Generic selectors
Exact matches only
Search in title
Search in content
Post Type Selectors

Digital medicine and the curse of dimensionality

Date/Time

December 14, 2021

Discussion Topic

A patient’s health state can be characterized by a multitude of signals from many different data modalities. This high-dimensional, personalized data stream aggregated over patients’ lives has spurred interest in developing new clinical AI models. One of the rate-limiting factors in developing AI models that generalize to real-world scenarios is the very attribute that makes the data exciting—their high-dimensional nature.

At DiMe’s #AskMeAnything Journal, author Visar Berisha, PhD led a discussion on how “the curse of dimensionality” can doom models to failure, even when they seem to work well during development. We explored the key highlights of his Nature publication “Digital medicine and the curse of dimensionality“, Visar also provided some suggestions on how to develop clinical AI models that are more likely to fare well during prospective validation.

 

Read the article

Listen to the discussion

View the presentation slides

 

Sign up to receive our monthly updates


Engage with the dime community on slack


USING A DIME RESOURCE? Share your story


Contact Us


Copyright ©2023 The Digital Medicine Society (DiMe). All Rights Reserved.