Immersive headset evaluation of visual field

Abstract

Techniques for assessing a visual field of a patient are presented. The techniques use a system that includes: an immersive headset; a patient input device; and an electronic processor coupled to the immersive headset and to the patient input device, where the electronic processor is configured to perform actions that include: causing the immersive headset to display a first sequence of stimuli to a first eye of the patient, where respective locations of individual stimuli from the first sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the first eye of the patient; receiving, from the patient input device, responses indicative of whether the patient perceived individual of the first sequence of stimuli; adapting the first sequence of stimuli based at least on the responses; and reporting a patient visual deficit pattern based on the causing and the receiving.

Description

IMMERSIVE HEADSET EVALUATION OF VISUAL FIELDRelated Application

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63 / 533,161 , entitled “Immersive Headset Evaluation of Visual Field,” and filed August 17, 2023.Field

[0002] This disclosure relates generally to ophthalmology and neurology.Background

[0003] Several neurological diseases (e.g., stroke, multiple sclerosis, idiopathic intracranial hypertension) and ophthalmological diseases (e.g., glaucoma) are known to affect the visual field. Hence, visual field assessment is an important part of the neuro-ophthalmologic assessment. Visual field defects are generally not diagnosed accurately by neurologists, as common examination techniques such as finger confrontation (i.e., having a patient follow a care provider’s finger visually) have sensitivity of only 35% for detecting visual field defects. By contrast, a quantitative assessment of a patient’s visual field makes it possible to accurately diagnose and follow up the progression of visual field defects over time.

[0004] Existing devices for detecting visual field deficits are immobile, large (e.g., 2’x2’), heavy (e.g., over 60 lbs.), expensive (e.g., $40,000), and require trained technicians to operate. A representative such device projects a series of white light stimuli of varying intensities (brightness) throughout a uniformly illuminated bowl in which the subject places their head. The patient uses a handheld tethered button thatthey press to indicate when they see a light, and the device provides a report of the results. Such devices are generally not readily available, particularly in settings such as urgent care facilities and emergency rooms.Summary

[0005] According to various embodiments, a system for assessing a visual field of a patient is presented. The system includes: an immersive headset; a patient input device; and an electronic processor communicatively coupled to the immersive headset and to the patient input device, the electronic processor configured to perform actions including: causing the immersive headset to display a first sequence of stimuli to a first eye of the patient, where respective locations of individual stimuli from the first sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the first eye of the patient; receiving, from the patient input device, responses indicative of whether the patient perceived individual of the first sequence of stimuli; adapting the first sequence of stimuli based at least on the responses; and reporting a patient visual deficit pattern based on the causing and the receiving.

[0006] Various optional features of the above system embodiments include the following. The actions may further include: providing the patient visual deficit pattern to a machine learning system, where the machine learning system is trained with training data, where the training data includes training visual deficit patterns and corresponding training diagnoses; obtaining, from the machine learning system, an indication of a patient diagnosis; and outputting the patient diagnosis. The indication of the patient diagnosis may include an indication of stroke. The indication of the patient diagnosis may include an indication of at least one of: multiple sclerosis,glaucoma, or idiopathic intracranial hypertension. The actions may further include: selecting a second sequence of stimuli based at least in part on the responses indicative of whether the patient perceived individual of the first sequence of stimuli; causing the immersive headset to display the second sequence of stimuli to a second eye of the patient, where respective locations of individual stimuli from the second sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the second eye of the patient; and receiving, from the patient input device, responses indicative of whether the patient perceived individual of the second sequence of stimuli; where the patient visual deficit pattern is further based on the responses indicative of whether the patient perceived individual of the second sequence of stimuli. The adapting may include adapting individual intensities of at least some of the first sequence of stimuli. The adapting may include adapting respective locations of at least some of the first sequence of stimuli. The adapting may include adapting using reinforcement learning. The patient input device may include a Bluetooth clicker. The immersive headset may include a smart phone.

