If they know a person’s sex, age and address, researchers at Electronic Diagnosis and Surveillance (EDAS) Healthcare, an Israeli start-up company, can predict whether that individual will likely have COVID-19.
The company’s artificial intelligence (AI) technology grew out of research led by EDAS Healthcare’s co-founder and epidemiological analyst Dr. Gal Almogy and Prof. Ran Nir-Paz, a microbiology and infectious diseases expert at Hadassah Hospital Ein Kerem. “The idea is to model mathematically the way infectious diseases move through a community,” explains Guy Livne, chief executive officer and co-founder. He notes that the company was founded in 2018, and “by January 2019, we were already tracking 14 respiratory pathogens in the Jerusalem district, including three types of influenza.”
It took EDAS Healthcare just a week to add the coronavirus to its platform’s AI engine. To date, the diagnostic model has already been tested on more than 50,000 Hadassah patients under Prof. Nir-Paz’s supervision. Currently, the accuracy of its COVID-19 algorithm stands at about 62 percent, but its researchers are working to improve that percentage.
As Livne explains, “Our system doesn’t need symptoms. Just give us your age, gender and address in the Jerusalem district, and we can immediately say what pathogen you don’t have and what we suspect you have been infected with.”
He adds that using anonymous age, gender and address data, EDAS can help local municipalities manage risk in their school systems. For example, when the model identifies student classes that are at risk, the municipality can then close those classes and send its students and teachers for COVID-19 testing. Read the full story in Israel 21c.