Systems and methods for analyzing brain activity and applications thereof
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10463271-B2
Publication Date
2019-11-05
Expiration Date
Abstract
In some embodiments, the present invention provides an exemplary inventive system that includes: an apparatus to record: individual's brain electrical activity, a physiological parameter of the individual, and iii) an environmental parameter; a computer processor configured to perform: obtaining a recording of the electrical signal data; projecting the obtained recording of electrical signal data onto a pre-determined ordering of a denoised optimal set wavelet packet atoms to obtain a set of projections; normalizing the particular set of projections of the individual using a pre-determined set of normalization factors to form a set of normalized projections; determining a personalized mental state of the individual by assigning a brain state; determining a relationship between: the physiological parameter, the environmental parameter, and the personalized mental state; generating an output, including: a visual indication, representative of the personalized mental state, and) a feedback output configured to affect the personalized mental state of the individual.
Core Innovation
The invention describes a wearable head apparatus configured to be worn on an individual's head to continuously record brain electrical activity together with at least one physiological parameter and at least one environmental parameter. A specifically programmed computer system includes non-transient memory and at least one processor that continuously obtains electrical signal data representative of the brain electrical activity and operates in real time.
The specifically programmed processor continuously projects the obtained recording onto a denoised optimal set of wavelet packet atoms to obtain a particular set of projections. The denoised optimal set is determined based on electrical signal data collected from a plurality of individuals representative of general brain activity, and the processor assigns a specific brain state to the individual based on applying at least one machine learning algorithm to the projections.
The processor continuously determines a relationship between the at least one physiological parameter, the at least one environmental parameter, and the at least one specific brain state. Based on the relationship, the system continuously generates an output that includes a visual indication representative of the specific brain state and a feedback output configured to affect, based on the relationship, the specific brain state of the individual.
Claims Coverage
The document contains two independent claims: clm-00001 (system) and clm-00014 (method). Each independent claim centers on continuous real-time wearably obtained EEG data projection using a denoised optimal set of wavelet packet atoms, machine-learning-based assignment of at least one specific brain state, determination of relationships among brain state, physiological parameters, and environmental parameters, and generation of a visual indication plus feedback output configured to affect the brain state.
Wearable head apparatus and continuous multimodal sensing with real-time processing
An apparatus configured to be worn on an individual's head and record the individual's brain electrical activity, at least one physiological parameter selected from the group consisting of heart rate, blood oxygen levels, body temperature, respiration rate, skin temperature, skin conductivity, and movement, and at least one environmental parameter, together with a specifically programmed computer system executing real-time operations on the electrical signal data.
Real-time projection onto a denoised optimal set of wavelet packet atoms determined from a plurality of individuals
Continuously projecting, in real time, the obtained recording of electrical signal data onto a denoised optimal set of wavelet packet atoms to obtain a particular set of projections, where the denoised optimal set of wavelet packet atoms has been determined based on electrical signal data collected from a plurality of individuals representative of general brain activity.
Machine-learning assignment of at least one specific brain state associated with mental state and/or neurological condition
Continuously determining, in real time, at least one mental state by assigning at least one specific brain state to the individual based on applying at least one machine learning algorithm to the particular set of projections of the individual, where the specific brain state is associated with a mental state, a neurological condition, or a combination of a mental state and a neurological condition.
Relationship determination among physiological parameter, environmental parameter, and specific brain state
Continuously determining a relationship between the at least one physiological parameter, the at least one environmental parameter, and the at least one specific brain state.
Real-time output with visual indication representative of specific brain state and relationship-based feedback configured to affect the specific brain state
Continuously generating, in real time, an output comprising a visual indication representative of the at least one specific brain state and a feedback output configured to affect, based on the relationship, the at least one specific brain state of the individual.
Wearable head-based data reception and processor-implemented continuous projection and state determination
Continuously obtaining, by a specifically programmed computer processor, a recording of electrical signal data representative of an individual's brain electrical activity received from an apparatus configured to be worn on an individual's head that records the individual's brain electrical activity, at least one physiological parameter selected from the group consisting of heart rate, blood oxygen levels, body temperature, respiration rate, skin temperature, skin conductivity, and movement, and at least one environmental parameter, followed by continuous projection and state determination.
Processor-based continuous determination of mental state via applying machine learning to wavelet-packet projections
Continuously projecting, in real time, the obtained recording of electrical signal data onto a denoised optimal set of wavelet packet atoms to obtain a particular set of projections, where the denoised optimal set of wavelet packet atoms has been determined based on electrical signal data collected from a plurality of individuals representative of general brain activity, and continuously determining, in real time, at least one mental state by assigning at least one specific brain state based on applying at least one machine learning algorithm to the particular set of projections.
Processor-based relationship determination and real-time output with visual indication and feedback configured to affect brain state
Continuously determining a relationship between the at least one physiological parameter, the at least one environmental parameter, and the at least one specific brain state, and continuously generating, in real time, an output comprising a visual indication representative of the at least one specific brain state and a feedback output configured to affect, based on the relationship, the at least one specific brain state of the individual.
Across clm-00001 and clm-00014, the claim coverage is directed to a wearable EEG-based system or processor-implemented method that continuously obtains brain electrical activity with physiological and environmental parameters, projects the brain electrical activity onto a denoised optimal set of wavelet packet atoms determined from a plurality of individuals, assigns at least one specific brain state using at least one machine learning algorithm, determines a relationship among physiological parameters, environmental parameters, and the specific brain state, and generates a visual indication plus a feedback output configured to affect the specific brain state.
Stated Advantages
Generates a visual indication representative of the at least one specific brain state.
Generates a feedback output configured to affect, based on the relationship, the at least one specific brain state of the individual.
Documented Applications
Monitoring therapy effectiveness.
Stimulus-response feedback for minimally conscious subjects, including music.
Infant developmental monitoring using musical stimuli, including monitoring mood/stress/attention.
Anesthesia and stage differentiation.
Detection of seizure-related abnormal activity.
Night monitoring/alerts.
Monitoring brain/mental states including examples such as Alzheimer’s, dementia, stress, fatigue, anxiety, epilepsy, traumatic brain injury, autism spectrum disorders, PTSD, migraine, chronic pain, coma, and sleep disorders.
Interested in licensing this patent?