With the number of overdose deaths in America continuing to be of grave concern, at Indiana University, researchers are developing a life-saving patch that can detect and treat an opioid overdose. The patch is roughly the size of a nicotine patch and has sensors that measure the wearer’s blood oxygen level, respiratory rate, pulse rate and blood pressure. That information is sent to the wearer’s smartphone, which uses artificial intelligence to detect changes indicative of an impending overdose. Artificial intelligence helps determine whether a person is at risk of developing respiratory depression before blood oxygen levels drop dangerously low. If the risk for respiratory depression is high, naloxone is administered directly through the patch to reverse the overdose. The device will be useful for people under a physician’s care who take opioids for medical conditions, says Ken Mackie, a professor at IU and one of the patch’s developers. If the opioid dosage changes or if it is switched from a long-acting to a short-acting version, for example, there is a greater risk of overdose, he says. Because oxygen levels, pulse rates and blood pressure can change due to other causes, the team must be certain the naloxone dose is administered only when respiratory depression is imminent. Mackie and his colleague, Feng Guo, a bioengineer at IU and the primary developer of the device, are currently working to train the algorithm to differentiate between conditions and make the device as accurate as possible, Guo says.
In other news, dogs have already shown the ability to detect cancer on human breath or urine, but is it possible ants could do the same thing more cost effectively? And could both dogs and ants one day be used to train artificial intelligence-powered devices to do the same thing? Researchers think so. The hope is that animals trained to detect cancer could save lives by detecting tiny trace amounts of chemicals known as volatile organic compounds early in the disease. To take it a step further, researchers are exploring if they can identify the volatile organic compounds related to a particular cancer, and then artificial intelligence can be used for diagnostic purposes. IUPUI researcher Mangilal Agarwal is trying to develop nano-sensors that are as accurate and sensitive as a dog or an ant. Such a sensor could not only diagnose but offer daily, non-invasive surveillance for people at risk of certain types of cancer. It could also help monitor a person’s treatment progress, as the sensor could measure a decline in cancer-related volatile organic compounds. Having an at-home test, like a breathalyzer or a pee stick, could help monitor the condition in real time, Agarwal says. He and his colleagues are currently working on developing portable equipment that can be used to help them identify specific volatile organic compounds related to various cancers without using the huge, expensive mass spectrometer instruments in the lab. Scientists are also working through issues with confounding smells, such as medications that might mask a specific volatile organic compound. Agarwal says it’s possible for biotechnology to mimic an animal’s ability to detect medical conditions, but can it be more accurate than a dog or an ant? That question remains unknown, he says.