Risk assessment method and system for Alzheimer's disease

Abstract

The invention discloses a risk assessment method and system for Alzheimer's disease, and relates to the technical field of data processing. The method comprises the following steps: acquiring brain magnetic resonance image data of a target user; performing time-frequency analysis on brain wave parameters in the brain magnetic resonance image data, determining a brain wave frequency spectrum curve, constructing a head movement track curve based on head posture parameters in the brain magnetic resonance image data, and generating a neuron activity curve based on brain blood flow parameters in the brain magnetic resonance image data; determining a plurality of target feature points; calculating a first risk value corresponding to each target feature point in the brain wave spectrum curve, a second risk value corresponding to the head movement track curve and a third risk value corresponding to the neuron activity curve; and determining an Alzheimer's disease risk assessment result by combining the first risk value, the second risk value and the third risk value. By implementing the technical scheme provided by the invention, the effect of improving the accuracy of risk assessment of the Alzheimer's disease is achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a risk assessment method, system, electronic device and storage medium for Alzheimer's disease. Background Art

[0002] With the advancement of medical technology, early diagnosis has become a key link in the management of many neurodegenerative diseases. Especially in the field of Alzheimer's disease research, the development of early diagnosis technology is of great significance for the prevention and treatment of the disease.

[0003] At present, the existing risk assessment methods for Alzheimer's disease mainly obtain data through electroencephalograms and other methods, and use the acquired single-dimensional data for risk assessment of Alzheimer's disease. However, in actual applications, since the risk of Alzheimer's disease is affected by multiple parameters, risk assessment based on single-dimensional data often lacks comprehensive consideration of multi-source data, making it difficult to comprehensively assess the patient's risk status, resulting in low accuracy in risk assessment for Alzheimer's disease. Summary of the invention

[0004] The present application provides a risk assessment method and system for Alzheimer's disease, which has the effect of improving the accuracy of risk assessment for Alzheimer's disease.

[0005] In a first aspect, the present application provides a method for risk assessment of Alzheimer's disease, comprising: Acquiring brain magnetic resonance image data of a target user; Performing time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data to determine the brain wave spectrum curve of the target user, constructing the head movement trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, and generating the neuron activity curve of the target user based on the brain blood flow parameters in the brain magnetic resonance image data; Determine a plurality of target feature points in the brain wave spectrum curve, the head movement trajectory curve, and the neuron activity curve; Calculating a first risk value corresponding to each of the target feature points in the brain wave spectrum curve, a second risk value corresponding to each of the target feature points in the head movement trajectory curve, and a third risk value corresponding to each of the target feature points in the neuron activity curve; The first risk value, the second risk value, and the third risk value are combined to determine an Alzheimer's disease risk assessment result of the target user.

[0006] In a second aspect of the present application, a risk assessment system for Alzheimer's disease is provided, the system comprising: A data acquisition module, used to acquire brain magnetic resonance image data of a target user; a curve determination module, configured to perform time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data, determine the brain wave spectrum curve of the target user, construct a head motion trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, and generate a neuron activity curve of the target user based on the brain blood flow parameters in the brain magnetic resonance image data; A risk value calculation module is used to determine a plurality of target feature points in the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve; calculate a first risk value corresponding to each of the target feature points in the brain wave spectrum curve, a second risk value corresponding to each of the target feature points in the head movement trajectory curve and a third risk value corresponding to each of the target feature points in the neuron activity curve; The risk assessment module is used to determine the Alzheimer's disease risk assessment result of the target user by combining the first risk value, the second risk value and the third risk value.

[0007] In a third aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program can implement a risk assessment method for Alzheimer's disease when loaded and executed by the processor.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a risk assessment method for Alzheimer's disease.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solution, the brain magnetic resonance image data of the target user is comprehensively analyzed and risk assessed, and the early risk of Alzheimer's disease is accurately identified and quantitatively assessed. By performing time-frequency analysis on brain wave parameters and obtaining brain wave spectrum curves, the electrical activity characteristics and cognitive function status of brain neurons can be accurately reflected; by analyzing the head posture parameters to construct the head movement trajectory curve, the subtle changes in motor control ability can be effectively captured; by analyzing the brain blood flow parameters to generate the neuron activity curve, the energy metabolism and functional status of brain tissue can be intuitively reflected. This multi-dimensional feature extraction method ensures the comprehensiveness of the evaluation indicators. In the feature analysis stage, by determining the target feature points in each curve, the key pathological changes can be accurately located, and by calculating the first risk value, the second risk value and the third risk value, the quantitative characterization of the abnormality degree can be achieved. This risk value calculation method based on multiple target feature points not only improves the accuracy of the evaluation, but also reflects the dynamic change process of the disease development. In the risk assessment stage, by combining the risk values ​​of the three dimensions for comprehensive analysis, a multi-level risk assessment system is established, which can effectively identify early pathological changes and potential risks, and improve the accuracy of risk assessment of Alzheimer's disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a flow chart of a risk assessment method for Alzheimer's disease provided in an embodiment of the present application; Figure 2 is a schematic diagram of a risk assessment system for Alzheimer's disease provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0011] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0012] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0014] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0015] The present application embodiment provides a method for risk assessment of Alzheimer's disease. In one embodiment, please refer to Figure 1 , Figure 1 This is a flow chart of a risk assessment method for Alzheimer's disease provided by an embodiment of the present application. The method can be implemented by a computer program, which can be integrated into an application or run as an independent tool application. The method can also be implemented by a single-chip microcomputer or run on a risk assessment system for Alzheimer's disease based on a von Neumann system. Specifically, the method can include the following steps: Step 101: Obtain brain magnetic resonance image data of a target user.

[0016] Among them, brain magnetic resonance image data refers to a collection of multi-dimensional physiological parameter information obtained by scanning the target user's brain through magnetic resonance imaging equipment. The brain magnetic resonance image data contains a variety of parameters reflecting the structure and functional state of the brain, mainly including brain wave parameters describing neuronal electrical activity, brain blood flow parameters representing the metabolic level of brain tissue, and head posture parameters reflecting motor control ability.

[0017] Specifically, the target user is first scanned by a magnetic resonance imaging device to obtain the target user's brain magnetic resonance image data. The magnetic resonance imaging device can simultaneously collect multiple dimensions of physiological parameter information, including brain wave parameters, brain blood flow parameters, and head posture parameters. Among them, the brain wave parameters reflect the state of electrical activity of the target user's brain neurons and can be used to evaluate the function of the nervous system; the brain blood flow parameters characterize the oxygen supply and metabolism level of the brain tissue and can reflect the activity of neurons; the head posture parameters reflect the target user's motor control ability, and these parameters are closely related to the pathogenesis of Alzheimer's disease. In the specific implementation, the magnetic resonance imaging device adopts high-resolution three-dimensional imaging technology to synchronously collect different parameter information through a multi-channel coil array to ensure the time consistency of the data. During the scanning process, the target user remains in a supine position with the head fixed to reduce motion artifacts. The scanning time usually lasts 15-20 minutes. After preprocessing, the collected magnetic resonance image data will automatically extract the above three types of parameter information and store them digitally. This multi-parameter synchronous acquisition method not only improves the efficiency of data acquisition, but also ensures the time correlation between different parameters, laying the foundation for subsequent comprehensive analysis.

[0018] Step 102: Perform time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data to determine the brain wave spectrum curve of the target user, construct the head movement trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, and generate the neuron activity curve of the target user based on the brain blood flow parameters in the brain magnetic resonance image data.

[0019] Among them, the EEG parameters refer to the potential fluctuation signals generated by the discharge of brain neuron groups collected by the electrode array set on the surface of the target user's scalp. This signal reflects the electrophysiological activity characteristics of neuron groups in different areas of the cerebral cortex when processing and transmitting information. The EEG parameters include EEG rhythms in different frequency bands, such as delta waves (0.5-4Hz), theta waves (4-8Hz), alpha waves (8-13Hz), beta waves (13-30Hz) and gamma waves (above 30Hz). Among them, alpha waves mainly reflect the basic activity state of the brain, beta waves are related to cognitive processing and attention, theta waves are related to memory and emotional processing, and gamma waves are closely related to advanced cognitive functions.

[0020] Brain blood flow parameters refer to real-time data obtained by measuring near-infrared spectral sensors that reflect the blood supply status of brain tissue. The data mainly includes blood oxygen concentration information and blood flow velocity information. The blood oxygen concentration information reflects the relative content of oxygenated hemoglobin and deoxygenated hemoglobin in brain tissue, while the blood flow velocity information represents the blood flow rate through the blood vessels in a specific brain area per unit time. When near-infrared light penetrates the scalp and skull to irradiate the brain tissue, hemoglobin in different oxygenation states has different absorption characteristics for near-infrared light of a specific wavelength. By detecting the intensity change of the reflected light, the dynamic change of blood oxygen concentration can be calculated.

[0021] Head posture parameters refer to a set of data collected in real time by an inertial measurement unit that reflects the movement state of the target user's head in three-dimensional space. The data mainly includes angular velocity information and acceleration information, where the angular velocity information describes the change in the rotation rate of the head around different axes, and the acceleration information reflects the change in the displacement acceleration of the head in space. Specifically, the gyroscope is responsible for collecting the angular velocity data of the head in three degrees of freedom: pitch, roll, and yaw, while the accelerometer measures the linear acceleration data of the head in three orthogonal directions: X, Y, and Z. These data can accurately characterize the instantaneous motion characteristics of the head, including the amplitude, speed, acceleration, and smoothness and coordination of the motion.

[0022] The EEG spectrum curve refers to the time series curve that reflects the energy changes of EEG activities in different frequency bands obtained by time-frequency analysis of EEG parameters. The curve represents the time dimension on the horizontal axis and the energy intensity of different frequency bands on the vertical axis, showing the dynamic change characteristics of EEG activities through continuous curve forms.

[0023] The head motion trajectory curve refers to a three-dimensional space curve that reflects the head motion characteristics after posture calculation and trajectory reconstruction of the head posture parameters. The curve is composed of a series of continuous spatial position points, each of which contains accurate three-dimensional coordinate information and corresponding timestamps, completely recording the spatial trajectory and time process of the head motion.

[0024] The neuron activity curve refers to a time series curve that reflects the level of neuronal metabolic activity in a local brain region, obtained by processing brain blood flow parameters. The curve represents the time process on the horizontal axis and the intensity of neuronal activity on the vertical axis, and is used to quantitatively describe the functional state and energy metabolism level of brain tissue.

[0025] Specifically, after acquiring multi-source data, it is necessary to convert various types of raw data into characteristic curves for analysis through special data processing methods. First, the collected EEG parameters are analyzed in time and frequency, and the time domain signal is decomposed into different frequency bands by wavelet transform method to obtain the dynamic characteristics of the energy of each frequency band changing with time. In the specific implementation, wavelet is selected as the basis function, and the original EEG signal is transformed into a continuous wavelet transform to calculate the time-frequency energy distribution diagram, and the EEG spectrum curve is drawn by extracting the energy change trend of different frequency bands. This curve can intuitively reflect the dynamic change process of EEG activity in different frequency bands, which is helpful to identify abnormal EEG rhythm patterns. Secondly, based on the head posture parameters collected by the inertial measurement unit, the angular velocity and acceleration data are fused and processed by the Kalman filter algorithm to eliminate measurement noise and drift errors, and then the posture solution algorithm is used to convert the processed data into spatial position coordinates, and finally a continuous head motion trajectory curve is constructed. This curve can accurately describe the spatial characteristics and time evolution process of head movement, which is convenient for discovering abnormal movement patterns. At the same time, for the parameters of brain blood flow, the hemodynamic response model is used to convert the near-infrared spectral signal into a time series reflecting the changes in local brain blood flow, and combined with the blood flow velocity information, a neuronal activity curve representing the metabolic activity of neurons is generated. This curve can reflect the functional activity state and energy metabolism level of different brain regions, and is helpful in discovering local blood flow abnormalities. Through the construction of these three characteristic curves, physiological information of different dimensions can be converted into a unified time series form, laying the foundation for subsequent multidimensional data fusion analysis.

[0026] Based on the above embodiment, as an optional embodiment, in step 102: performing time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data to determine the brain wave spectrum curve of the target user, this step may also include the following steps: Step 201: Determine a first EEG signal corresponding to the left brain region and a second EEG signal corresponding to the right brain region in the EEG wave parameters; and calculate a correlation coefficient between the first EEG signal and the second EEG signal.

[0027] The first EEG signal refers to the EEG time series signal collected from a specific electrode position in the left brain area of ​​the target user. This signal is a comprehensive expression of the electrical activity of the neuron group in the left hemisphere cerebral cortex, reflecting the functional state and information processing characteristics of the left brain area.

[0028] The second EEG signal refers to the EEG time series signal collected from the specific electrode position of the right brain area of ​​the target user. This signal is a comprehensive expression of the electrical activity of the neuron group in the cerebral cortex of the right hemisphere, reflecting the functional state and information processing characteristics of the right brain area.

[0029] The mutual correlation coefficient is a numerical indicator used to quantify the temporal correlation strength between the first and second EEG signals in the left and right brain regions. This coefficient is calculated using the Pearson correlation coefficient method, and its value range is between -1 and 1. It is used to characterize the degree of synchronization and functional connection strength between the signals of the two brain regions.

