Imagine trying to find a key that fits a lock, but the lock changes every time. This project looks at skin, lung, and bladder cancers to find the common patterns in how the body's immune system reacts to tumors. By using AI to spot these patterns, doctors can predict which patients will actually benefit from a specific drug before starting treatment.
Oncology treatments often fail because doctors cannot predict which patients will respond to immunotherapy. This leads to wasted medical resources and patients receiving ineffective, toxic treatments.
The project is building AI-based predictors for treatment response and privacy-preserving synthetic datasets based on multi-omics and clinical data from three cancer types.
If you are a drug discovery firm dealing with high failure rates in clinical trials — this project developed validated biomarkers and predictive models that boost drug discovery by identifying which patient profiles respond to therapy.
If you are an AI diagnostics developer dealing with a lack of high-quality training data — this project developed privacy-preserving synthetic datasets and AI-based predictors for treatment response across 3 major cancer types.
If you are a specialized oncology clinic dealing with unpredictable patient relapses — this project developed decision-support models that enable earlier relapse detection and reduce unnecessary treatments.
Based on available project data, no pricing or cost structures have been disclosed as the project is currently in the research and development phase.
The project specifically compiles data from skin, lung, and bladder cancer to identify critical elements of tumor-host interaction. Based on available project data, the current models are validated for these three types.
Based on available project data, the project focuses on generating a resource of harmonized data and validated biomarkers, but specific licensing terms are not provided.
The project generates privacy-preserving synthetic datasets and ensures all data is handled in compliance with legal and ethics frameworks.
The project period runs from 2024-01-01 to 2027-12-31, with an outreach plan involving regulators to support prompt uptake into health systems.
The consortium is research-heavy with 9 universities and 4 research institutes, but maintains a strategic industrial presence with 3 companies (18% ratio), including 3 SMEs. This balance suggests a strong focus on scientific discovery (multi-omics and AI) with a built-in pathway for commercial translation through the SME partners.
Contact the Institut National de la Santé et de la Recherche Médicale (INSERM) in France.
Contact us to connect with the MULTIR consortium for early access to synthetic datasets.
