APASL-ACLF Research Consortium-Artificial Intelligence (AARC-AI) model precisely predicts outcomes in acute-on-chronic liver failure patients.
cirrhosis
data science
machine learning
mortality
prognosis
Journal
Liver international : official journal of the International Association for the Study of the Liver
ISSN: 1478-3231
Titre abrégé: Liver Int
Pays: United States
ID NLM: 101160857
Informations de publication
Date de publication:
Feb 2023
Feb 2023
Historique:
revised:
13
06
2022
received:
11
01
2022
accepted:
05
07
2022
pubmed:
8
7
2022
medline:
25
1
2023
entrez:
7
7
2022
Statut:
ppublish
Résumé
We hypothesized that artificial intelligence (AI) models are more precise than standard models for predicting outcomes in acute-on-chronic liver failure (ACLF). We recruited ACLF patients between 2009 and 2020 from APASL-ACLF Research Consortium (AARC). Their clinical data, investigations and organ involvement were serially noted for 90-days and utilized for AI modelling. Data were split randomly into train and validation sets. Multiple AI models, MELD and AARC-Model, were created/optimized on train set. Outcome prediction abilities were evaluated on validation sets through area under the curve (AUC), accuracy, sensitivity, specificity and class precision. Among 2481 ACLF patients, 1501 in train set and 980 in validation set, the extreme gradient boost-cross-validated model (XGB-CV) demonstrated the highest AUC in train (0.999), validation (0.907) and overall sets (0.976) for predicting 30-day outcomes. The AUC and accuracy of the XGB-CV model (%Δ) were 7.0% and 6.9% higher than the standard day-7 AARC model (p < .001) and 12.8% and 10.6% higher than the day 7 MELD for 30-day predictions in validation set (p < .001). The XGB model had the highest AUC for 7- and 90-day predictions as well (p < .001). Day-7 creatinine, international normalized ratio (INR), circulatory failure, leucocyte count and day-4 sepsis were top features determining the 30-day outcomes. A simple decision tree incorporating creatinine, INR and circulatory failure was able to classify patients into high (~90%), intermediate (~60%) and low risk (~20%) of mortality. A web-based AARC-AI model was developed and validated twice with optimal performance for 30-day predictions. The performance of the AARC-AI model exceeds the standard models for outcome predictions in ACLF. An AI-based decision tree can reliably undertake severity-based stratification of patients for timely interventions.
Sections du résumé
BACKGROUND AND AIMS
OBJECTIVE
We hypothesized that artificial intelligence (AI) models are more precise than standard models for predicting outcomes in acute-on-chronic liver failure (ACLF).
METHODS
METHODS
We recruited ACLF patients between 2009 and 2020 from APASL-ACLF Research Consortium (AARC). Their clinical data, investigations and organ involvement were serially noted for 90-days and utilized for AI modelling. Data were split randomly into train and validation sets. Multiple AI models, MELD and AARC-Model, were created/optimized on train set. Outcome prediction abilities were evaluated on validation sets through area under the curve (AUC), accuracy, sensitivity, specificity and class precision.
RESULTS
RESULTS
Among 2481 ACLF patients, 1501 in train set and 980 in validation set, the extreme gradient boost-cross-validated model (XGB-CV) demonstrated the highest AUC in train (0.999), validation (0.907) and overall sets (0.976) for predicting 30-day outcomes. The AUC and accuracy of the XGB-CV model (%Δ) were 7.0% and 6.9% higher than the standard day-7 AARC model (p < .001) and 12.8% and 10.6% higher than the day 7 MELD for 30-day predictions in validation set (p < .001). The XGB model had the highest AUC for 7- and 90-day predictions as well (p < .001). Day-7 creatinine, international normalized ratio (INR), circulatory failure, leucocyte count and day-4 sepsis were top features determining the 30-day outcomes. A simple decision tree incorporating creatinine, INR and circulatory failure was able to classify patients into high (~90%), intermediate (~60%) and low risk (~20%) of mortality. A web-based AARC-AI model was developed and validated twice with optimal performance for 30-day predictions.
CONCLUSIONS
CONCLUSIONS
The performance of the AARC-AI model exceeds the standard models for outcome predictions in ACLF. An AI-based decision tree can reliably undertake severity-based stratification of patients for timely interventions.
Substances chimiques
Creatinine
AYI8EX34EU
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
442-451Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2022 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.
Références
Arroyo V, Angeli P, Moreau R, et al. The systemic inflammation hypothesis: towards a new paradigm of acute decompensation and multiorgan failure in cirrhosis. J Hepatol. 2021;74:670-685.
Sarin SK, Choudhury A, Sharma MK, et al. Acute-on-chronic liver failure: consensus recommendations of the Asian Pacific association for the study of the liver (APASL): an update. Hepatol Int. 2019;13:353-390.
Choudhury A, Kumar M, Sharma BC, et al. Systemic inflammatory response syndrome in acute-on-chronic liver failure: relevance of 'golden window': a prospective study. J Gastroenterol Hepatol. 2017;32:1989-1997.
Hernaez R, Solà E, Moreau R, Ginès P. Acute-on-chronic liver failure: an update. Gut. 2017;66:541-553.
