WO2019169166A1

WO2019169166A1 - Visual field progression

Info

Publication number: WO2019169166A1
Application number: PCT/US2019/020106
Authority: WO
Inventors: Mengyu WANG; Lucy Q. SHEN; Louis R. Pasquale; Tobias ELZE
Original assignee: Schepens Eye Research Institute Inc
Current assignee: Schepens Eye Research Institute Inc
Priority date: 2018-03-01
Filing date: 2019-02-28
Publication date: 2019-09-06
Anticipated expiration: 2020-09-01

Abstract

Methods, systems, and devices are provided for determining visual field progression of a patient. An exemplary method can include decomposing a present visual field and a plurality of past visual fields of the patient into a plurality of weighted visual field archetypes; determining whether each of the plurality of weighted visual field archetypes is increasing or decreasing in size relative to itself across the plurality of past visual fields and the present visual field; and determining if the patient is experiencing a loss of visual field based on the determination of whether each of the plurality of weighted visual field archetypes is increasing or decreasing.

Description

Visual Field Progression

RELATED APPLICATIONS

[0001] The present application claims priority to US Prov. Patent App. No. 62/637,181, entitled“Visual Field Progression,” and filed on March 1, 2018, which is incorporated herein by reference in its entirety.

FIELD

[0002] The present disclosure relates generally to visual field (VF) progression, and more particularly, to detecting and/or determining visual field progression based on special pattern analysis.

BACKGROUND

[0003] Generally, A visual field test is an eye examination on a patient that can detect various dysfunctions or issues in central and peripheral vision that may be caused by (and thus be a sign of) various medical conditions such as glaucoma, stroke, pituitary disease, etc. Visual field testing can be performed in a clinic on a machine called a perimeter by keeping a gaze of a patient fixed and presenting various objects at various places within the patient’s visual field. In particular, a Humphrey visual field analyzer (HFA) can be used, which is a machine used by clinicians to measure the visual field of a patient. For example, it is used by optometrists, orthoptists, and ophthalmologists. The HFA produces a standard analyzer printout that includes a variety of information about the eye being tested at that point in time. Clinicians then use this information to attempt to diagnose various medical conditions based on outputs from the machine, various expected patterns that may indicate one condition over another, etc.

[0004] However, this current approach has a variety of problems. For example, false positives and false negatives often occur during the test, thus providing inaccurate results when the clinician attempts to determine progression of and/or existence of various potential visual conditions or disease states. Furthermore, the analysis is subjective because each clinician examines the results and makes an individual, subjective determination based on the clinician’s experience level, training, background, etc. Thus, based on the clinician’s individual experience, skill, etc., determinations might be inconsistent and/or inaccurate.

[0005] Because of these and other reasons, the current approaches to determining and/or detecting visual field progression are not effective for many people.

SUMMARY

[0006] Methods, systems, and devices are provided herein for examining visual field progression, and more particularly, for detecting visual field progression based on special pattern analysis. For example in one exemplary embodiment, a method is provided for determining visual field progression of a patient including testing, on a visual device, a present visual field of the patient. The method also includes decomposing, by a processor, the present visual field and a plurality of past visual fields of the patient into a plurality of weighted visual field archetypes. The method further includes determining, by the processor, whether each of the plurality of weighted visual field archetypes is increasing or decreasing in size relative to itself across the plurality of past visual fields and the present visual field. The method also includes determining, by the processor, if the patient is experiencing a loss of visual field based on the determination of whether each of the plurality of weighted visual field archetypes is increasing or decreasing.

