I gave a talk on automatic methods to map from verbal autopsy interview results to underlying causes of death last August, and I like the slides so much that I’m going put them online here. Cheers to the new IHME themed templates for Power Point!
Category Archives: machine learning
One exciting announcement that I got to make at the Verbal Autopsy Congress last October is that the PHMRC gold standard verbal autopsy validation data is now available for all researchers. You can find it in the Global Health Data Exchange: Population Health Metrics Research Consortium Gold Standard Verbal Autopsy Data 2005-2011.
Insert an example of doing something with it here.
This week we heard from Ziad Obermeyer, a former IHMEer, and current Harvard prof and ER doc, about using big data to understand costs and improve predictions in the health system. And he didn’t say “big data” the whole time. Perhaps the video will appear here.
This week we had a seminar on Bayesian Dynamic Modeling from UW Stats professor Emily Fox. The video is archived here! This talk had some of the most successful embedded video that I’ve seen in a talk. I don’t think it made it into the video perfectly, though, so imagine dancing honeybees while you watch.
I need a graphic for dismod that makes the point as nicely as this one:
It’s from P. Dierckx, Curve and Surface Fitting with Splines, which also has some pretty pictures of bivariate splines doing their thing:
I mentioned in February a couple of contests that caught my eye, and the Whale Detection one turned out to be quite interesting. Now it has completed, and the prediction quality (AUC, if I recall correctly) has been raised from .72 to .98. Very cool.