A method for early screening of Alzheimer's disease

Abstract

The present invention relates to the field of cognitive impairment image processing technology, specifically a method for early screening of Alzheimer's disease, comprising the following steps: extracting the time and space coordinates of the gaze point from a visual scanning task in which Alzheimer's patients participate, recording the directional changes of the jumping behavior in the time and space coordinates, and generating jumping behavior distribution data. The present invention, by extracting the time and space coordinates of the gaze point and combining them with the directional changes of the jumping behavior, achieves a comprehensive characterization of the dynamic laws of the gaze behavior, and provides high-dimensional support for the detailed analysis of the patient's gaze behavior during the execution of the task. By constructing the jump event distribution, trajectory dynamic changes, and complexity quantification of the gaze path, the offset characteristics, jumping laws, and path fractal dimensions in the gaze behavior are accurately revealed, providing a quantitative description of abnormal behavior for screening.

Description

Technical Field

[0001] The present invention relates to the technical field of cognitive impairment image processing, and in particular to an early screening method for Alzheimer's disease. Background Art

[0002] Cognitive impairment image processing technology studies and addresses issues related to cognitive impairment by analyzing brain images, behavioral videos, or other relevant visual data. This technology primarily relies on artificial intelligence, deep learning, and pattern recognition techniques, combined with multimodal imaging (such as MRI, CT, PET, etc.) and neuroscience knowledge to identify early signs of cognitive impairment, providing a scientific basis for medical diagnosis, rehabilitation program design, and health monitoring. It is widely used in the early detection and intervention of neurological diseases such as Alzheimer's disease, Parkinson's disease, and autism.

[0003] Among them, early screening methods for Alzheimer's disease are an important application direction in the field of cognitive impairment image processing. They aim to discover early biomarkers or pathological characteristics of Alzheimer's disease by analyzing brain images or other related data. Their main purpose is to help clinicians diagnose the disease early through rapid and accurate screening methods, thereby formulating personalized intervention measures.

[0004] When analyzing gaze behavior, existing technologies have difficulty in dynamically recording the direction, amplitude, and time series characteristics of gaze point jump behavior, and are unable to deeply identify the changing patterns of gaze paths within and outside the task phase. For example, in a memory search task, existing methods can only roughly count the distribution of gaze points, but are unable to capture the microscopic characteristics of the distribution of return points, bifurcation points, and hotspot areas, resulting in the neglect of behavioral characteristics of abnormal task execution in patients. For the analysis of the complexity and changing patterns of gaze paths, existing technologies have difficulty in quantifying the complexity of gaze behavior through means such as path fractal dimension, making it difficult to identify cognitive abnormalities hidden in patients' jump paths. In the comparative analysis of hotspot areas and healthy groups, existing methods have difficulty in counting the hotspot distribution of gaze behavior based on jump frequency and direction changes, and are unable to reveal significant differences between patients and the control group during the task switching phase. The above-mentioned deficiencies result in insufficient coverage of dynamic behavioral characteristics by existing technologies in disease screening, which may lead to a decrease in the sensitivity of screening results to abnormal cognitive functions. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an early screening method for Alzheimer's disease.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for early screening of Alzheimer's disease, comprising the following steps:

[0007] S1: Extract the temporal and spatial coordinates of the gaze point from a visual saccade task performed by patients with Alzheimer's disease, record the directional changes of the jumping behavior in temporal and spatial coordinates, and generate jumping behavior distribution data;

[0008] S2: Based on the jump behavior distribution data, the direction, amplitude, and fixation duration of the jump events are grouped and arranged, and the position changes are recorded. Combined with the density of the fixation point distribution position, a fluctuation characteristic diagram of the visual saccade task is generated;

[0009] S3: Based on the fluctuation characteristic diagram of the visual saccade task, the distribution of target points and non-target points in the gaze path is recorded, and the return points and bifurcation points are marked with reference to the continuity and jump changes of the gaze behavior. The number and length of path switches are counted to generate the path characteristic data of the patient's memory search task;

[0010] S4: Based on the path characteristic data of the patient's memory search task, according to the relative position change between the target point and the fixation point, the direction and magnitude of the deviation event are recorded and the deviation category is distinguished to generate the path deviation characteristic data in the patient's search task;

[0011] S5: Collect data from the memory search phase of healthy subjects, compare it with the path deviation characteristic data of the patient search task, mark the hotspot areas and fixation points, analyze the differences in the hotspot distribution of the patient jump path and the control group, and generate hotspot fixation feature data;

[0012] S6: Based on the hotspot gaze feature data, record the number and location of gazes on the target object and the distractor, analyze the gaze path during the task switching phase, extract the behavioral characteristics of the target gaze path, generate early screening data for Alzheimer's disease, and apply it to early screening for Alzheimer's disease.

[0013] The present invention has the following improvements: the jump behavior distribution data includes time records of gaze points, multi-dimensional position distribution of jump directions, and gaze time duration data; the fluctuation characteristic diagram of the visual scanning task includes jump frequency change distribution in each stage of the gaze trajectory, dynamic fluctuation range of jump direction consistency, and trajectory distribution density information of the gaze time period; the patient memory search task path characteristic data includes gaze coverage distribution of target points, jump behavior statistics of non-target points, and the number and position relationship of return points in the path; the path offset characteristic data in the patient search task includes the distance change range between the target point and the gaze point, the direction angle distribution of the offset event, and the frequency statistics of the offset amplitude; the hotspot gaze feature data includes the coverage difference of the gaze point hotspot area between patients and healthy people, the distribution density of multi-frequency gaze points, and the priority grouping of the gaze hotspot area; the early screening data for Alzheimer's disease includes the stage change distribution of the number of target object gazes in dynamic task switching, the jump frequency distribution of the distractor gaze path, and the classification results of the gaze priority.

[0014] The present invention has been improved in that the specific steps of extracting the temporal and spatial coordinates of the gaze point from a visual saccade task performed by Alzheimer's patients, recording the directional changes of the jumping behavior in the temporal and spatial coordinates, and generating jumping behavior distribution data are as follows:

[0015] S101: Based on the temporal and spatial coordinates of the gaze points of Alzheimer's patients recorded by eye-tracking equipment during visual saccade tasks, identify the spatial relationship between the gaze points and the task targets, distractors, and blank areas in the visual saccade tasks, classify the association records between the gaze points and various area types, and generate spatial area distribution data of the gaze points;

[0016] S102: Based on the spatial distribution data of the fixation points, the number and duration of fixations on the target object, the distractors, and the blank area are counted, the time proportion of the fixation types is classified, the distribution characteristics of the fixation types are marked, and the fixation type time statistics are generated;

[0017] S103: Based on the temporal statistics of the gaze types, the spatial jump changes between gaze points are recorded, the angular characteristics of the jump directions are calculated, and according to the time series of the jump events, the change patterns of the jump directions are marked to generate jump behavior distribution data.

[0018] The present invention has been improved in that, based on the jump behavior distribution data, the direction, amplitude, and fixation duration of the jump events are grouped and arranged, and the position changes are recorded. Combined with the density of the fixation point distribution positions, the specific steps of generating a fluctuation characteristic diagram of the visual saccade task are as follows:

[0019] S201: Based on the jumping behavior distribution data, the jumping events are temporally segmented according to the time intervals and coordinate changes of the gaze points. The coordinate intervals are divided into equally spaced grids, and the fractal dimension of the jumping paths is calculated to quantify the complexity and variation of the jumping behaviors in the gaze paths, thereby establishing segmented trajectory records of the jumping events.

