Systems and methods for eye tracking

Abstract

Systems and methods for identifying a change in visual gaze of an individual over time are implemented and / or include collecting a data set, the collected data set being determined by an eye tracking device, indicative of a visual gaze of the individual for a visual stimulus; extracting one or more eye tracking metrics from the data set; and generating, via software executing on the processor, an indication of at least one of the diagnostic or subtype indication based on the one or more eye tracking metrics.

Description

Cross-reference to related applications

[0001] This application claims the benefit of and priority to U.S. Provisional Patent Application No. 63 / 385,953, filed on December 2, 2022, and entitled “Systems and Methods for Eye Tracking,” the entire contents of which are incorporated herein by reference for all purposes. Technical Field

[0002] The present disclosure relates to the field of eye tracking for screening for diseases such as, for example, autism spectrum disorders (ASD). Background Art

[0003] Eye tracking (ET) has been explored as a method for early and objective screening of various disorders, including autism spectrum disorder (ASD).

[0004] Early diagnosis and intervention significantly impact the prognosis of individuals with autism spectrum disorder (ASD). The Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) and the Autism Diagnostic Observation Schedule, Second Edition (ADOS-2) have been developed to provide formal diagnoses. However, these comparative methods are often lengthy, difficult, and costly. A shortage of resources for such assessments often delays diagnosis and further treatment. Despite progress and efforts, the average age of diagnosis remains 4-5 years. Furthermore, using comparative methods, children with ASD who are from ethnic minorities, low-income, and / or non-English speaking backgrounds are diagnosed later than their white counterparts.

[0005] There is a need for a metric system with greater sensitivity and specificity that can diagnose and / or differentiate disorders, including better differentiation between individuals with and without ASD. Early diagnosis and early intervention can significantly improve outcomes for children with ASD. Summary of the Invention

[0006] The present disclosure overcomes these and other shortcomings by providing systems and methods for eye tracking as a screening method, including screening for ASD. The systems and methods described herein provide improved sensitivity and specificity compared to comparable systems and methods.

[0007] According to one aspect of the present disclosure, a method for identifying changes in an individual's visual gaze over time is provided. The method includes collecting a dataset, the dataset being determined by an eye-tracking device and indicating the individual's visual gaze in response to a visual stimulus; extracting one or more eye-tracking metrics from the dataset; and generating, via software executed on a processor, at least one of a diagnosis or a subtype indicator based on the one or more eye-tracking metrics.

[0008] According to another aspect of the present disclosure, a method for identifying changes in an individual's visual gaze over time is presented. The system includes an eye-tracking device configured to track eye movements of a subject while the subject views a visual stimulus; a processor coupled to the eye-tracking device and comprising program instructions that, when executed, cause the system to: collect a dataset from the eye-tracking device indicating the individual's visual gaze toward the visual stimulus, extract one or more eye-tracking metrics from the dataset, and generate an indication of at least one of a diagnosis or a subtype of ASD based on the one or more eye-tracking metrics.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable medium is provided. The non-transitory computer-readable medium stores instructions that, when executed by a processor of a system, cause the system to perform operations comprising collecting a dataset, the dataset being determined by an eye-tracking device and indicating an individual's visual gaze with respect to a visual stimulus; extracting one or more eye-tracking metrics from the dataset; and generating, via software executed on the processor, an indication of at least one of a diagnosis or a subtype of ASD based on the one or more eye-tracking metrics. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Some embodiments of the present disclosure are described herein with reference to the accompanying drawings. This description, taken together with the drawings, makes it apparent to one of ordinary skill in the art how some embodiments of the present disclosure may be practiced. The drawings are for illustrative purposes only and are not intended to show structural details of the examples in more detail than is necessary for a basic understanding of the teachings of the present disclosure. In the drawings:

[0011] Figure 1A Example image displays according to various aspects of the present disclosure are shown.

[0012] Figure 1B Shown for Figure 1A The image shows an example graph of gaze data.

[0013] Figure 2 A graph showing examples of ADOS-2 scores.

[0014] Figure 3 Shown for Figure 1AThe image shows another graph of an example of gaze data.

[0015] Figure 4A An example video frame with a first overlay is shown in accordance with various aspects of the present disclosure.

[0016] Figure 4B An example video frame with a second overlay is shown in accordance with various aspects of the present disclosure.

[0017] Figure 4C An example video frame with a third overlay is shown in accordance with various aspects of the present disclosure.

[0018] Figure 5 Shown for Figure 4A The image shows an example graph of gaze data.

[0019] Figure 6 Shown for Figure 4A The image shows another graph of an example of gaze data.

[0020] Figure 7 Example video frames are shown in accordance with various aspects of the present disclosure.

[0021] Figure 8 Example video frames are shown in accordance with various aspects of the present disclosure.

[0022] Figure 9A A graph illustrating examples of eye tracking metrics in accordance with various aspects of the present disclosure.

[0023] Figure 9B Graph illustrating examples of eye tracking metric correlations in accordance with various aspects of the present disclosure.

[0024] Figure 10 Examples of eye tracking systems according to various aspects of the present disclosure are shown.

[0025] Figure 11 Examples of eye tracking methods according to various aspects of the present disclosure are shown. DETAILED DESCRIPTION

[0026] In the following detailed description, reference is made to the accompanying drawings, in which specific examples are shown by way of illustration. These examples are described in sufficient detail to enable those skilled in the art to practice the present disclosure. However, it should be understood that the detailed description and specific examples, while indicating examples of embodiments of the present disclosure, are given by way of illustration only and not by way of limitation. In accordance with the present disclosure, various substitutions, modifications, additions, rearrangements, or combinations thereof may be made within the scope of the present disclosure and will become apparent to those skilled in the art.

[0027] Unless otherwise indicated, the various features shown in the drawings are not drawn to scale. The illustrations presented herein are not necessarily actual views of any particular method, apparatus, or system, but are merely idealized representations for describing various embodiments of the present disclosure. Therefore, for the sake of clarity, the sizes of the various features shown may be arbitrarily expanded or reduced. In addition, for the sake of clarity, some drawings may be simplified. Therefore, the drawings may not depict all components of a given device (e.g., equipment) or method. In addition, the same reference numerals may be used throughout the specification and drawings to represent the same features.

[0028] It should be understood that any reference to an element herein using designations such as "first," "second," etc. does not limit the quantity or order of these elements unless such restrictions are explicitly stated. Specifically, these designations can be used as a convenient method of distinguishing two or more elements or element instances in this article. Therefore, reference to a first element and a second element does not mean that only two elements can be adopted here or that the first element must be positioned before the second element in some way. In addition, unless otherwise indicated, a group of elements may include one or more elements.

