AI Science Tracker
EN

Affiliated Dongyang Hospital

1 discovery from 2026

Discoveries

MAML-residual transformer for few-shot prediction of targeted therapy response in NSCLC.

Source check: Source checked. Not independent scientific confirmation.

Finding: The MAML-RT radiomics model predicted targeted-therapy response in NSCLC with accuracy 0.91 and AUC 0.93 in 300 patients; under a 50-case few-shot setting, AUC was 0.76. In an independent external validation cohort, AUC was 0.85 and accuracy 0.88. These are retrospective model evaluations, not evidence of improved treatment outcomes.

Technology: The MAML-RT framework combines model-agnostic meta-learning and residual transformers to predict targeted-therapy response from NSCLC radiomics in few-shot cohorts.

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

AI contribution
The MAML-RT framework combines model-agnostic meta-learning and residual transformers to predict targeted-therapy response from NSCLC radiomics in few-shot cohorts.
Test and result
MAML-RT combines model-agnostic meta-learning and residual transformers to predict targeted-therapy response from radiomics in NSCLC. It achieved AUC 0.93 in a 300-patient cohort, AUC 0.76 with 50 cases, and AUC 0.85 in an independent external cohort.
Limitation / still unknown
Independent replication and prospective real-world benefit are not established in the reviewed study.
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/PMC13468891/

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 3/5 · 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.