[0020] S202: Based on the jump event segmented trajectory record, extract the continuous change record of the gaze trajectory of the visual saccade task in chronological order, record the direction, amplitude and gaze time interval of each jump event in the gaze trajectory, and generate a gaze trajectory sequence feature record;

[0021] S203: Based on the gaze trajectory sequence feature records, the dynamic changes of the gaze trajectory within the task stage are analyzed, and according to the temporal change trend of the jump frequency, the transfer pattern of the gaze point in the gaze concentration area of ​​the visual saccade task, and the difference in the distribution of the gaze time within and outside the task stage, a fluctuation characteristic diagram of the visual saccade task is established.

[0022] The present invention has the following improvements: for calculating the fractal dimension of the jump path, the formula is adopted:

[0023]

[0024] Get the fractal dimension D f , represents the self-similarity of the path at multiple scales;

[0025] Where ∈ is the grid size, N(∈) is the number of grids covered by the jump path, T represents the temporal intensity of the fixation point in the jump path, log is used to map the number of grids covered by the jump path N(∈) and the change in grid scale ∈ to the logarithmic space, and log(1 / ∈) is the logarithm of the inverse of the grid scale, reflecting the change in the discretization scale of the path.

[0026] The present invention has been improved in that, based on the fluctuation characteristic diagram of the visual saccade task, the distribution of target points and non-target points in the gaze path is recorded, the continuity and jump changes of the gaze behavior are referred to, the return points and bifurcation points are marked, the number and length of path switches are counted, and the specific steps of generating the path characteristic data of the patient's memory search task are as follows:

[0027] S301: Based on the fluctuation characteristic diagram of the visual saccade task, extract the data source of the memory search phase in the visual saccade task by random clustering, record the starting point and ending point of the fixation path in the memory search phase, mark the spatial distribution positions of the target points and non-target points in the fixation path, and generate the target and non-target distribution data of the memory search phase;

[0028] S302: Based on the target and non-target distribution data of the memory search phase, extracting the gaze point position changes in the gaze path according to the time series of the gaze path, recording the direction changes and frequency of gaze point jump events, marking the return points and bifurcation points in the gaze path, and generating the memory search phase gaze path jump characteristic data;

[0029] S303: Based on the gaze path jump characteristic data of the memory search link, the number of gaze point switches and the path length in the gaze path are grouped and counted, the gaze behavior is classified according to the density of the intersection points of the gaze path, and the stage characteristics of the gaze path are integrated into the overall distribution of the task path to generate the patient's memory search task path characteristic data.

[0030] The present invention is improved in that, based on the path characteristic data of the patient's memory search task, the specific steps of recording the direction and magnitude of the deviation event and distinguishing the deviation categories according to the relative position change between the target point and the fixation point are as follows:

[0031] S401: Based on the patient's memory search task path characteristic data, the relative spatial positions of the target point and the gaze point in the gaze path during the memory search phase are recorded, the direction angle and amplitude of each offset event in the gaze path are marked, and spatial relationship data between the target point and the gaze point in the gaze path are generated;

[0032] S402: Based on the spatial relationship data between the target point and the gaze point in the gaze path, classify the gaze point offset events in the gaze path according to the directional consistency and magnitude of the offset events, annotate multiple distance offsets and directional distribution characteristics of the distance offset events, and generate classification data of the offset events in the gaze path;

[0033] S403: Based on the classification data of the offset events in the gaze path, the frequency distribution of each category of offset events is counted, the general direction and amplitude range of the offset events in the gaze path are marked, the statistical characteristics of the offset categories in the gaze path are summarized, and the path offset characteristic data in the patient search task is generated.

[0034] The present invention has the following improvements: collecting data from the memory search process of healthy people, comparing it with the path deviation characteristic data of the patient search task, marking hotspot areas and fixation points, analyzing the difference between the hotspot distribution of the patient jump path and the control group, and generating hotspot fixation feature data:

[0035] S501: Based on the collected data of the memory search phase of the healthy population, the data is compared with the path deviation characteristic data of the patient search task, the distribution of the gaze points in the gaze paths of the patients and the healthy population is marked, the number of gazes and path changes of the target points and non-target points are recorded and classified, and the comparison results of the gaze paths of the patients and the healthy population are generated;

[0036] S502: Based on the comparison results of the patient's gaze paths and those of the healthy subjects, the hotspot distribution of the patient and the healthy subjects is counted, the spatial positions and the number of gazes of the multi-frequency gaze points are marked, and the difference in the hotspot distribution in the patient's jump path and that of the healthy subjects is analyzed to generate the difference data of the hotspot distribution between the patient and the healthy subjects;

[0037] S503: Based on the difference data of the gaze hotspot distribution between the patient and the healthy group, the distribution center of the patient's gaze hotspot area is marked, and the coverage of the patient's hotspot area and the target point is counted to generate hotspot gaze feature data.

[0038] The present invention has been improved in that, based on the hotspot gaze feature data, the number and location of gazes on the target object and the distractor are recorded, the gaze path during the task switching phase is analyzed, the behavioral characteristics of the target gaze path are extracted, and early screening data for Alzheimer's disease is generated. The specific steps for applying the data to early screening for Alzheimer's disease are as follows:

[0039] S601: Based on the hotspot gaze feature data, the gaze point types of the gaze paths in the hotspot area are annotated by hierarchical residual analysis, the number of gazes and the spatial distribution of the target object and the distractors are recorded, and the hotspot area gaze point distribution characteristic data is generated according to the distribution characteristics of the gaze points in the hotspot area;

[0040] S602: Based on the hotspot area gaze point distribution characteristic data, recording the gaze path in the task dynamic switching stage, and according to the switching order and frequency of the target object and the interference object in the jump path, statistically analyzing the path priority area and jump frequency changes in the task switching stage to generate the gaze path characteristic data in the task dynamic switching stage;

[0041] S603: Based on the gaze path characteristic data during the dynamic switching phase of the task, the gaze priority deviation in the patient's gaze hotspot is marked, and the target point focusing frequency, jump direction and amplitude stability, and hotspot area coverage are recorded by task phase. The gaze behavior characteristics during the dynamic switching phase are extracted, and the patient's gaze behavior tendency in subsequent tasks is predicted to generate early screening data for Alzheimer's disease.

[0042] The present invention has the following improvements: for predicting the patient's gaze behavior tendency in subsequent tasks, the formula is used:

[0043]

[0044] Calculate the gaze behavior tendency value P t , which measures whether the patient is more inclined to fixate on the target point, distractor, or hotspot area in the subsequent task, and usually ranges from 0 to 1;

[0045] Among them, A i Represents the weight factor of the gaze point type in the current task stage, D′ i is the corrected duration of the fixation point, F i is the jump frequency of the fixation point, and n is the total number of fixations recorded in the current task.