[0007] According to various embodiments, a method of assessing a visual field of a patient using an immersive headset, a patient input device, and an electronic processor communicatively coupled to the immersive headset and to the patient input device is presented. The method includes: causing, by the electronic processor, the immersive headset to display a first sequence of stimuli to a first eye of the patient, where respective locations of individual stimuli from the first sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the first eye of the patient; receiving, from the patient input device, responses indicative of whether the patient perceived individual of the first sequence of stimuli; adapting, by the electronic processor, the first sequence of stimuli based at least onthe responses; and reporting, by the electronic processor, a patient visual deficit pattern based on the causing and the receiving.

[0008] Various optional features of the above method embodiments include the following. The method may further include: providing the patient visual deficit pattern to a machine learning system, where the machine learning system is trained with training data, where the training data includes training visual deficit patterns and corresponding training diagnoses; obtaining, from the machine learning system, an indication of a patient diagnosis; and outputting the patient diagnosis. The indication of the patient diagnosis may include an indication of stroke. The method may include providing emergency intervention to the patient, where the emergency intervention includes a clot reducing drug. The method may include: selecting a second sequence of stimuli based at least in part on the responses indicative of whether the patient perceived individual of the first sequence of stimuli; causing the immersive headset to display the second sequence of stimuli to a second eye of the patient, where respective locations of individual stimuli from the second sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the second eye of the patient; and receiving, from the patient input device, responses indicative of whether the patient perceived individual of the second sequence of stimuli; where the patient visual deficit pattern is further based on the responses indicative of whether the patient perceived individual of the second sequence of stimuli. The adapting may include adapting individual intensities of at least some of the first sequence of stimuli. The adapting may include adapting respective locations of at least some of the first sequence of stimuli. The adapting may include adapting using reinforcement learning. The patient input device may include a Bluetooth clicker. The immersive headset may include a smart phone.

[0009] Combinations, (including multiple dependent combinations) of the above-described elements and those within the specification have been contemplated by the inventors and may be made, except where otherwise indicated or where contradictory.Brief Description of the Drawings

[0010] Various features of the examples can be more fully appreciated, as the same become better understood with reference to the following detailed description of the examples when considered in connection with the accompanying figures, in which:

[0011] Fig. 1 depicts a system for assessing a visual field of a patient using an immersive headset, according to various embodiments;

[0012] Fig. 2 is a diagram of stimuli loci, depicting locations where stimuli may be presented according to various embodiments; and

[0013] Fig. 3 is a flow diagram for a method of assessing a visual field of a patient using an immersive headset, a patient input device, and an electronic processor communicatively coupled to the immersive headset and to the patient input device, according to various embodiments.Description of the Examples

[0014] Reference will now be made in detail to example implementations, illustrated in the accompanying drawings. Wherever convenient, the same reference numbers will be used throughout the drawings to refer to the same or like parts. In the following description, reference is made to the accompanying drawings that form a part thereof, and in which is shown by way of illustration specific exemplary examples in which the invention may be practiced. These examples are described in sufficientdetail to enable those skilled in the art to practice the invention and it is to be understood that other examples may be utilized and that changes may be made without departing from the scope of the invention. The following description is, therefore, merely exemplary.

[0015] Some embodiments assess a patient’s visual field in a short time (e.g., 2-7 minutes) using an inexpensive immersive headset, such as augmented or virtual reality headset (e.g., smartphone-based and / or tethered headset). Some embodiments examine each eye’s visual field by showing stimulus points of varying brightness in different areas of the visual field through the immersive headset. Some embodiments utilize a machine learning algorithm to diagnose any of a variety of conditions based in the visual field assessment. Thus, some embodiments utilize inexpensive readily-available immersive headsets, together with computing technology, to both identify visual field defects and provide a suggested diagnosis using machine learning.

