Of all the EHR problems encountered daily across the country, the only one to hit the major news outlets was a non-story about a missed Ebola diagnosis in Dallas, Texas. Before being retracted, the hospital’s claim of an Epic failure launched a slew of commentary in the health IT field. These swirled through my head last night as I tried to find a lesson in the incident.
The facts seem to be as follows. A 42-year-old man named Thomas Eric Duncan arrived from Liberia and checked in to the emergency room at Texas Health Presbyterian Hospital Dallas complaining of symptoms consistent with an Ebola diagnosis. He told the admitting nurse he had come from Liberia, and the nurse entered the data into the Epic EHR.
The purpose of recording the patient’s travel history, however, seemed to be simply to determine the need for immunizations, so the EHR kept it within a nurse’s section of the data (which the hospital called a “workflow”) and did not display it to the doctor. The doctor sent Duncan home, where he came into contact with about 100 people who were potentially infected. His symptoms worsened and he returned to the hospital two days later, where he was finally diagnosed correctly and admitted.
Late night musing #1: If Texas Health Presbyterian Hospital Dallas can’t diagnose a case of Ebola, why do they think they can treat one? The hospital has won numerous awards, including one for patient safety–I guess you’re safe once you’re admitted.
Meanwhile, the city of Dallas waited several extra days to clean up infected sheets and other belongings from the Duncan home. In Africa, such detritis are recognized as a major source of new Ebola infections.
Late night musing #2: Does this reflect the competence of public health officials in this country? Maybe we should turn the job over to the Secret Service.
It’s really a shame that the national press jumped on the hospital’s announcement that the EHR was the source of the problem. Commenters criticized the hospital right away, asking why the nurse didn’t simply tell the doctor, and why the doctor didn’t ask on his own.
Finally, the hospital backed off from blaming Epic, thus making the hospital look even stupider and more guilty than it already appeared. Nevertheless, EHRs at some hospitals may be designed to flag warning signals.
Clearly, there are many layers to this health care failure. I don’t blame the nurse, or even the doctor. ERs are always busy, and the nurse might never have known who would see the patient or even be in the ER when the doctor finally saw him.
But I do find a small lesson in the brief appearance of the EHR as a pivotal character in the story. The nurse thought he or she was doing their job just by entering the data into the EHR, and the doctor thought he was doing his job by reading it. The EHR had loomed as a magical solution to health care workflow–in the minds of hospital administrators, if not the ER staff.
Maybe if the nurse knew that the travel history was for the purpose of immunizations, he or she would not have relied on the EHR to use that information for diagnosis. Besides showing the need for training, some of my colleagues suggest that this problem calls for FDA regulation of EHR interfaces. They also suggest that systems use good user interface design to highlight important information (which would require a definition of what’s “important”) or at least allow searches for critical elements of the record.
Late night musing #3: Behind this also lies the mindlessness of much data collected by EHRs. I’m sure the nurse knew whether the unfortunate Mr. Duncan was a smoker and whether he suffered from depression, because regulations require these things to be recorded. Travel history became just another one of these automatic requirements to be tossed into the EHR and forgotten.
My story also concerns the musings of other health IT commentators, who suggested that EHRs be better integrated into “workflows”–as if every clinician follows a mechanical path of treatment and the EHR can figure out what it is.
Another thoughtful posting calls for integrating infectious diseaess into clinical decision support. But as my colleague Sandra Raup (R.D., J.D., M.P.H.) points out, CDS depends on a long history of clinical data collection. One can’t instantly add a new disease.
It might have been useful for some international health organization to realize, when the Ebola outbreak began to spread, that it would eventually break out of central Africa, and then to provide an app to hospitals around the world for checking symptoms and travel history. There is certainly a creative role for health IT to play.
I think the messiness of the Texas Health Presbyterian Hospital Dallas story shows why EHR failures, numerous as they are, don’t get reported in the press. There are just too many complicating factors. The EHR is partly configured by the clinic’s staff, who thereby become responsible for some of its decisions. The EHR failure usually comes when the staff is under stress, when they have communication problems, when the patient’s condition is rare. Ascribing blame becomes a tangled mess; one must start designing systems with multiple, redundant points to catch failures that can fall through the cracks.
So one level, this is just another sad story of humanity’s tendency to trust too much in its technology, a story that ranges from the flight of Icarus to the sail of the Titanic and the failure of the Fukushima Daiichi nuclear power plant. On other, it’s a familiar story of a systemic problem leading to what’s sometimes called a “normal failure.” Not much new to learn, but lots of work to do. Clinicians have to evaluate EHRs and know how the data is used, a more open system in all directions.