In another demonstration of the power of AI, researchers recently reported detecting COVID at an early stage before symptoms appeared simply by analyzing data from wrist-worn health trackers. What challenges does COVID present, what have researchers demonstrated, and how will health monitoring benefit from AI?
What challenges does CODIV present?
Now that the pandemic is all but over, COVID appears to be like any other cold virus that is virtually impossible to eliminate and will play a part in everyday life. As most people on the planet have been infected and/or vaccinated, there is no longer a need for COVID restrictions or the use of PPE, as those who survived now have antibodies.
But when COVID first emerged, it posed a serious threat to the world for many reasons. The first was that, unlike cold and flu viruses, COVID was a unique virus in that it had never interacted with the general population before. This meant that no natural protection method in the form of antibodies was available, and it meant that anyone who caught COVID had to effectively create their own vaccine via an immune response (and that immune response could be delayed when the body tries to identify the virus).
Second, in trying to respond to the virus, COVID has a bad habit of causing fluid to build up in the lungs. This allows the bacteria to cause a secondary infection leading to pneumonia, and it is this pneumonia that often leads to death.
Third, and probably most unfair, COVID is asymptomatic for a large percentage of the population, allowing it to spread extremely quickly. Moreover, COVID will not even show symptoms in those who are vulnerable to it for a long time (up to a week possible). Thus, COVID is virtually impossible to track and stop without using robust PPE methods, isolation, and frequent disinfection of surfaces, hands, and clothing.
Even though the COVID pandemic is now mostly over, it is still possible for new aerosol viruses similar to COVID to spread around the world, creating new pandemics. Although lessons have been learned regarding highly infectious viruses, preventing further pandemics will remain challenging.
Researchers demonstrate how wrist-worn health trackers can detect COVID early
In order to be able to prevent the spread of future viruses like COVID, it will be essential to identify those who carry them and isolate them to prevent further spread. The use of PCR tests and antigen tests can be used to confirm cases, but as COVID has demonstrated, trying to routinely test an entire population is difficult. Also, testing only people with symptoms does not identify infected people but have no visible symptoms.
Recognizing the challenges presented by COVID, researchers have recently developed methods for early detection of COVID, and one team may have had success with the use of off-the-shelf health trackers. Although the symptoms of COVID are not obvious, the body will still experience small changes that can be detected by wrist-worn health trackers with examples of minute changes including heart rate, sweating and blood pressure .
Of course, changes in any of these readings cannot automatically indicate COVID and trying to use traditional hard-coded statements to determine whether or not someone has COVID just doesn’t work. As such, researchers have turned to AI to detect symptoms, as AI can train itself to look for patterns that may not be obvious.
To train their AI, the researchers collected more than 1.5 million hours of data from 1,163 people under the age of 51 using Ava wristbands that work at night. These wristbands connect to a smartphone which also tracks prescription usage, activity and alcohol consumption. Finally, all participants were regularly subjected to PCR swab tests to identify those infected with COVID. The result of this trial showed that the AI could identify 68% of people who had COVID 2 days before the onset of symptoms.
Now the AI is being tested on a much larger sample of 20,000 people across the Netherlands to identify the accuracy of the AI and see if it continues to work after initial infections (as secondary infections can present weaker symptoms and therefore be more difficult to identify) .
How will health monitoring and AI improve medical science?
There are clearly significant advantages to using AI in medical diagnostics, including the ability to control infections, identify diseases at an early stage, and help doctors deliver the right treatment. But above all, AI in medical sciences will most likely be beneficial for enabling people to self-diagnose and self-medicate.
A good example where this would be very beneficial is skin cancer and moles. It’s highly likely that the vast majority of the population can’t identify potentially dangerous moles, and it’s even more likely that people don’t track the size of their moles or their location. Instead, people often rely on someone else to spot a mole, or a doctor to spot a mole, or a doctor to do a physical examination of their body, and whoever uses the NHS will know that the NHS never does anything without being harassed.
But, imagine a tanning bed-like machine that could photograph every inch of skin on the body, and that data is then fed into an AI that maps all moles, tracks their size, and compares them to malignant moles. known? Such a system could detect problems early and turn a 3-year battle with cancer into a 20-minute session with a nurse and a scalpel to remove the problematic mole.
The best part about an AI doctor? It would be almost free to operate, and it would only get better with time. Readings taken from each AI system can be used to further train the AI to recognize symptoms, and the use of software means the only real cost is the electricity needed to run the AI . Of course, additional costs would come in the form of machine rental, processing time, and licensing, but given that researchers have already demonstrated working AI diagnostic systems, it’s likely that such a system would be very cheap to operate.
Overall, AI is an extremely powerful tool that could revolutionize the medical field, and the use of AI diagnostics could cut out the middleman (i.e. GPs) and help patients to connect directly to specialists.