Moderate evidence
Published recordHealthGood Space
More
Multimodal multitask deep learning for predicting tertiary lymphoid structures and peritoneal recurrence in gastric cancer: a multicentre development, validation, and testing study
- Truvace record
- TRV-2026-3079raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Controlled or validated comparison
- Sources
- 1 sourcePeer-reviewed
- sha256
- 5b7c7d8849d6…check it
Peritoneal recurrence remains a common and fatal complication following curative gastric cancer surgery. Tertiary lymphoid structures are crucial indicators of immune response in cancer, and their maturation is associated with better prognosis and therapy outcomes. Evaluation of these structures could improve patient stratification for treatment of cancer but is hindered by the invasive and biased nature of histological methods. This study aimed to explore a non-invasive radiological method of assessment in pati…
The gain
In a retrospective study of eight Chinese gastric cancer cohorts, the CTransNet model split patients by risk: in the training cohort, 5-year peritoneal recurrence was 66.69% with low scores versus 26.28% with high scores.
What this doesn’t fix
The model was developed and tested on retrospective data from Chinese hospitals only, and its concordance index for predicting peritoneal recurrence-free survival was a modest 0.654 in the training cohort.
Sources
1 on file- The Lancet Digital Healthdoi:10.1016/j.landig.2026.101075
Cite this record
v1Truvace Impact Record TRV-2026-3079, v1: “Multimodal multitask deep learning for predicting tertiary lymphoid structures and peritoneal recurrence in gastric cancer: a multicentre development, validation, and testing study.” Truvace, 2026-11-20. /record/TRV-2026-3079 (accessed on the day you copy it). sha256 5b7c7d8849d6be2a…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-3079 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace