1 0 P R E C I S I O N M E D I C I N E Advances in cancer risk assessment and prevention French oncologists pick up the pace after pandemic time-out The pandemic-imposed pause for oncology care is coming to an end: Real-life data and person- alised screening techniques are set to improve cancer prevention and patients’ quality of life. In a dedicated press conference in Paris, French oncologists pre- sented promising research that might bring hope for many can- cer patients. French cancer centres are catching up after the coronavirus pandem- ic put oncology interventions on hold in 2020, and the spirit of a fresh start was prevalent at an event organised by Unicancer, a federation regrouping 19 leading institutions specialising in oncol- ogy. ‘We’re getting out of it, after experiencing delays that have been detrimental to patients’ recovery,’ Unicancer President Jean-Yves Blay, a professor of medical oncol- ogy at Claude Bernard University in Lyon, said. After all, the pandemic left a consid- erable dent in cancer care: French facilities registered a 7% diagnos- tic delay for oncology patients in the aftermath of the Covid-19 outbreak in 2020. One year later, Unicancer centres, which treat about 20% of patients with cancer in France, reported a 6% increase in activity. Unicancer presented a series of proposals to better fight cancer, which remains the leading cause of death in France, with nearly 400,000 new cases and more than 157,000 deaths each year. Proposals target healthcare profes- sions’ attractiveness and remuner- ation and offer strategies on how to boost follow-up and prevention. The experts agreed that 40% of cancers could be avoided if cur- rent knowledge about risk factors was translated into effective pub- lic health strategies. ‘We want to develop highly connected research points to improve prevention from risk factor identification to screen- ing,’ Blay said. ‘Treatment follow-up of cancers in children and rare can- cers, which remain difficult to treat, is also one of our priorities.’ With over 100 studies enrolling 8,000 patients in 2021, Unicancer touches on several aspects of research beyond the clinical spec- trum, focusing on issues such as patients’ quality of life and how to make use of data which is already available. A few months ago, the organisation launched a pilot project with Health Data Hub, a platform dedicated to facilitating the sharing of health data from a wide variety of sourc- es, to help accelerate research. The program, called UNIBASE, aims to harness data from electronic patient records and create a collec- tion of cancer reference databases within three years. ‘Having this huge amount of real-life health data will help us better predict or evalu- ate treatment,’ Blay said. Personalising screening and patient involvement Underlining the historical weak- ness of France’s public health cul- ture, the latest report of the French National Audit Office on preven- tion policies mentioned ‘mediocre results’, despite significant financial efforts similar to those of European neighbours. For example, screen- ing remains problematic in France. National programmes are organ- ised for breast cancer, colorectal cancer and cervical cancer, but par- m o c . k c o t S e b o d A – a i d e m . r e b i e r h c s r e t e p © ticipation remains insufficient. To improve screening efforts, research- ers are looking to more personalised approaches, for example in breast cancer screening programmes. To this end, Unicancer is taking part in MyPeBS, an EU-funded randomised controlled trial that aims to assess the value of personalised breast cancer screening for women aged 40 to 70 in Europe. The study plans to determine whether risk-based cancer screening in these women is non-inferior to the standard screen- ing programme currently offered in Belgium, France, Israel, Italy, and the United Kingdom. The pro- ject will follow 85,000 women over four years and could mean a great advance, Blay explained. ‘This study is a revolution in screening manage- ment. If completed, it will transform the routine,’ he said. Patient empowerment is another promise of personalised cancer medicine. The aim is to involve the patient in clinical decision-mak- ing, another speaker highlighted in the conference. ‘We’re witnessing a cultural change and a reconstruc- tion of clinical decision-making,’ Ariane Weinman, a representative at EURORDIS, a non-governmen- tal alliance of rare disease patient organisations, said. ‘Patients and their increasingly involved and informed, sometimes even receive dedicated training to prepare for the experience.’ families are Patient organisations also increas- ingly take part in clinical trials, which benefits everyone, according to Weinman. ‘The more involved the patients are, the better they will be able to follow their treatment and support research near the authorities,’ she concluded. Report: Mélisande Rouger Artificial intelligence and Deep learning to drive precision medicine Diving into medical big data Big data is transforming diagno- sis and medical care, but the criti- cal challenge remains over how to equally apply the benefits it delivers across real-world clinical settings. Industry expert Benoît Macq recognises that high quality data can be harvested from major university hospitals and academic centres but is convinced that the true value will emerge when it is accessible in a relevant way to clinicians and patients in smaller hospitals too. Prof Macq, who leads the PiLAB research team from the Institute of Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM) at the Université Catholique de Louvain in Belgium, explained that large-scale data sets can create predictors for diagnosis, treatment planning, and drug use, by har- nessing Artificial Intelligence (AI) and Deep Learning (DL) technolo- gies to acquire and analyse data to realise these goals. However, what An example of a prototype of Cone Beam CT that Prof Macqs team jointly developed with the IBA company for image-guided proton therapy. In the photograph is (from left): Eric de Lamotte (IBA), Benoît Macq, Merence Sibomana (PiLAB) and Rudi Labarbe (IBA). is key is that there is no centralised point of the data, but a system of “federated learning” where the DL model accesses a range of data silos in different hospitals. This brings data together to create a dis- tributed big data set, but with each institution retaining control of its data from a regulatory, cybersecuri- ty and patient privacy perspective. From this concept of federated learning, which groups organisa- tions together, the drive is to move to the next step of coalitional learn- ing between different institutions ‘to feed the new predictors, the new diagnosis and the new biomarkers’. With a challenge lying in the vary- ing data quality, annotation, clinical decision making and diagnosis, the move from federated learning to coalitional learning will help pro- vide cross control of data quality, he said. That will remove the variabil- ity in data and ‘align human judge- ment across a coalition’ in sharing data, procedural approaches, and joint strategy on the use of the data. A shift to coalitional learning increases the quality of the data, ensures validated expertise, and increases accuracy, said Professor Macq, who already applied this together with his team in areas such as proton therapy treatment planning and early detection of breast cancer. As an engineer, rath- er than a clinician, he emphasised the importance of ‘diving into the data’ from different places and making sense of it and being rel- evant to the patient. ‘We want to have a convergence with a coali- tional learning system where the data acquisition and the predic- tive model is increasing thanks to the contribution of the different institutions,’ said Macq. He further underlined the importance of diffe- rent types and sizes of institutions working together, as well as engi- neers collaborating with clinicians and data scientists, in constructing a DL model that is applicable and relevant to all clinical institutions and their patients. Precision medicine The benefit is to create precision medicine to deliver better diag- nosis and patient care, but also facilitate improved natural medi- cine. ‘The idea is to better under- stand diseases by trying to find causal relationships between DNA, RNA proteins and metabolics, and between different levels in the biol- ogy continuum to augment medi- cine,’ he said. He believes precision medicine will lower the costs as screening will be more efficient and treatment more precise and personalised. ‘Accessibility is our goal,’ he said, ‘and to increase the quality of treatment because it will be more personalised and delivered earlier Benoît Macq (ICTEAM) at Professor Benoît Macq leads PiLAB, a research team from the Institute of Information and Communication Technologies, Electronics and Applied Mathematics the Université Catholique de Louvain in Belgium, where around 30 researchers focus on three main research topics of: Signal & Pixels, Medical Imaging, and Interaction. The co-founder of 11 spin-off companies, he is a Fellow Member of the IEEE (The Institute of Electrical and Electronics Engineers) and a Member of the Royal Academy of Science of Belgium. with better diagnosis and better screening.’ This, he hopes, will cre- ate a new democracy to the use of the data so patients – whether at a university hospital or local hospital – will benefit equally. Report: Mark Nicholls EUROPEAN HOSPITAL Vol 31 Issue 2/22