Method and system for analysis of movement disorder treatment based on neural circuit feedback

Abstract

The present application relates to the technical field of neural information, in particular to a movement disorder treatment analysis method and system based on neural loop feedback, comprising the following steps: dividing functional partitions based on neural loop activity, extracting signal fluctuation and discharge trajectory to identify abnormal intervals, analyzing signal gradient and direction consistency according to candidate set, extracting distribution matrix to analyze uniformity and screen abnormal areas, evaluating deviation calibration level, screening partition adjustment, and outputting neural regulation linkage adjustment data table. In the present application, signal fluctuation and discharge trajectory are extracted based on neural loop activity division and time synchronization analysis, which can accurately identify abnormal intervals, and signal distribution matrix and functional feature analysis are used to strengthen local uniformity evaluation, optimize neural loop response coordination and signal conduction stability, realize accurate positioning and dynamic regulation of movement disorder causes, and ensure the pertinence and consistency of neural function evaluation and regulation.

Description

Technical Field

[0001] This invention relates to the field of neuroinformatics technology, and in particular to a method and system for analyzing the treatment of movement disorders based on neural circuit feedback. Background Technology

[0002] The field of neuroinformatics mainly involves the research and analysis of the nervous system. Combining computational science and biology, it uses various methods to model, analyze, and process the nervous system. Core aspects of this field include neural signal processing, neuronal network models, brain-computer interfaces, neurofeedback technology and its applications. Neuroinformatics technology has been widely used in fields such as bioinformatics, artificial intelligence, and cognitive science. Its aim is to explore the relationship between neuronal activity, brainwave patterns, and behavior by understanding the working mechanisms of the nervous system, thereby promoting a deeper understanding of neural functions.

[0003] Among them, the traditional method of movement disorder analysis based on neural circuit feedback refers to a method of analyzing movement disorders through neural circuit feedback technology. This method mainly relies on real-time monitoring of neural activity, analyzing the response of the nervous system through specific algorithms, and using feedback mechanisms to adjust the transmission of neural signals. Specifically, the traditional analysis method monitors brain waves, neuronal activity, and motor control signals in real time, and feeds back the data to the brain or neural circuits in order to regulate neural activity. This process involves multiple feedbacks and adjustments to analyze the manifestations and influencing factors of movement disorders.

[0004] Traditional methods for analyzing movement disorders rely on real-time monitoring of neural signals and regulation through feedback mechanisms. However, this approach often only processes neural activity at a macroscopic level, lacking in-depth characterization of local neural signal changes and inter-regional correlations. This can easily lead to inaccurate identification of abnormal areas and an inability to fully reflect the coordinated imbalance of functional zones within a neural circuit. Furthermore, its signal feedback is mainly based on overall regulation, ignoring the connectivity differences at the boundaries of zones. This results in abnormal activities in some key functional areas not being captured and analyzed in a timely manner, thus affecting the accurate judgment of the mechanism of movement disorder formation. Consequently, it leads to an imbalance in the range of regulatory responses and unstable neural activity correction effects, limiting the accuracy of neural circuit function assessment and the targeted nature of interventions. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and to propose a method and system for the treatment and analysis of movement disorders based on neural circuit feedback.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a method for analyzing the treatment of movement disorders based on neural circuit feedback, comprising the following steps:

[0007] S1: Based on the functional partitioning of neural circuit activity, extract the neural signal fluctuation curves and neuronal firing trajectories within the partitions, identify synchronous abnormal intervals of signal fluctuation amplitude and firing trajectory changes on the time axis, extract the corresponding partition numbers and spatial coordinates, and generate a candidate set of movement disorders.

[0008] S2: Based on the candidate set of movement disorders, extract the direction of the neural signal gradient and the firing fitting vector of the partition, analyze the consistency of their directions at the boundary of the partition, and combine the connectivity of the partition boundary to screen the partitions with connectivity and abnormal signal gradients to form a suspected movement disorder partition layer.

[0009] S3: Based on the suspected movement disorder partition layer, extract the neural signal distribution matrix and local functional features within the partition, analyze the signal uniformity and functional integrity, filter out abnormal areas of signal uniformity and functional integrity, and obtain a set of movement disorder linkage partitions.

[0010] S4: Based on the set of movement disorder linkage zones, analyze the activity trend of the neural circuits corresponding to the zones, assess the degree of deviation from the original neural activity baseline curve, mark the movement disorder level of the zones according to the deviation range, and output a list of abnormal neural zone activity analysis.

[0011] As a further aspect of the present invention, the candidate set of movement disorders includes signal mutation partition numbers, abnormal discharge fitting points, partition coordinate markers, and time series anomaly identifiers; the suspected movement disorder partition layer includes signal gradient anomaly partition identifiers, partition boundary connectivity units, partition boundary consistency blocks, and abnormal signal distribution grids; the movement disorder linkage partition set includes signal anomaly continuous partitions, functionally incomplete areas, plaque mutation overlapping areas, and linkage anomaly partition numbers; and the list of abnormal neural partition activity analysis includes risk level labels, partition response deviation values, local activity anomaly indicators, and baseline offset levels.

[0012] As a further aspect of the present invention, the step of obtaining the candidate set of movement obstacles specifically includes:

[0013] S111: Based on the functional partitioning of neural circuit activity, extract the neural signal fluctuation curves and neuronal firing trajectories of the partitions, compare and analyze the two types of data within the same partition, and obtain the trend value of the difference between signal and firing.

[0014] S112: Based on the trend value of the difference between the signal and the discharge, identify the fluctuation amplitude value and the deviation value of the discharge trajectory in the signal fluctuation curve, superimpose the two types of values ​​in time periods, extract the time interval where the fluctuation exceeds the preset benchmark value and the deviation value exceeds the preset threshold, and generate a set of high-frequency abnormal interval time periods.

[0015] S113: For the set of high-frequency abnormal interval time periods, match the corresponding partition number and spatial coordinate information, extract the partition location where the signal occurred, and generate a candidate set of movement obstacles.

[0016] As a further aspect of the present invention, the step of obtaining the suspected movement disorder partition layer specifically includes:

[0017] S211: Based on the candidate set of movement disorders, identify the direction of the neural signal gradient and the fitting vector of the discharge in the partition, extract the projection trajectory of the two at the boundary of the partition, analyze the distribution and aggregation of the boundary points in the partition, and obtain the partition boundary consistency map.

[0018] S212: Based on the partition boundary consistency map, filter the boundary regions with a aggregation degree higher than the average level, compare the spatial boundary of the overall neural circuit structure map, identify continuous boundary clusters belonging to the same partition, and obtain the signal gradient abnormality zoning within the neural partition.

