We are creating cutting-edge machine learning methods and applying them to drive a revolution in healthcare.
AI and machine learning
Time series analysis
Interpretability & explainability
Impact on healthcare
Risk & prognosis
Risk and disease trajectories
Treatments & clinical trials
Early warning systems
Missing data imputation
Phenotyping & subgroup analysis
To see what we’ve published in these sub-fields, click here.
This revolution isn’t about replacing healthcare professionals, or outsourcing their work; it’s about empowering them with reliable decision support and actionable intelligence.
Clinicians, patients, researchers and policymakers are at the heart of what we do. Through extensive collaboration, we are guided and inspired by stakeholders from all areas of healthcare.
Our research projects are targeted and practical; they originate from our guiding desire of solving real-world problems in healthcare.
What sets us apart
Our team is small but extraordinarily prolific. Led by Mihaela, our 2 postdocs and 10 Ph.D. students have 27 papers accepted at the four largest AI and machine learning conferences (14 at NeurIPS 2021, 4 at ICML 2021, 4 at AISTATS 2021, and 5 at ICLR 2021) in the last year alone. NESTA has recognized Mihaela as the female AI researcher in the UK with the largest number of publications in AI and machine learning.
The lab’s alumni around the world have become leaders in their fields, with some continuing to full professorships and others joining top private-sector teams including Google, Intel, Qualcomm and Apple.
One of our greatest assets is the extraordinary diversity of our team’s academic, professional and cultural backgrounds. Mihaela herself found her way into machine learning from electrical engineering, and has a wealth of experience in the private and public sectors.
We love a challenge
Medicine and, more generally, healthcare, stand apart from other areas where machine learning can be applied. Where we have seen advances in other fields driven by lots of data, it is the complexity of medicine, not the volume of data, that makes the challenge so hard.
But at the same time this makes medicine the most exciting area for anyone who is really interested in exploring the boundaries of machine learning, since we are given real-world problems to formalize and solve. And not only that—the solutions are ones that are societally important, and they potentially impact us all.
Mihaela sums up the challenge and opportunity below, in an excerpt from her 2020 ICLR keynote.
Impact throughout healthcare
While our research primarily exists to benefit patients and clinicians as “end users,” our machine learning methods can drive progress for stakeholders across the healthcare ecosystem, including clinical research and pharma.
For more details, see Mihaela’s chapter in the UK’s 2018 Annual Report of the Chief Medical Officer, discussing how machine learning can transform medicine and healthcare.