[0030] Specifically, after obtaining the EEG parameters of the target user, it is necessary to evaluate the functional connection status of the left and right brain regions, because early Alzheimer's disease will cause changes in the efficiency of information transmission between the cerebral hemispheres. First, according to the electrode layout standard of the international 10-20 system, the EEG parameters are divided into left and right brain regions according to spatial position. For the left brain region, the signals collected by electrodes such as F3, C3, P3, and T3 are selected as the first EEG signal. These electrodes correspond to the functional areas of the left hemisphere, such as the frontal lobe, central area, parietal lobe, and temporal lobe; for the right brain region, the signals of the corresponding electrodes such as F4, C4, P4, and T4 are selected as the second EEG signal, covering the corresponding functional areas of the right hemisphere. Before signal separation, preprocessing is required to improve the signal quality, including using a 50Hz notch filter to remove power frequency interference, applying the wavelet transform method to remove artifacts such as electromyography and electrooculography, and performing baseline drift correction. After obtaining the cleaned left and right brain signals, the signals are segmented using a 2-second time window, and 50% overlap is maintained between adjacent windows to ensure time continuity. Then, the Pearson correlation coefficient is calculated for the first EEG signal and the second EEG signal in each time window to obtain the cross-correlation coefficient reflecting the strength of functional connection between the left and right brains. The value range of this coefficient is between -1 and 1, which can quantitatively characterize the degree of synchronization between the two signals. By analyzing the time series characteristics of the cross-correlation coefficient, it can be found that under normal conditions, the EEG activities of the left and right brain regions show strong synchronization, and the cross-correlation coefficient is usually maintained at a high level of 0.6-0.8; in the early stages of the disease, due to the degeneration of neuronal function and damage to the corpus callosum fiber bundle, the cross-correlation coefficient will be significantly reduced to the range of 0.2-0.4, and there will be obvious fluctuations. This method based on cross-correlation analysis can sensitively detect abnormal changes in functional connections between the cerebral hemispheres, providing a reliable quantitative indicator for disease risk assessment.

[0031] Step 202: Filter the first EEG signal and the second EEG signal to obtain a first signal feature of the left brain region and a second signal feature of the right brain region.

[0032] The first signal feature refers to a multi-dimensional feature set obtained by frequency domain filtering decomposition and feature extraction of the first EEG signal in the left brain region. This feature set includes the energy distribution and time-varying characteristics of EEG activities in different frequency bands in the left brain region, and is used to characterize the functional state of the left hemisphere neuron population.

[0033] The second signal feature refers to the multi-dimensional feature set obtained by frequency domain filtering decomposition and feature extraction of the second EEG signal in the right brain area. This feature set includes the energy distribution and time-varying characteristics of EEG activities in different frequency bands in the right brain area, and is used to characterize the functional state of the right hemisphere neuron population.

[0034] Specifically, after completing the separation and correlation analysis of the left and right brain area signals, in order to further extract the characteristic information of the EEG activity, the first EEG signal and the second EEG signal need to be subjected to frequency domain analysis and filtering. This is because the EEG rhythms of different frequency bands reflect different states of neural activity, and Alzheimer's disease can cause changes in the energy distribution of specific frequency bands. In the specific implementation, the Butterworth bandpass filter is first used to decompose the signal in the frequency band, and the first EEG signal and the second EEG signal are respectively filtered into five frequency bands: δ wave (0.5-4Hz), θ wave (4-8Hz), α wave (8-13Hz), β wave (13-30Hz) and γ wave (30-45Hz). The order of the filter is set to 4th order to ensure good frequency selectivity and phase characteristics. The signal of each frequency band is subjected to Hilbert transform, and the instantaneous amplitude and phase information are calculated to obtain the envelope reflecting the energy change of each frequency band. Through this filtering process, the first signal characteristics of the left brain area and the second signal characteristics of the right brain area can be obtained respectively. These features include information such as the energy distribution of each frequency band, time-varying characteristics, and energy ratios between frequency bands. Under normal conditions, alpha waves show significant energy advantages when eyes are closed quietly, while the energy of theta and delta waves is relatively low; in the early stages of Alzheimer's disease, a significant decrease in alpha wave energy is observed, while the energy of theta waves is relatively enhanced. This change in spectral characteristics often precedes the onset of clinical symptoms. By comparing and analyzing the first signal feature and the second signal feature, we can find the energy asymmetry of the left and right brain regions in each frequency band, providing richer characteristic indicators for disease risk assessment.

[0035] Step 203: Generate a brain wave spectrum curve of the target user based on the mutual correlation coefficient, the first signal feature and the second signal feature.

[0036] Specifically, in order to accurately reflect the signal synergy of the left and right hemispheres of the target user's brain and their respective characteristic performances, it is necessary to generate the target user's brain wave spectrum curve based on the mutual correlation coefficient, the first signal feature and the second signal feature. First, the mutual correlation coefficient is used as a weight factor to adjust the fusion ratio of the first signal feature and the second signal feature. When the mutual correlation coefficient is high, it indicates that the signal synchronization of the left and right brain regions is strong. At this time, the fusion weight of the two signal features is increased; when the mutual correlation coefficient is low, the fusion weight is correspondingly reduced to highlight the difference in their respective characteristics. In the process of signal feature fusion, the first signal feature and the second signal feature are combined in a weighted average manner, and the time dimension information is introduced at the same time, and the characteristic values ​​at different time points are connected in sequence to form a spectrum curve that changes with time. The ordinate of the brain wave spectrum curve represents the signal intensity, and the abscissa represents the time. The fluctuation characteristics of the curve intuitively reflect the law of the target user's brain wave activity. This curve generation method based on multi-feature fusion not only retains the unique characteristics of the left and right brain regions, but also reflects the synergistic relationship between the two regions through the mutual correlation coefficient, so that the generated spectrum curve can more comprehensively characterize the overall working state of the brain.

[0037] Based on the above embodiment, as an optional embodiment, in step 102: constructing the head motion trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, this step may also include the following steps: Step 204: Obtain angular velocity information and acceleration information in the head posture parameters; determine the head rotation angle of the target user based on the angular velocity information, and determine the head displacement of the target user based on the acceleration information.

[0038] The angular velocity information refers to the physical quantity that describes the change in the rate at which the target user's head rotates around a fixed axis, indicating the angle of head rotation per unit time. The angular velocity information includes the instantaneous angular velocity values ​​of the head rotating around the X-axis (nodding action), Y-axis (shaking action), and Z-axis (tilting action) in three-dimensional space.

[0039] Acceleration information refers to the physical quantity that characterizes the rate of change of the target user's head movement speed, reflecting the speed of the head's movement state change in three-dimensional space. The acceleration information includes the head's linear acceleration components on the X-axis (front and back direction), Y-axis (left and right direction), and Z-axis (up and down direction), as well as the tangential acceleration component caused by rotation.

[0040] Specifically, angular velocity information and acceleration information are first extracted from the head posture parameters collected by the magnetic resonance imaging device. These two types of information reflect the dynamic characteristics of head rotation and translation movement, respectively. When processing angular velocity information, the numerical integration method is used to integrate the angular velocity over time to obtain the head rotation angle at different times. Select a suitable integration step, accumulate the angular velocity changes in each time period, and combine the gyroscope data for zero drift compensation to ensure the accuracy of the calculation results. For the processing of acceleration information, a double integration method is used. First, the acceleration is integrated once to obtain the velocity, and then the head displacement is obtained by a second integration. In the integration process, the Kalman filter algorithm is introduced to suppress the cumulative effect of the integral error, and the noise interference is filtered by setting a reasonable threshold. This analysis method based on kinematic parameters can quantitatively describe the stability and coordination of the target user's head movement, which are closely related to the degeneration of motor control function in the early stage of Alzheimer's disease. By accurately obtaining the head rotation angle and displacement information, reliable basic data can be provided for subsequent trajectory analysis, which helps to detect abnormal movement patterns early. At the same time, this analysis method has good real-time performance and can dynamically track changes in head movement status, improving the timeliness and accuracy of the evaluation.