[0019] S213: Invoke the signal gradient anomaly region within the neural region, and perform integrated analysis on the region boundary consistency, signal gradient dispersion, signal distribution uniformity, and discharge fitting delay, using the following formula:

[0020] ;

[0021] Calculate the signal distribution difference value, identify the high sensitivity response coefficient of movement obstacles, and perform partition matching based on the response blocks in the layer to form a suspected movement obstacle partition layer;

[0022] in, Represents the difference in signal distribution. Represents the number of signal sample points. Representing the The signal strength at each signal point Representing the The reference signal strength at each signal point The average value representing the signal strength. This represents the average value of the reference signal strength.

[0023] As a further aspect of the present invention, the step of obtaining the motion obstacle linkage partition set specifically includes:

[0024] S311: Based on the suspected movement disorder partition layer, extract the signal distribution matrix and local functional features of the numbered partitions in the layer, align the data in the partitions with timestamps, identify the signal intensity fluctuation value and functional integrity offset, and obtain the neural local movement disorder response feature set.

[0025] S312: Based on the aforementioned neural local motor disorder response feature set, jointly analyze the signal uniformity and functional integrity within the partition, calculate the signal-functional coupling feature value, filter the partition units with signal-functional coupling degree in the layer, and establish a spatial distribution map of signal-functional coordinated response.

[0026] S313: Call the signal function to coordinate the response spatial distribution map, cluster the partitions in the coupled feature value layer that exceed the collaborative recognition benchmark, label the partition codes and coordinates corresponding to the continuous abnormal areas, and obtain the motion obstacle linkage partition set.

[0027] As a further aspect of the present invention, the steps for obtaining the list of abnormal neural region activity are as follows:

[0028] S411: Based on the set of movement obstacle linkage zones, extract the activity distribution curve of the zone under the specified number, perform time uniform processing, identify the amount of activity change per unit time, and obtain the set of abnormal change rates of zone activity.

[0029] S412: Based on the set of abnormal change rates of partitioned activities, identify the activity distribution curve of the original neural activity stage, compare the current activity change sequence with the reference curve, identify the deviation level of partitioned activities, extract and mark partitions whose deviation level exceeds the upper limit of the warning, and obtain the set of partitions with sudden increase in deviation.

[0030] S413: Based on the aforementioned deviation abrupt increase partition set, bind the deviation level value of each partition to the position number in the neural circuit structure spatial diagram, sort them according to the deviation level, and output a list of abnormal neural partition activity.

[0031] As a further aspect of the present invention, the method further includes step S5:

[0032] S5: Call the list of abnormal activity analysis of neural regions, identify the corresponding number of the region in the neural circuit functional diagram, retrieve the list of regulatory response units, compare the response level with the neural protection priority sequence, filter the region number that needs to adjust the response coverage, and output the neural regulation linkage adjustment data table.

[0033] The neural regulation linkage adjustment data table includes the adjustment target partition number, response level adjustment parameters, protection priority comparison items, and linkage response trigger type.

[0034] As a further aspect of the present invention, the step of obtaining the neural modulation linkage adjustment data table specifically includes:

[0035] S511: Call the list of abnormal activity in the neural partition, extract the partition number in the neural circuit function diagram, map the partition risk level value to the regional coordinate boundary, identify the partition information corresponding to the neural protection level, and generate a neural partition risk distribution map.

[0036] S512: Based on the neural partition risk distribution map, extract the regulatory response unit number and response level, match the partition risk level with the regulatory response level, identify the unit number with insufficient response coverage, and obtain the list of neural partition response risk disconnection.

[0037] S513: Based on the list of neural partition response risk disconnection, extract the key partition numbers that need to improve the response coverage according to the level number in the neural protection priority sequence, output the adjustment control parameters linked with the original adjustment unit in sequence, and output the neural regulation linkage adjustment data table.

[0038] The neural circuit feedback-based movement disorder treatment analysis system is used to execute the above-mentioned neural circuit feedback-based movement disorder treatment analysis method. The system includes:

[0039] The signal monitoring module is based on the functional partitions of neural circuit activity. It compares the signal fluctuation amplitude and discharge trajectory changes within the same time period, filters out the synchronous abnormal intervals of the two, extracts the partition number and spatial coordinates, summarizes the abnormal time period and partition number, and generates a candidate set of movement disorders.

[0040] Based on the candidate set of movement disorders, the partition localization module identifies the consistency between the signal gradient direction and the discharge fitting vector, marks the partition boundary number, matches the overall structure diagram of the neural circuit, extracts the partition number range of the signal gradient abnormal area, and establishes a suspected movement disorder partition layer.

[0041] Based on the suspected motion obstacle partition layer, the obstacle linkage module retrieves the signal distribution matrix and the continuous data sequence of local functional features in the region, judges the connectivity and functional integrity of the abnormal signal boundary, marks the partition number that meets the linkage threshold of both, and outputs the motion obstacle linkage partition set.

[0042] The activity early warning module analyzes the activity distribution trend and the degree of deviation of the original neural activity baseline curve of the corresponding partition based on the partition number of the motion obstacle linkage partition set, extracts the partition number of the deviation trend, completes the level identification according to the risk classification standard, and generates a list of abnormal neural partition activity analysis.

[0043] Based on the list of abnormal activity in the neural partitions, the adjustment and optimization module finds the corresponding position number of the risk level partition in the neural circuit function diagram, retrieves the current adjustment response unit configuration list, compares the neural protection priority with the current response level, filters the partition numbers that need to be updated, and outputs the neural regulation linkage adjustment data table.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0045] In this invention, by extracting regional signal fluctuations and discharge trajectories based on the division of neural circuit activity and establishing a time synchronization analysis mechanism, the accurate identification of abnormal regions can be achieved. Combined with signal gradient direction and regional connectivity analysis, the spatial correlation characteristics of abnormal neural signals can be effectively revealed, thereby realizing the systematic screening and aggregation of abnormal activities in different regions. Furthermore, through signal distribution matrix and functional feature analysis, the assessment of local uniformity and functional integrity is strengthened, forming a multi-dimensional linkage regional identification mechanism. Finally, when outputting regional abnormality levels and linkage adjustment data, the overall response coordination and signal transmission stability of neural circuits are optimized, achieving precise localization and dynamic regulation of the causes of movement disorders, and ensuring the pertinence and consistency of neural function assessment and regulation. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0047] Figure 2 This is a flowchart of the candidate set of movement obstacles in this invention;

[0048] Figure 3 This is a flowchart of the suspected movement disorder partitioning layer in this invention;

[0049] Figure 4 This is a flowchart of the motion obstacle linkage partition set in this invention;

[0050] Figure 5 This is a flowchart of the list of abnormal neural region activity analysis in this invention;

[0051] Figure 6 This is a flowchart of the neural regulation linkage adjustment data table in this invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the 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 merely illustrative and not intended to limit the invention.