[0046] Compared with the prior art, the advantages and positive effects of the present invention are:

[0047] In the present invention, by extracting the time and space coordinates of the gaze point and combining it with the change in the direction of the jumping behavior, a comprehensive characterization of the dynamic laws of the gaze behavior is achieved, providing high-dimensional support for the detailed analysis of the patient's gaze behavior during the execution of the task. By constructing the jump event distribution, trajectory dynamic changes and complexity quantification of the gaze path, the offset characteristics, jump laws and path fractal dimensions in the gaze behavior are accurately revealed, providing a quantitative description of abnormal behavior for screening. Through the distribution statistics of target points and non-target points and the marking of return points and bifurcation points, the granularity of the memory search task path analysis is significantly improved, making the behavioral differences inside and outside the task stage clearer. Hot spot area analysis combines the priority areas of the gaze path with the task switching rules, and provides systematic data support for the comparative analysis of the patient's gaze behavior characteristics in complex tasks with healthy groups. By extracting behavioral feature data and dynamic change trends, the patient's gaze hot spot distribution and the abnormalities in the task switching stage are fully captured, providing data support for early clinical intervention measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of an early screening method for Alzheimer's disease is proposed for the present invention;

[0049] Figure 2 This is a detailed flow chart of step S1 of the present invention;

[0050] Figure 3 This is a schematic diagram of a detailed process of step S2 of the present invention;

[0051] Figure 4 This is a detailed flow chart of step S3 of the present invention;

[0052] Figure 5 This is a detailed flow chart of step S4 of the present invention;

[0053] Figure 6 This is a detailed flow chart of step S5 of the present invention;

[0054] Figure 7 This is a detailed flow chart of step S6 of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0056] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0057] See also Figure 1 The present invention provides a technical solution: an early screening method for Alzheimer's disease, comprising the following steps:

[0058] S1: Extract the temporal and spatial coordinates of the gaze point from a visual saccade task performed by patients with Alzheimer's disease, record the directional changes of the jumping behavior in temporal and spatial coordinates, and generate jumping behavior distribution data;

[0059] S2: Based on the jump behavior distribution data, the direction, amplitude and fixation duration of the jump events are grouped and arranged, and the position changes are recorded. Combined with the density of the fixation point distribution position, a fluctuation characteristic map of the visual saccade task is generated;

[0060] S3: Based on the fluctuation characteristic diagram of the visual saccade task, the distribution of target and non-target points in the gaze path is recorded. Referring to the continuity and jump changes of gaze behavior, the return points and bifurcation points are marked, and the number and length of path switches are counted to generate the path characteristic data of the patient's memory search task;

[0061] S4: Based on the path characteristic data of the patient's memory search task, according to the relative position change between the target point and the fixation point, the direction and magnitude of the deviation event are recorded and the deviation category is distinguished to generate the path deviation characteristic data in the patient's search task;

[0062] S5: Collect data from the memory search phase of healthy subjects, compare it with the path deviation characteristic data of the patient search task, mark the hotspot areas and fixation points, analyze the differences in the hotspot distribution of the patient jump path and the control group, and generate hotspot fixation feature data;

[0063] S6: Based on the hotspot gaze feature data, record the number and location of gazes on the target object and the distractor, analyze the gaze path during the task switching phase, extract the behavioral characteristics of the target gaze path, and generate early screening data for Alzheimer's disease, which is applied to early screening for Alzheimer's disease.

[0064] Jump behavior distribution data include time records of fixation points, multidimensional position distribution of jump directions, and gaze duration data. Fluctuation characteristic diagrams of visual saccade tasks include jump frequency change distribution at each stage of the gaze trajectory, dynamic fluctuation range of jump direction consistency, and trajectory distribution density information during the gaze time period. Path characteristic data of patient memory search tasks include gaze coverage distribution of target points, jump behavior statistics of non-target points, and the number and positional relationship of return points in the path. Path deviation characteristic data in patient search tasks include the distance variation range between target points and fixation points, directional angle distribution of deviation events, and frequency statistics of deviation amplitudes. Hotspot gaze feature data include coverage differences of fixation hotspot areas between patients and healthy subjects, distribution density of multi-frequency fixations, and priority grouping of fixation hotspot areas. Early screening data for Alzheimer's disease include stage-change distribution of target object fixations during dynamic task switching, jump frequency distribution of distractor gaze paths, and classification results of gaze priority.

[0065] See also Figure 2 ,From the visual saccade task participated by Alzheimer's patients, the time and space coordinates of the fixation point are extracted, the direction changes of the jumping behavior in the time and space coordinates are recorded, and the specific steps for generating the jumping behavior distribution data are as follows:

[0066] S101: Based on the temporal and spatial coordinates of the gaze points of Alzheimer's patients recorded by eye-tracking equipment during visual saccade tasks, identify the spatial relationship between the gaze points and the task targets, distractors, and blank areas in the visual saccade tasks, classify the association records between the gaze points and various area types, and generate spatial area distribution data of the gaze points;

[0067] First, the raw eye movement data is cleaned, removing incomplete data records and anomalous coordinate values ​​that deviate from the primary task area. For example, if a fixation point's distance from the center of the primary task area exceeds a certain threshold, the fixation record is discarded. The remaining data is then sorted chronologically to construct complete temporal and spatial trajectories. Clustering is used to classify fixations into target objects, distractors, and blank areas. The Euclidean distance from the fixation point to the region center is used as the primary classification criterion. The physical dimensions and boundary data of the task area are also used to adjust the boundaries. For example, when analyzing a task with three target regions and two distractor regions, the density of fixations within each region can be assessed. The classification results can be visually inspected and fixations within the fuzzy regions within the boundaries can be reallocated. Finally, the fixations and region types are classified and labeled, generating spatial region distribution data. Cluster analysis is performed using the K-Means method in Scikit-learn using Python tools. Matplotlib is used to generate a visual distribution plot, and the classification of data points within the fuzzy boundaries is manually adjusted based on the results.

[0068] S102: Based on the spatial distribution data of the fixation points, the number and duration of fixations on the target object, distractors, and blank areas are counted, the time proportion of the fixation types is classified, the distribution characteristics of the fixation types are marked, and the fixation type time statistics are generated;

[0069] By building a time series matrix, we can obtain the dwell time and frequency of each fixation point in different areas. Specifically, we extract the start and end times of fixations from timestamps, calculate the duration of each fixation, accumulate the total time within the area, and count the frequency. For example, for fixations in a target area, we record the dwell time of each fixation point in that area and calculate the total number of fixations. We then use this data to generate a fixation time distribution table by area type. We then analyze the temporal distribution characteristics of each area, visually presenting the fixation time and frequency in the form of a time series plot. Finally, we note the differences in the temporal distribution characteristics between the target area and the distractor area. For example, a patient's total fixation time in the target area may be significantly lower than that of a healthy control group. This characteristic data analysis can further reveal abnormalities in the patient's fixation behavior during task completion. We use Excel to import the fixation data to generate a time distribution table, and use ggplot2 in R to plot the fixation time series plot. A bar chart of the regional fixation time ratio further visualizes the results.

[0070] S103: Based on the temporal statistics of gaze types, record the spatial jump changes between gaze points, calculate the angular characteristics of the jump direction, and mark the change pattern of the jump direction according to the time series of jump events to generate jump behavior distribution data;

[0071] First, the coordinates of adjacent fixations are interpolated to obtain the spatial change vector of the jump event. For example, the length and direction of the displacement from one fixation point on the target object to the next fixation point on the distractor object are recorded. Next, the distribution of directional angles is analyzed, and the jump direction of the fixation point is divided into multiple intervals according to the angle. For example, 360 degrees is divided into eight 45-degree intervals. By statistically analyzing the frequency distribution within each interval, the main directional trends of the jump behavior are analyzed. Further, according to the jump frequency and directional change distribution, abnormal high-frequency directional areas or disordered jump areas are marked. For example, the jump path of a patient frequently jumps to the distractor and lacks obvious patterns, which is significantly different from the distribution of the target object as the main jump direction in the healthy control group. These characteristic data can provide effective clues for the early identification of Alzheimer's disease. The directional angle of each jump event is calculated using MATLAB's angle function. The frequency is counted by matching the directional angle with the interval boundary. The MATLAB bar function is called to generate a histogram of the directional angle distribution to intuitively display the directional jump characteristics.

