Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Medicine and Health Sciences
Measuring Birth Trauma Rates In Maine Using Public Data, Mike Lapika
Measuring Birth Trauma Rates In Maine Using Public Data, Mike Lapika
Thinking Matters Symposium Archive
An increasing number of states are creating databases that collect and organize health insurance claims from public and private health care payers. Since December 2016, at least 18 states have these “all-payer claims databases” (APCDs), including Maine. APCDs are intended to inform cost containment and quality improvement by increasing transparency and informing consumer choice. For this project, we assessed how Maine’s APCD data might be used to produce standardized quality measures across facilities in the state. Specifically, we tested a birth outcome quality measure developed by the Agency for Healthcare Research and Quality (AHRQ), Birth Trauma – Injury to Neonate …
Convolutional Neural Networks For Protein Image Classification, Nick Littlefield
Convolutional Neural Networks For Protein Image Classification, Nick Littlefield
Thinking Matters Symposium Archive
A solution to the Kaggle competition: Human Protein Atlas Image Classification. Using microscopic images of cells provided by the Human Protein Atlas, convolutional neural networks, CNNs, were used to analyze and predict the location of protein patterns. Challenges included working with an unbalanced dataset, finding a correct learning rate, and choosing a correct architecture to solve the problem. To learn how to overcome these challenges and gain more understanding of the problem, various kernels and discussion posts for the competition, as well as papers on different CNN architectures were used.