<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/3ef9f487cf1f41deb9ed02b5e5cefe3b&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/3ef9f487cf1f41deb9ed02b5e5cefe3b-7217cfdd85e0902a.jpg</thumbnail_url><duration>554.603</duration><title>Understanding Cause of Death in Patient Analysis</title><description>In this video, I discuss the importance of accurately determining the cause of death when analyzing patient data, as it significantly impacts our analysis. I highlight the challenges we face, such as the inaccessibility of death certificates and the fact that up to 40% of them may list incorrect causes of death. To address this, Veritas employs a method that derives cause of death from three years of clinical history, using a weighted algorithm to identify the most likely primary and secondary causes. I encourage you to consider how this data can enhance your analytics, risk models, and survival curves. Please take a moment to reflect on how we can better utilize this information in our work.</description></oembed>