Israel Uses AI to Help Identify People Most at Risk of COVID-19

Maccabi Healthcare Services, one of Israel’s largest health maintenance organization covering 2.4 million people, developed a system with AI company Medial EarlySign to identify people most vulnerable of covid-19. It has flagged 2% of its members amounting to around 40,000 people who have been put on a fast track for testing. The AI was adapted from an existing system trained to identify people most at risk from the flu. The predictions are based on a wide range of medical data: a person’s BMI, age, health conditions such as diabetes or heart disease, and any prior history of hospital admissions. The AI can process through a huge number of records and highlight “at risk” individuals who might have been missed from any manual analysis. It also uses the AI to help determine the level of treatment needed if patients fall sick, whether they should be cared for at home, put up in a quarantine hotel, or admitted to hospital. But exporting such a tool to other countries is limited due to the lack of data sets. Recent rules in the US support secure data transfer between hospitals and could make patient data more accessible.