[0029] As used herein, unless otherwise limited or defined, "or" indicates a non-exclusive list of components or operations that can exist in any different combination, rather than an exclusive list of components that can exist only as alternatives to each other. For example, a list of "A, B, or C" indicates the following options: A; B; C; A and B; A and C; B and C; and A, B, and C. Accordingly, the term "or" as used herein indicates exclusive alternatives only when preceded by an exclusive term, such as "only one of" or "exactly one of." For example, a list of "only one of A, B, or C" indicates the following options: A, but not B and C; B, but not A and C; and C, but not A and B. In contrast, a list that begins with "one or more" (and variations thereof) and includes "or" to separate the listed elements indicates an option of one or more of any or all of the listed elements. For example, the phrases "one or more of A, B, or C" and "at least one of A, B, or C" indicate the following options: one or more A; one or more B; one or more C; one or more A and one or more B; one or more B and one or more C; one or more A and one or more C; and one or more A, one or more B, and one or more C. Similarly, a list beginning with "plurality" (and variations thereof) and including "or" to separate the listed elements indicates an option of one or more of each of the plurality of listed elements. For example, the phrases "plurality of A, B, or C" and "two or more of A, B, or C" indicate the following options: one or more A and one or more B; one or more B and one or more C; one or more A and one or more C; and one or more A, one or more B, and one or more C.

[0030] As will be described herein, the present disclosure provides systems and methods for eye tracking as a screening method for ASD.The eye tracking system described herein includes an imaging device, a controller, and a display device.

[0031] Without wishing to be limited to any particular theory of operation, individuals with ASD have distinct eye movement and gaze patterns associated with distinct attentional characteristics, such as difficulty interpreting gaze cues, a preference for looking at more highly structured pictures, reduced attention to faces, and a lack of right hemisphere dominance in face processing.

[0032] The metric systems described herein include, but are not limited to, area of ​​interest (AOI) switching, attention shifts between AOIs, total gaze points or fixation counts by self-assigned AOI shift paths (e.g., favored or unfavored paths and their differences), and / or AOI vacancy rates. These eye tracking metrics have significantly higher sensitivity and specificity to distinguish those with ASD from those without, which can serve as biomarkers to aid in the early diagnosis and subtype classification of ASD. This, in turn, will allow for earlier and targeted interventions, leading to better prognosis for individuals with ASD, many of whom may otherwise require lifelong care due to social and / or intellectual disabilities.

[0033] As described in further detail below, this eye tracking metric system has increased sensitivity and specificity to distinguish individuals with ASD from those without ASD. Correlations between these new metrics and ADOS-2 subscales demonstrate the value of using eye tracking for screening and diagnosis of ASD.

[0034] This disclosure describes several eye tracking metrics, including but not limited to AOI switch incidence, attention shifts between AOIs, AOI shift paths (such as preferred and unpreferred paths and their differences), and AOI vacancy incidence. A measurement system is established for these metrics to detect core deficits in ASD with higher sensitivity and specificity than comparative examples, some of which use fixations, saccades, and pupil size to distinguish between ASD and non-ASD individuals.

[0035] The present disclosure further describes the correlation of these metrics with the ADOS-2 subscales to indicate the screening and diagnostic value of ASD using eye tracking. The non-ASD groups used in accordance with the systems and methods of the present disclosure are those at high risk for ASD or those with ASD features, rather than the neurotypical (NT) used in the comparison method. The differences between the ASD and non-ASD groups are smaller or more subtle, utilizing more sensitive or specific metrics.

[0036] The present disclosure provides non-invasive, rapid, objective, easy-to-apply, quantifiable biomarkers that can appear continuously from early childhood to old age. Eye tracking can be used as an early screening tool for ASD, which is simple to operate and has rapid conclusions. In the present disclosure, a system is established that has a set of metrics characterized by AOI switching counts, AOI shift paths (including favorite AOIs (FAS), unfavorable AOIs (UAS) and their differences), AOI vacancy incidence that directly reflects joint attention, and / or reference and attention fixations. These applications are more sensitive and specific for distinguishing ASD from non-ASD in high-risk groups with narrow gaps. These applications with customized example scenarios (usually lasting less than 1 minute) can be embodied as applications (apps) using smartphones, tablets, personal digital assistants (PDAs), laptops, desktop computers or other devices that have eye tracker devices (e.g., front-facing cameras) and connections to the Internet. The present disclosure may include a built-in computing system that can provide immediate preliminary results and, where appropriate, provide follow-up professional services for further evaluation. Centrally managed remote services can be combined with physician consultation to provide more sensitive, specific, and objective measurements of ASD characteristics. Thus, the present disclosure provides benefits in early diagnosis, screening, and subtyping of ASD as a reliable tool with simple application and rapid conclusions to guide early and targeted intervention.

[0037] Further data collection combined with deep learning and artificial intelligence will improve the accuracy of applications in different clinical settings, such as in early infancy, to identify high-risk individuals, thereby potentially preventing social impairments that might otherwise only appear in old age. This will significantly reduce the economic burden of ASD-related public health systems and eliminate the potential economic and psychological impact on the many affected families.

[0038] To illustrate the systems and methods of the present disclosure, an example experiment was conducted. The following discussion of this study is not intended to limit the scope of the claims.

[0039] Methods: In this disclosure, a new set of eye tracking metrics are presented, including AOI switches, total gaze points or fixation counts through self-assigned AOI shift paths, and AOI void counts (AVCs) in toddlers and preschoolers with ASD (n=22) and without ASD (n=17) using example video clips. Correlations between these eye tracking metrics and ADOS-2 subscales, as well as their cutoff scores, were also performed via linear regression analysis.

[0040] Participants: Thirty-nine individuals aged 18-84 months (i.e., toddlers and preschoolers) participated in the study. Participant recruitment included diverse racial groups to encourage a more ethnically heterogeneous study cohort. Enrolled study participants included 15 White (42.8%), 11 Asian (31.4%), and 9 subjects of other races (25.7%). Twenty-three males and 12 females participated in the study. Gender was defined by sex chromosome composition: "male" refers to individuals with XY chromosomes, and "female" refers to individuals with XX chromosomes. Individuals were recruited through clinical care clinics and an online recruitment site. All participants were included after being identified as high risk for ASD by a clinician or caregiver. High-risk status was confirmed by telephone screening prior to participation. Inclusion criteria included one or more of the following: (1) at least one sibling had a clinical diagnosis of ASD; (2) the caregiver or clinician had concerns about the child's development of social interactions, play, or other behaviors; and / or (3) the individual scored in the positive range on the Modified Checklist for Autism Toddlers (M-CHAT). Exclusion criteria included a significant congenital or genetic disorder or disease, or behavioral problems that would cause significant additional stress to the family and / or child during the testing period. Individuals with a previous diagnosis of ASD were also included, but the examiners were not informed of the diagnosis.

[0041] Assessment Instruments and Protocol: This study involved human participants and was reviewed and approved by the Institutional Review Board (IRB) of Massachusetts General Hospital. Participants' legal guardians provided informed consent for study participation. A telephone screening was conducted before the visit to determine whether the candidate met the study's inclusion criteria. During the telephone screening, some demographic information was recorded. During the visit, two different tests were performed. The first test was an eye-tracking study. Data collection was performed using a Tobie X3-120 eye tracker. The screen resolution was set to 1024 × 768 pixels, the sampling frequency was 250 Hz, and the spatial resolution was 0.03 degrees. Participants sat in front of a 22-inch widescreen LCD monitor in a dark, soundproof room. The center of their visual field was aligned with the center of the monitor, with an eye-to-monitor distance of 65 cm. Before a short video presentation, eye position correction was performed by having the subject fixate on a dynamic pink bunny (five-point calibration). Those who failed to follow the dynamic pink bunny's gaze did not continue the experiment. After the five-point calibration, a silent video clip of approximately 2 minutes was presented. Only data from participants who cooperated, completed the entire experiment, and passed quality checks were included in the data analysis.

[0042] Eye tracking stimulation:

[0043] however, it should be noted that this list is not exhaustive and other scenarios and / or parameters may be used without departing from the scope of this disclosure.The stimuli included several simple video clips and pictures.

[0044] The first video, designated Video 1, depicts a woman's face and a tablet. The video is 25 seconds long. The woman is shown on the left side of the screen and the tablet on the right. The 25 seconds are divided into four timeframes based on the following sequence of attentional focus: 1) The woman looks at the user while the tablet displays a moving object; 2) The woman turns the tablet off, then looks at the user while the tablet is blank; 3) The woman turns the tablet on again, similar to Focus 1; and 4) The woman turns the tablet off again, similar to Focus 2. This video is designed to test joint attention; in NT individuals, attention is expected to shift back and forth repeatedly, alternating from the tablet to the woman.

[0045] The second video, designated Video 2, depicts a female face. The video is 10 seconds long and consists of a woman mouthing the alphabet (without sound). The eyes, which play an important role in social and emotional expression, constitute one AOI, and the mouth, which represents functional responses associated with the (early) stages of canonical language development, constitutes another AOI.

[0046] The third video, Video 3, consists of a woman's sad face on the left side of the screen and a woman's neutral face on the right side. This video lasts for 10 seconds. After 5 seconds, the faces switch positions, such that the neutral face is on the left side of the screen and the sad face is on the right side, for another 5 seconds.

[0047] The fourth video, referred to as Video 4, depicts a person walking upright on one side of the screen, and the same person is rotated 180 degrees and displayed on the other side (the person appears to be walking upside down). Each person constitutes an AOI.

[0048] ADOS-2: The ADOS module used is based on the participant's age and takes approximately 30 minutes to an hour to complete. It consists of five modules, differentiated according to the participant's developmental and language level (Modules T, 1, 2, 3, and 4). Each ADOS-2 module concludes with one or more diagnostic algorithms consisting of items selected to maximize diagnostic sensitivity and specificity. In this study, the ADOS-2 was administered by professionally trained interviewers, in consultation with certified ADOS trainers as needed. Each subject's composite score, social affect (SA), and restrictive and repetitive behavior (RRB) subscores were recorded in a score booklet according to the standardized algorithm for the corresponding module and scored immediately after the visit. ADOS-2 Modules 1-3 include standardized calibrated severity scores (CSS) ranging from 1 to 10. ADOS scores are converted to total CSS, SA CSS, and RRB CSS. The ADOS-2 was administered by two different professionally trained administrators, and eye tracking was administered by three different professionally trained administrators. The total assessment time was approximately one hour.

[0049] Statistics: For ET, raw data were downloaded from Tobii Pro. Trials with less than 25% screen fixation time (percentage of trials in the ASD group and percentage of trials in the non-ASD group) were excluded from the final data analysis. Children with fewer than 50% valid trials (i.e., 6 trials) were also excluded from the study.

[0050] Correlations between total gaze counts (TGCs), fixation durations, fixation counts and AOI saccades, AOI switches and shifts, pupil size, and ADOS subscores were calculated for participants with and without ASD. ADOS scores were converted to total CSS, SA CSS, and RBB CSS for comparison across blocks T, 1, and 2. Sensitivity and specificity of each eye tracking score in predicting the final diagnosis were calculated, and a cutoff score with the desired sensitivity and specificity was selected to separate the ASD and non-ASD groups.

[0051] Each subject's TGC, ASC, FAS, and AVC were compared between the ASD and non-ASD groups and examined using the Wilcoxon rank-sum test. A discriminant analysis was performed to rank the AOIs based on their ability to classify subjects according to their ASD severity level. Data were analyzed using R / R-Studio. For the AOI shift analysis in Video 1, the total 25-second epoch was divided into four attention shift timeframes, as described above, and TGC, ASC, FAS, and AVC were compared within and across different attention shift timeframes between the ASD and non-ASD groups. Correlations were calculated between TGC, FAS, AVC, ASC, and ADOS total / subscore scores for ASD and non-ASD participants. Total CSS, SA CSS, and RRB CSS were calculated for comparisons across modules T, 1, and 2. The sensitivity and specificity of each ET metric score for predicting final diagnosis were calculated, and the cutoff score with the best sensitivity and specificity was selected to separate the ASD and non-ASD groups.

[0052] result:

[0053] 1. Demographic and clinical profile

[0054] In the study cohort, 39 children at high risk for ASD were included in the data analysis. Participants included 22 children with ASD and 17 children without ASD. Of these, 25 were male and 14 were female; 15 were white (42.8%), 11 were Asian (31.4%), and 9 were of other races (25.7%). Table 1 shows the demographic and clinical characteristics of all participants. There were no significant differences in age or sex between the ASD and non-ASD groups; however, as expected, there were significant differences in their ADOS-2 total scores and subscores (Table 1).

[0055] Table 1. Summary of study participant demographics and ADOS-2 scores.

[0056] 2. Differences in FAS and AVC between ASD children and non-ASD children.

