Systems and methods for personalized medicine for the brain

Abstract

The system provides customizable diagnostic tools to quantify brain health over the span of a lifetime and to assess the impact of various interventions. The system may be configured to receive information regarding a first user of the system; output, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for an assessment of the first user; receive data relating to the one or more cognitive tasks performed by the first user; generate at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user; and output a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user.

Description

SYSTEMS AND METHODS FOR PERSONALIZED MEDICINE FOR THE BRAIN CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority to U. S. Provisional Application Serial No. 63 / 615,466, entitled “SYSTEMS AND METHODS FOR PERSONALIZED MEDICINE FOR THE BRAIN” and filed on December 28, 2023, which is expressly incorporated by reference herein in its entirety.BACKGROUND

[0002] Field of the Invention

[0003] The embodiments described herein are generally directed to customized diagnostic tools to quantify brain health over the span of a lifetime and to assess the impact of various interventions on the brain circuits involved in sensory, cognitive and emotional processes.

[0004] Description of the Related Art

[0005] It is estimated that Alzheimer’s and other neurodegenerative diseases causing dementia will surpass cancer as the leading cause of death by the year 2040 [Ref 1J. With over 5 million new cases worldwide each year, the economic burden of dementia is rapidly outpacing cancer, cardiovascular disease, and stroke [Ref 2], At present, the worldwide population of individuals with dementia is at least 46.8 million and is projected to double by 2030 and triple by 2050. With an annual cost of care estimated at US $818 billion [Ref 5]. the cost of continued care is unsustainable. Alzheimer’s disease (AD) is the leading cause of dementia followed by dementia w ith Lewy bodies (DLB) and Parkinson’s disease with dementia (PDD) [Ref 3, 5], Distinguishing these dementia subtypes is critical, especially in studies examining genetic associations, neuroimaging, or putative biomarkers in the blood or cerebrospinal fluid (CSF), as the validity of such investigations often hinges on the homogeneity across subjects. In some aspects, biomarkers may refer to any measurable characteristics in the body that indicate the presence or progression of disease, health condition or response to a treatment or exposure.

[0006] Mental illness, including depression, anxiety, post-traumatic stress, and other psychiatric disorders, affects over 25% of the population wdth numbers increasing as a result of the COVID-19 pandemic. Over half of adults with a mental illness and over 60% of youth with major depression do not receive treatment [Ref 6], Untreated mental health issues lead to loss of self-esteem and confidence, increased substance abuse, diminished productivity, and113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001can result in harm to self and / or others [Ref 7]. Suicide is the 12th leading cause of death in the U. S. with a total of 1.2 million suicide attempts resulting in 45,979 deaths [Ref 8],SUMMARY

[0007] The following presents a simplified summan of one or more aspects in order to provide a basic understanding of such aspects. This summary' is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

[0008] The system provides customized diagnostic tools to quantify brain health over the span of a lifetime and to assess the impact of various interventions on the brain circuits involved in sensory, cognitive and emotional processes. The test is easy to administer, safe for frequent repeated test sessions and offers both passive and active testbeds customized for the patient’s abilities. There is a growing unmet need for novel methods for characterizing specific and quantifiable biomarkers associated with neurological and psychiatric diseases to guide the development of treatment plans for medical professionals while offering objective evidence of disease progression and efficacy of interventions to patients and their families.

[0009] In an aspect of the disclosure, a method, a computer-readable medium, and a system are provided. The system, in some aspects, may include a set of one or more processors configured to receive information regarding a first user of the system; output, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for an assessment of the first user; receive data relating to the one or more cognitive tasks performed by the first user; generate at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user; and output a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user.

[0010] In an aspect of the disclosure, a method, a computer-readable medium, and an system are provided. The system, in some aspects, may include a display, an additional memory, and a first additional set of processors (e.g., comprising a first computer or personal computing device such as a tablet) configured to display one or more prompts related to a first user of the system; receive, at least in part, information regarding the first user of the system2113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001based on the one or more prompts; and transmit, at least in part, the information regarding the first user of the system to a server using a first secure connection. The system may alternatively, or additionally, include an additional display, a second additional memory, and a second additional set of processors (e.g., comprising a second computer or personal computing device such as a tablet) configured to output, for the first user of the system to perform one or more cognitive tasks, a set of stimuli associated with the one or more cognitive tasks; receive, while the first user of the system performs the one or more cognitive tasks, one or more sets of data from one or more sources of input to the second computing device associated with the set of stimuli; generate, based on the set of stimuli and the one or more sets of data, data relating to the one or more cognitive tasks performed by the first user; and transmit, to a server using a second secure connection, the data relating to the one or more cognitive tasks performed by the first user. In some aspects, the first and second computing devices may be a same computing device or included within a same computing device.

[0011] In an aspect of the disclosure, a system is provided. The system, in some aspects, may include one or more of the set of one or more servers, the first computing device, the second computing device, one or more sets of sensors, a set of secure connections between the server and the first and second computing devices, and one or more displays and / or input / output devices and / or interfaces.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The details of the present invention, both as to its structure and operation, may be gleaned in part by study of the accompanying drawings, in which like reference numerals refer to like parts, and in which:

[0013] FIG. 1 illustrates an example infrastructure, in which one or more of the processes described herein may be implemented, according to an embodiment.

[0014] FIG. 2 illustrates an example processing system, by which one or more of the processes described herein may be executed, according to an embodiment.

[0015] FIG. 3 is a diagram illustrating the overall design of a system in accordance with some aspects of the disclosure.

[0016] FIG. 4 is an illustration of aspects of an AI / ML model training and implementation in accordance with some aspects of the disclosure.3113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0017] FIG. 5 is a graph illustrating an example change in the relative spectral power indicative of the different subtypes of dementia, specifically, Mild Cognitive Impairment (MCI), Lewy Body Dementia (LBD) and Alzheimer’s Disease (AD) as compared to the healthy controls.

[0018] FIG. 6 is a diagram illustrating an individual’s report matched to their peer group of healthy controls.

[0019] FIG. 7 is a diagram demonstrating an example change in amplitude for MCI and AD to the healthy population based on active auditory oddball (AAO) Event Related Potential (ERP).

[0020] FIG. 8 is a diagram illustrates an example change in attention for a MCI as compared to a healthy subject.

[0021] FIG. 9 is a diagram illustrating data collected at a first and second visit of a first patient to a primary care physician.

[0022] FIG. 10 illustrates a process for training a AI / ML model to diagnose a patient, according to an embodiment.

[0023] FIG. 11 illustrates a process for training a AI / ML model to generate tailored (or personalized) cognitive tests, according to an embodiment.

[0024] FIG. 12 illustrates a process for generating tailored (or personalized) cognitive tests, according to an embodiment.

[0025] FIG. 13 illustrates a process for generating tailored (or personalized) cognitive tests, according to an embodiment.

[0026] FIG. 14 illustrates a process for collecting data relating to at least generating tailored (or personalized) cognitive tests, according to an embodiment.

[0027] FIG. 15 illustrates a process for collecting data relating to at least generating at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user, according to an embodiment.DETAILED DESCRIPTION

[0028] In an embodiment, systems, methods, and non-transitory computer-readable media are disclosed for providing customized diagnostic tools to quantify brain health over the span of a lifetime and to assess the impact of various interventions on the brain circuits involved in sensory, cognitive and emotional processes. After reading this description, it will become4113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001apparent to one skilled in the art how to implement the invention in various alternative embodiments and alternative applications. However, although various embodiments of the present invention will be described herein, it is understood that these embodiments are presented by way of example and illustration only, and not limitation. As such, this detailed description of various embodiments should not be construed to limit the scope or breadth of the present invention as set forth in the appended claims.

[0029] FIG. 1 illustrates an example infrastructure in which one or more of the disclosed processes may be implemented, according to an embodiment. The infrastructure may comprise a platform 110 (e.g., one or more servers) which hosts and / or executes one or more of the various processes, methods, functions, and / or software modules described herein. Platform 110 may comprise dedicated servers, or may instead be implemented in a computing cloud, in which the resources of one or more servers are dynamically and elastically allocated to multiple tenants based on demand. In either case, the servers may be collocated and / or geographically distributed. Platform 110 may also comprise or be communicatively connected to a server application 112 and / or one or more databases 114.

[0030] In addition, platform 110 may be communicatively connected to one or more user systems 130 via one or more networks 120. Platform 110 may also be communicatively connected to one or more biomarker monitoring systems 140 via one or more networks 120. Alternatively, one or more biomarker monitoring systems 140 may be directly connected to platform 110 and / or directly connected to a user system 130. In some aspects, the connections may be secure connections complying with HIPAA regulations and / or standards.

[0031] Network(s) 120 may comprise the Internet, and platform 110 may communicate with user system(s) 130 through the Internet using standard transmission protocols, such as HyperText Transfer Protocol (HTTP). HTTP Secure (HTTPS). File Transfer Protocol (FTP), FTP Secure (FTPS), Secure Shell FTP (SFTP), and the like, as well as proprietary protocols. While platform 110 is illustrated as being connected to various systems through a single set of network(s) 120, it should be understood that platform 110 may be connected to the various systems via different sets of one or more networks. For example, platform 110 may be connected to a subset of user systems 130 and / or biomarker monitoring systems 140 via the Internet, but may be connected to one or more other user systems 130 and / or biomarker monitoring systems 140 via an intranet. Furthermore, while only a few user systems 130 and biomarker monitoring systems 140, one server application 112, and one set of database(s) 114 are illustrated, it should be understood that the infrastructure may comprise any number of user systems, biomarker monitoring systems, server applications, and databases.5113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0032] User system(s) 130 may comprise any type or types of computing devices capable of wired and / or wireless communication, including without limitation, desktop computers, laptop computers, tablet computers, smart phones or other mobile phones, servers, game consoles, televisions, set-top boxes, electronic kiosks, point-of-sale terminals, and / or the like. However, it is generally contemplated that user system 130 would comprise the personal computer or professional workstation of a subject (e.g., human patient), physician, health technician, researcher, data scientist, or other individual involved in a cognitive assessment or associated with a healthcare provider of the subject. Each user system 130 may comprise or be communicatively connected to a client application 132 and / or one or more local databases 134.

[0033] Biomarker monitoring sy stem(s) 140 may comprise any device or system of devices configured to acquire or collect physiological data for a subject while the subject performs one or more tasks. One skilled in the art will recognize that use of the term ‘’cognitive task” used herein may include any number of test conditions, included but not limited to a resting state with eyes open or closed and / or a which elicits mental processing based on delivery of audio or visual stimuli. Each biomarker monitoring system 140 may comprise one or more sensors that are attachable and detachable from one or more body parts of the subject (e.g.. head, neck, chin, chest, arm, leg, etc.). These sensors may include, for example, electroencephalographic (EEG) sensor(s), electromyographic (EMG) sensor(s), electrocardiographic (ECG) sensor(s), skin electrode(s), a blood pressure monitor, heart rate monitor, thermometer(s), a pulse oximeter, eye trackers, motion trackers, and / or the like. Biomarker monitoring system 140 may collect the output signals from all of the sensor(s) as physiological (or biomarker) data for the subject and transmit the physiological data to platform 110 (e.g., via network(s) 120 or directly) and / or user system 130 (e.g., via network(s) 120 or directly). Biomarker monitoring system 140 may comprise or consist of a compact device that is worn by the subject (e.g.. on the subject’s head). Alternatively, biomarker monitoring system 140 may be anon-wearable device or set of devices used in conventional sensory, cognitive and emotional assessments.

[0034] Platform 110 may comprise web servers which host one or more websites and / or web services. In embodiments in which a website is provided, the website may comprise a graphical user interface, including, for example, one or more screens (e.g., webpages) generated in HyperText Markup Language (HTML) or other language. Platform 110 transmits or serves one or more screens of the graphical user interface in response to requests from user system(s) 130. In some embodiments, these screens may be served in the form of a wizard, in which case two or more screens may be served in a sequential manner, and one or more of the sequential screens may depend on an interaction of the user or user system 130 with one or 6113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001more preceding screens. The requests to platform 110 and the responses from platform 110, including the screens of the graphical user interface, may both be communicated through network(s) 120, which may include the Internet, using standard communication protocols (e.g., HTTP, HTTPS, etc.). These screens (e.g., webpages) may comprise a combination of content and elements, such as text, images, videos, animations, references (e.g., hyperlinks), frames, inputs (e.g., textboxes, text areas, checkboxes, radio buttons, drop-down menus, buttons, forms, etc.), scripts (e.g., JavaScript), and the like, including elements comprising or derived from data stored in one or more databases (e.g., database(s) 114) that are locally and / or remotely accessible to platform 110. It should be understood that platform 110 may also respond to other requests from user system(s) 130.

[0035] Platform 110 may comprise, be communicatively coupled with, or otherwise have access to one or more database(s) 114. For example, platform 110 may comprise one or more database servers which manage one or more databases 114. Server application 112 executing on platform 110 and / or client application 132 executing on user system 130 may submit data (e.g., user data, form data, etc.) to be stored in database(s) 114, and / or request access to data stored in database(s) 114. Any suitable database may be utilized, including without limitation MySQL™, Oracle™, IBM™, Microsoft SQL™, Access™, PostgreSQL™, MongoDB™, and the like, including cloud-based databases and proprietary' databases. Data may be sent to platform 110, for instance, using the well-known POST request supported by HTTP, via FTP, and / or the like. This data, as well as other requests, may be handled, for example, by serverside web technology, such as a servlet or other software module (e.g., comprised in server application 112), executed by platform 110.

[0036] In embodiments in which a web service is provided, platform 110 may receive requests from user system(s) 130 and / or biomarker monitoring system(s) 140. and provide responses in extensible Markup Language (XML), JavaScript Object Notation (JSON), and / or any other suitable or desired format. In such embodiments, platform 110 may provide an application programming interface (API) which defines the manner in which user system(s) 130 and / or biomarker monitoring system(s) 140 may interact with the web service. Thus, user system(s) 130 and / or biomarker monitoring system(s) 140 (which may themselves comprise servers), can define their own user interfaces, and rely on the web service to implement or otherwise provide the backend processes, methods, functionality, storage, and / or the like, described herein. For example, in such an embodiment, a client application 132, executing on one or more user system(s) 130, may interact with a server application 112 executing on7113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001platform 110 to execute one or more or a portion of one or more of the various functions, processes, methods, and / or software modules described herein.

[0037] Client application 132 may be “thin,” in which case processing is primarily carried out server-side by server application 112 on platform 110. A basic example of a thin client application 132 is a browser application, which simply requests, receives, and renders webpages at user system(s) 130, while server application 112 on platform 110 is responsible for generating the webpages and managing database functions. Alternatively, the client application may be “thick,” in which case processing is primarily carried out client-side by user system(s) 130. It should be understood that client application 132 may perform an amount of processing, relative to server application 112 on platform 110. at any point along this spectrum between “thin” and “thick.” depending on the design goals of the particular implementation. In any case, the software described herein, which may wholly reside on either platform 110 (e.g., in which case server application 112 performs all processing) or user system(s) 130 (e.g., in which case client application 132 performs all processing) or be distributed between platform 110 and user system(s) 130 (e.g., in which case server application 112 and client application 132 both perform processing), can comprise one or more executable software modules comprising instructions that implement one or more of the processes, methods, or functions described herein.

[0038] The Biomarker Monitoring System 140 can transmit data during acquisition to the platform 110 or user system 130 by either wired or wireless means. In one embodiment a Bluetooth transmitter / receiver is employed for wireless transmission. In another embodiment, methods are employed to time stamp each sample of data acquired with the biomarker monitoring system 140 for synchronization with information presented by and / or acquired using the platform 110 or the user system 130. In the one embodiment, synchronization is achieved with millisecond-level precision.

[0039] FIG. 2 illustrates an example processing system 200, by which one or more of the processes described herein may be executed, according to an embodiment. For example, system 200 may be used as or in conjunction with one or more of the processes, methods, or functions (e.g.. to store and / or execute the software) described herein, and may represent components of platform 110, user system(s) 130, biomarker monitoring system(s) 140, and / or other processing devices described herein. System 200 can be any processor-enabled device (e.g., server,8113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001personal computer, etc.) that is capable of wired or wireless data communication. Other processing systems and / or architectures may also be used, as will be clear to those skilled in the art.

[0040] System 200 may comprise one or more processors 210. Processor(s) 210 may comprise a central processing unit (CPU). Additional processors may be provided, such as a graphics processing unit (GPU), an auxiliary processor to manage input / output. an auxiliary processor to perform floating-point mathematical operations, a special-purpose microprocessor having an architecture suitable for fast execution of signal-processing algorithms (e.g., digitalsignal processor), a subordinate processor (e.g., back-end processor), an additional microprocessor or controller for dual or multiple processor systems, and / or a coprocessor. Such auxiliary processors may be discrete processors or may be integrated with a main processor 210. Examples of processors which may be used with system 200 include, without limitation, any of the processors (e.g., Pentium™, Core i7™, Core i9™, Xeon™, etc.) available from Intel Corporation of Santa Clara, California, any of the processors available from Advanced Micro Devices, Incorporated (AMD) of Santa Clara, California, any of the processors (e.g., A series, M series, etc.) available from Apple Inc. of Cupertino, any of the processors (e.g.. Exynos™) available from Samsung Electronics Co., Etd., of Seoul, South Korea, any of the processors available fromNXP Semiconductors N. V. of Eindhoven, Netherlands, and / or the like.

[0041] Processor(s) 210 may be connected to a communication bus 205. Communication bus 205 may include a data channel for facilitating information transfer between storage and other peripheral components of system 200. Furthermore, communication bus 205 may provide a set of signals used for communication with processor 210, including a data bus, address bus, and / or control bus (not shown). Communication bus 205 may comprise any standard or nonstandard bus architecture such as, for example, bus architectures compliant with industry standard architecture (ISA), extended industry standard architecture (EISA), Micro Channel Architecture (MCA), peripheral component interconnect (PCI) local bus, standards promulgated by the Institute of Electrical and Electronics Engineers (IEEE) including IEEE 488 general-purpose interface bus (GPIB), IEEE 696 / S-100, and / or the like.

[0042] System 200 may comprise main memory 215. Main memory 215 provides storage of instructions and data for programs executing on processor 210, such as any of the software discussed herein. It should be understood that programs stored in the memory' and executed by processor 210 may be written and / or compiled according to any suitable language, including without limitation C / C++. Java. JavaScript, Perl. Python, Visual Basic.. NET, and the like. Main memory 215 is typically semiconductor-based memory such as dynamic random access 9113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001memory' (DRAM) and / or static random access memory (SRAM). Other semiconductor-based memory types include, for example, synchronous dynamic random access memory (SDRAM), Rambus dynamic random access memory (RDRAM), ferroelectric random access memory (FRAM), and the like, including read only memory (ROM).

[0043] System 200 may comprise secondary memory' 220. Secondary' memory 220 is a non-transitory computer-readable medium having computer-executable code and / or other data (e.g.. any of the software disclosed herein) stored thereon. In this description, the term “computer-readable medium” is used to refer to any non-transitory computer-readable storage media used to provide computer-executable code and / or other data to or within system 200. The computer software stored on secondary' memory 220 is read into main memory' 215 for execution by processor 210. Secondary memory 220 may include, for example, semiconductorbased memory, such as programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), and flash memory' (block-oriented memory' similar to EEPROM).