[0072] See also Figure 3 Based on the jump behavior distribution data, the direction, amplitude, and fixation duration of the jump events are grouped and arranged, and the position changes are recorded. Combined with the density of the fixation point distribution position, the specific steps for generating the fluctuation characteristic map of the visual saccade task are as follows:

[0073] S201: Based on the jumping behavior distribution data, the jumping events are temporally segmented according to the time intervals and coordinate changes of the fixation points. The fractal dimension of the jumping path is calculated by dividing the coordinate interval into equally spaced grids. The complexity and variation of the jumping behavior in the fixation path are quantified, and a segmented trajectory record of the jumping event is established.

[0074] Jump events are temporally segmented based on the time interval and coordinate changes of the fixation points. For example, the time interval of a jump path from point A (2, 3) to point B (5, 6) is 0.5 seconds, its direction is the vector angle from A to B, its magnitude is the Euclidean distance from point A to point B, and the fixation duration is 0.2 seconds at point A and 0.3 seconds at point B. The direction, magnitude, and duration of all paths are converted into discretized temporal and spatial trajectory data, which serve as the basis for fractal dimension calculation. The grid of jump paths is generated based on the coordinate range of the fixation points. First, the maximum and minimum coordinate values ​​of the task area are extracted. The coordinate interval is then divided into equally spaced grids according to the set grid size ∈. For example, in a 100×100 task area, when ∈ = 10, each grid has a side length of 10 units, and the task area is divided into a 10×10 grid matrix, with each grid corresponding to a unique spatial index. The path data is projected onto the grid index to determine the number of grids covered, N(∈). For example, point A (15, 25) and point B (45, 65) in the jump path fall on grids (2, 3) and (5, 7) respectively, and the jump path between the two points covers the index ranges of these grids.

[0075] To calculate the fractal dimension of the jump path, the formula is used:

[0076]

[0077] Get the fractal dimension D f , represents the self-similarity of the path at multiple scales;

[0078] Among them, D fUsed to quantify the complexity of jump paths, ∈ is the grid size, representing the size of the grid during path discretization. It is typically generated by setting a fixed grid spacing. An appropriate value for ∈ can be selected based on the task area size and resolution of the experimental scenario. N(∈) is the number of grid cells covered by the jump path, measuring the spatial complexity of the path at a specific grid size ∈. It is obtained by counting the number of grid cells in the discretized grid that contain jump path data. T is the sum of fixation durations, representing the temporal intensity of fixations within the jump path. It is obtained by summing the time intervals between all fixations. log is used to map the number of grid cells covered by the jump path, N(∈), and the changes in grid size ∈ into logarithmic space, facilitating linear processing of data at different orders of magnitude, thereby calculating the fractal dimension of the path. The logarithmic operation smooths high-order differences in data, making the fitting more robust. log(1 / ∈) represents the logarithm of the independent variable divided by 1 and the grid size ∈. It means taking the logarithm of the inverse of the grid size, which can reflect changes in the scale of path discretization.

[0079] For example, if the jump path data is as follows: grid size ∈: 0.1, 0.01, 0.001; number of grids N(∈): 50, 500, 5000; total fixation duration T = 10 seconds; log is the natural logarithm (base e), calculate:

[0080] log(N(∈)·T)=log(50·10)=2.698, log(500·10)=3.698, log(5000·10)=4.698

[0081] log(1 / ∈)=log(1 / 0.1)=1, log(1 / 0.01)=2, log(1 / 0.001)=3

[0082] Fitting slope:

[0083]

[0084] This result shows that the fractal dimension D f =1, fractal dimension D f The value range of is usually between 1 and 2. The closer the value is to 2, the more complex the jump path is and the wider the coverage is. The closer the value is to 1, the more linear the path is. For example, if the D f =1.8, indicating that the path segment presents high complexity and dispersion, while D f=1.2 indicates that the path tends to be simple and has strong directionality. Based on the local changes in the fractal dimension, abnormal features in the jump path are extracted. For example, if the fractal dimension of a certain path segment is significantly higher than that of other path segments, it can be marked as a complex jump segment, and the distribution characteristics of the gaze points in this segment can be further analyzed; if the fractal dimension gradually decreases, it can be marked as a concentrated jump segment, indicating jumping behavior directed to the target area. The jump path is divided into multiple segments according to temporal and spatial changes. Each segment corresponds to a fractal dimension value. The jump direction, amplitude, and gaze duration within the segment are recorded to generate a trajectory record of the jump event. For example, a trajectory segment from time 0 to 2 seconds has a direction of 45°, an amplitude of 10 units, and a fractal dimension of 1.7; the next trajectory segment from time 2 to 4 seconds has a direction of 90°, an amplitude of 5 units, and a fractal dimension of 1.3. Through this segmentation information, the jump behavior characteristics in the gaze path can be fully described. Combined with the distribution of fractal dimensions, the jump trajectory is divided into high-complexity jumps (such as fractal dimension D f >1.5), low complexity jumps (such as D f ≤1.5) and directional concentrated characteristic jumps, generating segmented trajectory records of jumping events according to classification, and providing basic data support for subsequent behavioral feature analysis.

[0085] S202: Based on the jump event segmented trajectory records, extract the continuous change records of the gaze trajectory of the visual saccade task in chronological order, record the direction, amplitude and gaze time interval of each jump event in the gaze trajectory, and generate a gaze trajectory sequence feature record;

[0086] Gaze trajectories were organized into a continuous record of changes in chronological order. The direction, amplitude, and gaze interval of each jump event were extracted. The timestamp information in the segmented trajectories was sorted and the jump order was annotated. Each jump event was connected according to the start and end points of the time axis to form a continuous time series record. Direction data was directly obtained from the segmented trajectories, amplitude data was combined with the spatial position changes recorded in the segmented trajectories, and the gaze interval was calculated by the difference between the start and end times. Each jump event was recorded in the following format: time period (e.g., 0-2 seconds), direction (e.g., 45°), amplitude (e.g., 10 units), and gaze interval (e.g., 2 seconds). By continuously splicing each segment record, a complete sequence of gaze trajectories was constructed, and this sequence was organized into a feature list segmented by time.

[0087] S203: Analyzing the dynamic changes of the gaze trajectory within the task phase based on the sequence feature records of the gaze trajectory, and establishing a fluctuation characteristic diagram of the visual saccade task based on the temporal trend of the jump frequency, the shift pattern of the gaze point in the focus area of ​​the visual saccade task, and the difference in the distribution of the gaze time within and outside the task phase;

[0088] The dynamic changes in gaze trajectories during the task phase were extracted. The phases were divided into time segments, and the gaze trajectories were segmented. The jump frequency, direction distribution, and amplitude of each segment were extracted for feature extraction. The relationship between the total amount of fixation time and the jump frequency within each segment was used to analyze the regularity of gaze behavior. Data segmentation and statistics were implemented using MATLAB tools. The readtable function was used to import the gaze trajectory sequence feature record file and segment it by timestamp. The jump frequency of each phase was extracted, and the histcounts function was used to generate a phase frequency distribution table. The spatial distribution of fixations in the gaze trajectories was extracted. The focus areas and inter-regional transition paths were recorded by region number. The frequency of fixation transitions from one region to another during each phase was counted to generate a region transition matrix. The rows in the matrix represent the starting regions, the columns represent the target regions, and the values ​​represent the frequency of region transitions. The region transition matrix generated using the accumarray function in MATLAB visually reflects the regularity of inter-regional gaze transitions. The distribution characteristics of fixation time within the task phase were compared with those outside of the phase to identify differences in fixation time within and outside of the task phase. Finally, a fluctuation characteristic plot was generated, showing the trend of jump frequency, the shift pattern of focus areas, and the difference in the distribution of fixation time within and outside of the task phase.

