System and method for collecting retinal signal data and removing artifacts

Abstract

A method and system for generating retinal signal data is disclosed. Calibration data corresponding to an individual can be received. A threshold impedance can be determined based on the calibration data. Retinal signal data corresponding to the individual can be received. An impedance of a circuit that collects the retinal signal data can be compared to the threshold impedance to determine whether the retinal signal data includes an artifact. A portion of the retinal signal data corresponding to the artifact can be removed from the retinal signal data.

Description

[Technical Field]

[0001] Cross-reference of related applications This application claims the interests of U.S. Provisional Patent Application No. 63 / 038,257, filed June 12, 2020; U.S. Provisional Patent Application No. 63 / 149,508, filed February 15, 2021; and International Application PCT / CA2021 / 050390 and U.S. Patent Application No. 17 / 212,410, both filed March 25, 2021. Each of the applications mentioned in this paragraph is incorporated herein by reference in its entirety.

[0002] This technology relates to a system and method for collecting and / or processing retinal signal data generated by light stimulation. [Background technology]

[0003] A signal is generally a function that conveys information about the operation of a physical or physiological system, or the attributes of some phenomenon. Signal processing is the process of extracting information from a signal. Retinal signal data, such as electroretinogram (ERG) data, may be collected for analysis. Retinal signal data can be collected using sensors, such as one or more electrodes attached to an individual. Electrodes can capture electrical signals. Light stimulators can be used to trigger electrical signals. Retinal signal data can be used by physicians as a diagnostic aid.

[0004] During the capture of retinal signal data, an individual's movement may affect the retinal signal data. This may be more common for individuals who are sensitive to their mental state, because these individuals may find it more difficult to remain still while retinal signal data is being captured. Furthermore, these movements are more likely to occur when the time for which retinal signal data is recorded is extended. The objective of this technology is to improve upon at least some of the limitations present in prior art. [Overview of the Initiative] [Means for solving the problem]

[0005] Embodiments of this technology were developed based on the developers' recognition of certain shortcomings associated with existing systems for collecting, processing, and / or analyzing retinal signal data. Retinal signal data may contain artifacts. These artifacts can hinder further analysis of the retinal signal data. It may be desirable to use retinal signal data that is free of artifacts and / or contains few artifacts. Whether or not the retinal signal data contains artifacts can be determined by using the dynamic resistance of the circuit collecting the retinal signal data, such as the impedance of the circuit.

[0006] Embodiments of this technology were developed based on the developers' observation that data obtained from electroretinography (ERG) can provide some insight into conditions such as medical status. However, existing methods for collecting and analyzing ERGs can only collect and analyze a limited amount of information from the acquired electrical signals. It has been found that expanding the amount of information collected regarding the retina's response to light stimuli makes it possible to generate retinal signal data that contains higher density information, more information, and / or additional types of information. This retinal signal data enables multimodal mapping of electrical signals and / or other data, and allows for the detection of additional features of multimodal mapping specific to particular conditions. Multimodal mapping may include multiple parameters of the retinal signal data, such as time, frequency, light stimulus parameters, and / or any other parameters.

[0007] Some parameters or data that directly affect electrical signals may not be collected during conventional ERG recording. However, the triggered electrical signal may directly depend on these parameters. These parameters may include real-time measurements of the optical spectrum, light intensity, illumination area, and / or the impedance of the circuit collecting the electrical signal.

[0008] Embodiments of this technology form the basis for collecting and / or processing retinal signal data that has more information, more information density, and / or additional types of information detail compared to conventional ERG data. The number and / or range of light intensity of the light stimulation may be increased. In certain embodiments, this retinal signal data enables mathematical modeling of datasets containing a large amount of information, identification of retinal signal features, and the ability to identify biological labels and / or indicators of life presence in the retinal signal data using, for example, retinal signal features. Certain non-essential embodiments of this technology also provide methods for collecting retinal signal data that has more information, more information density, and / or additional types of information compared to conventional ERG data.

[0009] In some cases, retinal signal data, or other signal data related to light stimulation, may contain artifacts. Artifacts may include distorted signals, interference, and / or other types of artifacts. Artifacts can be caused by one or more of the following: inadvertent capture of signals not originating from the retina, changes in electrode position, changes in contact of ground or reference electrodes, photomyoclonic reflexes, eyelid blinking, eye movements, and / or external electrical interference. These artifacts may limit or distort further analysis of retinal signal data. It would be beneficial if these artifacts could be removed, compensated for, or prevented.

[0010] Parameters of electrical signals emitted by an individual, such as voltage, current, impedance, and / or other parameters, can be measured. These parameters may be measured continuously over a period of time. During this period, the individual may be exposed to a flash of light. Data collected before the flash may be used as calibration data. Data collected after the flash may be retinal signal data. Baseline parameters of the electrical circuit capturing the electrical signal can be determined using calibration data such as baseline voltage, baseline current, baseline impedance, and / or any other parameters. The threshold impedance is determined based on the baseline impedance. Retinal signal data can be compared to the threshold impedance. If the impedance of the circuit during retinal signal data acquisition exceeds the threshold impedance, the retinal signal data may be determined to have artifacts. To indicate the presence of artifacts, the amount of change in the circuit's impedance and / or the rate of change in impedance may also be determined.

[0011] In conventional ERGs, flashes with the same parameters may be repeated multiple times, for example, 10 times. An electrical signal in response to each flash may be collected. Data on these electrical signals may be averaged, for example, by determining the average voltage of the electrical signals. To mitigate the impact of artifacts on the collected data, the same flash (i.e., flashes with the same flash parameters) may be repeated. For example, if a flash is repeated 10 times and an artifact occurs in the electrical signal in response to one of those flashes, the impact of these artifacts is mitigated by combining the data collected after that flash with the data collected after the other 9 flashes.

[0012] Artifacts can be detected by other means, such as monitoring the dynamic resistance of the acquisition circuit, including the impedance, admittance, and / or susceptance of the circuit that acquires the electrical signal. Retinal signal data can be acquired in response to a single flash and / or a reduced number of flashes, rather than repeating the same flash multiple times. The retinal signal data can be analyzed to determine whether the retinal signal data contains artifacts. For example, the impedance of the retinal signal data can be compared to a threshold impedance. If the impedance of the retinal signal data does not exceed the threshold impedance, the retinal signal data can be determined to be artifact-free. The retinal signal data can then be saved. In this way, retinal signal data can be acquired without repeating flashes with the same parameters, and / or the number of times flashes with the same parameters are repeated can be reduced. This can shorten the time used to acquire retinal signal data and reduce the impact of artifacts on the retinal signal data.

[0013] In certain embodiments, more efficient processing of retinal signal data is possible compared to ERG data. The advantage of retinal signal data compared to conventional ERG data is that it benefits from a large amount of information related to electrical signals and additional retinal signal functions. This additional data can be used to identify artifacts in the retinal signal data, remove artifacts in the retinal signal data, reduce artifacts in the retinal signal data, and / or compensate for artifacts in the retinal signal data.

[0014] In certain embodiments, artifacts are detected and / or removed from retinal signal data. Artifacts may be detected and / or removed in real time after the collection of retinal signal data is complete and / or during the collection of retinal signal data. If an artifact is detected during the collection of retinal signal data, an indicator that an artifact has been detected may be displayed to the operator. The parameters of a flash triggered before the retinal signal data containing the artifact can be determined, and a flash with the same parameters can be triggered. Retinal signal data occurring after that flash may be captured and / or stored for further analysis.

[0015] According to a first broad aspect of the present technology, a method is provided which is performed by at least one processor of a computing system, the method comprising: receiving retinal signal data corresponding to an individual; determining that the retinal signal data contains one or more artifacts by determining that the impedance of the circuit that collected the retinal signal data exceeds the threshold impedance of the circuit; modifying the retinal signal data to compensate for the artifacts; and storing the retinal signal data.

[0016] In some implementations of this method, the step of modifying retinal signal data to compensate for artifacts includes the step of removing at least a portion of the retinal signal data corresponding to the artifacts.

[0017] Some implementations of this method further include the steps of receiving calibration data corresponding to an individual, and determining the threshold impedance of a circuit based on the calibration data.

[0018] In some implementations of this method, retinal signal data is collected in response to at least one flash from a photostimulator, and calibration data is collected before the at least one flash by the same circuit that collected the retinal signal data, and the method further includes the step of generating at least one flash in the photostimulator.

[0019] In some implementations of this method, the retinal signal data has a sampling frequency between 4 kHz and 24 kHz.

[0020] In some implementations of this method, the retinal signal data is collected over a signal acquisition time of 200 milliseconds to 500 milliseconds.

[0021] In some implementations of this method, one or more artifacts include distortion of the retinal signal data.

[0022] In some implementations of this method, one or more artifacts are caused by one or more of: capture of electrical signals not originating from the retina, shift of electrode positions, change in contact of the ground or reference electrode, photomyoclonic reflex, eyelid blink, and eye movement.

[0023] In some implementations of this method, the method further includes: extracting one or more features of the retinal signal from the retinal signal data; extracting one or more descriptors from the features of the retinal signal; applying the one or more descriptors to a first mathematical model and a second mathematical model, where the first mathematical model corresponds to a first condition and the second mathematical model corresponds to a second condition, thereby generating a first prediction probability for the first condition and a second prediction probability for the second condition; and outputting the first prediction probability and the second prediction probability.

[0024] According to another broad aspect of the present technology, a method is provided that is executed by at least one processor of a computing system, the method including: receiving retinal signal data corresponding to an individual; determining that there are one or more artifacts in the retinal signal data by determining that an impedance of a circuit that collected the retinal signal data exceeds a threshold impedance of the circuit; storing an indicator in the retinal signal data for a period corresponding to the one or more artifacts; and storing the retinal signal data.

[0025] Some implementations of this method further include the steps of receiving calibration data corresponding to an individual, and determining the threshold impedance of a circuit based on the calibration data.

[0026] In some implementations of this method, the method further includes the step of determining the duration corresponding to one or more artifacts by determining the duration for which the impedance of the retinal signal data exceeds a threshold impedance.

[0027] In some implementations of this method, retinal signal data is collected in response to at least one flash from an optical stimulator, and calibration data is collected prior to at least one flash. The method further includes the step of generating at least one flash in the optical stimulator.

[0028] In some implementations of this method, the retinal signal data has a sampling frequency between 4 and 24 kHz.

[0029] In some implementations of this method, retinal signal data is collected over a signal acquisition time of 200 milliseconds to 500 milliseconds.

[0030] In some implementations of this method, one or more artifacts include distortions in the retinal signal data.

[0031] In some implementations of this method, one or more artifacts were caused by one or more of the following: capture of electrical signals not originating from the retina, shift in electrode position, changes in contact of the ground or reference electrode, photomyoclonic reflex, eyelid blinking, and eye movements.

[0032] In some implementations of this method, the method further includes the steps of: extracting one or more retinal signal features from retinal signal data; extracting one or more descriptors from the retinal signal features; applying one or more descriptors to a first mathematical model and a second mathematical model, wherein the first mathematical model corresponds to a first condition and the second mathematical model corresponds to a second condition, thereby generating a first predicted probability for the first condition and a second predicted probability for the second condition; and outputting the first predicted probability and the second predicted probability.

[0033] According to another broad aspect of the present technology, a method is provided which is performed by at least one processor of a computing system, and this method The steps include recording a first retinal signal dataset corresponding to an individual, The method includes the steps of determining that the first retinal signal dataset contains one or more artifacts by determining that the impedance of the circuit that collected the first retinal signal dataset exceeds a first threshold impedance of the circuit; recording a second retinal signal dataset corresponding to an individual; determining that the impedance of the circuit does not exceed a second threshold impedance of the circuit while recording the second retinal signal dataset; and saving the second retinal signal dataset.

[0034] In some implementations of this method, the method further includes the steps of recording a first calibration dataset corresponding to an individual before recording a first retinal signal dataset, determining a first threshold impedance of a circuit based on the first calibration dataset, recording a second calibration dataset corresponding to an individual before recording a second retinal signal dataset, and determining a second threshold impedance of a circuit based on the second calibration dataset.

[0035] In some implementations of the present method, the method further includes the steps of: recording a first calibration dataset, then triggering a photostimulator to generate a first flash based on a set of flash parameters, wherein the first retinal signal dataset responds to the first flash; and recording a second calibration dataset, then triggering a photostimulator to generate a second flash based on a set of flash parameters, wherein the second retinal signal dataset responds to the second flash.

[0036] In some implementations of this method, the first retinal signal dataset and the second retinal signal dataset have sampling frequencies between 4 and 24 kHz.

[0037] In some implementations of this method, the first and second retinal signal datasets are collected over signal acquisition times ranging from 200 milliseconds to 500 milliseconds.

[0038] In some implementations of this method, the method further includes the steps of: extracting one or more retinal signal features from a second retinal signal dataset; extracting one or more descriptors from the retinal signal features; applying one or more descriptors to a first mathematical model and a second mathematical model, wherein the first mathematical model corresponds to a first condition and the second mathematical model corresponds to a second condition, thereby generating a first predicted probability for the first condition and a second predicted probability for the second condition; and outputting the first predicted probability and the second predicted probability.

[0039] According to another broad aspect of the present technology, a method is provided which is performed by at least one processor of a computing system, the method comprising the steps of: receiving retinal signal data corresponding to an individual; inputting the retinal signal data into a machine learning algorithm (MLA), the MLA being trained using labeled retinal signal data, wherein each retinal signal dataset in the labeled retinal signal data includes a label indicating whether each retinal signal dataset contains artifacts; outputting retinal signal data adjusted by the MLA; and storing the adjusted retinal signal data.

[0040] In some implementations of this method, the retinal signal data has a sampling frequency between 4 and 24 kHz.

[0041] In some implementations of this method, retinal signal data is collected over a signal acquisition time of 200 milliseconds to 500 milliseconds.

[0042] In some implementations of this method, MLA removes the portion of the retinal signal data corresponding to the artifact.

[0043] In some implementations of this method, MLA adds an indicator to the retinal signal data that shows which parts of the retinal signal data contain artifacts.

[0044] In the context of this specification, unless otherwise specified, the terms “computer-readable media” and “memory” are intended to include media of all natures and types, non-exclusive examples of which include RAM, ROM, disks (such as CD-ROMs, DVDs, floppy disks, and hard disk drives), USB keys, flash memory cards, solid-state drives, and tape drives.

[0045] In the context of this specification, “database” means a collection of structured data, regardless of its specific structure, database management software, or the computer hardware on which the data is stored, implemented, or otherwise made available. A database may reside on the same hardware as the processes that store or use the information stored in it, or it may reside on separate hardware, such as a dedicated server or multiple servers.

[0046] In the context of this specification, unless otherwise specified, words such as “first,” “second,” and “third” are used as adjectives solely for the purpose of distinguishing the nouns they modify from one another, and not to describe any particular relationship between these nouns.

[0047] Each embodiment of the present technology has at least one of the above-described objectives and / or aspects, but not necessarily all of them. It should be understood that some aspects of the present technology resulting from attempts to achieve the above-described objectives may not satisfy these objectives and / or may satisfy other objectives not specifically described herein.

[0048] Additional and / or alternative features, aspects, and advantages of embodiments of this technology will become apparent from the following description, the accompanying drawings, and the accompanying claims.

[0049] To better understand this technology, as well as other aspects and further features, refer to the following description used in conjunction with the accompanying drawings. [Brief explanation of the drawing]

[0050] [Figure 1] This is a block diagram illustrating an exemplary computing environment according to various embodiments of this technology. [Figure 2] This is a block diagram of a retinal signal data processing system according to various embodiments of this technology. [Figure 3]This is a diagram illustrating an exemplary electrode arrangement for collecting retinal signal data according to various embodiments of this technology. [Figure 4] This is a flowchart illustrating methods for compensating for artifacts in retinal signal data using various embodiments of this technology. [Figure 5] This is a flowchart illustrating methods for detecting artifacts and issuing warnings during retinal signal data acquisition using various embodiments of this technology. [Figure 6] This is a flowchart illustrating how to remove artifacts from retinal signal data using machine learning algorithms (MLAs) according to various embodiments of this technology. [Figure 7] This is a flowchart illustrating a method for predicting the likelihood of a medical condition using various embodiments of this technology. [Figure 8] This figure shows three-dimensional retinal signal data generated by various embodiments of this technology at a sampling frequency of 16 kHz under bright-room conditions (adjusted to background light) with 45 light intensity steps from 0.4 cd.sec / m2 to 794 cd.sec / m2. [Figure 9] This figure shows the three-dimensional impedance of retinal signal data generated at 45 levels of light intensity (luminance) from 0.4 cd.sec / m2 to 794 cd.sec / m2 under various embodiments of this technology, as well as the impedance captured simultaneously with the amplitude of the retinal signal at a sampling frequency of 16 kHz. [Figure 10] This figure shows four-dimensional retinal signal data (amplitude vs impedance vs stimulation light brightness vs time) generated under bright-light conditions (adjusted to background light) at 45 light intensity (luminance) levels from 0.4 cd.sec / m2 to 794 cd.sec / m2, according to various embodiments of this technology, and simultaneous impedance captured at a sampling frequency of 16 kHz. [Figure 11]This figure shows 4D retinal signal data (amplitude vs impedance vs stimulation light brightness vs time) generated under various embodiments of this technology in bright light conditions (adapted to background light) at a sampling frequency of 4 kHz with 75 increased spectral intensities (luminance) from 0.4 cd.sec / m2 to 851 cd.sec / m2. A change in impedance is observed during signal recording at luminance 9 (0.9 cd.sec / m2) and 72 (624 cd.sec / m2), with the impedance higher than the baseline value of not exceeding 500 ohms, indicating the presence of two distortions in the signal. [Figure 12] This figure shows four-dimensional retinal signals (current vs. admittance vs. stimulated light luminance vs. time) generated (adapted to background light) at 75 levels of light intensity (luminance) from 0.4 cd.sec / m2 to 851 cd.sec / m2 in bright light conditions at a sampling frequency of 4 kHz, according to various embodiments of this technology. At luminance levels 9 (0.9 cd.sec / m2) and 72 (624 cd.sec / m2), impedance changes detected during signal recording, as shown in Figure 11, were rejected by this technology, and the signals were corrected accordingly. [Figure 13] This figure shows the four-dimensional retinal signal (current vs. admittance vs. stimulus light luminance vs. time) generated (adapted to background light) at 75 levels of light intensity (luminance) from 0.4 cd.sec / m2 to 851 cd.sec / m2 under bright light conditions with a sampling frequency of 4 kHz. Two distortions found in the retinal signal recording shown in Figure 11 were corrected at luminances of 9 (0.9 cd.sec / m2) and 72 (624 cd.sec / m2), respectively. [Modes for carrying out the invention]

[0051] Please note that unless otherwise explicitly specified in this specification, the drawings are not to a fixed scale.