[0044] Secondary memory 220 may include an internal medium 225 and / or a removable medium 230. Internal medium 225 and removable medium 230 are read from and / or written to in any well-known manner. Internal medium 225 may comprise one or more hard disk drives, solid state drives, and / or the like. Removable storage medium 230 may be, for example, a magnetic tape drive, a compact disc (CD) drive, a digital versatile disc (DVD) drive, other optical drive, a flash memory drive or card, and / or the like.

[0045] System 200 may comprise an input / output (I / O) interface 235. I / O interface 235 provides an interface between one or more components of system 200 and one or more input and / or output devices. Example input devices include, without limitation, sensors, keyboards, touch screens or other touch-sensitive devices, cameras, biometric sensing devices, computer mice, trackballs, pen-based pointing devices, and / or the like. Examples of output devices include, without limitation, other processing systems, cathode ray tubes (CRTs), plasma displays, light-emitting diode (LED) displays, liquid crystal displays (LCDs), printers, vacuum fluorescent displays (VFDs). surface-conduction electron-emitter displays (SEDs), field emission displays (FEDs). and / or the like. In some cases, an input and output device may be combined, such as in the case of a touch panel display (e.g., in a smartphone, tablet computer, or other mobile device).

[0046] System 200 may comprise a communication interface 240. Communication interface 240 allows software to be transferred between system 200 and external devices (e.g., printers), networks, or other information sources. For example, computer-executable code 10113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001and / or data may be transferred to system 200 from a network server (e.g., platform 110) via communication interface 240. Examples of communication interface 240 include a built-in network adapter, network interface card (NIC), Personal Computer Memory' Card International Association (PCMCIA) network card, card bus network adapter, wireless network adapter, Universal Serial Bus (USB) network adapter, modem, a wireless data card, a communications port, an infrared interface, an IEEE 1394 fire-wire, and any other device capable of interfacing system 200 with a network (e.g., network(s) 120) or another computing device. Communication interface 240 preferably' implements industry -promulgated protocol standards, such as Ethernet IEEE 802 standards, Fiber Channel, digital subscriber line (DSL), asynchronous digital subscriber line (ADSL), frame relay, asynchronous transfer mode (ATM), integrated digital services network (ISDN), personal communications services (PCS), transmission control protocol / Internet protocol (TCP / IP), serial line Internet protocol / point to point protocol (SLIP / PPP), and so on, but may also implement customized or non-standard interface protocols as well.

[0047] Software transferred via communication interface 240 is generally in the form of electrical communication signals 255. These signals 255 may be provided to communication interface 240 via a communication channel 250 between communication interface 240 and an external system 245 (e.g., which may correspond to a biomarker monitoring system 140, an external computer-readable medium, and / or the like). In an embodiment, communication channel 250 may be a wired or wireless network (e.g.. network(s) 120). or any variety of other communication links. Communication channel 250 carries signals 255 and can be implemented using a variety' of wired or wireless communication means including wire or cable, fiber optics, conventional phone line, cellular phone link, wireless data communication link, radio frequency (“RF”) link, or infrared link, just to name a few.

[0048] Computer-executable code is stored in main memory 215 and / or secondary memory 220. Computer-executable code can also be received from an external system 245 via communication interface 240 and stored in main memory 215 and / or secondary memory 220. Such computer-executable code, when executed, may enable system 200 to perform the various functions of the disclosed embodiments as described elsewhere herein.

[0049] In an embodiment that is implemented using software, the software may be stored on a computer-readable medium and initially loaded into system 200 by way of removable medium 230. I / O interface 235, or communication interface 240. In such an embodiment, the software is loaded into system 200 in the form of electrical communication signals 255. The11113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001software, when executed by processor 210, preferably causes processor 210 to perform one or more of the processes and functions described elsewhere herein.

[0050] System 200 may comprise wireless communication components that facilitate wireless communication over a voice network and / or a data network (e.g., in the case of user system 130). The wireless communication components comprise an antenna system 270, a radio system 265, and a baseband system 260. In system 200, radio frequency (RF) signals are transmitted and received over the air by antenna system 270 under the management of radio system 265.

[0051] In an embodiment, antenna system 270 may comprise one or more antennae and one or more multiplexors (not shown) that perform a switching function to provide antenna system 270 with transmit and receive signal paths. In the receive path, received RF signals can be coupled from a multiplexor to a low noise amplifier (not shown) that amplifies the received RF signal and sends the amplified signal to radio system 265.

[0052] In an alternative embodiment, radio system 265 may comprise one or more radios that are configured to communicate over various frequencies. In an embodiment, radio system 265 may combine a demodulator (not shown) and modulator (not shown) in one integrated circuit (IC). The demodulator and modulator can also be separate components. In the incoming path, the demodulator strips aw ay the RF carrier signal leaving a baseband receive audio signal, which is sent from radio system 265 to baseband system 260.

[0053] If the received signal contains audio information, then baseband system 260 decodes the signal and converts it to an analog signal. Then the signal is amplified and sent to a speaker. Baseband system 260 also receives analog audio signals from a microphone. These analog audio signals are converted to digital signals and encoded by baseband system 260. Baseband system 260 also encodes the digital signals for transmission and generates a baseband transmit audio signal that is routed to the modulator portion of radio system 265. The modulator mixes the baseband transmit audio signal with an RF carrier signal, generating an RF transmit signal that is routed to antenna system 270 and may pass through a power amplifier (not shown). The power amplifier amplifies the RF transmit signal and routes it to antenna system 270, where the signal is sw itched to the antenna port for transmission.

[0054] Baseband system 260 is communicatively coupled with processor(s) 210, which have access to memory 215 and 220. Thus, software can be received from baseband system 260 (e.g.. a baseband processor) and stored in main memory 210 or in secondary memory 220, or executed upon receipt. Such software, when executed, can enable system 200 to perform the various functions of the disclosed embodiments.12113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0055] The Dementias

[0056] Differential diagnosis, particularly in the early stages of the disease process, is difficult as there is considerable overlap in the clinical presentation of individuals with a probable neurodegenerative disorder e.g., Alzheimer’s Disease, Dementia with Lewy Bodies, Parkinson’s Disease Dementia, Progressive Supranuclear Palsy etc. [Ref 4], Early characterization is critical to initiate effective interventions. While there is currently no cure for dementia, there are now multiple disease-modifying drugs such as lecanemab and donanamab with more in the pipeline, and an explosion of products aimed at prevention.

[0057] Dementia diagnosis is often initiated by the primary care provider where the standard of care for initial diagnosis is the MMSE (Mini Mental Status Exam), a set of questions commonly used to check for cognitive impairment such as problems with thinking, communication, understanding and memory. This test, which was created nearly 50 years ago, includes 11 questions such as the year, day of the week, patient’s physical location at the time of the test, reading and following written instructions, such as “close your eyes,” remembering and repeating words, spelling a word backward and copying a picture. It also assumes the subject has at least an 8th grade education level, is fluent in the spoken language of the exam and possesses the abilities to hear, speak, and see [Ref 9], Although widely administered, the MMSE w as never meant to be used as a diagnostic tool as it lacks standardization [Ref 9], is not sensitive to early stages of the disease, cannot identify any subtypes of dementia, and offers no objective measure for treatment efficacy [Ref 10], The result is that an estimated 50%-70% of patients with a clinical diagnosis of Alzheimer’s are misdiagnosed in primary care where most patients are managed. Misdiagnosis remains high for patients with access to specialized memory clinics at 25%-30% despite the fact that they receive more comprehensive diagnostic work-ups that may include PET. blood or CSF biomarkers, neuropsychological testing and / or sleep assessment.

[0058] Psychiatric Disorders

[0059] For the first time in decades, a host of novel treatments are being introduced for mental illness including magnetic, electrical, ultrasonic stimulation and novel drugs such as psychedelic compounds (e.g., MDMA, LSD. psilocybin, and ketamine). Ideally, individuals at-risk for mental illness should be identified at the earliest stage with intervention strategies personalized to address the needs of each person. To achieve this goal, highly sensitive and specific assessment methods are required for early identification, alignment of optimal interventions and objective outcome measurement.13113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0060] In addition to the failure of many to seek help due to the stigma or denial, methods for screening and assessment of mental illness, in some aspects, may be limited as they are based solely on subjective measures including psychiatric interviews and subjective scales and surveys. The Beck Depression inventory contains 21 self-reported items that individuals complete using a multiple choice format [Ref 11]. The Center for Epidemiologic Studies Depression Scale was designed for use in the general population and is now used as a screener for depression in primary care. It includes 20 self-report items, scored on a 4-point scale that measures major dimensions of depression experienced in the prior week [Ref 11], Many assessments for psychiatric disorders rely heavily on self-reporting. However, subjective reporting (e.g., self-reporting) has multiple weaknesses including the fact that many people are unwilling, or even unable, to admit to, or fully describe, mental health issues. Additionally, individuals may mask problems with substance abuse or may not even be aware that anything is wrong with them.

[0061] Early detection and risk assessment may allow interventions to be introduced before the disease escalates and to avoid repeated exposure to trauma in highly vulnerable individuals. Ideally, routine and regular screening should be conducted with more objective assessment tools developed to access the preconscious mind to reveal underlying mental health issues and provide quantifiable metrics to assess level of risk for escalation of the disorders. The system specifically addresses the needs for objective measures of brain biomarkers associated with mental health and psychiatric disorders that includes monitoring the patient's disease trajectory.

[0062] Dementia or Depression?

[0063] Diagnostic profiles are further complicated by a significant overlap of dementia and depression, particularly in older adults. Dementia and depression are the most prevalent neuropsychiatric disorders in the older adult population and are often difficult to differentiate at early stages. There are cases of depression where inability to concentrate, mental slowing and lack of motivation contribute to an overall cognitive decline that may be misinterpreted as dementia. The molecular mechanisms underlying depression have not yet been characterized and it is currently unknown whether these are similar or distinctive for depression in dementia when compared to depression in primary psychiatric disease. Medical professionals and treatment developers need methods to objectively quantify and help unravel these diseases.

[0064] Large studies of treatment of depression comorbid with dementia with conventional pharmacotherapies targeting serotonin, norepinephrine and dopamine, reveal lower success rates in ameliorating depression than in other cohorts without dementia, however it is often14113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001difficult to assess changes in mood with the conventional subjective tests once dementia is present.

[0065] Early intervention in depressed patients at risk for dementia is recommended as there is evidence that treatment with antidepressants may significantly delay the onset of dementia. The challenge clinicians face in diagnosing and treating depression is the lack of objective biomarkers to establish the severity of the depression and to quantify treatment outcome. Subjective surveys and structured interviews are the primary assessment methods currently available to clinicians.

[0066] Personalized Diagnostic SystemVarious aspects of the disclosure relate to elements of a system providing an easy-to-use, scalable method for objective, sensitive, and specific assessment of brain biomarkers that can be rapidly deployed in any environment (e.g., an office, clinic, hospital or at home) resulting in a personalized profile for each individual. The system supports personalized assessment to identify objective biomarkers including selection of sensors, sensor sites (all other elements listed in step 140). One of the many steps that can be used to tailor the system to the individual’s health, cognitive capabilities, and demographic profile is to personalize the tasks and stimuli. In another embodiment, the system can be tailored to the individual by selection of EEG sensor locations sites. EEG sensor location selection may be made using the platform (110) or user system (130). In an alternative embodiment the biomarker monitoring system (140) is used to select the EEG sensor sites. Disease-specific neurophysiological abnormalities are associated with various cognitive disorders which could include Mild Cognitive Impairment, Alzheimer’s, Parkinson’s, Lewy Body and other dementias [Waninger, 2021, Ref 13], major depressive disorder (MDD), anxiety, and post-traumatic stress disorder (PTSD). Machine learning (ML) and / or artificial intelligence (Al) algorithms or models, in some aspects, may be used to extract biomarkers from databases of EEG, ECG, and other biomarker data from healthy as well as diseased brains.

[0067] The system, in some aspects, may be associated with providing one or more of resting state, sustained attention, image recognition, and / or verbal memory tasks for a user of the system to perform. In some aspects, the system may provide an easy-to-use. scalable method for objective, sensitive, and specific assessment of brain biomarkers that can be rapidly deployed in any environment (e.g., an office, clinic, hospital or at home) resulting in a personalized profile for each individual. The system supports personalized assessment to identify’ objective biomarkers using tasks and stimuli tailored to the individual’s health,15113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001cognitive capabilities and demographic profile. There are several important steps in personalizing the tasks.

[0068] The system provides customized diagnostic tools to assess the impact of various interventions on the brain circuits involved in sensory, cognitive and emotional processes that can be used repeatedly to quantify brain health over the span of a lifetime. The test is easy to administer, safe for frequent repeated test sessions and offers both passive and active testbeds customized for the patient’s abilities. There is a growing unmet need for novel methods for characterizing specific and quantifiable biomarkers associated with neurological and psychiatric diseases to guide the development of treatment plans for medical professionals while offering objective evidence of disease progression and efficacy of interventions to patients and their families.

[0069] Adjusting for individual cognitive performance skill levels

[0070] In some aspects, the system may perform a selection of one or more cognitive tasks (e.g., via an AI / ML algorithm and / or model) including those designed to assess various cognitive domains such as sensory discrimination, attention, memory, executive function across sensory modalities including but not limited to auditory and visual. In order to provide objective evaluations of brain health across very large populations, the tasks can be designed to activate specific neural networks known to be involved in sensory and cognitive processes in the brain. In some aspects, the system may assess skill levels and adjust the task difficulty to allow for a test design that will be appropriate for a particular user and can accommodate a wide range of levels of performance, even in impaired patients such as those with dementia or traumatic brain injury. The system, in some aspects, may be able to provide and / or perform several pre-test or practice tasks that are used to rapidly probe each patient’s level of performance. The tasks can then be adjusted (or selected) to meet the specific performance levels of each patient. For individuals completely incapable of understanding or performing any of the tasks, a comprehensive set of passive tasks can be delivered to generate sufficient EEG and ECG data to support the quantification of biosignatures comparable to those in patients with higher performance levels.

[0071] In some aspects, the selection of the one or more cognitive tasks may, based on the capability information, include at least one passive cognitive task or may include only passive cognitive tasks. A personalized set of passive tasks may provide further utility when compared with attention-demanding tasks that are ill suited for those with cognitive impairments. Similarly, skill-level adjusted cognitive tasks may provide further utility when compared with16113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001tasks designed for a more skilled user that are ill suited for those with lesser skills (e.g., a cognitive task designed for a college-educated may have less utility for a user with an elementary school education than a skill-level adjusted task accommodating an elementary school education).

[0072] Table 1 below illustrates a set of exemplary biosignatures (or biomarkers ) that distinguish patients with neurodegenerative (NDD) diseases (left column) and biosignatures (or biomarkers ) that distinguish patients with Major Depressive Disorder (MDD) (right column) from matched healthy controls. Selected features are combined using a AI / ML model (e.g., a trained neural network or other AI / ML architecture) that provides a composite score of cognitive decline using EEG / Event Related Potential (ERP) predictors. For example, data from at least three cohorts of patients diagnosed with Major Depressive Disorder have been collected using an EEG / ERP system designed to elicit affective responses (Emotional Face Recognition Memory) and assess sustained attention. In some aspects, AI / ML models and / or algorithms support (e.g., allow, or provide) the discrimination of patients whose cognitive decline is a result of depression, anxiety, or trauma from those with neurodegenerative disease. These distinctions, in some aspects, allow for selection and evaluation of optimal treatment protocols.17113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001Neurodegenerative Disease (NDD) Major Depressive Disorder (MDD) Resting State biomarker differences from matched healthyIncreased theta / delta Flatter 1 / f slope, frontally only Decreased alpha Decreased alphaIncreased Theta / alpha ratio Increased beta gamma, occipital Decreased beta Increased complexity (MSE) at fine scales, decreased complexity) at coarse scales (global to local shift, similar to aging effect) Decreased complexity) (MSE) in AD acrossall scalesIncreased theta coherenceDecreased 1 / f slope, temporal right onlyCognitive Event Related Potential (ERP) differences from matched healthy Decreased Late Positive Component in Increased N170 to Emotional Faces Recognition Memory & Sustained AttentiontasksIncreased Latencies in early Components Increased theta / alpha Active Auditory Oddball, Sustained synchronization for Sad faces 100- Attention & Recognition Memory 300ms post-stimulusSlower response and lower accuracy in Sustained AttentionIncreased P200 in Sustained AttentionTable 1. EEG / ERP biosignatures of NDD and MDD

[0073] Personalizing stimuli to elicit specific EEG biosignature profiles

[0074] In some aspects, a Clinical and Personal Information (CPI) module may be included in the system. The CPI module, in some aspects, may be a software program provided by and / or in communication with, a centralized server (or set of servers, for example, in a datacenter). The CPI software can be used to assess (e g., obtain, retrieve, or receive) demographic and health information with survey questions (e.g., via a questionnaire) to evaluate depression, anxiety, trauma, stress, sleep, and other mental health issues that is completed by, or on behalf of, users / patients. These data (sometimes referred to herein as “demographic information”), in combination with any information provided by healthcare providers (sometimes referred to18113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001herein as “health information”), in some aspects, may be labeled and categorized with the goal of organization into “construct clusters.” A construct cluster may be associated with a mapping between the types of information (e.g., all of the possible answers to the survey / questionnaire questions and / or categories of health information) that may be received regarding a user (e.g., any user generally) to a presence and, in some aspects, to a severity of a construct (where a construct may refer to a condition or set of related conditions with a common treatment) such as depression, anxiety, sleep issues, suicidality, addiction, and cognitive impairment. In some aspects, the labeling and categorization may be performed (during a training period and / or in real time) by a subject matter expert (SME) such as a physician or other healthcare professional, an AI / ML model / algorithm, or a combination of SME and AI / ML model / algorithm. For example, the AI / ML model / algorithm may be trained, based on information (e.g., demographic and health information) collected regarding a plurality’ of users and the “constructs” associated with their care (e.g., as labeled by a physician or other SME), to identify constructs associated with a current user from collected information regarding the current user. Constructs identified by the SME and / or AI / ML, in some aspects, may then be used to select specific content (e.g., words, images, videos, music, scents, or other evocative material) to be delivered as personalized stimuli in the EEG / ERP tasks.

[0075] For example, the selection of one or more cognitive tasks (e.g., one or more ty pes of task(s) and content associated with the one or more cognitive tasks) may be based, at least in part, on information regarding a user of the system. In some aspects, the information may include one or more of demographic information (e.g., information collected based on the questionnaires and / or self-reporting), health information (e.g., medical records or information provided by a doctor or other healthcare provider / professional), or assessed skill levels (e.g., capability’ information relating to an assessment of one or more capabilities of the first user related to the cognitive tasks). For example, in some aspects, the information may be identified as relating to one or more constructs and / or conditions such as depression, anxiety, trauma, stress, sleep, or other mental health issues (e.g., based on one or more questionnaires filled out by, or on behalf of the patient / user), the one or more selected cognitive tasks may include one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task, and the selected content may include one or more of words, images (e.g., a sad face, a happy face, or a neutral face), videos, music, scents, or other evocative material.19113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0076] For example, sad faces may be used for patients diagnosed with depression, as they produce larger EEG / ERPs in response to images of sad faces when compared to happy or neutral faces. Similarly, single words containing emotional content may be selected, in some aspects, in place of neutral words to elicit larger EEG / ERP responses / components. In some aspects, the differential effect is observed in healthy participants and enhanced in patients with depression [Ref 15, Ref 16, Ref 17]. Personalizing words or images can maximize these effects for each individual. The use of single word stimuli is used, in some aspects, as it allows hundreds of words to be quickly selected and to be presented rapidly.

