AI Science Tracker
EN

Department of Critical Care Medicine, Beijing Youan Hospital, Capital Medical University, China

1 discovery from 2024

Discoveries

A new prediction model for acute kidney injury following liver transplantation using grafts from donors after cardiac death.

Source check: Source checked. Not independent scientific confirmation.

Finding: A gradient-boosting model for acute kidney injury after liver transplantation using donation-after-circulatory-death grafts achieved AUC 0.75 in a later temporal cohort of 195 recipients. The retrospective, single-center evaluation had no external validation.

Technology: A gradient-boosting model used clinical features to predict acute kidney injury after liver transplantation with DCD grafts.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
The learned model estimated post-transplant AKI risk and was evaluated in a later cohort from the same center.
Test and result
In the later temporal cohort, the model reported AUC 0.75 (95% CI 0.67–0.81), F1 0.72, sensitivity 0.73 and specificity 0.63.
Limitation / still unknown
Retrospective single-center study: 894 recipients in model development and a later 195-recipient cohort from the same hospital. No external validation was reported.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11169688/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary full-text Methods and Results in Europe PMC/PMC and publisher publication record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.