[0007] The method can have numerous variations. For example, the plurality of weighted visual field archetypes can include 16 weighted visual field archetypes. Determining whether each of the plurality of weighted visual field archetypes is increasing or decreasing can include using linear regression. Determining whether each of the plurality of weighted visual field archetypes is increasing or decreasing can include calculating a slope of each of the plurality of weighted visual field archetypes over time. The plurality of weighted visual field archetypes can also include one weighted visual field archetype configured to represent a normal vision field. Determining if the patient is experiencing the loss of visual field can include finding a decreasing slope of the one weighted visual field archetype configured to represent the normal vision field. In another example, the plurality of weighted visual field archetypes can include one or more weighted visual field archetypes configured to represent a loss of vision field. Determining if the patient is experiencing the loss of visual field can also include finding an increasing slope of at least one of the one or more weighted visual field archetypes configured to represent the loss of vision field. In another example, decomposing the present visual field and the plurality of past visual fields of the patient into the plurality of weighted visual field archetypes can include determining a percentage of each of the plurality of weighted visual field archetypes present in the present visual field and the plurality of past visual fields of the patient. The method can also include using unsupervised machine learning. The processor can be part of the visual device, and the processor can be included in a remote computing device. The visual device can be a Humphrey visual field analyzer. The method can also include testing, on the visual device, a plurality of visual fields of the patient over a period of time.

[0008] In another aspect, a visual device is provided for determining visual field progression of a patient that includes at least one input, at least one display, at least one sensor, at least one memory, and at least one processor. The visual device is configured to test a present visual field of the patient; to decompose, by the processor, the present visual field and a plurality of past visual fields of the patient into a plurality of weighted visual field archetypes; to determine, by the processor, whether each of the plurality of weighted visual field archetypes is increasing or decreasing in size relative to itself across the plurality of past visual fields and the present visual field; and to determine, by the processor, if the patient is experiencing a loss of visual field based on the determination of whether each of the plurality of weighted visual field archetypes is increasing or decreasing.

[0009] The device can have various embodiments. For example, the plurality of weighted visual field archetypes can include 16 weighted visual field archetypes. The visual device can also be further configured to use linear regression. In another example, the visual device can be further configured to calculate a slope of each of the plurality of weighted visual field archetypes over time. In still another example, the plurality of weighted visual field archetypes can include one weighted visual field archetype configured to represent a normal vision field. The plurality of weighted visual field archetypes can include one or more weighted visual field archetypes configured to represent a loss of vision field. The visual device can also be further configured to determine a percentage of each of the plurality of weighted visual field archetypes present in the present visual field and the plurality of past visual fields of the patient. In another example, the device can be further configured to use unsupervised machine learning. The visual device can be further configured to test a plurality of visual fields of the patient over a period of time.

BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The invention will be more fully understood from the following detailed description taken in conjunction with the accompanying drawings, in which:

[0011] FIG. 1 illustrates an embodiment of a visual field analyzer;

[0012] FIG. 2 illustrates an analyzer printout produced by the visual field analyzer of FIG. 1;

[0013] FIG. 3 illustrates an example diagrammatic view of a device architecture;

[0014] FIG. 4 illustrates one embodiment of a procedure for determining visual field progression;

[0015] FIG. 5 illustrates an embodiment for performing the procedure for determining visual field progression of FIG. 4;

[0016] FIG. 6 illustrates a possible data exchange step of the procedure for determining visual field progression of FIG. 4;

[0017] FIG. 7 illustrates an embodiment of a 24-2 VF plot; [0018] FIG. 8 illustrates total deviation from the 24-2 VF plot of FIG. 7;

[0019] FIG. 9 illustrates an example of 16 visual field archetypes;

[0020] FIG. 10 illustrates an example of visual field decomposition into weighted visual field archetypes;

[0021] FIG. 11 illustrates an exemplary patient’s visual field information determined through the process discussed herein;

[0022] FIG. 12 illustrates decomposed visual field test results performed on patients using the process provided herein; and

[0023] FIG. 13 illustrates additional decomposed visual field test results performed on the same patients as in FIG. 12.

