1
|
Verma N, Choudhury A, Singh V, Duseja A, Al-Mahtab M, Devarbhavi H, Eapen CE, Goel A, Ning Q, Duan Z, Hamid S, Jafri W, Butt AS, Shukla A, Tan SS, Kim DJ, Hu J, Sood A, Goel O, Midha V, Ghaznian H, Sahu MK, Lee GH, Treeprasertsuk S, Shah S, Lesmana LA, Lesmana RC, Prasad VGM, Sarin SK. APASL-ACLF Research Consortium-Artificial Intelligence (AARC-AI) model precisely predicts outcomes in acute-on-chronic liver failure patients. Liver Int 2023; 43:442-451. [PMID: 35797245 DOI: 10.1111/liv.15361] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/11/2022] [Revised: 06/13/2022] [Accepted: 07/05/2022] [Indexed: 01/25/2023]
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.
Collapse
Affiliation(s)
- Nipun Verma
- Department of Hepatology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Ashok Choudhury
- Department of Hepatology, Institute of Liver and Biliary Sciences, New Delhi, India
| | - Virendra Singh
- Department of Hepatology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Ajay Duseja
- Department of Hepatology, Postgraduate Institute of Medical Education and Research, Chandigarh, India
| | - Manum Al-Mahtab
- Department of Hepatology, Bangabandhu Sheikh Mujib Medical University, Dhaka, Bangladesh
| | | | | | - Ashish Goel
- Department of Hepatology, CMC, Vellore, India
| | - Qin Ning
- Institute and Department of Infectious Disease, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Zhongping Duan
- Translational Hepatology Institute Capital Medical University, Beijing You'an Hospital, Beijing, China
| | - Saeed Hamid
- Department of Medicine, Aga Khan University Hospital, Karachi, Pakistan
| | - Wasim Jafri
- Department of Medicine, Aga Khan University Hospital, Karachi, Pakistan
| | - Amna Shubhan Butt
- Department of Medicine, Aga Khan University Hospital, Karachi, Pakistan
| | - Akash Shukla
- Department of Gastroenterology, Lokmanya Tilak Municipal General Hospital, and Lokmanya Tilak Municipal Medical College, Mumbai, India
| | - Soek-Siam Tan
- Department of Medicine, Hospital Selayang, Selangor, Malaysia
| | - Dong Joon Kim
- Department of Internal Medicine, Hallym University College of Medicine, Seoul, South Korea
| | - Jinhua Hu
- Department of Medicine, 302 Military Hospital, Beijing, China
| | - Ajit Sood
- Department of Gastroenterology, DMC, Ludhiana, India
| | - Omesh Goel
- Department of Gastroenterology, DMC, Ludhiana, India
| | - Vandana Midha
- Department of Gastroenterology, DMC, Ludhiana, India
| | - Hashmik Ghaznian
- Department of Hepatology, Nork Clinical Hospital of Infectious Disease, Yerevan, Armenia
| | - Manoj Kumar Sahu
- Department of Gastroenterology and Hepatology Sciences, IMS & SUM Hospital, Bhubaneswar, India
| | - Guan Huei Lee
- Division of Gastroenterology and Hepatology, Department of Medicine, National University Health System, Singapore, Singapore
| | | | | | | | - Rinaldi C Lesmana
- Digestive Disease and GI Oncology Centre, Medistra Hospital, Jakarta, Indonesia
| | | | - Shiv K Sarin
- Department of Hepatology, Institute of Liver and Biliary Sciences, New Delhi, India
| | -
- Department of Hepatology, Institute of Liver and Biliary Sciences, New Delhi, India
| |
Collapse
|