AI - empowered personalized cancer medicine | The University of Edinburgh

Edinburgh researchers in a pan-European consortium to develop user friendly Artificial Intelligence (AI) tools for cancer clinicians: November 2020

Clinical practice desperately needs tailored, targeted treatments for individual cancer patients. This is not easy to achieve, because every person has a unique variation of the human genome and even cancers of similar origin frequently display remarkable diversity at the molecular level.

Fortunately, years of intensive investigations have resulted in huge amounts of data on molecular signatures associated with different tumour types. Conclusions drawn from these data have enabled development of contemporary personalized medicine approaches that play an increasingly important role in the clinical management of cancer patients. However, processing and interpretation of the continuously accumulating information using current analytical tools is becoming more and more challenging, and it is very difficult to explore the full depth and breadth of the data being produced.

Many people believe that Artificial Intelligence (AI) approaches may significantly improve data analysis and decision making for human diseases, ultimately resulting in better and more personalised treatments being developed faster. Likewise, computer-aided diagnosis and treatment selection has potential to significantly reduce waiting times and improve both curative treatment of early disease and life-extending treatment of advanced disease. However, a key challenge is to connect all the dots: linking the latest clinical experience and molecular data in an accessible way for AI systems to find associations that researchers and clinicians can then test to develop more personalised options for patients.

To this end, investigators from the MRC Institute of Genetics & Molecular Medicine (Prof Ted Hupp, Dr Stefan Symeonides, both from the CRUK Edinburgh Centre), the University of Edinburgh School of Informatics (Dr Ajitha Rajan) and NHS Lothian (Dr Alexander Laird) joined a new multinational European effort to develop a personalized medicine system that can bring medical “AI-empowered knowledge” to the tips of the fingers of clinicians and clinical researchers. Prof David Harrison from the University of St Andrews formed an additional UK collaborator. The network is also led by Dr Javier Alfaro from the International Centre for Cancer Vaccine Science at the University Gdansk, (Poland) who have formed a strategic partnership with the University of Edinburgh through European Union Regional Development Funding.

The project titled “Knowledge At the Tip of Your fingers: Clinical Knowledge for Humanity” (KATY) aims to develop an AI-powered personalized medicine system built around two main components: a distributed knowledge graph that connects sources of medical knowledge, and a pool of “explainable predictors” that allow the AI to model patient outcomes. The system then relates that information to researchers and clinicians to help them see new options for patient treatment. The KATY system will be tested in clear cell renal cell carcinoma (ccRCC) - the most frequent subtype of renal (kidney) cancer accounting for ~80% of cases.

The KATY Project is funded by the European Union’s Horizon 2020 research and innovation programme (nearly EUR 8.5 million) and includes the following partners: University of Rome Tor Vergata, Italy (project coordinator); Alternative Energies and Atomic Energy Commission, France; FCiências.ID – Association for Research and Development in Sciences, Portugal; University of Edinburgh, United Kingdom; DS Tech Italy; Uniwersytet Gdanski, Poland, University of St Andrews, United Kingdom; University of Vienna, Austria; Fundacio Eurecat, Spain; Eurice, Germany, OpenEvidence, Spain; Fondazione IRCCS Istituto Nazionale dei Tumori, Italy; Lab4Life, Poland; Universidad de Zaragoza, Spain; Personal Genomics, Italy; Centre Hospitalier Universitaire de Grenoble, France; Lunds Universitet, Sweden; Health Policy Institute, Greece; Ethniko Kai Kapodistriako Panepistimo Athinon, Greece; National Technical University Of Ukraine Igor Sikorsky Kyiv Politechnic Institute, Ukraine.

We are really excited to be a part of the KATY project. Artificial Intelligence is playing an increasingly important role in biomedical research, but its integration into translational science and implementation into clinical practice is lagging behind. We believe that AI can bring significant advances to personalized cancer medicine and we hope that the project will demonstrate utility of AI approaches in clinical setting.

Professor Ted Hupp, Dr Alexander Laird and Dr Stefan Symeonides

AI - empowered personalized cancer medicine

Related Links