# US 2017/0281071 A1 · Methods and magnetic imaging devices to inventory human brain cortical function

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0281071 A1
- Document ID: US20170281071A1
- Status: Published application
- Kind: A1
- Application number: 15/472,130
- Filed: 2017-03-28
- Published: 2017-10-05
- Earliest claimed: 2016-03-30
- Assignees: Brain F.I.T. Imaging, LLC
- Applicants: Brain F.I.T. Imaging, LLC
- Inventors: John P. Ford; Gustavo P. Sudre
- Web page: https://patentgrep.com/patent/US20170281071A1

## CPC

- A61B 5/4088: {Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia}
- A61B 5/0042: {for the brain}
- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/246: using evoked responses
- A61B 5/6803: {Head-worn items, e.g. helmets, masks, headphones or goggles}
- A61B 5/70: {Means for positioning the patient in relation to the detecting, measuring or recording means}
- A61B 5/702: {Posture restraints}
- A61B 5/7203: {for noise prevention, reduction or removal}
- A61B 5/7257: {using Fourier transforms}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 5/7267: {involving training the classification device}
- A61P 25/28: for treating neurodegenerative disorders of the central nervous system, e.g. nootropic agents, cognition enhancers, drugs for treating Alzheimer's disease or other forms of dementia
- A61B 5/162: {Testing reaction times}
- A61B 2503/40: Animals
- A61B 2560/0223: of calibration, e.g. protocols for calibrating sensors
- A61B 2562/0223: Magnetic field sensors
- A61B 2576/026: for the brain
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- A61P: SPECIFIC THERAPEUTIC ACTIVITY OF CHEMICAL COMPOUNDS OR MEDICINAL PREPARATIONS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

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.

## Claims

### Claim 1

A method comprising:
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 a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak sub set;
inputting the parameter values into a model that is trained based on the parameters to determine whether the test patient is cognitively impaired; and
providing the determination.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values based on the individual epochs comprises:
identifying a weak subset of the epochs in the set having a weakest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a count of the epochs in the weak subset having the second peak.

### Claim 3 (depends on 2)

The method of claim 2 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak, and the second peak is a different one of those peaks.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values based on the individual epochs comprises:
identifying a strong subset of the epochs having a strongest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a count of the epochs in the strong subset having the second peak.

### Claim 5 (depends on 4)

The method of claim 4 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak, and the second peak is a different one of those peaks.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values based on the individual epochs comprises:
identifying a weak subset of the epochs having a weakest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a measure of amplitudes of the second peaks of the epochs in the weak subset.

### Claim 7 (depends on 6)

The method of claim 6 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak, and the second peak is a different one of those peaks.

### Claim 8 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values based on the individual epochs comprises:
identifying a strong subset of the epochs having a strongest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a measure of amplitudes of the second peaks of the epochs in the strong subset.

### Claim 9 (depends on 8)

The method of claim 8 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak, and the second peak is a different one of those peaks.

### Claim 10 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
identifying a strong subset of the epochs having a strongest amplitude for the first peak relative to the other epochs in the set; and
identifying a weak subset of the epochs having a weakest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a ratio of an area of the first peak in the weak subset to an area of the first peak in the strong subset.

### Claim 11 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
identifying a strong subset of the epochs having a strongest amplitude for the first peak relative to the other epochs in the set; and
identifying a weak subset of the epochs having a weakest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a ratio of an overall amplitude of a second peak in the strong subset to an overall amplitude of the second peak in the weak subset.

### Claim 12 (depends on 11)

The method of claim 11 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak, and the second peak is a different one of those peaks.

### Claim 13 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
identifying a strong subset of the epochs having a strongest amplitude for the first peak relative to the other epochs in the set; and
identifying a weak subset of the epochs having a weakest amplitude for the first peak relative to the other epochs in the set; and
determining one of the parameter values based on a ratio of a count of epoch in the strong subset having a second peak to a count of a number of epochs in the weak subset having the second peak.

### Claim 14 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on a count of the epochs in the tri-peak sub set.

### Claim 15 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on a count of the epochs in the set having the first peak, and the second peak.

### Claim 16 (depends on 15)

The method of claim 15 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak, and the second peak is a different one of those peaks.

### Claim 17 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on a count of the epochs in the tri-peak subset having the first peak.

### Claim 18 (depends on 17)

The method of claim 17 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak.

### Claim 19 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on a variability in duration of the epochs in the tri-peak subset having the first peak.

### Claim 20 (depends on 19)

The method of claim 19 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak.