[0089] See also Figure 4 Based on the fluctuation characteristic diagram of the visual saccade task, the distribution of target points and non-target points in the gaze path is recorded. Referring to the continuity and jump changes of gaze behavior, the return points and bifurcation points are marked, and the number and length of path switches are counted. The specific steps for generating the path characteristic data of the patient's memory search task are as follows:

[0090] S301: Based on the fluctuation characteristic diagram of the visual saccade task, extract the data source of the memory search phase in the visual saccade task by random clustering, record the starting point and ending point of the fixation path in the memory search phase, mark the spatial distribution positions of the target points and non-target points in the fixation path, and generate the target and non-target distribution data of the memory search phase;

[0091] The data source of the memory search link in the visual scanning task is extracted by random clustering, and the patient's gaze path data in the task is imported into a cluster analysis tool. For example, the Scikit-learn library in Python is used to perform clustering by calling the KMeans method. The number of clusters is set based on the actual number of task targets. The gaze points are divided into multiple clusters according to the Euclidean distance of the spatial position. Each cluster represents a gaze area. The clustering results are manually corrected to exclude non-target areas and are finally marked as target points or non-target points. Combined with the starting and ending point data of the gaze path, a time series record is generated to record the spatial distribution of target points and non-target points in each gaze path. For example, the proportion of time a patient's gaze path stays in the target point cluster is 70%, and the proportion of time it stays in the non-target point cluster is 30%. This distribution data can reflect the patient's ability to focus on the target point during the memory search process.

[0092] S302: Based on the target and non-target distribution data of the memory search phase, the gaze point position changes in the gaze path are extracted according to the time series of the gaze path, the direction changes and frequency of the gaze point jump events are recorded, and the return points and bifurcation points in the gaze path are marked to generate the memory search phase gaze path jump characteristic data;

[0093] The continuous position changes of the gaze point are extracted according to the time series of the gaze path, and the jump events of the gaze point are recorded. The jump direction characteristics are extracted by calculating the direction changes of adjacent gaze points. The direction angle difference is calculated using the atan2 function in MATLAB. By inputting the coordinates of two gaze points (x1, y1) and (x2, y2), the vector angle formed by the two points is calculated. The output direction difference is directly stored in a data table. At the same time, the frequency of jump events is counted, and the gaze points with a direction mutation frequency exceeding a certain threshold are marked as return points. For example, the return points of a patient account for 20% of the total number of gaze points, reflecting the instability of their jumping behavior. Bifurcation points are marked by counting the frequency of events in which a single gaze point jumps to multiple directions. The bifurcation point-dense areas are extracted. For example, in a certain section of the path, the bifurcation points of a patient are concentrated in a specific target area. The bifurcation point distribution is combined to evaluate the patient's jumping bias in the task.

[0094] S303: Based on the gaze path jump characteristic data of the memory search phase, the number of gaze point switches and the path length in the gaze path are grouped and counted, the gaze behavior is classified according to the density of the gaze path intersections, and the stage characteristics of the gaze path are integrated into the overall distribution of the task path to generate the patient's memory search task path characteristic data;

[0095] The gaze paths were grouped into stages, and the number of gaze point switches in each stage was counted. The path length was calculated based on the sequence of gaze points in the time period. The distribution of intersections was counted in the dense gaze point area, and the gaze path crossing behavior was divided into high-density paths and low-density paths. The path complexity was assessed by the segmented jump frequency and direction changes. For example, the jump frequency of a patient in the high-density area accounted for 60%, while that of the healthy control group was only 30%, reflecting the excessive dispersion of the patient's jumping behavior in the task. The gaze paths were divided into behavioral patterns of different complexities based on the number and distribution location characteristics of the intersections. The time period and intersection data were integrated to generate the overall distribution of the task path.

[0096] See also Figure 5 Based on the path characteristic data of the patient's memory search task, the specific steps for generating the path deviation characteristic data in the patient's search task are as follows:

[0097] S401: Based on the patient's memory search task path characteristic data, the relative spatial positions of the target point and the gaze point in the gaze path during the memory search phase are recorded, the direction angle and amplitude of each offset event in the gaze path are annotated, and spatial relationship data between the target point and the gaze point in the gaze path are generated;

[0098] The gaze path data was processed using the pandas and numpy libraries in Python. The difference between the spatial coordinates of the target point and the spatial coordinates of each gaze point was calculated, and the position differences in the x and y directions were extracted and stored as two columns of data. The distance from the gaze point to the target point was then calculated using the Euclidean distance formula and stored in a spatial relationship data file. On this basis, the direction angle calculation formula was used in combination with Python's math.atan2 function to calculate the direction angle of the gaze point offset event. The offset events were annotated based on the calculated amplitude. For example, the proportion of offset events with a direction angle of 30° in a certain path was 20%, indicating that the patient had a regular offset in a specific direction. Finally, the spatial relationship data of the target point and the gaze point in the gaze path were generated.

[0099] S402: Based on the spatial relationship data between the target point and the gaze point in the gaze path, classify the gaze point offset events in the gaze path according to the directional consistency and magnitude of the offset events, annotate multiple distance offsets and directional distribution characteristics of the distance offset events, and generate classification data of the offset events in the gaze path;

[0100] The deviation events in the gaze path were classified according to their directional consistency and amplitude. The directional deviation consistency ratio of each segment of the gaze path was statistically analyzed by segmentation. The directional deviation of the gaze path was classified and statistically analyzed using Python's groupby function. The amplitude was divided into short-distance deviation (less than a certain threshold) and long-distance deviation (greater than the threshold). Each deviation event was labeled based on the directional distribution characteristics. For example, in the data of a certain patient, the frequency of long-distance deviation events was higher than that of the healthy control group, reflecting the lack of stability during the task execution. Finally, the classification data of the deviation events in the gaze path was generated.

[0101] S403: Based on the classification data of gaze path deviation events, the frequency distribution of each category of deviation events is counted, the general direction and amplitude range of the deviation events in the gaze path are marked, the statistical characteristics of the deviation categories in the gaze path are summarized, and the path deviation characteristic data in the patient search task is generated;

[0102] The frequency distribution of each category of deviation events was statistically analyzed. The frequencies of all deviation events in the gaze path were summarized according to their classification results and further subdivided by combining the direction and amplitude range. The frequency histogram of each deviation event was drawn using the Python matplotlib library, and the general direction range of the deviation events was marked. For example, the deviation events of a patient were concentrated in the direction of 0° to 45°, and the amplitude range was 75% of the short-distance deviation. The data of the healthy control group was more evenly distributed. The deviation characteristics of the patients were extracted through comparative analysis. Combined with the statistical characteristics of the frequencies of different categories, the deviation category information in the gaze path was summarized as the patient search task path deviation characteristic data.

