Systems and methods for assessing pupillary response

Abstract

Exemplary systems provide a display and camera on the same side of the device. In some examples, instead of providing a flash of light as a stimulus, the system can utilize the user's eyelids to dark adapt the pupil and use ambient light and / or light from the display to mediate the stimulus. The use of a front-facing display and front-facing camera further allows the disclosed system to control ambient lighting conditions during image capture, ensuring that no additional pupil stimulation occurs while measuring the primary pupil response.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to and the benefit of U.S. Provisional Patent Application No. 62 / 892,977, filed August 28, 2019, entitled "SYSTEMS AND METHODS FOR EVALUATING PUPILLARY RESPONSES," which is incorporated herein by reference in its entirety.

[0002] The present disclosure relates to systems and methods for measuring and analyzing pupil responses and their characteristics and metrics. [Background technology]

[0003] Pupils constrict and dilate in response to a variety of external (e.g., light) and internal (e.g., cognitive / emotional) stimuli. Pupillary responses, such as the pupillary light reflex ("PLR"), are assessed for many aspects of physiological and behavioral health, and the traditional method of measurement uses a pupillometer. Pupillometers are expensive, costing as much as $4,500, are primarily used in medical settings, and must be used by trained clinicians. Another traditional measurement uses a penlight test, in which a clinician shines a penlight into the patient's eye and observes the pupil's response. Summary of the Invention [Problem to be solved by the invention]

[0004] While simple to perform, it suffers from significant qualitative drawbacks, including a lack of standardization, the need for deliberate training, inter-operator variability, and poor inter-observer reliability and reproducibility. Penlight testing is typically used in emergency first aid situations, where rapid, qualitatively crude assessment, ease, and convenience are prioritized over accuracy. Furthermore, even semi-automated conventional methods for measuring pupillary responses require novel or external physical hardware to ensure any or all of the following: (1) adequate ambient lighting conditions; (2) proper face / eye alignment guided by the front of the mobile device display; (3) sufficient stimulus for pupillary response; and / or (4) adequate processing power to perform external image processing / feature extraction.

[0005] In addition to the drawbacks of conventional pupillometry systems, these devices use visible light as a stimulus source followed by visible light as an illumination source for image capture, and in some instances, using the visible light spectrum to measure the pupil after the stimulus phase can result in unintended pupil responses, similar to the "observer effect" in physics, where simply observing a phenomenon necessarily alters that phenomenon, often as a result of the instrument somehow altering the state of the thing being measured. Furthermore, conventional systems must (1) provide sufficient light stimulus to achieve the high level of contrast necessary for pupil-iris segmentation and (2) ensure moderate to bright lighting conditions that illuminate the face for proper image capture.

[0006] Finally, these conventional methods typically only catch signs of disease development after the disease is acute or progressive, potentially past the most treatable stage of the disease. [Means for solving the problem]

[0007] Various examples of the present disclosure are directed to a system for assessing pupillary light reflex, including a system that requires a user to close and open their eyelids to deliver a light stimulus. The system includes a mobile device, a camera, a display, a processor, and a memory. The mobile device includes a front surface and a back surface, and the camera and display are located on the front surface of the mobile device. The memory includes multiple code sections executable by a processor or one or more processors or a server. The multiple code sections include a series of instructions. In some examples, the instructions provide for emitting at least one visible light stimulus via the display. Next, the instructions provide for receiving, from the camera, image data corresponding to at least one eye of the user. Next, the instructions provide for processing the image data to identify at least one pupil characteristic. Next, the instructions provide for determining a health condition based on the at least one pupil characteristic.

[0008] In some examples, the instructions further provide for outputting the health status to a display.

[0009] In some examples, processing the image data to identify the at least one pupil feature includes pre-processing the received image data.

[0010] In some examples, identifying the at least one pupil feature based on the received image data includes segmenting the received image data to determine a first data portion corresponding to a pupil of the eye and a second data portion corresponding to an iris of the eye.

[0011] In some examples, the at least one pupil characteristic includes at least one of pupil response latency, constriction latency, maximum constriction velocity, average constriction velocity, minimum pupil diameter, dilation velocity, 75% recovery time, average pupil diameter, maximum pupil diameter, constriction amplitude, constriction percentage, pupil escape, baseline pupil amplitude, post-illumination pupil response, and any combination thereof.

[0012] In some examples, determining the health state based on the at least one pupil characteristic further includes (1) determining a difference between each of the at least one pupil characteristic and a corresponding healthy pupil measurement, and (2) determining the health state based on the determined difference for each of the at least one pupil characteristic, e.g., the corresponding healthy pupil measurement obtained by the processor from an external measurement database.

[0013] In some examples, emitting at least one visible light stimulus by the display includes (1) receiving first image data of the eye when no light stimulus is provided by the display, (2) determining an amount of luminous flux to provide based on the first image data, (3) determining an area of ​​the display to output the determined amount of luminous flux to, and (4) outputting the determined amount of luminous flux to the determined area of ​​the display. In some examples, second image data of the eye is received after outputting the luminous flux. In some examples, the output luminous flux is adjusted based on the second image data.

[0014] In some examples, the instructions further provide for tagging a first pupillary response based on the received image data. Then, second image data is received. Then, the instructions provide for determining a change in lighting conditions based on the second image data. Then, the second pupillary response is tagged.

[0015] In some examples, the instructions provide for displaying an indication on a display that the user should close their eyes. This may include instructions to close the eyes for a predetermined period of time. In other examples, it may include instructions to wait for a tone or vibration to open the user's eye. The system can then receive image data from the camera corresponding to at least one of the user's eyes. In some examples, the system can process the image data to determine whether or when the user's eye is open (e.g., by identifying the pupil or iris in the image). The system can then determine the user's health status based on at least one pupil feature and display it on the display.

[0016] In some examples, the instructions to the user are a text-based display on the display accompanied by a message. In other examples, the system provides a voice command to the user to close their eyes. In other examples, the system provides a separate visual instruction to the user that is not a text-based message.

[0017] The present disclosure further provides an exemplary method for assessing pupillary light reflex. The method includes emitting at least one visible light stimulus via a display. Next, the method includes receiving image data corresponding to a user's eye from a camera. Next, the method includes processing the image data to identify at least one pupil feature. Next, the method includes determining a health condition based on the at least one pupil feature. Additional examples of this method are described above with respect to the exemplary system.

[0018] The present disclosure further provides a non-transitory machine-readable medium including machine-executable code. When executed by at least one machine, the machine-executable code causes the machine to emit at least one visible light stimulus via a display. The code then provides for receiving, from a camera, image data corresponding to a user's eye. The code then provides for processing the image data to identify at least one pupil characteristic. The code then provides for determining a health condition based on the at least one pupil characteristic. Additional examples of this code are provided above with respect to the exemplary system.

[0019] In another exemplary embodiment, the present disclosure provides another system for assessing pupillary light reflex. The system includes a hardware device, a camera, a display, a processor, and a memory. The hardware device includes a front surface and a back surface, and the camera and display are located on the front surface of the mobile device. The memory includes a plurality of code sections executable by the processor. The code sections include instructions for emitting at least one visual stimulus via the display. The instructions further provide for emitting at least one non-visible light via an infrared emitting device. The instructions then provide for receiving, from the camera or the infrared detector, image data corresponding to a user's eye. The instructions then provide for processing the image data to identify at least one pupil characteristic. The instructions then provide for determining a health condition based on the at least one pupil characteristic.

[0020] In some examples, the non-visible light has a wavelength between 700 nm and 1000 nm, hi some examples, the non-visible light includes far-infrared wavelengths.

[0021] In some examples, the camera is an infrared camera.

[0022] In some examples, identifying the at least one pupil feature based on the received image data includes (1) determining an image contrast of the received image data, (2) determining that the image contrast is below a threshold contrast level, and (3) outputting on the display a prompt to a user to provide second image data in a dimly lit area. For example, the at least one pupil feature is determined based on the second image data.

[0023] In some examples, the at least one pupil characteristic includes at least one of pupil response latency, constriction latency, maximum constriction velocity, average constriction velocity, minimum pupil diameter, dilation velocity, 75% recovery time, average pupil diameter, maximum pupil diameter, constriction amplitude, constriction percentage, pupil deviation, baseline pupil amplitude, post-illumination pupil response, and any combination thereof.

[0024] In some examples, identifying the at least one pupil feature based on the received image data further includes segmenting the received image data to determine a data portion corresponding to a pupil of the eye and a data portion corresponding to an iris of the eye.

[0025] In some examples, the hardware device is a headset.

[0026] In some examples, the hardware device is a smartphone.

[0027] The above summary is not intended to represent each embodiment or every aspect of the present disclosure. Rather, the foregoing summary merely provides examples of some of the novel aspects and features described herein. The above features and advantages, as well as other features and advantages of the present disclosure, will be readily apparent from the following detailed description of exemplary embodiments and modes for carrying out the invention when taken in conjunction with the accompanying drawings and appended claims. [Brief explanation of the drawings]

[0028] The accompanying drawings illustrate embodiments of the present invention and, together with the description, serve to explain and illustrate the principles of the invention. The drawings are intended to diagrammatically show major features of exemplary embodiments. The drawings are not intended to depict every feature of an actual embodiment or the relative dimensions of the depicted elements, and are not drawn to scale.

[0029] [Figure 1] 1 illustrates an example system 100 according to some implementations of the present disclosure. [Figure 2] 2 illustrates an example system 200 for measuring pupillary responses, according to some implementations of the present disclosure. [Figure 3] 3 illustrates an example methodology 300 for identifying and analyzing pupil features, according to some implementations of the present disclosure. [Figure 4A] 1 illustrates an example pupil response separated into subphases, according to some implementations of the present disclosure. [Figure 4B] 1 illustrates exemplary pupil responses compared between healthy and unhealthy subjects, according to some implementations of the present disclosure. [Figure 5] 10 shows average measured pupil responses according to some implementations of the present disclosure. [Figure 6A] 1 illustrates an exemplary pupil response to cognitive load, according to some implementations of the present disclosure. [Figure 6B] 1 illustrates an exemplary pupil response to cognitive load, according to some implementations of the present disclosure. [Figure 7] 1 illustrates exemplary pupil responses as a function of mild cognitive impairment, according to some implementations of the present disclosure. [Figure 8] 1 illustrates an exemplary pupil segmentation methodology in accordance with some implementations of the present disclosure. [Figure 9] 1 illustrates an exemplary red-eye reflex, according to some implementations of the present disclosure. [Figure 10] 1 illustrates an exemplary corneal light reflex, according to some implementations of the present disclosure. [Figure 11] 1 illustrates an exemplary pupil constriction, according to some implementations of the present disclosure. [Figure 12] 1 illustrates an example software application implementation that automatically detects proper lighting and spatial orientation, according to some implementations of the present disclosure. [Figure 13] 1 illustrates an exemplary eye boundary detection according to some implementations of the present disclosure. [Figure 14] 1 illustrates an example method for determining luminous flux, according to some implementations of the present disclosure. [Figure 15] 1 illustrates an exemplary methodology for identifying a second pupillary response, according to some implementations of the present disclosure. [Figure 16] 1 illustrates an exemplary methodology for measuring pupil response to non-visible light, according to some implementations of the present disclosure. [Figure 17] 1 illustrates an example methodology for determining appropriate image contrast, according to some implementations of the present disclosure. [Figure 18] 10 illustrates an example data comparison of pupil-iris segmentation between visible and non-visible light, according to some implementations of the present disclosure. [Figure 19] 1 illustrates an exemplary iris recognition according to some implementations of the present disclosure. [Figure 20] 10 illustrates exemplary normalized data when identifying the sclera, according to some implementations of the present disclosure. [Figure 21] 1 illustrates an exemplary methodology for measuring pupillary responses with eyelid-mediated stimulation, according to some implementations of the present disclosure. [Figure 22A] 10 shows PLR data illustrating the effects on specific metrics of left pupil movement after alcohol and coffee consumption, according to some implementations of the present disclosure. [Figure 22B] 10 shows PLR data illustrating the effects on specific metrics of right pupil movement after alcohol and coffee consumption, according to some implementations of the present disclosure. [Figure 23A] 10 shows PLR data illustrating the effects on specific metrics of left pupil movement after consumption of alcohol, antihistamines, opioid analgesics, and coffee, according to some implementations of the present disclosure. [Figure 23B] 1 shows PLR data illustrating the effects on specific metrics of right pupil movement following consumption of alcohol, antihistamines, opioid analgesics, and coffee, according to some implementations of the present disclosure. [Figure 24A] 10 shows PLR data illustrating the impact on specific metrics of left pupil movement after alcohol consumption and morning body stretching, according to some implementations of the present disclosure. [Figure 24B] 10 shows PLR data illustrating the impact on specific metrics of right pupil movement after alcohol consumption and morning body stretching, according to some implementations of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0030] The present invention is described with reference to the accompanying drawings, in which like reference numerals are used throughout to indicate similar or equivalent elements. The drawings are not drawn to scale and are provided solely to illustrate the present disclosure. Several aspects of the present disclosure are described below with reference to exemplary applications for illustration. It should be understood that numerous specific details, relationships, and methods are set forth to provide a thorough understanding of the present invention. However, one skilled in the relevant art will readily recognize that the present invention can be practiced without one or more of the specific details, or in other ways. In other instances, well-known structures or operations have not been shown in detail to avoid obscuring the invention. The present invention is not limited by the illustrated order of acts or events, as some acts may occur in different orders and / or concurrently with other acts or events. Moreover, not all illustrated acts or events are required to implement a methodology in accordance with the present invention.

[0031] overview The present disclosure is directed to systems and methods for measuring pupillary responses. For example, in some examples, instead of providing stimuli with flashes of light or displays, the system can utilize the user's eyelids to dark adapt the pupil and mediate the stimuli using ambient light (herein referred to as an "eyelid-mediated response" or "EMD"). Thus, when the user closes their eyelids, the pupil undergoes a process of dark adaptation, allowing the pupil to become accustomed to the darkness and effectively dilate. This serves as a baseline before a light stimulus is applied / allowed (e.g., the user opens their eyes)—in some examples, facilitating latency and other measurements and constriction without the need to separately apply a light-based stimulus (e.g., without the need to use a flash on the back of a mobile device), thus allowing the user to use a front-facing camera.

[0032] For example, in this example, the system may display instructions for the user to close their eyes for a predetermined amount of time or until they hear a tone or feel a vibration. This is highly advantageous because the inventors have shown that the contrast in light entering a user's eyes when their eyes are closed and when they are open (thus allowing all of the ambient light in the room to enter their eyes) is sufficient to elicit a pupillary reflex and detect a difference in pupillary reflex after a user has consumed alcohol or other drugs.

[0033] Another exemplary system provides a display and a camera on the same side of the device, where the display provides a visible light stimulus that stimulates the user's eyes and triggers a pupillary reflex. The camera simultaneously receives image data of the pupillary reflex. Thus, an exemplary device according to the present disclosure can provide a system that is more scalable (accessible, affordable, and convenient) and more accurate (objective and quantitative) than current systems and methods, and can be used by users with or without health professionals. For example, previous systems have attempted to measure pupillary light reflex using a rear-facing camera and flash on the back of a smartphone, but the system does not allow users to self-measure their own PLR, necessitating reliance on a second measurement operator and potential longitudinal measurement inconsistencies resulting from multiple measurement operators. However, previous systems have not attempted to use a forward-facing camera because the front of the mobile device does not include a flash and therefore could not generate a stimulus to initiate the pupillary light reflex.

[0034] Therefore, based on the methods and features described herein, it has been discovered that stimuli can be provided using a display on the front of a smartphone or similar device. This is highly advantageous because the use of a forward-facing camera and display allows users to perform pupillary light response measurements more accurately and frequently using their smartphone or other related device. This generally makes the disclosed system highly scalable, including being more affordable and easy to use. For example, because the display is also on the front of the device, users can accurately align their eyes without the assistance of another person. This allows users to perform measurements more frequently because they do not need a separate caregiver to perform the measurements. Thus, the system allows users to collect data more frequently and obtain time-series data regarding their health status (although a single measurement may not be sufficient to identify certain conditions requiring time-series data, such as establishing a baseline and deviations from the baseline). Furthermore, utilizing a display to provide stimuli allows the system to have more precise control and variability of the stimuli, given the range of intensities and colors that may be displayed. Finally, in some embodiments utilizing infrared detection, the system may be particularly advantageous because the infrared detection allows the eye to generate a sufficient pupillary response because the measurement light does not induce a secondary pupillary response, which is important because the maximum intensity of the display is lower than that of a back-flash, and therefore secondary responses may interfere with the ability to record an adequate pupillary light reflex. In some examples, the disclosed system includes a smartphone or other handheld computing device. Such a system allows for frequent and accurate data collection, which can provide important quantitative data regarding a user's health. In some examples, as further described herein, the present disclosure provides for the collection of a time series of health data that can be used to create baseline pupil metric measurements for a user.Thus, the present disclosure provides pre-diagnostic, pre-trauma, and / or pre-disease measurements that can be used to monitor disease and / or injury progression and / or establish an individualized time-series health baseline.

[0035] In some examples, the visual stimulus generates sufficient photon energy to elicit a full pupillary response. Exemplary methods further include collecting data before a light intensity threshold is reached and determining pupil metrics as a function of other factors affecting the pupillary response. The use of a forward-facing display and a forward-facing camera further allows the disclosed system to control ambient lighting conditions during image capture to ensure that a secondary, accidental pupillary response is not initiated when measuring a first, intentional pupillary response. In some examples, exemplary methods detect ambient light levels to account for the effect the ambient light level has on the detected pupillary metrics. In some examples, the data collected before the light intensity threshold is reached provides a baseline value for the user's pupillary metrics.

[0036] Some examples of the present disclosure further provide for using a visible stimulus to illuminate the face and then using an invisible light source for image capture. Using an invisible source can avoid unintentionally stimulating reflexes and falsifying data. Furthermore, performing assessments in dimly lit conditions can be beneficial in some instances, as a high level of contrast between the light stimulus intensity and the ambient lighting conditions is required to elicit the pupillary light reflex. However, in some instances, performing assessments in dimly lit areas presents challenges, as the darkness of the room can interfere with capturing high-quality eye images. For example, there is often minimal contrast between the pupil and the iris, especially in individuals with highly pigmented or darker irises. Distinguishing between these two features is important for properly segmenting features for extraction and metric calculation. An infrared camera or other infrared hardware can also provide high-resolution pupil images for effective feature segmentation.

[0037] System for measuring pupillary metrics - Patent application 1 provides an example system 100 according to some implementations of the present disclosure. In some examples, system 100 is a smartphone, a smartwatch, a tablet, a computing device, headgear, a headset, a virtual reality device, an augmented reality device, or any other device capable of receiving and interpreting physical signals. System 100 includes a housing 110, a display 112, a camera 114, a speaker 118, a vibration motor 120, and a sensor 116. FIG. 1 shows the front of system 100. The system may also include camera 114 on the back of housing 110 (not shown).