[0052] Specific aspects and embodiments of this technology relate to methods and systems for collecting retinal signal data. Generally, specific aspects and embodiments of this technology include, for example, the process of acquiring retinal signal data by the steps of: expanding the conditions of the light stimulus (e.g., the number and range of light intensities); recording the dynamic resistance (impedance) of the circuit used to collect the retinal signal with the electrical components of the signal itself; capturing retinal signal data over longer periods of time; and / or capturing retinal signal data at higher frequencies (sampling rates). The retinal signal data may be analyzed and / or processed to remove artifacts within the retinal signal data. Artifacts may be caused by the capture of electrical signals that do not originate from the retina. Artifacts may include distorted electrical signals in the retinal signal data that may be caused by, for example, a shift in the position or contact with the surface of the electrode from which the signal is collected, a change in contact with the ground or reference electrode, a photomyoclonic reflection, eyelid blinking, and / or eye movements. Artifacts may be detected and / or removed based on the impedance values ​​of the electrical circuit used to collect the retinal signal data. Based on impedance values, the signal amplitude values ​​of retinal signal data can be corrected. Portions of retinal signal data corresponding to artifacts can be removed from the retinal signal data.

[0053] The characteristics of a light stimulus, such as its light spectrum, intensity, and / or duration, or the surface it irradiates, can directly influence the electrical signals induced by the light stimulus. These characteristics can be measured in real time during the acquisition of retinal signal data. These characteristics can lead to more accurate recording and / or analysis of the electrical signals.

[0054] Certain aspects and embodiments of this technology provide a method and system for converting retinal signal data (voltage amplitude) into current values ​​(charge flow) by using real-time recording of impedance. This conversion can be performed in real time during the acquisition of retinal signal data.

[0055] Certain aspects and embodiments of this technology provide a method and system for detecting the occurrence of artifacts by analyzing the impedance of a circuit that collects electrical signals (including some or all of the electrode portions of the circuit). Artifact detection can be performed in real time during the collection of retinal signal data.

[0056] Certain aspects and embodiments of this technology provide methods and systems that can correct artifacts by converting retinal signal data into currents and analyzing the time-current function rather than the time-voltage function.

[0057] Certain aspects and embodiments of this technology provide methods and systems for removing artifacts by reconstructing retinal signal data based on a predefined impedance threshold.

[0058] The systems and methods described herein can be fully or at least partially automated to minimize clinician input in the acquisition and / or processing of retinal signal data.

[0059] The systems and methods described herein are based on retinal signal data that has a higher level of information compared to data captured by conventional ERGs. The collected retinal signal data can be analyzed using mathematical and statistical calculations to extract features of specific retinal signals. Retinal signal features may include parameters of the retinal signal data and / or features generated using the retinal signal data. Descriptors can be extracted from the retinal signal features. A graphical representation of the findings may be created and output to visually support the selections made when selecting the relevant retinal signal features and / or descriptors. Applications can apply mathematical and / or statistical analysis of the results to enable quantification of these retinal signal features and / or descriptors and comparison between various conditions. Based on retinal signal data and / or any other clinical information, classifiers can be constructed that describe vital indicators of the conditions identified in the retinal signal data. Individual retinal signal data can be collected, and the distance between the individual's retinal signal data and the identified vital indicators can be determined, for example, by using the classifiers.

[0060] Computing environment Figure 1 shows a computing environment 100 that can be used to implement and / or run any of the methods described herein. In some embodiments, the computing environment 100 may be implemented by any of the following: a conventional personal computer, a network device, and / or electronic devices (such as, but not limited to, mobile devices, tablet devices, servers, controller units, control devices, etc.), and / or any combination thereof suitable for the relevant task at hand. In some embodiments, the computing environment 100 comprises various hardware components, including one or more single-core or multi-core processors collectively represented by a processor 110, a solid-state drive 120, random-access memory 130, and an input / output interface 150. The computing environment 100 may be a computer specifically designed to run machine learning algorithms (MLAs). The computing environment 100 may be a general-purpose computer system.

[0061] In some embodiments, the computing environment 100 may be a subsystem of one of the systems listed above. In some other embodiments, the computing environment 100 may be a “off-the-shelf” general-purpose computer system. In some embodiments, the computing environment 100 may be distributed across multiple systems. The computing environment 100 may also be dedicated to the implementation of the Art. As those skilled in the Art will understand, several variations in how the computing environment 100 is implemented can be assumed without departing from the scope of the Art.

[0062] Those skilled in the art will understand that processor 110 generally represents processing power. In some embodiments, one or more dedicated processing cores can be provided instead of or in addition to one or more conventional central processing units (CPUs). For example, one or more graphics processing units 111 (GPUs), tensor processing units (TPUs), and / or other so-called acceleration processors (or processing accelerators) can be provided in addition to or in addition to one or more CPUs.

[0063] System memory typically includes random access memory 130, but more generally, it is intended to include any type of non-temporary system memory, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), read-only memory (ROM), or a combination thereof. While a solid-state drive 120 is shown as an example of a mass storage device, more generally, such a mass storage device may include any type of non-temporary storage device configured to store data, programs, and other information, and to make that data, programs, and other information accessible via the system bus 160. For example, a mass storage device may include one or more of a solid-state drive, a hard disk drive, a magnetic disk drive, and / or an optical disk drive.

[0064] Communication between various components of the computing environment 100 may be enabled by a system bus 160, which includes one or more internal and / or external buses (e.g., PCI bus, Universal Serial Bus, IEEE 1394 "FireWire" bus, SCSI bus, Serial-ATA bus, ARINC bus, etc.) to which various hardware components are electronically coupled.

[0065] The input / output interface 150 can enable networking functions such as wired or wireless access. For example, the input / output interface 150 may include, but is not limited to, network ports, network sockets, and network interface controllers. Several examples of how networking interfaces may be implemented will be apparent to those skilled in the art. For example, a network interface may implement specific physical and data link layer standards such as Ethernet, Fibre Channel, Wi-Fi, Token Ring, or serial communication protocols. These specific physical and data link layers provide the foundation for a complete network protocol stack, enabling communication between small groups of computers on the same local area network (LAN) and large-scale network communication via routable protocols such as the Internet Protocol (IP).

[0066] The input / output interface 150 may be coupled to the touchscreen 190 and / or one or more internal and / or external buses 160. The touchscreen 190 may be part of the display. In some embodiments, the touchscreen 190 is the display. The touchscreen 190 can also be referred to as the screen 190. In the embodiment shown in Figure 1, the touchscreen 190 comprises touch hardware 194 (e.g., pressure-sensitive cells embedded in a layer of the display that enable detection of physical interaction between the user and the display) and a touch input / output controller 192 that enables communication with the display interface 140 and / or one or more internal and / or external buses 160. In some embodiments, the input / output interface 150 may be coupled to, in addition to or instead of, the touchscreen 190, a keyboard (not shown), a mouse (not shown), or a trackpad (not shown) that allows the user to interact with the computing device 100.

[0067] According to some implementations of this technology, the solid-state drive 120 stores program instructions that are loaded into the random-access memory 130 and executed by the processor 110 to perform one or more operations as described herein. For example, at least a portion of the program instructions may be part of a library or application.

[0068] Retinal signal data processing system Figure 2 is a block diagram of the retinal signal data processing system 200 according to various embodiments of the present technology. The retinal signal data processing system 200 can collect retinal signal data from an individual. As described above, compared to conventional ERGs, the retinal signal data captured using the retinal signal data processing system 200 may include additional features and / or data such as impedance, higher measurement frequencies, extended range of retinal light stimulation, and / or longer measurement times. The retinal signal data processing system 200 can process and / or analyze the collected data. The retinal signal data processing system 200 may output the retinal signal data after detecting and / or removing artifacts such as distortion or interference from the retinal signal data.

[0069] It should be clearly understood that System 200 shown in the illustration is merely an illustrative implementation of the Art. Therefore, the following description is intended to be merely an illustrative example of the Art. This description is not intended to define the scope or indicate the boundaries of the Art. In some cases, examples of modifications to System 200 may be provided below, which may be useful. These are provided solely for the purpose of aiding understanding and do not define the scope or indicate the boundaries of the Art. These modifications are not an exhaustive list, and as those skilled in the art will understand, other modifications are likely possible. Furthermore, where this is not done (i.e., examples of modifications are not shown), it should not be interpreted that modifications are impossible and / or that what is described is the only way to implement that element of the Art. As those skilled in the art will understand, this is likely not the case. Furthermore, it should be understood that System 200 may, in some cases, provide a simpler implementation of the Art, in which case it is presented in this manner for the purpose of aiding understanding. As those skilled in the art will understand, various implementations of the Art may be more complex.

[0070] The retinal signal data processing system 200 may include an optical stimulator 205, which may be an optical stimulator for providing optical stimulation signals to an individual's retina. The retinal signal data processing system 200 may also include a sensor 210 for collecting electrical signals generated in response to optical stimulation. The retinal signal data processing system 200 may also include a data acquisition system 215, which may be a computing environment 100 for controlling the optical stimulator 205 and / or collecting data measured by the sensor 210. For example, the optical stimulator 205 and / or the sensor 210 may be commercially available ERG systems such as the Espion Visual Electrophysiology System from DIAGNOSYS, LLC or the UTAS and RETEVAL systems manufactured by LKC TECHNOLOGIES, INC.

[0071] The photostimulator 205 may be any type of light source capable of generating light within a specified range of wavelength, intensity, frequency, and / or duration, either alone or in combination. The photostimulator 205 can direct the generated light towards the individual's retina. The photostimulator 205 may include light-emitting diodes (LEDs) in combination with one or more other light sources, such as xenon lamps. The photostimulator 205 may provide a background light source.

[0072] The optical stimulator 205 may be configured to provide optical stimulation signals to the individual's retina. The collected retinal signal data may be dependent on the optical stimulation conditions. To maximize the potential for generating relevant retinal signal features in the retinal signal data, the optical stimulator 205 may be configured to provide a wide variety of optical conditions. The optical stimulator 205 may be configured to control the background light and / or the stimulation light directed to the retina when the light flashes.

[0073] The light stimulator 205 uses different background light wavelengths (e.g., approximately 300 to approximately 800 nanometers) and background light intensities (e.g., approximately 0.01 to approximately 900 cd / m²). 2) with different wavelengths (e.g., approximately 300 to approximately 800 nanometers), and light intensity (e.g., approximately 0.001 to approximately 3000 cd.s / m²). 2 The system may include any light source capable of generating a light beam with an illumination time (e.g., approximately 1 to approximately 500 milliseconds) and a time between each flash (e.g., approximately 0.2 to approximately 50 seconds).

[0074] The retinal signal data processing system 200 may include a sensor 210. The sensor 210 may be positioned to detect electrical signals from the retina. The sensor 210 may have one or more electrodes. The sensor 210 may be an electroretinogram sensor. Figure 3, described below, shows an example of electrode placement. A ground electrode may be placed in the skin in the center of the forehead. Reference electrodes for each eye may be placed in the earlobe, the temporal region near the eye, the forehead, and / or other skin areas. The ground electrode may function as a zero reference for the positive or negative polarity of the electrical signals. The ground electrode may be placed in the center of the forehead, the top of the head, and / or the wrist. Any part of the circuitry involved in acquiring electrical signals may benefit from real-time impedance monitoring.

[0075] Electrical signals from the retina can be triggered by light stimulation from the light stimulator 205 and collected as retinal signal data by the sensor 210. The retinal signal data can be collected by the sensor 210 by electrodes placed on the eyeball or in the nearby ocular region. Light can induce low-amplitude electrical signals generated by an individual's retinal cells. Different types of retinal cells are induced depending on the nature of the light (e.g., intensity, wavelength, spectrum, frequency, and duration of the flash) and the conditions of the light stimulation (e.g., background light, darkness, or the individual's light adaptation to this treatment), thus generating different electrical signals. These signals propagate within the eye and eventually through the optic nerve to the visual regions of the brain. However, like any electrical signal, they propagate in all possible directions depending on the conductivity of the tissue. Therefore, electrical signals can be collected in externally accessible tissues outside the eyeball, such as the conjunctiva.

[0076] There are several types of electrodes that can be used to collect electrical signals, and they are based on specific materials, conductivity, and / or shape. It should be understood that there are many possible designs for recording electrodes, and any suitable design or combination of designs can be used for sensor 210. Sensor 210 may include, for example, contact lenses, foils, wires, corneal wicks, wire loops, microfibers, and / or skin electrodes. Each electrode type has its own unique recording characteristics and inherent artifacts.

[0077] Electrical signals generated from the retina in response to light stimuli are collected by a circuit formed by different electrodes, such as the electrodes of sensor 210. The circuit may include preamplifiers, amplifiers, filters, analog-to-digital converters, and / or other electrical signal processing devices. The electrical signals may be collected as a potential difference between an electrode placed in the area receiving the electrical signals from the retina (such as the cornea or eyeball) (referred to as the "active" electrode) and an electrode placed nearby (referred to as the "reference" electrode). The potential difference is often collected relative to an electrical neutral point with respect to the ground electrode.

[0078] In addition to the sensor 210, the system 200 may also include other devices for monitoring and recording the light stimulus wavelength and / or light intensity. These devices may include a spectrometer, a photometer, and / or any other devices for collecting optical properties. The wavelength and / or light intensity of the light stimulus may affect the amount of light stimulus reaching the retina, and thus trigger a retinal signal in response to this stimulus. The collected light stimulus wavelength and / or light intensity data may be included in the retinal signal data. The collected light stimulus wavelength and / or light intensity data can be used to adjust various values ​​of the retinal signal data. These adjustments can be made after the collection of the retinal signal data and / or in real time during the collection of the retinal signal data.

[0079] In addition to the sensor 210, the system 200 may also include other devices (e.g., cameras for tracking pupil position and diaphragm) for monitoring eye position and / or pupil size, which both influence the amount of stimulating light reaching the retina and affect the electrical signals triggered in response to this stimulus. Eye position and / or pupil size data may be included in the retinal signal data. This data may be used to adjust the retinal signal data during and / or after its acquisition.

[0080] Electrical signals can be acquired between an active electrode (located above or near the eye) and a reference electrode. Electrical signals can be acquired with or without differential recording from a ground electrode. The electrodes of sensor 210 can be connected to a data acquisition system 215 which may include a recording device. Before being recorded, electrical signals can pass through any number of preamplifiers, amplifiers, filters, analog-to-digital converters, and / or any other signal processing devices. The data acquisition system 215 may enable amplification of the electrical signals and / or conversion of the electrical signals to digital signals for further processing. The data acquisition system 215 may implement frequency filtering that can be applied to the electrical signals from sensor 210. The data acquisition system 215 may store data representing the electrical signals in a database in the form of voltage versus time, etc.

[0081] The data acquisition system 215 may be configured to receive an individual's measured electrical signals from a sensor 210 and / or from stimulating light data from a light stimulator 205, and to store this acquired data as retinal signal data. The data acquisition system 215 may be operably coupled to a light stimulator 205, which may be configured to trigger electrical signals and provide data to the data acquisition system 215. The data acquisition system 215 can synchronize the light stimulation with the acquisition and recording of electrical signals. The data acquisition system 215 can acquire calibration data before the flash and retinal signal data after the flash. The calibration data and retinal signal data may have the same parameters and use the same circuitry.

[0082] The collected data may be provided to the data acquisition system 215 via any suitable method, such as a storage device (not shown) and / or a network. The data acquisition system 215 may be connectable to the sensor 210 and / or the optical stimulator 205 via a communication network (not shown). The communication network may be the Internet and / or an intranet. Multiple embodiments of the communication network can be envisioned and will be apparent to those skilled in the art.

[0083] Retinal signal data may include electrical response data (e.g., voltage and circuit impedance) with a light stimulation synchronization time (flash duration) and / or offset (baseline voltage and impedance before light stimulation), collected over several signal acquisition times (e.g., 5 to 500 milliseconds) at several sampling frequencies (e.g., 0.2 to 24 kHz). The data acquisition system 215 can acquire retinal signal data at frequencies (i.e., sampling rates) of 4 to 16 kHz or higher. This frequency may be higher than that of conventional ERGs. Electrical response data may be acquired continuously or intermittently.

[0084] Retinal signal data may include impedance measurements and / or other electrical parameters. Retinal signal data may include optical parameters such as changes in pupil size, illuminated retinal area, and / or applied luminance parameters (intensity, light frequency, signal sampling frequency). Retinal signal data may include population parameters such as age, sex, iris pigmentation, retinal pigmentation, and / or skin pigmentation as a surrogate for retinal pigmentation. Retinal signal data may include admittance, conductance, and / or susceptance data.

[0085] The data acquisition system 215 may include a sensor processor for measuring the impedance of an electrical circuit used to acquire retinal signal data. The impedance of the electrical circuit may be recorded simultaneously with the acquisition of other electrical signals. The acquired impedance data may be stored in the retinal signal data. A method for determining the impedance of the circuit simultaneously with the acquisition of electrical signals may be based on the process of injecting a reference signal of known frequency and amplitude through the recording channel of the electrical signal. This reference signal can then be filtered and processed individually. The electrode impedance can be calculated by measuring the magnitude of the output at the excitation signal frequency. The impedance can then be used as a covariate to increase the signal density along with the resistance of the circuit at each point in time of recording the electrical signal.

[0086] The data analysis system 220 can process the retinal signal data collected by the data acquisition system 215. The data analysis system 220 can use the recorded signal data and / or other information (related to the process of collecting the retinal signal data) to construct the retinal signal data and / or remove artifact components from the retinal signal data. The data acquisition system 215 can implement any of methods 800, 900, and / or 1000 (described in further detail below) for processing the retinal signal data. The data analysis system 220 can extract retinal signal features and / or descriptors from the retinal signal data and / or perform any other processing on the retinal signal data.

