An early cognitive impairment screening method and system based on multi-mode electromagnetic field biological detection

Abstract

The application belongs to the technical field of artificial intelligence, and particularly relates to an early cognitive impairment screening method and system based on multi-mode electromagnetic field biological detection, wherein the method comprises a first electrode sheet and a second electrode sheet arranged in advance on the forehead position and the back occipital position of the brain of a user to be detected, a third electrode sheet and a fourth electrode sheet arranged side by side on the left side of the brain, and a fifth electrode sheet and a sixth electrode sheet arranged side by side on the right side of the brain; a disturbance coefficient set of the user to be detected under a reference detection mode combination is obtained and input into a pre-trained early cognitive impairment screening model to obtain a prediction probability value of the user to be detected in terms of early cognitive impairment; the early cognitive impairment is screened by using the scheme, the accuracy is high, the universality is strong, and the scheme can be applied to the screening of crowds in communities, nursing homes and the like on a large scale.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of artificial intelligence, and particularly relates to an early cognitive impairment screening method and system based on multi-mode electromagnetic field biological detection. BACKGROUND

[0002] Mild cognitive impairment (MCI) refers to a significant impairment of memory or / and other cognitive functions of an individual compared with an age-matched and education-matched control group, but the daily life ability is normal, and it does not reach the usual dementia diagnostic criteria, which is a cognitive impairment syndrome between normal aging and dementia. In-depth study of MCI helps to find and screen high-risk groups of dementia, and provides the best time window for the treatment of dementia.

[0003] MCI can be divided into degenerative, vascular and somatic according to the cause; MCI can be divided into white matter hyperintensity type (MCI with white matter hyperintensities) and hippocampal atrophy type (MCI with hippocampal atrophy) according to the neuroimaging performance; MCI can also be divided into progressive MCI and stable MCI according to the change of the disease.

[0004] At present, the world is seeking a simple and effective method for MCI screening, and the main methods are as follows: 1. Scale method; 2. Biological detection; 3. Imaging detection.

[0005] The above methods can achieve screening and diagnosis to some extent, but all have their shortcomings, such as long time, consumption of expert resources, high cost, limited accuracy, etc., and cannot be used as a routine means of large-scale screening. The above methods each have many fatal shortcomings, such as rapid, non-invasive, digital, mobile and portable, low cost, accuracy and sensitivity, etc., and the above characteristics are the main content of future medical field to pursue early screening. Electromagnetic field biological detection technology is the current international frontier technology, especially the application of the technology in the detection of craniocerebral diseases is an important direction in the field of neurology in the future. At present, the application of electromagnetic field biological detection technology has achieved a relatively rough detection method for craniocerebral diseases, such as using detection parameters such as disturbance coefficient and biological impedance coefficient, to realize abnormal detection of whole brain caused by various diseases, and then diagnose through CT / MRI and other methods, and determine the treatment plan according to the diagnosis result.

[0006] For example, the applicant proposes a monitoring hydrocephalus and brain edema device based on electromagnetic field biological detection technology (see CN102525458B), and for example, the applicant also proposes a brain abnormal data processing method and device caused by cerebral infarction (see CN117688430A), which generates disturbance coefficients between electrode pieces by setting electrode pieces at the forehead position, the back of the head position, the left front side of the brain, the left back side of the brain, the right front side of the brain and the right back side of the brain, and determines the cerebral infarction abnormality of the subject according to the disturbance coefficients. Specifically, it performs machine learning by pre-acquiring the disturbance coefficient data set of healthy subjects and abnormal subjects caused by early cerebral infarction in the preset detection mode combination, thereby obtaining a multi-mode abnormality prediction model, and then inputting the acquired disturbance coefficient data set in the preset detection mode combination into the multi-mode abnormality prediction model to obtain the corresponding prediction result, thereby realizing early prediction of abnormalities caused by early cerebral infarction.

[0007] The above-mentioned scheme provides an abnormal prediction scheme for part of brain diseases, but is not suitable for abnormal prediction of early cognitive impairment. SUMMARY

[0008] The purpose of the present application is to provide an early cognitive impairment screening method and system based on multi-mode electromagnetic field biological detection, to partially solve or alleviate the deficiencies in the prior art, and to meet the needs of large-scale early cognitive screening in communities, welfare homes, elderly service centers and the like.