[0024] The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

[0025] It should be understood that the above-referenced drawings are not necessarily to scale, presenting a somewhat simplified representation of various preferred features illustrative of the basic principles of the disclosure. The specific design features of the present disclosure, including, for example, specific dimensions, orientations, locations, and shapes, will be determined in part by the particular intended application and use environment.

DETAILED DESCRIPTION

[0026] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. As those skilled in the art would realize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present disclosure. Further, throughout the specification, like reference numerals refer to like elements. [0027] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a,”“an,” and“the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms“comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term“and/or” includes any and all combinations of one or more of the associated listed items. The term“coupled” denotes a physical relationship between two components whereby the components are either directly connected to one another or indirectly connected via one or more intermediary components.

[0028] It is understood that the term“patient” or other similar term as used herein is inclusive of any subject— human or animal— on which an ocular assessment could be performed. The term“user” as used herein is inclusive of any entity capable of interacting with or controlling a device. The“user” may also be the“patient,” or the“user” and“patient” may be separate entities, as described herein.

[0029] Additionally, it is understood that one or more of the below methods, or aspects thereof, may be executed by at least one processor. The processor may be implemented in various devices, as described herein. A memory configured to store program instructions may also be implemented in the device(s), in which case the processor is specifically programmed to execute the stored program instructions to perform one or more processes, which are described further below. Moreover, it is understood that the below methods may be executed by a specially designed device, a mobile device, a computing device, etc.

comprising the processor, in conjunction with one or more additional components, as described in detail below.

[0030] Furthermore, the methods, or aspects thereof, of the present disclosure may be embodied as non-transitory computer readable media on a computer readable medium containing executable program instructions executed by the processor. Examples of the computer readable mediums include, but are not limited to, ROM, RAM, compact disc (CD)- ROMs, magnetic tapes, floppy disks, flash drives, smart cards and optical data storage devices. The computer readable recording medium can also be distributed in network coupled computer systems so that the computer readable media is stored and executed in a distributed fashion, e.g., by a telematics server or a Controller Area Network (CAN).

[0031] Referring now to embodiments of the present disclosure, clinicians struggle with detecting the progression of and/or existence of various visual conditions or disease states in an eye over time. When measuring the visual field of a patient, the results of a test (for example performed by a visual field analyzer 2, such as a Humphrey visual field analyzer like the Humphrey HFA Il-i - Perimetry as illustrated in FIG. 1) are provided to identify normal vision or a type of vision defect, condition, disease state, etc. in an eye of a patient. The results provide information regarding various defects, for example various locations of any disease processes or lesion(s) throughout the visual pathway of a patient. These results then guide the clinician to diagnose any conditions affecting the patient’s vision. Because these results can change over time as conditions change, for example as an eye disease like glaucoma progressively gets worse in a patient, the results from the visual field test can be stored and used for monitoring the progression of vision loss and the patient’ s condition. In such a situation, however, a clinician still must perform a subjective, personal analysis of the test results over a period of time, such as over a period of months and/or years, which might be inaccurate or miss important considerations. For instance, a clinician may perform a visual field test on a patient using the visual field analyzer 2 over several years. Each result is generated on an analyzer printout 4 that provides a variety of standard information, as illustrated in FIG. 2. The information provided relates generally to reliability indices 10, numerical displays 20, grey scale 30, total deviation 40, probability display 50, pattern deviation 60, global indices 70, glaucoma hemifield test 80, and visual field index 90. A clinician examines the results, especially the pattern of vision loss provided on the pattern deviation 60 plot, in an attempt to diagnose the type of vision loss present, if any. This identification can then be used by the clinician along with other clinical findings in the diagnosis of certain conditions. The clinician looks at the pattern deviation 60 plot for typical patterns or known examples of visual field loss. Based on the types of vision loss subjectively identified by the clinician, the clinician then attempts to diagnose various associated conditions that commonly produce the identified patterns of visual field loss.