[0053] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0054] Example 1

[0055] Please see Figure 1 This invention provides a technical solution, a method for analyzing the treatment of movement disorders based on neural circuit feedback, comprising the following steps:

[0056] S1: Based on the functional partitioning of neural circuit activity, extract the neural signal fluctuation curves and neuronal firing trajectories within the partitions, identify synchronous abnormal intervals of signal fluctuation amplitude and firing trajectory changes on the time axis, extract the corresponding partition numbers and spatial coordinates, and generate a candidate set of movement disorders.

[0057] S2: Based on the candidate set of movement disorders, extract the direction of the neural signal gradient and the fitting vector of the discharge in the partition, analyze the consistency of the direction of the two at the boundary of the partition, and combine the connectivity of the partition boundary to screen the partitions with connectivity and abnormal signal gradient to form a suspected movement disorder partition layer.

[0058] S3: Based on the suspected movement disorder partitioning layer, extract the neural signal distribution matrix and local functional features within the partition, analyze the signal uniformity and functional integrity, filter out abnormal areas of signal uniformity and functional integrity, and obtain a set of movement disorder linkage partitions.

[0059] S4: Based on the set of movement disorder linkage zones, analyze the activity trend of the neural circuits corresponding to the zones, assess the degree of deviation from the original neural activity baseline curve, mark the movement disorder level of the zones according to the deviation range, and output a list of abnormal neural zone activity analysis.

[0060] S5: Call the list of abnormal activity in neural regions, identify the corresponding number of the region in the neural circuit function diagram, retrieve the list of regulatory response units, compare the response level with the neural protection priority sequence, filter the region numbers that need to adjust the response coverage, and output the neural regulation linkage adjustment data table.

[0061] The candidate set of movement disorders includes signal mutation partition numbers, abnormal discharge fitting points, partition coordinate markers, and time series anomaly identifiers. The suspected movement disorder partition layer includes signal gradient anomaly partition identifiers, partition boundary connectivity units, partition boundary consistency blocks, and abnormal signal distribution grids. The movement disorder linkage partition set includes signal anomaly continuous partitions, functionally incomplete areas, plaque mutation overlapping areas, and linkage anomaly partition numbers. The list of abnormal neural partition activity includes risk level labels, partition response deviation values, local activity anomaly indicators, and baseline offset levels. The neural regulation linkage adjustment data table includes adjustment target partition numbers, response level adjustment parameters, protection priority comparison items, and linkage response trigger types.

[0062] Please see Figure 2 The specific steps for obtaining the candidate set of movement disorders are as follows:

[0063] S111: Based on the functional partitioning of neural circuit activity, extract the neural signal fluctuation curves and neuronal firing trajectories of the partitions, compare and analyze the two types of data within the same partition, and obtain the trend value of the difference between signal and firing.

[0064] Based on functional partitioning of neural circuit activity, two types of data were extracted from a designated functional partition (P03): neural signal fluctuation curves and neuronal firing trajectories. The neural signal fluctuation curves were obtained by continuously acquiring data for 10 seconds using a local field potential (LFP) monitoring device at a sampling rate of 1000 Hz. The data points were voltage sequences varying over time; for example, at specific time points of 1.0 second, 1.1 second, and 1.2 seconds, the voltage values ​​were -65 mV, -62 mV, and -70 mV, respectively. The neuronal firing trajectories were recorded using a multi-electrode array (MEA) to capture the action potential firing times of 50 independent neurons within the same partition, forming a spike pulse time sequence. For example, neuron N1 fired at 1.05 seconds and 1.15 seconds. A comparative analysis of the two types of data within the same partition was performed. Specifically, the 10-second data was divided into 100 consecutive 100-millisecond time windows. Within the time window, the standard deviation of the LFP signal is calculated to quantify the signal fluctuation amplitude, and the total number of firings in the neuron firing trajectory is counted to quantify the firing frequency. For example, in the first 100-millisecond time window, the standard deviation of the LFP signal is 2.5 mV, and the total number of firings of 50 neurons is 120; in the second time window, the standard deviation is 2.8 mV, and the total number of firings is 115. To obtain the trend value of the difference between the signal and the firing, the fluctuation amplitude and firing frequency of each time window are normalized. This processing adopts the Z-score method, that is, the current value is subtracted from the mean of the entire 10-second recording period, and then divided by the standard deviation to obtain the normalized fluctuation Z-score and the normalized firing Z-score. The absolute value of the difference between the two is calculated, and this difference is defined as the difference degree of the time window. The difference degrees of 100 time windows are arranged in chronological order to obtain the trend value of the difference between the signal and the firing.

[0065] S112: Based on the trend value of the difference between signal and discharge, identify the fluctuation amplitude value and the deviation value of the discharge trajectory in the signal fluctuation curve, superimpose the two types of values ​​in time periods, extract the time interval where the fluctuation exceeds the preset benchmark value and the deviation value exceeds the preset threshold, and generate a set of high-frequency abnormal interval time periods.

[0066] Based on the trend value of the difference between signal and discharge, the fluctuation amplitude value is defined as the difference between the maximum and minimum values ​​of the LFP signal voltage within each 100-millisecond time window. The deviation value of the discharge trajectory is the difference between the actual total number of discharges of neurons within that time window and the expected number of discharges predicted by a Poisson distribution model based on historical data from the previous 100 time windows. For example, for the 101st time window, the recorded maximum value of the LFP signal is -55 mV, the minimum value is -75 mV, the fluctuation amplitude value is 20 mV, and the actual number of discharges recorded is 150, while the expected number of discharges predicted based on historical data is 110, resulting in a deviation of 40. Subsequently, the fluctuation amplitude value and the deviation value are superimposed over time periods to extract the time intervals where the fluctuation amplitude exceeds a preset baseline value and the deviation value exceeds a preset threshold value. The preset baseline value for fluctuation is set with reference to the fluctuation amplitude values ​​of all time windows within the entire observation period. The mean is added to 1.5 times the standard deviation. Assuming the historical average fluctuation amplitude is 15 mV and the standard deviation is 2 mV, the preset benchmark value is 18 mV (15 + 1.5 × 2). The deviation threshold is set with reference to 30% of the historical average expected discharge number. If the historical average expected discharge number is 110 times, the threshold is 33 times (110 × 0.3). In this example, the fluctuation amplitude value of 20 mV is greater than 18 mV, and the deviation value of 40 times is greater than 33 times. This 101st time window is identified as an abnormal interval. This process is repeated for 10 consecutive minutes of monitoring data. All 100-millisecond time windows that meet the conditions are merged. For example, if the 101st to 105th and the 230th to 233rd time windows all meet the conditions, the generated time intervals are [10.0s, 10.5s] and [23.0s, 23.3s]. All such time intervals are collected to generate a high-frequency abnormal interval time set.

