The human brain remains one of medicine’s most fascinating and perplexing mysteries. Scientists still struggle to match neurological activity to brain function and detect problems early, slowing efforts to treat neurological disorders and other diseases.
Beacon Biosignals works to understand the brain by monitoring its activity during sleep. The company, founded by Dr. Jake Donoghue ’19 and former MIT researcher Jarrett Revels, has developed a lightweight headband that uses electroencephalogram (EEG) technology to measure brain activity while people sleep normally at home. This data is processed by machine learning algorithms to monitor the effects of novel therapies, find up-to-date signs of disease progression, and create patient cohorts for clinical trials.
“When you remove the sleep lab and bring clinical-grade EEG into the home, there’s a dramatic change,” says Donoghue, who serves as Beacon’s CEO. “It transforms sleep from a limited facility-based test to a scalable source of high-quality data for diagnostics, drug development and long-term assessment of brain health.”
Beacon partners with pharmaceutical companies to accelerate its path to patients. The company’s FDA 510(k)-cleared medical device has already been used in more than 40 clinical trials around the world in studies to treat conditions such as major depressive disorder, schizophrenia, narcolepsy, idiopathic hypersomnia, Alzheimer’s disease and Parkinson’s disease.
With each implementation, Beacon learns more about how the brain works – gaining knowledge that it uses to create a “base model” of the brain.
“We believe the dataset that will transform brain health does not exist yet, but we are building it quickly,” Donoghue says. “Our platform can characterize the heterogeneity of disease progression, generating dynamic insights that cannot be fully captured by static methods such as sequencing or imaging. The brain is an electrical organ and changes through synaptic plasticity, so tracking brain function across multiple diseases at scale will allow us to discover new disease subsets and map them over time.”
Brain lighting
Donoghue was educated in the Harvard-MIT Health Sciences and Technology Program, earning a doctorate in neuroscience from MIT under the supervision of Professor of Cognitive Sciences Earl K. Miller, and also completed clinical training as a physician. During the program, Donoghue trained at Massachusetts General Hospital and Boston Children’s Hospital, where he helped care for patients, including oncologists, during the development of genome sequencing to guide precision cancer therapies. He later worked in neurology and psychiatry, where care often relied on more iterative approaches, highlighting the ability to provide similar data-driven precision in brain health.
“What struck me most was the inability to measure brain function in the way cardiologists can monitor heart function in patients at home,” Donoghue says. “At MIT, I built a belief that processing large amounts of brain data and working to link it to brain function would impact how we identify and treat these neurological diseases.”
Toward the end of his training, Donoghue began to develop his ideas further, working with mentors including HST and Harvard Medical School professors Sydney Cash and Brandon Westover. He met Revels, who was working as a research software engineer at MIT’s Julia Lab during his Ph.D., and convinced him to start Beacon with him in 2019.
“We decided that starting a company to understand an organ of interest — the brain — would be a great start in understanding heterogeneous neuropsychiatric diseases and developing better treatments,” Donoghue recalls.
Beacon started as a computing and analytics company building wearable devices to expand clinical impact and reach. Since its inception, Beacon has partnered with huge pharmaceutical companies conducting clinical trials to offer a less invasive way to monitor brain activity and gain insight into how their drugs affect the brain as well as patients’ sleep.
“It was clear that sleep was the right window into understanding the brain,” Donoghue says. “Neural activity during sleep can be orders of magnitude greater and more structured, almost like language. This is a great surface for understanding how the brain functions and the effects of different drugs on the brain.”
Donoghue says Beacon devices can collect laboratory data on each patient for multiple consecutive nights, ensuring higher quality assessments. The company uses machine learning to draw conclusions such as the time patients spend in different sleep stages and the number of compact awakenings that occur throughout the night. It can also detect subtle changes in sleep architecture that can lead to cognitive decline.
“We are starting to analyze the characteristics of sleep activity and link them to outcomes in a way that has never been done before with such precision,” Donoghue says.
To date, Beacon has participated in clinical trials for sleep and mental health disorders, as well as neurodegenerative diseases, where sleep changes can occur years before symptoms appear.
“We work a lot on diseases like Alzheimer’s and Parkinson’s, which affected my grandfather,” Donoghue says. “We are analyzing the characteristics of rapid eye movement and slow-wave sleep to detect early changes that precede clinical symptoms. This is an opportunity to move these diseases from late diagnosis to much earlier data-driven detection.”
Improving brain therapies for millions
Last year, Beacon acquired an at-home sleep apnea testing company that serves more than 100,000 patients annually across the U.S., accelerating access to high-quality, comprehensive at-home testing and expanding the reach of its platform. The company then raised $97 million in November to accelerate that expansion.
“The vision has always been to reach patients and help them at scale,” Donoghue says. “The most important thing is that we are creating a longitudinal record of how the brain functions over time,” Donoghue says. “A patient can come in for a sleep apnea screening, but if they develop Parkinson’s disease years later, the earlier data provides insight into the disease before symptoms appear. This makes routine testing the basis for entirely new predictive biomarkers and a path to detecting and preventing brain diseases earlier, potentially before symptoms even appear.”