@adamperer@hci.social

· 42mo ago

Alex Cabrera ( @cabreraalex@hci.social ) gives another great talk at #chi2023 about Zeno, our new platform for machine learning evaluation and visualization: https://zenoml.com/ @cmudig@hci.social @cmuhcii@hci.social

zenoml.com

Zeno | AI Evaluation Platform

AI Evaluation Platform

7

0

1

0

Adam Perer @adamperer@hci.social

· 42mo ago

Alex Cabrera ( @cabreraalex@hci.social ) speaks at #chi2023 about an amazing framework describing how data scientists develop mental models of AI behavior https://dig.cmu.edu/publications/2022-aiffinity.html @cmudig@hci.social @cmuhcii@hci.social

CMU Data Interaction Group

What Did My AI Learn? How Data Scientists Make Sense of Model Behavior

Data scientists require rich mental models of how AI systems behave to effectively train, debug, and work with them. Despite the prevalence of AI analysis tools, there is no general theory describing how people make sense of what their models have learned. We frame this process as a form of sensemaking and derive a framework describing how data scientists develop mental models of AI behavior. To evaluate the framework, we show how existing AI analysis tools fit into this sensemaking process and

7

0

2

0

Adam Perer @adamperer@hci.social

· 42mo ago

Venkat Sivaraman gave an excellent talk at #chi2023 on how clinicians negotiate with AI when making high-stakes clinical decisions https://dig.cmu.edu/publications/2023-sepsis-ai.html @cmudig@hci.social @cmuhcii@hci.social

CMU Data Interaction Group

Ignore, Trust, or Negotiate: Understanding Clinician Acceptance of AI-Based Treatment Recommendations in Health Care

Artificial intelligence (AI) in healthcare has the potential to improve patient outcomes, but clinician acceptance remains a critical barrier. We developed a novel decision support interface that provides interpretable treatment recommendations for sepsis, a life-threatening condition in which decisional uncertainty is common, treatment practices vary widely, and poor outcomes can occur even with optimal decisions. This system formed the basis of a mixed-methods study in which 24 intensive care

6

0

3

0