[0057] Figure 1A A video image 110 is shown having a first area of ​​interest (AOI) 112 and a second AOI 114. As shown in one embodiment, the first AOI 112 is a woman's face and the second AOI 114 is a tablet. Video 1 (25 seconds) includes a woman on the left side of the screen (AOI-1 112 is her face) and a tablet (AOI-2 114) on the right side of the screen (see FIG. 1 ). Figure 1A The video lasted a total of 25 seconds and was divided into four time frames 1-2-3-4, as described above in the protocol (see Figure 1B): Frame 1 is when the tablet is turned on and the picture is moving, intended to attract the subject's attention to watch; Frame 2 is when the woman suddenly turns off the tablet and then stares at the user, and the subject is expected to turn to look at the woman's face, wondering what happened at this time; Frame 3 is when the woman turns the tablet on again; and Frame 4 is when the woman turns the tablet off again. The attention shift is expected during the tablet switching on and off. As can be seen in Figure 1B As seen in Figure 1, graph 120 shows gaze data for a first group (non-ASD individuals) 122 and a second group (ASD individuals) 124. The blue bars represent the TGC for the non-ASD group, and the red bars represent the TGC for the ASD group. The green area is the expected FAS path for NT subjects following the flat-face-flat-face sequence and the reverse sequence. The pink area is the unwelcome attention shift (UAS).

[0058] Both gaze point and gaze duration were analyzed, and significant differences were observed between groups and timeframes. Table 2 shows the relationship between gaze point and gaze duration and timeframe, AOI, group, and p-value between timeframes, indicating that both groups followed the same pattern of attention shifts, with non-ASD patients advancing further in this regard, which was statistically significant (p<0.05).

[0059] Table 2. Attention shift correlations with respect to time frame.

[0060] Table 3 summarizes the mean gaze and fixation duration for the ASD and non-ASD groups, overall and per-AOI timeframes, preferred and unpreferred AOIs across timeframes, and AOI vacancy counts across timeframes. Table 3 shows that the ASD group had significantly fewer gaze counts and fixation durations in the overall preferred AOI across timeframes compared to the non-ASD group (p < 0.0005), and significantly more gaze counts in the overall unpreferred AOI across timeframes compared to the non-ASD group (p < 0.05 for fixation duration and p < 0.025 for fixation counts). The difference between the two groups (preferred AOI minus unpreferred AOI) was further separated (p < 0.0005). Furthermore, attention in neither AOI was negatively correlated with such social functioning. These attentional occasions are referred to as AOI vacancy counts (AVCs). AOI vacancy counts were also significantly higher in the ASD group than in the non-ASD group (p < 0.001 for fixation duration and p < 0.0005 for fixation counts).

[0061] Table 3. Mean gaze with standard deviation on each AOI for the two groups.

[0062] The TGCs of both the ASD and non-ASD groups across the two AOIs were analyzed across different time frames (see Table 4A). This showed that for both AOIs, non-ASD children showed significant TGC differences between time frames 1→2, 2→3, and 3→4. In contrast, ASD children showed no TGC differences during the 1→2 and 2→3 shifts, and only began to show differences during the 3→4 shift for both AOIs; at the same time, the differences between the two subject groups showed significance in 1→2 and 2→3, but not in 3→4 (see Table 4A). When the FAS path and AVC (the subject's gaze counts not on either AOI) were further examined, it was found that the ASD group had significantly reduced TGC along the FAS across different time frames (p<0.00001) and significantly increased AVC (p<0.00001) compared to the non-ASD group (see Table 4B).

[0063] Table 4A. Significance comparison of total gaze counts across time frames for the ASD group relative to the non-ASD group

[0064] Table 4B. Comparison of favored shifts and vacant attention in the ASD group relative to the non-ASD group

[0065] Return Reference Figure 1A and Figure 1B , an example of one of the video images 110 from a video is shown, and gaze data is shown in graph 120. As Video 1 progresses, participants shift their gaze between a first AOI 112 and a second AOI 114. Gaze data for four time frames from two groups of participants is shown in graph 120.

[0066] If you can Figure 2 As seen in FIG, chart 200 shows a fitted line 210. This chart 200 shows example data from a correlation study based on a regression analysis between a significant eye tracking (ET) index and ASD severity based on the Autism Diagnostic Observation Schedule, Second Edition (ADOS-2) score. The favored AOI shift-unfavored AOI shift (FAS-UAS) of video 1 using video image 110 was negatively correlated with the ADOS-2 total score (r=-0.373, p=0.01948), SA score (r=-0.33, p=0.0412) and RRB score (r=-0.25, p=0.124). When using the ADOS-2 total CSS cutoff score of 5 and the FAS-UAS cutoff score of 641.1, the sensitivity was 91% and the specificity was 72%. The fitted line 210 shows the correlation between the two quantities, which indicates that different scores correspond to different probabilities of ASD.

[0067] Reference Figure 3 , chart 300 shows how video 1 Figure 1A The relationship between time and AVC (AOI vacancy count) for the non-ASD group (shown as circles) and the ASD group (shown as triangles) shown in video image 110 in FIG. When comparing the ASD group to the non-ASD group, AVC had the best sensitivity and specificity of all ET metrics. As shown in graph 300, a cutoff score of 0.305 for AVC versus time unit count for Video 1 achieved 88% sensitivity and 88% specificity for separating ASD from non-ASD. This means that the subject did not look at any of the presented AOIs and was not assumed to be uninterested, unengaged, or simply ignored their presence, which was more pronounced in subjects with ASD.

[0068] 3. Differences in ASC and AVC between ASD children and non-ASD children.

[0069] Video 2 (10 seconds) consists of a female speaking silently (lip-syncing the alphabet). Figures 4A-4C As seen in Figure 2, these video frames 410, 420, and 430 are from Video 2. This video is used to show the differences in ASC and AVC between children with ASD and those without ASD. Two AOIs are defined: AOI-1 412 is defined as the eye region, and AOI-2 414 is defined as the mouth region (see Figure 2). Figure 4A );

[0070] exist Figure 4B and Figure 4C In the AOIs, the subjects’ TGC and ASC were analyzed (i.e., switching between these two AOIs). Red dots represent the ASD group, and blue dots represent the non-ASD group. Figure 4B TGC is shown, Figure 4C The TFT (total fixation time) of the two groups is shown. It can be seen that the density distribution pattern is different between the ASD group (red) and the non-ASD group (blue). The ASD group has a more diverse and dispersed distribution.

[0071] The detailed results of gaze, fixation and saccade duration, pupil size, number of switches between two AOIs (AOI switches), and AOI vacancy counts are summarized in Table 5 below. The ASD group had significantly fewer AOI switches between AOIs 1 and 2 (P = 0.025), and the AOI vacancy counts in the ASD group were significantly higher relative to the non-ASD group (P = 0.0005). The ASD group was found to have smaller gaze duration, fixation length, saccade duration, and pupil size than the non-ASD group. However, the differences were not statistically significant (P > 0.05) or marginally significant (P = 0.05).