Moreau R, Jalan R, Gines P, et al. Acute-on-chronic liver failure is a distinct syndrome that develops in patients with acute decompensation of cirrhosis. Gastroenterology. 2013;144:1426-1437. 1437.e1421-1429.
Mahmud N, Kaplan DE, Taddei TH, Goldberg DS. Incidence and mortality of acute-on-chronic liver failure using two definitions in patients with compensated cirrhosis. Hepatology. 2019;69:2150-2163.
Choudhury A, Jindal A, Maiwall R, et al. Liver failure determines the outcome in patients of acute-on-chronic liver failure (ACLF): comparison of APASL ACLF Research Consortium (AARC) and CLIF-SOFA models. Hepatol Int. 2017;11:461-471.
Verma N, Dhiman RK, Singh V, et al. Comparative accuracy of prognostic models for short-term mortality in acute-on-chronic liver failure patients: CAP-ACLF. Hepatol Int 2021;15:753-765.
Le Berre C, Sandborn WJ, Aridhi S, et al. Application of artificial intelligence to gastroenterology and hepatology. Gastroenterology. 2020;158:76-94.e72.
Ahn JC, Connell A, Simonetto DA, Hughes C, Shah VH. The application of artificial intelligence for the diagnosis and treatment of liver diseases. Hepatology. 2020;73:2546-2563.
Garcia MS, Agarwal B, Mookerjee RP, et al. An accurate data preparation approach for the prediction of mortality in ACLF patients using the CANONIC dataset. Annu Int Conf IEEE Eng Med Biol Soc. 2019;2019:1371-1377.
Gustot T, Fernandez J, Garcia E, et al. Clinical course of acute-on-chronic liver failure syndrome and effects on prognosis. Hepatology. 2015;62:243-252.
Norgeot B, Quer G, Beaulieu-Jones BK, et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat Med. 2020;26:1320-1324.
Luo W, Phung D, Tran T, et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J Med Internet Res. 2016;18:e323.
Kursa MB, Rudnicki WR. Feature Selection with the Boruta Package. 2010. 2010;36:13.
Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29:1189-1232. 1144.
Natekin A, Knoll A. Gradient boosting machines, a tutorial. Front Neurorobot. 2013;7:21.
Breiman L. Random forests. Machine Learning. 2001;45:5-32.
Drolz A, Horvatits T, Rutter K, et al. Lactate improves prediction of short-term mortality in critically ill patients with cirrhosis: a multinational study. Hepatology. 2019;69:258-269.
Rai B. Advanced deep learning with R: become an expert at designing, building, and improving advanced neural network models using R, 2019.
Zhang Z. Naïve Bayes classification in R. Ann Transl Med. 2016;4:241.
Wisniewski G, Francois Y. Fast large-margin learning for statistical machine translation. Int J Comput Linguist Appl. 2013;4:45.
Loh WY. Classification and Regression Trees. Vol 1. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery; 2011:14-23.
Bennett K. Support Vector Machines: Hype or Hallelujah? Vol 2. ACM SIGKDD Explorations Newsletter; 2000:1-13.
Seni G, Elder J. Ensemble methods in data mining: improving accuracy through combining predictions; 2010.
Feurer M, Hutter F. Hyperparameter optimization. Automated Machine Learning. Springer, Cham; 2019:3-33.
Lunardon N, Menardi G, Torelli N. ROSE: a package for binary imbalanced learning. R Journal. 2014;6:79-89.
Huang J, Ling CX. Using AUC and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng. 2005;17:299-310.
Lattice SD. Multivariate Data Visualization with R. Springer Science & Business Media; 2008.
Gevrey M, Dimopoulos I, Lek S. Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Model. 2003;160:249-264.
Wei P, Lu Z, Song J. Variable importance analysis: a comprehensive review. Reliab Eng Syst Saf. 2015;142:399-432.
Štrumbelj E, Kononenko I. Explaining prediction models and individual predictions with feature contributions. Knowl Inf Syst. 2014;41:647-665.
Chen T, Guestrin C. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery; 2016:785-794.
Moreau R, Clària J, Aguilar F, et al. Blood metabolomics uncovers inflammation-associated mitochondrial dysfunction as a potential mechanism underlying ACLF. J Hepatol. 2020;72:688-701.
Kanwal F, Taylor TJ, Kramer JR, et al. Development, validation, and evaluation of a simple machine learning model to predict cirrhosis mortality. JAMA Netw Open. 2020;3:e2023780.
Murray CJL, Ikuta KS, Sharara F, et al. Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis. The Lancet. 2022;399:629-655.
Davoodi R, Moradi MH. Mortality prediction in intensive care units (ICUs) using a deep rule-based fuzzy classifier. J Biomed Inform. 2018;79:48-59.
Van Vleck TT, Chan L, Coca SG, et al. Augmented intelligence with natural language processing applied to electronic health records for identifying patients with non-alcoholic fatty liver disease at risk for disease progression. Int J Med Inform. 2019;129:334-341.
Ibrahim JG, Chu H, Chen MH. Missing data in clinical studies: issues and methods. J Clin Oncol. 2012;30:3297-3303.