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

Verma N 1 , Choudhury A 2 , Singh V 1 , Duseja A 1 , Al-Mahtab M 3 , Devarbhavi H 4 Show all authors , Eapen CE 5 , Goel A 5 , Ning Q 6 , Duan Z 7 , Hamid S 8 , Jafri W 8 , Butt AS 8 , Shukla A 9 , Tan SS 10 , Kim DJ 11 , Hu J 12 , Sood A 13 , Goel O 13 , Midha V 13 , Ghaznian H 14 , Sahu MK 15 , Lee GH 16 , Treeprasertsuk S 17 , Shah S 18 , Lesmana LA 19 , Lesmana RC 19 , Prasad VGM 20 , Sarin SK 2 , APASL ACLF Research Consortium (AARC) for APASL ACLF Working Party 2

Affiliations 

  • 1 Department of Hepatology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
  • 2 Department of Hepatology, Institute of Liver and Biliary Sciences, New Delhi, India
  • 3 Department of Hepatology, Bangabandhu Sheikh Mujib Medical University, Dhaka, Bangladesh
  • 4 Department of Hepatology, St John Medical College, Bangalore, India
  • 5 Department of Hepatology, CMC, Vellore, India
  • 6 Institute and Department of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
  • 7 Translational Hepatology Institute Capital Medical University, Beijing You'an Hospital, Beijing, China
  • 8 Department of Medicine, Aga Khan University Hospital, Karachi, Pakistan
  • 9 Department of Gastroenterology, Lokmanya Tilak Municipal General Hospital, and Lokmanya Tilak Municipal Medical College, Mumbai, India
  • 10 Department of Medicine, Hospital Selayang, Selangor, Malaysia
  • 11 Department of Internal Medicine, Hallym University College of Medicine, Seoul, South Korea
  • 12 Department of Medicine, 302 Military Hospital, Beijing, China
  • 13 Department of Gastroenterology, DMC, Ludhiana, India
  • 14 Department of Hepatology, Nork Clinical Hospital of Infectious Disease, Yerevan, Armenia
  • 15 Department of Gastroenterology and Hepatology Sciences, IMS & SUM Hospital, Bhubaneswar, India
  • 16 Division of Gastroenterology and Hepatology, Department of Medicine, National University Health System, Singapore, Singapore
  • 17 Department of Medicine, Chulalongkorn University, Bangkok, Thailand
  • 18 Global Hospitals, Mumbai, India
  • 19 Digestive Disease and GI Oncology Centre, Medistra Hospital, Jakarta, Indonesia
  • 20 Department of Gastroenterology, VGM Hospital, Coimbatore, India
Liver Int, 2023 Feb;43(2):442-451.
PMID: 35797245 DOI: 10.1111/liv.15361

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 

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.

Similar publications