[0072] If you can Figure 5As seen in FIG. 5 , graph 500 shows how video 2 Figures 4A-4C The relationship between time and AVC (AOI vacancy count) for the non-ASD group (shown as circles) and the ASD group (shown as triangles) shown in video frames 410, 420, and 430 in FIG. When comparing the ASD group to the non-ASD group, AVC had the best sensitivity and specificity of all ET metrics. As shown in graph 500, a cutoff score of 0.306 for AVC relative to time unit count achieved 100% sensitivity and 80% specificity. Trend line 510 shows that there was a correlation between the group that the participant was in (ASD versus non-ASD) and the AVC score. This means that the subject did not look at any of the presented AOIs, nor was it assumed to be uninterested, unengaged, or simply ignored its existence, which was more pronounced in subjects with ASD. Reduced TFTs for people and faces (which are related to TGCs), as well as attention disengagement problems, appear to be one of the earliest signs of ASD (38).

[0073] Reference Figure 6 Graph 600 shows the relationship between participant order for the non-ASD group (shown as circles) and participant order for the ASD group (shown as triangles) relative to AOI switch counts (ASCs) and a trend line 610. Another important new concept we introduced in this study is the ASC from one AOI to another. The data showed that in the switch from the eye region to the mouth region of the face of a silent female speaker, the ASD group had significantly lower ASC compared to the non-ASD group (p = 0.045), meaning that subjects with ASD were less motivated to compare differences between AOIs, while the commonly used measures of TFT and pupil size were found to be non-significantly different for the same stimulus. We found that a cutoff of 4.5 achieved 71% specificity and 64% sensitivity (p = 0.0452). These novel findings indicate that ASC is also more sensitive and specific for ET features than TFT and pupil size in distinguishing ASD from non-ASD, although less so than AVC or FAS-UAS. Consider the face of a woman speaking silently. People typically switch rapidly between the mouth area and the eyes to figure out what she is saying, rather than focusing continuously on either the eyes or mouth area. This can be described as "mind reading." Individuals with ASD have a lower ability or interest in mind reading or theory of mind (ToM); therefore, the switching from eyes to mouth is significantly less than in individuals without ASD. ToM is the human ability to perceive, interpret, and attribute the mental states of others, and alterations in this cognitive function are a core symptom of ASD.

[0074] Table 5. Gaze, saccade, pupil size, and AOI switching

[0075] Video 3 (5 seconds): This video consists of a woman's neutral face on the left side of the screen and her sad face on the right side of the screen, lasting 5 seconds. Figure 7 In FIG, video frame 710 shows a first expression 712 and video frame 720 shows a second expression 722. The first expression 712 is a neutral face and the second expression is a sad face. Table 6 summarizes the results of gaze density, fixations, and saccades. Compared with the non-ASD group, the ASD group fixed fewer fixations on both sad and neutral faces. The reduction in fixations on neutral faces was found to be significant (p=0.025), the ASD group had a significantly reduced number of AOI switches between sad and neutral faces (p=0.025), and the ASD group had a slightly smaller pupil size (p=0.05).

[0076] Table 6. Fixation duration, number of saccades, and switches between regions of interest in Video 3

[0077] Video 4 (a and b, 5 seconds each): One side of the screen shows a point light display of a person walking upright. On the other side, the same person is rotated 180 degrees, appearing to be walking upside down. Each person is identified as an AOI. Figure 8 Examples 2a and 2b are shown instead. Figure 8 , video frame 810 shows the gaze density of the first group 812 and the gaze density of the second group 814. Video frame 820 shows the gaze density of the first group 822 and the gaze density of the second group 824. Again, the red dots represent the gaze density of the ASD group and the blue dots represent the gaze density of the non-ASD group. Video 4 shows a walking skeleton for 10 seconds, and then each scene lasts for 5 seconds. On one side of the screen, a point light display of a person walking upright is shown. On the other side, the same person is rotated 180 degrees and the person appears to be walking upside down. Each person is identified as an AOI. Preferential attention to biological movement is a fundamental mechanism that promotes adaptive interactions with other organisms.

[0078] Table 7 below summarizes the gaze density, fixation, saccades, pupil size, and AOI switching between the two character skeletons. Again, it was found that the ASD group switched significantly less AOIs between the two walking characters as two separate regions of interest compared to the non-ASD group (P = 0.025), the pupil size of the ASD group was significantly smaller (P = 0.25), while the gaze density and fixation length in the AOI were found to be not statistically significant (P> 0.05). There was no statistical difference in their fixation / saccade ratio. When video 4b was presented, AOI switching no longer showed a significant difference between the two groups, but relative AOI switching was significant (p = 0.025), similar to pupil size in the AOI; at the same time, the gaze density of the ASD group on the AOI of the left upright walking character was found to be significantly lower than that of the non-ASD group (p = 0.025), while the fixation length was slightly significant (p = 0.05).

[0079] like Figure 9A As shown, chart 910 is an example graph showing time on the x-axis. The first 25 time units belong to the non-ASD group, which is represented in blue, and the last 25 time units belong to the ASD group, which is represented in red. Each point represents the average AOI vacancy rate (y-axis) for the subjects in that time unit. Trend line 912 shows the cutoff value of 0.306.

[0080] Reference Figure 9B , Chart 920 is an example graph of the relationship between AOI vacancy count and SA score, using 0.5 as the SA score cutoff, providing the following results: sensitivity = 85.7%, specificity = 60.8%, the x-axis represents the SA score, the y-axis represents the average AOI vacancy count across all time units in a subject, the cutoff value is -0.308, r = 0.32, r(tt) = 0.3.

[0081] Table 7. Fixation and saccade switching between regions of interest in Video 4

[0082] Based on ADOS-2 scores, a correlation study was performed to perform regression analysis between significant eye tracking indices and ASD severity. AOI switching was weakly negatively correlated with RRB scores (r = -0.269), while gaze density and fixation were found to be negatively correlated with SA in the eye and mouth regions, but not with RRB. Favored AOIs across time frames and missing AOIs on the video were also found to be negatively correlated with SA (r = -0.322 and r = -0.347, respectively), but not with RRB (r < 0.1). The cutoff scores for each eye tracking metric are shown in Table 8 below.

[0083] Table 8. Correlations between significant eye tracking metrics and ADOS scores

[0084] When detailed TGC, ASC, and AVC were studied, the ASD group was found to have significantly fewer ASCs (P=0.0452) and significantly more AVCs (P=0.000017) between AOI 1 and 2 compared to the non-ASD group, while the TGC of the ASD group was found to be significantly smaller than that of the non-ASD group for the AOI-1 region (P=0.00379) but not for the AOI-2 region (P=0.6537). The EP metrics TFT and pupil size (used in the comparison system) were also compared, and no significant differences were shown between the two groups (p>0.05), indicating that the sensitivity of AVC and ASC was significantly higher than that of the comparison metrics (see Table 9).