[0016] Some embodiments employ an algorithm that chooses the location, intensity (brightness), of each stimulus based on one or more previous responses. The algorithm may deploy a one or both of rule-based and / or reinforcement learning technique. For example, a rule-based approach may include displaying stimuli sequentially in each of the four quadrants of the patient’s field of view. The stimuli may be presented at locations specified by a grid of equidistantly spaced loci that lie in each of the four quadrants of patient’s field of vision for each eye. As another example, a reinforcement learning approach may select a location for a next stimulus of a sequence of stimuli based on one or more previous stimuli, such that the selected location efficiently (e.g., optimally) determines whether the patient has a spatial field defect and / or a particular diagnosis. Thus, if the patient fails to see a visual stimuluson the screen within the immersive headset, some embodiments adapt to identify the extent of the visual deficit, e.g., by displaying the visual stimulus again with a higher level of brightness, for example, in the region(s) where the patient failed to see a previous stimulus. Some embodiments report any detected visual field defects by way of a diagram that highlights areas of reduced or absent perception.

[0017] Some embodiments use a machine learning system that has been trained with training data that associates such diagrams with various diagnoses. Accordingly, some embodiments provide an indication of a suggested diagnosis based on detected visual field deficits.

[0018] These and other features and advantages are presented herein in reference to the accompanying figures.

[0019] Fig. 1 depicts a system 100 for assessing a visual field of a patient using an immersive headset 102, according to various embodiments. The system 100 includes an immersive headset 100, a patient input device 104, and a computer 110. The system 100 may test a patient for a visual field deficit and output one or both of a map representative of any detected visual field deficit and / or a diagnosis corresponding to a detected visual field defect. An example of a stimulus map, on which such a patient visual field deficit map may be based, is presented below at Fig. 2.

[0020] The immersive headset 102 may be implemented using any of a variety of hardware. According to some embodiments, the immersive headset 102 may be a virtual reality headset, which presents a computer display to the wearer stereoscopically. According to some embodiments, the immersive headset 102 may be an augmented reality headset, which presents a computer display to the wearer stereoscopically overlayed on to a view of the real world. An example such product isthe Microsoft HoloLens 2 Augmented Reality (AR) goggles. According to some embodiments, the immersive headset 102 may include a frame into which a standard smartphone is inserted, so that the display of the smart phone provides the images, which are conveyed to the user through optics within the headset (e.g., a virtual reality headset). More particularly, according to such embodiments, the smart phone may provide two images simultaneously, which the optics within the headset convey to the patient so as to appear as a single stereoscopic image. In general, the immersive headset may be communicatively coupled to the computer 110 by way of a cable or wirelessly, e.g., via Bluetooth.

[0021] Some embodiments use eye tracking technology, which may be included in the headset device 102, to ensure the eye location and data quality, and to produce reliability metrics such as fixation loss, false positive, and false negative rates.

[0022] The patient input device 104 may be a wired or wireless (e.g., Bluetooth) device the accepts input, such as a button depression, from the patient and conveys the input to the computer 110. According to some embodiments, the patient input device 104 may be a low-cost Bluetooth “clicker,” which is typically sold for use in triggering cameras.

[0023] The computer 110 may include various modules, such as a stimuli presentation system 112 and a trained machine learning diagnosis system 114, described in detail presently.

[0024] The stimuli presentation system 112 may be one or both of rule-based and / or adaptive.

[0025] According to some embodiments, the rule-based portion of the stimulus presentation system 112 may present stimuli to the patient according to any of a variety of rules. An example rule is: present stimuli only at locations specified by agrid of loci, where the loci are equidistant from adjacent loci within a given field of view quadrant. Another example rule is: present a subsequent stimulus in a quadrant different from the previous stimulus. Another example rule is: increase stimulus intensity (brightness) at the same location along a predetermined ladder of intensities when the patient does not register perceiving the stimulus at the location, up to a predetermined maximal brightness. Another example rule is: present stimuli at randomly selected locations, consistent with the other rules (e.g., randomly selected within a particular quadrant that is different from a quadrant within which a previous stimulus was presented).

[0026] The adaptive portion of the stimulus presentation system 112 may present stimuli according to an adaptive learning approach. For example, if a patient does not perceive a particular stimulus, the adaptive learning approach may select a next stimulus location based on an efficient (e.g., maximal) chance of determining a visual deficit. The adaptive approach may include prioritizing the presentation of stimuli to a second eye at a location of a visual field deficit detected in a first eye.