These results can be difficult to read, and the results must be read and analyzed over several years, requiring the clinician to compare subsequent results in an attempt to determine any meaningful pattern of change. This requirement results in subjective determinations that depend heavily on each clinician’ s own experience, training, and opinion rather than objective changes in the pattern over multiple tests. Given the difficulties involved, many approaches to detecting visual field progression only provide various global assessments of functional deterioration, noting general deterioration in an eye of a patient rather than specific assessments or patterns over time that could lead to more accurate diagnoses and/or directed treatment for the patient. Additionally, the clinician’s judgement of visual field progression in a patient relies heavily on examination of various visual field special patterns identified by the clinician when studying the results, making this type of judgement extremely difficult.

[0032] While a Humphrey visual field analyzer is discussed above, a variety of visual devices can be used herein. FIG. 3 illustrates an example diagrammatic view of an exemplary device architecture according to embodiments of the present disclosure. As shown in FIG. 3, a device 109 may contain multiple components, including, but not limited to, a processor (e.g., central processing unit (CPU) 110, a memory 120, a wired or wireless communication unit 130, one or more input units 140, and one or more output units 150. It should be noted that the architecture depicted in FIG. 3 is simplified and provided merely for demonstration purposes. The architecture of the device 109 can be modified in any suitable manner as would be understood by a person having ordinary skill in the art, in accordance with the present claims. The device architecture depicted in FIG. 3 should be treated as exemplary only and should not be treated as limiting the scope of the present disclosure. [0033] The processor 110 is capable of controlling operation of the device 109. More specifically, the processor 110 may be operable to control and interact with multiple components installed in the device 109, as shown in FIG. 3. For instance, the memory 120 can store program instructions that are executable by the processor 110 and data. The process described herein may be stored in the form of program instructions in the memory 120 for execution by the processor 110. The communication unit 130 can allow the device 109 to transmit data to and receive data from one or more external devices via a communication network. The input unit 140 can enable the device 109 to receive input of various types, such as audio/visual input, user input, data input, and the like. To this end, the input unit 140 may be composed of multiple input devices for accepting input of various types, including, for instance, one or more cameras 142 (i.e., an“image acquisition unit”), touch panel 144, microphone, sensors 146, one or more buttons or switches, and so forth. The input devices included in the input 140 may be manipulated by a user. Notably, the term“image acquisition unit,” as used herein, may refer to the camera 142, but is not limited thereto. The output unit 150 can display information on the display screen 152 for a user to view. The display screen 152 can also be configured to accept one or more inputs, such as a user tapping or pressing the screen 152, through a variety of mechanisms known in the art. The output unit 150 may further include a light source 154.

[0034] The device 109 can thus be programmed in a manner allowing it to perform the techniques for determining visual field progression described herein.

[0035] To this end, techniques are disclosed herein relating to visual field progression analysis, for example by automatically detecting and quantifying visual field progression with spatial pattern analysis for various eye diseases including but not limited glaucoma, age- related macular degeneration, cataract, etc.

[0036] The various approaches provided herein can provide both status outcome and spatial patterns of visual field progression to assist clinicians in assessing progression in patients as opposed to only providing global assessments of functional deterioration or requiring a clinician’s judgement of visual field progression to heavily rely on subjective examination of visual field spatial patterns. As illustrated in FIG. 4 and discussed in detail below, a clinician can test a patient’s visual field using a variety of testing means, such as by using a variety of visual devices such as automated standard peri merry like a Humphrey visual field analyzer.

If the visual field is reliable, the results can be decomposed by a processor, such as the processor in the device, into various visual field archetypes (AT), such as 16 weighted visual field archetypes. However, a variety of numbers of visual field archetypes can be used depending on the applicable eye condition(s) and scenario(s) of the patient(s), such as between 1 and 40, or such as 5, 10, 15, 20, 25, 30, etc. Results from multiple time periods for the same patient can then be analyzed, for example by a processor in the device or a separate computing device, to determine if there is visual field loss over time (such as comparing a first month to a second month or a first year to a second year) and, if so, if the loss matches one or more predetermined patterns representative of one or more disease conditions. Thus, the pattern over time and any change or shift in the pattern can be identified.