[0085] Table 9. Comparison of comparative eye tracking metrics and eye tracking metrics according to the present disclosure in the ASD group versus the non-ASD group for Video 2

[0086] 4. Correlation between significant ET measures and ADOS-2 scores / ASD diagnosis

[0087] Based on the ADOS-2 score, a correlation study was performed using regression analysis between the significant ET index and ASD severity. It was found that the FAS-UAS of Video 1 was negatively correlated with the ADOS-2 total score (r = -0.373, p = 0.01948), SA score (r = 0.33, p = 0.0412), and RRB score (r = -0.55, p = 0.124). When using an ADOS-2 total CSS cutoff score of 5 and a FAS-UAS cutoff score of 641.1, a sensitivity of 91% and a specificity of 72% were obtained.

[0088] When comparing the ASD group (red dots) and the non-ASD group (blue dots), AVC was found to have the best sensitivity and specificity among all ET metrics (including the comparison metric), and the results were consistent in Video 1 (88% sensitivity, 88% specificity, p < 0.00001, cutoff score 0.305) and Video 2 (100% sensitivity, 80% specificity, p < .000045, cutoff score 0.306). The sensitivity of ASC in Video 2 was 71% and the specificity was 64%, p = 0.04523, with a cutoff score of 4.5.

[0089] The ASD group had significantly fewer preferred AOI shifts for sequences of different attentional foci (p < 0.05); the ASD group had significantly fewer switch counts between one AOI and another (p < 0.05). The ASD group had significantly higher AOI gap counts than the non-ASD group (p = 0.0005). In addition, the preferred AOI shifts were found to be negatively correlated with the ADOS-2 SA subscale (r = -0.334), the AOI gap counts were positively correlated with SA (r = 0.347), and the AOI switches were negatively correlated with the RRB subscale (r = -0.373); the cutoff score for non-AOI counts yielded 80% sensitivity and 92% specificity.

[0090] discuss

[0091] In the aforementioned study, a set of eye-tracking metrics was developed and investigated. First, the concepts of "desired AOI shifts" and "undesired AOI shifts" were introduced, depending on whether attention shifts are typically expected or, conversely, undesired. This concept emphasizes the viewer's ability to adjust their attention to the currently appropriate object and reduce attention to less important objects, even if they are the "correct" object. This is a comprehensive ability. Second, the concept of attention-scaling (ASC) between two competing targets was introduced. Third, the concept of AVC was discussed as an eye-tracking metric to distinguish ASD from non-ASD in ASD characterized by core deficits. Compared to previously used TFTs and pupil size, these biomarkers were found to be more sensitive and reliable. Their cutoff scores were explored, and correlations with the ADOS-2 total score, SA score, and RRB subscore were found. Each of these biomarkers and their diagnostic value are discussed in more detail below. The subject population for this study included all toddlers or preschoolers at high risk for ASD, with ASD and non-ASD defined based on the DSM-5. The non-ASD group in this study was not the NT peers used in the comparative study. Differences between the ASD and non-ASD groups in this study may be subtle and small, which would require more sensitive or specific measures.

[0092] Using Video 1 to test joint attention (JA), the ASD group engaged in significantly fewer FASs across timeframes compared to the non-ASD group. The non-ASD group significantly outperformed the ASD group in FAS, while the ASD group moderately outperformed the non-ASD group in UAS. Differences between favored and unfavored AOIs may have led to further differences between the two groups. Across timeframes, the ASD group engaged in significantly fewer and more delayed attention shifts compared to the non-ASD group. These findings consistently reflect poor or absent JA in ASD. JA, an important human social communication and social cognitive skill, is a characteristic manifestation and early marker of significant impairment in ASD. JA begins to develop at 5 months of age, and the study found that at 10 months of age, infants later diagnosed with ASD initiated JA at a lower rate than controls. In this study, when their correlations with the ADOS-2 total and subscores were further explored, they were found to be negatively correlated with TGC on the FAS-UAS, which was significant for the total and SA scores (p < 0.05), but not for the RRB score (p > 0.05). This suggests a positive correlation between TGC within the popular AOI and social functioning: the higher the SA, the lower the social functioning. It is expected that the correlation would be higher if neurotypical controls were used rather than the high-risk non-ASD controls used in this study. ET measures using the FAS or FAS-UAS as reliable tests of JA traits are promising for the early diagnosis of ASD.

[0093] Another biomarker of interest is AVC, which was not achieved in the comparison sample. This represents TGC outside of all defined AOIs. AVC temporal unit counts were significantly increased in the ASD group compared to the non-ASD group (p < 0.00001 for Video 1, p = 0.000017 for Video 2), suggesting that subjects with ASD tend to pay far less attention than expected and may overlook shared interests or "spaces." Furthermore, a cutoff score of 0.305 for AVC relative to temporal unit counts in Video 1 achieved 88% sensitivity and 88% specificity for distinguishing ASD from non-ASD; similarly for Video 2, a cutoff score of 0.306 for AVC relative to temporal unit counts achieved 100% sensitivity and 80% specificity. This means that subjects did not look at any of the presented AOIs, nor were they assumed to be uninterested, unengaged, or simply ignored their presence, which was significantly more prevalent in subjects with ASD. Reduced TFTs for people and faces (which are associated with TGCs), as well as attentional disengagement issues, appear to be one of the earliest signs of ASD. Early reductions in social attention may represent an infant endophenotype for social motivational traits associated with ASD, while changes in general attention are often seen in attention-deficit and hyperactivity disorder (ADHD). Gaze-triggered attention was found to be reduced in individuals with ASD and influenced by self-relevant gaze cues, and correlated with symptom severity in ASD. This finding, with a favorable cutoff score, high sensitivity, and specificity, furthers the potential of ET as a valuable biomarker for early diagnosis.

[0094] Another important concept introduced in this study is the ASC from one AOI to another. In the switching from the eye region to the mouth region of the face of a silent female speaker, the ASD group had significantly lower ASC compared to the non-ASD group (p=0.045), which means that subjects with ASD were less motivated to compare differences between AOIs, while the TFT and pupil size metrics used in the comparison method were found to be no significant difference under the same stimulus. A cutoff of 4.5 achieved 71% specificity and 64% sensitivity (p=0.04523). These findings indicate that ASC is also more sensitive and specific to ET features than TFT and pupil size in distinguishing ASD from non-ASD. Referring to the scene of the face of a silent female speaker, NT people can quickly switch (switch) back and forth between the mouth region and the eyes to figure out what she is saying, rather than continuously focusing on the eyes or mouth region; this can be called "mind reading". ASD individuals have lower ability or interest in mind reading or theory of mind (ToM); therefore, the switching from eyes to mouth is significantly less than that of non-ASD individuals. ToM is the human ability to perceive, interpret, and attribute the mental states of others, and alterations in this cognitive function are a core symptom of ASD.