[0041] Step 205: Generate a head motion trajectory curve of the target user according to the head rotation angle and the head displacement.

[0042] Specifically, a three-dimensional coordinate system is first established to synchronize the head rotation angle and head displacement data in time, and the motion state of the head in space is described in the form of a parametric equation. Among them, the head rotation angle is decomposed into three components: pitch angle, yaw angle and roll angle, and the head displacement contains spatial coordinates in the three directions of X, Y and Z. Through the time series mapping method, the angle and displacement data of each time point are combined into a spatial position point, and the cubic spline interpolation algorithm is used to smoothly connect these discrete position points to form a continuous motion trajectory curve. In the process of curve generation, an adaptive filtering algorithm is introduced to eliminate the influence of high-frequency jitter and measurement noise to ensure the smoothness and accuracy of the trajectory curve. The generated head motion trajectory curve is presented in a three-dimensional graphical form, in which the shape of the curve reflects the spatial characteristics of the motion, the smoothness of the curve represents the coordination of the motion, and the density of the curve reflects the frequency characteristics of the motion. This visual trajectory expression method can not only intuitively reflect the stability and regularity of head movement, but also discover potential motion control abnormalities through quantitative analysis of trajectory characteristics. By comparing the standard trajectory pattern of normal people, abnormal motion characteristics related to Alzheimer's disease can be identified in time, providing a basis for risk assessment.

[0043] Based on the above embodiment, as an optional embodiment, in step 102: generating a neuron activity curve of a target user based on the brain blood flow parameters in the brain magnetic resonance image data, this step may also include the following steps: Step 206: Obtain blood oxygen concentration information and blood flow velocity information from the cerebral blood flow parameters; calculate the concentration change rate of the blood oxygen concentration information within a preset sampling period.

[0044] Among them, blood oxygen concentration information refers to the physiological parameter that reflects the ratio of hemoglobin to oxygen molecules in the target user's brain tissue, and represents the level of oxygen content in the local blood of the brain tissue. The blood oxygen concentration information includes the relative ratio of oxygenated hemoglobin and deoxygenated hemoglobin in the brain tissue, as well as the content of dissolved oxygen in the blood.

[0045] Blood flow velocity information refers to the physical quantity that characterizes the speed of blood flow in the target user's brain blood vessels, reflecting the dynamic characteristics of brain tissue blood perfusion. The blood flow velocity information includes the linear velocity and volume flow of blood flow in the cerebral arteries, veins and capillary networks, as well as the pulsation characteristics and direction information of the blood flow.

[0046] Specifically, first, blood oxygen concentration information and blood flow velocity information are extracted from the brain blood flow parameters collected by the magnetic resonance imaging device. These two types of information reflect the oxygen supply level and blood perfusion efficiency of brain tissue, respectively. When processing blood oxygen concentration information, a reasonable sampling period, such as 100 milliseconds, is set to perform time series analysis on the continuously collected blood oxygen concentration data. The instantaneous rate of change of blood oxygen concentration is obtained by calculating the difference in blood oxygen concentration between adjacent sampling points and dividing it by the sampling time interval. In order to improve the calculation accuracy, the sliding window method is used to average the data within multiple sampling periods, and a digital filtering algorithm is introduced to eliminate the influence of measurement noise. This time series-based analysis method can accurately reflect the dynamic change process of brain tissue oxygen supply status, and the rate of change of blood oxygen concentration directly reflects the oxygen consumption characteristics and metabolic activity of brain tissue. Since Alzheimer's disease is often accompanied by abnormal brain tissue metabolism in the early stage, potential pathological changes can be detected early by monitoring the change trend of blood oxygen concentration. At the same time, this analysis method has a high time resolution and can capture blood oxygen fluctuations in a short period of time, providing an important basis for evaluating the functional state of the brain. The acquisition and processing of this information provides reliable physiological parameter support for subsequent risk assessment and improves the accuracy of the assessment results.

[0047] Step 207: Based on a preset blood flow velocity mapping table, determine the brain oxygen supply index corresponding to the blood flow velocity information.

[0048] The preset blood flow velocity mapping table refers to a data structure that establishes the correspondence between blood flow velocity and brain oxygen supply index, which contains different blood flow velocity intervals and their corresponding standardized oxygen supply index reference values. The mapping table is constructed based on large-scale clinical research data and statistical analysis results of healthy people, and contains multiple blood flow velocity segmented intervals, each of which corresponds to a standardized oxygen supply index value.

[0049] The brain oxygen supply index is a comprehensive indicator used to quantitatively evaluate the adequacy of oxygen supply to brain tissue, reflecting the overall efficiency of blood perfusion and oxygen delivery to brain tissue. The index is a dimensionless value obtained by standardizing multiple physiological parameters such as blood flow velocity, vascular cross-sectional area, and blood oxygen concentration. Its value range is usually between 0 and 1. The larger the value, the better the oxygen supply.

[0050] Specifically, in order to accurately quantify the oxygen supply status of brain tissue, it is necessary to convert blood flow velocity information into a more physiologically meaningful brain oxygen supply index. First, a preset blood flow velocity mapping table is established. The mapping table is based on a large amount of clinical data statistical analysis and contains standardized oxygen supply index values ​​corresponding to different blood flow velocity intervals. When performing the mapping conversion, the real-time collected blood flow velocity information is matched with the velocity interval in the mapping table, and the corresponding brain oxygen supply index is determined by the piecewise linear interpolation method. In order to improve the accuracy of the conversion, the anatomical position and diameter of the blood vessels are considered in the mapping process, and the blood flow velocity in different brain regions is corrected by the corresponding weight coefficient. At the same time, the temperature correction and pressure compensation mechanism are introduced to eliminate the influence of environmental factors on the blood flow velocity measurement. This conversion method based on the mapping table not only simplifies the complex hemodynamic calculations, but also provides standardized evaluation indicators. By converting continuous blood flow velocity data into the brain oxygen supply index, the degree of oxygen supply to the brain tissue can be intuitively reflected. Since the early stage of Alzheimer's disease is often accompanied by insufficient blood supply to local brain tissue, this standardized oxygen supply index can help to detect potential circulatory dysfunction early. At the same time, this conversion method has good comparability, which facilitates comparative analysis between different periods and different individuals, and provides a quantitative basis for risk assessment.

[0051] Step 208: Generate a neuron activity curve of the target user based on the time change rate and the brain oxygen supply index.

[0052] Among them, the neuron activity curve refers to a graphical expression that describes the dynamic changes in the functional state of neurons in the target user's brain over time, reflecting the energy metabolism and information transmission efficiency of nerve cells.

