Deep learning (DL) has the potential to transform medical diagnostics. However, the
diagnostic accuracy of DL is uncertain. Our aim was to evaluate the diagnostic accuracy of …

Executive summary Availability of health technology is inversely related to health need.
Although health-care systems in high-income countries make extensive use of technology …

Background The relationship between the ability to recognize and respond to patient
deterioration (escalate care) and its role in preventing failure to rescue (FTR; mortality after a …

Screening mammography aims to identify breast cancer at earlier stages of the disease,
when treatment can be more successful. Despite the existence of screening programmes …

The volume and complexity of diagnostic imaging is increasing at a pace faster than the
availability of human expertise to interpret it. Artificial intelligence has shown great promise …

Background Artificial intelligence (AI) research in healthcare is accelerating rapidly, with
potential applications being demonstrated across various domains of medicine. However …

The ability to influence behaviour is central to many of the key policy challenges in areas
such as health, finance and climate change. The usual route to behaviour change in …

New insights from science and behaviour change could lead to significantly improved
outcomes, and at a lower cost, than the way many conventional policy tools are used …

The early prediction of deterioration could have an important role in supporting healthcare
professionals, as an estimated 11% of deaths in hospital follow a failure to promptly …

Every month at Google Campus in London, dozens of software developers, clinicians,
behavioural scientists and investors get together to discuss new strategies to influence …