[0095] Another finding was that pupil size was consistently smaller in ASD across all AOIs across different videos in at least a subset of the scenes. Comparison examples reported significantly smaller baseline pupil size in the ASD group compared to matched controls. Pupil dilation is determined by emotional arousal. Pupil dilation measures correlated with individual differences measured by the Social Responsiveness Scale (SRS), a quantitative measure of autistic traits. Other comparison examples showed that the pupils of ASD individuals initially constricted more, took longer to dilate, and ultimately dilated more than those of non-autistic participants. The amount by which autistic individuals' pupils dilate (dilate) when observing others interacting and the speed at which this occurs are related to their understanding of social behavior.

[0096] The above studies also showed that the ASD group had a consistent reduction in gaze duration compared to the non-ASD group. The shortest gaze duration was found in infants diagnosed with ASD at 36 months, making gaze duration a potential early marker of ASD. In this study, significant variability in saccades was found. A saccade is a rapid and simultaneous eye movement between two or more gaze phases in the same direction, designed to shift the fovea to an object of visual interest. In ASD, saccadic characteristics are associated with measures of restrictive and repetitive behavior. Reduced saccade amplitude and duration indicate that spatially focused gaze reduces visual exploration and emphasizes intrinsic rather than exogenous attention. Children with ASD make more saccades and have slower reaction times; however, exogenous and intrinsic orienting (including gaze cues) are intact in ASD. Saccades in individual ASD patients are characterized by reduced accuracy, increased variability in accuracy across trials, reduced peak velocity, and prolonged duration. At birth, infants can direct their gaze to interesting scenes in the environment, primarily using saccadic eye movements. These rapid gaze shifts from one location to another are variable in newborns and typically involve several low-volume saccades that successively bring the object of interest closer to the infant's focus. Results showed no significant differences in the number of fixations, fixation duration, number of saccades, saccade duration, saccade accuracy, and saccade latency across the different groups. Differences in gaze behavior in children with ASD may be due to atypical social preferences rather than impaired control of eye movements and not due to underlying oculomotor deficits.

[0097] Conclusion: This study developed a set of eye tracking metrics, including preferred AOI shifts, AOI vacancy counts, and AOI switches, and found them to be significantly more sensitive and specific than metrics used in the comparison sample (such as fixation duration) to distinguish ASD from non-ASD. This study further explored the correlation of these new metrics with ADOS-2 subscales to indicate the screening and diagnostic value of ASD using eye tracking.

[0098] Reference Figure 10, an eye tracking system 100 for screening for ASD (an example of an “eye tracking system” according to the present disclosure).

[0099] For example, Figure 10 As shown in , eye tracking system 1000 may include a controller 1010 having one or more inputs, a processor, a memory, and an output.

[0100] The eye tracking system 1000 may include, access, or communicate with one or more user interfaces and / or imaging devices 1020 by way of a wired or wireless connection to an input. In various implementations, the eye tracking system 1000 may include any computing device, apparatus, or system configured to execute instructions and provide input / output capabilities, and may operate in conjunction with or as part of other computing devices and sensors / detectors (local and remote). In this regard, the eye tracking system 1000 may be a system designed to integrate various software and hardware capabilities and functions, and / or may be capable of operating autonomously.

[0101] The input may include any one or more different input elements, such as a mouse, keyboard, touchpad, touch screen, buttons, etc., for receiving various selections and operation instructions from the user through touch, movement, voice, etc. The input may also include various drives and sockets, such as flash drives, USB drives, CD / DVD drives, and other computer-readable media sockets, for receiving various data and information. To this end, the input may also include various communication ports and modules, such as Ethernet, Bluetooth, or Wi-Fi, for exchanging data and information with these communication ports and modules and other external computers, systems, devices, machines, mainframes, servers, or networks.

[0102] In addition to being configured to perform various steps for operating the hair transplantation system, the processor 1012 can also be configured to run instructions stored in the memory 1014 in a non-transitory computer-readable medium. The instructions executable by the processor 1012 can correspond to various instructions for performing a hair transplantation procedure (such as those previously described). The memory 1014 can be or include non-volatile media, such as magnetic media or a hard disk, optical storage, or flash memory; volatile media, such as system memory, such as random access memory (RAM), such as dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), extended data output (EDO) DRAM, extreme data rate dynamic (XDR) RAM, double data rate (DDR) SDRAM, etc.; on-chip memory; and / or appropriate installation media, such as software media, such as a CD-ROM or floppy disk, on which programs can be stored and / or data communications can be buffered. Although non-transitory computer-readable media can be included in the memory 1014, it is understood that instructions executable by the processor 1012 can be stored in addition to or instead of another data storage location with non-transitory computer-readable media. For example, the hair transplantation system 1200 can be configured to implement cloud storage.

[0103] As used herein, a “processor” may include one or more separate electronic processors, each of which may include one or more processing cores, and / or one or more programmable hardware elements. A processor may be or include any type of electronic processing device, including but not limited to a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a microcontroller, a digital signal processor (DSP), or other device capable of executing software instructions. When a device is referred to as “including a processor,” one or all of the separate electronic processors may be external to the device (e.g., to implement cloud or distributed computing). In implementations where the device has multiple processors and / or multiple processing cores, the separate operations described herein may be performed by any one or more of the microprocessors or processing cores in serial or parallel, in any combination.

[0104] In some aspects, the processor 1012 can be configured to receive and process image data from a subject (such as a donor or recipient) captured by the imaging system 1020 to identify hair follicles and hair follicle orientation within a donor site of the donor, and / or determine an implantation location and necessary implantation angle within a recipient site. In some aspects, the processor 1012 can access information and data stored in or transmitted by the imaging system 1020, including video signals. In some aspects, the imaging system 1020 can acquire a single image or a continuous video signal using, for example, a camera, an infrared scanning system, or any other image capture or video recording device that can be used to periodically image and / or scan and / or continuously record a subject.

[0105] In some non-limiting examples, imaging system 1020 may include cameras such as standard complementary metal oxide semiconductor (CMOS) cameras and charge coupled device (CCD) cameras, etc. Display device 1030 may include a display configured to display video and / or still images, such as a liquid crystal display (LCD), an organic light emitting display (OLED), etc.

