E4

2 Articles

flow chart for Assessment of the Feasibility of Using Noninvasive Wearable Biometric Monitoring Sensors to Detect Influenza and the Common Cold Before Symptom Onset paper

Wearables Can Detect The Flu? Well…Maybe…

December 12, 2021 by 15 Comments

Surprisingly there are no pre-symptomatic screening methods for the common cold or the flu, allowing these viruses to spread unbeknownst to the infected. However, if we could detect when infected people will get sick even before they were showing symptoms, we could do a lot more to contain the flu or common cold and possibly save lives. Well, that’s what this group of researchers in this highly collaborative study set out to accomplish using data from wearable devices.

Participants of the study were given an E4 wristband, a research-grade wearable that measures heart rate, skin temperature, electrodermal activity, and movement. They then wore the E4 before and after inoculation of either influenza or rhinovirus. The researchers used 25 binary, random forest classification models to predict whether or not participants were infected based on the physiological data reported by the E4 sensor. Their results are pretty lengthy, so I’ll only highlight a few major discussion points. In one particular analysis, they found that at 36 hours after inoculation their model had an accuracy of 89% with a 100% sensitivity and a 67% specificity. Those aren’t exactly world-shaking numbers, but something the researchers thought was pretty promising nonetheless.

One major consideration for the accuracy of their model is the quality of the data reported by the wearable. Namely, if the data reported by the wearable isn’t reliable itself, no model derived from such data can be trustworthy either. We’ve discussed those points here at Hackaday before. Another major consideration is the lack of a control group. You definitely need to know if the model is simply tagging everyone as “infected” (which specificity does give us an idea of, to be fair) and a control group of participants who have not been inoculated with either virus would be one possible way to answer that question. Fortunately, the researchers admit this limitation of their work and we hope they will remedy this in future studies.

Studies like this are becoming increasingly common and the ongoing pandemic has motivated these physiological monitoring studies even further. It seems like wearables are here to stay as the academic research involving these devices seems to intensify each day. We’d love to see what kind of data could be obtained by a community-developed device, as we’ve seen some pretty impressive DIY biosensor projects over the years.

E4 Empatica device for measuring location, temperature, skin conductance, sleep, etc. on arm

Wearable Sensor For Detecting Substance Use Disorder

December 9, 2021 by 14 Comments

Oftentimes, the feature set for our typical fitness-focused wearables feels a bit empty. Push notifications on your wrist? OK, fine. Counting your steps? Sure, why not. But how useful are those capabilities anyway? Well, what if wearables could be used for a more dignified purpose like helping people in recovery from substance use disorder (SUD)? That’s what the researchers at the University of Massachusetts Medical School aimed to find out.

In their paper, they used a wrist-worn wearable to measure locomotion, heart rate, skin temperature, and electrodermal activity of 38 SUD patients during their everyday lives. They wanted to detect periods of stress and craving, as these parameters are possible triggers of substance use. Furthermore, they had patients self-report times during the day when they felt stressed or had cravings, and used those reports to calibrate their model.

They tried a number of classification models such as decision trees, discriminant analysis, logistic regression, and others, but found the most success using support vector machines though they failed to discuss why they thought that was the case. In the end, they found that they could detect stress vs. non-stress with an accuracy of 81.3% and craving vs. no-craving with an accuracy of 82.1%. Not amazing accuracy, but given the dire need for medical advancements for SUD, it’s something to keep an eye on. Interestingly enough, they found that locomotion data alone had an accuracy of approximately 75% when it came to indicating stress and cravings.

Much ado has been made about the insufficient accuracy of wearable devices for medical diagnoses, particularly of those that measure activity and heart rate. Maybe their model would perform better, being trained on real-time measurements of cortisol, a more accurate physiological measure of stress.

Finally, what really stood out to us about this study was how willing patients were to use a wearable in their treatment strategy. It’s sad that society oftentimes has a very negative perception of SUD patients, leading to fewer treatment options for patients. But hopefully, with technological advancements such as this, we’re one step closer to a more equitable future of healthcare.