A smart necklace that tracks heat signatures from lit cigarettes in real-time, how much smokers inhale and the time between puffs could help you stop smoking. Researchers at Northwestern Medicine in Chicago developed such a device that resembles a lapis blue pendant and detects users’ smoking habits much more reliably than previous systems.
Called SmokeMon, it does so by capturing heat signatures from thermal sensors while completely maintaining a smoker’s privacy, as it tracks only heat – not visuals, which is a critical factor for people to feel comfortable wearing it.
“This goes way beyond how many cigarettes a person smokes per day,” said senior investigator and preventive medicine Prof. Nabil Alshurafa, at Northwestern University’s Feinberg School of Medicine. “We can detect when the cigarette is being lit, when the person holds it to his or her mouth and takes a puff, how much smoke was inhaled, how much time between puffs and how long the cigarette has been in the mouth.”
The topography of smoking
All these details are called smoking topography, which is important because it allows scientists to measure and assess toxic carbon monoxide exposure among smokers and understand more deeply the relationship between chemical exposure and tobacco-related diseases including cancer, heart disease, stroke, lung disease, diabetes, COPD, emphysema and chronic bronchitis.
It also helps people in their efforts to quit smoking by understanding how smoking topography relates to relapse – going back to smoking regularly – which frequently happens in people who initially kick the habit.
If a former smoker takes a few puffs of a cigarette, do five puffs or five entire cigarettes send him into a full relapse? This information can be used to predict when a person will relapse and when to intervene with a phone call from a health coach, for example, or even a smartphone text or video message to help encourage them to prevent a relapse. The scientists also plan to study the effectiveness of the device in detecting smoking puffs and topography from electronic cigarettes.
“We want to catch them before they completely fall off the wagon,” Alshurafa said. “Once they do, it’s much harder for them to quit again.
“For many people who attempt to quit smoking, a slip is one or two cigarettes or even a single puff. But a slip is not the same as a relapse. A person can learn from slips by gaining awareness that he didn’t fail; they just had a temporary setback. To avoid a relapse, we can then begin to shift their focus on how we handle their triggers and deal with cravings.”
The study establishing the accuracy of the device and people’s willingness to wear it will be published in the latest issue of the journal Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies under the title “SmokeMon: Unobtrusive Extraction of Smoking Topography Using Wearable Energy-Efficient Thermal.”
“Now we can begin to test the effectiveness of this device in improving the success rate of smoking cessation programs by preventing relapse in smokers who are planning to quit,” Alshurafa said. “We will be able to test whether real-time feedback and interventions can be more effective than usual care.”
Each year, an average of more than eight million people around the world die due to smoking, which remains a leading cause of preventable disease, disability and death, accounting annually for more than 480,000 deaths (one in five) in the US alone, where almost 13% of adults smoke. The annual cost of healthcare spending and lost productivity due to smoking is more than $600 billion.
Existing devices that track smoking topography must be attached to the cigarette, which changes how a person smokes and makes the data less reliable. Some researchers have investigated non-obtrusive ways to measure smoking behavior, including the use of wrist-worn measurement unit sensors in smartwatches. However, such approaches are often confounded by non-smoking hand-to-mouth gestures and consequently, generate many false positives. Another option – wearable video cameras – creates privacy and stigma concerns, limiting the applicability of camera-based approaches in natural settings.
Nineteen participants were recruited for the study. They took part in 115 smoking sessions in which scientists examined their smoking behavior in controlled and free-living experiments.
As smokers wore the device, scientists trained a deep learning-based machine model to detect smoking events along with their smoking topography, including things like the timing of a puff, number of puffs, puff duration, puff volume, inter-puff interval and smoking duration. They also ran three focus groups with 18 tobacco-treatment specialists to understand how they felt about the device.
One smoking-cession specialist commented, “These real-time measurements can really help us understand the depth a person is at in their smoking habits and treat the patient accordingly.”