[0106] In some implementations, the controller 1010, imaging device 1020, and display device 1030 may be integrated into a single device. For example, the eye tracking system 1000 may be a laptop computer, a tablet computer, a notebook computer, a smartphone, a desktop computer, a personal digital assistant (PDA), etc. In other implementations, the imaging device 1020 and / or the display device 1030 may be separate devices configured to connect to the controller 1010. For example, the imaging device 1020 may be a webcam connected to the controller 1010, and / or the display device 1030 may be an external display (e.g., an external monitor) connected to the controller 1010. In such examples, the connection may be wired (e.g., via a Universal Serial Bus (USB) interface, a FireWire interface, a High-Definition Multimedia Interface (HDMI), a DisplayPort interface, etc.) or wireless (e.g., via a Wi-Fi interface, a Bluetooth interface, a Near Field Communication (NFC) interface, etc.).

[0107] The eye tracking system 1000 can be configured to implement the systems and methods described herein via a program installed locally on the device (e.g., an application) or via a remotely located program (e.g., via a network interface). In either case, the eye tracking system 1000 can be configured to present a graphical user interface (GUI) on the display device 1030 to display still images and / or video images, receive user input or selections, present instructions to the user, and the like.

[0108] Figure 11An example method 1100 according to the present disclosure is shown. For illustrative purposes, the method 1100 is described as being performed by the system 1000. However, the present disclosure is not limited thereto, and in some implementations, the method 1100 may be performed by another system (e.g., a server or other device that receives data from another system, such as the system 1000). The method 1100 may be performed on a subject (such as a human child).

[0109] Method 1100 also includes an operation 1102 of collecting a data set corresponding to the eye tracking device. For example, the data set may be generated by the eye tracking device and may indicate the individual's visual gaze at a visual stimulus. The visual stimulus may include any one or more of the above-mentioned scenes, such as Figure 1A 、 Figure 4A 、 Figure 7 and / or Figure 8 The video shown in .

[0110] Method 1100 further includes an operation 1104 of extracting one or more eye metrics from the dataset. Eye tracking metrics may include any combination of AOI switch incidence, AOI shift path, AOI void incidence, total gaze points, and / or fixation counts. Metrics may be related to ASD core deficits, including but not limited to repetitive and / or restrictive behaviors or social deficits.

[0111] Method 1100 further includes an operation 1106 of generating an indication based on the one or more eye tracking metrics. The indication may be at least one of a diagnosis or a subtype of ASD. In some implementations, operations 1102-1106 may be performed by a processor of a system executing method 1100 (e.g., in Figure 10 1010). In other implementations, operations 1102-1106 may be performed by another device based on data obtained by the eye tracking device. In other implementations, some of operations 1102-1106 may be performed by the eye tracking device (e.g., using a camera to collect data), while other operations of operations 1102-1106 may be performed by another device.

[0112] Figure 11 The operations need not be performed one after another in a strict sequence. For example, operation 1102 may be performed constantly or continuously to obtain an updated data set, and thereafter operation 1104 may be performed to extract one or more eye tracking metrics.

[0113] Other examples and uses of the disclosed technology will be readily apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. The description and examples given should be considered as exemplary only, and it is contemplated that the appended claims will cover any other such embodiments or modifications that fall within the true scope of the invention.

[0114] The Abstract is provided to enable the U.S. Patent and Trademark Office and the public to quickly ascertain the nature and gist of the technical disclosure upon a cursory inspection and is not intended to define, qualify, or limit the invention or any embodiment thereof.

Claims

1. A method for identifying changes in an individual's visual gaze over time, the method comprising: collecting a data set, the collected data set being determined by an eye tracking device and indicating an individual's visual fixation on a visual stimulus; extracting one or more eye tracking metrics from the dataset; as well as An indication of at least one of a diagnosis or a subtype indication is generated via software executing on a processor based on the one or more eye tracking metrics.

2. The method according to claim 1, characterized in that The one or more eye tracking metrics are at least one of an area of ​​interest (AOI) switch incidence rate, an AOI shift path, an AOI void incidence rate, total gaze points, or a fixation count.

3. The method according to claim 2, characterized in that The AOI switching incidence is associated with core deficits in autism spectrum disorder (ASD).

4. The method according to claim 3, characterized in that The core deficits in ASD include repetitive and / or restricted behaviors.

5. The method according to claim 2, characterized in that The AOI gap incidence is a measure of shifts between favored and unfavored pathways and is associated with core deficits in ASD, including social deficits.

6. The method according to claim 2, characterized in that The AOI shift pathway is associated with ASD core defects.

7. The method of claim 1, further comprising generating a report including the diagnosis or subtype indication.

8. The method according to claim 1, characterized in that The individual is a human child.

9. The method according to claim 1, characterized in that The eye tracking device is a camera.

10. A system for identifying changes in an individual's visual gaze over time, the system comprising: an eye tracking device configured to track eye movements of the subject while the subject views a visual stimulus; as well as a processor coupled to the eye tracking device and comprising program instructions that, when executed, cause the system to: collecting a data set from the eye tracking device, the data set indicating an individual's visual fixation on the visual stimulus, extracting one or more eye tracking metrics from the dataset, and An indication of at least one of a diagnosis or a subtype of ASD is generated based on the one or more eye tracking metrics.

11. The system according to claim 10, wherein: The one or more eye tracking metrics are selected from area of ​​interest (AOI) switch incidence, AOI shift path, AOI void incidence, total gaze points, and fixation count.

12. The system according to claim 11, wherein: The AOI switching incidence rate is correlated with the ASD core defect.

13. The system according to claim 12, wherein: The core deficits in ASD include repetitive and / or restrictive behaviors.

14. The system according to claim 11, wherein: The AOI gap incidence is a measure of the shift between favored and unfavored pathways and is associated with ASD core deficits.

15. The system according to claim 14, wherein: The core deficits of ASD include social deficits.

16. The system according to claim 11, wherein: The AOI shift pathway is associated with ASD core defects.

17. The system of claim 10, further comprising a display device coupled to the processor, the display device configured to display the visual stimulus.

18. The system according to claim 10, wherein: The eye tracking device is a camera.

19. A non-transitory computer-readable medium storing instructions that, when executed by a processor of a system, cause the system to perform the following operations, including: collecting a data set, the collected data set being determined by an eye tracking device and indicating an individual's visual fixation on a visual stimulus; extracting one or more eye tracking metrics from the dataset; as well as An indication of at least one of a diagnosis or a subtype of ASD is generated via software executing on the processor based on the one or more eye tracking metrics.

20. The non-transitory computer readable medium of claim 19, wherein The one or more eye tracking metrics are at least one of an area of ​​interest (AOI) switch incidence rate, an AOI shift path, an AOI void incidence rate, total gaze points, or a fixation count.

Images