DATA 
SCIENCE
FOR
HEALTH
EQUITY

We were thrilled to be joined by Kathy Harrison - Programme Lead, DataLoch, University of Edinburgh The recording is just the presentation part of the session - this was followed by discussion and Q&A which we did not record. DataLoch is a Safe Haven (otherwise known as a TRE or SDE) in Scotland, based in the new Usher Institute in Edinburgh. The DataLoch team research with access to primary and secondary care data. Kathy will share something about how the Scottish health dat

This event was co-hosted with READI (Research in Europe and Diversity Inclusion), a European initiative working to reshape clinical research towards greater representation and inclusion. We explored the challenges of recruiting diverse and representative populations into clinical trials across Europe, with a particular focus on process: what inclusive trial design looks like in practice, and what we can learn from ongoing efforts to embed it from the outset. The session inclu

The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community, the Alan Turing Institute Health Equity Interest Group, and the Department of Statistical Science at University College London. --- We are excited to present the next instalment of our webinar series with speaker Sharon Davis (Vanderbilt University Medical Center) Webinar Title: Supporting Responsible Deployment of AI in Healthcare with Sustai

This session sits within our Children & Families Theme which is focused on placing the child in the wider context of their family and environment, bringing together people passionate about using data science to better understand and address maternal, familial, and child health inequities. Expect space for knowledge sharing, thoughtful discussion, and community-building that connects researchers, clinicians, policymakers, and experts by experience, and amplifies diverse voices

This event was co-hosted with HDR UK, and explored the challenges in finding and accessing representative data and, crucially, how to overcome them. We hears about HDR UK’s work across data infrastructure, technology to improve access, and inclusion, with a particular focus on: The Health Data Research Gateway which is HDR UK’s online platform to help researchers find health datasets, The Cohort Discovery Tool to help researchers determine the size of the population relevant

The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community, the Alan Turing Institute Health Equity Interest Group, and the Department of Statistical Science at University College London. --- We are excited to present the next instalment of our webinar series with speaker Amanda Coston (UC Berkeley). Title: Evaluating Predictive Models Under Selection Bias and Covariate Shift Abstract: Understanding ho

This event was co-hosted with PEDRI and explored how researchers can take a more thoughtful and practical approach to improving diversity in their patient and public involvement and engagement (PPIE) work. The session focused on supporting researchers to make their PPIE work more inclusive by highlighting current best practice and addressing common challenges, such as how to engage meaningfully with diverse communities and avoid tokenistic approaches. It included practical ex

The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community, the Alan Turing Institute Health Equity Interest Group, and the Department of Statistical Science at University College London. --- We are excited to present the next instalment of our webinar series with speaker Brandon Dominique - (Northeastern University) Title: Post-Hoc Methods for Detecting and Correcting Subgroup Bias in Medical AI Syste

We were delighted to host Anna Palczewska, Rob Grout, and Frank Wood for the latest instalment of our monthly informal meetup - The DSxHE Download. Title: Predict, Prevent, Perform: Partnerships to Unlock the Power of AI & Analytics The recording is just the presentation part of the session - this was followed by discussion and Q&A which we did not record. In this presentation, we will be joined by colleagues from the Leeds Office of Data Analytics and Accenture who worked i

Here is the recording of our ECR-led webinar on why research on children and families matters and how inclusive, collaborative, and data-driven approaches can help advance health equity for children, young people, and families . Julia Shumway, UCL About Julia: Julia Shumway is a PhD student and research assistant at the University College London Great Ormond Street Institute of Child Health. The aim of her PhD is to understand the impact of placement in mainstream versus spe

We were delighted to host Carrie Alexander , for the latest instalment of our monthly informal meetup - The DSxHE Download. Title: AI Governance as a Knowledge Game The recording is just the presentation part of the session - this was followed by discussion and Q&A which we did not record. AI Ethics and Governance frameworks have proliferated in recent years, accompanied by criticism from hard law advocates who argue, for instance, that AI ethics frameworks are “useless” bec

We were delighted to host Claire Coffey - University of Cambridge, for the latest instalment of our webinar series on statistical methods for fairness and equity in healthcare. Topic: Are polygenic risk scores fair for cardiovascular disease risk prediction? Abstract: Polygenic risk scores (PRS) are increasingly proposed to enhance cardiovascular disease (CVD) risk prediction, particularly for individuals whose clinical risk estimates fall in intermediate ranges where treat

We were delighted to host Vincent Jeanselme a postdoctoral researcher at the reAIM Lab, Columbia University, for the latest instalment of our webinar series on statistical methods for fairness and equity in healthcare. Topic: Advancing AI-Based Risk Prediction for Improved Decision-Making in Healthcare Abstract Accurate prediction of patient outcomes plays a critical role in healthcare decision-making, shaping treatment strategies, clinical guidelines, hospital operations

Recording of the launch of the Data Diversity Theme, a new initiative from Data Science for Health Equity (DSxHE) in partnership with Cancer Research UK. Don't want to miss out on any future Data Diversity theme activities? Stay up to date by joining the #theme-data-diversity channel on our Slack workspace .

We were delighted to host Jake Hightower, data science and global health innovator, for the latest instalment of our webinar series on statistical methods for fairness and equity in healthcare. Topic: Preserving Health Equity in a Global Pandemic Model Abstract In an era of increasingly complex global health threats, pandemic modelling must evolve to reflect not only the spread of disease but the lived realities of those most affected. This talk presents a ground-breaking

We recently hosted a couple of virtual drop-in sessions to launch our latest DSxHE Theme on Data Diversity . These sessions served as both an introduction to the new theme and a starting point for an important conversation about diversity in biomedical datasets. The event featured interactive activities and thought-provoking discussions designed to spark engagement and reflection ( check out this blog post for more on that ). We also recorded a special segment with Brieuc Leh

We were delighted to host Stephen Pfohl, Senior Research Scientist at Google Research, for the latest instalment of our webinar series on statistical methods for fairness and equity in healthcare. Stephen shared insights from his research into the challenges of evaluating algorithmic fairness in clinical settings, highlighting that fairness assessments are never one-size-fits-all. Drawing on examples from his work, Stephen emphasized that evaluations of fairness must be groun

We were pleased to welcome Dr. John Ford, Director of the Health Equity Evidence Centre, for a recent webinar on using machine learning to tackle health and care inequalities. Dr. Ford shared how his team, in collaboration with the EPPI Centre at UCL, is developing living evidence maps , continuously updated tools that organise research on effective interventions. These maps address a growing challenge in public health: keeping pace with an ever-expanding evidence base, where

We were thrilled to host Dr. Briana Stephenson from the Harvard T.H. Chan School of Public Health in a past installment of our webinar series! Dr. Stephenson led a fascinating discussion on how mixture models can help uncover important patterns within underserved populations. She highlighted how traditional research methods often focus on majority subgroups, leaving smaller communities overlooked. In a diverse country like the United States, this "one-size-fits-all" approach