Techniques are described for determining cognitive impairment, an example of which includes accessing a set of epochs of magnetoencephalography (MEG) data of responses of a brain of a test patient to a plurality of auditory stimulus events; processing the set of epochs to identify parameter values one or more of which is based on information from the individual epochs without averaging or otherwise collapsing the epoch data. The parameter values are input into a model that is trained based on the parameters to determine whether the test patient is cognitively impaired.

Provided are computer-implemented methods for producing an index. The methods include conditioning electroencephalographic (EEG) signals present in an EEG recording previously obtained from an individual, e.g., an individual having dementia. In certain embodiments, the methods further include determining frequency domain features from the conditioned EEG signals, and determining connectivity features from the frequency domain features, where the connectivity features include connectivity features determined from a frequency range of from 35 Hz to 45 Hz divided into two or more sub-bands. The methods further include producing an index calculated at least in part as a function of one or more of the connectivity features determined from a frequency range of from 35 Hz to 45 Hz divided into sub-bands with varying contribution to the calculation of the index. Also provided are computer readable media and computer devices that find use, e.g., in practicing the methods of the present disclosure.

A method for classifying neurological disease status is described. The method includes acquiring, by a data preprocessor logic, patient image data. The method further includes generating, by a trained artificial neural network (ANN), a classification output based, at least in part, on the patient image data. The classification output corresponds to a neurological disease status of the patient. The trained ANN is trained based, at least in part, on longitudinal source data.

The present disclosure describes a method of regulating (re-balancing) the brain's immune system to decrease occurrence and/or severity of age-related diseases and increase life span. According to the method, an array of electromagnetic emitters are positioned proximal to the subject. An electromagnetic wave generator generates electromagnetic waves at a predetermined set of parameters. In an example of the emitters positioned proximal to the subject's head, the brain's immune function is normalized/rebalanced in an area under the electromagnetic emitters by applying the electromagnetic waves to the subject through the electromagnetic emitters. With either head or body placement of emitters, a rebalancing of the brain's cytokines/immune mediators occurs, which should result in less occurrence or severity of age-related diseases and, thus, increase human life span. Alternatively, electromagnetic treatment may increase human life span through other mechanism(s) or effects that work independent of, or in concert with, a reduced occurrence/severity of age-related diseases.

A method and system for monitoring impairment indicators. The method comprises, during a first time window, measuring a first movement signal related to movement of a person with a movement sensor associated with the person, and measuring a first environmental signal with an environmental sensor. The method further comprises electronically storing at least one numerical descriptor derived from the first movement signal and the first environmental signal as reference data for the person. The method further includes, during a second time window, measuring a second movement signal related to movement of the person with the movement sensor and measuring a second environmental signal with the environmental sensor; and comparing at least one numerical descriptor derived from the second movement signal and the second environmental signal to the reference data to identify an impairment indicator.

A method and system for monitoring impairment indicators. The method includes, during a first time window, measuring a first movement signal related to movement of the person with a movement sensor associated with the person, and measuring a first biological signal of the person with a biological sensor attached to the person. The method further includes electronically storing at least one numerical descriptor derived from the first movement signal and at least one numerical descriptor derived from the first biological signal as reference data for the person. The method includes during a second time window, measuring a second signal related to movement of the person with the movement sensor, and measuring a second biological signal of the person with the biological sensor. The method further includes comparing at least one numerical descriptor derived from the second signal and at least one numerical descriptor derived from the second biological signal to the reference data to identify an impairment indicator.

A method for monitoring impairment indicators, the method includes measuring, with a movement sensor attached to the person, a first signal related to movement of a person during a first time window and electronically storing the at least one numerical descriptor derived from the first signal as reference data for the person. The method further includes measuring, with the movement sensor attached to the person, a second signal related to movement of the person during a second time window and comparing at least one numerical descriptor derived from the second signal to the reference data as a factor to identify an impairment indicator. The present disclosure also includes a device for monitoring impairment indicators.

[Problem]

It is intended to quantitatively evaluate deterioration in brain function associated with a disease such as dementia, with a high degree of accuracy by a simplified method using signals acquired from a few sensors arranged on the scalp.

[Solution]

The present invention relates to a brain activity measurement device comprising: a signal acquisition part configured to acquire a signal from a brain of the subject, using three sensors attached to different locations on the surface of the head of a subject; a data extraction part configured to extract, from each of the three signals acquired from respective ones of the sensors, a deep-brain potential signal having a specific frequency band arising from an activity of a deep brain region, and acquire data from the extracted deep-brain potential signal with a sampling period; a correlation value calculation part configured to calculate a correlation value indicative of a correlative relationship among the deep-brain potential signals acquired from each respective sensors, based on a phase relationship among three pieces of time-series data each extracted from the respective sensors by the data extraction part; and an index value calculation part configured to analyze the deep-brain potential signals from the deep brain region, based on the calculated correlation value, to calculate an index value for determining a brain function.

A composite ocular blood flow analyzer uses pneumatic tonometric techniques and structures to produce accurate, stable, and repeatable readings of intraocular pressure. A computer processes the intraocular pressure readings to produce data relating to various aspects of ocular blood flow that can be used diagnostically to identify abnormalities in the eye and other parts of the body.

A machine learning system for aggregating electroencephalographic (EEG) data in preparation for downstream analysis via further machine learning models. Machine learning models can be used to assist in diagnosis of various mental health conditions, brain-computer interface, mood detection systems, or other biometric functions. Implementations of the present disclosure, employ a portion of the transformer network (the attention encoder stack) to aggregate EEG trials or EEG data segments, in a data-driven way, by ensuring the important content of each trial is not lost. Each EEG trial to be aggregated is converted into an input embedding, or a vector which numerically represents the data in the trial.