The Covid-19 pandemic has triggered a rapid surge of integration of new technologies into traditional healthcare. In order to contain and monitor the spread and have a better understanding of the virus, numerous medical companies are developing and integrating artificial intelligence (AI), machine learning (ML), and wearable technology into traditional healthcare. According to GlobalData forecasts, the market for AI/ML platforms will reach $52B in 2024, up from $29B in 2019.

One of the best ways to contain the COVID-19 spread is to warn asymptomatic individuals that they might be infectious. New Zealand-based company Datamine, specialising in AI, has created a personal early warning system, called ëlarm, that is able to identify Covid-19 cases up to three days before people knew they were infected. In New Zealand, the system has been operating successfully since last June. Wearable devices are able to track heart rate and other variables of the user. The ëlarm system gathers data from smartphones and wearables such as Fitbit, Apple Watch, and Samsung devices in order to create personal baselines of biometric data. In order to detect early signs of Covid-19 or other viral infections, the ëlarm system compares biometric changes of the user to the individual baselines that match Covid-19 patterns when the body starts fighting the infection.

Although baseline changes could indicate not only Covid-19 infection but a variety of other causes such as lack of sleep, dehydration, low blood sugar, anxiety, stress, and other viral or bacterial infections, it can help individuals to get tested and self-isolate even before symptoms appear, preventing the disease spread. Furthermore, ëlarm is not based on a specific smartwatch, allowing users to use the system with any kind of wearables. The ëlarm system shows that implementing AI and ML into the medical field can improve ways of diagnosing, managing, containing, and treating numerous diseases and health issues, and by analysing big data, it is possible to effectively analyse, process, and find new patterns in medical data.