[0103] See also Figure 6 ,Collect the data of memory search link of healthy people, compare it with the path deviation characteristic data of patients' search task, mark the hotspot areas and fixation points, analyze the differences between the hotspot distribution of patients' jump paths and the control group, and generate the hotspot fixation feature data in the following steps:

[0104] S501: Based on the collected data from the memory search phase of the healthy population, the data are compared with the path deviation characteristic data of the patient search task, the distribution of the gaze points in the gaze paths of the patients and the healthy population are marked, the number of gazes and path changes of the target points and non-target points are recorded and classified, and the comparison results of the gaze paths of the patients and the healthy population are generated;

[0105] The gaze path data of patients and healthy people were extracted and imported into Python's pandas and numpy libraries for data preprocessing. Pandas was used to filter out the task target-related gaze points and non-target gaze points, and the starting and ending points of each gaze path were recorded. The number of gazes on the target point and the number of gazes on the non-target point were counted separately, and the data were integrated into two groups: target gaze video data and non-target gaze video data. Combined with the sequence characteristics of the gaze path, the gaze distribution characteristics of patients and healthy people were annotated, and the distribution diagrams of the two groups of data were drawn using matplotlib. For example, in a certain test stage, the proportion of target point gaze time in healthy people was 75%, while that of patients was only 50%, reflecting the patients' attention deviation problem.

[0106] S502: Based on the comparison results of the patient's and healthy subjects' gaze paths, the hotspot distribution of the patient and healthy subjects is counted, the spatial position and the number of gazes of the multi-frequency gaze points are marked, and the difference in the hotspot distribution in the patient's jump path and that of the healthy subjects is analyzed to generate the difference data of the hotspot distribution between the patient and the healthy subjects;

[0107] The hotspot distribution of patients and healthy people was statistically analyzed. The DBSCAN method in Python's scikit-learn library was used for spatial clustering. The coordinates of each fixation point were input, and the hotspot areas were divided according to the Euclidean distance parameter. The areas with high-frequency fixations were identified, and the center coordinates and fixation frequency of each hotspot area were extracted. The hotspot area positions were marked by drawing a two-dimensional spatial distribution map. The fixation proportion of each hotspot area was calculated using pandas. For example, the fixation time of a patient in a hotspot area accounted for 65%, while that of healthy people was only 20%. The differences in fixation behavior between patients and healthy people were analyzed based on the hotspot distribution characteristics, and the difference data of fixation hotspot distribution between patients and healthy people were generated.

[0108] S503: Based on the difference data of the gaze hotspot distribution between patients and healthy people, the distribution center of the patient's gaze hotspot area is marked, and the coverage of the patient's hotspot area and the target point is counted to generate hotspot gaze feature data;

[0109] The distribution center of the patient's gaze hotspot area is marked. Combined with the location data of the target point, a scatter plot is drawn using the Python matplotlib library to indicate the relative position of the hotspot area and the target point. The patient's gaze tendency at the target point is assessed by counting the number of hotspot fixations within the target point coverage area. For example, in a patient's hotspot area, the fixation ratio within the target point coverage area is 35%, while that of healthy people is 80%. Combined with the distribution data, the patient's gaze hotspot characteristics are quantitatively evaluated. At the same time, the spatial overlap rate between the hotspot and the target point is calculated. The spatial overlap rate between the hotspot and the target point can be obtained by performing a spatial overlap analysis on the coverage area of ​​the hotspot area and the target point. First, based on the center point coordinates and radius of the hotspot area, the geometric shape of the hotspot area is created using the shapely library in Python. Then, combined with the geometric range of the target point, the intersection function in shapely is used to obtain the overlapping area of ​​the hotspot area and the coverage area of ​​the target point. The ratio of the overlapping area to the coverage area of ​​the target point is calculated. For example, if the overlapping area of ​​the hotspot area and the target point is 15 square units, and the total coverage area of ​​the target point is 50 square units, the overlap rate is 30%. This value reflects the degree to which the patient's gaze hotspot area is concentrated on the target point. The patient's gaze hotspot shift characteristics can be further analyzed by comparing multiple data sets.

[0110] See also Figure 7 Based on the hotspot gaze feature data, the number and location of gazes on the target and distractors are recorded, the gaze path during the task switching phase is analyzed, the behavioral characteristics of the target gaze path are extracted, and early screening data for Alzheimer's disease is generated. The specific steps for applying it to early screening for Alzheimer's disease are as follows:

[0111] S601: Based on the hotspot gaze feature data, the types of gaze points in the gaze path in the hotspot area are annotated through hierarchical residual analysis, the number of gazes and spatial distribution of the target object and the distractor are recorded, and the distribution characteristics of the gaze points in the hotspot area are generated according to the distribution characteristics of the gaze points in the hotspot area;

[0112] First, by collecting information on the patients' gaze paths during a visual saccade task, the fixations were overlaid with the boundaries of the hotspot areas. Spatial analysis was performed using ArcGIS to identify the specific locations of the target and distractors. The distribution of fixations on the target and distractors within the hotspot areas was then extracted. Hierarchical residual analysis was then used to further classify the fixations. The specific process of the hierarchical residual analysis involved using SPSS to group fixations according to the attributes of the target, distractors, and blank areas. The model variables were set as the spatial location and duration of the fixations. The difference between each group of fixations and the theoretical model was calculated and quantified as residual values. A significance test of the residuals was performed to identify fixation areas that deviated from the theoretical distribution, thereby identifying abnormal distributions within the hotspot areas. After the analysis was completed, the results were converted into classification layers, and visualization software such as Tableau was used to display the differences in the number of fixations and spatial distribution of the target and distractors.

[0113] S602: Based on the hotspot area gaze point distribution characteristic data, record the gaze path during the task dynamic switching stage, and according to the switching order and frequency of the target object and the distractor in the jump path, calculate the path priority area and jump frequency changes during the task switching stage to generate the gaze path characteristic data during the task dynamic switching stage;

[0114] First, gaze paths during the dynamic switching phase were extracted and spatially visualized using QGIS. The spatial distribution of fixations and jump paths was converted into intuitive layers. Hotspot locations were then annotated to clarify the distribution of each gaze path during the dynamic task switching phase. During the analysis, the Python pandas and matplotlib modules were used to perform a time series decomposition of the fixation switch sequence for the target and distractors, extracting jump events during path switching. To analyze the changes in path priority areas and jump frequency during the task switching phase, Origin software was used to perform time series statistics on the fixation point data. The frequency of fixations in different time intervals was correlated with their spatial distribution, and jump frequency maps within hotspot areas were generated. Finally, by integrating the fixation paths, the switch sequence and frequency characteristics of the target and distractors, and combining them with geospatial analysis tools, the characteristic data of the gaze paths during the dynamic switching phase were generated.

[0115] S603: Based on the gaze path characteristic data during the dynamic task switching phase, the deviation of the patient's gaze priority area in the gaze hotspot is marked. The target point focusing frequency, jump direction and amplitude stability, and hotspot area coverage are recorded by task stage. The gaze behavior characteristics during the dynamic switching phase are extracted, and the patient's gaze behavior tendency in subsequent tasks is predicted to generate early screening data for Alzheimer's disease.