[0087] The data output system 225 can output data collected by the data collection system 215. The data output system 225 can output results generated by the data analysis system 220. The data output system 225 can output predictions, such as predictions of the likelihood that an individual is exposed to one or more conditions, such as a mental state. For each condition, the output indicates the predictability of the individual's exposure to that condition. The output can be used by clinicians to help determine whether an individual has a medical condition and / or which medical condition the individual has.

[0088] The data acquisition system 215, the data analysis system 220, and / or the data output system 225 may be accessed by one or more users through their respective clinics and / or servers (not shown). The data acquisition system 215, the data analysis system 220, and / or the data output system 225 may also be connected to retinal signal data management software that can further extract features of retinal signals and analyze embedded biomarkers and / or biosignals. The data acquisition system 215, the data analysis system 220, and / or the data output system 225 may also be connected to appointment management software that can schedule appointments or follow-ups based on status determinations according to embodiments of system 200.

[0089] The data acquisition system 215, the data analysis system 220, and / or the data output system 225 may be distributed across multiple systems and / or combined within one or more systems. The data acquisition system 215, the data analysis system 220, and / or the data output system 225 may be geographically dispersed.

[0090] Figure 3 is a diagram 300 of exemplary electrode placements for collecting retinal signal data according to various embodiments of the present technology. A ground electrode 310 can be placed in the skin in the center of the forehead. The ground electrode 310 can function as a zero reference for the positive or negative polarity of the electrical signals collected by the reference electrodes 320, 330, 340, and 350. The reference electrodes 320, 330, 340, and 350 capture electrical signals emitted from the individual. A circuit can be formed using the ground electrode 310 and / or the reference electrodes 320, 330, 340, and 350. Various parameters of the circuit, such as current, voltage, impedance, and / or other electrical parameters, can be recorded. The ground electrode 310 and the reference electrodes 320, 330, 340, and 350 may be of any type, may have any shape, may be made of any suitable material, and / or may be any combination of different types of electrodes. For example, the ground electrode 310 may be a first type electrode, and the reference electrodes 320, 330, 340, and 350 may be a second type electrode different from the first type electrode.

[0091] It should be understood that diagram 300 is just one example of electrode placement on an individual, and any number of electrodes can be used and / or placed in any other suitable area. For example, the ground electrode 310 can be placed on the individual's wrist instead of the forehead.

[0092] Movement of the ground electrode 310 and / or reference electrodes 320, 330, 340, and / or 350 during data acquisition can cause artifacts in the retinal signal data. The methods described below can be used to alert clinicians to the occurrence of artifacts, compensate for artifacts in the retinal signal data, and / or re-record retinal signal data affected by the artifacts. These methods can mitigate and / or eliminate the effects of electrodes placed in positions that may cause artifacts in the retinal signal data. By using the methods described below, errors occurring during electrode placement and / or data acquisition can be compensated for, and / or the effects of these errors can be mitigated.

[0093] How to remove distorted signals Figure 4 is a flowchart of Method 400 for compensating for artifacts in retinal signal data according to various embodiments of the present technology. Retinal signal data may or may have been recorded using the Retinal Signal Data Processing System 200. All or part of Method 400 may be performed by the Data Acquisition System 215, the Data Analysis System 220, and / or the Prediction Output System 225. In one or more embodiments, Method 400 or one or more steps thereof may be performed by a computing system such as the Computing Environment 100. Method 400 or one or more steps thereof may be embodied in computer executable instructions stored in a computer-readable medium such as a non-temporary mass storage device, loaded into memory, and executed by a CPU. It should be understood that Method 400 is illustrative and some or part of the steps in the flowchart may be omitted and / or the order may be changed.

[0094] In step 405, calibration data may be collected. Calibration data may be collected over a predetermined period, such as 20 milliseconds. During the collection of calibration data, the individual's retina may not be stimulated by the photostimulator. In other words, the individual may not be exposed to photostimulation during the recording of calibration data. In step 405, electrical parameters and / or any other data may be collected. Current, voltage, impedance, and / or any other parameters may be collected.

[0095] In step 405, baseline parameters such as baseline current, voltage, impedance, and / or any other parameters can be determined. Baseline parameters may be determined based on calibration data. Baseline parameters may be the mean or median of the parameters recorded in the calibration data. For example, baseline impedance may be determined as the average of the impedances recorded in the calibration data. Baseline parameters may be used for all subsequent measurements. For example, the average voltage can be determined and this average voltage can be subtracted from subsequent measurements, such as those performed in step 410.

[0096] In step 410, retinal signal data can be acquired from the individual. The retinal signal data may include covariates and parameters that may affect the nature and quality of the retinal signal data, such as the parameters of the light stimulus and the impedance of the receiving electrical circuit used to collect the retinal signal data. The electrical circuit may be implemented in the device. The retinal signal data may include measured electrical signals captured by electrodes placed on the individual. The retinal signal data may include parameters of the system used to acquire the retinal signal data, such as the parameters of the light stimulus. The retinal signal data may include the impedance of the receiving electrical circuit that measures the electrical signals.

[0097] Retinal signal data may include impedance measurements and / or other electrical parameters. Retinal signal data may include parameters such as eye position, pupil size, applied brightness intensity, frequency of light stimulation, frequency of retinal signal sampling, illumination wavelength, illumination duration, background light wavelength, and / or background light intensity. Retinal signal data may include clinical information cofactors such as age, sex, iris pigmentation, retinal pigmentation, and / or skin pigmentation as a surrogate for retinal pigmentation. Therefore, in certain embodiments, method 400 includes collecting impedance measurements in step 410. The same set of parameters may be recorded in steps 405 and 410.

[0098] To generate retinal signal data, an individual's retina may be stimulated, for example, by using an optical stimulator 205, which may be one or more optical stimulators. The retinal signal data may be collected by a sensor, such as a sensor 210, which may comprise one or more electrodes and / or other sensors.

[0099] The light stimulation device uses different background light wavelengths (e.g., approximately 300 to 800 nanometers) and background light intensities (e.g., approximately 0.01 to 900 cd / m²). 2 ) with different wavelengths (e.g., approximately 300 to approximately 800 nanometers), and light intensity (e.g., approximately 0.01 to approximately 3000 cd.s / m²). 2 This may include any light source capable of generating a light beam with an irradiation time (e.g., approximately 1 to approximately 500 milliseconds) and a time between each flash (e.g., approximately 0.2 to approximately 50 seconds).

[0100] The retinal signal data may include electrical response data (e.g., voltage and circuit impedance) with synchronization time (flash duration) and offset (baseline voltage and impedance before the light stimulus) of the light stimulus, collected over several signal acquisition times (e.g., 5 to 500 milliseconds) at several sampling frequencies (e.g., 0.2 to 24 kHz). Therefore, step 410 may include collecting retinal signal data at frequencies of 4 to 16 kHz.

[0101] Baseline parameters can also be used as offsets for current, voltage, and / or any other electrical parameters. For example, voltage and / or current can be normalized based on baseline voltage and / or baseline current.

[0102] Steps 405 and 410 can be repeated to collect retinal signal data. Calibration data can be recorded in step 405 before each flash from the optical stimulator 205. For example, calibration data can be collected for 20 ms before a flash, and retinal signal data can be collected in step 410 after the flash. Then, calibration data can be recorded in step 405 before the next flash. Figure 5 illustrates this sequence in more detail.

[0103] After retinal signal data is collected by a physician or other medical professional, the retinal signal data can be uploaded to a server, such as a data analysis system 220, for analysis. The retinal signal data can be stored in the memory 130 of a computer system. In another embodiment, the retinal signal data is uploaded to the data analysis system 220 in real time while it is being collected.

[0104] In step 415, the collected retinal signal data may be determined to contain artifacts, such as distorted signals. Distorted signals may include spikes or other anomalous features. Artifacts in electrical signals recorded from any electrodes placed in an individual's tissue may directly affect the amplitude, impedance, admittance, and / or conductance (the ability of electric charge to flow through a particular path) of the circuit in which the electrode is part. These artifacts may be detected by analyzing the retinal signal data over time and identifying changes in amplitude, impedance, admittance, and / or conductance that may indicate artifacts. Retinal signal data may be determined to be likely to contain artifacts based on the amount and / or rate of change in the impedance of the circuit.

[0105] By comparing retinal signal data to a predetermined standard or pattern, it is possible to determine whether artifacts are present in the retinal signal data. For example, abrupt changes in gradient and / or baseline, as well as very short-term large fluctuations in amplitude and / or impedance, may be identified as indicating artifacts. To determine whether artifacts are present, such as the rate of change of impedance, the rate of change of parameters in the retinal signal data may be analyzed. Artifacts may be present in the recorded electrical signals of retinal signal data and / or any other types of data contained within the retinal signal data.

[0106] The impedance of the collected retinal signal data can be compared to the baseline impedance determined using the calibration data recorded in step 405. A threshold impedance can be determined based on the calibration data. For example, the threshold impedance may be 10 percent higher than the baseline impedance determined in step 405. If the impedance of the retinal signal data consistently exceeds the threshold, it can be determined that the retinal signal data contains artifacts. A period corresponding to the impedance exceeding the threshold can be determined. Retinal signal data recorded during that period can be labeled as containing artifacts, and / or the retinal signal data corresponding to that period can be deleted.

