HONG KONG – Israeli companies have produced some promising med-tech solutions for COVID-19, and the artificial intelligence space is turning out to be a particularly strong area of expertise for that tiny but mighty nation.
One of the four health maintenance organizations (HMO) in Israel, Maccabi Healthcare Services, has deployed a new AI-powered algorithm that identifies individuals estimated to be at the highest risk of severe COVID-19 complications due to pre-existing conditions and other health factors.
The algorithm was developed by health care solution provider Medial Earlysign Ltd. and the Kahn-Sagol-Maccabi Research and Innovation Institute.
“The world is currently at war with COVID-19 and our algorithm, developed together with Earlysign, will help us fight the virus effectively,” said Ran Sa'ar, the CEO of Maccabi Healthcare Services, in a statement. “The algorithm and the fast-tracked testing it enables will help reduce the number of severe COVID-19 cases and help save lives.”
The algorithm draws on Maccabi’s big data and then uses an analysis of dozens of routine medical factors to determine high-risk patients, such as their age, BMI, hospital admission history, respiratory disease incidence, medications prescribed, etc.
Once a person that has been flagged by the algorithm as high-risk reports COVID-19-like symptoms to a health care professional, the system will automatically alert the staff that the patient is in the high-risk group.
Then, the individual will be immediately sent for testing at either designated Maccabi facilities, drive-in stations or in their own home if necessary. This allows for quick medical intervention if a positive diagnosis follows, thus helping to contain the spread of the virus.
“As one of the largest HMOs in the world with 2.4 million members and 27 years' worth of electronic health records, Maccabi's algorithm relies on big data from one of the largest and highest-quality collections of anonymized EHRs in the world,” said Varda Shalev, director of the Kahn-Sagol-Maccabi Research and Innovation Institute.
“Early identification of those at greatest risk is crucial to supporting health care professionals and to flattening the curve of the pandemic," she added.
In building the new algorithm for COVID-19, Medial Earlysign utilized numerous aspects of its Flu Complications Algomarker that process medical data to provide risk assessment scores.
"Based on anonymized data collected from millions of people treated by Maccabi, our models were adapted and optimized according to existing medical knowledge and known risk factors relating to COVID-19,” said Jeremy Orr, the CEO of Medial Earlysign.
Orr said that the data from Maccabi is being continually updated, allowing them to improve the new algorithm.
The organizations involved did not respond to BioWorld’s queries regarding future plans for the algorithm.
Using AI for speech recognition
Meanwhile, another Israeli start-up, Cordio Medical Ltd., is currently testing its speech pattern recognition technology, which may be able to diagnose and remotely monitor COVID-19 patients at Haifa’s Rambam Hospital.
Cordio's technology was initially developed for the remote monitoring of heart failure patients. Its Hearo product works by analyzing recordings of a patient's speech recorded via a mobile device and detecting fluid collection in the lungs, which can be indicative of congestive heart failure.
Cordio has adapted this technology to identify the bilateral pneumonia with edema in the lungs that is characteristic of COVID-19. The startup says it can detect changes in lung fluids and the onset of inflammation even before patients themselves can.
Cordio believes remote diagnosis and monitoring will help with the problem of limited hospital beds and reduce health care staff infections.
The company expects the technology to reach tens of thousands of diagnosed patients in Israel within a few weeks. And it aims to establish a fully operational network within two months, once its efficacy has been proven.
There are now plans to conduct validation studies at leading U.S. institutions, but no further details have been revealed.
Next up to bat
Another Israel-based company, Bat-Call Ltd., is also tapping its AI and sound-based technology to support the early detection and monitoring of COVID-19 patients.
“Our device detects both body sounds and body infra-sounds. It is the only device in the world that analyzes body infra-sounds – clinical data that is not used by the medical community,” Doron Adler, the CEO and co-founder of Bat-Call, told BioWorld.
Adler expects to fully adapt the company’s pneumonia detection classifier “in a matter of few weeks” and to get expedited approvals for its stethoscope-like diagnostic.
However, even with the explosion of tech-driven solutions against the pandemic, authorities are taking precautions.
On April 26, Israel’s Supreme Court ruled that the government must bring its current practice of using mobile phone tracking data against COVID-19 into the legal domain. This means that Israeli authorities must launch prospective legislation by April 30 and pass it within a few weeks if it wants to continue tracking people's phones in its bid to contain the virus.