[0037] Thus in step 100, as illustrated in FIGS. 4 and 5, a clinician 102 can test a visual field of a patient 104 using a visual device 106, such as a Humphrey visual field analyzer. In step 200, it can be determined if the results of the visual field test of the patient 104 are reliable.

If not, the test can be repeated. The reliability of the test can be determined by the device 106, for example by identifying false positives and/or false negatives. If the test is reliable, analysis of the results can proceed. The information can either be kept on the device 106 and analyzed directly or can be transferred to another device 108 for analysis, such as a computing device, as illustrated in FIG. 6.

[0038] At step 300, the results of the test can be decomposed by processor(s) in one or both of the device(s) 106, 108. The results can take a variety of forms, such as various visual field plots like an illustrated 24-2 visual field plot 302 shown in FIG. 7 and similar to the analyzer printout 4 produced by a Humphrey visual field analyzer. However, a variety of other visual field plots can be used, and the present application is not limited thereto. However, if for example the visual field plot 302 is used, the total deviation from the 24-2 visual field plot can be used by processor(s) on the device(s) 106, 108 to analyze visual field progression of the patient, as illustrated in FIG. 8. The results of the test can be decomposed into one or more visual field archetypes, such as into 16 visual field archetypes illustrated in FIG. 9. As mentioned above, however, various different numbers of visual field archetypes can be used. The results can be decomposed into 16 visual field archetypes previously identified through a variety of techniques, such as by unsupervised machine learning. In FIG. 9, for example, a normal archetype is represented in AT1, and 15 visual field loss archetypes are represented in AT2-AT16. The results can also include various mean deviation or defect (MD) values and/or various pattern standard deviation (PSD) values. In some examples, MD can be a weighted mean value of all test points in a total deviation plot, and/or PSD can be a metric that indicates a difference in a sensitivity of adjacent tested points.

[0039] The 16 visual field archetypes illustrated in FIG. 9 were generated using visual field information from glaucoma patients. However, the same archetypes can be used for a variety of other conditions. Alternatively, new archetypes can be identified using visual field information from other conditions, such as stroke, pituitary disease, age-related macular degeneration, cataract, etc., by identifying a new set of archetypes to be used.

[0040] At step 300 the visual field of the patient from the current test is decomposed along with the visual field of the patient from a plurality of previous visual field tests. For example, a patient may participate in a visual field test once a year, and each year the results are saved and added to current and future analyses. While the exact time period may vary, the process discussed herein takes in and performs an analysis using each visual field from a series of at least two visual fields from one patient, for example patient 104, over a period of time, such as over a plurality of days, weeks, months, years, etc. For example, the process can be conducted over 2 years, 3 years, 4, years, 5 years, 6 years, 7 years, 8 years, 9 years, 10 years, etc. Thus at step 300, each visual field from a series of visual fields from the patient 104 are decomposed into the weighted combination of 16 visual field archetypes that have been previously identified by unsupervised machine learning. As shown in FIG. 10, visual field decomposition into weighted visual field archetypes can be illustrated, showing illustrative archetype coefficients, the visual field measurement, the computational decomposition of the analysis, and the total deviation. The illustrative archetype coefficient can represent, for example, the decomposition of the series of visual fields for the patient 104 into a single visual field measurement. The computational decomposition can represent, for example, a breakdown or analysis of what archetypes are present in the decomposition of the series of visual fields and approximate percentages of one or more archetypes.

[0041] As a non-limiting example, FIG. 10 illustrates a computational decomposition for the patient 104 of 43.7% AT1 (or the normal AT), 51.5% of AT3 (a loss AT), and 4.8% of AT4 (another loss AT). However, the exact values will vary depending on the patient and the condition. Thus, a detailed analysis of the visual field of the patient is possible using the process discussed herein.

