Artificial intelligence to create equitable multi-ethnic polygenic risk scores that improve clinical care

Overall Objective: To develop state-of-the-art artificial intelligence (AI) methods which address the ethnic inequities inherent in genomic medicine and rapidly emerging polygenic risk scores (PRSs). We will subsequently apply these approaches to demonstrate improved screening, diagnosis and treatment of common disease.

Background: Recent breakthroughs in genomics and machine learning have generated personalized medicine tools that have the potential to improve patient care and health maintenance through PRSs. PRSs are risk predictors, which combine information across the entire genome to predict a person's risk of disease, or whether they have unfavorable disease risk factors, such as high cholesterol levels. While still evolving rapidly, these PRSs are more predictive of susceptibility to disease than many traditional disease risk factors. Since PRSs can predict risk of disease they could be helpful in screening programs, by identifying a group of individuals at such low risk of disease, that screening would be unlikely to be helpful-thereby allowing screening programs to focus on individuals at highest risk. They could also refine diagnosis, by identifying people in the population most likely to have a disease and then targeting required diagnostic testing in those at highest risk. Last, they can also improve disease treatment by identifying individuals most likely to benefit from treatment.

While PRSs could help to improve clinical care, they have been largely developed in individuals of European-only ancestry. This is because the large cohorts from which PRSs have been developed consist predominantly of European-ancestry participants. Since genetic make-up varies by ancestry, the performance of these PRSs in non-European ancestries is considerably worse; it is known that not only differences in in genetic risk factors lead to attenuation of performance of PRSs, but also that changes in correlation patterns in our genomes due to distinct population histories decrease predictive accuracy even if the actual genetic risk factors remain the same.

This creates several important problems for the roll-out of such tests in the Canadian and UK healthcare environments. This is because approximately 22% of Canada's population and 12% of the UK are visible minorities. Further, these populations can have increased rates of health care utilization. Therefore, use of European-only PRSs could serve to worsen existing health disparities.

Canada's Chief Information Officer stated that, "Using Artificial Intelligence in government means balancing innovation with the ethical and responsible use of emerging technologies." Using PRSs developed to benefit only the majority group in our societies would not respect these directives and therefore our program will serve to ensure the responsible use of AI.

What are our Specific Goals?
1) To develop AI methods and open source software packages to improve the accuracy of PRSs for CHD and hyperlipidemia for individuals of non-European ancestry.
2) To compare the performance of these ancestry-adapted PRSs in individuals in a diverse set of cohorts, representing multiple ancestries in the UK and Canada.

The Team: Recruiting leaders across the UK and Canada, we have a depth of expertise in AI methods development, human genetics, clinical medicine, cohort development for minority groups, and statistical genetics. This gender-balanced team involves an appropriate mix of senior and junior investigators.

Relevance: Success in this AI-enabled program will allow for the transfer of recent advances in genomic medicine to the citizens of Canada and the UK, regardless of ancestry. The AI methods developed will be widely applicable to other PRSs in development by other groups. As genomics takes root in regular clinician-patient interactions, our set of AI-based tools will ensure that the benefit derived from these advances will be shared by all citizens of our countries.

In this proposal, we aim to address a real-world clinical problem that if not resolved will impair the equitable uptake of AI-based genomics into clinical care. Given the urgency of this problem, we have incorporated into our program from its inception end-users who will directly benefit from this research.

Who will benefit from this research? If successful, our research will predominantly benefit people who are of non-European descent. To realize this benefit, we have engaged four end-users (see Letters of Support). Here we describe each end-user and their role in the program.

The Integrated Health & Social Services University Network for West-Central Montreal (known by its French acronym CIUSSS) provides clinical care to approximately 362,000 people who are served by a partnership of more than 30 healthcare facilities. Included is one of Montreal's leading hospitals and three specialized hospitals, five community care clinics, two rehabilitation centres, four residential centres, two long-term geriatric residences, and two day centres. Dr. Lawrence Rosenberg is the CEO of this CIUSSS and directly supports our program of research since the largest multicultural community in Québec is served by this CIUSSS. Dr. Rosenberg is currently leading a team of researchers and clinicians to implement genomics-based medicine within the CIUSSS.

Health Data Research UK is the UK's national Institute for health data science, directed by Professor Andrew Morris. It is an independent, non profit organisation bringing together 22 of the UK's leading universities and research institutions to address a common mission of uniting the UK's health data to make discoveries that improve people's lives. HDR UK's vision is that every healthcare interaction and research endeavour will be enhanced by access to large scale data and advanced analytics. The ambition to generate advanced AI tools to address health inequalities and collaborative research presented in this proposal fully aligns with HDR UK's mission.

Genomics England is owned and funded by the Department of Health & Social Care, England, set up to deliver the 100,000 Genomes Project. Its four main aims are to create an ethical and transparent genomics medicine programme based on patient consent; to bring benefit to patients and set up a genomic medicine service for the NHS; to enable new scientific discovery and medical insights; and to kick-start the development of a UK genomics industry. The 100,000 Genomes Project aims to bring the benefits of personalised medicine to the NHS. To make sure patients benefit from innovations in genomics and contribute towards delivering high quality care for all, now and for future generations. Involvement of Genomics England will provide an important route to further demonstrate the clinical utility of the equitable PRSs developed within this project.

Think Research represents our knowledge translation partner. The clinical impact of our research can only be realized if physicians understand when to order PRSs, how to interpret their results, document their findings and alter patient care. We are not naive to the tremendous difficulties encountered when attempting to change the behaviour of physicians. Therefore we have engaged with Think Research, a Canadian company that has specialized in electronic health record clinical support tools. Think Research's solutions are used in over 2,000 health care facilities world-wide. After completion of our program, our knowledge translation partner will maximize the clinical utility of our research by enabling uptake in health care systems in both Canada and the UK. Despite our engagement with Think Research, they will have no access to data, or the algorithms that were derived from data.

Summary: Through careful engagement with four essential end-users we will maximize the clinical impact of our research program.