AI Science Tracker
EN

Heterogeneous graph neural network-based prediction of immune-related adverse events.

Department of Health Statistics · 29 Nov 2025 · medicine

Discovery

Heterogeneous graph neural network-based prediction of immune-related adverse events.

Source check: Source checked. Not independent scientific confirmation.

Finding: Methods use 2,576 patients from a clinical data platform to train a heterogeneous graph model; Results report irAE prediction and risk patterns. Retrospective discrimination supports the specified clinical prediction only.

Technology: The graph model predicts immune-related adverse events from EHR medication and patient features, with reported discrimination and treatment-stage risk patterns. The Methods specify the learned operation used for this case-specific result.

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

AI contribution
The graph model predicts immune-related adverse events from EHR medication and patient features, with reported discrimination and treatment-stage risk patterns. The Methods specify the learned operation used for this
Test and result
Methods use 2,576 patients from a clinical data platform to train a heterogeneous graph model; Results report irAE prediction and risk patterns. Retrospective discrimination supports the specified clinical prediction only
Limitation / still unknown
The source reports the cohort or measured dataset, comparison/reference and evaluation used for this specific result; conclusions remain limited to that design
Evidence sources and annotation context

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

Evidence sources: https://doi.org/10.1038/s41598-025-30266-0 · https://pubmed.ncbi.nlm.nih.gov/41315648/

Source checked · editorial details

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

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

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 2/5 · 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 in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.