[0038] Housing 110 provides a case for display 112, camera 114, speaker 118, vibration motor 120, and sensor 116. Housing 110 further contains any computing components (not shown) of system 100, including, for example, a processor, memory, wireless communication elements, and other elements readily contemplated in the art. The computing components further include any software configured to complete any of the processes described further herein.

[0039] Display 112 may be, for example, the screen of a smartphone, a smartwatch, an optical headset, or any other device. In some examples, display 112 may be an LCD screen, an OLED screen, an LED screen, or any other type of electronic display known in the art that displays images, text, or other types of graphic displays. For example, the screen may provide a plurality of light-emitting diodes or other means for generating a plurality of pixels, each pixel displaying a light stimulus.

[0040] The display 112 is configured to emit visual light. In some examples, the display 112 emits light over a portion of the surface area of ​​the display 112, and in other examples, the display 112 emits light over all of the surface area of ​​the display 112. The light emitted by the display 112 can be controlled to automatically emit light and increase or decrease the visual stimulus. In some examples, the display 112 displays image data captured by the camera 114. The display 112 can also display text and messages to the user. In some examples, the display 112 can display a live feed of image data output from the camera 114.

[0041] The camera 114 or multiple cameras 114 receive image data of the field of view in front of the camera 114. In some examples, the camera 114 receives photographic and / or video data. In some examples, the camera 114 receives continuous photographic data (e.g., at intervals of seconds, milliseconds, or microseconds). In some examples, the camera 114 is a visual light camera. In some examples, the camera 114 is an infrared camera and includes an infrared emitter. In some examples, the camera 114 automatically initiates image data capture based on detection of a particular stimulus (e.g., a user's face, a user's eyes, a user's pupils, and / or a user's iris). In some examples, the camera 114 is multiple cameras.

[0042] The sensor 116 may include, for example, any of a light sensor, a proximity sensor, an ambient sensor, and / or an infrared sensor. In some examples, the sensor 116 is communicatively coupled to the camera 114 and configured to initiate and / or terminate image data captured by the camera 114. As shown, the sensor 116 is on the same side of the system 100 as the camera 114. In some examples, the sensor 116 is located proximate to the camera 114.

[0043] 2 illustrates an exemplary system 200 configured to receive image data of a user's face, according to some implementations of the present disclosure. The system 200 includes the system 100, the camera 114, a user's eyes 202, a user's head 204, and a camera field of view 206. The system 100 and the camera 114 may be as discussed above with respect to FIG. 1. FIG. 2 illustrates that the system 100 may be positioned such that the camera 114 faces the user 204. For example, the eyes 202 of the user 204 may be within the field of view of the camera 206. Various embodiments of the present disclosure may be performed when the user 204 positions the system 100 in front of their face.

[0044] Methodology for analyzing pupillary responses The pupillary light reflex (PLR), which describes the constriction and subsequent dilation of the pupil in response to light, can serve as an important metric of autonomic nervous system function. Measurement of the PLR ​​can be used as an indicator of abnormalities in various neural pathways in the nervous system (and potentially other systems), and subsequently for the detection of developing diseases. As described herein, "heath status" can include pupillary light reflex measurement itself.

[0045] For example, mental health disorders such as alcoholism, seasonal affective disorder, schizophrenia, and generalized anxiety disorder, Alzheimer's disease and Parkinson's disease, autism spectrum disorder, and diabetes-related glaucoma and autonomic neuropathy may cause abnormalities in PLR. The methodology described below describes one such measure of one component of PLR, performed using a smartphone or similar device. In some embodiments, the smartphone not only captures phenotypic data for PLR measurement but also processes the data locally and in real time. Similarly, other quantifiable features measured from the eye / face (e.g., sclera color and deposit density) may also be processed locally. Thus, user privacy may be better protected and measurement time may be reduced. This method and system may also allow for the calculation of dynamically changing pupil diameter. This method and system may generate a more robust baseline for detecting statistical deviations in real time. Such deviations may be a sign of abnormalities in the physiological system to which the measure is causally related.

[0046] The PLR ​​measures described herein can be combined temporally and spatially with other measures, including, but not limited to, the user's voluntary blink rate in response to the word "blink," projected onto a screen, read by the user, and neurally processed through the motor cortex to produce measurable blinks of one or both eyes (which can be a measure of physiological changes occurring in voluntary nervous system pathways), the sclera (the whites of the eyes changing color gradients from red to yellow), other eye features, and the iris and limbus (e.g., cholesterol deposits and cardiovascular risk), and several other measured features extracted from the face / eye. These features can be measured in close spatial and temporal proximity to the user, providing a more efficient user experience and establishing baselines quantitatively and sequentially (through time) on an individualized basis that is convenient, affordable, and accessible from the user's living environment (e.g., home or non-medical). Such data can generate insights into various physiological systems (e.g., neural, cardiac, etc.) on a large and statistically significant scale, prior to clinical practice, as described herein.

[0047] 3 illustrates an exemplary methodology 300 that may be implemented in accordance with various embodiments of the present disclosure. Methodology 300 may be implemented in systems 100 and 200, as discussed with respect to FIGS. 1 and 2. In some examples, methodology 300 is implemented in a dark room, a dimly lit room, a room with natural light, or any other setting. In some examples, methodology 300 is implemented repeatedly, including by a user at night or before bedtime, when external variables such as light are minimal and controllable.

[0048] Methodology 300 begins at 310 by providing a light stimulus, in some examples, by emitting a visible light stimulus via a display (e.g., display 112 or sensor 116 of FIG. 1 ) or by providing an indication to a display that the user should close their eyes for a predetermined period of time. For example, the light stimulus causes pupil constriction. In some examples, pupil constriction increases as the contrast between the visible light stimulus and the ambient light level increases. The amount of visible light stimulus provided may be determined by methodology 1400 of FIG. 4 , discussed further below.

[0049] In some examples of 310, a visible light stimulus is automatically emitted when a camera (e.g., camera 114 of system 100 of FIG. 1) detects that a user's face (e.g., user 204 of FIG. 2) is at an appropriate spatial distance. In other examples, a message may be displayed on the screen telling the user to close their eyes once a face is detected. In some examples, the display first emits a notification of the impending display light stimulus. For example, turning briefly to FIG. 12, the display may display real-time captured image data of the user's face to provide a visual indication that the user's features have been properly detected. In some examples, the display is display 112 of FIG. 1. For example, circle 1202 may be placed over the user's eyes or nose. Turning briefly to FIG. 13, the display shows exemplary bounding boxes for the user's eyes, mouth, and nose.

[0050] 3, in some examples, 310 provides for first detecting the pupil. If the pupil is not detected, the user is notified that the configuration does not meet the criteria of methodology 300.

[0051] Next, methodology 300 provides for receiving image data corresponding to the user's eye at 320. Exemplary image data includes video and / or photographic data. In some examples, the image data is collected over a period of time (e.g., collected by camera 114 of FIG. 1). In some examples, the video is recorded at a frame rate of between 30-60 frames per second or higher. In some examples of 320, a set of still images is generated by the camera. In some examples of 320, the image data is captured as a grayscale video / image set or converted to grayscale after receipt.

[0052] Some examples of 320 include specific visual stimuli such as red-eye reflex, pupil response, iris and sclera data, eye-tracking data, and skin data.

[0053] Next, the methodology 300 proceeds to process the image data to identify pupil features, at 330 .

[0054] In some examples of 330, the received image data is first preprocessed to filter the data. Exemplary types of data preprocessing are described further below. In a simple exemplary protocol for preprocessing the data, the image data of 320 is cropped and filtered to obtain an image region. For example, the image is filtered based on set thresholds for brightness, color, and saturation. The image data is then converted to grayscale to improve the contrast between the pupil and iris, and the pupil-iris boundary is demarcated. In some examples of 330, shape analysis is performed to filter the image data based on a preselected circularity threshold. For example, to perform the shape analysis, the pixel contours and convex shapes are scanned. In some examples of 330, a baseline image is compared to the received image data of 320 to aid in preprocessing.

[0055] In some examples, 330 further provides for determining the surface area of ​​the pupil and iris region as detected in the image data. For example, an algorithm in the image analysis software determines a parameter of pupil size over a series of recorded images by assessing the time elapsed between each image and determining the rate at which the pupil size changes over time.

[0056] In some examples, identifying information is optionally removed from the sensor data at 330. In other words, the most relevant key phenotypic features of interest can be extracted from the raw image data. Exemplary features include pupil velocity (e.g., magnitude and direction), sclera color, measures of tissue inflammation, and / or other features. These features can be expressed as scalar numbers after extracting relevant metrics from the underlying raw data. Images of identifiable users are not utilized.

[0057] In some examples, 330 provides for determining whether additional data is needed, for example, by displaying an alert identifying the type of measurement needed and user instructions for capturing the appropriate type of measurement on the display.