[0107] In step 420, artifacts can be removed from the retinal signal data. The dynamic characteristics of the circuit used to collect the electrical signal can be used to determine which parts of the retinal signal data contain artifacts. For example, changes in conductance of a circuit including an "active" electrode and a "reference" electrode, or a circuit including an electrical neutral point relative to the ground electrode, are parameters used to detect and remove artifacts. The lower the impedance of the circuit used to collect the electrical signal, the better the quality of the collected electrical signal. The impedance of a suitable circuit for collecting retinal signal data is usually less than 5 kΩ. In some cases, with appropriate electrodes and circuitry, the impedance of a circuit including an "active" electrode and a "reference" electrode can be as low as 100 Ω.

[0108] Artifacts can be detected, compensated for, and / or eliminated using real-time impedance measurements that rectify the collected electrical signals with respect to the conductivity of the signal-collecting circuit. The electrical signals can be adjusted based on the characteristics of the stimulus that triggered the electrical signals (e.g., light intensity, light spectrum, irradiated retinal surface). These adjustments can eliminate and / or correct artifacts, such as by adjusting the amplitude of current and / or voltage.

[0109] The time periods corresponding to artifacts can be determined, and all or part of the signals recorded during those periods can be corrected or removed. Artifacts can be removed from the retinal signal data and / or ignored for subsequent signal analysis. For example, periods of retinal signal data can be labeled as corresponding to artifacts. Data collected during these periods may not be used when the retinal signal data is later analyzed.

[0110] Working at higher sampling frequencies and / or collecting large amounts of signal information can minimize the impact of removing any artifacts. The signal can also be corrected to some extent by considering the dynamics of the receiving circuit, which is based on adding conductance to the retinal signal data features (as an additional retinal signal feature of the retinal signal data).

[0111] Retinal signal data in response to individual flashes may be determined to contain artifacts, and all retinal signal data in response to that flash may be removed from the retinal signal data. A subset of retinal signal data in response to a flash may be deleted. For example, an electrical signal may be recorded for 200 milliseconds, and the impedance of the recording circuit may be below the threshold impedance in the first 150 milliseconds and above the threshold impedance in the last 50 milliseconds. The retinal signal data from the first 150 milliseconds may be saved and used for subsequent processing, but the retinal signal data from the last 50 milliseconds may not be saved and cannot be used for subsequent processing.

[0112] In step 425, retinal signal data may be re-recorded. A portion of the retinal signal data may be determined to be highly likely to contain artifacts. These periods may be determined based on impedance exceeding a threshold during the recording of the retinal signal data. Instead of removing artifacts in step 420, or in addition to doing so, portions of the retinal signal data affected by artifacts may be re-recorded. The stimuli applied to the individual during the period in which artifacts were detected may be reapplied, and the electrical signals generated in response to those stimuli may be recorded. Impedance may be monitored during the capture of the electrical signals. If the impedance remains below the threshold impedance, this indicates that the re-recorded data is likely to be free of artifacts, and the re-recorded data may be saved as retinal signal data. The original portions of the retinal signal data containing artifacts may be replaced with the re-recorded data.

[0113] In step 430, the recorded retinal signal data may be stored for further analysis. The retinal signal data may be used to predict whether an individual is exposed to a condition such as a mental disorder. Although method 400 is described herein as applicable to retinal signal data, it should be understood that method 400 may be applicable to any other type of collected signal data.

[0114] How to provide a distorted signal warning Figure 5 is a flowchart of Method 500 for detecting artifacts and issuing warnings during retinal signal data acquisition, according to various embodiments of the present technology. All or part of Method 500 may be performed by a data acquisition system 215, a data analysis system 220, and / or a predictive output system 225. In one or more embodiments, Method 500 or one or more steps thereof may be performed by a computing system, such as a computing environment 100. Method 500 or one or more steps thereof may be embodied in computer executable instructions stored in a computer-readable medium, such as a non-temporary mass storage device, loaded into memory, and executed by a CPU. It should be understood that Method 500 is illustrative, and some or part of the steps in the flowchart may be omitted and / or their order may be changed.

[0115] In step 505, calibration data may be recorded. The actions performed in step 505 may be similar to those described above with respect to step 405 of method 400. Baseline and / or threshold parameters may be determined based on the calibration data. For example, the baseline and threshold impedances may be determined in step 505.

[0116] In step 510, a flash can be triggered using predetermined parameters. These parameters may include brightness, wavelength, exposure time, background light wavelength, and / or background light intensity.

[0117] In step 515, retinal signal data can be obtained from the individual. The actions performed in step 510 may be the same as those described above with respect to step 410 of method 400. An indicator of the parameters of the flash triggered in step 510 may be stored along with the corresponding retinal signal data acquired in step 515.

[0118] In step 520, the collected retinal signal data may be compared to the threshold impedance determined in step 505 based on calibration data. If the collected retinal signal data in step 515 is always above the threshold, it may be determined that the retinal signal data contains and / or is likely to contain artifacts. The impedance of the circuit collecting the retinal signal data may be compared to the threshold impedance. If the impedance of the circuit collecting the retinal signal data is always above the threshold, it may be determined that the retinal signal data contains artifacts. The actions performed in step 515 may be similar to those described above with respect to step 415 of method 400. Although step 520 describes comparing impedance to threshold impedance, other indicators of the dynamic resistance of the circuit may be used. For example, threshold admittance and / or threshold susceptance may be determined. The admittance and / or susceptance of the circuit collecting the retinal signal data collected in step 515 may be compared to threshold admittance and / or threshold susceptance. If admittance and / or susceptance ever exceed the threshold, the collected retinal signal data may be determined to contain artifacts in step 520.

[0119] Artifact detection may be performed while retinal signal data is being collected in real time or near real time. Retinal signal data may be monitored continuously and / or over a predetermined period of time. All or part of the retinal signal data can be monitored to determine whether any artifacts are present in the data. Artifacts may appear in data relating to electrical signals within the retinal signal data, such as the amplitude of current and / or voltage of the collected electrical signals.

[0120] By comparing retinal signal data to a predetermined standard or pattern, it is possible to determine whether artifacts are present in the retinal signal data. For example, abrupt changes in gradient and / or baseline, as well as very short-term large fluctuations in amplitude and / or impedance, may be identified as indicating artifacts. Artifacts may be present in the recorded electrical signals of retinal signal data and / or any other types of data contained within the retinal signal data.

[0121] If the impedance exceeds a threshold impedance and / or if an artifact is detected using other techniques, method 500 may proceed to step 525. In step 525, a warning may be issued indicating that an artifact has been detected. The warning may be issued after one or more artifacts have been detected in the retinal signal data. A warning may be issued if the impedance exceeds a threshold impedance. For example, a warning may be issued if the position of the electrodes changes or moves during recording. For example, a warning may be issued due to any drift caused by eye movement or blinking. A warning may be issued after an artifact has been detected for a threshold period (e.g., 2 seconds). The warning may indicate the sensor causing the artifact. A warning may be issued based on abrupt changes in slope and / or baseline, and / or large fluctuations in amplitude and / or impedance. The warning may be an audible and / or visual warning.

[0122] In step 530, the operator may adjust the data acquisition system 215, sensor 210, and / or optical stimulator 205 based on the warning. The operator may adjust one or more sensors and / or any other part of the data acquisition system. The operator may be notified whether the adjustment was successful in correcting the problem, such as by the notification being cleared. Steps 525 and 530 are optional.

[0123] After step 530, the flash may be triggered again in step 510 using the same parameters. In step 515, the corresponding retinal signal data may be obtained, and in step 520, the retinal signal data may be compared to a threshold impedance to determine whether the retinal signal data contains artifacts. If the retinal signal data does not exceed the threshold impedance, method 500 may proceed to step 535. Otherwise, if the retinal signal data again contains artifacts, method 500 may proceed to step 525, and the same flash may be triggered in step 510.

[0124] In step 535, retinal signal data may be stored. The retinal signal data may be stored for further analysis, such as predicting whether an individual has a medical condition. The retinal signal data may be stored along with the flash parameters triggered in step 510. The actions performed in step 535 may be similar to those described above with respect to step 430 of method 400. Although method 500 is described herein as applicable to retinal signal data, it should be understood that method 500 may be applicable to any retinal signal data and / or any other type of collected signal data.

[0125] In step 540, the following set of parameters may be selected for the flash. A set of flash parameters may be predetermined, or the following set of parameters may be selected from a predetermined order. If there are no more parameters to select, method 500 may terminate. Otherwise, method 500 may proceed to step 510, where a flash may be triggered with the selected parameters.

[0126] Instead of checking the impedance in step 520 after each flash is triggered, artifact detection may be performed after all flashes have been triggered, or after a series of flashes have been triggered. For example, a series of flashes for a first luminance may be triggered, retinal signal data may be acquired for each flash, and then the impedance of the retinal signal data may be compared to the threshold impedance of each flash to determine whether any of the retinal signal data may contain artifacts. Then a series of flashes for a second luminance may be triggered. Calibration data may be collected before each flash, and a threshold impedance may be determined for each individual flash.

[0127] How to remove distorted signals using MLA Figure 6 is a flowchart of Method 600 for removing artifacts from retinal signal data using a machine learning algorithm (MLA) according to various embodiments of the present technology. All or part of Method 600 may be performed by a data acquisition system 215, a data analysis system 220, and / or a predictive output system 225. In one or more embodiments, Method 600 or one or any of its steps may be performed by a computing system, such as a computing environment 100. Method 600 or one or more of its steps may be embodied in computer executable instructions stored in a computer-readable medium, such as a non-temporary mass storage device, loaded into memory, and executed by a CPU. It should be understood that Method 600 is illustrative, and some or part of the steps in the flowchart may be omitted and / or their order may be changed.

