American firms are interested in the new AI-powered algorithm that has already identified approximately 40,000 patients in Israel at the highest risk for complications and targeted them for fast-tracked testing and treatment.
By Yakir Benzion, United With Israel
An Israeli HMO has deployed a new AI-powered algorithm that identifies individuals who meet the criteria for being in the highest risk group for severe coronavirus complications, allowing hospitals and medical systems to fast-track them for testing and treatment.
Maccabi Healthcare Services, Israel’s leading HMO with 2.4 million members, was developed by Maccabi’s research wing in partnership with an Israeli high-tech company Medial EarlySign in Hod Hasharon, just north of Tel Aviv.
While Maccabi is a large HMO dealing daily with medical care for its members, Medial EarlySign’s founders are a mathemetician and an engineer whose experience in dealing with big data led them to apply advanced mathematical algorithms and machine learning technology to the healthcare sector.
People with pre-existing conditions and other health factors are known to be among the most endangered by COVID-19. Maccabi says the new algorithm has already identified the top 2 percent of the highest-risk patients and identified some 40,000 of its members by a deep analysis of all Maccabi patients’ anonymized electronic health records.
Medial EarlySign has already developed machine learning-based technology solutions that aid in the early detection and prevention of other high-burden diseases.
Maccabi said it is currently in advanced negotiations with prominent medical systems in the United States who are interested in the algorithm as part of their COVID-19 healthcare protocols.
“The world is currently at war with COVID-19 and our algorithm, developed together with EarlySign, will help us fight the virus effectively,” Maccabi CEO Ran Sa’ar said. “The algorithm and the fast-tracked testing it enables will reduce the number of severe COVID-19 cases and help save lives.”
The software processes all the patients in an organization’s database and flags high-risk patients. If one of those patients calls to report COVID-19-like symptoms, the system automatically notifies the medical professional that the patient is in the high-risk group and they can be sent for immediate testing.
In Israel, the tests are performed at designated Maccabi facilities, drive-in stations or, if necessary, in the patient’s home. This allows for medical procedures to begin as quickly as possible following a positive diagnosis, helping to limit the spread of the virus.
The algorithm analyzes dozens of routine medical factors including age, weight, body mass index, hospital admission history, medication history, smoking, and medical history including heart or respiratory diseases and diabetes.
The new software also classifies patients according to three levels of estimated risk and help the decision making process to keep the patient at home, move them to a designated COVID-19 quarntine center, or admit them to hospital.
Prof. Varda Shalev, director of the Kahn-Sagol-Maccabi Research and Innovation Institute, said having 27 years of patient data allowed them to show how deep analysis of the big data of anonymized electronic health records (EHRs) could be optimized help fight the pandemic.
“Early identification of those at greatest risk is crucial to supporting healthcare professionals and to flattening the curve of the pandemic,” she said.