[0077] Selecting stimuli personalized to the individual

[0078] The system creates a personalized profde by extracting a cross section of information from the patient or caregivers or healthcare providers responses to brief questionnaires detailing the patient’s functional capabilities and the reasons for completing the testing (e.g., symptoms). This information can be used to select words, images, video clips, music clips, or other evocative material (e.g., olfactory scents) with the goal of activating neural circuits associated with memory, atention, and emotion. These stimuli may be embedded in various tasks either those requiring responses from the patient or in those where the patient views the stimuli and remains passive. Each set of stimuli and tasks, in some aspects, may be specifically designed to provide personalized brain responses appropriate for the individual. These selections might be made based upon AI / ML using the database of past studies that provides a correlation between the questionnaire responses and potential afflictions (e.g., conditions and / or constructs such as Alzheimer’s disease, Parkinson’s Dementia, Mild Cognitive Impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders, and HIV-related cognitive decline). Tasks and stimuli may be known (based on data collected for a plurality of prior users / patients) to elicit event-related neural signatures that, in some aspects, may be used to create and / or generate a personalized profile of objective biomarkers that may then be selected (e.g., as one or more cognitive tasks and / or associated content / stimuli for presenting to the user / patient) based upon analysis of the database (e.g., a mapping of CPI, or constructs identified based on the CPE to one or more cognitive tasks and / or one or more types of content, or specific content for presentation to a user / patient).

[0079] The system, in some aspects, may leverage technologies including EEG data, AI / ML assisted software, a database of EEG / ERP records acquired from healthy controls and patient populations with neurological and psychiatric disorders, a CPI module that provides delivery of surveys and / or questionnaires (e.g.. Beck Depression Inventory. Profile of Mood20113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001States, Stanford Sleepiness Scale, etc.) that are used to assess demographic and health information, and a secure method of data transmission.

[0080] In some aspects, the system may include streamlined and / or automated data-cleaning and analysis pipelines to support identification and validation of pre-conscious ERP biomarkers associated with neurodegenerative and psychiatric diseases. The identification and validation of pre-conscious ERP biomarkers, in some aspects, may allow the system to differentiate the dementia subtypes, depressive, anxiety, and PTSD. For example, data-cleaning and analysis pipelines and / or algorithms, in some aspects, may extract features for inputs to AI / ML classifiers to characterize disease severity [Ref 18], quantify drowsiness and mental workload [Ref 19, Ref 20, Ref 21] and characterize drug responses [Ref 22],

[0081] The system, in some aspects, may apply these technologies to personalize profiling and identify objective measures which may include pre-conscious neurophysiological signals that reflect personal knowledge that is inaccessible by current methods. In some aspects, a personalized profile may be acquired by extracting a cross section of information from the individual responses to the CPI surveys and questionnaires.

[0082] The user / patient may be presented with the one or more cognitive tasks selected based on the CPI and stimulus and response synchronized neural and physiological data may be acquired to assess signatures obtained during stimulus presentation and during the pre- and post-response intervals to profile measures. The same categories may be employed to select personally relevant words / phrases with personally relevant content to elicit event-related potentials that will be analyzed to extract neural signatures. EEG / ECG features, in some aspects, may be combined using AI / ML models and cross-validated using normative and patient databases.

[0083] The system, in some aspects, may profile an individual’s biographical and health information to create a personalized set of stimuli designed to evoke neural and physiological signatures in support of an objective, scalable method designed to augment diagnostic procedures and to support treatment providers in personalizing behavioral health interventions.

[0084] FIG. 3 is a diagram 300 illustrating the overall design of a system in accordance with some aspects of the disclosure. In some aspects, the processes associated with the system may be organized into three steps associated with data uploads from a computing device to a platform for processing and further development of an AI / ML model / algorithm to expand automation and enhance system accuracy. In some aspects, the computing device may be one or more of computing device 302A, computing device 302B, or computing device 302C which21113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001may correspond to a user system 130 of FIG. 1, and the platform 310 may correspond to platform 110 of FIG. 1. Example processes associated with the three steps are detailed below.

[0085] At a first step, an operator 301 may use a computing device 302A implementing (or executing) the CPI module to complete a survey and / or questionnaire presented on a display of the computing device 302A (e.g., a survey or questionnaire accessed through a portal to the platform 310). The operator 301 may be a patient (where a patient may alternatively be referred to as a user of the system) or another person (e.g., a caregiver or physician) entering information on behalf of the patient. The questionnaire questions, in some aspects, may be presented as (and may elicit) binary choices (e.g., toggles or radio buttons for yes / no responses), multiple choice, and / or text entry to gather relevant biographical and health-related information (e.g., current and / or historical health-related information). In some aspects, the information obtained by the CPI module may include capability information as described above. For example, the capability information may be received (e.g., may be received from another computing device for assessing a skill level, an education level, and / or one or more capabilities of the first user related to the cognitive tasks) and / or assessed by the CPI module.

[0086] The computing device 302A. in some aspects, may provide, or transmit, the information received for the patient to the platform 310 for processing by one or more servers 312 (e.g., one or more processors implementing one or more application corresponding to the application 112 of FIG. 1) and / or one or more databases 314 (which may be referred to as memory and, in some aspects, correspond to the set of database(s) 114 of FIG. 1). The computing device 302A may transmit the information via a secure connection through a network 340 (e.g., a network corresponding to the network 120 of FIG. 1) to an interface 316A (as an example of an interface in a set of one or more interfaces including interfaces 316A, 316B, and 316C between a computing device in the set of one or more computing devices and the platform 310 that may be used to perform some aspects of the disclosure). The information received for the patient, in some aspects, may be processed by the one or more processors (e.g., associated with the one or more servers 312) based on information stored on the one or more databases 314. In some aspects, the information may be stored in the one or more databases for subsequent retraining of one or more AI / ML models. The information stored on the one or more databases, in some aspects, may include at least one AI / ML model used to analyze the information (e.g., the responses provided to the surveys and / or questionnaires) to extract a hierarchy of constructs based on cross-referenced responses associated with cognitive and mental health, as well as facts about the individual.22113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0087] The AI / ML model, in some aspects, may design a testbed, either passive or active, of personalized stimuli for the patient. The design of the testbed, in some aspects, may include a selection of one or more cognitive tasks associated with one or more stimuli (e.g., particular content to be provided to a patient in association with the one or more cognitive tasks). For example, in some aspects, the information provided by the computing device 302A may be identified as relating to one or more constructs and / or conditions such as depression, anxiety, trauma, stress, sleep, or other mental health issues (e.g., based on one or more questionnaires filled out by, or on behalf of the patient / user), the one or more selected cognitive tasks may include one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task, and the selected content may include one or more of words, images (e.g., a sad face, a happy face, or a neutral face), videos, music, scents, or other evocative material. In some aspects, the testbed (e.g., the selected set of one or more cognitive tasks and associated stimuli) may be stored in the one or more databases 314 or other memory for subsequent training, or updating, of the AI / ML model to improve the utility of future testbed selections.

[0088] The CPI collected by the CPI module, in some aspects, may be used to assess health information to establish inclusion / exclusion criteria for the testbed (e.g., criteria for which cognitive tasks to include or exclude from the testbed) and to evaluate sleep, mental health, and other information using surveys relevant to the patient’s health concerns. As described above, the patient (or an operator on behalf of the patient) may complete the questionnaire using the portal and data acquired is sent to the database including standard scores and item responses. The CPI (and the CPI module) may be associated with numerous questionnaires and scales covering assorted topics such as cognition, depression, personality, social background, and more.

[0089] The questionnaire may include a general screener to gather various biographical and personal / medical history, as well as a targeted set of standardized cognitive and mental health screening questionnaires routinely used to assess personality, mental health, and to establish inclusion / exclusion criteria. The system, in some aspects, may be automatically notified when a questionnaire has been completed and the AI / ML model may be used based on the responses to develop a personalized testbed, stimuli and event related potential (ERP) tasks. To prepare a personalized profile for the patient these data (e.g., the CPI) may be labeled and categorized with the goal of organization into “construct clusters” to map the presence and severity of constructs such as cognitive issues, depression, anxiety, sleep issues, suicidality,23113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001addiction, and cognitive impairment. There is significant redundancy across the standardized surveys and opportunity to cross reference responses to further validate the constructs and refine the statements for validation. Additionally, the format and phraseology of the questions differ across questionnaires supporting cross-validation of constructs and supporting alignment with one or more cognitive or psychiatric issues.

[0090] A software module, the CPI database, and EEG device and EEG acquisition software, in some aspects, may utilize AI / ML tools. The software module (e.g., the CPI module describe above) may contain questionnaire mapping and logic that reviews all questionnaire and survey responses to determine a personalized testbed, stored securely with the patient’s profile. The module connects an individual’s biographical information and testbed derived from the CPI database with the ERP task structures to create personalized tasks that will run in a task player (e.g., on computing device 302B) with synchronization of personalized stimuli with physiological responses via EEG, ECG, and pupillometry.

[0091] Neurocognitive tasks may be selected based on a review7of neuropsychological tests used to evaluate attention, learning, and memory in combination with neurophysiological methods to assess alertness and memory. Alternate versions of tests can be provided to mitigate learning effects and have test-retest reliability.

[0092] Examples of the Testbed tasks

[0093] 5-minute Resting State Eyes Open (EO) and Eyes Closed (EC).

[0094] The 3-Choice Vigilance Task (3CVT) could incorporate common measures of sustained attention, as in Continuous Performance Test, Wilkinson Reaction Time, and PVT-192 (psychomotor vigilance task), requiring discrimination primary (70%) and two secondary (30%) geometric shapes presented for 0.2 seconds over a 20-minute period. Training prior to the start minimizes practice effects.

[0095] The Standard Image Recognition (SIR) test evaluates attention, encoding, and image recognition memory. During encoding, 20 images are presented twice, and these 20 images are then randomly interspersed with 80 additional images. Subjects indicate whether or not the image was in the training set.

[0096] The Emotional Image Recognition (EIR) task presents emotional faces (happy, sad and neutral) or words selected to elicit emotional responses. The task is designed to characterize neural responses to emotional content. The task can be passive or active. Active versions include: 1) a set of target faces or words to be memorized and later recognized when combined24113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001with non-target faces or words, 2) respond by rating type and level of emotional content, 3) respond to each stimulus as quickly as possible.

[0097] The Auditory Oddball (AO) task delivers audio tones, such as a standard and deviant tone. The task can present a number of tones with deviant tones are notably different than non-deviant tones. Tones could be delivered at the constant interstimulus intervals.

[0098] The ECG, in some aspects, may be filtered to improve the contrast between the QRS complex and the T wave. The inter-beat R-R interval represents the number of seconds between consecutive R-waves. Heart rate is estimated as a number of beats per minute, i.e., 60 / R-R interval. The algorithm assesses the quality of detected beats by monitoring the standard deviation of the consecutive beats. Each of the HR and HRV measures can be quantified in stimulus-locked intervals (e.g., measurement taken in relation to the moment a stimulus appears) or response-locked intervals (e.g., measurement taken in relation to the moment a subject performs an activity, whether before or after the performance of the activity). HRV, in some aspects, may also be computed to quantity parasympathetic vs. sympathetic arousal, evaluated through the ratio of low frequency (LF) to high frequency (HF) HRV. Higher LF / HF ratios are associated with increased sympathetic activation, and stress / anxiety states.

[0099] Pupillometry, in some aspects, may be acquired using an eye tracking hardware and software. To control for individual differences in resting pupil diameter, baseline correction for pupillometry data is performed by subtracting patient's pupil diameters from the statistical mode of their entire pupillometry recording. Data can be averaged and quantified in stimulus or response-locked intervals.

[0100] Development of Al algorithms

[0101] In some aspects, human experts may initially map responses to the CPI surveys and / or questionnaires, identify the dominant construct, and select personalized stimuli for visual and word tasks. The expert’s labeling and logic captured in a neural network automated and assisted defining these tasks. The testbed designed by the expert was used as a feature vector to train the Al model to develop personalized word and visual inputs (stimuli). Once trained, the Al model qualified (or generated) words, visuals, and word associations used as personalized stimuli for the patient. A database with a large amount of healthy and clinical population data is used to prime the network. Additionally, data from ongoing data collection may be used to continue to fine-tune the neural network (e.g., the AI / ML model). For example, data may be provided by a clinician, patient, caregiver, or family members. Each time a clinician uploads data they may include one or more of an indication, a diagnosis, treatment or intervention, and / or a description of the patient or reason for testing. Subjective complaints 25113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001such as patient does not feel as competent as they used to feel may be used in some aspects to define keywords and / or label data. Accordingly, label data may include one or more of indications, treatments, interventions, patient complaints, patient’s life profile (such as working, living alone, financial stabilities, and such), age, gender, or similar data. Constructs, in some aspects, may be built with the label data and the AI / ML model may use the label data (e.g., the labels) to further expand the intelligence and / or accuracy of the AI / ML model. In some aspects, a clinician may be able to effectively reverse engineer the AI / ML model to understand the elements used by the AI / ML model to generate the constructs.

[0102] FIG. 4 is a diagram 400 illustrating aspects of training and implementing a AI / ML model in accordance with some aspects of the disclosure. While the AI / ML model training and implementation is described without reference to a specific architecture, the description may, for example, apply to one or more of Neural Networks (NN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Neural Networks (LSTM), Generative Adversarial Networks (GANs), Support Vector Machines (SVMs), Principal Component Analysis (PCA). Linear Discriminant Analysis (LDA), Elastic Net (EN). or Naive Bayes (NB).

[0103] In the context of the description above, a database may store training datasets 402 including input data 406 and output data 408 for each dataset in a plurality of datasets included in the training datasets 402. The input data may be the labeled CPI (e.g., for an AI / ML model for testbed generation) or the biomarker and additional data associated with the patient’s performance of the one or more cognitive tasks defined and / or specified by the testbed (e.g., for an AI / ML model for diagnosis). Similarly, the output data may be a testbed generated based on the labeled CPI or the diagnosis based on the biomarker and additional data associated with the patient’s performance of the one or more cognitive tasks defined and / or specified by the testbed. In some aspects, the datasets are checked for accuracy and / or validity (e.g., by a human expert) before being added to the training datasets 402.

[0104] To train an AI / ML model, the training datasets 402 may be provided to a set of one or more ML model training processor(s) 404. The set of one or more ML model training processor(s) 404, may separate input data 406 and output data 408 for one or more datasets. The input data 406 for the one or more datasets may be provided as input data to a current ML model 410 to produce one or more inferences 412 corresponding to the one or more datasets. The one or more inferences may be compared to the output data 408 in a module 420 that may receive the one or more inferences 412. the output data 408, and a set of current model parameters for the ML model 410. The module 420, based on some quantitative measures of 26113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001accuracy of the one or more inferences 412, may either update or validate the current ML model 410 (e.g., provide feedback such as information regarding updates to weights used in a neural network or identify that the ML model has met a threshold for accuracy) based on some quantitative measures of accuracy.

[0105] Once the module 420 has validated a current model, the ML model 430 (e.g., an AI / ML model for generating a testbed from CPI, or for diagnosis based on task performance) may be provided to a database 435 storing one or more ML models for one or more applications and / or tasks. To use an AI / ML model based on receiving collected data 440 (e.g., input data for the AI / ML model collected by a user system and / or computing device and, in some aspects, preprocessed), a set of one or more ML model inference processor(s) 450 may retrieve a corresponding ML model from the database 435 and perform and / or generate an inference 452 (e.g., generate output) based on the collected data 440. In the context of model training, the inference 452 and the collected data 440 may be provided to a validation module 460 to determine if the inference 452 was accurate and / or had utility. For example, the collected data 440 and the inference 452 may be stored for review by a human expert or may be assumed to be valid if no changes were made to the inference 452 by a human expert such as a physician in assessing, diagnosing, or treating a patient associated with the inference 452. If the inference is determined to be valid, the collected data 440 and the inference 452 may be added to the training datasets 402 for additional training, or fine-tuning, of the ML model 430. In some aspects (not shown in FIG. 4). the inference 452 may be provided to a patient or user (e.g., to a computing device 302B or 302C) to guide the assessment or treatment of the patient.

[0106] Returning to the discussion of FIG. 3, in some aspects, the system may be configured to accept as input EEG data collected with at least the standard international 10-20 system for neurology. In some aspects, however, data collected with a denser array may also be acceptable. To provide more accurate results, the data should be clean and free from artifact. In some aspects, EEG data and label data may be used with additional collected biomarker data to develop a comprehensive, objective profile of the patient's brain health, where additional label data and biomarker profiling overtime may provide the patient (or physician) with trajectory measures that indicate future health.

[0107] The portal, as described above in relation to computing device 302A and / or computing device 302B, in some aspects, may be a software application that is used to acquire de-identified and encrypted patient data, transfer this data to a secure server, monitor completed acquisitions, and download data. The functions of the portal may include to communicate between EEG acquisition software and the portal, control access to data, store original data,27113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001and log user interaction with the data. The system, in some aspects, may be configured to be HIPAA compliant with all access and system user interaction compliant with 21 CFR 11.

[0108] EEG / ERP Data reduction and feature extraction

[0109] EEG data, in some aspects, may be filtered and cleaned using a pre-processing pipeline at the client side (e.g., at user system 130 or computing device 302B) or at a server side (e.g., by an application 112 within platform 110 or processing pipeline 318 within platform 310). The filtering and / or feature extraction, in some aspects, may include bandpass filtering, gross artificial artifact removal, artifact decontamination using independent component analysis (ICA), or other filtering or feature extraction methods and / or algorithms.

[0110] Primary Power Spectral Density (PSD) Measures

[0111] Both eyes-open and eyes-closed data, in some aspects, may be analyzed by computing PSD estimation of artifact-free EEG data. For each EEG channel, PSD estimation may be based on FFT of 1 -second long epochs (Kais er- windowed, 50% overlap) according to the methodology. Both absolute and relative PSD for each 1 -second epoch is computed for each frequency bin from 1 to 49 Hz (1 Hz resolution) as well as frequency bands. Secondary PSD measures computed in some aspects may include frequency and the power of the Posterior Dominant Rhythm (PDR), also known as Individual Alpha Frequency (IAF), the frequency and power of the individual Theta Trough (ITT) defined as the local minimum of the PSD graph in the Theta (4-8 Hz) range, the spatial distribution of Alpha. IAF is determined for each patient as the peak alpha frequency in eyes closed condition, individualized alpha and theta ranges are defined as IAF+[-2 2]Hz and IAF+[-6 -3]Hz, respectively. Individualized relative and absolute alpha and theta, lAlpha and ITheta, are evaluated using individualized frequency ranges.

[0112] Periodic and Aperiodic Analysis

[0113] Conventional power measures, in some aspects, may be augmented with the analysis of aperiodic and periodic components using a Fitting Oscillations and One-Over-F (FOOOF) algorithm. The FOOOF algorithm approximates the aperiodic component of the log power spectrum with an exponential function parametrized with offset b and exponent s: AP(f)=b~ logl0 s, for each frequency =1 to 40Hz. The offset is related to the total power, while the exponent captures the 1 / f slope of the EEG spectrum. Although purely mathematical and “agnostic to underlying physiological generators”, the slope of the aperiodic component has been linked to synaptic excitation / inhibition balance.

