This session is about Saving Lives Using Interpretable Machine Learning in HealthCare. It\u2019s critical to make sure healthcare models are safe to deploy. One challenge is that most patients are receiving treatment and that affects the data. A model might learn high blood pressure is good for you because the treatment given when you have blood pressure lowers risk compared to healthier patients with lower blood pressure. There are many ways confounding can cause models to predict crazy things. In the first presentation Rich Caruana will talk about problems that we see in healthcare data thanks to interpretable machine learning. In the second presentation, Ankur Teredesai from UW will talk about Fairness in Machine Learning for HealthCare. And in the last presentation Marzyeh Ghassemi from Toronto will talk about how Interpretable, Explainable, and Transparent AI can be Dangerous in HealthCare. Looks like an exciting lineup, so please join us!<\/p>\n
Session Lead: Rich Caruana, Microsoft<\/p>\n
Speaker: Rich Caruana, Microsoft
\nTalk Title: Saving Lives with Interpretable Machine Learning<\/p>\n
Speaker: Ankur Teredesai, University of Washington
\nTalk Title: Fairness in Healthcare AI<\/p>\n
Speaker: Marzyeh Ghassemi, University of Toronto
\nTalk Title: Expl-AI-n Yourself: The False Hope of Explainable Machine Learning in Healthcare<\/p>\n","protected":false},"excerpt":{"rendered":"
This session is about Saving Lives Using Interpretable Machine Learning in HealthCare. It\u2019s critical to make sure healthcare models are safe to deploy. One challenge is that most patients are receiving treatment and that affects the data. A model might learn high blood pressure is good for you because the treatment given when you have […]<\/p>\n","protected":false},"featured_media":680001,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556,13553],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-679998","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-medical-health-genomics","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/vO7h2-_VwWE","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/679998"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/679998\/revisions"}],"predecessor-version":[{"id":680004,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/679998\/revisions\/680004"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/680001"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=679998"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=679998"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=679998"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=679998"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=679998"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=679998"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}