Switzerland Launches National AI Initiative for Personalized Cancer Care
A new national initiative led by the EPFL AI Center integrates artificial intelligence into cancer care. NAIPO (National AI Initiative for Precision Oncology) was recently awarded Innosuisse Flagship funding and aims to develop a secure, federated infrastructure to enable AI-enhanced precision oncology across Switzerland while ensuring sensitive and personal health data remains protected.
According to the Global Cancer Observatory, cancer remains one of the country’s most pressing public health challenges, with nearly 58,000 new cases and close to 20,000 deaths recorded in 2022. Despite Switzerland’s advanced healthcare system, truly personalized care remains difficult to achieve, in part due to fragmented data and lack of integration across institutions. The cost of such treatments continues to rise, there is a growing need for care that is not only more effective, but also fairer in terms of access and better aligned with patients’ values and needs. Meeting this challenge requires closer coordination among all stakeholders in the Swiss healthcare landscape to ensure that each patient receives timely, tailored, and equitable care; regardless of where they are treated.
Led by the EPFL AI Center, NAIPO responds to this need with an integrated, AI-powered precision oncology platform that aims to transform cancer care delivery. By deploying advanced AI models at every stage of the patient journey, the initiative seeks to optimize diagnostics, personalize treatments, and streamline clinical decision-making. “The approach builds on lessons from previous healthcare projects, emphasizing the development of novel, clinically informed AI tools through the seamless integration of a common data platform, continuous adaptation of robust models, and well-designed clinical interfaces and patient apps.” says Dorina Thanou, lead of the initiative at the EPFL AI Center.
NAIPO has been awarded Flagship Initiative funding by Innosuisse, the Swiss agency supporting innovation. Deployed over four years, with a large transdisciplinary team of Swiss leading institutions working on the research and implementation, NAIPO represents the biggest nation-wide effort of its kind. It is led by the EPFL AI center in collaboration with ETH AI Center, the Swiss Data Science Center (SDSC), the Universities of Applied Sciences and Arts of Northwestern Switzerland, the Bern University of Applied Sciences, the University Hospitals of Basel, Bern, Geneva, Zürich, regional and private clinics, Roche, SOPHIA GENETICS, Switch, and Tune Insight amongst the key players.
Pioneering Oncology research
From a research perspective, NAIPO pioneers a range of new approaches in AI for precision oncology. These include the development of AI agents to assist in clinical decision-making, large language models for mining clinical records, foundation models for analysis and prediction of treatment efficiency, and privacy-preserving algorithms for secure handling of sensitive patient data. AI predictions will be further supported by high-throughput experimental models and molecular data, leveraging patient avatars. “The combination of these technologies will allow us to capture and model the uniqueness of each patient” said Elisa Oricchio, director of the Swiss Institute of Experimental Cancer Research (ISREC) at EPFL. The program will redefine the role of AI in medicine and contribute to position Switzerland as a leader in medical AI innovation.
“The ability to tailor predictions and recommendations to individual patients is one of the most exciting aspects of NAIPO,” said Charlotte Bunne, professor at EPFL working on model development. “Our models will continuously learn from curated biomedical literature and clinical databases to remain at the forefront of scientific knowledge: identifying new targets, biomarkers, and investigational drugs. We also aim to generate novel AI-based biomarkers by analyzing tissue and blood samples with clinically validated models integrated into decision-support tools.”
Deployment and long term vision
The program’s roadmap foresees clinical pilots at cantonal hospitals and private clinics, leading to a national rollout within four years. In addition to advancing cancer care, the infrastructure is intended to serve as a model for future applications in other disease domains.
“This initiative marks a transition toward a proactive model for precision oncology,” said Olivier Michielin, Head of Precision Oncology at Geneva University Hospitals (HUG) and Clinical Coordinator of the project. “It reflects a commitment to ensuring that all patients, regardless of where they are treated within this network, benefit from the latest advances in AI-supported medicine.”
Ensuring secure, privacy-conscious collaboration across institutions is also central to the initiative. The infrastructure will rely on federated learning and modern data governance to enable collective intelligence without centralizing sensitive health data. “We’re building a secure and federated infrastructure that allows institutions to collaborate without compromising privacy,” said Nora Toussaint, lead of the initiative at the Swiss Data Science Center (SDSC). “Our goal is to make trust and transparency fundamental to the technical design.”
NAIPO’s long-term vision includes reducing disparities in access, accelerating the discovery of new biomarkers and treatments, and supporting sustainable innovation across the Swiss healthcare system. Milestones and key results will be shared as the project progresses.