[0027] The machine learning diagnosis system 114 may be trained with training data that associates visual field defects (e.g., maps representative thereof) with various diagnoses. A novel input of a visual field deficit detected in the patient may result in an output indicative of any of a variety of diseases. Non-limiting examples of diseases for which the machine learning system may be trained to detect include: stroke, idiopathic intracranial hypertension, glaucoma, etc. The machine learning diagnosis system may include a neural network, for example, such as a convolutional neural network or a transformer.

[0028] The machine learning diagnosis system 114 may interface with the adaptive portion of the stimulus presentation system 112 to optimize stimuluspresentation. For example, the stimulus presentation system 112 may present stimuli to a second eye based on visual field defects detected in a first eye. This allows for detecting homonymous visual defects, for example, which are indicative of diseases such as strokes.

[0029] According to some embodiments, an operator of the system 100 may select various parameters for a patient visual field deficit test. Such parameters include, by way of non-limiting example, visual field scope (e.g., 24° from central, 30° from central, or any quantity in between), number of stimuli presented (e.g., any number from 100 to 300), stimuli color, and / or shape of presented stimuli (e.g., circular, hexagonal, triangular, or more generally, any polygon).

[0030] Fig. 2 is a diagram 200 of stimuli loci (e.g., 202), depicting locations where stimuli may be presented, according to various embodiments. The diagram 200 corresponds to a field of view of a patient. Note that the loci (e.g., 202) are equidistantly spaced from adjacent loci within each of the four quadrants. That is, in a quadrant, the distance between a given locus and an adjacent (nearest) locus is the same for each locus adjacent (nearest) to the given locus.

[0031] According to some embodiments, a visual field deficit report may be generated based on the diagram 200 of Fig. 2. For example, the locations on the diagram may be populated with various shades of grey, from black to white, representative of the least intensity (brightness) stimuli at the respective locations that the patient perceived. Such a visual field deficit report may be presented to an operator of an embodiment, e.g., an operator of the system 100, on a monitor of the computer 110.

[0032] Fig. 3 is a flow diagram for a method 300 of assessing a visual field of a patient using an immersive headset, a patient input device, and an electronicprocessor communicatively coupled to the immersive headset and to the patient input device, according to various embodiments. The method may be practiced using a system such as the system 100, as shown and described in reference to Fig. 1 , where the immersive headset may be implemented as the immersive headset 102, the patient input device may be implemented as the patient input device 104, and the electronic processor may be implemented by way of the computer 110.

[0033] At 302, the method 300 includes causing, by the electronic processor, the immersive headset to display a first sequence of stimuli to a first eye of the patient. The first sequence of stimuli may be presented, for example, at locations as shown and described herein in reference to Fig 2. The stimuli may be presented in sequence, e.g., as shown and described herein in reference to Figs. 1 and / or 2, e.g., according to one or both of rule-based and / or reinforcement learning technique. By way of nonlimiting example, respective locations of individual stimuli from the first sequence of stimuli may be selected from among locations that are equidistantly spaced within quadrants of a field of view of the first eye of the patient, as shown and described in reference to the diagram 200 of Fig. 2.

[0034] At 304, the method 300 includes receiving, from the patient input device, responses indicative of whether the patient perceived individual of the first sequence of stimuli. The responses may be in the form of button activations by the patient on the patient input device, for example. The responses may be received from the patient input device by a computer, such as the computer 100 as shown and described herein in reference to Fig. 1 .

[0035] At 306, the method 300 includes adapting, by the electronic processor, the first sequence of stimuli based at least on the responses of 304. The adapting can include any, or any combination, of: adapting individual intensities of at least some ofthe first sequence of stimuli, adapting respective locations of at least some of the first sequence of stimuli, and / or adapting using reinforcement learning. The adaptation may be according to one or both of rule-based and / or reinforcement learning technique, as described herein in reference to Fig. 1 .

