Join us for the official launch of DiMe’s Integrated Evidence Plans (IEP) resources, designed to help you overcome key challenges in evidence generation and commercial adoption of digital health technologies (DHTs)!
Join us for our launch, “Unlocking impact through investment: Building the business case for digital endpoints,” on Mar. 26 at 11 a.m. ET. Learn how new resources support you in measuring ROI and building your business case for digital endpoints.
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.
