Researchers highlight Epic Deterioration Index lack of transparency 

The EPIC Deterioration Index, which helps identify when to move a patient in or out of intensive care, was only moderately successful in differentiating low-risk and high-risk patients, according to researchers.

Physicians Vishal Khetpal, MD, and Nishant Shah, MD concluded that a research study involving 392 Covid-19 patients found that the Deterioration Index was moderately successful in discriminating between low-risk patients and those at high risk of ICU transfer, ventilation, or death.

Rolled out at speed during the COVID-19 pandemic, the Epic Deterioration Index (EDI) is a propritary machine learning algorithm developed by private electronic health record company Epic Systems that helps identify when to move a patient in or out of intensive care. Epic is said to hold over 250 million patients' electronic records in the US, and has been taken up by hundreds of hospitals across the US. 

However, despite general concerns about medical system accuracy and bias, Epic chose to limit expert access to raw data and equations and failed to have the system independently validated or peer-reviewed before launch, the reseachers said.

The finding raised questions about Epic System's governance and commitment to transparency and accountability, as well as about the EDI's accuracy and reliability.