Displaying results 1 - 2 of 2
-
Human-learned lessons about machine learning in public health surveillance
Content Type: Webinar
Presented December 13, 2018. For public health surveillance, is machine learning worth the effort? What methods are relevant? Do you need special hardware? This talk was motivated by these and other questions asked by ISDS members. It will focus… read more… http://www.mayofamily.com/RLM/txt_Clarke_Superiority.html "What we want are new … what was the reported blood pressure during last office visit? – [Unsupervised learning] Represent patterns and … how much is enough? https://hyperboleandahalf.blogspot.com/2010/04/alot-is-better-than-you-at-everything.html • … -
Rapid classification of autism for public health surveillance
Content Type: Webinar
This presentation given August 3, 2017 describes work toward applying machine learning methods to CDC’s autism surveillance program. CDC’s population-based autism surveillance is labor-intensive and costly, as it requires clinicians to manually… read more… settings1 1. Rice et al. IMFAR 2014 https://imfar.confex.com/imfar/2014/webprogram/Paper17138.html Current diagnostic … 14.6 (13.6-15.7) 0.94 Boys 25.4 (23.5-27) 24.1 (22.3-26.1) 0.95 Girls 5.5 (4.6-6.5) 4.9 (4.1-5.9) 0.89 … Predict- DSM-1A + 120 49 DSM-1A - 51 9946 Sensitivity: 70.2% PPV: 71.0% Cohen kappa: 0.71 ROC AUC: 0.962Fasttext, …