In an op-ed published May 28 by Fast Company, Drs. Khetpal and Shah, an internal medicine physician and an assistant professor of medicine at Brown University, respectively, explained the emergence of Epic’s Deterioration Index model during the pandemic and how it could change how physicians practice medicine.
Five insights from the article:
1. Epic had been developing the index for years, and some hospitals were using the tool before the pandemic, but the EHR company expanded it to help health systems triage COVID-19 patients.
2. The index works by analyzing factors such as patient breathing rate and blood potassium level to determine low-risk patients and those who are at high risk of needing to be transferred to an intensive care unit, getting placed on a ventilator or dying while being admitted to the hospital.
3. Drs. Khetpal and Shah wrote that the index is different and proprietary because it was widely launched before rigorous peer review; although physicians are given a list of the variables used “to calculate the index and a rough estimate of each variable’s impact on the score, [they] aren’t allowed under the hood to evaluate the raw data and calculations.”
4. Because the tool wasn’t independently validated or peer-reviewed before being rapidly deployed to hospitals and health systems, it remains unclear if there are any biases encoded in the index, such as underestimating the pain of minority patients, according to the article authors.
5. Drs. Khetpal and Shah wrote that Epic should immediately release the underlying equations and anonymized datasets it used for its internal evaluations of the index so that physicians and researchers can “better understand any potential implications they may have for health equity.”
Editor’s note: Epic did not respond to Becker’s request for comment.