[0058] In some examples of 330, the features include (1) pupil response latency, which includes the time it takes the pupil to react to a light stimulus, measured, for example, in milliseconds; (2) maximum diameter, which is the largest pupil diameter observed; (3) maximum constriction velocity (MCV), which is the maximum velocity observed during the constriction period; (4) average constriction velocity (ACV), which is the average velocity observed over the entire constriction period; (5) minimum pupil diameter, which is the smallest diameter observed; (6) dilation velocity, which is the average velocity observed over the entire dilation period; (7) 75% recovery time, which is the time it takes for the pupil to reach 75% of its initial diameter value; (8) mean diameter, which is the average of all diameter measurements taken in the time series; (9) pupil deviation; (10) baseline pupil amplitude; (11) pupil response after illumination; (12) maximum pupil diameter; (13) other pupil response measurements known in the art; and (14) any combination thereof. In some examples of 330, similar metrics are determined for the iris.

[0059] For example, the contraction latency is the time it takes for the contraction to complete (t flash )-contraction(t initial For example, constriction velocity is a measure of how fast the pupil constricts in millimeters per second. For example, constriction amplitude is measured as (Diameter before exposure) max )-(Diameter after exposure min For example, contraction rate is measured as the contraction amplitude divided by the diameter max The dilation latency is measured by taking the dilation latency as a percentage of the pupil diameter in millimeters per second. For example, dilation velocity is a measure of the rate at which the pupil dilates in millimeters per second. Many of the above characteristics can be derived by assessing the pupil diameter in the first image, the pupil diameter in the second image, and the length of time between the two images, as readily contemplated by one skilled in the art. Furthermore, one skilled in the art will readily appreciate that dilation latency, dilation velocity, dilation amplitude, and dilation percentage can similarly be calculated based on the data provided at 320.

[0060] Additional features include, for example, spontaneous blink reflex rate in response to the word "blink" projected on a screen (which can be a measure of spontaneous nervous system pathways), sclera (white to yellowing of the eye) color features, iris and limbus features (cholesterol deposits and cardiovascular risk), and several other measured features extracted from the face / eyes.

[0061] Some examples of 330 provide for predicting or estimating pupil measurements based on observed trajectories of collected image data.

[0062] Next, methodology 300 provides, at 340, determining a health condition based on the pupil characteristics identified at 330. In some examples, the health condition is the pupil light reflex measurement itself or other clinically relevant pupil measure or characteristic. In some examples at 340, the characteristics determined at 330 are compared to corresponding values ​​of healthy individuals to identify abnormalities. In some examples, the characteristics are compared to the user's time-series data, and a variation in the currently measured value from an established time-series baseline (individual) may indicate a medical condition or disease performance measure. In some examples at 340, an individual user baseline is established over time-series use of system 200, and a notification is provided when the pupil characteristics identified at 330 deviate from the established individual baseline by 1.5 standard deviations or another predetermined threshold deviation. For example, the threshold deviation varies depending on the medical condition. In some examples, 340 relies on a universal or external database of healthy individuals until an individual user provides 20 separate PLR ​​measures according to methodology 300.

[0063] In some examples of methodology 300, the image data includes data for both of the user's eyes. At 330, the pupillary reflex of each eye is analyzed separately, but at 340, the two features are analyzed together to determine health status, as changes in pupillary light reflex between each eye may indicate a medical condition (e.g., stroke).

[0064] In some embodiments of methodology 300, an alert is provided based on the received data. For example, if a digital marker of disease is detected, a pre-disease detection alert is received by system 100 and presented, for example, on display 112. In some embodiments, an audio alert can supplement or replace the graphical alert. Thus, a user can become aware of an oncoming disease, disorder, or precursor to a disease and take further action. Other information as described above, such as a suggestion to contact a physician for a physical examination, can also be received and presented.

[0065] In some examples of the system 200 of FIG. 2 and the methodology 300 of FIG. 3, a smartphone is held in the hand indoors with controlled ambient light at a naturally controlled observation spatial distance from the user's face (e.g., within 6-24 or 6-12 inches horizontally from the user's face, within 6 inches vertically from eye level, and within 6 inches horizontally (from the user's right to left) from the user's nose, although other distances may be possible). In some embodiments, holding the smartphone in this position for a controlled period of time (e.g., at least 5 seconds) activates an app (via sensors and software) that records HD video of the subject's face (particularly the eye and pupil reflections) at 60+ or ​​120+ frames per second when triggered by a short, intense flash of light provided from the smartphone's touchscreen or other light source during recording, or by an indication that the user should close their eyes for a predetermined period of time. In some examples, the flash of light is focused and has a known intensity from both its origin, and the intensity of light reaching the pupil can also be estimated by the known inverse relationship between the light source and the square of the distance from the pupil. Thus, images of the user's face are captured before, during, and after a brief, intense flash of light. In some embodiments, recording begins before the flash or within at least 1 second and 5 seconds of the user being instructed to open their eyes, and continues after the flash or after the user opens their eyes. Notably, the intensity reaching the pupil can be estimated by the known inverse relationship with the square of the distance between the pupil and the light source.

[0066] Exemplary pupillary response curves FIG. 4A illustrates an exemplary pupil response curve and various features that can be identified at different points on the curve. For example, these features can be analyzed with respect to the methodology 300 discussed above. FIG. 4A illustrates that when a light stimulus is provided, a baseline pupil diameter is first detected, and then MCV, MCA, and pupil deviation are assessed. When the light stimulus is turned off, a post-illumination pupil response (PIPR) can be assessed.

[0067] 4B shows another exemplary PLR curve, including (1) latency, (2) contraction velocity, (3) contraction amplitude, (4) contraction fraction, and (5) diastolic velocity. The dashed line indicates an abnormal PLR curve, which has increased latency, slower velocity, and decreased amplitude compared to the normal PLR curve shown in the solid line.

[0068] Data preprocessing and processing In some examples of 330, the received image data is pre-processed. Exemplary pre-processing techniques are discussed herein.

[0069] The frames in the sequence are smoothed to remove noise from the system due to natural pupil fluctuations, iris color variations, and variations caused by the device itself. A Gaussian smoothing operator can be used to slightly blur the image and reduce noise. The 2D Gaussian equation has the form:

number

number

[0070] In some examples of this disclosure, the PLR ​​is represented as a smoothed Fourier transform. For example, when using a histogram representation of a smoothed grayscale frame, a threshold function binarizes the image. This threshold function can be determined by distinguishing between dark and light pixels on the histogram. Based on this, the image can be binarized to distinguish between the sclera and the pupil by labeling white areas of the image with 1 and black areas with 0. This effectively creates a black square with a white circle that clearly represents the pupil for analysis. The pupil is typically elliptical, but can be represented as a circle by averaging its axes. The diameter can be measured in pixels between the two white pixels furthest from each other. This pixel measurement can be converted to millimeters using a reference of known dimensions held near the eye. For example, the depth of a smartphone from a face can be determined using a dot projector on the smartphone.

[0071] The differential equation describing the pupillary light reflex in terms of pupil diameter luminous flux as a function of light can be written as follows:

number

number

[0072] D is measured as the pupil diameter (mm), and Φ(t-τ)r represents the intensity of light reaching the retina at time t. Therefore, using data from the video (e.g., the diameter of the white circle representing the pupil in each frame, the time between frames, and the conversion between pixels and millimeters), we can determine pupil velocity using the differential equation above. We can determine pupil velocity both in response to the flash (smaller diameter) and during recovery (larger diameter).

[0073] In some examples, preprocessing involves cropping the video to include each individual eye region. This can be done by applying a simple heuristic of the known structure of the human face. The video can then be submitted for processing, which can include, for example, decomposing the received visual stimulus into a series of images and processing them one by one. The images are manipulated to eliminate eyeglass aberrations, blinking, and small hand movements during image capture. Pupil boundary detection using the entropy of contour gradients can be used to extract the size of each pupil, creating a data series that can be visualized.

[0074] In some embodiments, an eye tracker can be used to capture frames of the eye with different levels of dilation. A user can manually tag the pupil diameter in each frame. The tagged data can be used to train a segmentation model using the tagged pupils. For example, U-Net or a similar service can be used to output a shape from which the diameter can be inferred. A pipeline can be implemented that processes frames of the recorded video and graphs pupil dilation over time.

[0075] In some data processing examples, hue, saturation, and brightness values ​​are used to filter received image data. For example, if a pixel's "V" value (representing brightness) exceeds 60, the pixel may be removed. In another example, pixels may be filtered based on LAB values, where "L" represents the pixel's brightness and "A" and "B" represent the opponent color values. Because the pupil is the darkest part of the eye, removing pixels with an "L" value greater than 50 leaves only pixels that are relatively dark and likely to contain the pupil.

[0076] Additional exemplary processing steps include: (1) duplicating the filtered image and discarding the removed portion to display only the region of interest (ROI); (2) converting the filtered ROI pixels to grayscale; (3) filtering the grayscale pixels based on luminance or intensity values, for example, by filtering pixels with an L value greater than 45; (4) scanning the remaining pixels for contours and convex shapes; (5) scanning the incremental gradient of the pixel grayscale values; (6) constructing shapes based on or defined by the contours; (7) filtering those shapes based on size and circularity; (8) determining the surface area of ​​the pupil and iris regions; and (9) determining the relative change of the two regions over time.

[0077] In some examples of filtering based on circularity, the device removes values ​​that are not at or near a circularity value of 1.0. For example, a circle has a circularity value at or near 1.0, while an elongated ellipse may have a circularity value of approximately 0.25.

[0078] Predicting health conditions based on pupil characteristics Various aspects of the methodology 300 340 of Figure 3 can be used to identify whether a user has various medical conditions, disease severities, or other health ailments. Figures 5-7 below show example data corresponding to example health conditions.

[0079] Figure 5 shows the mean measured pupil responses correlated with Alzheimer's disease. For example, Figure 5 shows that the latency, MCV, MCA, and amplitude are significantly different between the cognitively healthy and Alzheimer's disease patient groups.

