Study on Surveillance of COVID-19 Using Smart Wearable Devices
This article is about an Early Detection Method along with regular remote surveillance and assessment of COVID-19 infected patients using smart wearable devices. It will help the patient to regularly analyze his/her condition by constantly monitoring physiological parameters with the help of a smart wearable device also resulting in Remote Monitoring and Virtual Assessments of patients by the medical staff.
At present, this technology may be particularly useful, as more patients with mild symptoms of COVID-19 are being asked to stay at home and report changes in their respiratory symptoms via telemedicine modalities in an attempt to reduce the spread of the disease.
These devices will notify wearable device users of any possibility of infection before they develop any clinical symptoms by collecting information on various physiological parameters. An Artificial Intelligence and Machine Learning based algorithm will notify the wearable device user about any abnormalities it observed in the physiological parameters and inform them to self-isolate themselves, seek care and go for diagnostic testing, and take other steps to mitigate the transmission of the infection. In addition to that these wearable devices can also be used for remotely monitoring the patient by allowing patients to report their vitals from home, saving critical hospital resources, and reducing the risk of transmission to health care providers by avoiding in-person assessments. Remote patient monitoring using wearable sensor technology provides an opportunity for developing more effective patient interventions, balancing nurse-patient care ratios, and decreasing costs associated with readmission rates and futile medical care.
COVID-19 leads to significant, metabolic changes, systemic mitochondrial dysfunction, considerable muscle wasting, and loss of function throughout the illness and during recovery. These metabolic needs will initially decrease in acute infection and subsequently increase as patients face the transition from the acute phase of COVID illness to the recovery phase. COVID-19, just like other viral illnesses, is associated with several physiological changes that can be monitored using wearable sensors. An explainable AI model can be trained, having as input the physiological parameters measured by the device and check for any abnormalities in the readings. This would allow physicians to anticipate the severity of the disease and, therefore, select the best clinical management of the patient including hospital admission, type of treatment, and ICU transfer in advance. This data will also guide nutrition and metabolic/clinical care in all stages of COVID-19 care. Digital health technologies that measure physiologic parameters can be leveraged to help identify population clusters to identify an emerging COVID-19 outbreak.
The physiological parameters that can be measured by wearable devices include heart rate, sleep, blood oxygen saturation, electrocardiogram, and exercise records. These will be continuously collected from the day of admission. The primary outcome of the AI model will be to analyze the deterioration of the disease and its correlation with the change of physiological parameters. This correlation between various physiological parameters can also be used to early detect the symptoms of COVID-19.
Many physiological metrics derived from heart rhythm such as heart rate (HR), heart rate variability (HRV), resting heart rate (RHR), and respiration rate (RR) could serve as potential markers of COVID-19 infection and are already measured by some wearable devices such as the Apple Watch, WHOOP Strap, Fitbit, Zephyr BioHarness, or VivaLNK Vital Scout. Many wearables report more complex metrics such as stress, recovery, activity, and sleep, which are typically calculated using a combination of cardiac and accelerometer-derived metrics. Due to the integration of multiple measurements, these metrics should exhibit an aggregate higher signal-to-noise ratio (SNR) than individual raw signals alone and, therefore, have higher predictive value. Core body temperature and arterial oxygen saturation (SpO2) are also of clinical value due to the high prevalence of fever and respiratory symptoms in COVID-19.
Real-time monitoring of the physiological factors such as HR, HRV, SpO2, Temperature, RR, and Cardiovascular stress and analyzing them using an AI and ML-based algorithm will help us to detect COVID-19 at its pre-symptomatic stage. This will also allow the medical practitioners to easily keep records of the patients when they are in-home quarantine. These physiological changes measured by wearable devices can potentially be detected before a user experiences any significant clinical symptoms of illness. The primary outcome of an AI and ML-based algorithm will be to find the deterioration of the disease and its correlation with the changes in physiological parameters shown by wearable devices.
We believe that Artificial intelligence can revolutionize, subsidize, and extend the reach of our ageing healthcare system. Artificial Intelligence can prove to be humanity’s greatest asset in its fight against COVID-19.
For more stories and information about AI and Machine Learning based ongoing research areas and recent developments in AI, you can follow me on Medium.
