Comparative accuracy of prognostic models for short-term mortality in acute-on-chronic liver failure patients: CAP-ACLF

Verma, Nipun; Dhiman, Radha K.; Singh, Virendra; Duseja, Ajay; Taneja, Sunil; Choudhury, Ashok; Sharma, Manoj Kumar; Eapen, C E; Devarbhavi, Harshad; Mahtab, Mamun Al; Shukla, Akash; Salehiniya, Hamid; Jafri, Wasim; Butt, Amna; Ning, Qin; Chen, Tao; Tan, Soek Siam; Lesmana, Laurentius A.; Lesmana, Cosmas Rinaldi Adithya; Sahu, Manoj Kumar; Hu, Jinhua; Lee, Guan Huei; Sood, Ajit; Midha, Vandana; Ghazinian, Hasmik; Kim, Dong Joon; Treeprasertsuk, Sombat; Prasad, V G Mohan; Dokmeci, A. Kadir; Sollano, José D.; Shah, Samir; Payawal, Diana A.; Rao, Padaki Nagaraja; Kulkarni, Anand V.; Lau, George; Duan, Zhongping; Chen, Yu; Yokosuka, Osamu; Abbas, Zaigham; Karim, Fazal; Chowdhury, Debashish; Prasad, Ananta Shrestha; Sarin, Shiv Kumar

doi:10.1007/s12072-021-10175-w

Cited by 16 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We identified that creatinine, coagulopathy, circulatory failure and leucocytosis at day 7 and sepsis at day 4 were the top‐most important predictors of 30‐day mortality in ACLF patients. These correspond to our recent findings where the day‐7 AARC model was better than conventional models in ACLF patients 7,8 . SIRS and sepsis have been previously reported as independent predictors of mortality in ACLF 3 .…”

Section: Discussionsupporting

confidence: 92%

“…In this study, we could demonstrate better discrimination and accuracy of predictions with ML models than the existing standard AARC model/MELD score and those reported in the literature. 7,8,11,35 The better performance of models in our study could be related to a higher number of patients n = 2481 vs. n = 255 in Garcia et al, 11 robust feature selection methods (Boruta vs. mutual information) and refinement with model tuning. Further, model interpretation was made in our study, which was not described in other studies.…”

Section: Sensitivity Analysismentioning

confidence: 68%

“…Although APASL-ACLF Research Consortium (AARC) model is a valid tool for outcome predictions, 7,8 about 20%-30% of ACLF outcomes are poorly predicted with this model. 7,8 Also other models lack the specificity of predictions in APASL-ACLF patients. 7,8 Hence, a need for precision in outcome predictions persists in these patients.Artificial intelligence (AI) is gaining considerable momentum in healthcare, and machine learning (ML), a field in AI, is concerned with developing models or algorithms to interpret complex/large data.…”

mentioning

confidence: 99%

See 2 more Smart Citations

APASL‐ACLF Research Consortium–Artificial Intelligence (AARC‐AI) model precisely predicts outcomes in acute‐on‐chronic liver failure patients

Verma,

Choudhury,

Singh

et al. 2022

Liver International

Self Cite

View full text Add to dashboard Cite

Acute insults on underlying chronic liver disease (CLD) result in systemic inflammation, perturbed homeostasis, multiorgan dysfunctions and high mortality in acute-on-chronic liver failure (ACLF) patients. [1][2][3] Although multiple definitions exist for this syndrome, 4 a common denominator includes high short-term mortality. 2,5 The Asia Pacific Association for the Study of the Liver (APASL) defines ACLF in CLD patients without prior decompensation as an acute hepatic insult resulting in jaundice, coagulopathy, ascites or encephalopathy within 4 weeks. 2 This constitutes around 25% of all incident-ACLFs among hospitalized cirrhosis in the USA. 6 The syndrome is dynamic with a reversible component where patients may recover or improve from this syndrome and may not require definite treatment. 2 On the flip side, the definite treatment, that is liver transplantation, is limited by resources, organ availability and expertise. 2 Thus, it is pertinent to predict the outcomes precisely, which will help stratify patients for an appropriate level of care, communicate prognosis and guide the allocation of resources. Although APASL-ACLF Research Consortium (AARC) model is a valid tool for outcome predictions, 7,8 about 20%-30% of ACLF outcomes are poorly predicted with this model. 7,8 Also other models lack the specificity of predictions in APASL-ACLF patients. 7,8 Hence, a need for precision in outcome predictions persists in these patients.Artificial intelligence (AI) is gaining considerable momentum in healthcare, and machine learning (ML), a field in AI, is concerned with developing models or algorithms to interpret complex/large data. The applications of AI in gastroenterology and hepatology are increasingly recognized. 9,10 Recently, an ML model-extreme gradient boosting (XGB) was demonstrated to perform better than logistic regression to predict mortality in ACLF patients from Europe. 11

show abstract

Section: Discussionsupporting

confidence: 92%

Section: Sensitivity Analysismentioning

confidence: 68%

mentioning

confidence: 99%

See 1 more Smart Citation

APASL‐ACLF Research Consortium–Artificial Intelligence (AARC‐AI) model precisely predicts outcomes in acute‐on‐chronic liver failure patients

Verma,

Choudhury,

Singh

et al. 2022

Liver International

Self Cite

View full text Add to dashboard Cite

show abstract

“…Prognosis is more accurately estimated when the scores are applied at 3 to 7 days than at time of diagnosis [25,28]. These findings are in keeping with the dynamic nature of ACLF.…”

Section: Prognostic Stratificationsupporting

confidence: 71%

“…These findings are in keeping with the dynamic nature of ACLF. Prognostic scores have also been applied to determine futility of treatments in ACLF patients [28,29]. Thus, it is necessary to overcome the above-mentioned limitations by creating models based only on objective, verifiable and continuous variables [16].…”

Section: Prognostic Stratificationmentioning

confidence: 99%

Acute-on-Chronic Liver Failure in Cirrhosis

Gambino

Piano

Angeli

2021

JCM

View full text Add to dashboard Cite

Acute-on-chronic liver failure (ACLF) is a syndrome that develops in patients with acutely decompensated chronic liver disease. It is characterised by high 28-day mortality, the presence of one or more organ failures (OFs) and a variable but severe grade of systemic inflammation. Despite the peculiarity of each one, every definition proposed for ACLF recognizes it as a proper clinical entity. In this paper, we provide an overview of the diagnostic criteria proposed by the different scientific societies and the clinical characteristics of the syndrome. Established and experimental treatments are also described. Among the former, the most relevant are directed to support organ failures, treat precipitating factors and carry out early assessment for liver transplantation (LT). Further studies are needed to better clarify pathophysiology of the syndrome and discover new therapies.

show abstract