[0114] Rhythmicity Analysis28113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0115] In addition to the standard PSD measures derived through session- wide averaging, a rhythmicity analysis may be conducted, in some aspects, to pinpoint the predominant rhythm / frequency (indicated by the peak in PSD) within each 1 -second epoch. The analysis calculates the percentage of the epoch in which a specific frequency serves as the dominant rhythm.

[0116] Coherence Analysis

[0117] Resting state coherence, in some aspects, may be calculated between pairs of EEG channels using the “mscohere” function within MATLAB which calculates a magnitude-squared coherence estimate. For every pair of signals, represented as x(t) and y(t), the magnitude-square coherence as a function of frequency (1) is defined by: C(f)= Pxy(f)Pxx(f)Pyy(f). where Pxy represents the cross power spectral density computed using Welch’s overlapped averaged periodogram with a 2-second Kaiser window and 50% overlap. Coherence, in some aspects, may be calculated across moving 20 second windows and report the average and standard error.

[0118] Complexity Analysis

[0119] Computations include correlation dimension, Lyapunov exponent and advanced methods for detecting determinism vs. randomness measures of complexity21 (in which higher complexity is interpreted as more random and less predictable). The analyses of Multiscale Entropy (MSE) in patients with MDD and PTSD have validated its significance for making baseline comparisons with healthy controls and monitoring treatment effects.

[0120] Heart Rate Variability Analysis

[0121] HRV measures are generally useful for assessing anxiety and stress levels. Preprocessing of the inter-beat interval data during each phase of resting state may be carried out in MATLAB using the HRVTool toolbox. Initially, the data may be filtered to remove artifacts using the default thresholds provided by the toolbox. In some aspects, HR and the following HRV measures may be computed: root mean square of successive differences (RMSSD), standard deviation of normal -to-normal inter-beat intervals (SDNN), percentage of successive normal intervals of more than 50 ms (pNN50). the median distance to the center of the RR interval return map (rrHRV), low frequency component (LF), high-frequency component (HF), and low to high-frequency ratio (LFHF).

[0122] Resting state EEG

[0123] As part of the analysis of the data collected from older patients and complementary data from other studies, the utility of resting state EEG as a method to identify biomarkers of cognitive decline was shown in both Alzheimer’s Disease and Alpha-Synucleinopathies (PDD 29113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001and DLB). The EEG power in the Delta frequency band (slow) is affected by Alzheimer’s disease and this effect is oppose that of healthy aging.

[0124] It is significant that increases in slow-frequency EEG along with decreases in fastfrequency EEG, relative to MCI and healthy control populations, represents an important EEG biomarker in the progression of Alzheimer’s disease [Ref 23, 24], On average, Alzheimer’s patients show significantly higher Delta power, Theta power, and Theta-to-Alpha power ratio with significantly lower Alpha power [Ref 24], Alzheimer’s disease groups differences in both power and coherence (compared to healthy controls) in both Theta and Alpha bands are significant across all areas of the brain, while for MCI patients, significant differences were limited to right temporal, left temporal, and left frontal channels with no significant differences in Alpha band [Ref 24].

[0125] For the MCI patients. Alpha coherence differed significantly only at four pairs of channels mainly from right-temporal to left-temporal and left-frontal areas. In both the MCI and Alzheimer’s disease groups, the temporal areas showed the most significant changes (smallest p-values) compared to healthy controls. The changes in Alzheimer’s disease may start with localized changes in temporal areas that manifest in the Theta band as increases in both power and coherence, while in the Alpha band only coherence decreases in the same limited areas. These changes may further progress into spatially widespread changes in both power and coherence in the Theta band and Alpha band where it found increases and decreases respectively. FIG. 5 is a graph 500 illustrating an example change in the relative spectral power indicative of the different subtypes of dementia, specifically. Mild Cognitive Impairment (MCI), Lewy Body Dementia (LBD) and Alzheimer’s Disease (AD) as compared to the healthy controls. FIG. 6 is a diagram 600 illustrating an individual's report 610 matched to their peer group of healthy controls.

[0126] Event-Related Potentials (ERPs)

[0127] For each patient, event related responses may be calculated by averaging across repeated trials. The morphology of the resulting wave forms may be analyzed by measuring the peaks characteristic for a given ERP task, such as Pl, N170, P300 etc. This includes positive and negative early peak measures of amplitudes and latency as well as mean amplitudes of late cognitive components. ERP component amplitudes and latencies are calculated for all sensor sites to provide topographical maps and regional specificity. FIG. 7 is a diagram 700 demonstrating an example change in amplitude for Mild Cognitive Impairment to the healthy population based on AAO ERP. For example, graph 710 illustrates a voltage measured at a midline central electrode (Cz) while graph 720 illustrates a voltage measured midline parietal 30113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001electrode (Pz). FIG. 8 is a diagram 800 illustrates an example change in attention for a MCI as compared to a healthy subject. Diagram 800 includes a table 810 indicating a measured characteristic / feature 811, a value calculated for the patient 813, a healthy range 815, and a graphical representation of the percentile in which the value calculated for the patient falls 817. Diagram 800 further includes an illustration 820 of data associated with a first cognitive task and an illustration 830 of data associated with a second cognitive task.

[0128] Single-trial measures for ERP tasks

[0129] Single-trial measures uncover potentially more sensitive indicators of symptom severity and predictors of response to treatment. This entails evaluating event-related spectral perturbation (ERSP), event-related coherence (ERCOH) and inter-trial coherence (ITC).

[0130] Returning to the discussion of FIG. 3, the platform 310 may provide the testbed (e.g., an indication of the selected one or more cognitive tasks and the related content) to computing device 302B. The computing device 302B may output one or more of audio stimuli (e.g., via speakers, headphones, etc.) or visual stimuli (e.g., via a display, a headset, etc.) for a patient associated with the one or more cognitive tasks provided, or indicated, by the platform 310. For example, the patient may be administered the test (e.g., provided the stimuli associated with the one or more cognitive tasks) at a clinician’s office, a medical treatment center, or in their home.

[0131] During the task, the patient may be monitored by one or more biomarker monitoring systems 323 (e.g., biomarker monitoring systems 140 as described in relation to FIG. 1). For example, a video camera 323A may (when presenting visual stimuli via a screen of the computing device 302B) track eye movements and or other motions of the patient. In some aspects, a set of EEG sensors 323B may collect EEG data, while a headset 323C may track eye movements and changes in pupil dilation (or other pupillometric data). While three example sensors are illustrated, the system may use additional sensors as part of monitoring system 323 as described in relation to the biomarker monitoring systems 140 of FIG. 1. Task performance (e.g., responses to stimuli for active tasks and the timing of the responses), EEG / ECG data (e.g., features of the EEG / ECG data such as EEG / ECG based signatures), and / or additional biomarker data, in some aspects, may be collected and / or extracted and the data may be uploaded to the portal (e.g., a portal provided by platform 310) for processing. In some aspects, some pre-processing may be done at the computing device 302B, while in other aspects, raw data is provided to the portal (or platform 310) and additional processing may be performed by a processing pipeline 318 (which may correspond to an application 112 of FIG. 1) before providing the processed data to the one or more databases 314 and / or the one or more servers 31113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001312. Additional biomarkers (e.g., beyond the EEG / ECG based signatures) may be used, in some aspects, to quantify and / or to validate each individual’s hierarchical mental and cognitive health profile. The labeled data (e.g., with labels generated programmatically or by a physician as described above), in some aspects, may additionally be used to further train and / or refine the AI / ML model (e.g., an additional AI / ML model associated with diagnosis and / or reporting). For example, multiple iterations of training and / or updating may be performed with sets of additional (e.g., newly acquired) data sets to evolve (retrain and / or refine) the AI / ML models and / or algorithms as described in relation to FIG. 4 above.

[0132] Collected and / or extracted EEG / ERP / HRV features, in some aspects, may be evaluated to distinguish between disease states, to quantify disease severity (or distance from the healthy controls), map disease trajectory in the patient, and to objectively measure treatment efficacy. The features may also be combined in AI / ML models to provide more sensitive and specific metrics.

[0133] Modeling Large Datasets

[0134] Each task session results in thousands of EEG / ERP features that can be used individually or in combination in data-driven pattern recognition designed to classify and characterize subtypes of conditions (e.g., stimulus or response ty pes) for advanced modeling approaches. These metrics can also be referenced to the database of healthy and patient populations or compared in repeated measures (e.g., of a same patient) to assess changes over time (i.e., assess interventions). The large number of features (dimensions) provides a powerful basis for detecting subtle patterns of differences. This can also pose the problem of overfitting the training data and emergence of models that will not generalize to the new data. Multiple validated Linear Discriminant Analysis (LDA) models specifically tailored for real-time and offline classifications based on EEG including real-time cognitive state detection [Ref 20, 19, 21] may be used in some aspects.

[0135] Cluster-based permutation test

[0136] To address the fact that EEG / ERP data show high correlations between adjacent frequencies and neighboring channels, channel-frequency clusters of significant differences between experimental conditions identified using permutation tests to detect the largest clusters of significant differences.

[0137] Task Player

[0138] The Task Player (e.g., implemented or executed on computing device 302B) may synchronize the presentation of each neurocognitive task with the EEG, ECG, and performance metrics with millisecond resolution. The Task Player platform supports over a dozen 32113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001neurocognitive tasks each designed to stimulate specific activation of emotion, verbal memory, sustained attention, working memory, and visual and auditory perception. The platform, in some aspects, may be configurable to easily add new tasks and designs and implements personalized stimuli for multiple tasks. The combination of EEG, ECG, and performance metrics derived using this platform are proven highly sensitive and specific in quantifying daytime drowsiness associated either with sleep deprivation in healthy patients or in sleep disordered patients, predicting susceptibility to sleep deprivation, differentially profiling neurocognitive deficits in patients with Alzheimer’s, Parkinson’s, and other dementias, and HIV-related cognitive decline [Ref 25, 26, 20, 27-30, 21, 31, 18, 23, 32], Other applications include comparing efficacy of various therapies for neurological and psychiatric disorders and quantifying the effects of drugs including amphetamine, benzodiazepines, cannabis, nicotine, and numerous novel CNS therapeutic compounds [Ref 26, 33, 34, 35],

[0139] Quantification of ERP components

[0140] Validated EEG-based biomarkers for Alzheimer’s Disease (AD), Parkinson’s Disease Dementia (PDD), Mild Cognitive Impairment (MCI), Post-Traumatic Stress Disorder (PTSD), General Anxiety Disorder (GAD) and Major Depressive Disorder (MDD) using targeted synchronized stimuli to evoke EEG responses relevant to characterizing these populations for applications in clinical trials [Ref 34-38] are evaluated.

[0141] EEG is synchronized to the presentation of each neurocognitive task at the millisecond resolution. Resting state EEG measures are computed on an epoch by epoch (1-second) basis. EEG output variables include power spectral densities (PSD) for the 1 Hz frequency bins (1-59 Hz), EEG bands Delta, Theta, fast & slow Alpha, Beta, and Gamma across 1-60 Hz. During neurocognitive tasks, performance metrics such as accuracy, reaction time, and variability of reaction time are automatically derived and summarized. Time-locked (e.g., specifically aligned to a particular point in time) event-related EEG features such as ERP, error-related negativity (ERN), and event-related desynchronization / synchronization (ERD / ERS) may be computed, including stimulus-locked and response-locked events. Clinical applications for ERPs have been extensively investigated including studies of Alzheimer's [Ref 39-51, Ref 57-57], ERPs track the flow of information from sensory processing and analysis to response. Early components reflect sensory processing of the characteristics of the stimuli but can be influenced by arousal and attention [Ref 58, 65], Selective attention increases the amplitude of the N100 in comparison to unattended stimuli [Ref 68, 69],

[0142] The late ERP components reflect feature evaluation, memory matching, and processing speed [Ref 59, 70, 71], Shorter P300 latency reflects superior cognitive 33113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001performance, with delayed P300s associated with cognitive decline [Ref 72-73], Case Study 1 describes the case of a patient, where both their resting state and ERP measures were affected one year after the initial visit showing evidence of cognitive decline. Additional EEG metrics derived from AMP include coherence and phase synchrony, and representing neural synchrony, which is a coordination of neural activity' across brain areas [Ref 74, 75],

[0143] PTSD and MDD patients' evidence unique pre-conscious ERP components associated with symptoms of the disorders. In PTSD, an enhanced early attentional component (200-300 ms post-stimulus) was identified likely reflecting hypervigilance and inability' to correctly discriminate stimuli. The late positive component (LPP) associated with accurate recognition and decision-making is suppressed in PTSD. When individuals with high major life stress levels were compared to the PTSD and healthy groups, they showed suppression of the LPP but no evidence of enhanced early components. This confirms ERP measures may reveal early evidence of stress-related impairment that could be a precursor to an eventual PTSD diagnosis and provide support for early interventions.

[0144] MDD patients show enhanced N170 components when viewing sad faces in comparison to neutral faces, another example of quantifiable pre-conscious ERP components in MDD.

[0145] Depression vs Dementia

[0146] The system, in some aspects, may use a modified Permutation Feature Importance (PFI) technique to measure the contribution of each feature to the fitted models of cognition and depression at the same time. For each predictor, the system quantifies the importance of each feature by the value of the decrease in accuracy when the predictor is randomly shuffled. Subsequently, and for each model, the predictors are selected for which the ratio of change in accuracy for that model divided by the other model is maximized (i.e., features that are very important for one model and not important for the competing model). Monitoring over time of the patients include reassessing the scores of both models at future testing and comparing them against the prediction of the model at baseline assessment and the patient’s trajectory' overtime.

[0147] Repeated testing to quantify treatment efficacy and map disease trajectories

[0148] The system provides the capability to assess patients across multiple timepoints to evaluate the efficacy of interventions including drugs, neuromodulation with electrical, magnetic, light or sound therapies, and prevention strategies such as exercise, nutrition, or cognitive training. The test is noninvasive, safe for repeated measurements (unlike PET or spinal taps for CSF), and inexpensive in comparison to imaging and full neuropsychological evaluations. Proprietary databases include many repeated tests on healthy participants and 34113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001various patient populations (e.g., Alzheimer's and other dementias, Mild Cognitive Impairment, Long COVID, etc.) that demonstrate the changes in the biomarker profiles over months and years. These data are combined, in some aspects, using AI / ML models / algorithms derived from (e.g., trained based on) the normative (e.g., healthy) and diseased databases (e.g., training datasets associated with healthy and diseased populations) to quantify and map the trajectory of disease progression. The biomarker profiles, in some aspects, are computed with reference to age and sex-matched healthy controls to account for changes in the EEG and ERP across the lifespan.

[0149] With repeated testing an individualized model can be created to summarize the progression of the biomarkers over time and compare the trajectory of changes to healthy aging and / or to patient cohorts with similar biomarker profiles or with similar diseases. Results have been particularly illuminating for patients diagnosed with Mild Cognitive Impairment (MCI), a diagnosis used to define early stages of cognitive decline that may progress to AD or one of other dementias (estimated 30 - 50% progress to dementia). A subset of MCI may show progression of cognitive impairment but remain in the MCI category throughout life, capable of maintaining independent lives, and a smaller subset will return to normal cognition. There are currently no methods to predict. Blood, CSF and neuroimaging can quantify levels of abnormal proteins such as Beta-amyloid and Tau — all known to accumulate during the progression to AD, however these measures are not sensitive for early detection and not correlated with severity of cognitive decline.

[0150] Biomarker profile reports generated by the system, in some aspects, are providing objective measures of disease trajectories uncovering specific root causes of disease progression or improvement leading to discovery' of accurate prognostic measures to guide treatment and optimize outcomes. Several of our cases studies revealed cognitive impairment that was reversed after a patient was treated with Ozempic, controlled blood sugar and lost weight. Others have severe depression and anxiety sufficient to impair cognitive performance. These patients require alternative treatments and should not have been burdened with an MCI diagnosis with the concern that they were on the path to dementia. Similarly, it is important to note that many patients tested repeatedly with MMSE and told they are normal have revealed serious disease progression as measured by our biomarker profiles.

[0151] When a novel treatment is introduced (such as photobiomodulation) and results in significant movement of an individual’s biomarker profile in the direction of the healthy controls, this new treatment is entered into the database so that other patients receiving this treatment can be flagged and compared. This method supports the development of biomarker 35113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001profiles specific to a particular treatment or to a sub-group of patients that may exhibit similar biomarker profiles.

[0152] Patient Case Studies

[0153] Case Study 1 - Misdiagnosis

[0154] A 64 year old man went to his primary care physician concerned about memory loss. His physician gave him the MMSE (Mini-Mental State Examination) which is the standard of care for dementia diagnosis. He scored a 29 out of the possible 30 signifying normal brain health. At the same visit he was also administered the System EEG protocol that confirmed the state of his cognitive health.

[0155] The following year he returned and was given another MMSE and run through the System EEG protocol again. This visit his MMSE score was 25, which is still in the normal range. His EEG results had a very different story. His cognitive health had declined in comparison to his peer group matched healthy controls. However, even more concerning, when compared to his prior assessment, his trajectory shows a steep decline indicating that he will move into Alzheimer's Disease. FIG. 9 is a diagram 900 illustrating data collected at a first and second visit of a first patient to a primary care physician. Diagram 900 illustrates data 910 captured during a first visit, and data 920 captured during a following visit along with a graph 930 comparing time series data captured during the first and following visits.

[0156] Case Study 2 - Diabetes and Ozempic

[0157] A 75-year-old woman has been struggling with diabetes for 15 years. The woman controls her diabetes with metformin and has seen some success but not a full halt in progression. Her care team reports significant weight gain, blood tests indicate slowed kidney function, and her visual acuity has deteriorated faster than expected. She has also noted that the stress of managing her diabetes has affected her mental health, reporting frequent episodes of brain fog.

[0158] The woman was referred to a neurologist to address her memory issues and was administered the System EEG protocol that revealed significant changes in her cognitive biomarkers consistent with cognitive decline. These results indicate her symptoms are more serious than stress management and may be a side effect of diabetes disease progression. She starts a regimen to manage her cognitive decline symptoms with minimal impact on improving her brain health.

[0159] Approximately seven months after her initial run through the System EEG protocol, the woman is prescribed Ozempic to address her diabetes-related weight gain. She experiences substantial weight loss, and her diabetes becomes significantly better controlled.36113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001The woman reports a marked improvement in her mental health and brain fog. initially attributing it to the alleviation of stress associated with diabetes. A follow-up System EEG test reveals significant improvement in her cognitive biomarkers, strongly suggesting that the relief of cognitive symptoms are a result of diabetes disease management. Cognitive decline and dementia symptoms associated with diabetes disease progression are well-reported in the literature and are commonly overlooked in practice, but her EEG assessment is sensitive enough to reveal these changes and aid in treatment selection.

[0160] Case Study 3 - Innovative Treatment

[0161] A 59-year-old man with a family history of Alzheimer’s underwent testing using the System EEG protocol, which revealed early signs of cognitive decline. Concerned about his brain health, he sought treatments with minimal side effects to slow or potentially prevent further decline. He enrolled in a photo biomodulation study — a novel, non-invasive light therapy targeting the pathology of Mild Cognitive Impairment.

[0162] After completing a six-week course of treatment, he returned for a follow-up test with the System protocol. The results showed his biomarkers had shifted back toward those of a healthy population, suggesting the treatment was effective. Based on this objective evidence, he chose to enroll in an extended open-label study of the therapy.

