A radiomics-based machine learning model and SHAP for predicting spread through air spaces and its prognostic implications in stage I lung adenocarcinoma: a multicenter cohort study.
Source check: Source checked. Not independent scientific confirmation.
Finding: An elastic-net radiomics model selected from 15 machine-learning methods used preoperative CT tumor and peritumoral features to predict spread through air spaces in 609 stage-I lung-adenocarcinoma patients from three centers.
Technology: A multicentre radiomics model predicted spread through air spaces and prognosis in stage-I lung adenocarcinoma.
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- A multicentre radiomics model predicted spread through air spaces and prognosis in stage-I lung adenocarcinoma.
- Test and result
- Radiomics AUCs were 0.791 in training and 0.829/0.807 in two external tests; a combined clinical-imaging model reached 0.894 in one external set, while predicted or confirmed spread was associated with shorter progression-free survival. Prospective validation remains needed.
- Limitation / still unknown
- The reviewed source does not establish prospective benefit, broad external validity, or replication beyond the reported 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/PMC12482768/
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 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.