HomeScienceAI Model Predicts Liver Metastasis Ris
SCIENCE

AI Model Predicts Liver Metastasis Risk in Gastric Cancer

Researchers built a multimodal system combining CT scans, tumor slides, and clinical data to forecast post-surgery liver metastasis in gastric cancer patients.

WHAT YOU NEED TO KNOW
  • The Radiopathomics-Clinical Stratification Assessment model posted area under the curve metrics between 0.862 and 0.909 across testing cohorts.
  • The system combines preoperative CT radiomics, hematoxylin and eosin tumor slide pathomics, and standard clinical markers.
  • Testing groups included internal, external, public, and prospective clinical trial cohorts under identifier NCT02555358.

Researchers created an interpretable diagnostic model named the Radiopathomics-Clinical Stratification Assessment to predict postoperative liver metastasis in patients with locally advanced gastric cancer, Nature Communications reported. The system, known as RCSA, identifies patients at risk of relapsing months after an apparently curative operation, addressing a diagnostic gap left by standard tumor staging.

Ping’an Ding and Jiaxuan Yang co-led the study, which combines three streams of routine patient data. The tool integrates radiomic features extracted from preoperative computed tomography scans, pathomic features derived from routine hematoxylin and eosin tumor slides, and conventional clinical markers. The team trained RCSA on records from a single medical center before testing it across separate internal, external, public, and prospective trial cohorts, including prospective trial NCT02555358.

Testing across the validation cohorts yielded area under the receiver operating characteristic curve values between 0.862 and 0.909 when separating high-risk patients from low-risk individuals. The researchers noted that tumors labeled low-risk possessed a markedly more active immune environment. This biological distinction indicates that low-risk patients are the subgroup most likely to gain a survival benefit from additional immunotherapy.

Contributors to the project included researchers from the Fourth Hospital of Hebei Medical University, Sichuan University, Ant Group’s Ant Healthcare unit, and regional medical facilities across Hebei, Hubei, and Jiangsu provinces. The work received backing from several regional and national initiatives, including the National Natural Science Foundation of China and the Hebei Natural Science Foundation.

Xentir Media
Xentir Media NewsroomSource-backed AI and technology coverage, drafted by Xentir's automated editorial system under fixed human-set rules. See our editorial policy and AI usage policy.
J
Jomon · Founder & EditorFounder and editor of Xentir Media. Sets the editorial rules the newsroom system runs under, and is accountable for its corrections. About Jomon · [email protected]
The Xentir Brief
The developments worth knowing — one useful email.
Get the Brief →