Online symptom checkers unreliable for COVID-19 triage

Though promising, coronavirus disease 2019 (COVID-19) symptom checkers—online, patient-led triage systems—are unable to reliably distinguish mild from severe COVID-19 and may instead put the public and healthcare workers at greater risk of infection, according to a recent study.

“Beyond the patient safety concerns, there is no evidence that COVID-19 symptom checkers reduce the healthcare burden associated with the pandemic,” the researchers said. “Our results suggest, by delaying the presentation of time-critical cases to medical care, it is quite likely the … symptom checkers increase the healthcare burden associated with the SARS-CoV-2 pandemic.”

The present analysis looked at six symptom checkers deployed nationwide (in Singapore, the US, England, Wales, Scotland, and Northern Ireland) as triage tools, testing them against 52 simulated COVID-19 cases of various severities, presentations, and patient factors. The outcome was total referral ratio, defined as the proportion of cases referred for clinical contact regardless of level.

Of all symptom checkers, the one used in Singapore had the highest referral ratio and recommended that 100 percent of the simulated cases proceed to clinical contact. Singapore was followed by the US (67 percent), Wales (65 percent), England (62 percent), and Scotland (54 percent). Of note, the national symptom checker of Northern Ireland referred less than half (46 percent) of cases to clinical contact. [BMJ Health Care Inform 2021;28:e100448]

Looking at the specific features of each symptom checker, the researchers found that Singapore’s checker refers all patients for a same-day assessment, directing them to any of the country’s public health clinics. Meanwhile, those who report any degree of breathing problems are advised to contact emergency care.

In the US, the symptom checker took age into consideration. All patients older than 65 years with suspected COVID-19 were referred for medical contact regardless of assumed severity or other comorbidities. On the other hand, patients under 65 years of age with mild or moderate shortness of breath were advised to stay at home.

In contrast, except for Wales, all countries in the UK used symptom checkers that did not account for age. For instance, even older patients who reported fever and coughs for a week would be advised to remain at home without clinical contact. In Wales, suspected COVID-19 patients over the age of 70 were advised to call the national emergency number.

“Even during a period of low healthcare burden, the symptom checkers deployed by both the US and UK maintained a high threshold for onward referral. Neither symptom checker reliably triaged treatable, time-critical cases into healthcare contact or follow-up and were unable to consistently differentiate mild from severe COVID-19,” the researchers said.

“In the absence of any safety, efficacy, or quality assurance studies to support the use of symptom checkers as triage tools, our results necessitate a recommendation for … further analysis prior to their ongoing use in COVID-19 clinical care pathways,” they added.

“The stakes of patient triage are simply too high, and the reliability of symptom checkers is simply too poor, to justify their ongoing use,” the researchers said.