[0053] Specifically, in order to display the functional state of the target user's brain neurons, it is necessary to generate a neuron activity curve based on the time rate of change of blood oxygen concentration and the brain oxygen supply index. First, the time rate of change of blood oxygen concentration and the brain oxygen supply index are synchronized to ensure the correspondence between the two sets of data on the time axis. The linear weighted method is used to fuse the two indicators, where the weight coefficient of the time rate of change is set to 0.6, reflecting the dominant role of neuronal metabolic demand, and the weight coefficient of the brain oxygen supply index is set to 0.4, reflecting the basic support role of oxygen supply capacity. In the data processing process, the sliding average algorithm is used to smooth the calculation results, and a suitable time window (usually 200 milliseconds) is selected for data smoothing to eliminate the influence of instantaneous fluctuations. At the same time, a fixed sampling interval (usually 50 milliseconds) is set to ensure the uniform distribution of data points. In the coordinate system, time is used as the horizontal axis, the marking unit is seconds, the calculated neuron activity intensity is used as the vertical axis, and the numerical range is normalized to between 0-1. By connecting adjacent data points and using the cubic spline interpolation method to achieve smooth transition, a continuous neuron activity curve is finally formed. This visual expression can directly reflect the dynamic changes in neuronal activity. The fluctuation amplitude of the curve reflects the degree of change in neuronal excitability, and the fluctuation frequency of the curve represents the rhythmic characteristics of neuronal activity. Since early Alzheimer's disease often manifests as subtle changes in neuronal function, potential functional abnormalities can be detected early by analyzing the characteristic parameters of the activity curve, such as the average activity level, fluctuation period, and peak-to-valley ratio. This analysis method has high temporal accuracy and can capture rapid changes in neuronal activity.

[0054] Step 103: Determine multiple target feature points in the brain wave spectrum curve, the head movement trajectory curve, and the neuron activity curve.

[0055] Among them, target feature points refer to key data points with specific physiological significance in the EEG spectrum curve, head movement trajectory curve and neuron activity curve. These data points can reflect significant changes in the functional state of the brain.

[0056] Specifically, in order to accurately capture the key change characteristics of the target user's brain function state, it is necessary to extract target feature points with diagnostic value from the EEG spectrum curve, head movement trajectory curve and neuron activity curve. The three curves are synchronously analyzed using a unified time base, and feature points with physiological significance are identified on each curve. In the EEG spectrum curve, the peak points, valley points and inflection points of α waves (8-13Hz), β waves (14-30Hz) and θ waves (4-7Hz) are mainly extracted. These feature points reflect the intensity changes of brain activities in different frequency bands. In the head movement trajectory curve, the turning points, pause points and acceleration change points of the movement speed are identified. These feature points characterize the stability and coordination of the head movement. In the neuron activity curve, the maximum, minimum and mutation points of the activity intensity are focused on. These feature points reflect the dynamic changes of the neuron function state. In the feature point extraction process, the threshold detection method is used to determine the value mutation position, and the effective feature points are screened by setting reasonable threshold parameters (such as the deviation from the local mean is more than 20%). At the same time, a time window constraint is introduced to ensure that there is a sufficient time interval between adjacent feature points (usually not less than 100 milliseconds) to avoid feature points being too dense. For each identified feature point, its time coordinate and amplitude information are recorded, and the feature points are classified and labeled for subsequent extraction and analysis of target features. This feature point extraction method can effectively capture key change information in the curve and provide accurate quantitative indicators for assessing the early risk of Alzheimer's disease. Since the early stage of the disease often manifests as coordinated abnormalities of multiple physiological indicators, potential functional disorders can be discovered by analyzing the spatiotemporal correlation of feature points on different curves. This multi-dimensional feature extraction method improves the sensitivity and specificity of diagnosis and provides a reliable data basis for subsequent risk assessment.

[0057] Based on the above embodiment, as an optional embodiment, in step 103: determining multiple target feature points in the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve, this step may also include the following steps: Step 301: Divide the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve into multiple time windows.

[0058] Specifically, in order to accurately analyze the dynamic change characteristics of the target user's brain function state, it is necessary to divide the EEG spectrum curve, head movement trajectory curve and neuron activity curve into time windows. First, a unified time base is determined, and the total time range (usually 10 minutes) in the detection process is divided into multiple continuous and equal-length time windows. The length of each time window is set to 30 seconds, and a 25% overlap area is allowed between adjacent windows to ensure the continuity of data analysis. In the division process, a synchronized time scale is used for the three curves to ensure that the data of different curves in the same time window have a time correspondence. In order to improve the accuracy of the analysis, equal-interval sampling is used in each time window, and the sampling interval is set to 50 milliseconds to ensure the uniform distribution of data points. At the same time, the Hanning window function is used for smoothing at the window boundary to reduce the impact of window segmentation on signal continuity. This time window division method can decompose long-term continuous signals into multiple short-time series that are easy to analyze, which is conducive to capturing feature changes on the local time scale. Since the functional changes in the early stage of Alzheimer's disease are often manifested as abnormal fluctuations in certain time periods, the time intervals in which these abnormalities occur can be accurately located through window analysis.

[0059] Step 302: Based on multiple data points of the EEG spectrum curve, the head movement trajectory curve and the neuron activity curve in each time window, the mean and standard deviation of the EEG spectrum curve, the head movement trajectory curve and the neuron activity curve in each time window are calculated accordingly.

[0060] Specifically, the data points in each 30-second time window are first preprocessed to remove possible outliers (data points outside the range of plus or minus three times the standard deviation of the local mean). For the EEG spectrum curve, the arithmetic mean of the energy of the α, β and θ frequency bands is calculated to reflect the average intensity level of EEG activity in each frequency band; at the same time, the standard deviation of the energy values ​​of these frequency bands is calculated to characterize the discrete degree of energy fluctuation. For the head movement trajectory curve, the arithmetic mean of the movement speed is calculated to reflect the overall activity of the head movement; the standard deviation of the speed value is calculated to characterize the changing characteristics of movement stability. For the neuronal activity curve, the arithmetic mean of the activity intensity is calculated to reflect the average functional level of the neuronal population; the standard deviation of the activity value is calculated to characterize the fluctuation amplitude of the functional state. In the calculation process, for the n sampling points in each time window, the mean calculation adopts the arithmetic mean formula, and the standard deviation calculation adopts the overall standard deviation formula to ensure the accuracy of the statistical results. This statistical feature calculation method can summarize the detailed changes in the time window into statistically significant characteristic parameters. Since early Alzheimer's disease often manifests as abnormal fluctuations in physiological indicators, overall changes in functional levels can be found by analyzing the mean, and abnormalities in functional stability can be identified by analyzing the standard deviation. For each time window, the six statistical features calculated (the mean and standard deviation of each of the three curves) are combined into feature vectors, which fully reflect the statistical characteristics of the brain's functional state during that time period.

[0061] Step 303: For each time window, data points in the EEG spectrum curve, the head movement trajectory curve, and the neuron activity curve that exceed a preset multiple of the mean standard deviation are determined as target feature points.

[0062] Specifically, in order to accurately identify abnormal fluctuation points with diagnostic value from massive data, it is necessary to screen the data points of the three curves in each time window based on statistical characteristics, and determine the data points that significantly deviate from the normal range as target feature points. First, a corresponding standard deviation multiple threshold is set for each curve, where the threshold of the EEG spectrum curve is set to 2.5 times the standard deviation, taking into account the natural fluctuation characteristics of the EEG signal; the threshold of the head movement trajectory curve is set to 2 times the standard deviation, reflecting the strict requirements of motor coordination; the threshold of the neuron activity curve is set to 3 times the standard deviation, reflecting the larger physiological fluctuation range of neuron activity. In each 30-second time window, the deviation between each data point and the mean of the window is calculated, and the absolute value of the deviation is divided by the corresponding standard deviation to obtain the standardized deviation value. When the standardized deviation value of a data point exceeds the preset multiple threshold, the point is marked as a target feature point, and its time coordinates, amplitude and curve type are recorded at the same time. This feature point recognition method based on statistical significance can adaptively adjust the judgment criteria and reasonably determine abnormal fluctuation points under different activity states. Because functional abnormalities in the early stages of Alzheimer's disease often manifest as discrete mutational events, this method can accurately capture these critical moments of change.