[0163] Case Study 4 - PTSD

[0164] A 58-y ear-old female patient presented with complaints of memory impairment and depressive symptoms. Symptom onset occurred shortly after a sudden ugly divorce, immediately followed by the onset of the COVID-19 pandemic. The patient reported significant difficulty coping with these acute stressors and was unable to seek timely support due to the lockdown. She subsequently experienced a rapid decline in memory' and cognitive function, which ultimately led to the loss of her job.

[0165] The patient reported mild subjective memory difficulties, including occasional lapses in attention during tasks. She remains functional in her daily activities, including living independently and driving. However, collateral history from her daughter revealed more pronounced impairments. According to her daughter, the patient had become disoriented while driving on multiple occasions and frequently lost her train of thought mid-conversation. Persistent depressive symptoms were also present, and the patient was convinced that pharmacological intervention alone will resolve her condition.

[0166] To date, the patient has undergone trials of three different antidepressant medications without notable improvement. She has also been monitored for mild cognitive37113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001impairment, which currently has no definitive treatment. Despite these efforts, the patient continues to insist that her depression can be effectively managed with medication alone.

[0167] Subsequently, the patient was administered the System EEG protocol, a personalized brain scan assessment. The results revealed findings inconsistent with a diagnosis of depression or mild cognitive impairment. Instead, the imaging suggested a pattern indicative of post-traumatic stress disorder (PTSD). This revised diagnosis allowed for a shift in the therapeutic approach, focusing on stress recovery as the primary driver of her symptoms. The diagnosis also facilitated a discussion with the patient, helping her understand that her condition requires a multifaceted treatment strategy, rather than relying solely on pharmacological management. A new treatment plan targeting PTSD has since been implemented and has already shown rapid and significant improvements in the patient's brain health.

[0168] FIG. 10 illustrates a process 1000 for training a AI / ML model to diagnose a patient, according to an embodiment. Process 1000 may be implemented by server application 112, client application 132, biomarker monitoring system 140. a combination of server application 112 and client application 132, a combination of biomarker monitoring system 140 and server application 112, a combination of biomarker monitoring system 140 and client application 132, or a combination of biomarker monitoring system 140, server application 112, and client application 132. While process 1000 is illustrated with a certain arrangement and ordering of subprocesses, process 1000 may be implemented with fewer, more, or different subprocesses and a different arrangement and / or ordering of subprocesses. In addition, it should be understood that any subprocess, which does not depend on the completion of another subprocess, may be executed before, after, or in parallel with that other independent subprocess, even if the subprocesses are described or illustrated in a particular order.

[0169] Subprocess 1002 may obtain a plurality of datasets including a first plurality of datasets relating to healthy brains and a second plurality of datasets relating to unhealthy brains. The plurality of datasets may comprise information regarding any of the biomarkers and of the diagnoses relating to cognitive or psychiatric health discussed above in relation to FIGs. 1-9. In some aspects, the collected data may be associated with electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data. In some aspects, the biomarker data and / or the diagnoses may be associated with one or more of: aheart rate (HR); a HR Variability (HRV); a primary power spectral density (PSD) measures; a periodic analysis; an aperiodic analysis; a rhythmicity analysis; a coherence analysis; a complexity’ analysis; a HRV analysis; a resting state EEG; an event-related potentials (ERPs); a single-trial measures for ERP tasks;38113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001or a cluster-based permutation test. The plurality of datasets, in some aspects, may include datasets relating to a set of one or more previous assessments performed at a set of previous times for a same patient and / or user. For example, referring to FIG. 4, the system may obtain the training datasets 402, where the input data may be the biomarker and additional data associated with the patient’s performance of one or more cognitive tasks and the output data may be a diagnosis based on the biomarker and additional data associated with the patient’s performance of the one or more cognitive tasks.

[0170] Subprocess 1004 may train, using the plurality of datasets obtained in subprocess 1002, a machine learning (ML) model to diagnose a user based on one or more datasets collected for the user at one or more times. The diagnoses, in some aspects, may relate to cognitive or psychiatric health such as Alzheimer’s disease. Parkinson’s Dementia, Mild Cognitive Impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders, and HIV-related cognitive decline, among others. For example, referring to FIG. 4, the system may train the ML model 410 using the training datasets 402 to produce the trained ML model 430 that may then be used to generate a diagnosis based on one or more datasets collected for the user at one or more times (e.g., one or more sets of biomarker and additional data associated with the patient’s performance of one or more cognitive tasks at different times).

[0171] Subprocess 1006 may obtain an additional dataset associated with the diagnosis by the trained ML model and return to subprocess 1004 to train (or refine), using the plurality of datasets obtained in subprocess 1002 and the additional dataset associated with the diagnosis by the trained ML model, the machine learning (ML) model to diagnose a user based on one or more datasets collected for the user at one or more times. In some aspects, the refining and / or retraining may occur at fixed intervals or may occur based on a number of additional datasets obtained. For example, referring to FIG. 4, the system may train the ML model 410 using the updated training datasets 402 based on the generated diagnosis to produce the trained ML model 430.

[0172] FIG. 11 illustrates a process 1100 for training a AI / ML model to generate tailored (or personalized) cognitive tests, according to an embodiment. Process 1100 may be implemented by server application 112. client application 132. biomarker monitoring system 140, a combination of server application 112 and client application 132, a combination of biomarker monitoring system 140 and server application 112, a combination of biomarker monitoring system 140 and client application 132, or a combination of biomarker monitoring system 140, server application 112, and client application 132. While process 1100 is illustrated with a certain arrangement and ordering of subprocesses, process 1100 may be implemented 39113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001with fewer, more, or different subprocesses and a different arrangement and / or ordering of subprocesses. In addition, it should be understood that any subprocess, which does not depend on the completion of another subprocess, may be executed before, after, or in parallel with that other independent subprocess, even if the subprocesses are described or illustrated in a particular order.

[0173] Subprocess 1102 may obtain a plurality of datasets including a first plurality of datasets relating to healthy brains and a second plurality of datasets relating to unhealthy brains. The plurality of datasets may comprise information regarding demographic data, health data, capability information relating to an assessment of one or more capabilities of a user related to the cognitive tasks, or additional label data and information regarding cognitive tests used based on the information regarding the demographic data, the health data, or the additional label data (e.g., whether determined by a human expert or an AI / ML model) discussed above in relation to FIGs. 1-9. In some aspects, the health information comprises first health information received from a healthcare provider. The information, in some aspects, may relate to one or more of depression, anxiety, trauma, stress, sleep, or other mental health issues. In some aspects, the information may be obtained based on an output for display of one or more questionnaires designed to elicit at least a portion of the information. For example, referring to FIG. 4, the system may obtain the training datasets 402, where the input data may be the labeled CPI and the output data may be a testbed generated based on the labeled CPI.

[0174] Subprocess 1104 may train, using the plurality of datasets obtained in subprocess 1102, a machine learning (ML) model to generate tailored (or personalized) cognitive tests for a user based on one or more of demographic data or health data of the user. In some aspects, the ML model may further be trained to generate the tailored cognitive tests (or select the one or more cognitive tasks) based on the capability information. The generation of the tailored cognitive tests may include generating a type of task and, at least in part, content of at least one cognitive task of a set of the one or more cognitive tasks that make up the tailored cognitive test. The one or more cognitive tasks, in some aspects, may comprise types of cognitive tasks designed to assess one or more of sensory discrimination, attention, memory, executive function across one or more sensory modalities. The types of cognitive tasks, in some aspects, may also include passive and active tasks, where the one or more cognitive tasks may include at least one passive task or only passive tasks (e.g., based on the capability information). In some aspects, the one or more cognitive tasks may comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR) task, or 40113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001an Auditory Oddball (AO) task. The content of the at least one cognitive task, in some aspects, may comprises one or more of words, images, videos, music, scents, or other evocative material. In some aspects, the images may include images of one or more of a sad face, a happy face, or a neutral face. Generating the tailored cognitive tests, in some aspects, may include selecting the one or more cognitive tasks based on one or more conditions indicated by the information regarding the user, where the one or more conditions comprise one or more of Alzheimer’s disease. Parkinson’s dementia, mild cognitive impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders and HIV -related cognitive decline. Training the ML model, in some aspects, may include training the ML model to generate a mapping between the types of the information that may be received from a user to a presence and a severity of one of a condition of the one or more conditions or a construct of a plurality’ of constructs, where the plurality of constructs comprises depression, anxiety, sleep issues, suicidality, addiction, and cognitive impairment, and wherein to select the one or more cognitive tasks, the at least one processor, individually or in any combination, is configured to select the one or more cognitive tasks based on the generated mapping. For example, referring to FIG. 4, the system may train the ML model 410 using the training datasets 402 to produce the trained ML model 430 that may then be used to generate tailored (or personalized) cognitive tests for a user based on one or more of demographic data or health data of the user (or, in some aspects, the capabilities of the user).

[0175] Subprocess 1106 may obtain an additional dataset associated with the tailored cognitive tests generated by the trained ML model and return to subprocess 1 104 to train (or refine), using the plurality of datasets obtained in subprocess 1102 and the additional dataset associated with the tailored cognitive tests generated by the trained ML model, the ML model to generate the tailored cognitive tests for a user based on one or more of demographic data or health data of the user. In some aspects, the refining and / or retraining may occur at fixed intervals or may occur based on a number of additional datasets obtained. For example, referring to FIG. 4, the system may train the ML model 410 using the updated training datasets 402 based on the generated tailored cognitive tests to produce the trained ML model 430.

[0176] FIG. 12 illustrates a process 1200 for generating tailored (or personalized) cognitive tests, according to an embodiment. Process 1200 may be implemented by server application 112, client application 132, biomarker monitoring system 140, a combination of server application 112 and client application 132. a combination of biomarker monitoring system 140 and server application 112, a combination of biomarker monitoring system 140 and client application 132, or a combination of biomarker monitoring system 140, server application 112,41113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001and client application 132. While process 1200 is illustrated with a certain arrangement and ordering of subprocesses, process 1200 may be implemented with fewer, more, or different subprocesses and a different arrangement and / or ordering of subprocesses. In addition, it should be understood that any subprocess, which does not depend on the completion of another subprocess, may be executed before, after, or in parallel with that other independent subprocess, even if the subprocesses are described or illustrated in a particular order.

[0177] Subprocess 1202 may receive information regarding a first user of the system. In some aspects, the information comprises one or more of demographic information or health information. The health information, in some aspects, comprises first health information received from a healthcare provider. In some aspects, the information relates to one or more of depression, anxiety, trauma, stress, sleep, or other mental health issues (e.g., one or more constructs) or conditions such as Alzheimer’s disease, Parkinson’s dementia, mild cognitive impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders and HIV-related cognitive decline. In some aspects, the information may be received, at least in part, based on the output for display of one or more questionnaires to elicit at least a portion of the information. Subprocess 1202, in some aspects, may include indicating for an element of a system performing the process 1200 to output the one or more questionnaires. For example, referring to FIGs. 1 or 3, a first application 112 or server of the one or more servers 312 may direct (or provide an indication to) a user system 130 or computing device 302A to display a questionnaire or survey as described in relation to FIG. 3. In some aspects, the information regarding the first user may further include capability information relating to an assessment of one or more capabilities of the first user related to the cognitive tasks. The capability information, in some aspects, may be based on a set of one or more preliminary cognitive tests and / or assessments of a skill level of a patient (e.g.. a mental capacity and / or an education level) that may also be elicited by the questionnaire discussed above.

[0178] Subprocess 1204 may select, based on the information regarding the first user of the system, the one or more cognitive tasks. The one or more cognitive tasks may be selected based on one or more conditions indicated by the information regarding the first user of the system, where the one or more conditions comprise one or more of Alzheimer’s disease. Parkinson’s dementia, mild cognitive impairment, depression, anxiety’, post-traumatic stress disorder, sleep disorders and HIV -related cognitive decline. As discussed above in relation to process 1100 of FIG. 11, a system performing process 1100 may have generated a mapping between the types of the information that may be received from a user to a presence and a severity of one of a condition of the one or more conditions or a construct of a plurality of 42113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001constructs, wherein the plurality of constructs comprises depression, anxiety, sleep issues, suicidality, addiction, and cognitive impairment, and wherein to select the one or more cognitive tasks, the at least one processor, individually or in any combination, is configured to select the one or more cognitive tasks based on the generated mapping. In some aspects, the generated mapping is embodied in a trained ML model and the selection by subprocess 1204 is based on the ML model. In some aspects, the one or more cognitive tasks may be selected by the subprocess 1204 based on the capability information. For example, based on the capability information, the one or more cognitive tasks may comprise at least one passive cognitive task. In some aspects, e.g., based on the capability information indicating a severely limited capacity of the first user, the one or more cognitive tasks may comprise only passive cognitive tasks. For example, referring to FIGs. 1 or 3, a first application 112 or server of the one or more servers 312 may, based on information from a user system 130 or computing device 302A, design a testbed, either passive or active, of personalized stimuli for the patient. The design of the testbed, in some aspects, may include a selection of one or more cognitive tasks associated with one or more stimuli (e.g., particular content to be provided to a patient in association with the one or more cognitive tasks).

[0179] Subprocess 1206 may output, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for an assessment of the first user. In some aspects, the output may be provided to a user system or computing device for providing the one or more cognitive tasks to the user as will be described below in relation to FIG. 15 and process 1500. For example, referring to FIGs. 1 or 3, a first application 1 12 or server of the one or more servers 312 may direct (or provide an indication to) a user system 130 or computing device 302B to output one or more of audio stimuli (e.g.. via speakers, headphones, etc.) or visual stimuli (e.g., via a display, a headset, etc.) for a patient associated with the one or more cognitive tasks provided, or indicated, by the platform 310 (e.g., to administer the one or more cognitive tasks to the patient) as described in relation to FIG. 3.

[0180] The first indication of the one or more cognitive tasks, in some aspects, may comprise an additional indication of a type of task and, at least in part, content of at least one cognitive task of the one or more cognitive tasks. In some aspects, the one or more cognitive tasks may comprise types of cognitive tasks designed to assess one or more of sensory discrimination, attention, memory, executive function across one or more sensory modalities. The one or more cognitive tasks, in some aspects, may comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR)43113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001task, or an Auditory Oddball (AO) task. In some aspects, the content of the at least one cognitive task comprises one or more of words, images, videos, music, scents, or other evocative material, where the images may comprise, images of one or more of a sad face, a happy face, or a neutral face. Based on the first indication, an additional component of a system or an associated system may administer the one or more cognitive tasks, collect data related to the performance of the cognitive tasks, and transmit the information to a component of the system for additional analysis as described in relation to FIG. 15. process 1500, and subprocesses 1504-1510 below.

[0181] FIG. 13 illustrates aprocess 1300 for generating tailored (or personalized) cognitive tests, according to an embodiment. Process 1300 may be implemented by server application 112, client application 132, biomarker monitoring system 140. a combination of server application 112 and client application 132, a combination of biomarker monitoring system 140 and server application 112, a combination of biomarker monitoring system 140 and client application 132, or a combination of biomarker monitoring system 140, server application 112, and client application 132. While process 1300 is illustrated with a certain arrangement and ordering of subprocesses, process 1300 may be implemented with fewer, more, or different subprocesses and a different arrangement and / or ordering of subprocesses. In addition, it should be understood that any subprocess, which does not depend on the completion of another subprocess, may be executed before, after, or in parallel with that other independent subprocess, even if the subprocesses are described or illustrated in a particular order.

[0182] Subprocess 1302 may receive data relating to the one or more cognitive tasks performed by the first user. In some aspects, the data relating to the one or more cognitive tasks performed by the first user comprises at least first data related to stimuli presented in association with the one or more cognitive tasks and second data regarding responses to the stimuli presented in association with the one or more cognitive tasks. The first data and the second data, in some aspects, may be synchronized. The synchronization may be based on an association with an objective time (e.g., time-locked based on a reference timing at the system), a time of providing a stimulus (e.g., stimulus-locked), and / or a time relative to receiving a response (e.g.. response-locked). In some aspects, the first data and the second data may be synchronized with millisecond resolution. The second data comprises biomarker data and the data relating to the one or more cognitive tasks performed by the first user further comprises one or more of additional biomarker data or label data. In some aspects, the biomarker data comprises one or more of electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data. The data, in some aspects, may be pre-processed based 44113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001on and / or associated with one or more of one or more of: a heart rate (HR); a HR Variability (HRV); a primary power spectral density (PSD) measures; a periodic analysis; an aperiodic analysis; arhythmicity analysis; a coherence analysis; a complexity analysis; a HRV analysis; a resting state EEG; an event-related potentials (ERPs); a single-trial measures for ERP tasks; or a cluster-based permutation test. For example, referring to FIGs. 1 and 3, the platform 110 or the platform 310 may receive data relating to the one or more cognitive tasks performed by a patient using a user system 130 or computing device 302B in association with one or more biomarker monitoring systems 323 or 140.

[0183] In some aspects, the one or more cognitive tasks may be a first set of cognitive tasks and the data relating to the first set of cognitive tasks is first data associated with a first assessment performed at a first time. The system or component performing the process 1300, in some aspects, may also store additional data relating to a set of one or more previous assessments performed at a set of previous times.

[0184] Subprocess 1304 may generate at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user. In some aspects, the subprocess 1304 may generate the at least one of the one or more diagnoses or the one or more analyses for the first user by providing the data relating to the one or more cognitive tasks performed by the first user to an additional ML model (e.g., an ML model different from the ML model for generating the testbed. or tailored cognitive test). In some aspects, before providing the data as inputs to the ML model, the subprocess 1304 may include pre-processing or non-ML model based analysis such as one or more of one or more of: a heart rate (HR); a HR Variability (HRV); a primary power spectral density (PSD) measures; a periodic analysis; an aperiodic analysis; a rhythmicity analysis; a coherence analysis; a complexity analysis; a HRV analysis: a resting state EEG; an event-related potentials (ERPs); a single-trial measures for ERP tasks; or a cluster-based permutation test. In some aspects, the additional ML model may implicitly perform the previously mentioned analyses along with additional analyses learned through the training process. The additional ML model may, based on the input data, produce an inference or output data relating to the at least one of the one or more diagnoses or the one or more analyses for the first user. In some aspects, the subprocess 1304 may generate the at least one of the one or more diagnoses or the one or more analyses for the first user based on the additional (stored) data relating to the set of one or more previous assessments performed at the set of previous times.

[0185] Subprocess 1306 may output a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user. The output may be for a display 45113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001to a user or health care professional to assess the diagnosis and / or potential treatments. For example, referring to FIGs. 1, 3. and 5-9, the platform 110 or the platform 310 may provide a user system 130 or a computing device 302C with any of the reports or analyses of FIGs. 5-9.

[0186] FIG. 14 illustrates a process 1400 for collecting data relating to at least generating tailored (or personalized) cognitive tests, according to an embodiment. Process 1400 may be implemented by server application 112, client application 132. biomarker monitoring system 140, a combination of server application 112 and client application 132, a combination of biomarker monitoring system 140 and server application 112, a combination of biomarker monitoring system 140 and client application 132, or a combination of biomarker monitoring system 140, server application 112, and client application 132. While process 1400 is illustrated with a certain arrangement and ordering of subprocesses, process 1400 may be implemented with fewer, more, or different subprocesses and a different arrangement and / or ordering of subprocesses. In addition, it should be understood that any subprocess, which does not depend on the completion of another subprocess, may be executed before, after, or in parallel with that other independent subprocess, even if the subprocesses are described or illustrated in a particular order.