[0036] At 308, the method 300 includes reporting, by the electronic processor, a patient visual deficit pattern based on the causing and the receiving. By way of nonlimiting example, the reporting may be by way of displaying a visual field deficit report, which may be generated based on the diagram 200 of Fig. 2. The display may be on a monitor of the computer 100, for example.

[0037] At 310, the method 300 includes providing the patient visual deficit pattern to a machine learning system, such as the trained machine learning diagnosis system 112 as shown and described herein in reference to Fig. 1. The machine learning system may be trained to associate a patient visual deficit pattern with a diagnosis indication. The machine learning system may be trained by propagating training data through the machine learning system during a training phase, where the training data includes training visual deficit patterns labeled with corresponding training diagnoses. Once trained, the machine learning system may receive a patient visual deficit pattern and output an associated patient diagnosis indication, e.g., as described presently in reference to 312.

[0038] At 312, the method 300 includes obtaining, from the machine learning system, an indication of a patient diagnosis. The indication of the patient diagnosis may include an indication of stroke, for example. The indication may be a code representative of a particular diagnosis in the form of a word, a phrase, a numeral, a vector, or a data structure.

[0039] At 314, the method 300 includes outputting the patient diagnosis. The indication of the patient diagnosis may be output by, for example, displaying it on a monitor, such as a monitor of the computer 110 as shown and described herein in reference to Fig. 1 , and / or may be output in computer readable form to a medical records system, e.g., over a network connection.

[0040] At 316, the method 300 includes providing emergency intervention to the patient, wherein the emergency intervention comprises a clot reducing drug, such as, by way of non-limiting example, intravenous administration of tissue plasminogen activator (TPA), also known as alteplase.

[0041] Potential use cases for, and example advantages of, various embodiments include the following.

[0042] 1 . Use case: Acute stroke.

[0043] A. Advantage: Improved stroke diagnosis. Visual fields are typically not accurately assessed in the acute setting (such as an emergency room or urgent care facility) by clinicians because the finger confrontation test is only 35% sensitive. Additionally, many patients are unaware of their visual field deficits, making misdiagnosis even more likely. A system, such as the system 100, which provides a portable device that can reliably assess the visual fields in a timely fashion can result in faster and more accurate diagnosis of stroke.

[0044] B. Advantage: Better treatment with clot buster medications in the acute setting. With faster stroke diagnosis, some embodiments provide the opportunity to treat the patients with visual field loss due to stroke with clot buster medications (thrombolytics) within the critical 4.5-hour window.

[0045] C. Advantage: Better connection of the patients with visual field loss to appropriate resources and better patient safety. Patients with stroke whowould have not been diagnosed with visual field loss otherwise may be connected to appropriate resources (e.g., low vision clinic, driving evaluation and safety) for better patient safety.

[0046] D. Advantage: Assessment of the changes in visual fields and neurologic outcomes. With the ability to assess patient visual fields acutely, some embodiments open the door for reliable follow up of the visual field deficits.

[0047] E. Advantage: Paving the way for future therapeutic trials.Trials of the medications or mechanical thrombectomy for strokes affecting visual fields are lacking, mainly because the accurate acute assessment of visual fields and follow up have not been feasible. Some embodiments can pave the way for such trials.

[0048] 2. Use case: Detection and / or diagnosis of autoimmune neurologic disorders affecting visual fields, such as Multiple Sclerosis (MS).

[0049] 3. Use case: Assessment of brain tumors affecting visual fields as a sensitive functional indicator of tumor growth, especially when tumor growth is small but in critical areas where MRI is not the best indicator, or when frequent MRIs are not feasible.

[0050] 4. Use case: Triage, assessment and follow up of ophthalmologic causes of visual field loss such as glaucoma, optic neuritis, or idiopathic intracranial hypertension, especially in low-resource settings.

[0051] 5. Use case: In home follow up of patients with known visual field deficits. Patients with known visual field deficits (due to any cause) can objectively follow changes in their vision and response to treatment at home instead of waiting months for their next follow up with their physician.