[0067] S113: For the high-frequency abnormal interval time set, match the corresponding partition number and spatial coordinate information, extract the partition location where the signal occurred, and generate a candidate set of movement obstacles;

[0068] For high-frequency abnormal time intervals (e.g., {[10.0s, 10.5s], [23.0s, 23.3s], ...}), a pre-stored neural circuit functional partition map is retrieved. This map records the unique number of each functional partition and its geometric range in a three-dimensional brain spatial coordinate system (e.g., the Bregma coordinate system). The coordinate range of partition P03 is (X: 1.5-2.5mm, Y: 2.0-3.0mm, Z: -3.0 to -4.0mm). Since the abnormal time interval data comes from the monitoring electrode of partition P03, the time interval is bound to the partition number P03. Then, the partition location where the signal occurred is extracted, that is, the spatial coordinate information of the partition. Information is appended to each abnormal event record to form a structured data entry containing time, partition number, and spatial location. For example, the record {Abnormal time period: [10.0s, 10.5s], partition number: P03, spatial coordinates: (X: 1.8mm, Y: 2.2mm, Z: -3.5mm)} is generated, where the spatial coordinates are the precise location of the monitoring electrode within the partition. The process from S111 to S113 is repeated for all functional partitions to collect the partition information of all partitions that have detected high-frequency abnormal intervals. For example, in addition to P03, partitions P08 and P15 are also found to have such abnormalities. Finally, the information of P03, P08, and P15 is integrated to generate a candidate set of movement disorders.

[0069] Please see Figure 3 The specific steps for obtaining the suspected movement disorder partition layer are as follows:

[0070] S211: Based on the candidate set of movement disorders, identify the direction of the neural signal gradient and the fitting vector of the discharge in the partition, extract the projection trajectory of the two at the boundary of the partition, analyze the distribution and aggregation of the boundary points in the partition, and obtain the partition boundary consistency map.

[0071] Based on the candidate set of movement disorders ({P03, P08, P15}), taking partition P03 as an example, the method for calculating the gradient direction of neural signals is as follows: On a 4×4 microelectrode array deployed within partition P03, during the identified abnormal time period [10.0s, 10.5s], the spatial gradient of the average amplitude of the LFP signal recorded by each electrode is calculated using the finite difference method, i.e., the rate of change of signal intensity on the X, Y, and Z axes, resulting in a three-dimensional vector, such as (0.5, -0.2, 0.1) mV / mm. The method for calculating the discharge fitting vector is as follows: Analyze the discharge time series of all neurons on the array within the same time period, and determine the dominant direction and speed of information transmission by calculating the cross-correlation function of the discharge times of different neurons, thus fitting a... A vector representing the direction of discharge activity propagation, such as (0.6, -0.15, 0.08) mm / ms, is used. Then, the projection trajectory of the two at the boundary of the partition is extracted. The boundary plane equation of partition P03 and the adjacent partition (such as P04) is retrieved (such as x=2.5mm). The gradient vector and the discharge fitting vector are projected onto this plane. The distribution number and aggregation degree of the boundary points in the partition are analyzed. Specifically, the boundary is divided into a grid of 100×100 micrometers. The number of times the projection trajectory passes through each grid during the abnormal period is counted. If a grid is passed through more than 10 times, it is recorded as a boundary point. The total number of all boundary points is counted. The DBSCAN algorithm is used to analyze its spatial aggregation degree, identify high-density clusters, and obtain the partition boundary consistency map.

[0072] S212: Based on the partition boundary consistency map, filter the boundary areas with a higher degree of aggregation than the average level, compare the spatial boundaries of the overall neural circuit structure map, identify continuous and belonging to the same partition boundary clusters, and obtain the signal gradient abnormality zoning within the neural partition.

[0073] Based on the boundary consistency map, the density of all boundary point clusters in the map is first calculated (defined as the number of points in the cluster divided by the cluster area), and the average density of all clusters is calculated. For example, the average density is 5 points / 0.01 mm². Then, clusters with a density greater than this average are selected as boundary regions with high aggregation. Next, the spatial boundaries of the overall neural circuit structure map are compared, and the selected high aggregation boundary regions are matched with predefined macroscopic spatial boundaries representing different anatomical structures or functional modules to identify continuous boundary clusters belonging to the same partition. For example, three adjacent high aggregation clusters (C1, C2, C3) are found to be located inside partition P03 and adjacent to its boundary with partition P08. The three clusters form a continuous band-like region in space and do not cross into partition P08. The continuous region composed of C1, C2, and C3 is then identified, and the signal gradient abnormality region within the neural partition is obtained.

[0074] S213: Invoke the signal gradient anomaly region within the neural partition, and perform integrated analysis on partition boundary consistency, signal gradient dispersion, signal distribution uniformity, and discharge fitting delay, using the following formula:

[0075] ;

[0076] Calculate the signal distribution difference value, identify the high sensitivity response coefficient of movement obstacles, and perform partition matching based on the response blocks in the layer to form a suspected movement obstacle partition layer;

[0077] in, Represents the difference in signal distribution. Represents the number of signal sample points. Representing the The signal strength at each signal point Representing the The reference signal strength at each signal point The average value representing the signal strength. This represents the average value of the reference signal strength.

[0078] The signal gradient anomaly region within the neural partition is invoked, and various indicators are first quantified: the consistency of the partition boundary is obtained by calculating the average value of the cosine of the angle between the projection direction of the signal gradient vector and the firing fitting vector on the interface; the closer the value is to 1, the higher the consistency. The signal gradient dispersion is obtained by calculating the average Euclidean distance between the signal gradient vectors recorded by each microelectrode within the anomaly region; the larger the distance, the higher the dispersion. The signal distribution uniformity is measured by the Gini coefficient to measure the distribution difference of signal intensity within the region; the closer the value is to 0, the more uniform the distribution. The firing fitting delay is the average time lag of the propagation of neuronal firing activity in space, calculated by cross-correlation analysis during the abnormal period; the indicators are comprehensively evaluated by calculating the signal distribution difference value.

[0079] For example, selecting within this abnormal zone The signal strength of these three points was calculated using a microelectrode array. (unit: The reference signals are defined as {120, 150, 90}, and the signal intensity at the corresponding location is extracted from the historical data of the same region in the healthy control group. (unit: ), whose values ​​are {110, 115, 105};

[0080] First, calculate the average:

[0081] ;

[0082] ;

[0083] Then substitute the values ​​into the formula to calculate:

[0084] ;

[0085] The advantage of this formula lies in its ability to more sensitively capture abnormal patterns in signal fluctuations by comparing not only the mean differences in signal strength but also the differences in signal variance. This quantification of fluctuation patterns is crucial for identifying dynamic anomalies that traditional mean analysis cannot detect. After the value is determined, the high-sensitivity response coefficient for movement obstacles is identified. This coefficient is based on... The value is defined hierarchically, for example, setting a response coefficient threshold: when When the coefficient is low; when When, the coefficient is medium; when When the coefficient is high, in this example... The high response coefficient is used to perform partition matching based on the response blocks in the layer. All partitions with high response coefficients (such as P03) are highlighted on the three-dimensional brain map to form a suspected movement disorder partition layer.

