If you are a drug developer dealing with high clinical trial failure rates — this project developed AI models validated on 2,200 patients that can better identify which patients will actually respond to immunotherapy. This allows for more precise patient stratification and higher success rates in trials.
AI Decision Support Platform for Personalized Lung Cancer Immunotherapy Treatment
Imagine trying to find the right key for a lock, but the lock keeps changing shape. Current lung cancer tests are like using one simple key for everyone, which only works for about half the patients. This project builds a smart digital brain that looks at a patient's entire biological map and medical images to predict exactly which treatment will work for them.
What needed solving
Current lung cancer immunotherapy only works for 30-50% of patients because the single biomarker used (PD-L1) is insufficient. This leads to wasted healthcare spending and patients receiving toxic treatments that do not work.
What was built
A secure data-sharing platform and three AI-based decision-support devices, including the Individual Patient Decision Aid System (IPDAS).
Who needs this
Who can put this to work
If you are a software provider dealing with the lack of integrated diagnostic tools — this project developed the Individual Patient Decision Aid System (IPDAS) that gives patients personalized info on treatment options. This can be integrated into existing e-Health portals to improve patient engagement.
If you are a clinic dealing with the high cost of ineffective treatments — this project developed a decision-support system that reduces the economic burden by preventing undue toxicity and unnecessary drug use. It uses multi-omics data from 200 patients to guide therapeutic decisions.
Quick answers
What is the cost or pricing model for this AI platform?
Based on available project data, no specific pricing or commercial cost model is mentioned; the project was funded with an EU contribution of EUR 9,996,695.
Can this be scaled to an industrial level?
Yes, the project has already established a secure data-sharing platform that is fully operational and has processed data from over 2,200 patients across 10 countries.
Who owns the IP and how is licensing handled?
Based on available project data, specific IP and licensing terms are not detailed, though the consortium includes 5 industry partners and 2 SMEs.
How does this integrate into existing hospital workflows?
The project uses a secure data-sharing and elaboration system that supports radiomics segmentation and standardized multi-omics pipelines for harmonization across centers.
What is the timeline for market availability?
The project period runs from 2022-06-01 to 2027-05-31, with predictive models built between 2023 and 2024 currently undergoing validation.
Who built it
The consortium is well-balanced for commercialization, featuring a 31% industry ratio with 5 industry partners, including 2 SMEs. The collaboration spans 10 countries, combining the academic rigor of 5 universities and 3 research institutes with the practical application capabilities of industrial partners, coordinated by a major Italian cancer institute.
Contact Fondazione IRCCS Istituto Nazionale dei Tumori in Italy
Talk to the team behind this work.
Contact us to explore licensing opportunities for the IPDAS decision-support system.