[0116] During the dynamic switching phase, deviations from the priority regions within the gaze hotspots were annotated by integrating the distribution of hotspots within the patient's gaze path and gaze records within the task phase. The specific process involved first defining the priority region as the portion of the hotspot with a high density of fixations. Then, based on the gaze path records within the task phase, fixations that deviated from the center of the hotspot were screened. Next, the frequency of target fixation was recorded by task phase, including the number and duration of fixations made by the patient at each phase. Jump direction and amplitude stability were determined by analyzing jump events between the patient's fixations, specifically by counting the range of jump direction changes and the degree of amplitude fluctuation. Regarding hotspot coverage, the degree of match between the patient's fixation hotspot and the task target was assessed based on the spatial overlap between fixations and target points within the hotspot. Combined with these data, these features were used to extract features of the patient's gaze behavior during the dynamic switching phase, ultimately forming a complete description of how the patient's gaze behavior varied across the different task phases.

[0117] To predict the patient's gaze behavior tendency in the subsequent task, the formula is used:

[0118]

[0119] Calculate the gaze behavior tendency value P t , which measures whether the patient is more inclined to fixate on the target point, distractor, or hotspot area in the subsequent task, and usually ranges from 0 to 1;

[0120] Among them, A i It represents the weight factor of the fixation point type in the current task stage. This value is determined by experimental analysis and obtained by comparing the fixation preferences of healthy people and patients in the task. i The corrected duration of the fixation point is expressed in seconds. The corrected duration is adjusted by combining the patient's standard fixation duration with the actual fixation duration of the task phase. The correction formula is: D' i =DL i +k·(T′ norm -T′ act ), DL i is the original duration of the fixation point, obtained directly from the eye tracking device. The timestamp of the fixation point, T′ norm is the standard fixation time, referring to the historical average fixation time of healthy people, T′ actis the actual fixation time, which is recorded by the patient's duration at the fixation point. k is the adjustment coefficient, which depends on the experimental correction results. For example, in a certain experiment, the task data of 50 subjects were fitted and corrected. The initial setting k = 1 was used. Through gradual adjustment, it was found that when k = 1.25, the model's prediction error of the target point focusing frequency was minimized, and the fitting results of the jump amplitude stability were consistent with the experimental observations. Therefore, k = 1.25 was used as the final adjustment coefficient for subsequent analysis. i It represents the jump frequency of the gaze point, which is the number of times it jumps from other gaze points to the current point per unit time. This data is obtained by counting the event records of the gaze path data during the dynamic switching phase of the task. n represents the total number of gaze points recorded in the current task, and is obtained by counting the number of gaze path records.

[0121] For example, if a task contains the following gaze point data: Gaze point 1 (target point): A1 = 1.0, DL1 = 3s, T′ norm =4s, T′ act =2s, F1=5; fixation point 2 (distractor): A2=0.5, DL2=2s, T′ norm =3s, T′ act =2.5s, F2=3; fixation point 3 (hotspot): A3=0.8, DL3=4s, T′ norm =5s, T′ act =3s, F3=4.

[0122] Corrected duration calculation:

[0123] For fixation point 1: D'1 = 3 + k (4 - 2); for fixation point 2: D'2 = 2 + k (3 - 2.5); for fixation point 3: D'3 = 4 + k (5 - 3). Assuming k = 0.5, the calculation results are: D'1 = 3 + 0.5 2 = 4 seconds; D'2 = 2 + 0.5 0.5 = 2.25 seconds; D'3 = 4 + 0.5 2 = 5 seconds.

[0124] Substitute into the formula:

[0125]

[0126] The results show that the patient's gaze behavior tendency index in subsequent tasks is higher, close to the distribution of target points and hot spots. Combined with this tendency value, it can further predict the patient's ability to focus on the target point, thereby providing a reference for the evaluation of patients' cognitive function changes in early screening of Alzheimer's disease.

[0127] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for early screening of Alzheimer's disease, characterized in that: The following steps are involved: Extract the temporal and spatial coordinates of the gaze point from a visual saccade task performed by patients with Alzheimer's disease, record the directional changes of the jumping behavior in temporal and spatial coordinates, and generate jumping behavior distribution data; Based on the jump behavior distribution data, the direction, amplitude and fixation duration of the jump events are grouped and arranged, and the position changes are recorded. Combined with the density of the fixation point distribution position, a fluctuation characteristic diagram of the visual saccade task is generated; Based on the fluctuation characteristic diagram of the visual saccade task, the distribution of target points and non-target points in the gaze path is recorded, the continuity and jump changes of the gaze behavior are referred to, the return points and bifurcation points are marked, the number and length of path switches are counted, and the path characteristic data of the patient's memory search task is generated; Based on the path characteristic data of the patient's memory search task, according to the relative position change between the target point and the fixation point, the direction and magnitude of the deviation event are recorded and the deviation category is distinguished to generate the path deviation characteristic data in the patient's search task; Collect data from the memory search phase of healthy subjects, compare it with the path deviation characteristic data of the patient search task, annotate hotspot areas and fixation points, analyze the differences in the hotspot distribution of the patient jump path and the control group, and generate hotspot fixation feature data; Based on the hotspot gaze feature data, the number and position of gazes on the target object and the distractor are recorded, the gaze path during the task switching phase is analyzed, the behavioral characteristics of the target gaze path are extracted, and early screening data for Alzheimer's disease is generated for application in early screening for Alzheimer's disease.

2. The method for early screening of Alzheimer's disease according to claim 1, characterized in that: The jumping behavior distribution data includes the time record of the gaze point, the multi-dimensional position distribution of the jump direction and the gaze time duration data. The fluctuation characteristic diagram of the visual scanning task includes the jump frequency change distribution of each stage in the gaze trajectory, the dynamic fluctuation range of the jump direction consistency and the trajectory distribution density information of the gaze time period. The patient memory search task path characteristic data includes the gaze coverage distribution of the target point, the jump behavior statistics of the non-target point and the number and position relationship of the return points in the path. The path offset characteristic data in the patient search task includes the distance change range between the target point and the gaze point, the direction angle distribution of the offset event and the frequency statistics of the offset amplitude. The hotspot gaze feature data includes the coverage difference of the gaze point hotspot area between patients and healthy people, the distribution density of multi-frequency gaze points and the priority grouping of the gaze hotspot area. The early screening data for Alzheimer's disease includes the stage change distribution of the number of target object gazes in dynamic task switching, the jump frequency distribution of the distractor gaze path and the classification results of the gaze priority.

3. The method for early screening of Alzheimer's disease according to claim 1, characterized in that: The specific steps for extracting the temporal and spatial coordinates of the gaze point from a visual saccade task performed by patients with Alzheimer's disease, recording the directional changes of the saccade behavior in the temporal and spatial coordinates, and generating saccade behavior distribution data are as follows: Based on the temporal and spatial coordinates of the gaze points of Alzheimer's patients recorded by eye movement equipment during visual saccade tasks, the authors identify the spatial relationship between the gaze points and the task targets, distractors, and blank areas in the visual saccade tasks, classify the association records between the gaze points and various area types, and generate spatial area distribution data of the gaze points. Based on the spatial distribution data of the fixation points, the number and duration of fixations on the target object, the distractors, and the blank area are counted, the time proportion of the fixation types is classified, the distribution characteristics of the fixation types are marked, and the statistical results of the fixation type time are generated; Based on the temporal statistics of the gaze types, the spatial jump changes between gaze points are recorded, the angular characteristics of the jump directions are calculated, and the change patterns of the jump directions are marked according to the time series of the jump events to generate jump behavior distribution data.

