APASL‐ACLF Research Consortium–Artificial Intelligence (AARC‐AI) model precisely predicts outcomes in acute‐on‐chronic liver failure patients. (11th October 2022)

• Record Type: Journal Article
• Authors: Verma, Nipun; Choudhury, Ashok; Singh, Virendra; Duseja, Ajay; Al‐Mahtab, Manum; Devarbhavi, Harshad; Eapen, Chundamannil E.; Goel, Ashish; Ning, Qin; Duan, Zhongping; Hamid, Saeed; Jafri, Wasim; Butt, Amna Shubhan; Shukla, Akash; Tan, Soek‐Siam; Kim, Dong Joon; Hu, Jinhua; Sood, Ajit; Goel, Omesh; Midha, Vandana; Ghaznian, Hashmik; Sahu, Manoj Kumar; Lee, Guan Huei; Treeprasertsuk, Sombat; Shah, Samir; Lesmana, Laurentius A.; Lesmana, Rinaldi C.; Prasad, V. G. Mohan; Sarin, Shiv K.
• Is Part Of: Liver international. Volume 43:Number 2(2023)
• Page Start: 442
• Page End: 451
• Publication Date: 2022-10-11
• Subjects: cirrhosis -- data science -- machine learning -- mortality -- prognosis; Liver -- Periodicals; Liver -- Diseases -- Periodicals; 616.362
• DOI: 10.1111/liv.15361
• Languages: English
• ISSNs: 1478-3223

Abstract

Abstract: Background and Aims: We hypothesized that artificial intelligence (AI) models are more precise than standard models for predicting outcomes in acute‐on‐chronic liver failure (ACLF). 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: 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: 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.