AI-Driven Ruleset Helps Detect COVID-19 Novel Coronavirus in Patients

Persivia (Marlborough, MA), a provider of real-time bundled payment, value-based care, population health, and quality management solutions, has launched a new COVID-19 surveillance module within its Soliton AI engine. Delivered as part of its CareSpace platform, the module uses data from multiple sources to identify patients who could be infected with COVID-19 novel coronavirus. Given the shortage of tests for COVID-191, the ruleset will help healthcare professionals more effectively target patients who need to be tested.

Persivia partners with hospitals and practices to help manage value based care programs, quality, care and risk in both inpatient and ambulatory environments. Its Bundled Payment solution can follow a patient from admission thru post-acute stays and into the home. The company’s Care solutions help improve care delivery and quality scores for at risk providers, while helping increase revenue in FFS models and its value based solutions help improve MIPs scores and help ACOs and CPC+ practices control costs and achieve the maximum bonuses and incentives. Persivia’s Quality solutions cover everything from IQR, TJC and MU CQMs to MIPS, ACO, CPC+ and commercial CQMs.


Persivia’s new Soliton module targets suspected COVID-19 cases by processing structured and unstructured data that the company acquires and normalizes from disparate sources, including real-time EHR data. The Soliton AI engine uses evidence-based algorithms to identify specific concepts and keywords in structured and unstructured data to identify potential cases of interest. Patients who are identified as having three or more relevant symptoms, as identified by CDC guidelines, such as fever, shortness of breath, and cough, are flagged with a level one alert. At this lowest level, the patient's physician is prompted to educate the patient about COVID-19 and monitor their status. If Persivia also identifies a travel or exposure history the alert gets raised to a level two, where a CDC test is recommended. Patients receive a level three alert when they are presumed positive for COVID-19 and level four when they are confirmed with symptoms. Medical professionals are also able to search for all patients flagged as possibly having COVID-19, and can filter them by alert level and symptoms. Over the coming weeks and months, Persivia will be able to adapt and add to the ruleset as it finds out more about the disease, its symptoms, and progression.

"In 2014, the medical world received a rude awakening about the fallibility of our fragmented healthcare system when a man with Ebola symptoms was erroneously discharged from the hospital," said Fauzia Khan, MD, Persivia's Chief Medical Officer. "The inability to match the documentation of travel history in the intake nurse's notes with the symptoms coded by the physician was a flaw – one we have bridged with our ability to create evidence-based rulesets within CareSpace. CareSpace is built to acquire, aggregate, and normalize data from multiple sources which ensures it doesn't miss any piece of recorded information about a patient from anywhere along the care continuum. This is critical when it comes to public health threats. We hope our ruleset will help healthcare organizations across the country identify the novel coronavirus in patients more quickly and effectively, leading to more appropriate testing, timely care, and better health outcomes."

Related Links:
Persivia