[0042] At steps 400 and 500, the possible progression of a condition and/or loss of visual field can be determined. For example, the slope over time of the visual field archetypes can be calculated by processor(s) of the device(s) 106, 108, such as over days, weeks, months, or years. When using the 16 visual field archetypes discussed herein, the slope over time of the 16 archetype weights can be calculated. Whether the possible condition and/or loss of visual field of the patient 104 is progressing or not can be determined at step 500 by analyzing if the normal AT (represented by AT1) has substantially decreased over the series of visual fields (for example, such that AT slope > 0.01 / year; p value < 0.01) or if any of the 15 visual field loss ATs (represented by AT2-AT16 and representing loss of visual field associated with one or more visual conditions) have substantially increased (for example, such that AT slope < - 0.01 / year; p value < 0.01). While specific values are provided herein, these are illustrative and non- limiting. A variety of different values can be used depending on the condition(s) being tracked, such as by looking for a slope of -1.0, -0.1, -0.01, -0.001, 0, 0.001, 0.01, 0.1, 1.0, etc. and/or a p value of -1.0, -0.1, -0.01, -0.001, 0, 0.001, 0.01, 0.1, 1.0, etc. In other words, analysis can be performed by processor(s) of the device(s) 106, 108 to determine if the normal archetype has gotten worse or declined in prominence (by decreasing) or if any of the archetypes identifying visual field loss that can correspond to one or more visual conditions has improved in prominence (by increasing), either of which would indicate a worsening of the visual field of the patient 104. This determination can be made using linear regression. Thus at steps 400 and 500, the processor(s) can calculate the slopes b of the 16 visual field archetype weights, and if the normal AT slope bΐ decreases and/or if any of the loss AT slopes b2-16 increases, the patient 104 is progressed, representing a loss of visual field and/or worsening of the patient’s condition. If the normal AT slope bΐ does not decrease and/or if any of the loss AT slopes b2-16 do not increase, the patient 104 is not progressed, representing no change in the patient’s visual field and/or condition. If no visual condition or disease state has been previously identified for the patient 104, this lack of progression can indicate that no disease state is present.

[0043] As an example and as illustrated in FIG. 11, the patient 104 can have eight visual fields resulting from 7.2 years of follow-ups with the clinician 102. Again, however, a variety of numbers of visual fields can be used over a variety of time periods. The visual fields for each visit can be represented in VF1-VF8. As explained above, the slope over time of the 16 archetype weights discussed herein can be calculated, and a determination can be made regarding whether the patient is progressed or not progressed. As illustrated in FIG. 11 and as an example, the slope for AT3 (which is a loss VF) equals 0.066 / year, and the p < 0.006. Thus, the patient is progressed and appears to have loss of visual field associated with AT3. While a specific example is provided here focused on AT3, the same process of analysis can be applied to any AT values depending on the specific patient results and/or the specific condition being analyzed.

[0044] Thus through this process, unsupervised machine learning can be used to quantify each visual field into weighted sub-patterns, and linear regression can be used to detect whether and which sub-pattems of visual field progresses over the course of a period of time (for example, over several years). An unsupervised machine learning based progression detection algorithm is used that provides both progression global outcomes and a progression spatial pattern. Thus, the results over years can be combined through this process to show the pattern of development of loss of visual field and/or a condition. The ability to provide both progression global outcomes and a progression spatial pattern can lead to more accurate and correct diagnosis and treatment along with assisting clinicians in assessing progression of one or more visual conditions as compared to the approaches currently available.

