6(2):163–9. 10.1002/lt.500060218 .
- Gordon L, Olshen RA. Tree-structured survival analysis. Cancer treatment reports. 1985;69(10):1065–9. .
- Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees Monterrey, CA, USA: Wadsworth and Brooks; 1984.
- Garzotto M, Beer TM, Hudson RG, Peters L, Hsieh YC, Barrera E, et al. Improved detection of prostate cancer using classification and regression tree analysis. Journal of clinical oncology: official journal of the American Society of Clinical Oncology. 2005;23(19):4322–9. 10.1200/JCO.2005.11.136 .
- Aguiar FS, Almeida LL, Ruffino-Netto A, Kritski AL, Mello FC, Werneck GL. Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients. BMC pulmonary medicine. 2012;12:40 10.1186/1471-2466-12-40
- O'Grady JG, Schalm SW, Williams R. Acute liver failure: redefining the syndromes. Lancet. 1993;342(8866):273–5. .
- Atterbury CE, Maddrey WC, Conn HO. Neomycin-sorbitol and lactulose in the treatment of acute portal-systemic encephalopathy. A controlled, double-blind clinical trial. Am J Dig Dis. 1978;23(5):398–406. Epub 1978/05/01. .
- Kamath PS, Wiesner RH, Malinchoc M, Kremers W, Therneau TM, Kosberg CL, et al. A model to predict survival in patients with end-stage liver disease. Hepatology. 2001;33(2):464–70. 10.1053/jhep.2001.22172 .
- Hubbard AE, Ahern J, Fleischer NL, Van der Laan M, Lippman SA, Jewell N, et al. To GEE or not to GEE: comparing population average and mixed models for estimating the associations between neighborhood risk factors and health. Epidemiology. 2010;21(4):467–74. 10.1097/EDE.0b013e3181caeb90
- Team. RDC, editor R: a language and environment for statistical computing.2008; Vienna, Austria.
- Therneau TM, Atkinson EJ. An introduction to recursive partitioning using the Rpart routines Mayo Foundation [Internet] 1997.
- Sing T, Sander O, Beernwinkel N, Lengauer T. ROCR: visualizing classifier performance in R. Bioinformatics. 2005;21(20).
- Clemmesen JO, Larsen FS, Kondrup J, al. e. Cerebral herniation in patients with acute liver failure is correlated with arterial ammonia concentration. Hepatology. 1999;29:648–53.
- Audimoolam VK, McPhail MJW, Wendon JA, Willars C, Bernal W, Desai SR, et al. Lung Injury and Its Prognostic Significance in Acute Liver Failure. Critical care medicine. 2014;42(3):592–600. 10.1097/01.ccm.0000435666.15070.d5
- Nakayama N, Oketani M, Kawamura Y, Inao M, Nagoshi S, Fujiwara K, et al. Algorithm to determine the outcome of patients with acute liver failure: a data-mining analysis using decision trees. Journal of gastroenterology. 2012;47(6):664–77. 10.1007/s00535-012-0529-8
- Koch DG, Battenhouse H, Durkalski V, Lee WM, Reuben A. Clinical predictor of spontaneous survival in acute liver failure patients with advanced coma. Hepatology. 2012;56(4(Suppl)):965A.
Source: PubMed