### Claim 21 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on an average in duration of the epochs in the tri-peak subset having the first peak.

### Claim 22 (depends on 21)

The method of claim 21 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak.

### Claim 23 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on a variability in duration of the epochs in the tri-peak subset having the first peak divided by an average in duration of the epochs in the tri-peak subset having the first peak.

### Claim 24 (depends on 23)

The method of claim 23 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak.

### Claim 25 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on an aggregate magnitude of the first peak in epochs containing the first peak.

### Claim 26 (depends on 25)

The method of claim 25 wherein the first peak is the type-A peak, the type-B peak, or the type-C peak.

### Claim 27 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on latencies of the first peaks in epochs in the tri-peak subset.

### Claim 28 (depends on 27)

The method of claim 27 wherein the parameter value is further based on at least one of a variance, standard deviation, mean, median, and mode of the latencies of the first peaks.

### Claim 29 (depends on 27)

The method of claim 27 wherein the first peak is the type-A peak or the type-C peak.

### Claim 30 (depends on 29)

The method of claim 29 wherein the latency of the first peak is determined starting from a second latency of the second peak occurring before or after the first peak in time in the epoch.

### Claim 31 (depends on 29)

The method of claim 29 wherein the latency of the first peak in the epochs is determined based on when a first derivative of a signal within the epoch is substantially zero.

### Claim 32 (depends on 27)

The method of claim 27 wherein the first peak is the type-B peak.

### Claim 33 (depends on 32)

The method of claim 32 wherein the latency of the first peak in one of the epochs is determined based on when a signal in the epoch is at substantially its maximum absolute value.

### Claim 34 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on onsets of the first peaks in epochs in the tri-peak subset.

### Claim 35 (depends on 34)

The method of claim 34 wherein the parameter value is further based on at least one of a variance, standard deviation, mean, median, and mode of the onsets of the first peaks.

### Claim 36 (depends on 34)

The method of claim 34 wherein the first peak is the type-B peak.

### Claim 37 (depends on 36)

The method of claim 36 wherein the onset of the first peak in one of the epochs is determined based on when a signal in the epoch is more than twice a standard deviation of a baseline signal.

### Claim 38 (depends on 34)

The method of claim 34 wherein the first peak is the type-A peak or the type-C peak.

### Claim 39 (depends on 38)

The method of claim 38 wherein the onset of the first peak in one of the epochs is determined based on when a first derivative of a signal in the epoch changes sign.

### Claim 40 (depends on 1)

The method of claim 1, wherein determining one of the plurality of the parameter values comprises:
determining one of the parameter values based on offsets of the first peaks in epochs in the tri-peak subset.

### Claim 41 (depends on 40)

The method of claim 40 wherein the parameter value is further based on at least one of a variance, standard deviation, mean, median, and mode of the onsets of the first peaks.

### Claim 42 (depends on 40)

The method of claim 40 wherein the first peak is the type-B peak.

### Claim 43 (depends on 42)

The method of claim 42 wherein the onset of the first peak in one of the epochs is determined based on when a signal in the epoch is more than twice a standard deviation of a baseline signal after a type-B peak latency for the epoch.

### Claim 44 (depends on 42)

The method of claim 42 wherein the offset of the type-A peak in one of the epochs is determined based on when a first derivative of a signal in the epoch changes sign.

### Claim 45 (depends on 42)

The method of claim 42 wherein the onset of the type-C peak in one of the epochs is determined based on when a signal returns to a same value as an offset for the type-B peak, or a threshold time, whichever occurs first.

### Claim 46 (depends on 1)

The method of claim 1, wherein the plurality of parameters comprise a badInPool parameter, and a plurality of additional parameters, and wherein determining a value of the badInPool parameter comprises:
determining a count of a number of the additional parameters that, for each additional parameter, have a value for the test patient that has a probability of being in a normal value distribution that is smaller than a smallest normal test patient probability of being in the normal value distribution.

### Claim 47 (depends on 1)

The method of claim 1, wherein the plurality of parameters comprise a weightInPool parameter, and a plurality of additional parameters, and wherein determining a value of the weightInPool parameter comprises:
summing, for each of the additional parameters, a difference between a smallest normal test patient probability of being in a normal value distribution, and a probability of a value of the additional parameter for the test patient being in the normal value distribution.

### Claim 48 (depends on 1)

The method of claim 1 wherein the model is a one-step model configured to classify the test patient as cognitively impaired or not-cognitively impaired.

