Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

Anna Noel-Storr

Information Specialist

My work at Oxford began with a heavy emphasis on a particular health care domain: dementia. This is a debilitating and devastating disease, currently with no known cure and with only a limited number of treatments that provide meaningful improvements to dementia-related symptoms. My work initially focused on identifying relevant health evidence that would help researchers synthesize the available research in order to better understand the effects of certain treatments. In doing this work I developed an online comprehensive register of dementia trials: ALOIS (named after Alois Alzheimer).

The work on the ALOIS register marked the beginning of my research and work into exploring the role of human effort in the evidence synthesis process. Since then, I have gone on to lead several large projects and initiatives that aim to better harness our greatest asset – people – in the production and maintenance of health evidence. The centerpiece of my work is Cochrane Crowd (http://crowd.cochrane.org), a citizen science platform that hosts a range of micro-tasks aimed at identifying and describing health research. This work has not only resulted in the identification of over 35,000 trials from a community of 8000 strong, it has helped to create large, high-quality datasets that have then be used to build and train machine learning routines.

Over the last two years I have worked increasingly with experts in machine learning in an effort to understand better the optimal ways in which humans and machines can work together. It has become increasingly clear that without better use of automation and semi-automation, we will not be able to keep up with the data deluge, and that it is through carefully evaluated human-machine workflows that we can gain significant increases in efficiency without compromising on quality.