[0187] Subprocess 1402 may display one or more prompts related to the first user of the system. In some aspects, the one or more prompts may be associated with one or more surveys and / or questionnaires. The one or more prompts may be associated with, e.g., one or more of the Beck Depression Inventory, the Profile of Mood States, the Stanford Sleepiness Scale, or other surveys / questionnaires, that are used to assess demographic and health information. In some aspects, the one or more prompts may be displayed on a computing device such as a phone, tablet, or computer for a user to interact with using one or more interfaces (keyboard, mouse, touchpad, touchscreen, etc.) of the computing device. For example, referring to FIGs.1 and 3 a user system 130 or a computing device 302A may display one or more prompts for collecting CPI to a user such as a patient or operator 301.

[0188] Subprocess 1404 may receive, at least in part, the information regarding the first user of the system (e g., where the information may refer to information used by an ML model to generate tailored cognitive tests as described above) based on the one or more prompts. In some aspects, one or more of demographic data, health data, and capability information may be received based on the one or more prompts. For example, referring to FIGs. 1 and 3 a user system 130 or a computing device 302A may receive CPI and / or capability information from a user such as a patient or operator 301 based on the display of the one or more prompts for collecting CPI.46113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0189] Subprocess 1406 may transmit, at least in part, the information regarding the first user of the system to one or more processors over a first secure connection. The one or more processors, in some aspects, may be associated with a platform, one or more servers, an ML model or may be part of a same device performing subprocess 1406. The secure connection may be a HIP AA compliant connection or may be referred to as secure based on encryption or a stripping of personally identifiable information. In some aspects, subprocess 1404 and or subprocess 1406 may be associated with a pre-processing of the information regarding the first user of the system to reduce overhead and / or to format the information for inputting to a trained ML model. For example, referring to FIGs. 1 and 3 a user system 130 or a computing device 302A may receive CPI and / or capability information from a user such as a patient or operator 301 based on the display of the one or more prompts for collecting CPI and transmit the CPI and / or capability information to the platform 110 or the platform 310 for analysis (e.g., to generate a testbed, or tailored cognitive tests, comprising one or more cognitive tests and their associated stimuli).

[0190] FIG. 15 illustrates a process 1500 for collecting data relating to at least generating at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user, according to an embodiment. Process 1500 may be implemented by server application 112, client application 132, biomarker monitoring system 140, a combination of server application 112 and client application 132, a combination of biomarker monitoring system 140 and server application 112, a combination of biomarker monitoring system 140 and client application 132, or a combination of biomarker monitoring system 140, server application 112, and client application 132. While process 1500 is illustrated with a certain arrangement and ordering of subprocesses, process 1500 may be implemented with fewer, more, or different subprocesses and a different arrangement and / or ordering of subprocesses. In addition, it should be understood that any subprocess, which does not depend on the completion of another subprocess, may be executed before, after, or in parallel with that other independent subprocess, even if the subprocesses are described or illustrated in a particular order.

[0191] Subprocess 1502 may receive, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for an assessment of the first user. Subprocess 1502 may correspond to subprocess 1206 of FIG. 12, where subprocess 1502 receives the output of subprocess 1206. Accordingly, the description of the content of the output associated with subprocess 1206 may be equally applicable to the subprocess 1502. For example, the first indication of the one or more cognitive tasks, in some aspects, may comprise 47113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001an additional indication of a type of task and, at least in part, content of at least one cognitive task of the one or more cognitive tasks. In some aspects, the one or more cognitive tasks may comprise types of cognitive tasks designed to assess one or more of sensory discrimination, attention, memory, executive function across one or more sensory modalities. The one or more cognitive tasks, in some aspects, may comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task. Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task. In some aspects, the content of the at least one cognitive task comprises one or more of words, images, videos, music, scents, or other evocative material, where the images may comprise, images of one or more of a sad face, a happy face, or a neutral face. For example, referring to FIGs. 1 or 3, a user system 130 or computing device 302B may receive, from a first application 112 or server of the one or more servers 312, an indication of the type and content of one or more cognitive tasks. In some aspects, the indication may further include (or indicate) a command and / or direction to administer the one or more cognitive tasks to the patient via a Task Player as described above. For example, the user system 130 or computing device 302B may be indicated to output the indicated content associated with, or in the context of, the one or more cognitive tasks, where the indicated content may include one or more of audio stimuli (e.g., via speakers, headphones, etc.) or visual stimuli (e.g., via a display, a headset, etc.) for a patient associated with the one or more cognitive tasks provided, as described in relation to FIG. 3.

[0192] Subprocess 1504 may output, for the first user of the system to perform the one or more cognitive tasks, a set of stimuli associated with the one or more cognitive tasks. For example, the subprocess 1504 may present stimuli such as one or more of words, images, videos, music, scents, or other evocative material, where the images may comprise images of one or more of a sad face, a happy face, or a neutral face in association with one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task. For example, referring to FIGs. 1 or 3, a user system 130 or computing device 302B may present one or more cognitive tasks (e.g., via a task player) based on an indication from the first application 112 or the server of the one or more servers 312 of the type and content of the one or more cognitive tasks.

[0193] Subprocess 1506 may receive, while the first user of the system performs the one or more cognitive tasks (e.g., responds to the set of stimuli), one or more sets of data from one or more sources of input to the second computing device associated with the set of stimuli. The 48113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001one or more sources of input, in some aspects, may comprise at least one or more sets of sensors for collecting one or more of electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data. In some aspects, the one or more sets of data may be associated with an objective time (e.g., time-locked based on a reference timing at the system), a time of providing a stimulus (e.g., stimulus-locked), and / or a time relative to receiving a response (e.g., response-locked). For example, referring to FIGs. 1 or 3, a user system 130 or computing device 302B may receive one or more sets of data from one or more the biomarker monitoring system 140 or from the one or more biomarker monitoring systems 323 while presenting the one or more cognitive tasks (e.g., via a task player) based on the indication from the first application 112 or the server of the one or more servers 312 of the type and content of the one or more cognitive tasks.

[0194] Subprocess 1508 may generate, based on the set of stimuli and the one or more sets of data, the data relating to the one or more cognitive tasks performed by the first user. The data relating to the one or more cognitive tasks performed by the first user may comprise at least first data related to stimuli presented in association with the one or more cognitive tasks and second data regarding responses to the stimuli presented in association with the one or more cognitive tasks. The subprocess 1508 may synchronize the first data and the second data to generate the relating to the one or more cognitive tasks performed by the first user. The synchronization may be based on an association with an objective time (e.g., time-locked based on a reference timing at the system), a time of providing a stimulus (e.g., stimulus-locked), and / or a time relative to receiving a response (e.g., response-locked). In some aspects, the first data and the second data may be synchronized with millisecond resolution. The second data comprises biomarker data and the data relating to the one or more cognitive tasks performed by the first user further comprises one or more of additional biomarker data or label data. In some aspects, the biomarker data comprises one or more of electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data. In association with the subprocess 1508, the data, in some aspects, may be pre-processed based on and / or associated with one or more of one or more of: a heart rate (HR); a HR Variability (HRV); a primary power spectral density (PSD) measures; a periodic analysis; an aperiodic analysis; a rhythmicity analysis; a coherence analysis; a complexity analysis; a HRV analysis; a resting state EEG; an event-related potentials (ERPs); a single-trial measures for ERP tasks; or a cluster-based permutation test. For example, referring to FIGs. 1 and 3, the platform 110 or the platform 310 may generate data relating to the one or more cognitive tasks performed by a patient using a user system 13049113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001or computing device 302B in association with one or more biomarker monitoring systems 323 or 140.

[0195] Subprocess 1510 may transmit to the one or more processors using a second secure connection, the data relating to the one or more cognitive tasks performed by the first user. The one or more processors, in some aspects, may be associated with a platform, one or more servers, an ML model or may be part of a same device performing subprocess 1510. The second secure connection may be a HIP AA compliant connection or may be referred to as secure based on encryption or a stripping of personally identifiable information. In some aspects, subprocess 1408 and or subprocess 1410 may be associated with a pre-processing of the information regarding the first user of the system to reduce overhead and / or to format the information for inputting to a trained ML model. For example, referring to FIGs. 1 and 3 a user system 130 or a computing device 302A may generate the data relating to the one or more cognitive tasks performed by a patient and transmit the generated data to the platform 110 or the platform 310 for analysis (e.g., to generate at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user).

[0196] Although FIGs. 10-15 are described as different processes 1000 to 1500, in some aspects a single system may perform one or more of the processes 1000 to 1500 at one or more components of the system. For example, while some processes have been described in relation to different computing devices of FIG. 3, a same computing device or a single system comprising multiple computing devices may perform one or more of the processes 1000 to 1500. As a non-limiting set of example architectures, one or more processors and one or more memories associated with a platform may perform process related to training and / or implementing the ML models discussed above, while data collection (CPI and biomarker data) associated with one or more cognitive tasks may be performed by a set of one or more computing devices associated with a healthcare provider (e.g., an office or clinic). As an alternative example, the one or more processors and one or more memories associated with a platform may perform process related to training the ML models discussed above and provide the trained ML models to a set of one or more computing devices associated with a healthcare provider (e.g., an office or clinic) for the one or more computing devices to perform data collection (CPI and biomarker data) associated with one or more cognitive tasks, use the ML models to perform the functions described above, and provide the collected data to the one or more processors and one or more memories associated with a platform to perform further training of the ML models.50113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0197] References

[0198] All of the following references are hereby incorporated herein by reference as if set forth in full:

[0199] Ref l Lilienfeld, D. E. and D. P. Perl, Projected neurodegenerative disease mortality in the United States, 1990-2040. Neuroepidemiology7, 1993. 12(4): p. 219-28.

[0200] Ref 2 Ferri. C. P., et al., Global prevalence of dementia: a Delphi consensus study. The Lancet. 2005. 366(9503): p.2112-2117.

[0201] Ref 3 McKeith IG, Galasko D, Kosaka K, et al. Consensus guidelines for the clinical and pathologic diagnosis of dementia with Lewy' bodies (DLB): report of the Consortium on DLB international workshop. Neurology7, 1996. 47: p. 1113-1124.

[0202] Ref 4 Metzler-Baddeley C. A review of cognitive impairments in dementia with Lewy bodies relative to Alzheimer's disease and Parkinson's disease with dementia. Cortex. 2007 Jul;43(5):583-600.

[0203] Ref 5 Al-Nuaimi AH, et al. Robust EEG Based Biomarkers to Detect Alzheimer's Disease, brain sciences, 2021.11(8): 1026.

[0204] Ref 6 Mental Health America. 2022. The State of Mental Health In America. Mental Health America, [accessed 2022 Mar 28], https: / / www.mhanatiorial.org / issues / state-mental-health-america.

[0205] Ref 7 Connell J, Brazier J, O’Cathain A, Lloyd-Jones M, Paisley S. 2012. Quality of life of people with mental health problems: a synthesis of qualitative research. Health Qual Life Outcomes. 10(l):138. doi: 10.1186 / 1477-7525-10-138.

[0206] Ref 8 American Foundation for Suicide Prevention. 2022. Suicide statistics. AFSP.org. [accessed 2022 Mar 28], https: / / afsp.org / suicide-statistics / .

[0207] Ref 9 American Bar Association. [2024 Mar 28] https: / / www.americanbar.org / groups / law_aging / publications / bifocal / Vol45

[0208] Ref 10 NIH National Library7of Medicine, https: / / www.nlm.nih.gov /

[0209] Ref 11 American Psychological Association. https: / 7www.apa.org / dcpression-guideline / assessment#:~:text=The%20Beck%20Depression%20Inventory%20(BDI,for%20a ges%2013%20to%2080.

[0210] Ref 12 Waninger S, Berka C, Stevanovic Karie M, Korszen S, Mozley PD, Henchcliffe C, Kang Y, Hesterman J, Mangoubi T, Verma A. 2020. Neurophysiological Biomarkers of Parkinson’s Disease. Journal of Parkinson's Disease. 10(2):471-480. doi:10.3233 / JPD-191844.51113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0211] Ref 13 A. H. Meghdadi, C. Berka, C. Richard, G. Rupp, S. Smith, M. Stevanovic Karie, K. McShea, E. Sones, K. Marinkovic. and T. Marcotte, “EEG Event Related Potentials in Sustained, Focused and Divided Attention tasks: Potential Biomarkers for Cognitive Impairment in HIV Patients,” Clinical Neurophysiology, 2020. doi: 10.1016 / j.clinph.2020.11.026.

[0212] Ref 14 Waninger S, Berka C, Stevanovic Karie M. Korszen S, Mozley PD, Henchcliffe C. Kang Y, Hesterman J. Mangoubi T, Verma A. 2020. Neurophysiological Biomarkers of Parkinson’s Disease. Journal of Parkinson’s Disease. 10(2):471-480. doi:10.3233 / JPD-191844.

[0213] Ref 15 Kissler J, Herbert C, Winkler I, Junghofer M. 2009. Emotion and attention in visual word processing — An ERP study. Biological Psychology. 80(l):75— 83. doi:10.1016 / j.biopsycho.2008.03.004.

[0214] Ref 16 Kissler J, Herbert C. 2013. Emotion, Etmnooi, or Emitoon? - Faster lexical access to emotional than to neutral words during reading. Biological Psychology.92(3):464-479. doi: 10.1016 / j.biopsy cho.2012.09.004.

[0215] Ref 17 Keuper K, Zwanzger P, Nordt M, Eden A. Laeger I, Zwitserlood P. Kissler J, Junghofer M, Dobel C. 2014. How ‘love’ and ‘hate’ differ from ‘sleep’: Using combined electro / magnetoencephalographic data to reveal the sources of early cortical responses to emotional words: How Love and Hate Differ From Sleep. Hum Brain Mapp.35(3): 875-888. doi: 10.1002 / hbm.22220.

[0216] Ref 18 Waninger S, Berka C, Stevanovic Karie M, Korszen S, Mozley PD, Henchcliffe C, Kang Y, Hesterman J, Mangoubi T, Verma A. 2020. Neurophysiological Biomarkers of Parkinson’s Disease. Journal of Parkinson's Disease. 10(2):471-480. doi:10.3233 / JPD-191844.

[0217] Ref 19 Berka, C., Levendowski, D., Cvetinovic, M., Petrovic, M., Davis, G., Lumicao, M., Zivkovic, Popovic, M. and Olmstead, R. (2004). Real-time analysis of EEG indices of alertness, cognition, and memory' acquired with a wireless EEG headset. International Journal of Human-Computer Interaction, 17(2), 151-170.

[0218] Ref 20 Berka, C.. Levendowski, D., & Lumincao, M. (2007). EEG correlates of task engagement and mental workload in vigilance, learning and memory tasks. Aviation Space and Environmental Medicine, 78(5).

[0219] Ref 21 Johnson, R., Popovic, D., Olmstead. R., Stikic, M., Levendowski, D., and Berka, C. (2011). Drowsiness / alertness algorithm development and validation using52113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001synchronized EEG and cognitive performance to individualize a generalized model. Biological Psychology, 87(2). 241-250.

[0220] Ref 22 Richard CD, Poole JR, McConnell M, Meghdadi AH, Stevanovic-Karic M, Rupp G, Fink A, Schmitt R, Brown TL, Berka C. 2021. Alterations in Electroencephalography Theta as Candidate Biomarkers of Acute Cannabis Intoxication. Front Neurosci. 15:744762. doi:10.3389 / fnins.2021.744762.

[0221] Ref 23 Meghdadi, A. H.. et al. Resting state EEG biomarkers of cognitive decline associated with Alzheimer’s Disease and Mild Cognitive Impairment. PLOS ONE, 2021. doi: 10.1371 / journal. pone.0244180.

[0222] Ref 24 Bradshaw J, Saling M, Hopwood M, Anderson V, Brodtmann A. Fluctuating cognition in dementia with Lewy bodies and Alzheimer’s disease is qualitatively distinct. J Neurol Neurosurg Psychiatry 2004;75:382-387.

[0223] Ref 25 Westbrook P, Berka C, Levendowski DJ, Lumicao MN, Davis G, Olmstead RE, Cvetinovic M, Petrovic MM, Zavora TM. 2002. Biobehavioral Quantification of Alertness and Memory in Patients with Sleep Apnea. Sleep. 25: A49-A50.

[0224] Ref 26 Berka C, Levendowski DJ, Davis G, Yau A, Whitmoyer M. Fateh R. Zivkovic VT, Olmstead RE. 2006. Nicotine administration and withdrawal effects on EEG metrics of attention, memory and workload: implications for cognitive resource allocation. In: Augmented Cognition: Past, Present and Future. Foundations of Augmented Cognition. Strategic Analysis. Inc. p. 174-183. https: / / www.researchgate.net / profile / Chris-Berka / publication / 236610975_Nicotine_Administration_and_Withdrawal_Effects_on_EEG_ Metrics_of_Attention_Memory_and_Workload_Implications_for_Cognitive_Resource_Alloc ation / links / 0deec5183fe0feda92000000 / Nicotine-Administration-and-Withdrawal-Effects-on-EEG-Metrics-of- Attend on-Memory-and-Workload-Implications-for-Cognitive-Resource-Allocation.pdf.

[0225] Ref 27 Berka C, Ayappa I, Burschtin O, Piyathilake H, Rapoport D, Westbrook P, Johnson R, Popovic D, Behneman A, Pojman N. 2009. High Throughput Brain-Behavior Assay: Quantification of EEG and Performance in Patients Referred for Assessment of Daytime Drowsiness. Vol. 32. Seattle, WA: SLEEP. p. A161. https: / / academic.oup.com / DocumentLibraiy7SLEEP / AbstractBook2009.pdf.

[0226] Ref 28 Pojman Nicholas, Johnson Robin, Kintz Natalie, Behneman Adrienne, Popovic D. Davis G. Westbrook P, Levendowski D, Berka C. 2009. Assessing Fatigue using EEG Classification Metrics during Neurocognitive Testing. Vol. 32. Seattle. WA: SLEEP, p. Al 61. https: / / academic.oup.com / DocumentLibrary / SLEEP / AbstractBook2009.pdf.53113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0227] Ref 29 Pojman N, Behneman A, Kintz N, Johnson R, Chung G, Nagashima S, Espinosa P, Berka C. 2009. Characterizing the Psychophysiological Profile of Expert and Novice Marksmen. In: Schmorrow DD, Estabrooke IV, Grootjen M, editors. Foundations of Augmented Cognition. Neuroergonomics and Operational Neuroscience. Vol. 5638. Berlin, Heidelberg: Springer Berlin Heidelberg. (Lecture Notes in Computer Science), p. 524-532.[accessed 2022 May 20], http: / / link.springer.com / 10.1007 / 978-3-642-02812-0_61.

[0228] Ref 30 Johnson, R. R.. A. Behneman, and P. Mills. Mitigation of sleep deprivation through Omega-3 fatty acids: neurocognitive, inflammatory, EEG and EKG evidence. Society for Neuroscience Abstracts, 2010. 40: p. 297.10.

[0229] Ref 31 Waninger S., et al. Event-related potentials during sustained attention and memory tasks: Utility as biomarkers for mild cognitive impairment. Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, 2018. 10:452-460.

[0230] Ref 32 Meghdadi AH, Berka C, Richard C, Rupp G, Smith S, Stevanovic Karie M, McShea K, Sones E, Marinkovic K, Marcotte T. (2021) EEG event related potentials in sustained, focused and divided attention tasks: Potential biomarkers for cognitive impairment in HIV patients. Clin Neurophysiol. Feb;132(2):598-611. PubMed PMID: 33573761; NIHMSID: NIHMS1658147.

