University of Cambridge > Talks.cam > Cambridge Statistics Discussion Group (CSDG) > All models are wrong and yours are useless: making clinical prediction models impactful for patients

All models are wrong and yours are useless: making clinical prediction models impactful for patients

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Peter Watson.

: Most published clinical prediction models are never used in clinical practice which leads to a huge gap between academic research and clinical implementation. Here, I propose a checklist to enable academic researchers to be proactive partners in improving clinical practice and to design models in ways that ultimately benefit patients. Over the years I have come to see academic papers not as ends in themselves, but as the beginning of the journey to clinical implementation, and I am frustrated with how little of my own work ever had clinical impact. I argue that you should outline the road to implementation whilst designing your prediction tool by thinking about what medical decisions they are making and how these tools can be used in routine practice. I will illustrate these ideas by discussing AI models from our work to find a minimally invasive alternative to endoscopy and looking at ways of assessing breast cancer survival rates after surgery that can be used in the clinic.

This talk is part of the Cambridge Statistics Discussion Group (CSDG) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity