A cognitive function evaluation method based on multi-source information fusion

Abstract

The disclosure provides a kind of cognitive function evaluation method based on multi-source information fusion, it is related to health management technical field.The specific implementation of the method includes: obtaining the heart-brain coupling data index of the old people, concentration data index, electrooculogram-skin electricity emotional data index and proprioceptive balance index;In the evaluation period, respectively, the heart-brain coupling data index, concentration data index, electrooculogram-skin electricity emotional data index, proprioceptive balance index and corresponding index threshold are compared, to determine the index coefficient of the heart-brain coupling data index, the index coefficient of the concentration data index, the index coefficient of the electrooculogram-skin electricity emotional data index and the index coefficient of the proprioceptive balance index;Combine each index coefficient, evaluate the cognitive dysfunction degree of the old people.This embodiment can be more convenient, accurate and efficient to evaluate cognitive function, and early discover the cognitive dysfunction of the old people, has very extensive application prospect in the field of health management.

Description

[0001] This application is a divisional application of the invention patent application with application number "202311319824.0", application date October 12, 2023, and invention title "A Cognitive Function Assessment Method and System Based on Multi-Source Information Fusion". Technical Field

[0002] This disclosure relates to the field of health management technology, and in particular to a cognitive function assessment method and system based on multi-source information fusion. Background Technology

[0003] As the global population ages, the prevalence of cognitive impairment among the elderly is gradually increasing, which not only seriously affects their quality of life but also places a heavy burden on families and society.

[0004] At present, the assessment of cognitive impairment mainly relies on the Clinical Cognitive Assessment Scale. However, the assessment of the scale is greatly affected by the patient's cooperation and the assessor's assessment level, resulting in low accuracy and efficiency of classification assessment. Its practical application has certain limitations and it cannot be used to assess cognitive impairment efficiently, conveniently and in a timely manner. Summary of the Invention

[0005] In view of this, the present disclosure provides a cognitive function assessment method and system based on multi-source information fusion, which can solve the problems of low accuracy and efficiency of scale-based classification assessment, certain limitations in practical application, and inability to efficiently, conveniently, and timely assess cognitive impairment.

[0006] To achieve the above objectives, according to one aspect of this disclosure, a cognitive function assessment method based on multi-source information fusion is provided, comprising:

[0007] Collect brain oxygenation signals, electrocardiogram signals, electrooculogram signals, electrodermal conductance signals, and balance signals in elderly individuals;

[0008] Based on the brain oxygen signal, the electrocardiogram signal, the electrooculogram signal, the ductus skin light signal, and the balance signal, the heart-brain coupling data index, attention data index, electrooculogram-ductus skin light emotion data index, and proprioceptive balance index of the elderly are extracted;

[0009] The degree of cognitive impairment in older adults is assessed using the heart-brain coupling data index, the attention data index, the electrooculography-cortical conductance emotion data index, and the proprioceptive balance index.

[0010] According to another aspect of this disclosure, a cognitive function assessment system based on multi-source information fusion is provided, comprising:

[0011] The acquisition module is used to collect brain oxygenation signals, electrocardiogram signals, electrooculogram signals, skin conductance signals, and balance signals in the elderly.

[0012] The information processing and analysis module is used to extract the heart-brain coupling data index, attention data index, electrooculogram-skin electrocardiogram signal, electrooculogram signal, electrodermal conductance signal, and proprioceptive balance index of the elderly based on the brain oxygen signal, the electrocardiogram signal, the electrooculogram signal, the electrodermal conductance signal, and the balance signal.

[0013] The cognitive function assessment module is used to assess the degree of cognitive impairment in older adults using the heart-brain coupling data index, the attention data index, the electrooculography-cortical conductance emotion data index, and the proprioceptive balance index.

[0014] One or more technical solutions provided in this application embodiment collect low-cost and easily monitored brain oxygen signals, electrocardiogram signals, electrooculogram signals, skin conductance signals, and center of gravity change signals to calculate the heart-brain coupling data index, attention data index, emotion data index, and proprioceptive balance index of the elderly. The comprehensive analysis is then used to assess the degree of cognitive dysfunction, enabling a convenient, accurate, and efficient assessment of cognitive function and early detection of cognitive dysfunction in the elderly. This has high practical application value and broad application prospects in the field of health management. Attached Figure Description

[0015] Further details, features, and advantages of this disclosure are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0016] Figure 1 A flowchart of a cognitive function assessment method based on multi-source information fusion according to an exemplary embodiment of the present disclosure is shown;

[0017] Figure 2 A flowchart is shown of a method for calculating an electrooculography-cortical conductance emotion data index according to an exemplary embodiment of the present disclosure;

[0018] Figure 3 A schematic block diagram of a cognitive function assessment system based on multi-source information fusion according to an exemplary embodiment of the present disclosure is shown. Detailed Implementation

[0019] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0020] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0021] The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "in embodiments of the invention" means "at least one embodiment". Definitions of other terms will be given in the description below.

[0022] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0023] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0024] The present disclosure is described below with reference to the accompanying drawings.

[0025] Figure 1 A flowchart of a cognitive function assessment method based on multi-source information fusion according to an exemplary embodiment of the present disclosure is shown, such as... Figure 1 As shown, the cognitive function assessment method based on multi-source information fusion disclosed herein includes the following steps:

[0026] Step S101: Collect brain oxygenation signals, electrocardiogram signals, electrooculogram signals, skin conductance signals, and balance signals from the elderly.

[0027] In this embodiment, during each virtual reality cognitive task, the elderly person is continuously monitored for 20 minutes using a near-infrared brain oxygen meter, an electrocardiogram (ECG) monitor, an electrooculogram (EOG) monitor, and a physiological information monitor to obtain brain oxygen signals, ECG signals, EOG signals, and skin conductance signals under the virtual reality cognitive task. During each perturbation task, the elderly person is continuously monitored for 15 minutes using a balance meter and a near-infrared brain oxygen meter to obtain balance signals and brain oxygen signals under the perturbation task. The balance signal is the signal indicating the change in the elderly person's center of gravity.

[0028] Step S102: Based on the brain oxygen signal, the electrocardiogram signal, the electrooculogram signal, the skin conductance signal, and the balance signal, extract the heart-brain coupling data index, attention data index, electrooculogram-skin conductance emotion data index, and proprioceptive balance index of the elderly.

[0029] In this embodiment of the disclosure, brain oxygenation signals and electrocardiogram signals under virtual reality cognitive tasks are coupled and calculated to obtain the heart-brain coupling data index XN for elderly individuals. dn The attention data index YR of the elderly was obtained by calculating brain oxygenation signals and electrooculogram signals under virtual reality cognitive tasks using power spectrum analysis. op Time-frequency domain features were extracted from electrooculography (EOG) and electrodermal conductance (EDC) signals under virtual reality cognitive tasks to establish the SG emotional data index of EOG-EDC in the elderly; brain oxygenation signals and center of gravity change signals under perturbation tasks were coupled and calculated to obtain the proprioceptive balance index PN. gn . Specifically:

[0030] (1) Heart-brain coupling data index XN dn The calculation is shown in the following formula:

[0031]

[0032] In the above formula, LF and HF are the low-frequency power and high-frequency power of the heart rate variability index extracted from the electrocardiogram signal, respectively.

[0033] ER LP The coupling value between electrocardiogram signals and brain oxygenation signals in the left brain region of elderly individuals during virtual reality cognitive tasks;

[0034] ER RP The coupling value between electrocardiogram signals and brain oxygenation signals in the right brain region of elderly individuals during virtual reality cognitive tasks;

[0035] η is the correction coefficient. When the elderly person is right-handed, η∈[0.5,1); when the elderly person is left-handed, η∈(0,0.5).

[0036] in:

[0037] The coupling value (ER) between electrocardiogram (ECG) signals and brain oxygenation signals in the left brain region during virtual reality cognitive tasks. LP The calculation is shown in the following formula:

[0038]

[0039] In the above formula, LN represents the number of channels in the left brain region;

[0040] ER Lk (w) represents the power spectrum of the electrocardiogram signal and the brain oxygen signal of the kth channel in the left brain region under the virtual reality cognitive task;

[0041] EC(w) is the autopower spectrum of the time series of electrocardiogram signals under virtual reality cognitive tasks;

[0042] FR Lk(w) represents the autopower spectrum of the brain oxygen signal in the kth channel of the left brain region during a virtual reality cognitive task.

[0043] The coupling value (ER) between electrocardiogram (ECG) signals and brain oxygenation signals in the right brain region during virtual reality cognitive tasks. RP The calculation is shown in the following formula:

[0044]

[0045] In the above formula, RN represents the number of channels in the right brain region;

[0046] ER Ri (w) represents the power spectrum of the electrocardiogram signal and the brain oxygen signal of the i-th channel in the right brain region under the virtual reality cognitive task;

[0047] FR Ri (w) represents the autopower spectrum of the brain oxygen signal in the i-th channel of the right brain region during a virtual reality cognitive task.

[0048] (2) Focus Data Index YR op The calculation is shown in the following formula:

[0049]

[0050] In the above formula, the focus data index YR op Characterizes the coupling strength between brain oxygen signals and electrooculogram signals in different brain regions during virtual reality cognitive tasks;

[0051] OR m (w) represents the power spectrum of the electrooculogram signal and the brain oxygen signal of the m-th channel under virtual reality cognitive task;

[0052] EO(w) is the autopower spectrum of the time series of electrooculogram signals under virtual reality cognitive tasks;

[0053] FR m (w) represents the autopower spectrum of the brain oxygen signal in the m-th channel during a virtual reality cognitive task.

[0054] (3) The calculation of the mood data index SG based on electrooculography-cortical conductance is as follows: Figure 2 As shown, it includes the following steps:

[0055] Step S201: Extract time-frequency domain features from the OR of the electrooculogram (EOG) signal using a long short-term memory (LSTM) network, and output the EOG feature vector. As shown in the following formula:

[0056]

[0057] In the above formula, σ() is the first activation function of the Long Short-Term Memory network;

[0058] tanh() is the second activation function for Long Short-Term Memory (LSTM) networks;

[0059] W LSTM1 The input gate weights are used for the input gates in the Long Short-Term Memory network to extract electrooculogram features.

[0060] W LSTM2 Forget gate weights for extracting electrooculogram features from long short-term memory networks;

[0061] B LSTM1 Input gate bias for the input gate used to extract electrooculogram features from the Long Short-Term Memory network;

[0062] B LSTM2 Forget gate bias for extracting electrooculogram features from long short-term memory networks.

[0063] Step S202: Extract time-frequency domain features from the skin conductance signal GR using a long short-term memory network, and output the skin conductance feature vector. As shown in the following formula:

[0064]

[0065] In the above formula, W LSTM3 The input gate weights are used for the input gates in the Long Short-Term Memory network to extract skin conductance features;

[0066] W LSTM4 Forget gate weights for extracting electrodermal features from long short-term memory networks;

[0067] B LSTM3 Input gate bias for the input gate used to extract skin conductance features in a long short-term memory network;

[0068] B LSTM4 Forget gate bias for extracting electrodermal features from long short-term memory networks.

[0069] Step S203: Based on the hierarchical cross-attention mechanism, process the electrooculogram feature vector. and skin conductance eigenvectors Perform feature fusion to obtain a fused feature vector. As shown in the following formula:

[0070]

[0071] In the above formula, w OR1 ,...,w ORA Electroocular feature vector The various features OR LSTM1 ,...,OR LSTMA The weight values ​​of attention weights;

[0072] wGR1 ,...,w GRB Skin conductance feature vector The various features of GR LSTM1 ,...,GR LSTMB The weight values ​​of the attention weights; where the electrooculogram feature vector The a-th feature OR LSTMa The weight values ​​of the attention weights are shown in the following formula:

[0073]

[0074] In the above formula, μ a Electroocular feature vector The a-th feature OR LSTMa The fluctuation value.

[0075] A is the electrooculography feature vector. The number of features;

[0076] Skin conductance eigenvector The a-th feature GR LSTMb The weight values ​​of the attention weights are shown in the following formula:

[0077]

[0078] In the above formula, λ b Skin conductance feature vector The b-th feature GR LSTMb The fluctuation value;

[0079] B is the skin conductance characteristic vector. The number of features.

[0080] Step S204, fuse the feature vectors Inputting the data into the softmax classifier yields the SG index of electrooculography-cortical conductance, as shown in the following formula:

[0081]

[0082] In the above formula, W d B d These represent the classification weights and classification biases of the softmax classifier, respectively.

[0083] Furthermore, different values ​​of the electrooculography-cortical conductance (EOG) emotion index SG represent different emotion types. For example, SG∈[0.6,0.9) indicates a positive emotion type, SG∈[0.3,0.6) indicates a neutral emotion type, and SG∈(0,0.3] indicates a negative emotion type.

[0084] Furthermore, before extracting the time-frequency domain features of the electrooculogram (EOG) signal OR and the electrodermal signal GR, the EOG signal OR and the electrodermal signal GR are preprocessed. This includes removing noise interference from the EOG signal OR using a median filter, and removing artifacts from the EOG signal OR based on spline interpolation and standard deviation methods to obtain the preprocessed EOG signal OR; and removing noise interference from the electrodermal signal GR using a linear smoothing filter to obtain the preprocessed electrodermal signal GR.

[0085] (4) Proprioceptive balance index PN gn The calculation is shown in the following formula:

[0086]

[0087] In the above formula, DP gn This represents the variance of the center of gravity change signal under the perturbation task.

[0088] PR LB The coupling value between the center of gravity change signal and the brain oxygenation signal in the left brain region under the perturbation task;

[0089] PR RB The coupling value between the center of gravity change signal and the brain oxygenation signal in the right brain region under the perturbation task;

[0090] δ is the correction coefficient.

[0091] in:

[0092] The variance DP of the center of gravity change signal gn The calculation is shown in the following formula:

[0093]

[0094] In the above formula, n is the number of segments for random sampling of the center of gravity change signal, which can be selectively set as needed;

[0095] PG j Let be the centroid value at time j, representing the centroid change signal.

[0096] This represents the mean of the center of gravity change signal.

[0097] The coupling value PR between the center of gravity change signal and the brain oxygenation signal in the left brain region under the perturbation task LB The calculation is shown in the following formula:

[0098]

[0099] In the above formula, LN represents the number of channels in the left brain region;

[0100] PG Lk(w) represents the power spectrum of the center of gravity change signal and the brain oxygen signal of the kth channel in the left brain region under the perturbation task;

[0101] PF(w) is the self-power spectrum of the time series of the centroid change signal under the disturbance task;

[0102] FR Lk (w) represents the autopower spectrum of the brain oxygen signal in the kth channel of the left brain region under the perturbation task;

[0103] The coupling value PR between the center of gravity change signal and the brain oxygenation signal in the right brain region under the perturbation task RB The calculation is shown in the following formula:

[0104]

[0105] In the above formula, RN represents the number of channels in the right brain region;

[0106] PG Ri (w) represents the power spectrum of the center of gravity change signal and the brain oxygen signal of the i-th channel in the right brain region under the perturbation task;

[0107] FR Ri (w) represents the autopower spectrum of the brain oxygen signal in the i-th channel of the right brain region under the perturbation task.

[0108] Step S103: Assess the degree of cognitive impairment in the elderly using the heart-brain coupling data index, the attention data index, the electrooculography-cortical conductance emotion data index, and the proprioceptive balance index.

[0109] In this embodiment of the invention, the degree of cognitive impairment in the elderly is calculated as follows:

[0110] K = A1 * XN dn +A2*YR op +A3*SG+A4*PN gn

[0111] In the above formula, K represents the degree of cognitive impairment. Different values ​​represent different degrees of cognitive impairment, including normal cognitive function, mild cognitive impairment, moderate cognitive impairment, and severe cognitive impairment.

[0112] A1, A2, A3, and A4 represent the heart-brain coupling data index XN, respectively. dn YR (Attention Count Index) op Emotional data index SG (electrooscopic-skin conductance index) and proprioceptive balance index PN gn The exponential coefficient.

[0113] Furthermore, based on the index thresholds of each index and the number of times each index threshold was exceeded within the assessment period, and according to the importance of each index, the degree of cognitive impairment in the elderly was assessed in sequence to determine the values ​​of each coefficient, thereby calculating the degree of cognitive impairment in the elderly. Among these, the index thresholds include the heart-brain coupling index threshold XN. dn,max Attention Index Threshold YR op,max The emotional index threshold SG of electrooculography-cortical conductance max and the proprioceptive balance index threshold PN gn,max The threshold values ​​for each index can be selectively set according to actual cognitive rehabilitation needs; the heart-brain coupling data index XN dn And focus data index YR op Its importance is superior to the electrooculogram-cortical conductance (EOG-SC) mood data index and the proprioceptive balance index (PN). gn . Specifically:

[0114] (1) Beware of brain-brain coupling data index XN dn Exceeding the heart-brain coupling index threshold XN within 2 weeks dn,max The number of times is less than or equal to 2, and the focus data index YR op Exceeding the focus index threshold YR within 2 weeks op,max When the number of occurrences is less than or equal to 2, the emotional index threshold SG of electrooculography-cortical conductance is no longer considered. max and the proprioceptive balance index threshold PN gn,max The indicators were calculated, and A1=A2=A3=A4=0 was determined. The degree of cognitive impairment was assessed as normal cognitive function.

[0115] (2) Beware of brain-brain coupling data index XN dn And focus data index YR op Exceeding the heart-brain coupling index threshold XN within 2 weeks dn,max And focus index threshold YR op,max When the number of occurrences is greater than 2, the emotional index threshold SG of electrooculography-cortical conductance is calculated. max and the proprioceptive balance index threshold PN gn,max ;

[0116] When the electrooculogram-cortex transduction (EOG-CTR) sentiment index SG does not exceed the EOG-CTR threshold SG within 2 weeks... max and the proprioceptive balance index PN gn The proprioceptive balance index threshold PN was not exceeded within 2 weeks. gn ,m ax At that time, A1 = A2 = 1, A3 = A40 = , and the degree of cognitive impairment was assessed as mild cognitive impairment;

[0117] (3) Beware of brain-brain coupling data index XN dn And focus data index YR op Exceeding the heart-brain coupling index threshold XN within 2 weeks dn,max And focus index threshold YR op,max The number of times was greater than 2, and the electrooculogram-cortex transduction (EOG-CTR) sentiment data index SG exceeded the EOG-CTR threshold SG within 2 weeks. max The number of times is less than 4, and the proprioceptive balance index PN gn Exceeding the proprioceptive balance index threshold PN within 2 weeks gn,max If the number of occurrences is less than 4, then A1 = A2 = 1, A3 = A4 = 0.5, and the degree of cognitive impairment is assessed as moderate cognitive impairment.

[0118] (4) Beware of brain-brain coupling data index XN dn And focus data index YR op Exceeding the heart-brain coupling index threshold XN within 2 weeks dn,max And focus index threshold YR op,max The number of occurrences was greater than 2, and the electrooculography-cortical conductance emotional data index SG and proprioceptive balance index PN were also present. gn Exceeding the electrooculography-cortex conductivity index threshold SG within 2 weeks max and the proprioceptive balance index threshold PN gn,max If the number of occurrences is greater than or equal to 4, then A1 = A2 = A3 = A4 = 1, and the degree of cognitive impairment is assessed as severe cognitive impairment.

[0119] In this embodiment of the disclosure, medical staff can also assess the degree of cognitive impairment of the elderly based on the cognitive function assessment method of multi-source information fusion disclosed in this disclosure, and combine the results of other examination items of the elderly to further accurately assess the degree of cognitive impairment of the elderly, so as to improve the accuracy of cognitive function assessment of the elderly.

[0120] In this embodiment of the invention, the cognitive function assessment method based on multi-source information disclosed herein can fully leverage the correlation and complementarity of multi-source heterogeneous data, and assess the degree of cognitive impairment in the elderly in a low-cost, comprehensive, efficient, objective, simple, timely and accurate manner. It has high objectivity and practical application value, and can detect cognitive impairment defects in the elderly at an early stage, reminding the elderly population to take timely intervention measures based on the assessment results to delay the decline of cognitive function.

[0121] Figure 3 This is a schematic diagram of the main modules of a cognitive function assessment system based on multi-source information fusion according to an embodiment of this disclosure, as shown below. Figure 3 As shown, the cognitive function assessment system 300 based on multi-source information fusion disclosed herein includes:

[0122] The acquisition module 301 is used to acquire brain oxygen signals, electrocardiogram signals, electrooculogram signals, skin conductance signals, and balance signals in the elderly.

[0123] The information processing and analysis module 302 is used to extract the heart-brain coupling data index, attention data index, electrooculogram-skin electrocoagulation emotional data index, and proprioceptive balance index of the elderly based on the brain oxygen signal, the electrocardiogram signal, the electrooculogram signal, the skin conductance signal, and the balance signal.

[0124] In this embodiment of the invention, the information processing and analysis module 302 includes a heart-brain coupling index module 3021, a focus index module 3022, an emotion index module 3023, and a proprioceptive balance index module 3024.

[0125] The cognitive function assessment module 303 is used to assess the degree of cognitive impairment in the elderly through the heart-brain coupling data index, the attention data index, the electrooculography-cortical conductance emotion data index, and the proprioceptive balance index.

[0126] Furthermore, the cognitive function assessment system 300 based on multi-source information fusion also includes an interaction module 304 for displaying the degree of cognitive impairment assessed by the cognitive function assessment module 303.

Claims

1. A cognitive function assessment method based on multi-source information fusion, characterized in that, include: Obtaining the heart-brain coupling data index XN in older adults dn YR (Attention Count Index) op Emotional data index SG (electrooscopic-skin conductance index) and proprioceptive balance index PN (proprioceptive balance index) gn ; in: in, , These are the low-frequency and high-frequency power values ​​of the heart rate variability index extracted from the electrocardiogram signal, respectively. The coupling value between electrocardiogram signals and brain oxygenation signals in the left brain region of elderly individuals during virtual reality cognitive tasks; The coupling value between electrocardiogram signals and brain oxygenation signals in the right brain region of elderly individuals during virtual reality cognitive tasks; For correction factors; in, Electrooculocardiogram (EOG) signals and the first [unclear] in virtual reality cognitive tasks Power spectrum of brain oxygenation signal in each channel; The autopower spectrum of the time series of electrooculogram signals under virtual reality cognitive tasks; For the first virtual reality cognitive task The autopower spectrum of brain oxygenation signals in each channel; in, , These are the classification weights and classification biases of the softmax classifier, respectively. in, This represents the variance of the center of gravity change signal under the perturbation task. The coupling value between the center of gravity change signal and the brain oxygenation signal in the left brain region under the perturbation task; The coupling value between the center of gravity change signal and the brain oxygenation signal in the right brain region under the perturbation task; For correction factors; During the evaluation period, the heart-brain coupling data index XN was calculated respectively. dn The focus data index YR op The electrooculo-cortical conductance emotion data index SG and the proprioceptive balance index PN gn Heart-brain coupling index threshold XN dn,max Attention Index Threshold YR op,max The emotional index threshold SG of electrooculography-cortical conductance max Proprioceptive balance index threshold PN gn,max By comparison, the heart-brain coupling data index XN was determined. dn The index coefficient A1, the focus data index YR op The exponential coefficient A2, the exponential coefficient A3 of the electrooculography-cortical conductance emotion data index SG, and the proprioceptive balance index PN gn The exponential coefficient A4; Combined with the aforementioned heart-brain coupling data index XN dn The index coefficient A1, the focus data index YR op The exponential coefficient A2, the exponential coefficient A3 of the electrooculography-cortical conductance emotion data index SG, and the proprioceptive balance index PN gn The exponential coefficient A4 is used to assess the degree of cognitive impairment K in older adults, as shown in the following formula: K=A1*XN dn +A2*YR op +A3*SG+A4*PN gn 。 2. The cognitive function assessment method as described in claim 1, characterized in that, Also includes: When XN dn Exceeding XN within the evaluation period dn,max The number of times ≤ 2, and YR op Exceeding YR within the evaluation period op,max When the number of occurrences is ≤2, A1 = A2 = A3 = A4 = 0, and the degree of cognitive impairment K is considered to be normal cognitive function.

3. The cognitive function assessment method as described in claim 1, characterized in that, Also includes: When XN dn Exceeding XN within the evaluation period dn,max Number of times > 2, YR op Exceeding YR within the evaluation period op,max When the number of occurrences is greater than 2, calculate SG and PN. gn,max ; When SG does not exceed SG during the evaluation period max and PN gn The PN value did not exceed the specified evaluation period. gn,max When A1 = A2 = 1 and A3 = A4 = 0 are determined, the degree of cognitive impairment K is assessed as mild cognitive impairment.

4. The cognitive function assessment method as described in claim 1, characterized in that, Also includes: When XN dn Exceeding XN within the evaluation period dn,max Number of times > 2, YR op Exceeding YR within the evaluation period op,max The number of times is greater than 2, and SG exceeds SG within the stated evaluation period. max Number of times < 4 times, PN gn Exceeding PN within the evaluation period gn,max If the number of occurrences is less than 4, then A1 = A2 = 1, A3 = A4 = 0.5, and the degree of cognitive impairment K is assessed as moderate cognitive impairment.

5. The cognitive function assessment method as described in claim 1, characterized in that, Also includes: When XN dn Exceeding XN within the evaluation period dn,max Number of times > 2, YR op Exceeding YR within the evaluation period op,max The number of times is greater than 2, and SG exceeds SG within the stated evaluation period. max ≥4 times, PN gn Exceeding PN within the evaluation period gn,max If the number of occurrences is ≥4, then A1 = A2 = A3 = A4 = 1, and the degree of cognitive impairment K is assessed as severe cognitive impairment.

Images