Like the swirls in fingerprints, a person’s breathing pattern might be unique to them — offering a way not only to identify individuals, but also to identify some of their physical and mental traits.

A team of researchers measured the breathing of 97 healthy people for 24 hours, and found that they could identify participants with relatively high accuracy from their breathing pattern alone. What’s more, they found that these patterns can be correlated with body-mass index (BMI) and signs of depression and anxiety.

“In a way, we’re reading the mind through the nose,” says co-author Noam Sobel, a neurobiologist at the Weizmann Institute of Science in Rehovot, Israel. “This could be a very powerful diagnostic tool.” The team published its study today in Current Biology¹.

Taking a breath

Breathing is deeply connected to the brain. Every inhalation and exhalation is coordinated to supply the oxygen needed for the brain to manage the body’s systems. Sobel and his team wondered: if every brain functions differently, shouldn’t every person’s breathing be unique, too?

To test this, the researchers developed a custom, wearable device that records airflow through each of a person’s nostrils. Mounted on the back of the neck, the device, which has tubes fitted under the nose, tracks people’s breathing during their everyday routines, both while they are awake and while they are asleep.

To characterize a person’s breath pattern, the team extracted 24 parameters from the airflow data, including duration of inhalation and exhalation and airflow asymmetry between nostrils. They separated the periods when participants were awake and asleep, and trained a machine-learning algorithm with the data.

When 42 of the participants came back to the laboratory weeks, months and even two years later, to take part in another 24-hour measurement, the trained algorithm could identify them from their breath patterns. Data from periods when the participants were awake gave more accurate results than did those from sleeping periods, but when the researchers used a 100-parameter characterization of a full data set instead of one using 24 parameters, they could pick individuals out with 96.8% accuracy.

Given this success, Sobel and his colleagues began wondering whether they could learn more from the breath patterns.

Healthy breathing

The researchers collected data on the participants’ BMIs, and from questionnaires that assess levels of depression and anxiety. An analysis found correlations between this information and the breathing patterns, even though most participants had low-level scores on the questionnaires.

For instance, the breathing profiles during sleep of people with higher BMIs were different from those of people with lower BMIs. And those who scored higher on the questionnaires for anxiety or depression had distinct patterns in how they inhaled and exhaled.