Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

One key feature of our research is using data collected from the world around us. This could be de-identified patient records, weather station measurements or satellite imagery. This real-world international evidence uses federated analytics to safely and securely combine individual person-level data into valuable learning.

These days, so much of our lives produces data. At PHI, we use this routinely collected data and combine it with the latest analysis pathways from artificial intelligence and medical statistics. Using data collected down to the level of individuals, we can then produce useful resources like clinical models for predicting health outcomes.

To preserve an individual's privacy in this process, we use de-identified data and federated analytics. Federated analytics enables data analysis without centralising it. Instead of sending personal data to a central server, it remains on users' devices, and algorithms process the data locally. From this analysis, we can produce aggregate trends which can be used in research, but which are anonymous and in which no individual's data can be identified, making it a promising solution for data-driven applications.

Many of our research projects in this area also focus on COVID-19, as PHI continues to aid efforts to understand and combat the pandemic. See more about our pandemic response here.

Featured Projects



Rare heart diseases during the COVID-19 Pandemic



Patient Groups in Osteoarthritis


PHI Link COVID-19 Vaccination in Brazil and Pakistan
PHI Link HIPPOCRATES: Promoting early identification and improving outcomes for patients with psoriatic arthritis
PHI Journal Article icon

Unraveling COVID-19: A Large-Scale Characterization of 4.5 Million COVID-19 Cases Using CHARYBDIS

PHI Journal Article icon

A standardized analytics pipeline for reliable and rapid development and validation of prediction models using observational health data