[0128] In step 605, retinal signal data may be acquired from the individual. The retinal signal data may also be retinal signal data. The actions performed in step 605 may be the same as those described above with respect to step 410 of method 400. Calibration data may also be acquired, for example, before triggering the retinal signal data.

[0129] In step 610, all or part of the captured retinal signal data may be input to a machine learning algorithm (MLA). Calibration data may also be input to the MLA. The MLA may identify parts of the retinal signal data that contain artifacts. The MLA may be based on any suitable MLA architecture, such as a neural network, and may consist of one or more MLAs.

[0130] MLAs can remove artifacts based on predefined thresholds in the dynamics of the receiving circuit, such as impedance or signal amplitude thresholds, baselines, or changes to those parameters. MLAs can also remove artifacts based on learned patterns derived from signals containing known artifacts, identify various types of artifacts such as signal distortion, and / or remove unwanted signals not generated from the retina. Each of these individual tasks can be performed by a separate MLA. An MLA can output a reconstructed signal free of artifacts.

[0131] MLAs can be trained on labeled training data. Labelled training data may include datasets of retinal signal data affected by artifacts of known origin. Labels may indicate the nature of the artifact (e.g., electrode displacement, blinking, eye movements, and / or signal distortion such as drift or interference). After training, MLAs may be able to predict the duration of artifact occurrences. MLAs may also be able to predict the causes of artifacts.

[0132] MLA can be used to make predictions based on previously recorded data and / or data being recorded in real time. When MLA is used during signal acquisition, it may output a notification when artifacts are detected.

[0133] In step 615, the MLA may output adjusted retinal signal data from which artifacts have been removed. Artifacts may be compensated for by replacing them with other data, correcting distorted signals, or ignoring portions of the signal in which artifacts were detected.

[0134] In step 620, the adjusted retinal signal data may be stored. The actions performed in step 620 may be similar to those described above with respect to step 430 of method 400. Although method 600 is described herein as applicable to retinal signal data, it should be understood that method 600 may be applicable to any retinal signal data and / or any other type of collected signal data.

[0135] Methods for predicting the likelihood of a medical condition Figure 7 is a flowchart of Method 700 for predicting the likelihood of a medical condition according to various embodiments of the present technology. All or part of Method 700 may be performed by a data acquisition system 215, a data analysis system 220, and / or a prediction output system 225. In one or more embodiments, Method 700 or one or more steps thereof may be performed by a computing system, such as a computing environment 100. Method 700 or one or more steps thereof may be embodied in computer executable instructions stored in a computer-readable medium, such as a non-temporary mass storage device, loaded into memory, and executed by a CPU. It should be understood that Method 700 is illustrative, and some or part of the steps in the flowchart may be omitted and / or their order may be changed.

[0136] Method 700 includes steps of performing various activities, such as extracting retinal signal features from retinal signal data, as will be described in more detail below; selecting retinal signal features most relevant to a particular condition; combining and comparing these retinal features to generate mathematical descriptors best suited to the conditions being analyzed or compared; generating multimodal mappings; identifying biomarkers and / or indicators of life presence of a condition; and / or predicting the likelihood that a patient will fall into any of the conditions.

[0137] In step 705, retinal signal data may be received. Retinal signal data may be captured using a predefined acquisition protocol. Retinal signal data may include measured electrical signals captured by electrodes placed on the patient. Retinal signal data may include parameters of the system used to acquire retinal signal data, such as parameters of the light stimulus. Retinal signal data may include the impedance of the receiving electrical circuit used in the device that measures the electrical signals.

[0138] Retinal signal data may include impedance measurements and / or other electrical parameters. Retinal signal data may also include optical parameters such as changes in pupil size, and / or applied luminance parameters (intensity, wavelength, spectrum, frequency of light stimulation, frequency of retinal signal sampling).

[0139] After retinal signal data is collected by a physician or other medical professional, the retinal signal data may be uploaded to a server such as a data analysis system 220 for analysis. In step 705, retinal signal data may be retrieved from the data analysis system 220. The retinal signal data may be stored in the memory 130 of the computer system.

[0140] The retinal signal data received in step 705 may be collected and / or processed to reduce, remove, and / or compensate for artifacts, for example, by using one of methods 400, 500, and / or 600. As described above, portions of the retinal signal data may be flagged as containing artifacts, such as portions of the circuit that collect retinal signal data exceeding the threshold impedance. Flagged data may not be used in the next steps of method 700. For example, if the retinal signal data corresponding to an individual flash is determined to have artifacts, the retinal signal data corresponding to that flash may not be used in the following steps of method 700.

[0141] In step 710, retinal signal features may be extracted from retinal signal data. Extraction of retinal signal features may be based on processing the retinal signal data and / or transformations of those data using multiple signal analysis methods such as polynomial regression, wavelet transform, and / or empirical mode decomposition (EMD). Extraction of retinal signal features may be based on parameters derived from those analyses or specific modeling, such as principal components and most discriminant predictors, parameters from linear or nonlinear regression functions, higher amplitude frequencies, differences in Kullback-Leibler coefficients, Gaussian kernel features, log-likelihoods of differences, and / or high-energy regions. These analyses may be used to determine the contribution of each specific retinal signal function and to statistically compare retinal signal functions.

[0142] The characteristics of the retinal signals to be extracted may be predetermined. The characteristics of the retinal signals to be extracted may be determined by analyzing labeled datasets of retinal signal data from multiple patients. Each patient represented in the dataset may have one or more associated conditions that the patient is prone to, and / or one or more conditions that the patient is less prone to. These conditions can be labels for each patient's dataset. By analyzing retinal signal datasets from patients sharing the same conditions, the characteristics of the retinal signals to be extracted can be determined. Based on the retinal signal characteristics, a multimodal map may be generated. Based on the multimodal map, a domain may be determined.

[0143] In step 715, descriptors may be extracted from the features of the retinal signal. The mathematical descriptor may be a mathematical function that combines features from the retinal signal data and / or clinical cofactors. The descriptor may exhibit retinal signal features specific to a state or population, taking into account further differentiation between groups of patients. Descriptors may be selected to obtain components of the bio-existence indicators that together contribute most to a mathematical model of the state, for example, by using PCA, SPCA, or other methods used for selecting and / or combining features from the retinal signal data, or by matching and merging descriptors and cofactors using formulas or relations.

[0144] In step 720, an individual's clinical information may be received. Clinical information may include medical records and / or other data collected about the individual. Clinical data may include the results of questionnaires and / or clinical tests administered by a healthcare professional.

[0145] In step 725, clinical information may be used to generate clinical information cofactors. Clinical information cofactors may be selected based on their impact on retinal signal data. Clinical information cofactors may include an individual's age, sex, skin pigmentation that can be used as a surrogate for retinal pigmentation, and / or other indicators of clinical information relevant to the individual.

[0146] In step 730, clinical information cofactors and / or descriptors can be applied to a mathematical model of the state. Any number of mathematical models can be used. The physician can select the mathematical models to use. Each model may correspond to a specific condition or control.

[0147] In step 735, each model may determine the distance between the patient and the vitality index of the model's state. The principal components of the retinal signal data may be located within the domain corresponding to the condition. Descriptors and / or clinical information cofactors may be compared to the vitality index of each model.

[0148] In step 740, each model may output a predicted probability that an individual is exposed to a model state. The likelihood of an individual falling into a particular state can be predicted based on the level of statistical significance when comparing the size and location of the individual's descriptors with descriptors in the model. The predicted probability may be binary, indicating whether or not the vitality indicator of the state is present in the individual's retinal signal data. The predicted probability may also be a percentage indicating the likelihood that the individual is exposed to the condition.

[0149] In step 745, the predicted probability of an individual being exposed to each condition may be output. An interface and / or report may be output. The interface may be output to a display. The interface and / or report may be output to a clinician. The output may indicate the likelihood that an individual is exposed to one or more conditions. The output may indicate the individual's position within the pathology. The predicted probabilities can be saved.

[0150] The output may include a determination of the medical condition, the predicted probability of the medical condition, and / or the degree to which an individual's retinal signaling data matches that condition and / or other conditions. The predicted probability may be in the form of a disease concordance rate and may provide an objective neurophysiological measure to further support the clinician's disease hypothesis.

[0151] The output can be used in conjunction with the clinician's tentative hypothesis of the patient's condition to increase confidence in the clinician's assessment of the condition and / or to initiate an earlier or more effective treatment plan. The output can be used to initiate treatment earlier rather than spending additional time clarifying the condition and treatment plan. The output can reduce the level of uncertainty for the clinician and / or individual in the clinician's tentative hypothesis of the condition. The output can be used to select medications to administer to the individual. The selected medications can then be administered to the individual.

[0152] Method 700 may be used to monitor an individual's condition. The individual may have been previously diagnosed with the condition. Method 700 may be used to monitor the progression of the condition. Method 700 may be used to monitor and / or modify the treatment plan for the condition. For example, Method 700 may be used to monitor the effectiveness of medications being used to treat the condition. Retinal signal data may be collected before, during, and / or after an individual receives treatment for the condition.

