An observational study in Liver Cirrhosis, sponsored by University Health Network, Toronto. Active, not recruiting at 1 site in Canada. Open to participants aged 18 Years to 70 Years. Per ClinicalTrials.gov, last updated 2026-10-21.
Sponsored by University Health Network, Toronto · Observational
To examined the opportunity for Artificial Intelligence (AI) agents to evaluate transplant candidacy objectively at LT-SC, with a large language models (LLM) representing the expertise of each individual specialist (hepatologist, surgeon, anesthesiologist, psychiatrist and social worker) and coming up with a group consensus decision upon inter-agent communication using prompts GPT-4 in OpenAI (private version).
The study seeks to evaluate the feasibility and acceptability of integrating such AI agents into LT candidate assessments with a retrospective evaluation and validation of a multi-disciplinary selection committee of AI agents (AI-SC) at major transplant centers, including MeDanTa (India), King Saud bin Abdulaziz University (Saudi Arabia), King Abdullah International Medical Research Center (Saudi Arabia), National University Hospital (Singapore), UCSF Health (US), Vanderbilt University Medical Center (US), John Hopkins Hospital (US), Mayo Clinic (US), Royal Prince Alfred Hospital (AU), and University Health Network (UHN-CA).
1,668 studies on the registry are indexed under Liver Cirrhosis; 360 are open to participants now.
This study's planned enrollment of 1,000 is above the median of 152 across 605 observational studies indexed under Liver Cirrhosis.
Browse Liver Cirrhosis studies →University Health Network, Toronto is the lead sponsor of 1,432 studies on the registry; 292 are open to participants now.
Of its 17 completed or terminated interventional studies of FDA-regulated products, 3 (18%) have results posted.
Counted across the registry records on this site, refreshed daily.
patient with liver cirrhosis on evaluation for liver transplant
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
AI - Selection Committee
Other: evaluate the alignment between AI-SC recommendations and LT-SC decisions · Other: Multi AI-SC model
Human Liver Transplant Selection Committee
To validate the developed model, we invited other collaborating centers, including Vancouver Coastal Health (Canada), Mayo Clinic (US), John Hopkins Hospital (US), Royal Prince Alfred Hospital (AU), National University of Singapore (Singapore), UCSF Health (US), Vanderbilt University Medical Center (US), John Hopkins Hospital (US), MeDanTa (India), and Ministry of National Guard Health Affairs (Saudi Arabia) to perform a validation as an extension of data governance phase.
To evaluate the feasibility and acceptability of integrating such multi AI-SC(Selection Committee) agents into LT candidate assessments.
Concordance of AI-SC vs LT-SC review
· Our primary outcome will be any substantial change in the content, method, or result of the patient assessment between the AI-SC and conventional reports. We will calculate the percentage of concordance between the two, and the similarity of report generated by the human and the AI-SC will be evaluated using ROUGE score (Recall-Oriented Understudy for Gisting Evaluation), a quantitative metric that assesses textual similarity3.
Time frame: 3 months
Concordance between AI-SC vs LT-SC
Our primary outcome will be any substantial change in the content, method, or result of the patient assessment between the AI-SC and conventional reports. We will calculate the percentage of concordance between the two, and the similarity of report generated by the human and the AI-SC will be evaluated using ROUGE score (Recall-Oriented Understudy for Gisting Evaluation), a quantitative metric that assesses textual similarity3
Time frame: 3 months
Time of adjudication
• The secondary outcomes will be the safety of assessments in cases where substantial changes are made, time required for adjudications, frequency of decision changes between AI-SC and conventional LT-SC. We will also evaluate the consistency of the decision making across controversial variables, such as age, cardiovascular health, and frailty over time, to evaluate whether AI-SC can provide more objectivity in the decision-making.
Time frame: 3 months
Plan to share: No
No publications or documents are linked to this record.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is active, not recruiting, as verified in May 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
University Health Network, Toronto →