[0086] Please see Figure 4 The specific steps for obtaining the set of motion obstacle linkage zones are as follows:

[0087] S311: Based on the suspected movement disorder partition layer, extract the signal distribution matrix and local functional features of the numbered partitions in the layer, align the data in the partitions with timestamps, identify the signal intensity fluctuation value and functional integrity offset, and obtain the neural local movement disorder response feature set.

[0088] Based on a partitioned layer of suspected movement disorders (labeled partitions P03 and P08), taking partition P03 as an example, the signal distribution matrix is ​​a 10×10 matrix, where each element represents the average LFP signal power of a sub-region within that partition at a specific time point. Local functional characteristics are a set of quantitative indicators, including the average expression level of dopamine D2 receptors in that partition (obtained from PET data, value 0.85), the proportion of GABAergic neurons (obtained from histological data, value 18%), and the activation volume of oxygen-dependent (BOLD) signals (obtained from fMRI data, value 120 mm³). These indicators are used to analyze the partitions. The internal data is timestamped to identify signal intensity fluctuations and functional integrity offsets. Signal intensity fluctuations are obtained by calculating the square root of the sum of the squares of the differences between all elements in the signal distribution matrix at two consecutive time points (100 milliseconds apart). Functional integrity offsets are obtained by comparing the current functional feature value with the corresponding normal value extracted from the healthy baseline database. For example, if the normal BOLD activation volume of the P03 partition is 200 mm³, the current offset is -80 mm³ (120-200). The calculated fluctuation value and offset are integrated to obtain the neural local motor disorder response feature set.

[0089] S312: Based on the response characteristic set of localized motor disorders, a joint analysis of signal uniformity and functional integrity within the region is performed, using the following formula:

[0090] ;

[0091] Calculate the signal functional coupling characteristic value, filter the partition units of signal functional coupling degree in the layer, and establish a spatial distribution map of signal functional coordinated response;

[0092] in, Represents the functional coupling characteristic value of the signal. This represents the coupling response value between the k-th signal unit and the j-th signal unit. This represents the average response value of the j-th signal unit. represents the standard deviation of the j-th signal unit, and n represents the total number of signal units;

[0093] Based on the response feature set of localized motor disorders, a joint analysis of signal uniformity and functional integrity within a region is performed. Signal uniformity is quantified by calculating the coefficient of variation (standard deviation divided by mean) of the signal distribution matrix; a smaller value indicates a more uniform spatial distribution of the signal. Functional integrity is assessed by a weighted sum of the offsets of various functional features. The weights are set based on prior knowledge of the correlation between each functional feature and the motor disorder. The signal-functional coupling feature value Q is calculated to quantify the degree of coupling anomaly in a specific region within the collaborative network.

[0094] The formula's operational logic works by calculating a signal unit. With all signal units The unit is quantized by the square root of the sum of the squared standardized deviations of the coupled response values ​​relative to their respective average responses. The degree of coupling anomaly in the entire network is essentially a multi-dimensional Mahalanobis distance, measuring the "anomaly" or "abnormality" of a point in a multivariate distribution. For example, analyzing the coupling relationship between partition P03 (as unit k) and two other partitions P08 and P15 (as units j=1, 2, and therefore n=2) in the suspected movement disorder partition layer, the coupling response value... It is obtained by calculating the cross-correlation coefficient of the time series of signal intensity fluctuation values ​​in different partitions. (Assuming the calculation yields...) (Coupling between P03 and P08) = 0.8 (Coupling between P03 and P15) = 0.3. Historical data shows that the average coupling response value of P08 is... =0.5, standard deviation =0.1; Average coupling response value of P15 =0.4, standard deviation =0.2;

[0095] Substitute the value into the formula:

[0096] ;

[0097] The advantage of this formula lies in its comprehensive consideration of the deviations of multiple coupling relationships, normalizing them using their respective standard deviations. This allows coupling relationships of varying strengths and variability to be fairly compared and integrated, thereby more accurately identifying nodes exhibiting abnormal behavior in multi-partition cooperative networks and calculating... After setting the value, the filter layer identifies partitions with abnormal signal-functional coupling, setting the coupling threshold to 2.5 (determined based on the 95th quantile of the Q-value distribution calculated from a large amount of healthy control data). In this example... Therefore, partition P03 was identified as a coupling anomalous unit, and all such anomalous units and their associated units were identified. The values ​​are visualized in a three-dimensional brain atlas to establish a spatial distribution map of the coordinated response of signal functions.

[0098] S313: Call the signal function to coordinate the response spatial distribution map, cluster the partitions in the coupled feature value layer that exceed the collaborative recognition benchmark, label the partition codes and coordinates corresponding to the continuous abnormal areas, and obtain the set of motion obstacle linkage partitions;

[0099] The spatial distribution map of the coordinated response of the signal function was invoked. All partitions with a Q value greater than 2.5 in the layer, such as P03 (Q=3.04), P08 (Q=2.85), and P15 (Q=2.60), were initially marked as abnormal. Connected component analysis based on spatial proximity was used to cluster the abnormal partitions. If two abnormal partitions are anatomically adjacent, they are grouped into the same cluster. Assuming that P03 is adjacent to P08 in the neural circuit structure map, while P15 is not adjacent to either of them, then P03 and P08 are clustered into a continuous abnormal region {P03, P08}, while P15 is in its own cluster. Subsequently, the partition codes and coordinates corresponding to the continuous abnormal regions were labeled, and a unique region ID, such as "linkage zone A", was assigned to the cluster {P03, P08}. The partition codes {P03, P08} contained in it and the overall spatial coordinate range covered by the partition were recorded to obtain the set of linkage partitions for movement disorders.

[0100] Please see Figure 5 The specific steps for obtaining the list of abnormal neural region activity analysis are as follows:

[0101] S411: Based on the set of movement obstacle linkage zones, extract the activity distribution curve of the zone under the specified number, perform time uniform processing, identify the amount of activity change per unit time, and obtain the set of abnormal change rates of zone activity.

