Acute respiratory distress syndrome (ARDS) affects one in 10 critical care patients. It is a condition in which the lungs cannot provide the body’s vital organs with enough oxygen, often as a result of infection. It is fairly common, but under-recognised and difficult to treat, partly due a lack of understanding of the underlying biology. Could machine learning help us identify more effective treatments for patients with ARDS?

Huge amounts of data are generated by modern microscopy and imaging studies. Our work helps researchers make sense of this data by visualising datasets in intuitive and immersive formats. This has applications across a range of domains, and our current work is investigating how doctors can make use of new software to analyse brain scans and prepare for surgeries.

Having the full institutional history of patient data to draw upon in decision making is one advantage of AI that clinicians are keen to embrace. AI-enabled data analysis could help clinicians pursue more effective treatments for issues such as post-operative bleeding, but AI tools will need to be fit for clinical practice.

On 19 November, Accelerate brought together researchers from across Cambridge to share perspectives on how AI is supporting their work. This post summarises some of the key points from discussions.