[0045] TEST DATA:

[0046] The process discussed herein using an algorithm to detect visual field worsening to provide both status outcome and spatial patterns of visual field progression was tested. Eyes from multiple sites were selected with at least 5 reliable automated visual fields and at least 5 years follow-up using the Swedish Interactive Threshold Algorithm (SITA) Standard strategy and 24-2 pattern. The time between each visual field was restricted to be at least 6 months. Each visual field was decomposed into a weighed sum of 16 visual field archetypes, including 1 normal AT and 15 visual field loss ATs, as previously illustrated in FIG. 9. For each eye, linear regressions were applied from follow-up time to the 16 AT weights of the visual fields. If any of the weights substantially changes for the 15 visual field loss ATs (AT slope > 0.01 / year and p < 0.01) and/or the normal AT (AT slope < -0.01 / year and p <

0.01), the eye was determined to be worsening. Again, the specific values provided herein and the specific determination are for exemplary purpose only and are not limiting thereto. The algorithm and process discussed herein was compared to existing algorithms including MD slope, Advanced Glaucoma Intervention Study (AGIS) scoring, Collaborative Initial Glaucoma Treatment Study (CIGTS) scoring, and the permutation of pointwise linear regression (PoPLR). The concordance between those algorithms was evaluated by Kappa coefficient.

[0047] 12,217 eyes were selected for the illustrative analyses herein. The mean ± standard deviation of age, MD, and PSD at the first visual field measurement were 63.8 ± 12.7 years, - 4.1 ± 5.2 dB, and 3.9 ± 3.5 dB. The median of follow-up time and number of visual fields was 7.1 years and 6. The prevalence of visual field progression by AT slope, MD slope, AGIS scoring, CIGTS scoring, and PoPLR were 10.3%, 9.3%, 3.9%, 9.4% and 9.2%. The progression detection by AT slope was in fair agreement (Kappa 0.2 to 0.4) with MD slope (0.38), AGIS (0.23), CIGTS (0.25), and PoPLR (0.27). The overall Kappa coefficient between existing algorithms was 0.34. Among the progressed 1,262 eyes determined by AT analysis, 89.6%, 9.8%, and 0.6% of the eyes had 1, 2 and 3 ATs progressed, and the 3 most frequent progressed archetypes were AT8 (17.3%), AT6 (15.2%) and AT3 (8.3%), as illustrated in FIGS. 12 and 13. A specific analysis with age ranges, initial results, follow-up times, numbers of visual field measurements, ongoing results, etc. is provided above.

However, patients can be treated with a range of ages (e.g. 15 years old to 100 years old, 30 to 90, 50 to 85, etc.), initial results, follow-up times (e.g. 1 month to 30 years, 1 year to 20 years, 2 years to 10 years, etc.), numbers of visual field measurements (e.g. 2 to 20, 3 to 10, 4 to 8, etc.), ongoing results (e.g. number of progressed archetypes, such as 1, 2, 3, 4, 5, etc., the specific archetype that has progressed, such as AT1, AT2, AT3, AT4, AT5, AT6, AT7, AT8, AT9, AT10, etc., and even the archetypes used in the analysis, which can vary depending on the condition being analyzed, characteristics of the population being tested, etc.) and are not limited to the illustrative analysis above. The algorithm and process discussed herein based on AT analysis can thus provide information of spatial pattern of visual field progression in addition to status outcome. The spatial patterns of visual field progression can be used to assist clinicians to assess progression.

[0048] While there have been shown and described illustrative embodiments that provide for visual field testing in eyes, it is to be understood that various other adaptations and modifications may be made within the spirit and scope of the embodiments herein. For instance, while a visual device is frequently mentioned throughout the present disclosure, the techniques described herein may also be implemented on various computers or similar machines. Thus, the embodiments of the present disclosure may be modified in any suitable manner in accordance with the scope of the present claims. [0049] The foregoing description has been directed to embodiments of the present disclosure. It will be apparent, however, that other variations and modifications may be made to the described embodiments, with the attainment of some or all of their advantages. Accordingly, this description is to be taken only by way of example and not to otherwise limit the scope of the embodiments herein.

