What if a fitness tracker sitting on your wrist could detect COVID-19 even before you developed symptoms? An impressive new study claims that it is not only possible, but preliminary investigations have found that infection can be detected approximately 48 hours before symptoms appear.
New research began in early 2020, shortly after the pandemic began. A team of researchers wondered whether data from a wrist-worm health tracker could be used to pick up on small changes in a person’s vital signs that precede the onset of COVID-19.
Nearly 1,000 young participants were recruited from an ongoing observational health study and were provided with a commercially available wrist-worn device known as an Ava bracelet. The device is worn at night and measures heart rate, breathing rate, skin temperature, heart rate variability and blood flow every 10 seconds. It is commonly used as a form of fertility monitoring because of its ability to track real-time changes to these five health measures.
During the one-year-long study, 11% of the cohort came down with a laboratory-confirmed case of COVID-19. About half of those COVID-positive subjects had a good month’s worth of wearable data before their infection, allowing researchers to develop an algorithm that could detect small changes in the early stages of the disease.
All five measures recorded by the wearable found noticeable changes in the days before COVID symptoms appeared. Notably, heart rate changes, heart rate variability and wrist skin temperature were the most important early features of COVID-19, the first noticeable symptoms.
A novel machine-learning algorithm was trained on 70% of the COVID-positive cohort and then tested on the remaining 30%. Notably, the algorithm accurately caught 68% of the positive COVID cases two days before any symptoms appeared.
“Wearable sensor technology is an easy-to-use, low-cost method to enable individuals to track their health and well-being during a pandemic,” the researchers conclude in the new study. “Our research shows that these devices, partnered with artificial intelligence, can push the boundaries of personalized medicine and detect diseases earlier than SO” [symptom onset]potentially reducing virus transmission in communities.”
The idea that health wearables can detect infectious diseases before any tangible symptoms appear. A fascinating study published last year tested the idea on influenza and the common cold.
That research actually infected several dozen young volunteers with rhinovirus, or H1N1, and then tracked a number of health measures over the following days using a fitness tracker. The study not only established that infections can be predicted using wearable health data approximately 24 hours before symptoms appear, but the severity of subsequent infections can also be predicted with about 90% accuracy. Is.
The ability to detect infections by combining advanced algorithms with real-time health data from wearables is promising, said David Conan, an author of this new COVID-detection study. His team is now conducting a larger study of the COVID-detection system in 20,000 subjects. The results of that investigation are expected later this year.
“that an existing medical device can be used in a different sense [shows] Wearables have a promising future,” Conan said. “It’s not just related to COVID, in future diseases, it could also lead to preventive treatments and prevent significant complications.”
The new study was published in the journal BMJ Open,
Source: McMaster University
Source