[0102] Based on a set of linkage zones for movement disorders, such as a set containing {linkage zone A: {P03, P08}}, the average firing frequency data of neuronal clusters continuously recorded at a sampling rate of 1 Hz via implanted electrodes over the past 24 hours is retrieved for each zone (P03 and P08) within linkage zone A. This data constitutes a raw high-resolution time series containing 86,400 data points. For rhythm analysis, this raw series is downsampled to calculate the average firing frequency every 60 seconds (i.e., every minute), thereby generating an activity distribution curve containing 1,440 data points, which reflects the diurnal activity rhythm of the zones. Subsequently, time unification processing is performed, aligning the data acquisition timestamps of all linkage zones using the Network Time Protocol (NTP) to ensure that the activity distribution curves of all zones are precisely synchronized on the time axis, eliminating errors introduced by device clock drift. After processing, the change in activity per unit time is identified, specifically by performing a first-order difference operation on the minute-level activity distribution curve containing 1,440 data points, i.e., calculating the difference in activity intensity between every two adjacent time points (1 minute apart). For example, if the average firing frequency of partition P03 is 85 Hz at time point t (10th minute) and 92 Hz at time point t+1 (11th minute), then the change in activity within that 1-minute unit time is +7 Hz. Performing this difference calculation point by point on the entire 24-hour time series yields a new time series containing 1439 change values. This series quantifies the instantaneous rate of change of neural activity intensity and constitutes the partition activity abnormal change rate set.

[0103] S412: Based on the abnormal change rate set of partition activity, identify the activity distribution curve of the original neural activity stage, compare the current activity change sequence with the reference curve, identify the deviation level of partition activity, extract and mark partitions whose deviation level exceeds the upper limit of the warning, and obtain the partition set of sudden deviation increase.

[0104] Based on the abnormal rate of change set of zonal activity, the original neural activity baseline curve is a statistically representative 24-hour standardized activity rhythm template constructed from a long-term monitoring database containing 100 healthy subjects, for the same anatomical zonal region (e.g., P03), by averaging and spline smoothing multiple sample data. This template serves as a reference benchmark. Subsequently, the activity change sequence of the current zonal region is compared with the reference curve. This comparison is performed in the frequency domain: First, a Fast Fourier Transform (FFT) is performed on the activity change rate sequence of the current zonal region and the change rate sequence of the reference curve, respectively, to transform them from the time domain to the frequency domain, obtaining their respective power spectral density (PSD) plots. Within several preset specific frequency bands (e.g., the super-diurnal rhythm band 0.1-1.0 cycles / hour, the peri-diurnal rhythm band), the difference integral between the power spectrum of the current zonal region and the reference power spectrum is calculated. Based on the magnitude of this integral value, the level of deviation of zonal activity is identified. The criteria for classifying deviation levels were pre-determined through cluster analysis of a large amount of confirmed patient data: a difference integral value in the range of 0-0.5 (unit: au²) was level 1 (normal); 0.5-1.5 was level 2 (mild deviation); 1.5-3.0 was level 3 (moderate deviation); and greater than 3.0 was level 4 (severe deviation). The upper limit of the warning was set as the starting value for level 3, i.e., a difference integral value exceeding 1.5. Partitions whose deviation level exceeded the upper limit of the warning were extracted and marked. For example, partition P03 had a power spectrum difference integral of 3.2 in the super-solar rhythm band, exceeding the threshold of 3.0, and was judged as a level 4 deviation. At this time, partition P03 was marked as a deviation surge. All partitions that had experienced level 3 or level 4 deviations in any frequency band within 24 hours (such as P03 and P08) were aggregated to obtain the deviation surge partition set.

[0105] S413: Based on the deviation increase partition set, bind the deviation level value of each partition to the position number in the neural circuit structure spatial diagram, sort according to the deviation level, and output a list of abnormal neural partition activity analysis.

[0106] For each partition in the set of partitions with a sudden increase in deviation, a structured data record is created. This record contains multiple fields: the partition's anatomical identifier (e.g., P03, corresponding to the globus pallidus in the basal ganglia), its highest deviation grade value (e.g., 4), the specific frequency band that resulted in the highest rating (e.g., the hyperotropic frequency band), and the partition's unique location index number in the global 3D brain atlas (e.g., PN-003). The same operation is performed on partition P08, generating the record {Partition: P08, Highest Deviation Grade: 3, Abnormal Frequency Band: Hyperotropic Frequency Band, Location Number: PN-008}. Subsequently, partitions are sorted according to their deviation grade, with risk grade defined as a direct mapping of deviation grade, where grade 4 corresponds to the highest risk, followed by grade 3. A stable sorting algorithm is used to ensure that partitions with the same risk grade maintain their original relative order. In this example, P03 has a higher risk than P08, and the sorted list is [P03, P08]. Finally, this sorted list of partitions, along with the complete structured data record of each partition, is output to a standardized data file (e.g., JSON or XML format). This file not only contains the sorting results but also provides detailed quantitative indicators and metadata for each abnormal partition, forming a list of abnormal neural partition activity that can be directly parsed and executed by subsequent control modules.

[0107] Please see Figure 6 The specific steps for obtaining the neural regulation linkage adjustment data table are as follows:

[0108] S511: Call the list of abnormal activity analysis of neural partitions, extract the partition number in the neural circuit function diagram, map the partition risk level value to the regional coordinate boundary, identify the partition information corresponding to the neural protection level, and generate a neural partition risk distribution map.

[0109] The unique location numbers (PN-003 and PN-008) of each region in the neural circuit function diagram were extracted from the list of abnormal neural region activity. Next, the risk level values ​​of each region were mapped to a predefined regional coordinate boundary database. This database stores the three-dimensional coordinate range (e.g., a voxel set based on the Bregma coordinate system) corresponding to each location number. Simultaneously, the risk level values ​​were linked to a visualization rendering rule base. This rule base defines the graphical representation parameters of different risk levels on the 3D visualization interface. For example, risk level 4 (corresponding to P03) is mapped to a rendering color (#FF0000, red), transparency (0.4), and a blinking animation effect with a frequency of 2 Hz; risk level 3 (corresponding to P08) is mapped to a color (#FFFF00, yellow), transparency (0.6), and no blinking effect. Subsequently, the region information corresponding to the neural protection level was identified. The neural protection level is the intervention priority set according to the risk level, where risk level 4 corresponds to Level 1 protection (highest priority), and risk level 3 corresponds to Level 2 protection. Accordingly, partition P03 is marked as a first-level protection requirement object and P08 is marked as a second-level protection requirement object. Finally, in an interactive 3D brain model rendering engine, according to the above mapping rules, the voxel set corresponding to P03 is rendered with a red flashing effect, and the voxel set corresponding to P08 is rendered with a yellow static semi-transparent effect, thereby generating a dynamic and visualized neural partition risk distribution map.

[0110] S512: Based on the neural partition risk distribution map, extract the regulatory response unit number and response level, match the partition risk level with the regulatory response level, identify the unit number with insufficient response coverage, and obtain the list of neural partition response risk disconnection.