[0080] 6A-6B show exemplary pupillary responses to cognitive load, according to some implementations of the present disclosure. Figures 6A-6B demonstrate the correlation between psychoperceptual pupillary responses and Alzheimer's disease. Cognitive load is measured by the ability to recall three, six, or nine digit numbers. Figures 6A-6B show that as cognitive load increased, the amnesic single-domain mild cognitive impairment (S-MCI) group exhibited significantly greater pupil dilation than the cognitively healthy control (CN) group. Furthermore, at a given cognitive load, the multi-domain mild cognitive impairment (M-MCI) group exhibited significantly less dilation than both the cognitively normal and S-MCI groups. This indicates a cognitive load that far exceeded the group's capabilities.

[0081] 7 shows exemplary pupillary responses as a function of mild cognitive impairment, according to some implementations of the present disclosure. For example, the data shows that pupil dilation increases with a load from 3 to 6 digits, and then decreases as capacity is reached at a load of 9 digits. Thus, the present disclosure contemplates that individuals with lower cognitive abilities will exhibit greater pupil dilation under lower loads and smaller pupil dilation under higher loads.

[0082] Pupil Segmentation The present disclosure provides a pupil segmentation method. Eye image data can be segmented into three main parts: pupil, iris, and sclera. An image segmentation algorithm can be used to provide the desired segmentation.

[0083] FIG. 8 illustrates an exemplary pupil segmentation process. First, a grayscale image of the eye is received. Then, a balanced histogram is created based on the gray levels of each of the pixels. For example, balanced histogram thresholding segmentation, K-means clustering, or edge detection and region filling can be used. The exemplary balanced histogram segmentation algorithm sets a threshold gray level of pixels to determine which correspond to the pupil. The pixel corresponding to the pupil will be the darkest pixel.

[0084] In one example, K-means clustering selects k (e.g., k is 4 in this example) data values ​​as initial cluster centers. The distance between each cluster center and each data value is determined. Each data value is assigned to the closest cluster. The means of all clusters are then updated, and the process is repeated until clustering is no longer possible. Each cluster is analyzed to determine the cluster containing the pupil pixels, obtaining the segmentation result. This method can be used to segment a region of interest from a background based on the four main parts of the eye, which have different colors: the black pupil, the white sclera, the colored iris, and the skin background.

[0085] The method shown in Figure 8 further provides edge detection and region filling to enhance the image and link the dominant pixels of the pupil. To obtain the final segmentation result, holes of a specific shape and size are filled.

[0086] After segmentation, the area of ​​the pupil is determined and measured in pixels, which is converted to a physical size (e.g., millimeters) based on the scale of the camera that collected the image data.

[0087] Red-eye reflex 9 illustrates exemplary red-eye reflex data collection according to some implementations of the present disclosure. For example, image data highlighting the red reflex of a user's retina is collected. The present disclosure then provides for determining whether the red reflex is dim (which may be a sign of strabismus or retinoblastoma), whether the reflex is yellow (which may be a sign of Coats' disease), and / or whether the reflex is white or includes eyeshine (which may be a sign of retinoblastoma, cataracts, retinal detachment, and / or eye infection). These methodologies can thus provide features used to determine health status, in accordance with 330 and 340 of methodology 300 of FIG. 3.

[0088] Corneal light reflex FIG. 10 illustrates exemplary corneal light reflex data collection according to some implementations of the present disclosure. For example, image data capturing the degree of strabismus (eye misalignment) is collected. The present disclosure then provides for determining whether the captured data includes any of the following: (A) a small dot of light in the center of the pupil; (B), (C), and (D) deviations in dot placement from the center of the pupil, indicating eye misalignment. These methodologies can thus provide features used to determine health status, in accordance with 330 and 340 of methodology 300 of FIG. 3 .

[0089] Pupil diameter measurement 11 shows exemplary pupil diameter measurements. For example, 1112 and 1122 show baseline pupil diameters for subjects 1110 and 1120, respectively. Subject 1110 is healthy, and subject 1120 has Alzheimer's disease. MCV and MCA can be calculated based on the methods discussed herein.

[0090] Judging the amount of visual stimulation Methodology 1400 of FIG. 14 provides an exemplary method for determining the amount of visual stimulation to provide on a display. For example, methodology 1400 is implemented as part of step 310 of methodology 300 of FIG. 3. In some examples, methodology 1400 is implemented in systems 100 and 200 of FIGS. 1 and 2, respectively. In some examples, the display stimulation is utilized in combination with an eyelid-mediated response by providing a light stimulation from the display before or when the user opens their eyes based on elapsed time or a determination that the user's eyes are open. Thus, the combination of pupil dark adaptation when the eyes are closed, eye opening, and light stimulation combine to provide a larger light stimulation that may be necessary in some embodiments to elicit a sufficient pupillary light reflex.

[0091] Methodology 1400 begins by receiving first image data at 1410 when no light stimulus is provided. For example, camera 114 of system 100 receives image data of a user without providing a light stimulus from display 112 or sensor 116.

[0092] Next, methodology 1400 provides for determining an amount of light flux to provide at 1420 based on the first image data received from 1410 .

[0093] In some examples, 1420 also determines the type of light output from the display. For example, the wavelength of the light (or color of light within the visible light spectrum) to be displayed is determined. Each user's eye has melanoptic receptors that are activated by different colors. Thus, 1420 provides for controlling the wavelength (or color) of light to activate specific melanoptic receptors and specific receptor pathways in the user's eye. In some examples, these pathways allow for the depiction of diseases mediated by specific receptor pathways. This may be based on a determination of ambient light. Thus, the system can modulate the output of the display as a stimulus based on the amount of ambient light and the wavelength of the ambient light.

[0094] Next, methodology 1400 provides for determining an area of ​​the display for outputting luminous flux, at 1430. In some examples, the entire display surface area is used. In other examples, only a portion of the display surface area is used.

[0095] In some examples of methodology 1400, the amount of luminous flux and the area of ​​the display for outputting the luminous flux (eg, 1420 and 1430) are determined simultaneously or in any order.

[0096] Next, the methodology 1400 provides, at 1440, outputting the determined amount of luminous flux to the determined area of ​​the display.

[0097] In some examples of methodology 1400, additional image data of the eye is received after the light beam is output. In some examples, the light beam is adjusted based on the received image data.

[0098] Identifying multiple pupil responses In some examples of the present disclosure, a method for identifying multiple pupillary responses is provided. For example, such a method identifies whether the quality of an image dataset is degraded by unintentional pupillary stimulation (e.g., during methodology 300 of FIG. 3). FIG. 15 shows an example methodology 1500 for identifying and tagging unintentional pupillary responses according to some implementations of the present disclosure. For example, methodology 1500 can be performed before, during, and / or after methodology 300 of FIG. 3.

[0099] 15 initially provides for tagging a first pupillary response based on the received image data at 1510. For example, the first pupillary response includes a change in any of the pupil characteristics as discussed herein.

[0100] Next, methodology 1500 provides, at 1520, receiving second image data subsequent to the first received image data.

[0101] Next, methodology 1500 provides for determining a change in lighting conditions, at 1530. For example, the change in lighting conditions may be determined based on a luminance difference between the image data received from 1510 and the second image data received from 1520.

[0102] Next, methodology 1500 provides for tagging the second pupillary response in the second image data at 1540. For example, if the second image data is a series of images, 1540 provides for identifying an image or images that occur simultaneously with or closely in time after the change in lighting conditions. In some examples, the second pupillary response is identified as any one of the pupil features discussed herein.

[0103] Infrared measurement implementation The present disclosure further provides for image capture using non-visible light stimuli and / or an infrared camera. For example, the sensor 116, infrared emitter, and / or display 112 of FIG. 1 can provide non-visible light emission. In some examples, the camera 114 is an infrared camera and includes one or more infrared emitters. FIG. 16 illustrates an exemplary methodology 1600 that can be implemented in the systems 100 and / or 200 of FIGS. 1 and 2, respectively. This can be useful for various embodiments disclosed herein, including providing eyelid-mediated responses in a dark room that also utilize screen-based visible light stimuli. Thus, in a dark or dimly lit room, a user can close their eyes to block out remaining light, allowing for even higher contrast based on screen-based stimuli in a dark room.

[0104] Methodology 1600 provides, at 1610, emitting a visible light stimulus by a display (e.g., display 112 or sensor 116 of FIG. 1). For example, the visible light stimulus has a wavelength greater than 1000 nm. The visible light stimulus is directed toward a user's face. The visible stimulus is configured to initiate a pupillary response in the user's eye.

[0105] Next, methodology 1600 provides, at 1620, emitting a non-visible light stimulus by a display (e.g., display 112 of FIG. 1 or sensor 116, e.g., an infrared emitter). The non-visible light stimulus is configured to illuminate the user's face sufficiently to cause a sufficiently high image contrast (high enough for pupil-iris segmentation). Thus, 1620 takes advantage of the high image contrast typically provided by infrared light. For example, the non-visible light stimulus provided at 1620 is a light stimulus having a wavelength between 600 nm and 1000 nm.

[0106] Because 1620 provides sufficient illumination to provide sufficiently high image contrast, methodology 1600 requires fewer visual stimuli in step 1610 than methodologies that rely solely on visual stimuli (including, for example, methodology 300 of FIG. 3). Thus, methodology 1600 can more accurately elicit a pupil response because the visual stimuli provided in 1610 do not need to illuminate the user's face.

