Akrivia AI Enabled Secure Real World Data Platform

A billion people worldwide live with mental disorders, with global costs projected to surpass £5tn by 2030\. In the UK, mental illness is the leading cause of disability, affecting one in six adults annually. Despite this, current treatments for mental disorders are effective for fewer than 50% of patients, reflecting the fact that we still understand very little about their underlying causes.

One challenge is that diagnostic labels (like, 'major depression', 'schizophrenia', etc) do not necessarily correspond with biological differences between patients. Consequently, researchers are increasingly focusing on features that bridge diagnostic categories, like symptoms, blood tests, brain scans, or life circumstances (trauma, inequality etc).

This trend is part of the so-called 'precision medicine' model - finding the right treatment, for the right patient at the right time.

Electronic health records (EHRs) can be extremely useful in 'precision' research. EHRs capture patients' full history, including rich information on symptoms, life circumstances etc. Unfortunately, EHRs can be difficult to use for research. This is partly due to a lack of secure, privacy-preserving access infrastructure, and partly because EHRs are not designed for research, meaning their data can be hard to analyse, especially at scale.

To address these issues, the Akrivia Health team have established a 15-year collaboration with the NHS, developing a secure, strictly access-controlled platform for research access to anonymised EHRs. Akrivia has developed a system of 'natural language processing' (NLP) algorithms to translate sensitive clinical notes into anonymised, structured tables that preserve only research-relevant information.

Akrivia's platform now includes anonymised data from ~4.6 million patients', and is used to support precision research into mental health across the NHS (for free), academia (at a large discount) and industry.

Since spinning out from Oxford University in 2019, demand for Akrivia's services has grown dramatically. In response, Akrivia is seeking Innovate support to transform our current manual, labour-intensive service into a highly-automated, scalable platform. We will develop materials to help users understand our data, standardise processes for contracting and project review by our oversight committee (including patient representatives), and build a more scalable version of our current secure data access environment.

We will guide this work by involving patient groups, legal experts and potential users, and will continue expanding our dataset to increase its research impact. Ultimately, we aim to improve patients' lives by enabling research to understand the causes of mental illness develop more effective treatments.