Nov. 11, 2021 -- To get people with COVID-19 the most appropriate care – and to limit the number of patients with milder disease coming to acute care centers– researchers at the University of Pennsylvania devised an online, automated symptom triage system.

How and why they developed the publicly available tool, and how well the technology agrees with triage of the same COVID-19 patients by doctors and nurses, is highlighted in a study published Nov. 3 in Applied Clinical Informatics.

The technology is not meant to replace provider judgment, "but rather to offer a way to safely offload clinical volume," co-lead study author Elana Meer, a researcher and an MD/MBA student at the Wharton School at the University of Pennsylvania, says.

"We hope that by improving our screening and triage mechanisms, we would actually help physicians have more time to spend with patients that need the physician’s knowledge, experience and clinical judgement," she says.

Meer and her colleagues found the triage by the tool and providers agreed 29% of the time. But that's not the full story.

The technology was designed to be conservative and err on the side of patient safety.

"We wanted a false negative rate -- meaning the chance that the tool would suggest a patient stay home when in reality they needed to seek care -- to be basically zero," Meer said.

In an additional 70% of cases, the symptom checker assigned a higher clinical severity than the clinician who later managed the patient, Meer says. In these cases the provider was able to safely "down-triage" the patient to a lower level of COVID-19 severity.

"From our standpoint, this was a win," Meer says. "The symptom checker successfully flagged almost all patients of concern and made reasonable and appropriately conservative referrals to expert clinicians in over 99% of cases."

Only six patients were 'up-triaged' by a doctor or nurse to a more severe category.

These results are based on a group of 782 people who completed both the online triage assessment and later consultation with a provider via a traditional phone triage call.

A Good First Step

There is a "huge need for an accurate triage tool," and this is a "good beginning," Theresa Cullen, MD, public health director from Pima County, AZ, said when asked to comment on the study.

"This tool can be perceived as an initial step in developing an accurate triage tool," she says.

If and when 70% of patients triaged to a higher level of care than needed seek such care, she added, it could strain resources and have an overall "potential negative impact on accessibility to clinical care."

Majority of People Asymptomatic

The comparison was limited to people assigned a moderately severe level of COVID-19 illness by the triage tool. People in this group were told to call the phone triage line at University of Pennsylvania. In contrast, people assigned a low or high disease severity received other instructions. For example, those classified with severe disease were told to call 911 or seek emergency care in person.

The triage tool was used 30,321 times by 20,930 unique patients between its launch on May 4, 2020 and Jan. 31, 2021.

Of the 30,321 completions, the tool classified 51.7% people as asymptomatic, 15.6% as low severity, 21.7% as moderate severity and 11.0% as high severity.

Not Your Typical Online Symptom Checker

The tool differs from online symptom checkers, Meer says.

"Internet resources can often triage patients’ needs inaccurately, generating worry among patients and unnecessary visits to the emergency room or hospital," she says. Instead, well-designed triage tools "could facilitate the patient receiving care from the right provider, at the right time, from the right location, or appropriately managing their symptoms at home."

Furthermore, the University of Pennsylvania tool could save time. The technology saves information using a unique code, so when a patient subsequently calls or visits the health system, providers do not need to start from scratch.

About 65% of online triage users were female and about 60% were younger than 40.

Cullen would have liked to see more older participants in the study. She pointed out that "only 13% of patients were over 61, even though a high risk for COVID-19 morbidity and mortality is increasing age, so utilization of this tool with those over 65 would be important."

Interestingly, the researchers note that "racially, demographics of the tool’s users nearly matched those of the Philadelphia metropolitan area, which was reassuring in the context of concerns that lack of access to internet resources may disproportionately impact people of color."

Triaging Other Patients Possible

The findings of this study could apply beyond COVID-19, the researchers note. After some upfront work on algorithms and testing, "similar triage tools could really be applied in any clinical setting," Meer says. "For example, a tool based on a similar premise was applied to the ophthalmology department to help triage patients presenting to acute care clinic with concerns.”

Rigorously validated triage tools can offer multiple advantages, Meer says. "Patients may benefit by gaining immediate access to accurate, vetted information. Health systems may benefit by offloading call centers and triaging patients so providers can focus their time, which is becoming increasingly limited, on patients who are most likely to benefit from a conversation or their care."