[0111] Based on the risk distribution map of neuroregions, the regulatory response unit numbers and their current response levels associated with high-risk regions (P03, P08) are extracted. Regulatory response units are pre-implanted interventional devices with closed-loop regulation capabilities, such as deep brain stimulators (DBS) or focused ultrasound transducers. Each unit has a unique hardware ID, and its current response level (e.g., "Off", "Low", "Medium", "High") is recorded in the device status register. For example, querying the device mapping table reveals that the spatial range of unit DBS-01 covers region P03, and its current response level is "Low"; the range of unit FUS-01 covers region P08, and its response level is "Medium". Next, a matching analysis between the regional risk level and the regulatory response level is performed. This analysis is conducted by querying a "risk-response matching matrix," which defines the minimum response level required for each neuroprotection level (derived from the risk level). For example, Level 1 protection requirement (risk 4) requires a "High" response, and Level 2 protection requirement (risk 3) requires a "Medium" response. Comparing the primary protection requirements of partition P03 with the "low" response level of its regulating unit DBS-01 revealed that the actual response was lower than required, indicating a significant response deficit. A comparison with partition P08 showed that its secondary protection requirements matched the "medium" response level of FUS-01. Subsequently, the unit numbers with insufficient response coverage were identified, and all regulating units with response deficits and their associated partition information were recorded. In this example, due to the response mismatch in P03, information such as unit DBS-01, its target partition P03, risk level 4, current response "low," and required response "high" was compiled into a single record, ultimately forming a list of neural partition response risk disconnects.

[0112] S513: Based on the list of risk disconnection in neural partition response, and based on the level number in the neural protection priority sequence, extract the key partition number that needs to improve the response coverage, output the adjustment control parameters linked with the original regulation unit in sequence, and output the neural regulation linkage adjustment data table.

[0113] Based on the list of neural partition response risk disconnects, which clearly indicates the record {Partition: P03, Risk Level: 4, Modulation Unit: DBS-01, Current Response: Low, Required Response: High}, according to a preset neural protection priority sequence, the first-level protection requirement (corresponding to risk level 4) is placed with the highest priority. Therefore, the modulation task related to P03 is processed first, and the key partition number that needs to be improved in response coverage, namely P03, is extracted. Subsequently, the adjustment control parameters linked with the original modulation unit (DBS-01) are output in sequence. This process is completed by calling a parameter optimization engine. This engine has a built-in biophysical model that can calculate the optimal combination of stimulation parameters based on the electrophysiological characteristics of the target partition and the required response level (from "low" to "high"). For the DBS unit DBS-01, the calculation result of the engine is a set of specific parameter adjustment instructions. For example, the instruction set specifies: linearly increase the stimulation pulse frequency from the current 80 Hz to 130 Hz, with an adjustment slope of 10 Hz / second; step adjust the pulse width from 60 microseconds to 90 microseconds; and non-linearly titrate the stimulation voltage from 1.5 volts to 2.5 volts. The titration process is controlled by the β-band power feedback of the real-time LFP signal to maintain it at the target inhibition level. A series of precise control parameters with timing and logical conditions are packaged together with metadata such as the regulation unit ID (DBS-01) and target partition (P03) to generate a machine-readable instruction file, namely the neural regulation linkage adjustment data table, and then sent to the neural regulation execution hardware.

[0114] The neural circuit feedback-based movement disorder treatment analysis system is used to execute the above-mentioned neural circuit feedback-based movement disorder treatment analysis method. The system includes:

[0115] The signal monitoring module is based on the functional partitions of neural circuit activity. It compares the signal fluctuation amplitude and discharge trajectory changes within the same time period, filters out the synchronous abnormal intervals of the two, extracts the partition number and spatial coordinates, summarizes the abnormal time period and partition number, and generates a candidate set of movement disorders.

[0116] The partition localization module is based on a candidate set of movement disorders. It identifies the consistency between the signal gradient direction and the discharge fitting vector, marks the partition boundary number, matches the overall structure map of the neural circuit, extracts the partition number range of the signal gradient abnormal area, and establishes a suspected movement disorder partition layer.

[0117] The obstacle linkage module is based on the suspected motion obstacle partition layer. It retrieves the signal distribution matrix and the continuous data sequence of local functional features in the region, judges the connectivity and functional integrity of the abnormal signal boundary, marks the partition number that meets the linkage threshold of both, and outputs the motion obstacle linkage partition set.

[0118] The activity early warning module analyzes the activity distribution trend of the corresponding zone and the degree of deviation from the original neural activity baseline curve based on the zone number of the movement disorder linkage zone set, extracts the zone number of the deviation trend, completes the level labeling according to the risk grading standard, and generates a list of abnormal neural zone activity analysis.

[0119] The regulation and optimization module, based on the list of abnormal activity in neural regions, finds the corresponding position number of the risk level region in the neural circuit function diagram, retrieves the current regulation response unit configuration list, compares the neural protection priority with the current response level, filters the region numbers that need to be updated, and outputs the neural regulation linkage adjustment data table.

[0120] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for analyzing the treatment of movement disorders based on neural circuit feedback, characterized in that, Includes the following steps: S1: Based on the functional partitioning of neural circuit activity, extract the neural signal fluctuation curves and neuronal firing trajectories within the partitions, identify synchronous abnormal intervals of signal fluctuation amplitude and firing trajectory changes on the time axis, extract the corresponding partition numbers and spatial coordinates, and generate a candidate set of movement disorders. S2: Based on the candidate set of movement disorders, extract the direction of the neural signal gradient and the firing fitting vector of the partition, analyze the consistency of their directions at the boundary of the partition, and combine the connectivity of the partition boundary to screen the partitions with connectivity and abnormal signal gradients to form a suspected movement disorder partition layer. The specific steps for obtaining the suspected movement disorder partition layer are as follows: S211: Based on the candidate set of movement disorders, identify the direction of the neural signal gradient and the fitting vector of the discharge in the partition, extract the projection trajectory of the two at the boundary of the partition, analyze the distribution and aggregation of the boundary points in the partition, and obtain the partition boundary consistency map. S212: Based on the partition boundary consistency map, filter the boundary regions with a aggregation degree higher than the average level, compare the spatial boundary of the overall neural circuit structure map, identify continuous boundary clusters belonging to the same partition, and obtain the signal gradient abnormality region within the neural partition. S213: Invoke the signal gradient anomaly region within the neural region, and perform integrated analysis on the region boundary consistency, signal gradient dispersion, signal distribution uniformity, and discharge fitting delay, using the following formula: ； Calculate the signal distribution difference value, identify the high sensitivity response coefficient of movement obstacles, and perform partition matching based on the response blocks in the layer to form a suspected movement obstacle partition layer; in, Represents the difference in signal distribution. Represents the number of signal sample points. Representing the The signal strength at each signal point Representing the The reference signal strength at each signal point The average value representing the signal strength. This represents the average value of the reference signal strength. S3: Based on the suspected movement disorder partition layer, extract the neural signal distribution matrix and local functional features within the partition, analyze the signal uniformity and functional integrity, filter out abnormal areas of signal uniformity and functional integrity, and obtain a set of movement disorder linkage partitions. S4: Based on the set of movement disorder linkage zones, analyze the activity trend of the neural circuits corresponding to the zones, assess the degree of deviation from the original neural activity baseline curve, mark the movement disorder level of the zones according to the deviation range, and output a list of abnormal neural zone activity analysis.

