Electronic health record company Epic offers financial incentives to healthcare systems that use its proprietary algorithms – and those algorithms can provide inaccurate predictions, a New statistics survey found.
Epic is the largest electronic health records company in the United States and holds the health records of approximately 250 million people. The company has around 20 algorithms designed to predict things like how long a patient will stay in hospital, which patients could become seriously ill, and which could develop a fatal disease called sepsis.
Like many other groups that build health algorithms, Epic does not publicly share the details of how the algorithms are built. Researchers at hospitals that use Epic are able to scrutinize the tools, but any investigation is difficult: they cannot disclose confidential information and may fear complicating their employer’s relationship with the company if they publish. negative results, New statistics reported.
Studies that have been done on algorithms show that they often do not work as well as advertised. An analysis of the sepsis algorithm, which Epic says works 76% of the time, found it was only correct 63% of the time.
Despite the problems with the algorithms, Epic is pushing hospitals to adopt them. The company’s “honor roll” program has awarded hundreds of thousands of dollars, and in some cases nearly $ 1 million, to health systems implementing technical upgrades, including algorithms. “It would be a terrible world where Epic gives people a million dollars, and the end result is patient health getting worse,” Glenn Cohen, director of the Petrie-Flom Center for Health Law Policy, Biotechnology, and Bioethics at Harvard. University, says New statistics. Financial incentives could create a conflict of interest.
“The Epic Honor Roll is a voluntary program that encourages adoption of features that help save lives, increase data exchange and improve satisfaction for patients, physicians and healthcare systems.” , Epic said in a statement to New statistics.
Some healthcare systems with robust financial resources and IT services are able to analyze Epic’s standard algorithms and adjust them according to their needs. Others, however, may not be able to examine the tools as closely. “The less sophisticated hospitals that don’t have the big data teams are also the ones where $ 1 million is likely to make the biggest difference,” Cohen said.