This project could save lives
The problem of a drug overdose has never been worse with over 41 000 deaths just from the opioid overdose in the US this year. Now, a team of software engineering students at Carnegie Mellon has developed the HopeBand – wearable device which monitors the oxygen level in blood by using pulse oximetry and measuring light reflected back from the skin to a sensor. The wristband detects an imminent overdose and not only alarms the user by emitting sound and flashing red, but also will send a text message to the emergency number giving the wearer’s location. An early alert could give enough time to administer naloxone, which is an opioid antagonist that can reverse the overdose.
“Imagine having a friend who is always watching for signs of overdose; someone who understands your usage pattern and knows when to contact [someone] for help and make sure you get help,” – says Rashmi Kalkunte, a software engineering student at Carnegie Mellon University
The team’s focus is to develop a cheap wearable device which will track user’s health no matter where they go. They started working on the project after being approached and sponsored by Pinney Associates, a pharmaceutical consulting firm. Their idea was also recognised during the Health 2.0 Conference held in Santa Clara where they won third place in finals of the Robert Wood Johnson Foundation’s Opioid Challenge.
The future development
For now the device is still in the phase of lab trials, however, the tests so far look promising.
“The challenge is that we cannot actually just test the device on a human subject,” – says Puneetha Ramachandra, a master’s degree candidate in software engineering at Carnegie Mellon.
There is still room for much more things to implement. One can see that there might be a lot of false positives since every person is different and reacts differently to certain drugs. Luckily the team does have knowledge of this fact and they have a lot of ideas what can be changed in the future.
“I can absolutely see additional sensors being incorporated to give a machine-learning backend a bigger dataset to work with, reducing the number of false positives, for example. Or, once clinical trials are open, assembling a much larger, more diverse corpus for ML training that encompasses a wide range of physical variables – like age, sex, race, etc. – that could affect what an overdose state looks like!” – says Soham Donwalkar.
The HopeBand will initially be distributed free-of-charge to opioid users through needle exchange programs. If this works out, they plan to start selling the device for the commercial use with the price tag of around $16 and 20$. Of course, this is a device for people who are actually worried about their health state. It won’t help those, who are so addicted that nothing will change their mind. Overall, this can be a very useful product.