Advancing Neuroscience Through Wearable Devices and Multimodal Data Analysis

Between 2021 and 2028, the global wearable technology market is expected to grow at a compound annual growth rate of 13.8% to reach a whopping $118.16 billion. While the widespread adoption of wearable devices is largely driven by smartwatches, the range of wearable devices and other digital technologies is seemingly endless. Faster, more reliable, comfortable, and non-invasive wearable devices are producing data from biosensors at an unprecedented scale.

In healthcare, wearables are already making their mark, providing simple, yet accurate approaches to patient monitoring, screening, and diagnosis. They’re also being used as novel tools to assist with treatment, post-treatment, and ongoing management based on real-time physiological data. Wearable devices—including hearables, smartwatches, smart glasses, smart clothing, fitness trackers, and skin patches—and multimodal data analysis hold significant promise in both clinical and research environments. 

There is an opportunity for advancing neuroscience through wearable devices and multimodal data analysis by unlocking new links between the brain and other parameters of bodily function, providing a whole new paradigm for researching and understanding neurological disease signatures. This may enable a new, novel approach to diagnosing neurological diseases.

How Wearable Devices will Advance Neuroscience

Wearable devices are bringing increased awareness around health and wellness worldwide. Consumers continue to gravitate towards the concept of understanding and monitoring their health. Wearables are consumerizing healthcare—their ubiquity enables future multimodal consumer-level brain health technologies to be built on top of them.

When data from wearables, such as vitals, activity levels, and sleep, are paired with multimodal neurocognitive function data, we can gain a greater understanding of the connections between the brain and other subsystems within the body.

Wearables and body-worn sensors can produce data streams measuring aspects like body temperature, heart rate, blood oxygen levels, sweat gland activation, sleep-wake cycles, and respiration rate and can be paired with portable devices. Integrated sensors in portable devices can produce diverse multimodal data streams measuring aspects like speech and articulation, gait, eye movement, and fine motor coordination.

When paired with strong analytical tools, such as artificial intelligence, data from wearables, combined with multimodal data collection through portable devices, will change neuroscience as we know it. Feeding large data sets collected by digital neurocognitive function assessments and wearable devices from healthy individuals and those impacted by specific neurological diseases to artificial intelligence algorithms can determine links, patterns, and complex disease signatures associated with a breadth of neurological diseases. This method offers a highly accessible, cost-efficient, and non-invasive approach for assessing neurocognitive function and enhancing our understanding of neurological disease signatures.

Improving Neurological Disease Diagnostics

Currently, healthcare providers, researchers, and pharmaceutical companies alike rely on outdated cognitive and functional measurement tools that are highly variable during annual wellness visits. The lack of granularity and highly variable results of these assessments can lead to delayed diagnoses or misdiagnoses of neurological diseases like Alzheimer’s and Parkinson’s. To confirm neurological disease diagnoses, healthcare providers rely on expensive and invasive diagnostic tools, such as positron emission tomography (PET) scans and cerebrospinal fluid analysis. 

However, wearable devices, body-worn sensors, and portable devices can provide new, innovative solutions. If high-quality multimodal brain health data and wearable data are collected on a large scale over time, this can lead to the training of artificial intelligence on larger data sets, enabling the ability to identify patterns across the data and providing a non-invasive method for neurological disease diagnosis.