Sensyne Health | Discovery Sciences

What we do

1
Build & Protect

We build large datasets of anonymised patient data in collaboration with the NHS, providing a rich source of clinical information while protecting patient privacy.

2
Curate & Analyse

We curate and analyse the datasets using AI algorithms.

3
Identify

We identify patterns using proprietary machine learning and deep learning technologies.

4
Discover

We discover new insights of significant value to patients, clinicians and the life science industry.

The Discovery Sciences Team at Sensyne Health combines clinical and data science expertise to develop machine learning technologies applied to ethically sourced anonymised electronic patient record (EPR) data received from our unique partnership with the NHS.

We use EPR information to create large longitudinal datasets, then develop clinically driven AI technology that analyses and contextualises that information to identify previously unseen patterns and insights that can be used to undertake advanced medical research, improve pharmaceutical development and deliver better patient care.

Paul Drayson, CEO
The current medical discovery system involves interpreting enormous volumes of diverse information. It can be like finding a needle in a haystack, without knowing what a needle is, what a needle looks like or where the haystack is.  We aim to change that.
Paul Drayson
CEO

The way we work

Using real-world data has a real-world impact.  We use it to:
Improve

Improve

Improve clinical trials by distinguishing specific groups of patients and Identifying sub-sets of responders and non-responders.

Understand

Understand

Understand the mechanism of disease in the real world in order to personalise treatment  and coherently diagnose sufferers of poorly understood diseases.

Predict

Predict

Predict clinical events earlier such as stroke or heart failure.

Discover

Discover

Discover new treatments faster to address unmet medical needs.

Impact - Using real world evidence

Information based on RWE can provide vital indicators to better prevent, treat and understand the cause and progression of disease. It enables a level of insight and analysis simply not possible to achieve from other research datasets.  It is richer, more extensive and more representative of large patient populations.

Approach - ‘Bedside to bench’

Traditionally, medicinal research starts in the lab.  We take a different approach. From ‘bedside to bench’ deconstructing the classical R&D pipeline model by putting patient data and patient outcomes at the beginning of the drug discovery and development process.

Drug development stages diagram
Drug development stages diagram

Case Studies