Claims

WHAT IS CLAIMED IS:

1. A method of determining visual field progression of a patient comprising:

testing, on a visual device, a present visual field of the patient;

decomposing, by a processor, the present visual field and a plurality of past visual fields of the patient into a plurality of weighted visual field archetypes;

determining, by the processor, whether each of the plurality of weighted visual field archetypes is increasing or decreasing in size relative to itself across the plurality of past visual fields and the present visual field; and

determining, by the processor, if the patient is experiencing a loss of visual field based on the determination of whether each of the plurality of weighted visual field archetypes is increasing or decreasing.

2. The method of claim 1, wherein the plurality of weighted visual field archetypes includes 16 weighted visual field archetypes.

3. The method of claim 1, wherein determining whether each of the plurality of weighted visual field archetypes is increasing or decreasing includes using linear regression.

4. The method of claim 1, wherein determining whether each of the plurality of weighted visual field archetypes is increasing or decreasing includes calculating a slope of each of the plurality of weighted visual field archetypes over time.

5. The method of claim 1, wherein the plurality of weighted visual field archetypes includes one weighted visual field archetype configured to represent a normal vision field.

6. The method of claim 5, wherein determining if the patient is experiencing the loss of visual field includes finding a decreasing slope of the one weighted visual field archetype configured to represent the normal vision field.

7. The method of claim 1, wherein the plurality of weighted visual field archetypes includes one or more weighted visual field archetypes configured to represent a loss of vision field.

8. The method of claim 7, wherein determining if the patient is experiencing the loss of visual field includes finding an increasing slope of at least one of the one or more weighted visual field archetypes configured to represent the loss of vision field.

9. The method of claim 1, wherein decomposing the present visual field and the plurality of past visual fields of the patient into the plurality of weighted visual field archetypes includes determining a percentage of each of the plurality of weighted visual field archetypes present in the present visual field and the plurality of past visual fields of the patient.

10. The method of claim 1, further comprising using unsupervised machine learning.

11. The method of claim 1, wherein the processor is part of the visual device.

12. The method of claim 1, wherein the processor is included in a remote computing device.

13. The method of claim 1, wherein the visual device is a Humphrey visual field analyzer.

14. The method of claim 1, further comprising testing, on the visual device, a plurality of visual fields of the patient over a period of time.

15. A visual device for determining visual field progression of a patient comprising: at least one input;

at least one display;

at least one sensor;

at least one memory; and

at least one processor,

wherein the visual device is configured: to test a present visual field of the patient,

to decompose, by the processor, the present visual field and a plurality of past visual fields of the patient into a plurality of weighted visual field archetypes,

to determine, by the processor, whether each of the plurality of weighted visual field archetypes is increasing or decreasing in size relative to itself across the plurality of past visual fields and the present visual field, and

to determine, by the processor, if the patient is experiencing a loss of visual field based on the determination of whether each of the plurality of weighted visual field archetypes is increasing or decreasing.

16. The device of claim 15, wherein the plurality of weighted visual field archetypes includes 16 weighted visual field archetypes.

17. The device of claim 15, wherein the visual device is further configured to use linear regression.

18. The device of claim 15, wherein the visual device is further configured to calculate a slope of each of the plurality of weighted visual field archetypes over time.

19. The device of claim 15, wherein the plurality of weighted visual field archetypes includes one weighted visual field archetype configured to represent a normal vision field.

20. The device of claim 15, wherein the plurality of weighted visual field archetypes includes one or more weighted visual field archetypes configured to represent a loss of vision field.

21. The device of claim 15, wherein the visual device is further configured to determine a percentage of each of the plurality of weighted visual field archetypes present in the present visual field and the plurality of past visual fields of the patient.

22. The device of claim 15, wherein the visual device is further configured to use unsupervised machine learning.

23. The device of claim 15, wherein the visual device is further configured to test a plurality of visual fields of the patient over a period of time.