[0063] Step 104: Calculate the first risk value corresponding to each target feature point in the EEG spectrum curve, the second risk value corresponding to each target feature point in the head movement trajectory curve, and the third risk value corresponding to each target feature point in the neuron activity curve.

[0064] Among them, the first risk value refers to a quantitative indicator calculated based on the abnormal characteristics of the target feature points in the EEG spectrum curve, which comprehensively reflects the degree of abnormality of the brain's electrical activity at a specific moment.

[0065] The second risk value refers to a quantitative index calculated based on the abnormal features of the target feature points in the head motion trajectory curve, which comprehensively reflects the abnormal degree of the target user's head motion control ability.

[0066] The third risk value refers to a quantitative indicator calculated based on the abnormal characteristics of the target feature points in the neuron activity curve. This indicator comprehensively reflects the degree of abnormality in the functional state of the brain neuron population.

[0067] Specifically, in order to accurately quantify the abnormality of each physiological indicator of the target user, it is necessary to calculate the risk value corresponding to the target feature point in the EEG spectrum curve, the head motion trajectory curve and the neuron activity curve respectively. In the specific implementation, the target feature points of each curve are first classified and grouped according to the time window and curve type. For the target feature point in the EEG spectrum curve, three key factors are considered when calculating its first risk value: the standardized deviation amplitude of the feature point (for example, accounting for 40% of the weight), the energy proportion of the feature point in the corresponding frequency band (for example, accounting for 35% of the weight), and the time correlation with the adjacent feature point (for example, accounting for 25% of the weight). The weighted and normalized processing of these three factors is performed to obtain the first risk value ranging from 0 to 1. For the target feature point in the head motion trajectory curve, the focus of calculating its second risk value is: the mutation amplitude of the motion speed (for example, accounting for 45% of the weight), the rate of change of motion acceleration (for example, accounting for 30% of the weight), and the abnormality of the motion duration (for example, accounting for 25% of the weight). The second risk value is also obtained through weighted fusion and normalization. For the target feature points in the neuron activity curve, the third risk value is calculated by comprehensively considering: the degree of deviation of activity intensity (for example, 50% of the weight), the persistence of activity changes (for example, 30% of the weight), and the synchronization with other physiological indicators (for example, 20% of the weight). These factors are weighted and normalized to obtain the third risk value. This multi-dimensional risk quantification method can comprehensively assess the severity of different types of physiological abnormalities. Since Alzheimer's disease often manifests as coordinated abnormalities of multiple indicators in the early stages, by calculating risk values ​​in different dimensions, the early signs of the disease can be accurately captured.

[0068] Based on the above embodiment, as an optional embodiment, in step 104: calculating the first risk value corresponding to each target feature point in the brain wave spectrum curve, the second risk value corresponding to each target feature point in the head movement trajectory curve, and the third risk value corresponding to each target feature point in the neuron activity curve, this step may also include the following steps: Step 401: Calculate the average characteristic values ​​of the EEG spectrum curve, the head movement trajectory curve and the neuron activity curve at each target characteristic point respectively.

[0069] The average eigenvalue refers to the comprehensive numerical index obtained by extracting features and weighted averaging the corresponding physiological indicators within the local time window corresponding to the target feature point.

[0070] Specifically, the target feature points of each curve are first grouped in time series, and a sampling window (for example, the window length is 2 seconds) is taken with the target feature point as the center to extract the data sequence in the window. For the target feature points of the EEG spectrum curve, when calculating its average eigenvalue, the spectrum data in the window is first decomposed into α waves, β waves and θ waves, and then the weighted average of the energy of each frequency band is calculated. The weight coefficient is determined according to the correlation between each frequency band and cognitive function. For the target feature points of the head movement trajectory curve, when calculating its average eigenvalue, the instantaneous velocity, acceleration and angular velocity in the window are comprehensively considered, and the weighted average is obtained after normalization. For the target feature points of the neuronal activity curve, when calculating its average eigenvalue, the activity intensity data in the window is smoothed, and the average activity level is calculated after removing high-frequency noise. This average eigenvalue calculation method based on a local window can effectively extract stable features around the target feature points and reduce the impact of random fluctuations.

[0071] Step 402: Obtain a preset first correlation coefficient corresponding to the brain wave spectrum curve, a preset second correlation coefficient corresponding to the head movement trajectory curve, and a preset third correlation coefficient corresponding to the neuron activity curve.

[0072] Among them, the preset first correlation coefficient refers to a weight coefficient determined based on large-scale clinical research data and expert experience, which reflects the importance of the brain wave spectrum curve in the early diagnosis of Alzheimer's disease.

[0073] The preset second correlation coefficient refers to a weight coefficient determined based on large-scale clinical research data and expert experience, which reflects the importance of the head movement trajectory curve in the early diagnosis of Alzheimer's disease.

[0074] The preset third correlation coefficient refers to a weight coefficient determined based on large-scale clinical research data and expert experience, which reflects the importance of the neuronal activity curve in the early diagnosis of Alzheimer's disease.

[0075] Specifically, firstly, based on large-scale clinical research data and expert experience, the correlation strength of the three curves with the early diagnosis of Alzheimer's disease is determined through statistical analysis. For the EEG spectrum curve, the preset first correlation coefficient is set to 0.4, because the change of EEG activity is one of the most significant and specific manifestations of the early stage of the disease; for the head movement trajectory curve, the preset second correlation coefficient is set to 0.3, reflecting the important supplementary role of motor control dysfunction in the early diagnosis of the disease; for the neuron activity curve, the preset third correlation coefficient is set to 0.3, reflecting the indicative role of neuron function status on disease progression. The setting of these correlation coefficients adopts an adaptive weighting mechanism, that is, the coefficient value can be dynamically adjusted according to the diagnostic value of each indicator at different stages of the disease, but the sum of the three coefficients is always guaranteed to be 1. This correlation coefficient configuration scheme based on clinical verification can effectively balance the contribution of various physiological indicators in risk assessment and improve the accuracy and reliability of the assessment results. Since the development of Alzheimer's disease often presents the characteristics of coordinated changes in multiple physiological indicators, this multi-dimensional pathological change can be better captured by reasonably setting the correlation coefficient.

[0076] Step 403: Multiply the preset first correlation coefficient by the average eigenvalue of the EEG spectrum curve at each target feature point to obtain a first risk value; multiply the preset second correlation coefficient by the average eigenvalue of the head movement trajectory curve at each target feature point to obtain a second risk value; multiply the preset third correlation coefficient by the average eigenvalue of the neuron activity curve at each target feature point to obtain a third risk value.

