Novartis teams up with Oxford researchers to crunch big data into clinical insights
Since Vas Narasimhan’s Day 1 as CEO of Novartis, he has championed data science and digital technologies as a key priority at the pharma giant. Almost a year into his tenure, in a recent conversation with the tech VC firm Andreessen Horowitz, he highlighted the abilities to analyze pathology images and centralize clinical trial planning as two promising applications of machine learning.
But, he admitted, there are areas where it’s “simply not met up”:
The Holy Grail of having unstructured machine learning go into big clinical data lakes and then suddenly finding new insights, we’ve not been able to crack, mostly because the data… to link it up… We are spending a lot of our energy just trying to get all of our data harmonized, so that some algorithm could maybe find anything of use.
It appears that Novartis is now ready to dive into that lake with the help of an esteemed academic partner.
The Swiss drugmaker has two projects in mind to kick off the 5-year research alliance with the Big Data Institute at the University of Oxford. The first one will focus on multiple sclerosis, leveraging clinical and magnetic resonance imaging, or MRI, data of 35,000-plus patients in hopes of understanding patterns and disease progression. Ultimately, the company says, the exercise should make clinical trials more efficient and targeted.
For the second project, Novartis wants the BDI to deploy its deep learning algorithm across different datasets — imaging, proteomic, genomic, clinical — from more than 11,000 patients who have taken its interleukin-17 inhibitor, Cosentyx. The hope is to enable quicker diagnosis and explore commonalities between diseases treated by the drug, including psoriasis, psoriatic arthritis, ankylosing spondylitis and rheumatoid arthritis.
These individuals, though, only represent a fraction of the pool of patients Novartis and BDI are pulling data from. With access to data from UK Biobank, Genomics England and China Kadoorie Biobank, the alliance will draw on a total of 5 million patients — a number reflective of Novartis’ ambition to adopt data science in clinical research at scale, spokesperson Eric Althoff tells Endpoints News in an email.
We asked what the operation will look like on the ground, and here’s their response:
Oxford is building an IT environment for the collaboration – they will host the environment and NVS is supporting the build.
Today we have approx 20 people from Oxford and 20 people from NVS involved – this includes data wrangling experts, data scientists, statisticians, IT experts and clinical experts.
Novartis added that other partners like the Medical Research Council Harwell Institute and Oxford’s Department of Statistics will also play a role.
Featured image: Oxford’s Big Data Institute. OXFORD via YOUTUBE