[0231] Ref 33 Stone BT, Correa KA, Brown TL, Spurgin AL, Stikic M, Johnson RR, Berka C. 2015. Behavioral and Neurophysiological Signatures of Benzodiazepine-Related Driving Impairments. Front Psychol. 6:1799. doi:10.3389 / fpsyg.2015.01799.

[0232] Ref 34 Furey M, Saad Z, Meghdadi A, Waninger S, Berka C, Kolb H, van Nueten L, Ceusters M, van der Ark P, de Boer P. 2018. P2X7 Receptor Antagonism Modulates the Processing of Faces Based on Emotion Expression in Major Depressive Disorder. In: NEUROPSYCHOPHARMACOLOGY. Vol. 43. NATURE PUBLISHING GROUP MACMILLAN BUILDING, 4 CRINAN ST, LONDON N 1 9XW, ENGLAND, p. S429-S429. https: / / advancedbrainmonitoring.box.com / shared / static / ljilszzmpf9flal76ks49av50osnwqm3. pdf.

[0233] Ref 35 Furey M, Meghdadi A. Richard C, Saad Z, Berka C, Bhattacharya A, Kolb H, Van Nueten L, Ceusters M, van der Ark P. et al. 2019. Reduced Baseline Resting-State Alpha Powder Reverses Following P2X7 Inhibition in Major Depression. In: NEUROPSYCHOPHARMACOLOGY. Vol. 44. NATURE PUBLISHING GROUP MACMILLAN BUILDING, 4 CRINAN ST, LONDON N1 9XW, ENGLAND, p. 436-436. https: / / advancedbrainmonitoring.app.box.eom / s / nfltst65176wqy41qg9ox4v7ivi4636e.54113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0234] Ref 36 Rozgic V, Vazquez-Reina A, Crystal M, Srivastava A, Tan V, Berka C.2014. Multi-modal prediction of PTSD and stress indicators. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). p. 3636-3640.

[0235] Ref 37 Smith S, Chang R, Tan V, Correa K, Crystal M, Johnson R, Berka C.2015. Heart-Rate Variability and Power Spectral Densities as Neurophysiological Indices of PTSD, https: / / advancedbrainmonitoring. app. box. com / s / dt 81 g6oz2b0cbxf799g7nlcqeu 1 abO 15

[0236] Ref 38 Tan V, Ankrom A, Correa K, Crystal K. Berka C. 2015. Event-Related Potential Assessment of Cognitive Tasks in PTSD, [accessed 2022 Mar 25], https: / / advancedbrainmonitoring.app.box.eom / s / yarv93 opadck3fl317eCb s0d9s4o63.

[0237] Ref 39 Guntekin B, Saatci E, Yener G. Decrease of evoked delta, theta and alpha coherences in Alzheimer patients during a visual oddball paradigm. Brain Res, 2009.1235:109-16.

[0238] Ref 40 Juckel G, Clotz F, Frodl T, KawohlW, Hampel H, Pogarell O, Hegerl U. Diagnostic usefulness of cognitive auditory' event-related P300 subcomponents in patients w ith Alzheimers disease? J Clin Neurophysiol, 2008. 25(3): 147-52.

[0239] Ref 41 Ohchney JM. Taylor JR, Gatherwright J, Salmon DP. Bressler AJ, Kutas M, Iragui-Madoz VJ. Patients with MCI and N400 or P600 abnormalities are at very high risk for conversion to dementia. Neurology', 2008. 70(19):1763-70.

[0240] Ref 42 Missonnier P. Deiber MP, Gold G. Herrmann FR, Millet P, Michon A, Fazio-Costa L. Ibanez V, Giannakopoulos P, Working memory load-related electroencephalographic parameters can differentiate progressive from stable mild cognitive impairment. Neuroscience, 2007. 150(2):346-56.

[0241] Ref 43 Bennys K, Portet F, Touchon J, Rondouin G. Diagnostic value of event-related evoked potentials N200 and P300 subcomponents in early diagnosis of Alzheimer’s disease and mild cognitive impairment. J Clin Neurophysiol, 2007. 24(5):405-12.

[0242] Ref 44 Giannakopoulos P, Missonnier P, K ovari E, Gold G, Michon A. Electrophysiological markers of rapid cognitive decline in mild cognitive impairment. Front Neurol Neurosci, 2009. 24:39-46.

[0243] Ref 45 Missonnier P. Gold G, Fazio-Costa L, Michel JP, Mulligan R, Michon A, Ibanez V, Giannakopoulos P. Early event-related potential changes during working memory activation predict rapid decline in mild cognitive impairment. J Gerontol A Biol Sci Med Sci, 2005. 60(5):660-6.55113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0244] Ref 46 Liedorp M, van der Flier WM, Hoogervorst EL, Scheltens P, Siam CJ. Associations between paterns of EEG abnormalities and diagnosis in a large memory clinic cohort. Dement Geriatr Cogn Disord, 2009. 27(1): 18-23.

[0245] Ref 47 Haupt M, Gonzlez-Hemndez JA, Scherbaum WA. Regions with different evoked frequency band responses during early-stage visual processing distinguish mild Alzheimer dementia from mild cognitive impairment and normal aging. Neurosci Let, 2008. 442(3):273-8.

[0246] Ref 48 Fernandez R, Kavcic V, Duffy CJ. Neurophysiologic analyses of low-and high-level visual processing in Alzheimer disease. Neurology, 2007. 68(24):2066-76.

[0247] Ref 49 Crowley K, Trinder J, Colrain IM. Evoked K-complex generation: the impact of sleep spindles and age. Clin Neurophysiol, 2004. 115(2):471- 6.

[0248] Ref 50 Caravaglios G, Costanzo E, Palermo F, Muscoso EG. Decreased amplitude of auditory event-related delta responses in Alzheimer’s disease. Int. J. Psychophysiol, 2008. 70(l):23-32.

[0249] Ref 51 Papaliagkas V, Kimiskidis V. Tsolaki M, Anogzanakis G. Usefulness of event-related potentials in the assessment of mild cognitive impairment. BMC Neuroscience.2008. 9:107.

[0250] Ref 52 Frodl T, Hampel H, Juckel G, Burger K, Padberg F, Engel RR, Moller HJ, Hegerl U. Value of event-related P300 subcomponents in the clinical diagnosis of mild cognitive impairment and Alzheimer’s Disease. Psychophysiology. 2002. 39(2): 175-81.

[0251] Ref 53 Polich J and Corey-Bloom J. Alzheimer’s disease and P300: review and evaluation of task and modality. Curr Alzheimer Res, 2005. 2(5):515-25.

[0252] Ref 54 van Deursen JA, Vuurman EF, Smits LL. Verhey FR, Riedel WJ. Response speed, contingent negative variation and P300 in Alzheimer’s disease and MCI. Brain Cogn, 2009. 69(3):592-9.

[0253] Ref 55 Karrasch M, Laine M, Rinne JO, Rapinoja P, Sinerva E, Krause CM. Brain oscillatory responses to an auditory verbal working memory task in mild cognitive impairment and Alzheimer’s disease. Int J Psychophysiol, 2006. 59(2): 168-78.

[0254] Ref 56 Gam H. Waser M, Deistler M, Schmidt R, et al. Quantitative EEG in Alzheimer's disease: Cognitive state, resting state and association with disease severity. Int J Psychophysiol. 2014 Jun 14. pii: S0167- 8760(14)00137-8. doi: 10.1016 / j.ijpsycho.2014.06.003. [Epub ahead of print]56113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0255] Ref 57 Keller, J, BD Hicks, and G Miller, Psychophysiology in the study of psychopathology, in Handbook of Psychophysiology, JT Caciooppo, LG Tassinary, and GG Bemtson, Editors 2000, Cambridge University Press: Cambridge p 719-750

[0256] Ref 58 Hillyard, SA, et al, Electrical signs of selective attention in the human brain Science, 1973 182(108): p 177-80

[0257] Ref 59 Hillyard, SA and M Kutas, Electrophysiology of cognitive processing Annu Rev Psychol, 1983 34: p 33-61

[0258] Ref 60 Luck, SJ and SA Hillyard, The role of attention in feature detection and conjunction discrimination: an electrophysiological analysis Int J Neurosci, 1995 80(1-4): p 281-97

[0259] Ref 61 Bashore, TR, et al, Is handwriting posture associated with differences in motor control? An analysis of asymmetries in the readiness potential Neuropsychologia, 1982 20(3): p 327-46

[0260] Ref 62 Kotterba, S. et al, Neuropsychological investigations and event-related potentials in obstructive sleep apnea syndrome before and during CP AP -therapy J Neurol Sci, 1998 159(1): p 45-50

[0261] Ref 63 Walsleben, JA, NK Squires, and VL Rothenberger, Auditory event-related potentials and brain dysfunction in sleep apnea Electroencephalogr Clin Neurophysiol, 1989 74(4): p 297-311

[0262] Ref 64 Inoue. Y, et al, P300 abnormalities in patients with severe sleep apnea syndrome Psychiatry Clin Neurosci, 2001 55(3): p 247-8

[0263] Ref 65 Coles, MG, MK Scheffers, and L Fournier, Where did you go wrong? Errors, partial errors, and the nature of human information processing Acta Psychol (Amst), 1995 90(1-3): p 129-44

[0264] Ref 66 Kramer, AF and T Weber, Applications of psychophysiology to human factors, in Handbook of Psychophysiology, JT Caciooppo, LG Tassinary, and GG Bemtson, Editors 2000, Cambridge University Press: Cambridge p 794-814

[0265] Ref 67 Findley, LJ. et al, Driving simulator performance in patients with sleep apnea Am Rev Respir Dis. 1989 140(2): p 529-30

[0266] Ref 68 Luck, SJ and SA Hillyard, The role of attention in feature detection and conjunction discrimination: an electrophysiological analysis Int J Neurosci, 1995 80(1-4): p 281-97

[0267] Ref 69 Naatanen. R, AW Gaillard, and S Mantysalo. Early selective-attention effect on evoked potential reinterpreted Acta Psychol (Amst), 1978 42(4): p 313-2957113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0268] Ref 70 Polich, J and A Kok. Cognitive and biological determinants of P300: an integrative review Biol Psychol, 1995 41(2): p 103-46

[0269] Ref 71 Polich, J, et al, P300 latency reflects the degree of cognitive decline in dementing illness Electroencephalogr Clin Neurophysiol, 1986 63(2): p 138-44

[0270] Ref 72 Dustman, RE, et al, Age and fitness effects on EEG, ERPs, visual sensitivity, and cognition Neurobiol Aging, 1990 11(3): p 193-200

[0271] Ref 73 Campbell, KB, et al, Evoked potential correlates of human information processing Biol Psychol, 1979 8(1): p 45-68

[0272] Ref 74 Leocani, L and G Comi, EEG coherence in pathological conditions J Clin Neurophysiol. 1999 16(6): p 548-55

[0273] Ref 75 Weiss, S and HM Mueller. The contribution of EEG coherence to the investigation of language Brain Lang, 2003 85(2): p 325-43.

[0274] The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles described herein can be applied to other embodiments without departing from the spirit or scope of the invention. Thus, it is to be understood that the description and drawings presented herein represent a presently preferred embodiment of the invention and are therefore representative of the subject matter which is broadly contemplated by the present invention. It is further understood that the scope of the present invention fully encompasses other embodiments that may become obvious to those skilled in the art and that the scope of the present invention is accordingly not limited.

[0275] As used herein, the terms “comprising,” “comprise,” and “comprises” are open-ended. For instance, “A comprises B” means that A may include either: (i) only B; or (ii) B in combination with one or a plurality, and potentially any number, of other components. In contrast, the terms “consisting of,” “consist of,” and “consists of’ are closed-ended. For instance, “A consists of B” means that A only includes B with no other component in the same context.

[0276] Combinations, described herein, such as “at least one of A, B. or C.” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ include any combination of A, B, and / or C, and may include multiples of A. multiples of B, or multiples of C. Specifically, combinations such as “at least one of A. B, or C,” “one or more of A. B, or C,” “at least one of A, B. and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof’ may be A only, B only, C only, A and 58113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001B, A and C, B and C, or A and B and C, and any such combination may contain one or more members of its constituents A, B, and / or C. For example, a combination of A and B may comprise one A and multiple B’s, multiple A’s and one B, or multiple A’s and multiple B’s.

[0277] Aspect 1 is a system comprising: at least one memory; and at least one processor coupled to the at least one memory7and, based at least in part on information stored in the at least one memory, the at least one processor is configured to: receive information regarding a first user of the system; output, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for an assessment of the first user; receive data relating to the one or more cognitive tasks performed by the first user; generate at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user; and output a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user.

[0278] Aspect 2 is the system of aspect 1, wherein the information comprises one or more of demographic information or health information.

[0279] Aspect 3 is the system of aspect 2, wherein the health information comprises first health information received from a healthcare provider.

[0280] Aspect 4 is the system of any of aspects 2 and 3, wherein the information relates to one or more of depression, anxiety7, trauma, stress, sleep, or other mental health issues.

[0281] Aspect 5 is the system of any of aspects 2 to 4, wherein the at least one processor, individually or in any combination, is further configured to: output for display one or more questionnaires to elicit at least a portion of the information, wherein to receive the information, the at least one processor, individually or in any combination, is configured to receive the information in response to the output of the one or more questionnaires.

[0282] Aspect 6 is the system of any of aspects 1 to 5, wherein the first indication of the one or more cognitive tasks comprises an additional indication of a type of task and, at least in part, content of at least one cognitive task of the one or more cognitive tasks.

[0283] Aspect 7 is the system of aspect 6, wherein the one or more cognitive tasks comprise types of cognitive tasks designed to assess one or more of sensory7discrimination, attention, memory, executive function across one or more sensory modalities.

[0284] Aspect 8 is the system of any7of aspects 6 and 7, wherein the one or more cognitive tasks comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task.59113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0285] Aspect 9 is the system of any of aspects 6 to 8, wherein the content of the at least one cognitive task comprises one or more of words, images, videos, music, scents, or other evocative material.

[0286] Aspect 10 is the system of aspect 9, wherein the images comprise, images of one or more of a sad face, a happy face, or a neutral face.

[0287] Aspect 11 is the system of any of aspects 6 to 10, wherein the at least one processor, individually or in any combination, is further configured to: select, based on the information regarding the first user of the system, the one or more cognitive tasks.

[0288] Aspect 12 is the system of aspect 11, wherein the one or more cognitive tasks are selected based on one or more conditions indicated by the information regarding the first user of the system.

[0289] Aspect 13 is the system of aspect 12, wherein the one or more conditions comprise one or more of Alzheimer's disease, Parkinson's dementia, mild cognitive impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders and HIV-related cognitive decline.

[0290] Aspect 14 is the system of aspect 13, wherein the at least one processor, individually or in any combination, is further configured to: generate a mapping between the types of the information that may be received from a user to a presence and a severity7of one of a condition of the one or more conditions or a construct of a plurality of constructs, wherein the plurality of constructs comprises depression, anxiety, sleep issues, suicidality, addiction, and cognitive impairment, and wherein to select the one or more cognitive tasks, the at least one processor, individually or in any combination, is configured to select the one or more cognitive tasks based on the generated mapping.

[0291] Aspect 15 is the system of any of aspects 11 to 14, wherein the selection is based on a machine learning model.

[0292] Aspect 16 is the system of aspect 15, wherein the at least one processor, individually or in any combination, is further configured to: train the machine learning model based on additional information regarding a plurality of additional users.

[0293] Aspect 17 is the system of any of aspects 11 to 15. wherein the at least one processor, individually or in any combination, is further configured to: receive capability information relating to an additional assessment of one or more capabilities of the first user related to the cognitive tasks, wherein to select the one or more cognitive tasks, the at least one processor, individually or in any combination, is configured to select the one or more cognitive tasks based on the capability information.60113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0294] Aspect 18 is the system of aspect 17, wherein, based on the capability information, the one or more cognitive tasks comprise at least one passive cognitive task.

[0295] Aspect 19 is the system of aspect 18, wherein, based on the capability information, the one or more cognitive tasks comprise only passive cognitive tasks.

[0296] Aspect 20 is the system of any of aspects 1 to 19, wherein the data comprises at least first data related to stimuli presented in association with the one or more cognitive tasks and second data regarding responses to the stimuli presented in association with the one or more cognitive tasks.

[0297] Aspect 21 is the system of aspect 20, wherein the first data and the second data are synchronized.

[0298] Aspect 22 is the system of aspect 21, wherein the first data and the second data are synchronized with millisecond resolution.

[0299] Aspect 23 is the system of any of aspects 20 to 22, wherein the second data comprises biomarker data and the data further comprises one or more of additional biomarker data or label data.

[0300] Aspect 24 is the system of aspect 23. wherein the biomarker data comprises one or more of: electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data.

[0301] Aspect 25 is the system of aspect 24, wherein the biomarker data is associated with one or more of: a heart rate (HR); a HR Variability (HRV); a primary power spectral density (PSD) measures; aperiodic analysis; an aperiodic analysis; arhythmicity analysis; a coherence analysis; a complexity analysis; a HRV analysis; a resting state EEG; an event-related potentials (ERPs); a single-trial measures for ERP tasks; or a cluster-based permutation test.

[0302] Aspect 26 is the system of any of aspects 1 to 25. wherein the one or more cognitive tasks is a first set of cognitive tasks and the data relating to the first set of cognitive tasks is first data associated with a first assessment performed at a first time, wherein the at least one processor, individually or in any combination, is further configured to: store additional data relating to a set of one or more previous assessments performed at a set of previous times, and wherein to generate the at least one of the one or more diagnoses or the one or more analyses for the first user, the at least one processor, individually or in any combination, is configured to generate the at least one of the one or more diagnoses or the one or more analyses for the first user based on the additional data relating to the set of one or more previous assessments performed at the set of previous times.61113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0303] Aspect 27 is the system of aspect 26, wherein to generate the at least one of the one or more diagnoses or the one or more analyses for the first user, the at least one processor, individually or in any combination, is configured to generate the at least one of the one or more diagnoses or the one or more analyses for the first user by providing the data relating to the one or more cognitive tasks performed by the first user to an additional machine learning model.

[0304] Aspect 28 is the system of any of aspects 1-27. further comprising: a first secure connection between the system and a first computing device, wherein the system is configured to receive the information regarding the first user of the system from the first computing device using the first secure connection.

[0305] Aspect 29 is the system of aspect 28, further comprising: the first computing device, wherein the first computing device comprises: a display in communication with the first user of the system; at least one additional memory; and at least one additional processor coupled to the display and the at least one additional memory and, based at least in part on information stored in the at least one additional memory7, the at least one processor is configured to: display one or more prompts related to the first user of the system; receive, at least in part, the information regarding the first user of the system based on the one or more prompts; and transmit, at least in part, the information regarding the first user of the system to the system using the first secure connection.

[0306] Aspect 30 is the system of any of aspects 28 and 57, further comprising: a second secure connection between the system and a second computing device, wherein the system is configured to output the first indication of the one or more cognitive tasks for the assessment of the first user to the second computing device using the second secure connection, and wherein the system is configured to receive the data relating to the one or more cognitive tasks performed by the first user from the second computing device using the second secure connection.