[0077] Specifically, in order to convert the characteristic values ​​of each physiological indicator into a risk assessment indicator with comparability and practical diagnostic significance, it is necessary to perform weighted calculation on the preset correlation coefficient and the corresponding average characteristic value. First, for the EEG spectrum curve, the preset first correlation coefficient 0.4 is multiplied by the average characteristic value at each target characteristic point to obtain the first risk value reflecting the degree of EEG abnormality; then for the head movement trajectory curve, the preset second correlation coefficient 0.3 is multiplied by the average characteristic value at each target characteristic point to obtain the second risk value characterizing motor function abnormality; finally, for the neuron activity curve, the preset third correlation coefficient 0.3 is multiplied by the average characteristic value at each target characteristic point to obtain the third risk value reflecting the functional state of the neuron. This weighted calculation method not only takes into account the actual measured values ​​of each physiological indicator, but also reflects the importance of different indicators in disease diagnosis through the preset correlation coefficient. Since the early manifestations of Alzheimer's disease often involve coordinated changes in multiple physiological systems, this method of calculating each risk value separately can independently evaluate the degree of abnormality of each system. In practical applications, this calculation scheme can effectively balance the contribution of various indicators, so that the calculated risk value not only maintains the changing characteristics of the original characteristics, but also reflects the importance judgment of different indicators in clinical diagnostic experience. Through this weighted conversion, physiological indicators of different dimensions and different physical meanings can be uniformly converted into standardized risk assessment indicators, providing standardized input parameters for subsequent comprehensive risk assessment.

[0078] Step 105: Determine the Alzheimer's disease risk assessment result of the target user by combining the first risk value, the second risk value, and the third risk value.

[0079] Among them, the Alzheimer's disease risk assessment result refers to a comprehensive assessment index obtained by performing nonlinear weighted fusion calculation on the first risk value, the second risk value and the third risk value. The result includes quantitative risk level judgment, such as low risk 0-0.3, medium risk 0.3-0.6, high risk 0.6-1.0, as well as abnormal characteristic analysis of various physiological functions.

[0080] Specifically, a three-dimensional feature space is first constructed, with the first risk value, the second risk value and the third risk value as the three coordinate axes, and the risk status of the target user is represented as a feature point in the space. Then, a nonlinear weighted fusion algorithm is used to consider the interaction between the three risk values ​​to calculate the comprehensive risk score. The algorithm not only considers the independent contribution of each risk value, but also introduces cross terms to characterize the amplification effect of multi-system collaborative abnormalities, that is, when multiple risk values ​​increase at the same time, the comprehensive risk will show nonlinear growth. Based on a large amount of clinical validation data, multiple risk thresholds are set, and the comprehensive risk score is divided into three levels: low risk (0-0.3), medium risk (0.3-0.6) and high risk (0.6-1.0). In addition, the time series analysis method is used to examine the changing trend of each risk value, and the risk change rate is used as an important supplementary information for the evaluation results. This multidimensional risk assessment method can effectively capture subtle changes in the early stage of the disease, especially when some physiological indicators have not yet reached an obviously abnormal level. By analyzing the collaborative change pattern of multiple indicators, potential pathological changes can be discovered early. In practical applications, this assessment method not only gives a quantitative risk level judgment, but also provides a detailed abnormal feature analysis report, including the specific abnormal manifestations and change trends of various physiological functions, providing decision support for clinicians to formulate personalized intervention plans.

[0081] Based on the above embodiment, as an optional embodiment, in step 105: combining the first risk value, the second risk value and the third risk value to determine the Alzheimer's disease risk assessment result of the target user, this step may also include the following steps: Step 501: Calculate the weighted average of the first risk value, the second risk value and the third risk value; determine the risk probability corresponding to the weighted average based on a preset risk threshold interval, wherein the preset risk threshold interval includes weighted average intervals corresponding to multiple risk probabilities.

[0082] Among them, risk probability refers to a standardized probability indicator obtained by weighted average calculation of the first risk value, the second risk value and the third risk value, and mapping based on a preset risk threshold interval. Its numerical range is 10%-90% or above, reflecting the possibility of the target user suffering from Alzheimer's disease.

[0083] Specifically, the weighted average algorithm is first used to calculate the comprehensive value of the first risk value, the second risk value and the third risk value. The weight configuration based on clinical research optimization is used in the calculation process, and the three risk values ​​are assigned weight coefficients of 0.4, 0.3 and 0.3 respectively. This weight distribution not only takes into account the clinical importance of each indicator, but also maintains consistency with the aforementioned correlation coefficient. Then, the weighted average is mapped based on the risk threshold interval established by large-scale clinical data statistical analysis. The preset risk threshold intervals include: the weighted average in the range of 0-0.2 corresponds to a risk probability of 10%-30%, indicating a slight abnormality; the range of 0.2-0.4 corresponds to a risk probability of 30%-50%, indicating a moderate abnormality; the range of 0.4-0.6 corresponds to a risk probability of 50%-70%, indicating a significant abnormality; the range of 0.6-0.8 corresponds to a risk probability of 70%-90%, indicating a serious abnormality; the range of 0.8-1.0 corresponds to a risk probability of more than 90%, indicating an extremely severe abnormality.

[0084] Step 502: According to the risk probability, the Alzheimer's disease risk level corresponding to the target user is matched in the database.

[0085] Specifically, a mapping relationship table between risk probability and risk level was first constructed in the pre-established risk assessment database. The table was formulated based on a large number of clinical case statistics and expert consensus, and the risk probability was divided into five intervals corresponding to different risk levels: 10%-30% corresponds to mild risk, indicating that only regular observation is required; 30%-50% corresponds to low risk, and it is recommended to strengthen cognitive function monitoring; 50%-70% corresponds to moderate risk, requiring targeted intervention; 70%-90% corresponds to high risk, and specialist evaluation and early intervention are recommended; and more than 90% corresponds to extremely high risk, requiring immediate professional medical intervention. By querying the database, the system matches the risk probability of the target user with the preset level interval to determine its corresponding risk level. This risk grading method based on database matching has strong reliability and standardized characteristics, and can provide a clear grading basis for clinical decision-making.

[0086] Step 503: Generate a risk assessment report corresponding to the risk probability and risk level, and use the risk assessment report as the Alzheimer's disease risk assessment result of the target user.

[0087] Specifically, a standardized report template is first constructed, which contains core contents such as patient basic information, evaluation date, test data of various physiological indicators, risk value analysis results, risk probability and risk level. In the process of report generation, the system automatically integrates the specific data of the first risk value, the second risk value and the third risk value and their time series change trends, and combines the calculated risk probability and the matching risk level to generate a graphic evaluation report. The report not only shows the quantitative evaluation results, but also contains targeted health advice and intervention plans. For example, for patients with moderate risk (risk probability 50%-70%), the report will detail the areas of cognitive function that need to be focused on and the recommended preventive measures. In terms of the visual presentation of the report, trend charts, radar charts and other charts are used to intuitively display the abnormal degree and change characteristics of various indicators, so that doctors and patients can understand the evaluation results. This standardized report output method has good clinical practicality, can provide doctors with complete diagnosis and treatment reference information, and also facilitates patients to understand their own health status.

