One of Israel’s largest health maintenance organizations is using AI to assist identify which of the two .4 million people it covers are most in danger of severe COVID-19 complications. Maccabi Healthcare Services says the system—which it developed with AI company Medial EarlySign—has already flagged 2% of its members, amounting to around 40,000 people. Once identified, individuals are placed on a quick track for testing.
The AI was adapted from an existing system trained to spot people most in danger from the flu, using many records from Maccabi going back 27 years. to form its predictions, the system draws on a variety of medical data, including a person’s age, BMI, health conditions like a heart condition or diabetes, and former history of hospital admissions. The AI can trawl through a huge number of records and spot at-risk individuals who may need to be been missed otherwise.
Maccabi also uses the AI to assist determine the extent of treatment the people it flags might require if they fall sick—whether they ought to have cared for the reception , put up during a quarantined hotel, or admitted to hospital. The organization says it now lectures major US health providers that have an interest in using the AI to fast-track their own high-risk patients.
Using AI to spot vulnerable people could save lives, says Darren Schulte, an MD and CEO of AI firm Apixio, which develops software to research unstructured medical data, like doctors’ notes. Schulte thinks the Maccabi tool could even be wont to isolate high-risk members of the population when lockdown measures are relaxed, perhaps moving people into special housing faraway from relations who could also be undiagnosed carriers of the virus.
But bringing such a tool to other countries might not be straightforward. In the US, medical records are locked up inside many various health-care systems. “Our ability to develop algorithms to spot individuals as high risk is restricted by the shortage of knowledge sets,” says Schulte. “Even in my City, I think it’s a challenge to craft one data set that brings together patient information across the massive hospitals.”
The COVID-19 pandemic might change this, he believes. He notes that recent rules introduced by the Office of the National Coordinator for Health Information Technology, a division of the United States government liable for health-care IT, support secure data transfer between different hospitals. “We just need providers to form patient data accessible,” he says.