Collaborative Research Project 5

Principal investigators: Jayashree Kalpathy-Cramer (UColorado Anschutz), Judy Gichoya (Emory University), and Laura Coombs (ACR®)

COVID pneumonia machine learning algorithm validation and visualization.

Updated January 20, 2023


Screen Shot 2021-07-23 at 1.02.14 PM.png

Investigators have been working on creating a validation a dataset using MIDRC data from diverse locations to validate and compare available COVID classification algorithms on chest x-rays for clinical effectiveness. They have also been developing open source visual analytic tools that a) allow radiologists to perform subset analyses to look for biases in the COVID classification model and b) can evaluate the effect of changing thresholds on model performance.

Current plans include

  • Examine whether imaging findings (CXR) anytime during the course of the disease are associated with the likelihood of developing PASC. Examine whether long-covid findings from a single institution dataset (MGH) are genaralizeble to the MIDRC dataset

CRP5.jpg
Previous
Previous

CRP 4: Deep Learning of Echocardiography for Detection of Myocarditis Cardiac Injury ...

Next
Next

CRP 6: Safe public training dataset for COVID-19 machine learning algorithms