[0153] Method 700 may be used to identify and / or monitor neurological symptoms of infections such as viral infections. For example, Method 700 can be used to identify and / or monitor neurological symptoms in individuals infected with COVID-19. Retinal signal data may be collected from individuals who are infected with or have been infected with COVID-19. The retinal signal data can be evaluated using Method 700 to determine whether a patient has neurological symptoms, the severity of those symptoms, and / or to develop a treatment plan for those symptoms.

[0154] Figure 8 shows the sampling rate of 0.4 cd.sec / m² under bright-light conditions (adjusted to background light) at a sampling frequency of 16 kHz according to various embodiments of this technology. 2 ~794 cd.sec / m 2It is three-dimensional retinal signal data generated at 45 levels of light intensity (luminance steps). The recording starts 20 milliseconds before triggering the retinal signal to determine the baseline amplitude value of each light stimulus luminance (light stimulus at 0 milliseconds indicated by the black line).

[0155] Figure 9 shows the amplitude of the retinal signal at a sampling frequency of 16 kHz according to various embodiments of the present technology, under photopic conditions (adjusted to background light), from 0.4 cd·sec / m 2 to 794 cd·sec / m 2 It is the three-dimensional impedance of retinal signal data generated at 45 levels of light intensity (luminance) from 0.4 cd·sec / m to 794 cd·sec / m, and impedance capture is also performed simultaneously. The retinal signal is triggered at 0 milliseconds for each of the 45 light intensities.

[0156] Figure 10 shows, according to various embodiments of the present technology, at a sampling frequency of 16 kHz, 0.4 cd·sec / m 2 to 794 cd·sec / m 2 It is four-dimensional retinal signal data (amplitude vs impedance vs luminance of the stimulating light vs time) generated at 45 levels of light intensity (luminance) under photopic conditions (adjusted to background light) and simultaneous impedance capture. The grayscale indicates the impedance values according to the scale on the right side of the figure. The baseline impedance is generally less than 2 kΩ and does not change significantly during the recording of the retinal signal, except in cases of artifacts, electrode displacement, or signal interference.

[0157] Figure 11 shows, according to various embodiments of the present technology, at a sampling frequency of 4 kHz, under photopic conditions (adapted to background light), 0.4 cd·sec / m 2 to 851 cd·sec / m 2 It is four-dimensional retinal signal data (amplitude vs impedance vs luminance of the stimulating light vs time) generated at 75 incremental light intensities (luminance). The grayscale indicates the impedance values according to the scale on the right side of the figure. The change in impedance occurs at luminance 9 (0.9 cd·sec / m 2 ) and 72 (624 cd·sec / m 2During signal recording at ), the impedance was higher than the baseline value but did not exceed 500 ohms, indicating the presence of two distortions in the signal. Artifact 1110 at brightness 9 may have been caused by electrode displacement and / or loss of contact. Artifact 1120 at brightness 72 may have been caused by signal drift.

[0158] Figure 12 shows the sampling rate of 0.4 cd.sec / m² under bright-field conditions (adapted to background light) at a sampling frequency of 4 kHz for various embodiments of this technology. 2 ~851 cd.sec / m 2 This is a 4D retinal signal (current vs. admittance vs. stimulated light luminance vs. time) generated at 75 increments of spectral intensity (luminance). The grayscale shows the admittance values ​​according to the scale on the right side of the figure. Each value corresponds to luminance 9 (0.9 cd.sec / m²). 2 ) and 72 (624 cd.sec / m²) 2 The impedance changes found during the signal recording shown in Figure 11 are rejected by this technique, and the signal is modified accordingly, as indicated by the amplitude and admittance values.

[0159] Figure 13 shows a sampling rate of 0.4 cd.sec / m² under bright-field conditions (adapted to background light) at a sampling frequency of 4 kHz. 2 ~851 cd.sec / m 2 This is a 4D retinal signal (current vs. admittance vs. stimulated light luminance vs. time) generated at 75 increments of spectral intensity (luminance). The grayscale shows the admittance values ​​according to the scale on the right side of the figure. Each value corresponds to luminance 9 (0.9 cd.sec / m²). 2 ) and 72 (624 cd.sec / m²) 2 ) And the two distortions seen in the retinal signal shown in Figure 11 are corrected.

[0160] The techniques, systems, and methods described herein can be applied to any type of signal in which the electrode position and conductance directly relate to the quality of the recorded signal, that is, components unrelated to the signal itself can be removed or, for example, the electrode displacement can be adjusted. [Explanation of Symbols]

[0161] 100 Computing Environments 110 processors 120 Solid State Drives 130 Random Access Memory 150 Input / Output Interfaces 160 Internal bus and / or external bus 190 Touchscreen 192 Touch Input / Output Controller 194 Touch Hardware 200 Retinal Signal Data Processing System 205 Photostimulator 210 sensors 215 Data Acquisition Systems 220 Data Analysis Systems 300 Diagrams 310 Ground electrode 320, 330, 340, 350 reference electrode 400, 500, 600, 700, 800, 900, 1000 methods 1110, 1120 Artifacts

Claims

1. A method performed by at least one processor of a computing system, wherein the method is A step of receiving retinal signal data corresponding to an individual, The steps include determining that there is one or more artifacts in the retinal signal data by determining the amount and / or rate of change in the impedance of the circuit that collects the retinal signal data, The steps include storing an index in the retinal signal data for the period corresponding to the one or more artifacts, The steps include saving the aforementioned retinal signal data, The steps include extracting one or more retinal signal features from the aforementioned retinal signal data, The steps include extracting one or more descriptors from the characteristics of the retinal signal, A step of applying one or more descriptors to a first mathematical model and a second mathematical model, wherein the first mathematical model corresponds to a first condition, the second mathematical model corresponds to a second condition, and thereby generates a first predicted probability for the first condition and a second predicted probability for the second condition. The steps include outputting the first predicted probability and the second predicted probability, Methods that include...

2. The steps include receiving calibration data corresponding to the aforementioned individual, The steps include determining the threshold impedance of the circuit based on the calibration data, The method according to claim 1, further comprising:

3. The method according to claim 1, further comprising the step of determining the period corresponding to one or more artifacts by determining the period during which the impedance of the retinal signal data exceeds a threshold impedance.

4. The method according to any one of claims 1 to 3, wherein the retinal signal data responds to at least one flash from a photostimulator, calibration data corresponding to the individual is collected prior to the at least one flash, and the method further comprises the step of causing the photostimulator to emit the at least one flash.

5. The method according to any one of claims 1 to 4, wherein the retinal signal data has a sampling frequency between 4 and 24 kHz.

6. The method according to any one of claims 1 to 5, wherein the retinal signal data is collected over a signal acquisition time of 200 milliseconds to 500 milliseconds.

7. The method according to any one of claims 1 to 6, wherein the one or more artifacts include distortion of the retinal signal data.

8. The method according to any one of claims 1 to 7, wherein the one or more artifacts are caused by one or more of the following: capture of an electrical signal not originating from the retina, shift in electrode position, change in contact of a ground or reference electrode, photomyoclonic reflex, eyelid blinking, and eye movement.

9. The method according to claim 1, further comprising the step of removing the artifact from the retinal signal data.

10. The method according to claim 1, further comprising the step of correcting the artifact by adjusting the amplitude of the current and / or voltage of the retinal signal data.

11. A method performed by at least one processor of a computing system, wherein the method is A step of receiving retinal signal data corresponding to an individual, A step of inputting the retinal signal data into a machine learning algorithm (MLA), wherein the MLA is trained using labeled retinal signal data, and each retinal signal dataset in the labeled retinal signal data includes a label indicating whether each retinal signal dataset contains one or more artifacts, based on the amount and / or rate of change of the impedance of the circuit and based on a time index corresponding to one or more artifacts. The steps include outputting retinal signal data adjusted by the aforementioned MLA, The steps include saving the adjusted retinal signal data, The steps include extracting one or more retinal signal features from the aforementioned retinal signal data, The steps include extracting one or more descriptors from the characteristics of the retinal signal, A step of applying one or more descriptors to a first mathematical model and a second mathematical model, wherein the first mathematical model corresponds to a first condition, the second mathematical model corresponds to a second condition, and thereby generates a first predicted probability for the first condition and a second predicted probability for the second condition. The steps include outputting the first predicted probability and the second predicted probability, Methods that include...

12. The method according to claim 11, wherein the retinal signal data has a sampling frequency between 4 and 24 kHz.

13. The method according to claim 11 or 12, wherein the retinal signal data is collected over a signal acquisition time of 200 milliseconds to 500 milliseconds.

14. The method according to any one of claims 11 to 13, wherein the MLA removes the portion of the retinal signal data corresponding to an artifact.

15. The method according to any one of claims 11 to 14, wherein the MLA adds an indicator to the retinal signal data indicating which portion of the retinal signal data contains artifacts.

16. A system comprising at least one processor and a memory that stores a plurality of executable instructions, which, when executed by the at least one processor, cause the system to perform the method according to any one of claims 1 to 10 or any one of claims 11 to 15.

17. The system according to claim 16, further comprising a light stimulation device.

18. The system according to claim 16 or 17, further comprising one or more sensors for collecting the retinal signal data.

19. A non-temporary computer-readable medium containing instructions, when executed by a processor, causing the processor to perform the method according to any one of claims 1 to 10 or any one of claims 11 to 15.

Images