[0052] According to some embodiments, the method 300 further includes, prior to reporting the patient visual deficit pattern at 308, the following actions: selecting a second sequence of stimuli based at least in part on the responses indicative of whether the patient perceived individual of the first sequence of stimuli; causing the immersive headset to display the second sequence of stimuli to a second eye of the patient, wherein respective locations of individual stimuli from the second sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the second eye of the patient; and receiving, from the patient input device, responses indicative of whether the patient perceived individual of the second sequence of stimuli. According to such embodiments, the patient visual deficit pattern may be further based on the responses indicative of whether the patient perceived individual of the second sequence of stimuli.

[0053] Certain examples can be performed using a computer program or set of programs. The computer programs can exist in a variety of forms both active and inactive. For example, the computer programs can exist as software program(s) comprised of program instructions in source code, object code, executable code or other formats; firmware program(s), or hardware description language (HDL) files. Any of the above can be embodied on a transitory or non-transitory computer readable medium, which include storage devices and signals, in compressed or uncompressed form. Exemplary computer readable storage devices include conventional computer system RAM (random access memory), ROM (read-only memory), EPROM (erasable, programmable ROM), EEPROM (electrically erasable, programmable ROM), flash memory, and magnetic or optical disks or tapes.

[0054] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), andcomputer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented using computer readable program instructions that are executed by an electronic processor.

[0055] These computer readable program instructions may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the electronic processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram block or blocks.

[0056] In embodiments, the computer readable program instructions may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, statesetting data, configuration data for integrated circuitry, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++, or the like, and procedural programming languages, such as the C programming language or similar programming languages. The computer readable program instructions may executeentirely on a user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.

[0057] As used herein, the terms “A or B” and “A and / or B” are intended to encompass A, B, or {A and B}. Further, the terms “A, B, or C” and “A, B, and / or C” are intended to encompass single items, pairs of items, or all items, that is, all of: A, B, C, {A and B}, {A and C}, {B and C}, and {A and B and C}. The term “or” as used herein means “and / or.”

[0058] As used herein, language such as “at least one of X, Y, and Z,” “at least one of X, Y, or Z,” “at least one or more of X, Y, and Z,” “at least one or more of X, Y, or Z,” “at least one or more of X, Y, and / or Z,” or “at least one of X, Y, and / or Z,” is intended to be inclusive of both a single item (e.g., just X, or just Y, or just Z) and multiple items (e.g., {X and Y}, {X and Z}, {Y and Z}, or {X, Y, and Z}). The phrase “at least one of” and similar phrases are not intended to convey a requirement that each possible item must be present, although each possible item may be present.

[0059] The techniques presented and claimed herein are referenced and applied to material objects and concrete examples of a practical nature that demonstrably improve the present technical field and, as such, are not abstract, intangible or purely theoretical. Further, if any claims appended to the end of this specification contain one or more elements designated as “means for [perform]ing [a function]...” or “step for [performing [a function]...”, it is intended that such elements are to be interpreted under 35 U.S.C. § 112(f). However, for any claims containing elements designated in any other manner, it is intended that such elements are not to be interpreted under 35 U.S.C. § 112(f).

[0060] While the invention has been described with reference to the exemplary examples thereof, those skilled in the art will be able to make various modifications to the described examples without departing from the true spirit and scope. The terms and descriptions used herein are set forth by way of illustration only and are not meant as limitations. In particular, although the method has been described by examples, the steps of the method can be performed in a different order than illustrated or simultaneously. Those skilled in the art will recognize that these and other variations are possible within the spirit and scope as defined in the following claims and their equivalents.

Claims

What is claimed is:1 . A system for assessing a visual field of a patient, the system comprising: an immersive headset; a patient input device; and an electronic processor communicatively coupled to the immersive headset and to the patient input device, the electronic processor configured to perform actions comprising: causing the immersive headset to display a first sequence of stimuli to a first eye of the patient, wherein respective locations of individual stimuli from the first sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the first eye of the patient; receiving, from the patient input device, responses indicative of whether the patient perceived individual of the first sequence of stimuli; adapting the first sequence of stimuli based at least on the responses; and reporting a patient visual deficit pattern based on the causing and the receiving.