[0088] Reference Figure 2 , is a risk assessment system for Alzheimer's disease provided in an embodiment of the present application, the system comprising: a data acquisition module, a curve determination module, a risk value calculation module, and a risk assessment module, wherein: A data acquisition module, used to acquire brain magnetic resonance image data of a target user; A curve determination module is used to perform time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data, determine the brain wave spectrum curve of the target user, construct the head movement trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, and generate the neuron activity curve of the target user based on the brain blood flow parameters in the brain magnetic resonance image data; A risk value calculation module is used to determine multiple target feature points in the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve; calculate a first risk value corresponding to each target feature point in the brain wave spectrum curve, a second risk value corresponding to each target feature point in the head movement trajectory curve and a third risk value corresponding to each target feature point in the neuron activity curve; The risk assessment module is used to determine the Alzheimer's disease risk assessment result of the target user by combining the first risk value, the second risk value and the third risk value.

[0089] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0090] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0091] The communication bus 302 is used to realize the connection and communication between these components.

[0092] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0093] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0094] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0095] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program for a risk assessment method for Alzheimer's disease.

[0096] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the memory 305 to store an application for a risk assessment method for Alzheimer's disease. When executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0097] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0102] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0103] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not recorded in the present disclosure. The description and examples are to be regarded as exemplary only.

Claims

1. A method for risk assessment of Alzheimer's disease, characterized in that: include: Acquiring brain magnetic resonance image data of a target user; Performing time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data to determine the brain wave spectrum curve of the target user, constructing the head movement trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, and generating the neuron activity curve of the target user based on the brain blood flow parameters in the brain magnetic resonance image data; Determine a plurality of target feature points in the brain wave spectrum curve, the head movement trajectory curve, and the neuron activity curve; Calculating a first risk value corresponding to each of the target feature points in the brain wave spectrum curve, a second risk value corresponding to each of the target feature points in the head movement trajectory curve, and a third risk value corresponding to each of the target feature points in the neuron activity curve; The first risk value, the second risk value, and the third risk value are combined to determine an Alzheimer's disease risk assessment result of the target user.

2. The risk assessment method for Alzheimer's disease according to claim 1, characterized in that: The step of performing time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data to determine the brain wave spectrum curve of the target user includes: Determine the first EEG signal corresponding to the left brain region and the second EEG signal corresponding to the right brain region in the EEG wave parameters Calculating a mutual correlation coefficient between the first EEG signal and the second EEG signal; Performing filtering processing on the first EEG signal and the second EEG signal to obtain a first signal feature of the left brain region and a second signal feature of the right brain region; Based on the mutual correlation coefficient, the first signal feature and the second signal feature, a brain wave spectrum curve of the target user is generated.

3. The risk assessment method for Alzheimer's disease according to claim 1, characterized in that: The step of constructing a head motion trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data includes: Obtaining angular velocity information and acceleration information in the head posture parameters; Determine the rotation angle of the target user's head based on the angular velocity information, and determine the displacement of the target user's head based on the acceleration information; A head movement trajectory curve of the target user is generated according to the head rotation angle and the head displacement.

4. The risk assessment method for Alzheimer's disease according to claim 1, characterized in that: The step of generating the neuron activity curve of the target user based on the brain blood flow parameter in the brain magnetic resonance image data comprises: Obtaining blood oxygen concentration information and blood flow velocity information from the cerebral blood flow parameters; Calculating the concentration change rate of the blood oxygen concentration information within a preset sampling period; Determining a brain oxygen supply index corresponding to the blood flow velocity information based on a preset blood flow velocity mapping table; A neuron activity curve of the target user is generated according to the time change rate and the brain oxygen supply index.

5. The risk assessment method for Alzheimer's disease according to claim 1, characterized in that: The determining of a plurality of target feature points in the brain wave spectrum curve, the head movement trajectory curve, and the neuron activity curve comprises: Dividing the brain wave spectrum curve, the head movement trajectory curve, and the neuron activity curve into a plurality of time windows; Based on a plurality of data points of the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve in each of the time windows, correspondingly calculating the mean and standard deviation of the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve in each of the time windows; For each of the time windows, data points in the EEG spectrum curve, the head movement trajectory curve, and the neuron activity curve that exceed a preset multiple of the mean value by standard deviation are determined as target feature points.

6. The risk assessment method for Alzheimer's disease according to claim 1, characterized in that: The calculating of the first risk value corresponding to each target feature point in the brain wave spectrum curve, the second risk value corresponding to each target feature point in the head movement trajectory curve, and the third risk value corresponding to each target feature point in the neuron activity curve includes: Respectively calculating the average characteristic values ​​of the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve corresponding to each of the target characteristic points; Obtaining a preset first correlation coefficient corresponding to the brain wave spectrum curve, a preset second correlation coefficient corresponding to the head movement trajectory curve, and a preset third correlation coefficient corresponding to the neuron activity curve; Multiplying the preset first correlation coefficient by the average characteristic value of the brain wave spectrum curve corresponding to each target characteristic point to obtain a first risk value; Multiplying the preset second correlation coefficient by the average characteristic value of the head motion trajectory curve corresponding to each target characteristic point to obtain a second risk value; The preset third correlation coefficient is multiplied by the average characteristic value of the neuron activity curve corresponding to each target characteristic point to obtain a third risk value.

7. The risk assessment method for Alzheimer's disease according to claim 1, characterized in that: The combining the first risk value, the second risk value, and the third risk value to determine the Alzheimer's disease risk assessment result of the target user includes: Calculating a weighted average of the first risk value, the second risk value, and the third risk value; Determine the risk probability corresponding to the weighted average value based on a preset risk threshold interval, wherein the preset risk threshold interval includes a plurality of weighted average value intervals corresponding to risk probabilities; According to the risk probability, matching the Alzheimer's disease risk level corresponding to the target user in the database; A risk assessment report corresponding to the risk probability and the risk level is generated, and the risk assessment report is used as the Alzheimer's disease risk assessment result of the target user.

8. A risk assessment system for Alzheimer's disease, characterized in that: The system comprises: A data acquisition module, used to acquire brain magnetic resonance image data of a target user; a curve determination module, configured to perform time-frequency analysis on the brain wave parameters in the brain magnetic resonance image data, determine the brain wave spectrum curve of the target user, construct a head motion trajectory curve of the target user based on the head posture parameters in the brain magnetic resonance image data, and generate a neuron activity curve of the target user based on the brain blood flow parameters in the brain magnetic resonance image data; A risk value calculation module is used to determine a plurality of target feature points in the brain wave spectrum curve, the head movement trajectory curve and the neuron activity curve; calculate a first risk value corresponding to each of the target feature points in the brain wave spectrum curve, a second risk value corresponding to each of the target feature points in the head movement trajectory curve and a third risk value corresponding to each of the target feature points in the neuron activity curve; The risk assessment module is used to determine the Alzheimer's disease risk assessment result of the target user by combining the first risk value, the second risk value and the third risk value.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a risk assessment method for Alzheimer's disease as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, a risk assessment method for Alzheimer's disease as described in any one of claims 1 to 7 is executed.

Images