MétaCan
Menu
Back to cohort
Record W4412851165 · doi:10.1016/j.ajt.2025.07.2270

The AI Agent in the Room: Informing Objective Decision Making at the Transplant Selection Committee

2025· article· en· W4412851165 on OpenAlexaff
Bima J. Hasjim, F.G. Lee, Tayyab S. Diwan, S. Raju, James A. Gross, A. Sidhu, Hirohito Ichii, Ramaswamy Krishnan, Muhammad Mamdani, Disha Sharma, Meghashyam Bhat

Bibliographic record

VenueAmerican Journal of Transplantation · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsYork UniversityUniversity of Toronto
Fundersnot available
KeywordsMedicineSelection (genetic algorithm)Intensive care medicineArtificial intelligenceComputer science

Abstract

fetched live from OpenAlex

Purpose: Transplantation is one of the few areas in medicine where the definitive treatment is rationed.Subjective decision-making pose challenges towards the transplant selection process.It has been proposed that large language models (LLMs) through autonomous artificial intelligent (AI) agents could provide objectivity in decision-making to solve complex problems.Thus, we examined the performance of a multidisciplinary selection committee of AI agents (AI-SC) as a proof-of-concept towards objectivity in the liver transplant (LT) selection process.Methods: This was a hybrid cohort study of adult (≥18-years-old) LT candidates between 2004-2023 from the Scientific Registry of Transplant Recipients (SRTR) database.Patients receiving LT were retrospectively analyzed and a hypothetical cohort of patients with standard absolute contraindications to LT were generated.The AI-SC's performance to 1) waitlist candidates if LT would offer a 6-month or 1-year survival benefit or 2) decline candidates if contraindications to LT were present or if LT would not offer a survival benefit were analyzed.The AI-SC consisted of four LLMs: transplant hepatologist, transplant surgeon, cardiologist, and social worker (Figure ).Cosine similarity index analysis identified the most prevalent variables used by each AI agent of the AI-SC in their decision making.Results: Of 8,412 patients, 83.6% were waitlisted and 16.4% had contraindications to LT.The AI-SC was able to accurately identify contraindications to LT (accuracy: 98.2%, 95%CI 97.9%-98.4%),predict 6-month (94.9%, 95%CI 94.4%-95.3%),and 1-year (92.0%, 95%CI 91.4%-92.6%)survival.HCC burden beyond Milan criteria was the most common reason for accepted patients who were declined (False Negative).Malignancy was the most common cause of death prior to 6-month (21.7%) or 1-year (28.5%) end points (False Positive).Each AI agent used different variables in their decision making and report generation, but indication for LT and recipient age were among the top 5 most important variables used by all members of the AI-SC.Conclusions: LLMs can be leveraged to simulate the LT-SC meetings and provide accurate, objective insights on patients who may or may not benefit from LT. Lessons learned from this study are a provocative step towards making the LT selection process more equitable and objective.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.016
metaresearch head score (Gemma)0.092
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Commentary · Consensus signal: none
Teacher disagreement score0.016
Threshold uncertainty score0.084

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0160.092
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0020.002
Scholarly communication0.0090.007
Open science0.0010.003
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0080.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.034
GPT teacher head0.400
Teacher spread0.366 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreCommentary

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations2
Published2025
Admission routes1
Has abstractno

Explore more

Same venueAmerican Journal of TransplantationSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207