2. The system of claim 1 , wherein the actions further comprise: providing the patient visual deficit pattern to a machine learning system, wherein the machine learning system is trained with training data, wherein thetraining data comprises training visual deficit patterns and corresponding training diagnoses; obtaining, from the machine learning system, an indication of a patient diagnosis; and outputting the patient diagnosis.

3. The system of claim 2, wherein the indication of the patient diagnosis comprises an indication of stroke.

4. The system of claim 3, wherein the indication of the patient diagnosis comprises an indication of at least one of: multiple sclerosis, glaucoma, or idiopathic intracranial hypertension.

5. The system of claim 1 , wherein the actions further comprise: selecting a second sequence of stimuli based at least in part on the responses indicative of whether the patient perceived individual of the first sequence of stimuli; causing the immersive headset to display the second sequence of stimuli to a second eye of the patient, wherein respective locations of individual stimuli from the second sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the second eye of the patient; and receiving, from the patient input device, responses indicative of whether the patient perceived individual of the second sequence of stimuli;wherein the patient visual deficit pattern is further based on the responses indicative of whether the patient perceived individual of the second sequence of stimuli.

6. The system of claim 1 , wherein the adapting comprises adapting individual intensities of at least some of the first sequence of stimuli.

7. The system of claim 1 , wherein the adapting comprises adapting respective locations of at least some of the first sequence of stimuli.

8. The system of claim 1 , wherein the adapting comprises adapting using reinforcement learning.

9. The system of claim 1 , wherein the patient input device comprises a Bluetooth clicker.

10. The system of claim 1 , wherein the immersive headset comprises a smart phone.

11. A method of assessing a visual field of a patient using an immersive headset, a patient input device, and an electronic processor communicatively coupled to the immersive headset and to the patient input device, the method comprising: causing, by the electronic processor, the immersive headset to display a first sequence of stimuli to a first eye of the patient, wherein respective locations ofindividual stimuli from the first sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the first eye of the patient; receiving, from the patient input device, responses indicative of whether the patient perceived individual of the first sequence of stimuli; adapting, by the electronic processor, the first sequence of stimuli based at least on the responses; and reporting, by the electronic processor, a patient visual deficit pattern based on the causing and the receiving.

12. The method of claim 11 , further comprising: providing the patient visual deficit pattern to a machine learning system, wherein the machine learning system is trained with training data, wherein the training data comprises training visual deficit patterns and corresponding training diagnoses; obtaining, from the machine learning system, an indication of a patient diagnosis; and outputting the patient diagnosis.

13. The method of claim 12, wherein the indication of the patient diagnosis comprises an indication of stroke.

14. The method of claim 13, further comprising providing emergency intervention to the patient, wherein the emergency intervention comprises a clot reducing drug.

15. The method of claim 11 , further comprising: selecting a second sequence of stimuli based at least in part on the responses indicative of whether the patient perceived individual of the first sequence of stimuli; causing the immersive headset to display the second sequence of stimuli to a second eye of the patient, wherein respective locations of individual stimuli from the second sequence of stimuli are selected from among locations that are equidistantly spaced within quadrants of a field of view of the second eye of the patient; and receiving, from the patient input device, responses indicative of whether the patient perceived individual of the second sequence of stimuli; wherein the patient visual deficit pattern is further based on the responses indicative of whether the patient perceived individual of the second sequence of stimuli.

16. The method of claim 11 , wherein the adapting comprises adapting individual intensities of at least some of the first sequence of stimuli.

17. The method of claim 11 , wherein the adapting comprises adapting respective locations of at least some of the first sequence of stimuli.

18. The method of claim 11 , wherein the adapting comprises adapting using reinforcement learning.

19. The method of claim 11 , wherein the patient input device comprises aBluetooth clicker.

20. The method of claim 11 , wherein the immersive headset comprises a smart phone.

Images