TURIN, Italy: Reply [EXM, STAR: REY] and the European Institute of Oncology (IEO) have launched a collaboration focused on the co-development and training of domain-specific Large Language Models for oncology. The initiative brings together Reply’s expertise in building frontier generative models grounded in enterprise knowledge with the IEO’s clinical expertise and data assets to develop models tailored to highly complex oncology settings.

As a first step, the IEO’s clinical teams and Information Systems department are working with a multidisciplinary Reply team with deep expertise in healthcare and LLM specialisation to define and prioritise the use cases that will guide development, while also mapping the available data assets to identify the datasets best suited to support model training.

The initial areas of focus are breast oncology, urologic oncology and prevention, selected to assess their clinical relevance and evaluate their technical feasibility. Clinical reports, diagnostic images, structured data and other relevant clinical information in these areas are being analysed in terms of type, volume, quality and accessibility. This will help define datasets aligned with the selected use cases and inform the next stages of development.

Building on this work, the programme will move into a phase focused on training Large Language Models on the selected use cases, followed by the development and deployment of the resulting solutions in clinical settings to support prevention, diagnosis and treatment.

The project is one of the first initiatives developed within Reply Model Factory, Reply’s industrial platform for building frontier generative models grounded in enterprise knowledge and designed to power AI systems and agents aligned with each organisation’s operating context. Within this framework, use case definition, data source qualification, dataset preparation and model training form part of an integrated process designed to ensure full control over data, processes and outcomes.

“At the IEO, artificial intelligence is not simply a technology; it is a valuable ally to medicine,” said Annarosa Farina, Director of Information Systems, IEO Monzino Group. “It helps accelerate research, diagnosis and treatment by enabling us to interpret the complexity of cancer through the analysis of large volumes of clinical and scientific data. This can lead to faster decisions, more personalised therapies and new opportunities for patient care.”

“As Generative AI becomes increasingly integrated into decision-making and operational processes, real value will come from models built on each organisation’s own knowledge, data and expertise. Our collaboration with IEO is designed to bring these elements together and create the conditions for training domain-specific Large Language Models capable of supporting concrete application scenarios,” said Carlo Malgieri, Partner at Laife Reply.

Reply

Reply [EXM, STAR: REY, ISIN: IT0005282865] specialises in the design and implementation of solutions based on new communication channels and digital media. As a network of highly specialised companies, Reply supports major industrial groups in the telecom and media; industry and services; banking and insurance and public sectors in defining and developing business models enabled by the new paradigms of AI, cloud computing, digital media and the internet of things. Reply's services include: consulting, system integration and digital services. www.reply.com

IEO - Istituto Europeo di Oncologia

The European Institute of Oncology (IEO) is a Scientific Institute for Research, Hospitalisation and Healthcare (IRCCS) and an internationally recognised centre of excellence in oncology. The Institute has developed an innovative model of care built on core principles such as patient centrality, the full integration of research and clinical practice, early diagnosis and prevention. This is further strengthened by a data-driven strategy that enables the rapid development of artificial intelligence algorithms to accelerate diagnosis and improve the efficiency of treatment pathways. www.ieo.it

Fonte: Business Wire