4. The method for early screening of Alzheimer's disease according to claim 1, wherein: Based on the jump behavior distribution data, the direction, amplitude, and fixation duration of the jump events are grouped and arranged, and the position changes are recorded. Combined with the density of the fixation point distribution position, the specific steps for generating the fluctuation characteristic diagram of the visual saccade task are as follows: Based on the jumping behavior distribution data, the jumping events are temporally segmented according to the time intervals and coordinate changes of the fixation points. The fractal dimension of the jumping path is calculated by dividing the coordinate interval into equally spaced grids, quantifying the complexity and variation of the jumping behavior in the fixation path, and establishing a segmented trajectory record of the jumping events. Based on the jump event segmented trajectory record, extracting the continuous change record of the gaze trajectory of the visual saccade task in chronological order, recording the direction, amplitude and gaze time interval of each jump event in the gaze trajectory, and generating a gaze trajectory sequence feature record; Based on the characteristic records of the gaze trajectory sequence, the dynamic changes of the gaze trajectory within the task stage are analyzed. According to the temporal variation trend of the jump frequency, the transfer pattern of the gaze point in the fixation focus area of ​​the visual saccade task, and the difference in the distribution of the gaze time within and outside the task stage, a fluctuation characteristic diagram of the visual saccade task is established.

5. The method for early screening of Alzheimer's disease according to claim 4, characterized in that: To calculate the fractal dimension of the jump path, the formula is used: Get the fractal dimension D f , represents the self-similarity of the path at multiple scales; Where ∈ is the grid size, N(∈) is the number of grids covered by the jump path, T represents the temporal intensity of the fixation point in the jump path, log is used to map the number of grids covered by the jump path N(∈) and the change in grid scale ∈ to the logarithmic space, and log(1 / ∈) is the logarithm of the inverse of the grid scale, reflecting the change in the discretization scale of the path.

6. The method for early screening of Alzheimer's disease according to claim 1, characterized in that: Based on the fluctuation characteristic diagram of the visual saccade task, the distribution of target points and non-target points in the gaze path is recorded, the continuity and jump changes of the gaze behavior are referred to, the return points and bifurcation points are marked, and the number and length of path switches are counted. The specific steps for generating the path characteristic data of the patient's memory search task are as follows: Based on the fluctuation characteristic diagram of the visual saccade task, the data source of the memory search phase in the visual saccade task is extracted by random clustering, the starting point and the ending point of the fixation path in the memory search phase are recorded, the spatial distribution positions of the target points and non-target points in the fixation path are marked, and the target and non-target distribution data of the memory search phase are generated; Based on the target and non-target distribution data of the memory search phase, the gaze point position changes in the gaze path are extracted according to the time series of the gaze path, the direction changes and frequency of the gaze point jump events are recorded, the return points and bifurcation points in the gaze path are marked, and the memory search phase gaze path jump characteristic data is generated; Based on the gaze path jump characteristic data of the memory search link, the number of gaze point switches and the path length in the gaze path are grouped and counted, the gaze behavior is classified according to the density of the intersection points of the gaze path, and the stage characteristics of the gaze path are integrated into the overall distribution of the task path to generate the patient's memory search task path characteristic data.

7. The method for early screening of Alzheimer's disease according to claim 1, characterized in that: Based on the path characteristic data of the patient's memory search task, the specific steps of recording the direction and magnitude of the deviation event and distinguishing the deviation categories according to the relative position change between the target point and the gaze point are as follows: Based on the patient's memory search task path characteristic data, the relative spatial position of the target point and the gaze point in the gaze path during the memory search phase is recorded, the direction angle and amplitude of each offset event in the gaze path are marked, and spatial relationship data between the target point and the gaze point in the gaze path are generated; Based on the spatial relationship data between the target point and the gaze point in the gaze path, the gaze point offset events in the gaze path are classified according to the directional consistency and magnitude of the gaze point offset events, multiple distance offsets and directional distribution characteristics of the distance offset events are annotated, and classification data of the offset events in the gaze path are generated; Based on the classification data of the deviation events in the gaze path, the frequency distribution of each category of deviation events is counted, the general direction and amplitude range of the deviation events in the gaze path are marked, the statistical characteristics of the deviation categories in the gaze path are summarized, and the path deviation characteristic data in the patient search task is generated.

8. The method for early screening of Alzheimer's disease according to claim 1, wherein: Data from the memory search phase of healthy subjects were collected and compared with the path deviation characteristic data from the patient search task. Hotspot areas and fixation points were annotated. The differences in the hotspot distribution of the patients' jump paths and the control group were analyzed. The specific steps for generating hotspot fixation feature data are as follows: Based on the collected data from the memory search phase of the healthy population, the data were compared with the path deviation characteristic data in the patient search task, the distribution of gaze points in the gaze paths of the patients and healthy population was marked, the number of gazes and path changes of target points and non-target points were recorded and classified, and the comparison results of the gaze paths of the patients and healthy population were generated; Based on the comparison results of the gaze paths of the patients and healthy people, the hot spot distribution of the patients and the healthy people is counted, the spatial positions and gaze times of the multi-frequency gaze points are marked, the difference in the hot spot distribution in the patients' jump paths and that of the healthy people is analyzed, and the difference data of the gaze hot spot distribution between the patients and the healthy people is generated; Based on the difference data of the gaze hotspot distribution between the patients and the healthy population, the distribution center of the patient's gaze hotspot area is marked, and the coverage of the patient's hotspot area and the target point is counted to generate hotspot gaze feature data.

9. The method for early screening of Alzheimer's disease according to claim 1, characterized in that: Based on the hotspot gaze feature data, the number and location of gazes on the target object and the distractor are recorded, the gaze path during the task switching phase is analyzed, the behavioral characteristics of the target gaze path are extracted, and early screening data for Alzheimer's disease is generated. The specific steps for applying it to early screening for Alzheimer's disease are as follows: Based on the hotspot gaze feature data, the gaze point types of the gaze paths in the hotspot area are annotated by hierarchical residual analysis, the number of gazes and spatial distribution of the target object and the distractor are recorded, and the hotspot area gaze point distribution characteristic data is generated according to the distribution characteristics of the gaze points in the hotspot area; Based on the hotspot area gaze point distribution characteristic data, the gaze path in the task dynamic switching stage is recorded, and according to the switching order and frequency of the target object and the interference object in the jump path, the path priority area and jump frequency changes in the task switching stage are counted to generate the gaze path characteristic data in the task dynamic switching stage; Based on the gaze path characteristic data during the dynamic switching phase of the task, the gaze priority deviation in the patient's gaze hotspot is marked, and the target point focusing frequency, jump direction and amplitude stability, and hotspot area coverage are recorded according to the task stage. The gaze behavior characteristics in the dynamic switching phase are extracted, and the patient's gaze behavior tendency in subsequent tasks is predicted to generate early screening data for Alzheimer's disease.

10. The method for early screening of Alzheimer's disease according to claim 9, characterized in that: To predict the patient's gaze behavior tendency in the subsequent task, the formula is used: Calculate the gaze behavior tendency value P t , which measures whether the patient is more inclined to fixate on the target point, distractor, or hotspot area in the subsequent task, and usually ranges from 0 to 1; Among them, A i Represents the weight factor of the gaze point type in the current task stage, D′ i is the corrected duration of the fixation point, F i is the jump frequency of the fixation point, and n is the total number of fixations recorded in the current task.

Images