Discover cutting-edge research, news, and tools that power computational neurology and psychiatry. As active members of the communities we serve, we're dedicated to the highest quality science and contributing to open source projects across the ecosystem.
NewsView All News
Research from Beacon Biosignals presented at Alzheimer's Association International Conference
Beacon Biosignals announces partnership with Stratus to advance at-home brain monitoring and machine learning-enabled neurodiagnostics
Startups are turning to a century-old technology to fuel a resurgence in neuro drug development
34 healthcare and biotech startups that are set to take off in 2022, according to top investors
Scientific PublicationsView All Publications
Association of Sleep EEG-Based Brain Age Index With Dementia
The brain age index may be a useful biomarker associated with dementia and could have utility as a screening tool for the presence of underlying neurodegenerative disease and monitoring of disease progression.
Interrater Reliability of Experts in Identifying Interictal Epileptiform Discharges in EEGs
This study’s findings suggest that experts can identify whether EEGs contain IEDs with substantial reliability. Lower reliability regarding individual IEDs may be largely explained by various experts applying different thresholds to a common underlying statistical model.
A hidden Markov model reliably characterizes ketamine-induced spectral dynamics in macaque local field potentials and human EEGs
Ketamine is an NMDA receptor antagonist commonly used to maintain general anesthesia. At anesthetic doses, ketamine causes high power gamma (25-50 Hz) oscillations alternating with slow-delta (0.1-4 Hz) oscillations. These dynamics are readily observed in local field potentials (LFPs) of non-human primates (NHPs) and electroencephalogram (EEG) recordings from human subjects. Here, we characterize ketamine’s neural dynamics using a hidden Markov model (HMM).
Interhemispheric transfer of working memories
We studied how WM is integrated across hemifields by recording neural activity bilaterally from prefrontal cortex. Around the time of transfer, synchrony between the two prefrontal hemispheres peaked in theta and beta frequencies, with a directionality consistent with memory trace transfer. This illustrates how the two cortical hemispheres can stitch together WM traces across visual hemifields.
Light affects mood and learning through distinct retina-brain pathways
These results provide new insights into the neural basis required for light to influence mood & learning.
Large-scale automated sleep staging
Training with a large data set enables automated sleep staging that compares favorably with human scorers. Because testing was performed on a large and heterogeneous data set, the performance estimate has low variance and is likely to generalize broadly.
Neural effects of propofol-induced unconsciousness and its reversal using thalamic stimulation
Unconsciousness is linked to cortical and thalamic slow frequency synchrony coupled with decreased spiking, and loss of higher-frequency dynamics. This may disrupt cortical communication/integration.
Single-neuron dynamics in human focal epilepsy
This is the first study of large ensembles of single neurons during seizures in persons with epilepsy. Contrary to the traditional view, neuronal spiking activity during seizures was highly heterogeneous and changed significantly preceding clinical onset.
Open Source SoftwareView All Software
A Julia package for high-throughput manipulation of structured signal data across arbitrary domain-specific encodings, file formats and storage layers
Tables.jl-friendly mechanisms for constructing, reading, writing, and validating Arrow tables against extensible, versioned, user-specified schemas.
Effects Prediction for Linear and Generalized Linear models
Performance evaluation tools for multiclass, multirater classification models
Tools we use
Betting big on quantitative neurobiomarkers
Jake Donoghue, MD PhD
- Introducing Beacon Biosignals: a neurotechnology company founded to develop machine learning-enabled EEG neurobiomarkers and accelerate precision medicine for any disease state affecting the brain
- Founded by MD/PhDs and engineers from Harvard and MIT, Beacon is propelled by the vision of a computing platform designed to scale the interrogation of large brain datasets with unprecedented throughput & capability
- Beacon’s EEG neurobiomarker platform is engineered to accelerate clinical trials and enable new treatments for patients with neurological & psychiatric disease