[0107] Methodology 1600 further provides for receiving, at 1630, image data corresponding to the user's eye. In some examples, the received image data is a set of images or a video. In some examples, the set of images is collected at regular intervals (e.g., intervals measured in seconds, milliseconds, and / or microseconds) for a period of time (e.g., 1 minute, 2 minutes, 3 minutes, or more). In some examples, the image data received at 1630 is received from an infrared camera.

[0108] Methodology 1600 further provides for processing the image data to identify pupil features, at 1640. For example, the received image data is processed according to any of the methodologies discussed with respect to 330 of methodology 300 of FIG. 3. Methodology 1600 then provides for determining a health status based on the identified pupil features, at 1650. For example, the health status is determined according to any of the methodologies discussed with respect to 340 of methodology 300 of FIG. 3.

[0109] Thus, methodology 1600 avoids confounding pupil response results with additional unintended stimuli.

[0110] Identifying suitable lighting conditions Some examples of the present disclosure provide for automatically detecting whether lighting conditions are sufficient to provide image data of adequate quality for determining various pupil characteristics discussed herein. Figure 17 shows an example methodology 1700 for assessing lighting conditions according to some implementations of the present disclosure. Methodology 1700 can be performed by systems 100 and / or 200 of Figures 1 and 2, respectively. In some examples, methodology 1700 is performed before, after, and / or during methodology 300 and / or methodology 1600 of Figures 3 and 16, respectively.

[0111] Methodology 1700 provides for determining image contrast of the received image data, at 1710. For example, image contrast may be determined with respect to brightness, color, saturation, and / or any other visual image analysis means, as known in the art.

[0112] Next, methodology 1700 provides for determining whether the contrast of the image is below a threshold contrast level at 1720. For example, 1720 is provided for determining whether pupil-iris segmentation can be performed based on the provided image data. In some examples, 1720 provides for determining whether pupil-iris segmentation can be performed with a particular accuracy threshold and / or confidence measure.

[0113] Next, at 1730, methodology 1700 provides for outputting a prompt to the user to provide second image data in a dimmer or brighter location if the stimulus is ambient light mediated by the user's eyelids (e.g., the user closing / opening their eyes).

[0114] When used in combination with methodology 1600, methodology 1700 provides for ensuring that the user is in a location that is dimly lit enough to provide high contrast for pupil segmentation.

[0115] Experimental Data - Infrared FIG. 18 illustrates exemplary image data compared between a set of images captured with visible light (image sets 1810 and 1830) and a set of images captured with infrared light (image sets 1820 and 1840). Image sets 1820 and 1840 show a much clearer delineation between the subject's pupil and iris than image sets 1810 and 1830, which were captured with visible light. In particular, image set 1830 captures a dark iris, where the pupil and iris are similar in color and have low contrast, making pupil segmentation nearly impossible. Thus, FIG. 18 illustrates the utility of methodology 1600 of FIG. 16 for collecting image data with an invisible stimulus and methodology 1700 of FIG. 17 for ensuring sufficiently high pupil-iris image contrast.

[0116] Implementation of eyelid-mediated responses 21 is a flowchart providing a detailed example of how the disclosed systems and methods may be implemented while utilizing a user's eyelids to dark adapt the pupils and using ambient light to mediate the stimulus (herein an "eyelid-mediated response"). Thus, when a user closes their eyelids, the pupils undergo a process of dark adaptation, allowing them to become accustomed to the darkness and effectively dilate. This serves as a baseline before applying a light stimulus (e.g., the user opens their eyes), facilitating measurement of latency and maximum construction.

[0117] For example, in this example, the system may display instructions for the user to close their eyes for a predetermined amount of time or until they hear a tone or feel a vibration. This is highly advantageous because the contrast of light entering the user's eyes when their eyes are closed versus open (thus, in a dark or dimly lit room, where all the ambient light in the room is entering the user's eyes or a screen-based stimulus is permitted) may be enough to elicit the pupillary reflex.

[0118] For example, the typical maximum lux emitted by a display at a typical viewing distance (e.g., 200 lux) may not be sufficient to elicit a sufficient pupillary light reflex (e.g., 300 lux or more may be required). However, the contrast of light entering the eye in the open and closed states under normal lighting conditions is sufficient to elicit a pupillary light reflex. Otherwise, the ambient light may be too bright, making it difficult to ensure sufficient contrast between the ambient light and the light stimulus to generate a pupillary light reflex. Therefore, eyelid-mediated implementations can avoid the need for additional light stimuli (e.g., flashing lights or brightened displays). In another example, eyelid-mediated stimulation can allow the display to provide sufficient additional stimulation to elicit a response when baseline dilation begins from when the user closes their eyes for a sufficient period of time.

[0119] Thus, using this system, in some instances, light-based stimuli do not need to be provided by the device. Thus, the user can hold the phone with the display facing them (since flashing is not required). Furthermore, the display does not need to provide light stimuli to the user's eyes; in some instances, a rear-facing camera can be utilized to assess eyelid-mediated pupillary responses. Furthermore, utilizing eyelid-mediated responses may be more desirable than shining a light bright enough into the user's eyes to elicit a pupillary reflex, as this may be more comfortable for the user. In other instances, closing the user's eyes in combination with light stimuli from the display may be sufficient to elicit a pupillary light reflex.

[0120] This method also allows the user to easily perform the method in any well-lit or bright room where there is sufficient ambient light to elicit a reflex after opening the eyes from a closed, dark-adapted state. FIG. 21 provides an example of performing this method. In some examples, the system may initially provide a live feed of image data on the display 112 (e.g., using a circle or arrow displayed on the live image data for the user to line up their eyes) to allow the user to properly align their eyes in front of the camera 114, as described herein. In other examples, a rear-facing camera may be utilized, and feedback to the user may be purely audio or vibrational, indicating when to open and close their eyes, and whether the rear-facing camera and their eyes are properly aligned.

[0121] The system can then provide instructions 2110 that the user should close their eyes. This can include a text-based message displayed on the display 112. For example, the display 112 can display the text "Close your eyes for [3, 10, 15] seconds," or close your eyes until you hear a tone [or feel a vibration]. The system can then start a timer for 3 seconds (or 4, 10, 15, or any other suitable time sufficient to elicit the pupillary light reflex) and begin recording image data output from the camera 114 after the set time has elapsed. In other examples, the system can sound a tone or energize a vibration motor after the set time has elapsed, informing the user that they can open their eyes 2120. In these examples, the system begins recording image data at or just before the tone or vibration is initiated.

[0122] In some examples, the system may process the image data (e.g., using computer vision to identify the pupil, iris, or other features of the eye) until it determines that at least one of the user's eyes is open, and then detect or filter frames that determine that the user's eyes are closed. This may be important because it allows the system to identify the first frame in which the user's eyes are open (by starting camera 114 recording while the user's eyes are still closed), thus capturing all or most of the pupillary light reflex.

[0123] In some examples, this may include determining pupil diameter based on a partial image of the pupil before the user's eyes are fully open or when the user's eyes are not fully open. For example, the system may extrapolate or otherwise estimate the full pupil diameter from the partial diameter. For example, if the visible pupil circular angle is less than 360 degrees, known mathematical functions (e.g., trigonometry) may be used to estimate the full pupil diameter. This may include determining pupil diameter from a small portion of the pupil that is visible (e.g., a visible circular angle of 90 degrees). In some examples, the accuracy of the partial measurement pupil diameter estimation may be high enough to be used in health condition calculations, including, for example, quantitative measurements of the pupil light reflex.

[0124] Additionally, the system may also identify frames in which the user's eyes are properly focused on a particular point on the camera or screen, thus enabling accurate measurements of pupil diameter to be performed. The system may include instructions (e.g., arrows) on the display as to where the user should focus their gaze. In another example, the system may determine the direction of the user's gaze and approximate pupil diameter based on those measurements.

[0125] Additionally, the system may continue to monitor the frames to determine that enough frames have been captured with the user's eyes open for a sufficient period of time (e.g., the user quickly closes their eyes). If an insufficient number of usable frames have been captured to determine pupillary light reflex or other relevant pupil characteristics, the process may start over.

[0126] The system can then receive visual data corresponding to the eyes of the user 320, and the system can process the image data in the same manner as described herein with respect to Figure 3. This includes processing the image data to identify pupil features 330 and processing the pupil features to determine the health status of the user 340.

[0127] Example of experimental data: Use of eyelid-mediated smartphone applications The inventors tested an example eyelid-mediated smartphone application to determine whether this implementation is sufficient to induce PLR ​​and detect the use of specific drugs. Thus, data generated by measuring PLR across several key metrics using an eyelid-mediated response-based application after consumption of several key drugs demonstrates consistency with the expected physiological effects described herein when tested using an eyelid-mediated response-based application. Thus, the data demonstrate that the eyelid-mediated implementation can effectively assess pupillary light reflex consistent with established methods for assessing PLR and deliver sufficient stimulation to further detect the consumption of specific drugs by patients.