2. The method for analyzing the treatment of movement disorders based on neural circuit feedback according to claim 1, characterized in that, The candidate set of movement disorders includes signal mutation partition numbers, abnormal discharge fitting points, partition coordinate markers, and time series anomaly identifiers. The suspected movement disorder partition layer includes signal gradient anomaly partition identifiers, partition boundary connectivity units, partition boundary consistency blocks, and abnormal signal distribution grids. The movement disorder linkage partition set includes signal anomaly continuous partitions, functionally incomplete areas, plaque mutation overlapping areas, and linkage anomaly partition numbers. The list of abnormal neural partition activity includes risk level labels, partition response deviation values, local activity anomaly indicators, and baseline offset levels.

3. The method for analyzing the treatment of movement disorders based on neural circuit feedback according to claim 1, characterized in that, The specific steps for obtaining the candidate set of movement obstacles are as follows: S111: Based on the functional partitioning of neural circuit activity, extract the neural signal fluctuation curves and neuronal firing trajectories of the partitions, compare and analyze the two types of data within the same partition, and obtain the trend value of the difference between signal and firing. S112: Based on the trend value of the difference between the signal and the discharge, identify the fluctuation amplitude value and the deviation value of the discharge trajectory in the signal fluctuation curve, superimpose the two types of values ​​in time periods, extract the time interval where the fluctuation exceeds the preset benchmark value and the deviation value exceeds the preset threshold, and generate a set of high-frequency abnormal interval time periods. S113: For the set of high-frequency abnormal interval time periods, match the corresponding partition number and spatial coordinate information, extract the partition location where the signal occurred, and generate a candidate set of movement obstacles.

4. The method for analyzing the treatment of movement disorders based on neural circuit feedback according to claim 1, characterized in that, The specific steps for obtaining the set of motion obstacle linkage zones are as follows: S311: Based on the suspected movement disorder partition layer, extract the signal distribution matrix and local functional features of the numbered partitions in the layer, align the data in the partitions with timestamps, identify the signal intensity fluctuation value and functional integrity offset, and obtain the neural local movement disorder response feature set. S312: Based on the aforementioned neural local motor disorder response feature set, jointly analyze the signal uniformity and functional integrity within the partition, calculate the signal-functional coupling feature value, filter the partition units with signal-functional coupling degree in the layer, and establish a spatial distribution map of signal-functional coordinated response. S313: Call the signal function to coordinate the response spatial distribution map, cluster the partitions in the coupled feature value layer that exceed the collaborative recognition benchmark, label the partition codes and coordinates corresponding to the continuous abnormal areas, and obtain the motion obstacle linkage partition set.

5. The method for analyzing the treatment of movement disorders based on neural circuit feedback according to claim 4, characterized in that, The specific steps for obtaining the list of abnormal neural region activity are as follows: S411: Based on the set of movement obstacle linkage zones, extract the activity distribution curve of the zone under the specified number, perform time uniform processing, identify the amount of activity change per unit time, and obtain the set of abnormal change rates of zone activity. S412: Based on the set of abnormal change rates of partitioned activities, identify the activity distribution curve of the original neural activity stage, compare the current activity change sequence with the reference curve, identify the deviation level of partitioned activities, extract and mark partitions whose deviation level exceeds the upper limit of the warning, and obtain the set of partitions with sudden increase in deviation. S413: Based on the aforementioned deviation abrupt increase partition set, bind the deviation level value of each partition to the position number in the neural circuit structure spatial diagram, sort them according to the deviation level, and output a list of abnormal neural partition activity.

6. The method for analyzing the treatment of movement disorders based on neural circuit feedback according to claim 1, characterized in that, The method also includes step S5: S5: Call the list of abnormal activity analysis of neural regions, identify the corresponding number of the region in the neural circuit functional diagram, retrieve the list of regulatory response units, compare the response level with the neural protection priority sequence, filter the region number that needs to adjust the response coverage, and output the neural regulation linkage adjustment data table. The neural regulation linkage adjustment data table includes the adjustment target partition number, response level adjustment parameters, protection priority comparison items, and linkage response trigger type.

7. The method for analyzing the treatment of movement disorders based on neural circuit feedback according to claim 6, characterized in that, The specific steps for obtaining the neural modulation linkage adjustment data table are as follows: S511: Call the list of abnormal activity in the neural partition, extract the partition number in the neural circuit function diagram, map the partition risk level value to the regional coordinate boundary, identify the partition information corresponding to the neural protection level, and generate a neural partition risk distribution map. S512: Based on the neural partition risk distribution map, extract the regulatory response unit number and response level, match the partition risk level with the regulatory response level, identify the unit number with insufficient response coverage, and obtain the list of neural partition response risk disconnection. S513: Based on the list of neural partition response risk disconnection, extract the key partition numbers that need to improve the response coverage according to the level number in the neural protection priority sequence, output the adjustment control parameters linked with the original adjustment unit in sequence, and output the neural regulation linkage adjustment data table.

8. A motion disorder treatment and analysis system based on neural circuit feedback, characterized in that, The system is used to implement the movement disorder treatment analysis method based on neural circuit feedback as described in any one of claims 1-7, the system comprising: The signal monitoring module is based on the functional partitions of neural circuit activity. It compares the signal fluctuation amplitude and discharge trajectory changes within the same time period, filters out the synchronous abnormal intervals of the two, extracts the partition number and spatial coordinates, summarizes the abnormal time period and partition number, and generates a candidate set of movement disorders. Based on the candidate set of movement disorders, the partition localization module identifies the consistency between the signal gradient direction and the discharge fitting vector, marks the partition boundary number, matches the overall structure diagram of the neural circuit, extracts the partition number range of the signal gradient abnormal area, and establishes a suspected movement disorder partition layer. Based on the suspected motion obstacle partition layer, the obstacle linkage module retrieves the signal distribution matrix and the continuous data sequence of local functional features in the region, judges the connectivity and functional integrity of the abnormal signal boundary, marks the partition number that meets the linkage threshold of both, and outputs the motion obstacle linkage partition set. The activity early warning module analyzes the activity distribution trend and the degree of deviation of the original neural activity baseline curve of the corresponding partition based on the partition number of the motion obstacle linkage partition set, extracts the partition number of the deviation trend, completes the level identification according to the risk classification standard, and generates a list of abnormal neural partition activity analysis. Based on the list of abnormal activity in the neural partitions, the adjustment and optimization module finds the corresponding position number of the risk level partition in the neural circuit function diagram, retrieves the current adjustment response unit configuration list, compares the neural protection priority with the current response level, filters the partition numbers that need to be updated, and outputs the neural regulation linkage adjustment data table.

Images