Improving Clinical Outcomes in Cancer Care
AI Predicts Cancer Metastasis with 80% Accuracy
Researchers at the University of Geneva develop MangroveGS to estimate tumor spread and prevent overtreatment.

A digital visualization of a gene-expression analysis overlaying a medical scan, representing the MangroveGS AI model's ability to predict cancer spread.
Photo: Avantgarde News
Researchers at the University of Geneva (UNIGE) developed an AI tool called MangroveGS to predict the risk of cancer metastasis [1][2]. The model analyzes gene-expression signatures to estimate how likely a tumor is to spread to other organs [1]. This development was recently published in the journal Cell Reports [1][2]. The model demonstrates nearly 80% accuracy in predicting metastasis and recurrence specifically for colon cancer [1][2]. Beyond colon cancer, researchers found the tool shows significant promise for evaluating stomach, lung, and breast cancers [1][3]. MangroveGS aims to assist clinicians in personalizing treatments for patients [2]. By identifying low-risk individuals, the tool could potentially prevent unnecessary and heavy treatments, such as chemotherapy, for those unlikely to experience recurrence [1][3].
Editorial notes
Transparency note
Drafted with LLM; human-edited
- AI assisted
- Yes
- Human review
- Yes
- Last updated
Risk assessment
Reviewed for sourcing quality and editorial consistency.
Sources
- 1.↗
scitechdaily.com
https://scitechdaily.com/new-ai-model-predicts-cancer-spread-with-incredible-accuracy/
- 2.↗
unige.ch
https://www.unige.ch/medias/en/2026/une-ia-pour-predire-le-risque-de-metastases-des-cancers
- 3.↗
avisdexperts.ch
https://avisdexperts.ch/en/intervention/mangrove-gs-tool-anticipate-risk-metastasis
Related stories
View allTopics
About the author
Avantgarde News Desk covers improving clinical outcomes in cancer care and editorial analysis for Avantgarde News.