### Claim 49 (depends on 1)

The method of claim 1 wherein the model is a two-part model, the model comprising a first part configured to predict a mini-mental state examination (MMSE) score for test patient, and a second part configured to classify the test patient as cognitively impaired or not-cognitively based on the predicted MMSE score.

### Claim 50 (depends on 1)

The method of claim 1 wherein the model was trained using at least one of a random forest model, a gradient boosting model, a support vector machine (SVM) model, a linear SVM model, a radial basis function kernel SVM, a linear regression, and a logistic regression.

### Claim 51 (depends on 1)

The method of claim 1 wherein A-type peaks occur in epochs in the range of about 50 to 100 ms after the auditory stimulus event.

### Claim 52 (depends on 1)

The method of claim 1 wherein B-type peaks occur in epochs in the range of about 100 to 200 ms after the auditory stimulus event.

### Claim 53 (depends on 1)

The method of claim 1 wherein C-type peaks occur in epochs in the range of about 200 to 400 ms after the auditory stimulus event.

### Claim 54 (depends on 1)

The method of claim 1, further comprising the earlier steps of:
transmitting from an audio speaker the plurality of auditory stimulus events; and
recording the set of epochs with a MEG sensor located proximally to the brain of the test patient.

### Claim 55 (depends on 54)

The method of claim 54 wherein the MEG sensor is a SQUID.

### Claim 56 (depends on 54)

The method of claim 54, further comprising:
recording at least one additional set of epochs with at least one additional MEG sensor also located proximally to the brain of the test patient, each of the MEG sensors located at a different location around the brain of the test patient.

### Claim 57 (depends on 56)

The method of claim 56, further comprising:
processing the sets of epoch to identify the MEG sensor having a highest percentage of epochs having a type-A peak; and
wherein accessing the set of epochs of MEG data comprises accessing the set of epochs associated with the MEG sensor having the highest percentage of epochs having the type-A peak.

### Claim 58 (depends on 56)

The method of claim 56, further comprising:
processing the sets of epoch to identify the MEG sensor having a highest percentage of epochs having a type-B peak; and
wherein accessing the set of epochs of MEG data comprises accessing the set of epochs associated with the MEG sensor having the highest percentage of epochs having the type-B peak.

### Claim 59 (depends on 56)

The method of claim 56, further comprising:
processing the sets of epoch to identify the MEG sensor having a highest intensity of a type-A peak in an epoch; and
wherein accessing the set of epochs of MEG data comprises accessing the set of epochs associated with the MEG sensor having the highest intensity of the type-A peak.

### Claim 60 (depends on 56)

The method of claim 56, wherein the MEG sensors are located on an ipsilaterial side the brain of the test patient.

### Claim 61 (depends on 56)

The method of claim 56 wherein the auditory stimulus events are approximately 50 milliseconds in duration.

### Claim 62 (depends on 56)

The method of claim 56 wherein the auditory stimulus events are spaced at least 500 milliseconds apart.

### Claim 63 (depends on 54)

The method of claim 54 wherein the auditory stimulus events comprise tones between 600 to 700 Hertz, inclusive.

### Claim 64 (depends on 1)

The method of claim 1 wherein the set of epochs comprises at least 250 epochs.

### Claim 65

A method comprising:
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 a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values, at least one of the parameter values determined based on analyzing MEG data from individual epochs within at least one of the set of epochs and the tri-peak subset of epochs;
inputting the parameter values into a model that is trained based on the parameters to determine whether the test patient is cognitively impaired; and
providing the determination.

### Claim 66

A method comprising:
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 a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining, a plurality of parameter values, the determining comprising
identifying a strongA subset of the epochs of the set having a strongest amplitude for the type-A peak relative to the other epochs in the set;
determining a strongA_Bnum parameter representing a count of the epochs in the strongA subset having a type-B peak;
identifying a weakA subset of the epochs of the set having a weakest amplitude for the type-A peak relative to the other epochs in the tri-peak sub set;
determining a weakA_B amp parameter representing a measure of amplitudes of the type-B peaks of the epochs in the weakA subset;
determining a weakA_Camp parameter representing a measure of amplitudes of the type-C peaks of the epochs in the weakA subset;
an A*B*C parameter representing a count of the epochs in the tri-peak subset; and
a nA parameter representing a count of the epochs in the set having a type-A peak;
inputting the parameter values into a model that is trained based on the parameters to determine whether the test patient is cognitively impaired; and
providing the determination.