[0128] For example, Figure 22A shows PLR data showing the effects on specific metrics of left pupil movement after alcohol and coffee consumption using an eyelid-mediated application. For example, Figure 22A shows that coffee significantly increased velocity compared to baseline, and alcohol decreased velocity. Thus, FIG. 22A confirms that an eyelid-mediated response-based application on a smartphone or mobile device can be utilized to determine whether a patient has consumed alcohol; FIG. 22B shows PLR data illustrating the impact on specific metrics of right pupil movement after alcohol and coffee consumption using an eyelid-mediated application; FIG. 23A shows PLR data illustrating the impact on specific metrics of left pupil movement after alcohol, antihistamines, opioid analgesics, and coffee consumption using an eyelid-mediated application; FIG. 23B shows PLR data illustrating the impact on specific metrics of right pupil movement after alcohol, antihistamines, opioid analgesics, and coffee consumption using an eyelid-mediated application; FIG. 24A shows PLR data illustrating the impact on specific metrics of left pupil movement after alcohol consumption and morning body stretching using an eyelid-mediated application; and FIG. 24B shows PLR data illustrating the impact on specific metrics of right pupil movement after alcohol consumption and morning body stretching using an eyelid-mediated application.

[0129] Experimental Data: Reproducibility of PLR Data Using Eyelid-Mediated Applications Table 1 below shows the reproducibility of processed data between the right and left eyes using the eyelid mediation application after applying the smoothing technique. The high scores in Table 1 indicate that EMD mediation is highly accurate within a PLR session, as metrics are highly reproducible between eyes. [Table 1]

[0130] Table 2 below shows the standard deviations achieved over time using the eyelid-mediated application after applying the smoothing technique. High scores indicate stability and reproducibility of the metric over time. [Table 2]

[0131] Thus, Tables 1 and 2 demonstrate the reproducibility of PLR metrics between eyes and over time using eyelid-mediated applications, and the systems and methods disclosed herein can be reliably used to measure PLR ​​characteristics.

[0132] Additional Software Implementations Exemplary Software Applications The present disclosure contemplates an exemplary health application that renders a template with alignment marks for a user's key facial features on a client device display. The health application instructs the user to align key facial features with the alignment marks displayed on the smartphone screen. The user's facial features are selected and aligned to ensure triangulation in depth and angle, where these facial features remain fixed over time in three-dimensional space and cannot be changed voluntarily or involuntarily by the user. The client device can provide an indicator, such as a green light, when a measurement is about to be taken. The health application flashes a light on the client device and captures video of the user's eyes with one of its sensors, a high-resolution camera. Using the video, the health application determines pupil diameter reflex velocity, which is the rate at which the pupil diameter of the user's eyes constricts in response to light and then expands again to a normal baseline size. Thus, active phenotypic data of pupil velocity is captured. Pupil velocity can be used to determine whether a developing disease, disorder, or disease precursor for a specific neurological disorder is present. Furthermore, the use of the camera can capture other phenotypic data. For example, the color of the eye's sclera is visible. The color of the eye's sclera can be used to determine whether various developing diseases, disorders, or disease precursors are present in a user. Yellow eye sclera may indicate jaundice. Reddish eye sclera may indicate cardiovascular problems due to constriction of the eye's blood vessels. Similarly, redness of the sclera, considered in the context of frequency and time, may indicate substance abuse. Another phenotypic feature, a ring around the eye's pupil, may indicate cholesterol deposits, which are typically associated with cardiovascular problems. Changes in pigmentation or mole growth on a user's face may indicate a skin disorder, such as melanoma. Thus, a single active test can generate data as quantified measures of multiple phenotypic features associated with multiple diseases.

[0133] To measure PLR, the user is instructed to align their eyes with the camera, which provides the appropriate image size for further image processing and pupil measurement. A camera session is initiated, the user's face is detected, and images of the user's eyes are captured. The background color and phone brightness (or torch level adjustment, if using a front-facing camera) are adjusted to create different levels of brightness / darkness. Images can be processed in real time, including segmentation, obtaining pupil diameter, and tracking the measurement of pupil constriction rate over time. Finally, the user can be presented with measurement results, including reaction time for both eyes, constriction rate, and percentage of pupil closure.

[0134] Automatic Face Detection Automatic face detection is possible using the nose tip and two pupils. In some embodiments, the controlled spatial distance is achieved by the user aligning their face with three red triangular points on the viewfinder (two for the pupils and one for the nose tip). Through machine vision, the pupils are recognized as aligned with the red points, and the nose tip (based on the RGB color of the nasal skin) is aligned with the nose tip. An ambient light sensor is then used to check for any ambient light (noise) that may add a confounding variable to the measurement. If the alignment (depth / angle) and lighting are sufficient, the red point turns green, notifying the user that they are ready to take action within a certain time. Figure 12 illustrates this process.

[0135] A flash of light is provided and video is captured. Face detection can be performed using one or more frames of the video. Thus, after capturing the video, with the assistance of a machine vision-based algorithm, the smartphone automatically detects the pixel-based location of the nose tip, as well as the two pupils (which may be projected onto the screen), ensuring that the measurements are triangularly and spatially consistent. The specific shape and distance of these three reference points cannot be voluntarily or involuntarily changed over time by facial muscles, further ensuring control and consistency.

[0136] The face detection / machine vision portion of this method can be implemented using open source and / or proprietary software. As a result, faces and eyes can be detected (as shown in Figures 12-13). In some embodiments, the input video / video frames are grayscale. If a face is detected in the video, the system proceeds to detect eyes within the coordinates of the face. If no face is detected, the user is notified that the given video does not meet the criteria for valid detection.

[0137] A facial recognition algorithm can be used to guide the user in real time during the pre-capture phase. In some embodiments, this can be achieved by using OpenCV (an open-source computer vision library), ARKit (augmented reality kit), or other facial recognition mechanisms. Facial recognition can be used to identify eye locations on the image and prompt the user to manipulate the device to position the camera in the desired location. Once the camera is positioned, the image data capture phase can occur. Modern smartphones can be capable of emitting over 300 nits (1 candela / m²). Video footage can be as short as 10-20 seconds, which may be sufficient to obtain sufficient data for PLR analysis. The camera on a modern smartphone (e.g., camera 114 in FIG. 1) is used to capture video before, during, and after the screen flash.

[0138] In some embodiments, face capture combined with face and eye recognition may also be used in performing PLR measurements. Some face recognition frameworks, such as the Vision Framework, can detect and track human faces in real time by creating requests and interpreting the results of those requests. Such tools can be used to locate and identify facial features (such as the eyes and mouth) in an image. A facial landmark request first locates all faces in an input image and then analyzes each to detect facial features. In other embodiments, face tracking, for example, via an augmented reality session, may be used. One example of such a mechanism is ARKit. Using such a mechanism, a user's face may be detected with a front-facing camera system. The camera image may be rendered into view along with virtual content by configuring and running an augmented reality session. Such a mechanism can provide a coarse 3D mesh geometry that matches the size, shape, topology, and current facial expression and features of the user's face. One such mechanism can be used to capture and analyze the image, or multiple mechanisms can be combined. For example, one is used to capture the image and another is used to analyze the image.

[0139] Disclosed Computer and Hardware Implementations It should be understood at the outset that the disclosure herein can be implemented in any type of hardware and / or software, including pre-programmed general-purpose computing devices. For example, the system can be implemented using a server, a personal computer, a portable computer, a thin client, or any suitable single or multiple devices. The disclosure and / or its components can be a single device at a single location, or multiple devices at single or multiple locations connected together using any suitable communications protocol by any communications medium, such as electrical cable, fiber optic cable, or wirelessly.

[0140] It should also be noted that the present disclosure is illustrated and discussed herein as having multiple modules that perform specific functions. It should be understood that these modules are merely illustrated generally based on their functionality for clarity purposes and do not necessarily represent specific hardware or software. In this regard, these modules may be hardware and / or software implemented to substantially perform the specific functions discussed. Furthermore, modules may be combined together within the present disclosure or divided into additional modules based on desired specific functionality. Therefore, the present disclosure should not be construed as limiting the present invention, but should be understood merely to illustrate one example implementation.

[0141] A computing system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship. In some implementations, a server sends data (e.g., HTML pages) to client devices (e.g., for the purpose of displaying the data and receiving user input from a user interacting with the client device). Data generated at the client device (e.g., results of user interaction) may be received from the client device at the server.

[0142] Implementations of the subject matter described herein can be implemented in a computing system that includes back-end components, e.g., as a data server, or middleware components, e.g., as an application server, or front-end components, such as a client computer having a graphical user interface or web browser through which a user can interact with implementations of the subject matter described herein, or any combination of one or more such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communications network. Examples of communications networks include local area networks (“LANs”) and wide area networks (“WANs”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks).

[0143] Implementations of the subject matter and operations described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed herein and structural equivalents thereof, or in one or more combinations thereof. Implementations of the subject matter described herein can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on a computer storage medium for execution by or to control the operation of a data processing apparatus. Alternatively or additionally, the program instructions can be encoded in an artificially generated propagated signal, e.g., a mechanically generated electrical, optical, or electromagnetic signal generated to encode information for transmission to a suitable receiving apparatus for execution by the data processing apparatus. A computer storage medium can be, or be included in, a computer-readable storage device, a computer-readable storage substrate, a random or serial access memory array or device, or one or more combinations thereof. Furthermore, while a computer storage medium is not a propagated signal, a computer storage medium can be a source or destination of computer program instructions encoded in an artificially generated propagated signal. A computer storage medium may also be, or be included in, one or more separate physical components or media (e.g., multiple CDs, disks, or other storage devices).

[0144] The operations described herein may be implemented as operations performed by a "data processing apparatus" on data stored in one or more computer-readable storage devices or received from other sources.

