Papers of the day   All papers

Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making


May 05 2019 Carrie Cai

How can human-centered tools make AI more useful to doctors? I'll be presenting on our #chi2019 paper tomorrow, which won a best paper honorable mention! Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-making Monday 11am
15 replies, 491 likes

May 06 2019 Jeff Dean

.@Carryveggies et al. of @GoogleAI presented work at #chi2019 on tools that allow doctors to interact with AI systems to make better decisions. Fig. 5 in the paper shows a user evaluation of the system in terms of diagnostic utility, effort, trust, & "would use in practice".
3 replies, 146 likes

Jul 19 2019 TechCrunch

Google’s SMILY is reverse image search for cancer diagnosis
0 replies, 35 likes

May 06 2019 Martin Wattenberg

What does it really mean to design for human/AI collaboration? How can doctors and ML work together effectively? If you're at CHI, go to this talk for some answers! (And if you're not, the paper's online.)
2 replies, 34 likes

Jul 24 2019 Carrie Cai

A nice summary (by TechCrunch) of our CHI '19 research on the HCI+AI challenges of building reverse-image-search for cancer diagnosis. paper: @GoogleAI @GoogleBrain
0 replies, 21 likes

May 05 2019 Been Kim

Work with real doctors on how AI can help doctors! @Carryveggies is presenting this work at #CHI2019 tomorrow!
0 replies, 21 likes

May 15 2019 Enrico Bertini

@magneticnorth I good recent example I like is this one:
1 replies, 4 likes

May 07 2019 Giorgio Quer

How can doctors and AI work together?
0 replies, 2 likes

Nov 11 2019 Khadijah

Currently being discussed at #CSCW2019...SMILY:augment similar image search with refinement tools
0 replies, 1 likes

Jul 20 2019 mjgarciag

An example of ML application to assist specialists in decision making: "Users adopted new strategies when using refinement tools, re-purposing them to test and understand the underlying algorithm and to disambiguate ML errors from their own errors.:
0 replies, 1 likes