pulse oximeter as a small sticker that sticks on your fingernail and measures heart rate, motion, and blood oxygen

This Fingernail Sticker Can Detect When You Stop Breathing

Sometimes we dig through the archives to see what kind of crazy hacks we can pull out of the depths of the world wide web and this one was worth sharing. Researchers at Northwestern University developed a sticker that’s applied to the fingernail and measures heart rate, motion, and blood oxygen, all without a battery.

The photoplethysmograph (PPG) system is similar to what we’ve covered before and the motion sensor is simply an accelerometer, so we won’t go over those aspects of the device. The parts of the device that did catch our attention were the battery-less operation as well as its size. It’s just so dang small! And fits snuggly on a fingernail or on even on your earlobe. The size here is actually a very interesting feature and not just a marketing plug. Because the device is so small and lightweight, it is very easy to adhere to the fingernail or skin with very little sensory perception. Basically, the person wearing the device won’t even notice it’s there. That’s definitely an advantage over the traditional, bulky, hospital-grade instruments we’ve grown accustomed to.

The device adheres really well given its small and lightweight design, so motion artifacts are significantly reduced. Motion artifacts in PPG-based devices are due to the relative motion between the optode (LED and photodiode) and the skin. The traditional approaches of ensuring the device don’t move are for the patient to keep very still during a recording, to wear the device tightly against the skin (think of how tightly you need to wear your smartwatch to get consistent readings), or use some seriously tough and uncomfortable adhesive as you may have done if you’ve ever gotten an electrocardiogram reading before. This device eliminates those three problems.pulse oximeter as a small sticker that sticks on your fingernail and measures heart rate, motion, and blood oxygen

The other aspect of the device that caught our attention is its use of wireless power instead of a battery. In some senses, this could be seen as an advantage or as a disadvantage. The device relies on NFC for power and data transmission, a pretty common approach for devices that only need to be used intermittently. Wireless power could be a bit problematic for continuous monitoring devices which provide readings every second or several times a second. But who knows, wireless power seems to be everywhere these days.

Digging into the details a bit, the double-layer antenna is designed around the circumference of the device using wet etching to create traces on a copper polyimide foil. The team electroplated holes through the different layers of the device (optode layer, first antenna layer, polyimide, second antenna layer, component layer, protective top coat) connecting the antenna to the die pad NFC chip (SL13A, AMS AG). Connecting the chip requires some pretty fine-pitch soldering techniques, but nothing we’re not accustomed to here at Hackaday. Overall, they seemed pretty successful, obtaining a Q factor of 16 and a transmission distance of 30 mm using a smartphone and not some giant reader antenna.

Definitely, a really cool project that we recommend checking out.

Custom-designed photoplethysmogram designed to fit in ear like an ear bud

Breathe Through Your Ears?

With all the attention given to heart rate monitoring and step counting, respiratory rate monitoring is often overlooked. Smartwatches are starting to incorporate respiratory rate monitoring more and more these days. However, current devices often simply look at breaths per minute without extracting more interesting features of the respiratory waveform which could give us more insight into our bodies than breaths per minute could alone. [Davies] and his team decided they wanted to change that by making an earbud that can measure respiratory rate. Continue reading “Breathe Through Your Ears?”

Infant is wearing sensor vest as she is held by her mom. ECG, respiration, and accelerometry data is also showing.

Open Source Wearables For Infants

We’ve seen plenty of hacks that analyze biometric signals as measures of athletic performance, but maybe not as many hacks that are trying to study behavior. Well, that’s exactly what developmental psychologists at Indiana University and the University of East Anglia have done with their open-source, wireless vest for measuring autonomic function in infants.

infant biosensor vest for heart rate, motion, and respiratory rateTheir device includes a number of components we’ve seen already. There is an HC-05 Bluetooth module, AD8232 electrocardiography (ECG) analog front-end, LIS3DH 3-axis accelerometer, MCP73831 LiPo charger, a force-sensitive resistor for measuring respiration, and a Teensy microcontroller. Given how sensitive an infant’s skin can be, they opted for fabric electrodes for the ECG instead of those awful sticky ones that we’re accustomed to. They then interfaced the conductive fabric with copper plates using snap fasteners (or press studs or snap buttons, whichever terminology you’re more familiar with). The copper plates were connected to the circuit board using standard electrical wire. Then, they embedded the sensors into a vest they sewed together themselves. It’s basically a tiny weighted vest for infants but it seems well-padded enough to be somewhat comfortable.

They did a short test analyzing heart and breathing rates during a period of “sustained attention,” basically when you’re quietly fixated on a single object or activity for a period of a few minutes or longer. They were really pleased with the vest’s ability to collect consistent data and noted that heart and respiratory rate variability decreased during the sustained activity test, which was an expected outcome. Apparently, when you’re pretty fixated on a singular task, your body naturally calms down, so to speak, and the variability in some of your physiological responses decreases. Well, unless someone slowly walks up behind you and pinches you, of course.

They provided detailed instructions for recreating the vest, so be sure to check those out. They probably want their device to look a lot less than body armor though. Maybe the Sewbo can help them out with their next iteration.

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…

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

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.