[0145] The term "data processing apparatus" encompasses all types of apparatus, devices, and machines for processing data, including, for example, a programmable processor, a computer, a system on a chip, or a combination of the above. An apparatus may include special-purpose logic circuitry such as an FPGA (field-programmable gate array) or an ASIC (application-specific integrated circuit). In addition to hardware, an apparatus may also include code that creates an execution environment for a computer program, such as code comprising processor firmware, a protocol stack, a database management system, an operating system, a cross-platform runtime environment, a virtual machine, or one or more combinations thereof. The apparatus and execution environment may implement a variety of different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.

[0146] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and can be deployed in any form, such as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored as part of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple associated files (e.g., files storing one or more modules, subprograms, or portions of code). A computer program can be deployed to be executed on one computer, or on multiple computers located at one site, or distributed across multiple sites and interconnected by a communications network.

[0147] The processes and logic flows described herein may be performed by one or more programmable processors executing one or more computer programs to perform actions by manipulating input data and generating output. The processes and logic flows may also be performed by, and an apparatus may also be implemented as, special purpose logic circuitry, such as, for example, an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0148] Processors suitable for executing a computer program include, by way of example, both general-purpose and special-purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor receives instructions and data from a read-only memory or a random-access memory, or both. The essential elements of a computer are a processor for performing actions in accordance with the instructions and one or more memory devices for storing instructions and data. Typically, a computer includes or is operatively coupled to receive data from, transfer data to, or both of, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical, or optical disks. However, such devices are not required for a computer. Furthermore, a computer can be incorporated into another device, e.g., a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name just a few. Suitable devices for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, by way of example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic disks such as internal or removable hard disks, magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0149] conclusion The various methods and techniques described above provide several ways of implementing the present invention. Of course, it should be understood that not all described objectives or advantages can be achieved in accordance with any particular embodiment described herein. Thus, for example, those skilled in the art will recognize that a method can be practiced in a manner that achieves or optimizes one advantage or advantages taught herein without necessarily achieving other objectives or advantages taught or suggested herein. Various alternatives are described herein. It should be understood that some embodiments specifically include one, another, or several features, other embodiments specifically exclude one, another, or several features, and still other embodiments reduce a particular feature by including one, another, or several advantageous features.

[0150] Furthermore, those skilled in the art will recognize the applicability of various features from different embodiments. Similarly, the various elements, features, and steps discussed above, and other known equivalents to each such element, feature, or step, may be employed in various combinations by those skilled in the art to implement methods consistent with the principles described herein. Some of the various elements, functions, and steps may be specifically included or excluded in various embodiments.

[0151] While the present application has been disclosed in the context of particular embodiments and examples, those skilled in the art will recognize that the embodiments of the present application go beyond the specifically disclosed embodiments to other alternative embodiments and / or uses, and modifications and equivalents thereof.

[0152] In some embodiments, the terms "a," "an," and "the," and similar references when used in the context of describing particular embodiments of the application (particularly in the context of the claims below) can be interpreted to cover both the singular and the plural. The recitation of ranges of values ​​herein is merely intended to serve as a shorthand method for individually referring to each separate value falling within the range. Unless otherwise stated herein, each separate value is incorporated herein as if individually set forth herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or clearly contradicted by context. The use of any and all examples or exemplary language (e.g., "etc.") provided with respect to particular embodiments herein is intended merely to better illuminate the application and does not pose a limitation on the scope of the application as otherwise claimed. No language in the specification should be construed as indicating any non-claimed element essential to the practice of the application.

[0153] Certain embodiments of the present application are described herein. Variations of these embodiments will become apparent to those skilled in the art upon reading the foregoing description. It is contemplated that those skilled in the art can employ such variations as appropriate, and may practice the application otherwise than as specifically described herein. Accordingly, many embodiments of the present application include all modifications and equivalents of the subject matter recited in the claims appended hereto as permitted by applicable law. Moreover, any combination of the above-described elements in all possible variations thereof is encompassed by this application unless otherwise indicated herein or clearly contradicted by context.

[0154] Specific implementations of the subject matter have been described. Other implementations are within the scope of the following claims. In some cases, the actions recited in the claims may be performed in a different order to achieve desirable results. Also, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results.

[0155] All patents, patent applications, patent application publications, and other materials, such as articles, books, specifications, publications, documents, articles, and / or the like, referenced herein are hereby incorporated by reference for all purposes, except for any prosecution file history related thereto, which is either inconsistent with or contradictory to this document, or which may have a limiting effect on the broadest scope of any claims now or in the future related hereto. By way of example, in the event of a conflict or inconsistency between the explanations, definitions, and / or term usage associated with any of the incorporated materials and the explanations, definitions, and / or term usage associated herein, the explanations, definitions, and / or term usage in this document shall control.

[0156] Finally, it should be understood that the embodiments of the application disclosed herein are illustrative of the principles of the embodiments of the application. Other modifications that can be employed may be within the scope of the application. Thus, by way of example, and not of limitation, alternative configurations of the embodiments of the application may be utilized in accordance with the teachings herein. Accordingly, the embodiments of the application are not limited to that precisely as shown and described.

Claims

1. 1. A system for assessing pupillary light reflex, comprising: Mobile devices and a camera located on one side of the device; a display located on the one side of the device; and a processor; a memory having stored therein a plurality of code sections executable by said processor; Equipped with the plurality of code sections stored in the memory displaying a live feed of image data output from the camera on the display; displaying a pair of circles or other markings on the display and displaying instructions that the user should make eye contact with the pair of circles or other markings; displaying instructions on the display requesting the user to close their eyes for at least a predetermined period of time and then open their eyes; receiving image data from the camera corresponding to at least one eye of the user with the user's eye open; processing the image data to identify at least one pupil feature; determining a health status based on the at least one pupil characteristic; Including instructions for A system characterized by:

2. the instructions further provide for outputting the health status on the display.

2. The system of claim 1.

3. The health condition comprises pupillary light reflex, coffee consumption, alcoholism level, opioid addiction level, antihistamine consumption level, or coffee consumption level.

2. The system of claim 1.

4. displaying instructions on the display requesting the user to close their eyes includes displaying a text-based message requesting the user to close their eyes for at least the predetermined period of time.

2. The system of claim 1.

5. displaying instructions on the display requesting the user to close their eyes includes displaying a text-based message requesting the user to close their eyes until the predetermined time has elapsed and an audible instruction to open their eyes is heard.

2. The system of claim 1.

6. the instructions further provide for outputting the audible indication through a speaker.

6. The system of claim 5.

7. the image data is received after outputting the audible indication; The system of claim 6 .

8. the instructions further provide for verifying whether one or both eyes of the user are open prior to processing the image data.

8. The system of claim 7.

9. displaying instructions on the display requesting the user to close their eyes includes displaying a text-based message requesting the user to close their eyes until they feel a vibration indication after the predetermined time for opening their eyes has elapsed.

2. The system of claim 1.

10. the instructions further provide for energizing a vibration motor to generate the vibration indication.

10. The system of claim 9.

11. the instructions further provide for determining when the eyes of the user identified in the live feed of the image data are within the pair of circles.

2. The system of claim 1.

12. displaying an instruction on the display requesting the user to close their eyes is initiated after determining that the user's eyes are within the pair of circles. The system of claim 11 .

13. processing the image data to identify at least one pupil feature further includes segmenting the received image data to determine a first data portion corresponding to a pupil of the at least one eye and a second data portion corresponding to an iris of the at least one eye.

2. The system of claim 1.

14. the at least one pupil characteristic comprises pupillary response latency, constriction latency, maximum constriction velocity, average constriction velocity, minimum pupil diameter, dilation velocity, 75% recovery time, average pupil diameter, maximum pupil diameter, constriction amplitude, constriction percentage, pupil deviation, baseline pupil amplitude, post-illumination pupillary response, and any combination thereof; 2. The system of claim 1.

15. determining a health status based on the at least one pupil characteristic; determining a difference between each of the at least one pupil feature and a corresponding healthy pupil measurement, the corresponding healthy pupil measurement being obtained by the processor from an external measurement database; determining the health status based on the determined difference for each of the at least one pupil characteristic and the corresponding healthy pupil measurement; further comprising:

2. The system of claim 1.

16. and first determining whether ambient light is bright enough to elicit a pupillary light reflex, and then initiating display of instructions on the display requesting the user to close their eyes.

2. The system of claim 1.

17. processing the image data to identify at least one pupil feature; determining image contrast of the received image data; determining that the image contrast is below a threshold contrast level; outputting a prompt to the user on the display to provide second image data in a more brightly lit location; further comprising:

2. The system of claim 1.

18. 1. A method for assessing pupillary light reflex, comprising: displaying a live feed of image data output from the camera on the display; displaying a pair of circles or other markings on the display and displaying instructions that a user should align their eyes with the pair of circles or other markings; providing a first instruction that the user should close their eyes for at least a predetermined period of time and then open their eyes; receiving image data from the camera corresponding to at least one eye of the user with the user's eye open; processing the image data to identify at least one pupil feature; determining a pupillary light reflex based on the at least one pupil characteristic; A method comprising:

19. 1. A non-transitory machine-readable medium containing machine-executable code that, when executed by at least one machine, causes the machine to: displaying a live feed of image data output from the camera on the display; displaying a pair of circles or other markings on the display and displaying instructions that a user should align their eyes with the pair of circles or other markings; displaying instructions on the display requesting the user to close their eyes for at least a predetermined period of time and then open their eyes; receiving image data from the camera corresponding to at least one eye of the user with the user's eye open; processing the image data using at least one or more processors to identify at least one pupil feature; determining a pupillary light response based on the at least one pupil characteristic using the at least one processor; 10. A non-transitory machine-readable medium for executing the method of claim 10.

Images