NYU Tandon researchers have reached a key milestone in their quest to develop wearable technology that successfully measures key brain mechanisms through the skin.
Rose Faghih, an associate professor of biomedical engineering, has been working for seven years on technology that can measure mental activity using electrodermal activity (EDA) – an electrical phenomenon in the skin that is influenced by brain activity related to the emotional state. Internal stresses, whether caused by pain, exhaustion, or a particularly busy schedule, can cause changes in EDA – changes that directly correlate to mental states.
The overarching goal – a multi-modal non-invasive smart brain state decoder for wearable adaptive closed-loop architectures, or MINDWATCH, as Faghih calls it – would act as a way to monitor a wearer’s mental state and offer nudges that would help them return to a more neutral state of mind. For example, if a person were experiencing a particularly severe episode of work-related stress, the MINDWATCH could detect this and automatically play relaxing music.
Now Faghih – together with Rafiul Amin, his former PhD student – has done a crucial task needed to monitor this information. For the first time, they have developed a new inference engine capable of monitoring brain activity through the skin in real time with high scalability and accuracy. The results are presented in a new paper, “Physiological characterization of electrodermal activity enables inference of scalable autonomic nervous system activation in near real-time», published in PLOS Computational Biology.
“Inferring autonomic nervous system activation from wearable devices in real time opens up new opportunities to monitor and improve mental health and cognitive engagement,” Faghih says.
Previous methods measuring sympathetic nervous system activation through the skin took minutes, which is impractical for wearable devices. While his previous work focused on inferring brain activity through sweat activation and other factors, the new study additionally models the sweat glands themselves. The model includes a 3D state-space representation of direct sweat secretion via pore opening, along with diffusion followed by corresponding evaporation and reabsorption. This detailed gland model provides exceptional insight for inferring brain activity.
The new model was run on data from 26 healthy people. Researchers have shown that they can decipher brain signals with high reliability. Moreover, the computing power required by their new algorithm is minimal and can obtain brain and physiological information in seconds while another previous approach would take minutes. This means that a small, portable surveillance technology capable of incredible speed, great scalability and extraordinary reliability is at your fingertips.
The wider impact and applications of the methodology include performance monitoring, mental health monitoring, pain measurement and cognitive stress. Mental health tracking can help better manage autism, post-traumatic stress disorder, excessive irritability, suicidal tendencies, and more. Performance tracking and cognitive stress tracking can help improve individual productivity and quality of life.
“A person’s performance changes based on their cognitive engagement and level of arousal.” Faghih said. For example, very low or very high arousal levels can lead to poor performance. Therefore, it is expected that. Ultimately, researchers can use inferred autonomic nervous system activation and decoded arousal to develop interventions to improve productivity.
An example of application of this method is the early diagnosis of disorders such as diabetic neuropathy. Small nerves transmit brain stimulation to many parts of the body, including those related to the skin conductance response. To track received brain activity, EDA can be measured and monitored regularly in skin areas of the body prone to neuropathy. If an area of the skin has neuropathy (that is, tiny nerves have been damaged), the brain will not activate that area. By monitoring changes, doctors can see how a condition like diabetic neuropathy is progressing and may lead to changes in treatment plans.
Another example is that of a newborn in extreme pain following surgery, who cannot express his level of pain. Physicians can use EDA recordings and infer brain activity to assess infant pain and intervene as needed.
For Faghih, this work could represent a breakthrough for mental health care. Monitoring the mental status of vulnerable people could help them get more effective care and prevent the serious consequences of declining mental health or mood swings.
His team is currently working on ways to integrate the model into wearable devices, including eliminating informational “noise” caused by factors such as robust movement and exercise, as well as finding potential partnerships to design. and fabricate the devices that would carry the algorithm.
Reference: Amin R, Faghih RT. Physiological characterization of electrodermal activity allows evolutionary inference of autonomic nervous system activation in near real-time. PLOS Comput Biol. 2022;18(7):e1010275. do I: 10.1371/log.pcbi.1010275
This article was republished from the following materials. Note: Material may have been edited for length and content. For more information, please contact the quoted source.