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 announce the next instalment of our webinar series with speaker Catalina Vallejos from the University of Edinburgh.

Specific details on the topic are as below:

Topic: 

Using routine healthcare data to predict future health

Abstract:

Can we identify who will experience an adverse health event (e.g. disease onset) weeks, months or even years before it happens? Questions like this are at the core of health data science research and have been empowered by the increasing ability to securely access routinely collected electronic health records (EHR). EHR is a rich source of data which contains detailed information about entire patient populations. However, extracting robust insights from EHR is not a trivial task for multiple reasons including recording errors, unstructured data collection and observational biases, amongst others. In this talk, I will provide an overview of our research in this area, highlighting how EHR can be used to stratify individuals according to their risk profiles and disease trajectories. I will also describe the development of SPARRAv4 (Scottish Patients at Risk of Readmission and Admission version 4) a risk score developed in collaboration with Public Health Scotland and that will be shortly deployed at national level in primary care settings. Finally, I will describe some of the practical and methodological challenges that we have encountered throughout these projects.

Speaker Biography:

Catalina Vallejos leads the Biomedical Data Science research group at the MRC Human Genetics Unit within the University of Edinburgh. Her research group has a cross-disciplinary research programme at the intersection between statistics, machine learning and biomedicine: addressing complex biomedical questions and technologies whilst developing new computational methods and open-source software. Catalina’s work covers a wide range of application areas and data types: from helping to improve our understanding of complex biological processes (such as aging) using single cell sequencing data to translational projects, developing clinical risk prediction tools using routinely collected electronic health records. This includes the development of SPARRAv4, a risk score that predicts emergency admission risk and that will be deployed to support primary care intervention across Scotland.

Catalina is a co-Director for the Edinburgh Cross-Disciplinary Fellowships programme and is ELLIS Health Scholar. She is an alumnus of The Alan Turing Institute, where she was part of the inaugural cohort of Research Fellows and, subsequently, a Turing Fellow. Catalina completed a PhD in Statistics at the University of Warwick and post-doctoral training in a joint appointment between the MRC Biostatistics Unit and the EMBL European Bioinformatics Institute in Cambridge. Previously, she completed a BSc and MSc in Statistics at the Pontificia Universidad Catolica de Chile.

--

Please direct any questions about the webinar series to Dr Brieuc Lehmann at b.lehmann@ucl.ac.uk.