[0307] Aspect 31 is the system of aspect 30, further comprising: the second computing device, wherein the second computing device comprises: an additional display in communication with the first user of the system; at least one second additional memory; and at least one second additional processor coupled to the additional display and the at least one second additional memory and, based at least in part on information stored in the at least one second additional memory, the at least one processor is configured to: output, for the first user of the system to perform the one or more cognitive tasks, a set of stimuli associated with the one or more cognitive tasks; receive, while the first user of the system performs the one or more cognitive tasks, one or more sets of data from one or more sources of input to the second 62113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001computing device associated with the set of stimuli; generate, based on the set of stimuli and the one or more sets of data, the data relating to the one or more cognitive tasks performed by the first user; and transmit, to the system using the second secure connection, the data relating to the one or more cognitive tasks performed by the first user.

[0308] Aspect 32 is the system of aspect 31, wherein the one or more sources of input comprise at least one or more sets of sensors for collecting one or more of electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data, the system further comprising: the one or more sets of sensors coupled to the second computing device.

[0309] Aspect 33 is the system of any of aspects 30 to 32, further comprising: a third secure connection between the system and a third computing device, wherein the system is configured to output the second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user to the third computing device using the third secure connection, wherein one or more of the first computing device or the second computing device is a same computing device as the third computing device, and wherein one or more of the first secure connection or the second secure connection is a same secure connection as the third secure connection.

[0310] Aspect 34 is a method comprising: receiving information regarding a first user of a system; outputting, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for a cognitive assessment of the first user; receiving data relating to the one or more cognitive tasks performed by the first user; generating at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user; and outputting a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user.

[0311] Aspect 35 is the method of aspect 34, wherein the information comprises one or more of demographic information or health information.

[0312] Aspect 36 is the method of aspect 35, wherein the health information comprises first health information received from a healthcare provider.

[0313] Aspect 37 is the method of any of aspects 35 and 36, wherein the information relates to one or more of depression, anxiety, trauma, stress, sleep, or other mental health issues.

[0314] Aspect 38 is the method of any of aspects 35 to 37, further comprising: outputting for display one or more questionnaires to elicit at least a portion of the information, wherein the receiving the information is in response to outputting the one or more questionnaires.63113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0315] Aspect 39 is the method of any of aspects 34 to 38, wherein the first indication of the one or more cognitive tasks comprises an additional indication of a type of task and. at least in part, content of at least one cognitive task of the one or more cognitive tasks.

[0316] Aspect 40 is the method of aspect 39, wherein the one or more cognitive tasks comprise ty pes of cognitive tasks designed to assess one or more of sensory7discrimination, attention, memory, executive function across one or more sensory modalities.

[0317] Aspect 41 is the method of any of aspects 39 and 40. wherein the one or more cognitive tasks comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task, Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task.

[0318] Aspect 42 is the method of any of aspects 39 to 41, wherein the content of the at least one cognitive task comprises one or more of words, images, videos, music, scents, or other evocative material.

[0319] Aspect 43 is the method of aspect 42, wherein the images comprise, images of one or more of a sad face, a happy face, or a neutral face.

[0320] Aspect 44 is the method of any of aspects 39 to 43, further comprising: selecting the one or more cognitive tasks based on the information regarding the first user of the system.

[0321] Aspect 45 is the method of aspect 44, wherein the one or more cognitive tasks are selected based on one or more conditions indicated by the information regarding the first user of the system.

[0322] Aspect 46 is the method of aspect 45, wherein the one or more conditions comprise one or more of Alzheimer's disease, Parkinson's dementia, mild cognitive impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders and HIV-related cognitive decline.

[0323] Aspect 47 is the method of aspect 46, further comprising: generating a mapping between the types of the information that may be received from a user to a presence and a severity of one of a condition of the one or more conditions or a construct of a plurality of constructs, wherein the plurality of constructs comprises depression, anxiety, sleep issues, suicidality, addiction, and cognitive impairment, and wherein the selection of the one or more cognitive tasks is further based on the generated mapping.

[0324] Aspect 48 is the method of any of aspects 44 to 47, wherein the selection is based on a machine learning model.

[0325] Aspect 49 is the method of aspect 48, further comprising: training the machine learning model based on additional information regarding a plurality of additional users.64113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0326] Aspect 50 is the method of any of aspects 44 to 49. further comprising: receiving capability information relating to an additional assessment of one or more capabilities of the first user related to the cognitive tasks, wherein the selection of the one or more cognitive tasks is further based on the capability information.

[0327] Aspect 51 is the method of aspect 50, wherein, based on the capability information, the one or more cognitive tasks comprise at least one passive cognitive task.

[0328] Aspect 52 is the method of aspect 51, wherein, based on the capability information, the one or more cognitive tasks comprise only passive cognitive tasks.

[0329] Aspect 53 is the method of any of aspects 34 to 52, wherein the data comprises at least first data related to stimuli presented in association with the one or more cognitive tasks and second data regarding responses to the stimuli presented in association with the one or more cognitive tasks.

[0330] Aspect 54 is the method of aspect 53, wherein the first data and the second data are synchronized.

[0331] Aspect 55 is the method of aspect 54, wherein the first data and the second data are synchronized with millisecond resolution.

[0332] Aspect 56 is the method of any of aspects 53 to 55, wherein the second data comprises biomarker data and the data further comprises one or more of additional biomarker data or label data.

[0333] Aspect 57 is the method of aspect 56, wherein the biomarker data comprises one or more of: electrocardiography (ECG) data, pupillometry data, or electroencephalography (EEG) data.

[0334] Aspect 58 is the method of aspect 57. wherein the biomarker data is associated with one or more of: a heart rate (HR); a HR Variability (HRV); a primary power spectral density (PSD) measures; a periodic analysis; an aperiodic analysis; a rhythmicity analysis; a coherence analysis; a complexity analysis; a HRV analysis; a resting state EEG; an event-related potentials (ERPs); a single-trial measures for ERP tasks; or a cluster-based permutation test.

[0335] Aspect 59 is the method of any of aspects 34 to 58, wherein the one or more cognitive tasks is a first set of cognitive tasks and the data relating to the first set of cognitive tasks is first data associated with a first assessment performed at a first time, the method further comprising: storing additional data relating to a set of one or more previous assessments performed at a set of previous times, and wherein generating the at least one of the one or more diagnoses or the one or more analyses for the first user is further based on the additional data relating to the set of one or more previous assessments performed at the set of previous times.65113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001

[0336] Aspect 60 is the method of aspect 59, wherein generating the at least one of the one or more diagnoses or the one or more analyses for the first user comprises providing the data relating to the one or more cognitive tasks performed by the first user to an additional machine learning model.66113102-0022 WOO 1 / 89543843

Claims

Attorney Docket No. 113102-0022W001CLAIMSWhat is claimed is:

1. A system comprising:at least one memory; andat least one processor coupled to the at least one memory and, based at least in part on information stored in the at least one memory, the at least one processor is configured to:receive information regarding a first user of the system;output, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for an assessment of the first user;receive data relating to the one or more cognitive tasks performed by the first user;generate at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user; andoutput a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user.

2. The system of claim 1. wherein the information comprises one or more of demographic information or health information.

3. The system of claim 2, wherein the health information comprises first health information received from a healthcare provider.

4. The system of any of claims 2 and 3, wherein the information relates to one or more of depression, anxiety, trauma, stress, sleep, or other mental health issues.

5. The system of any of claims 2 to 4, wherein the at least one processor, individually or in any combination, is further configured to:output for display one or more questionnaires to elicit at least a portion of the information, wherein to receive the information, the at least one processor, individually or in any combination, is configured to receive the information in response to the output of the one or more questionnaires.67113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W0016. The system of any of claims 1 to 5, wherein the first indication of the one or more cognitive tasks comprises an additional indication of a type of task and, at least in part, content of at least one cognitive task of the one or more cognitive tasks.

7. The system of claim 6, wherein the one or more cognitive tasks comprise types of cognitive tasks designed to assess one or more of sensory discrimination, attention, memory, executive function across one or more sensory modalities.

8. The system of any of claims 6 and 7, wherein the one or more cognitive tasks comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task. Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task.

9. The system of any of claims 6 to 8, wherein the content of the at least one cognitive task comprises one or more of words, images, videos, music, scents, or other evocative material.

10. The system of claim 9, wherein the images comprise, images of one or more of a sad face, a happy face, or a neutral face.

11. The system of any of claims 6 to 10, wherein the at least one processor, individually or in any combination, is further configured to:select, based on the information regarding the first user of the system, the one or more cognitive tasks.

12. The system of claim 11, wherein the one or more cognitive tasks are selected based on one or more conditions indicated by the information regarding the first user of the system.

13. The system of claim 12, wherein the one or more conditions comprise one or more of Alzheimer’s disease. Parkinson’s dementia, mild cognitive impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders and HIV -related cognitive decline.

14. The system of claim 13, wherein the at least one processor, individually or in any combination, is further configured to:68113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001generate a mapping between the types of the information that may be received from a user to a presence and a severity of one of a condition of the one or more conditions or a construct of a plurality of constructs, wherein the plurality’ of constructs comprises depression, anxiety7, sleep issues, suicidality’, addiction, and cognitive impairment, and wherein to select the one or more cognitive tasks, the at least one processor, individually or in any combination, is configured to select the one or more cognitive tasks based on the generated mapping.

15. The system of any of claims 11 to 14, wherein the selection is based on a machine learning model.

16. The system of claim 15, wherein the at least one processor, individually or in any combination, is further configured to:train the machine learning model based on additional information regarding a plurality of additional users.

17. The system of any of claims 11 to 15, wherein the at least one processor, individually or in any combination, is further configured to:receive capability’ information relating to an additional assessment of one or more capabilities of the first user related to the cognitive tasks, wherein to select the one or more cognitive tasks, the at least one processor, individually or in any combination, is configured to select the one or more cognitive tasks based on the capability information.

18. The system of claim 17, wherein, based on the capability information, the one or more cognitive tasks comprise at least one passive cognitive task.

19. The system of claim 18, wherein, based on the capability information, the one or more cognitive tasks comprise only passive cognitive tasks.

20. The system of any of claims 1 to 19, wherein the data comprises at least first data related to stimuli presented in association with the one or more cognitive tasks and second data regarding responses to the stimuli presented in association with the one or more cognitive tasks.

21. The system of claim 20, wherein the first data and the second data are synchronized.69113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W00122. The system of claim 21, wherein the first data and the second data are synchronized with millisecond resolution.

23. The system of any of claims 20 to 22, wherein the second data comprises biomarker data and the data further comprises one or more of additional biomarker data or label data.

24. The system of claim 23, wherein the biomarker data comprises one or more of:electrocardiography (ECG) data,a heart rate (HR),a HR Variability (HRV),pupillometry data, orelectroencephalography (EEG) data.

25. The system of claim 24, wherein the biomarker data is associated with one or more of: a heart rate (HR);a HR Variability (HRV);a primary power spectral density (PSD) measures;a periodic analysis;an aperiodic analysis;a rhythmicity analysis;a coherence analysis;a complexity analysis;a HRV analysis;a resting state EEG;an event-related potentials (ERPs);a single-trial measures for ERP tasks; ora cluster-based permutation test.

26. The system of any of claims 1 to 25, wherein the one or more cognitive tasks is a first set of cognitive tasks and the data relating to the first set of cognitive tasks is first data associated with a first assessment performed at a first time, wherein the at least one processor, individually or in any combination, is further configured to:store additional data relating to a set of one or more previous assessments performed at a set of previous times, and wherein to generate the at least one of the one or more diagnoses 70113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001or the one or more analyses for the first user, the at least one processor, individually or in any combination, is configured to generate the at least one of the one or more diagnoses or the one or more analyses for the first user based on the additional data relating to the set of one or more previous assessments performed at the set of previous times.

27. The system of claim 26, wherein to generate the at least one of the one or more diagnoses or the one or more analyses for the first user, the at least one processor, individually or in any combination, is configured to generate the at least one of the one or more diagnoses or the one or more analyses for the first user by providing the data relating to the one or more cognitive tasks performed by the first user to an additional machine learning model.

28. The system of any of claims 1-27, further comprising:a first secure connection between the system and a first computing device, wherein the system is configured to receive the information regarding the first user of the system from the first computing device using the first secure connection.

29. The system of claim 28, further comprising:the first computing device, wherein the first computing device comprises:a display in communication with the first user of the system;at least one additional memory; andat least one additional processor coupled to the display and the at least one additional memory and, based at least in part on information stored in the at least one additional memory, the at least one processor is configured to:display one or more prompts related to the first user of the system; receive, at least in part, the information regarding the first user of the system based on the one or more prompts; andtransmit, at least in part, the information regarding the first user of the system to the system using the first secure connection.

30. The system of any of claims 28 and 57, further comprising:a second secure connection between the system and a second computing device, wherein the system is configured to output the first indication of the one or more cognitive tasks for the assessment of the first user to the second computing device using the second secure connection, and wherein the system is configured to receive the data relating to the one or more 71113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001cognitive tasks performed by the first user from the second computing device using the second secure connection.

31. The system of claim 30, further comprising:the second computing device, wherein the second computing device comprises:an additional display in communication with the first user of the system; at least one second additional memory; andat least one second additional processor coupled to the additional display and the at least one second additional memory and, based at least in part on information stored in the at least one second additional memory, the at least one processor is configured to:output, for the first user of the system to perform the one or more cognitive tasks, a set of stimuli associated with the one or more cognitive tasks;receive, while the first user of the system performs the one or more cognitive tasks, one or more sets of data from one or more sources of input to the second computing device associated with the set of stimuli; generate, based on the set of stimuli and the one or more sets of data, the data relating to the one or more cognitive tasks performed by the first user; and transmit, to the system using the second secure connection, the data relating to the one or more cognitive tasks performed by the first user.

32. The system of claim 31, wherein the one or more sources of input comprise at least one or more sets of sensors for collecting one or more of electrocardiography (ECG) data, a HR data, a HRV data, pupillometry data, or electroencephalography (EEG) data, the system further comprising:the one or more sets of sensors coupled to the second computing device.

33. The system of any of claims 30 to 32, further comprising:a third secure connection between the system and a third computing device, wherein the system is configured to output the second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user to the third computing device using the third secure connection, wherein one or more of the first computing device or the second computing device is a same computing device as the third computing device, and wherein one72113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001or more of the first secure connection or the second secure connection is a same secure connection as the third secure connection.

34. A method comprising:receiving information regarding a first user of a system;outputting, based on the information regarding the first user of the system, a first indication of one or more cognitive tasks for a cognitive assessment of the first user;receiving data relating to the one or more cognitive tasks performed by the first user; generating at least one of one or more diagnoses or one or more analyses for the first user based on the data relating to the one or more cognitive tasks performed by the first user; andoutputting a second indication of the at least one of the one or more diagnoses or the one or more analyses for the first user.

35. The method of claim 34. wherein the information comprises one or more of demographic information or health information.

36. The method of claim 35, wherein the health information comprises first health information received from a healthcare provider.

37. The method of any of claims 35 and 36, wherein the information relates to one or more of depression, anxiety, trauma, stress, sleep, or other mental health issues.

38. The method of any of claims 35 to 37, further comprising:outputting for display one or more questionnaires to elicit at least a portion of the information, wherein the receiving the information is in response to outputting the one or more questionnaires.

39. The method of any of claims 34 to 38, wherein the first indication of the one or more cognitive tasks comprises an additional indication of a type of task and, at least in part, content of at least one cognitive task of the one or more cognitive tasks.73113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W00140. The method of claim 39, wherein the one or more cognitive tasks comprise types of cognitive tasks designed to assess one or more of sensory- discrimination, attention, memory, executive function across one or more sensory modalities.

41. The method of any of claims 39 and 40, wherein the one or more cognitive tasks comprise one or more of a 5-minute Resting State Eyes Open (EO) task, and a Resting State Eyes Closed (EC) task, a 3-Choice Vigilance task, a Standard Image Recognition (SIR) task. Emotional Image Recognition (EIR) task, or an Auditory Oddball (AO) task.

42. The method of any of claims 39 to 41, wherein the content of the at least one cognitive task comprises one or more of words, images, videos, music, scents, or other evocative material.

43. The method of claim 42, wherein the images comprise, images of one or more of a sad face, a happy face, or a neutral face.

44. The method of any of claims 39 to 43. further comprising:selecting the one or more cognitive tasks based on the information regarding the first user of the system.

45. The method of claim 44, wherein the one or more cognitive tasks are selected based on one or more conditions indicated by the information regarding the first user of the system.

46. The method of claim 45, wherein the one or more conditions comprise one or more of Alzheimer’s disease. Parkinson’s dementia, mild cognitive impairment, depression, anxiety, post-traumatic stress disorder, sleep disorders and HIV-related cognitive decline.

47. The method of claim 46, further comprising:generating a mapping between the types of the information that may be received from a user to a presence and a severity of one of a condition of the one or more conditions or a construct of a plurality of constructs, wherein the plurality- of constructs comprises depression, anxiety, sleep issues, suicidality, addiction, and cognitive impairment, and wherein the selection of the one or more cognitive tasks is further based on the generated mapping.74113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W00148. The method of any of claims 44 to 47, wherein the selection is based on a machine learning model.

49. The method of claim 48, further comprising:training the machine learning model based on additional information regarding a plurality of additional users.

50. The method of any of claims 44 to 49, further comprising:receiving capability information relating to an assessment of one or more capabilities of the first user related to the cognitive tasks, wherein the selection of the one or more cognitive tasks is further based on the capability information.

51. The method of claim 50, wherein, based on the capability information, the one or more cognitive tasks comprise at least one passive cognitive task.

52. The method of claim 51, wherein, based on the capability information, the one or more cognitive tasks comprise only passive cognitive tasks.

53. The method of any of claims 34 to 52, wherein the data comprises at least first data related to stimuli presented in association with the one or more cognitive tasks and second data regarding responses to the stimuli presented in association with the one or more cognitive tasks.

54. The method of claim 53, wherein the first data and the second data are synchronized.

55. The method of claim 54, wherein the first data and the second data are synchronized with millisecond resolution.

56. The method of any of claims 53 to 55, wherein the second data comprises biomarker data and the data further comprises one or more of additional biomarker data or label data.

57. The method of claim 56, wherein the biomarker data comprises one or more of:electrocardiography (ECG) data,a heart rate (HR),a HR Variability (HRV),75113102-0022 WOO 1 / 89543843Attorney Docket No. 113102-0022W001pupillometry data, orelectroencephalography (EEG) data.

58. The method of claim 57, wherein the biomarker data is associated with one or more of:a heart rate (HR);a HR Variability (HRV);a primary power spectral density (PSD) measures;a periodic analysis;an aperiodic analysis;a rhythmicity analysis;a coherence analysis;a complexity analysis;a HRV analysis;a resting state EEG;an event-related potentials (ERPs);a single-trial measures for ERP tasks; ora cluster-based permutation test.

59. The method of any of claims 34 to 58, wherein the one or more cognitive tasks is a first set of cognitive tasks and the data relating to the first set of cognitive tasks is first data associated with a first assessment performed at a first time, the method further comprising:storing additional data relating to a set of one or more previous assessments performed at a set of previous times, and wherein generating the at least one of the one or more diagnoses or the one or more analyses for the first user is further based on the additional data relating to the set of one or more previous assessments performed at the set of previous times.

60. The method of claim 59, w herein generating the at least one of the one or more diagnoses or the one or more analyses for the first user comprises providing the data relating to the one or more cognitive tasks performed by the first user to an additional machine learning model.76113102-0022 WOO 1 / 89543843

Images