### Claim 67

A method of diagnosing cognitive impairment in a patient, the method comprising:
accessing a set of epochs of magnetoencephalography (MEG) data of responses of the patient's brain to a plurality of auditory stimulus events;
processing the set of epochs to identify a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak sub set;
inputting the parameter values into a model that is trained based on the parameters to determine whether a patient is cognitively impaired; and
providing the determination.

### Claim 68

A method of diagnostically discriminating cognitive impairment in a patient caused by neurodegeneration from cognitive impairment of other etiology, the method comprising:
accessing a set of epochs of magnetoencephalography (MEG) data of responses of the patient's brain to a plurality of auditory stimulus events;
processing the set of epochs to identify a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak sub set;
inputting the parameter values into a model that is trained based on the parameters to determine whether a patient is cognitively impaired and to discriminate cognitive impairment caused by neurodegeneration from cognitive impairment of other etiology; and
providing the determination.

### Claim 69

A method of treating a patient having cognitive impairment, the method comprising:
administering a therapeutically effective amount of an anti-cognitive impairment therapeutic agent to a patient who has been determined to have cognitive impairment,
wherein the determination was made by a method comprising
accessing a set of epochs of magnetoencephalography (MEG) data of responses of the patient's brain to a plurality of auditory stimulus events;
processing the set of epochs to identify a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak subset;
inputting the parameter values into a model that is trained based on the parameters to determine whether a patient is cognitively impaired and to discriminate cognitive impairment caused by neurodegeneration from cognitive impairment of other etiology; and
providing the determination.

### Claim 70 (depends on 69)

The method of claim 69, further comprising the antecedent step of determining that the patient has cognitive impairment, wherein the determination is made by a method comprising
processing the set of epochs to identify a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak subset;
inputting the parameter values into a model that is trained based on the parameters to determine whether a patient is cognitively impaired and to discriminate cognitive impairment caused by neurodegeneration from cognitive impairment of other etiology; and
providing the determination.

### Claim 71 (depends on 70)

The method of claim 70, wherein the anti-cognitive impairment therapeutic agent is a disease-modifying anti-neurodegeneration agent.

### Claim 72 (depends on 71)

The method of claim 71, wherein the disease-modifying anti-neurodegeneration agent binds to one or more of beta-secretase 1 (BACE-1), gamma secretase, Tau, Aβ, amyloid precursor protein (APP), α-synuclein, leucine rich repeat kinase 2 (LRRK2), parkin, presenilin 1, presenilin 2, apolipoprotein E4 (ApoE4), huntingtin, p75 neurotrophin receptor (p75NTR), CD20, prion protein (PrP), and death receptor 6 (DR6).

### Claim 73 (depends on 70)

The method of claim 70, wherein the anti-cognitive impairment therapeutic agent is a cognitive symptom enhancement agent.

### Claim 74

A method of setting the dosage of an anti-cognitive impairment therapeutic agent in a patient having cognitive impairment, comprising:
accessing a set of epochs of magnetoencephalography (MEG) data of responses of the patient's brain to a plurality of auditory stimulus events;
processing the set of epochs to identify a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak sub set;
inputting the parameter values into a model that is trained based on the parameters to determine whether a patient is cognitively impaired and to discriminate degrees of cognitive impairment; and
providing the determination as to degree of cognitive impairment; and
setting the dosage of the anti-cognitive impairment therapeutic agent based on the determined degree of the patient's cognitive impairment.

### Claim 75

A method of titrating the dosage of an anti-cognitive impairment therapeutic agent in a patient having cognitive impairment, comprising:
performing a first determination and a second determination of the degree of cognitive impairment at a spaced interval during which interval the patient has been receiving an anti-cognitive impairment therapeutic agent at a first dosage level; and
increasing the dose of the anti-cognitive impairment therapeutic agent to a second dosage level if the degree of cognitive impairment has increased between the first and second determinations,
wherein each of the first and second determinations is made by
accessing a set of epochs of magnetoencephalography (MEG) data of responses of the patient's brain to a plurality of auditory stimulus events;
processing the set of epochs to identify a tri-peak subset of the epochs, each epoch in the subset comprising a first peak, a second peak, and a third peak;
determining a plurality of parameter values by analyzing the individual epochs of the MEG data,
at least one of the parameter values determined based on a count of epochs in the set having one or more of the first, second, and third peaks; and
at least one of the parameter values determined based on amplitudes of one of first, second, and third peaks of at least some of the epochs in the tri-peak subset;
inputting the parameter values into a model that is trained based on the parameters to discriminate degrees of cognitive impairment; and
providing the determination as to degree of cognitive impairment.
