There will soon be a necklace that might encourage you to stop smoking. Researchers from Northwestern Medicine have developed a smart neck-worn device that resembles a lapis blue pendant and detects smoking far more accurately than earlier systems. By gathering heat signatures from thermal sensors, it achieves this.
SmokeMon is a necklace that entirely protects a smoker’s privacy by only monitoring heat and not images, which is essential for individuals to feel at ease wearing it.
“This goes way beyond how many cigarettes a person smokes per day,” said senior investigator Nabil Alshurafa, associate professor of preventive medicine at Northwestern University Feinberg School of Medicine. “We can detect when the cigarette is being lit, when the person holds it to their mouth and takes a puff, how much they inhale, how much time between puffs and how long they have the cigarette in their mouth.”
All these details are called smoking topography, which is essential for two reasons. The first is that it allows scientists to measure and assess harmful 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.
The second is to help people in their efforts to quit smoking by understanding how smoking topography relates to relapse (going back to smoking regularly), which happens frequently in people who quit.
Imagine a former smoker taking a couple cigarette puffs. Do five puffs or five cigarettes in their entirety trigger a full relapse? With the aid of this data, it is possible to anticipate when a person will relapse and to take appropriate action, such as calling them on the phone or sending them a text or video message on their smartphone to encourage them to avoid relapsing. The efficiency of the instrument in detecting smoking puffs and topography from electronic cigarettes will also be investigated by the researchers.
The study establishing the accuracy of the device and people’s willingness to wear it will be published on February 13 in Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies.
Globally, more than 8 million deaths are attributed to smoking each year. Smoking remains a leading cause of preventable disease, disability and death in the U.S., accounting for more than 480,000 deaths every year (or one in five deaths). It was estimated to cost the U.S. more than $600 billion in 2018 (combining healthcare spending and lost productivity). In the U.S., 12.5 per cent of adults smoke.
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 behaviour, including the use of wrist-worn inertial 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 behaviour 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.