[0009] In order to solve the above-mentioned technical problems, the present application specifically adopts the following technical scheme:

[0010] The first aspect of the present application is to provide an early cognitive impairment screening method based on multi-mode electromagnetic field biological detection, which comprises:

[0011] S101 pre-setting first electrode pieces and second electrode pieces on the cranial brain of the user to be detected at the forehead position and the back of the head position, and pre-setting third electrode pieces and fourth electrode pieces on the left side of the cranial brain, and pre-setting fifth electrode pieces and sixth electrode pieces on the right side of the cranial brain;

[0012] S102 acquiring the disturbance coefficient set of the user to be detected under the reference detection mode combination, and inputting it into the pre-trained early cognitive impairment screening model to predict the prediction probability value of the occurrence of early cognitive impairment of the user to be detected;

[0013] Wherein, the disturbance coefficient set under the reference detection mode combination includes: the first disturbance coefficient set and the second disturbance coefficient set under the preset first four-electrode detection mode and the second four-electrode detection mode, and the third to sixth disturbance coefficient sets under the first to fourth three-electrode detection modes;

[0014] In the first four-electrode detection mode, the first electrode patch at the forehead position is the excitation transmitting end, and the second electrode patch at the back of the head, and the third electrode patch and the fifth electrode patch at the left and right sides of the brain are the excitation receiving ends. Correspondingly, the first disturbance coefficient set includes the seventh disturbance coefficient R7, the fifth disturbance coefficient R5 and the sixth disturbance coefficient R6 between the first electrode patch and the second electrode patch, the third electrode patch and the fifth electrode patch respectively;

[0015] In the second four-electrode detection mode, the second electrode patch at the back of the head is the excitation transmitting end, and the first electrode patch at the forehead position, and the fourth electrode patch and the sixth electrode patch at the left and right sides of the brain are the excitation receiving ends. Correspondingly, the second disturbance coefficient set includes the eighth disturbance coefficient R7', the third disturbance coefficient R3 and the fourth disturbance coefficient R4 between the second electrode patch and the first electrode patch, the fourth electrode patch and the sixth electrode patch respectively;

[0016] In the first three-electrode detection mode, the third electrode patch at the left side of the brain is the excitation transmitting end, and the first electrode patch at the forehead position and the fifth electrode patch at the right side of the brain are the excitation receiving ends. Correspondingly, the three disturbance coefficient set includes the twelfth disturbance coefficient R5' and the first disturbance coefficient R1 between the third electrode patch and the first electrode patch and the fifth electrode patch respectively;

[0017] In the second three-electrode detection mode, the fourth electrode patch at the left side of the brain is the excitation transmitting end, and the second electrode patch at the back of the head and the sixth electrode patch at the right side of the brain are the excitation receiving ends. Correspondingly, the four disturbance coefficient set includes the tenth disturbance coefficient R3' and the second disturbance coefficient R2 between the fourth electrode patch and the second electrode patch and the sixth electrode patch respectively;

[0018] In the third three-electrode detection mode, the fifth electrode patch at the right side of the brain is the excitation transmitting end, and the first electrode patch at the forehead position and the third electrode patch at the left side of the brain are the excitation receiving ends. Correspondingly, the five disturbance coefficient set includes the thirteenth disturbance coefficient R6' and the eighth disturbance coefficient R1' between the fifth electrode patch and the first electrode patch and the third electrode patch respectively;

[0019] In the fourth three-electrode detection mode, the sixth electrode patch at the right side of the brain is the excitation transmitting end, and the second electrode patch at the back of the head and the fourth electrode patch at the left side of the brain are the excitation receiving ends. Correspondingly, the six disturbance coefficient set includes the eleventh disturbance coefficient R4' and the ninth disturbance coefficient R2' between the sixth electrode patch and the second electrode patch and the fourth electrode patch respectively;

[0020] The step of training the early cognitive impairment screening model comprises the following steps:

[0021] S201: Obtain a health perturbation coefficient dataset of a plurality of healthy subjects under the combination of the reference detection modes;

[0022] S202: Obtain an abnormal perturbation coefficient dataset of a plurality of early cognitive impairment subjects under the combination of the reference detection modes;

[0023] S203: Obtain a scale detection result of the plurality of early cognitive impairment subjects obtained through a specified scale method;

[0024] S204: Input the health perturbation coefficient dataset, the abnormal perturbation coefficient dataset, and the scale detection result into a pre-constructed neural network model for learning to obtain the early cognitive impairment screening model.

[0025] Preferably, the step of training the early cognitive impairment screening model further comprises the following steps:

[0026] S205: Obtain and identify the associated past medical history of the plurality of early cognitive impairment subjects; the associated past medical history comprises at least one of hypertension, stroke, cerebral infarction, and genetic factors;

[0027] S206a: If there are two or more past medical histories, obtain a perturbation coefficient set of the subject under the combination of the reference detection modes, and input the perturbation coefficient set, the health perturbation coefficient dataset, and the scale detection result into a pre-constructed neural network model for training to obtain a first prediction model;

[0028] S206b: If there is a single past medical history, respectively obtain a perturbation coefficient set of the subject under the combination of the reference detection modes and under the fifth to eighth three-electrode detection modes, and input the perturbation coefficient sets, the health perturbation coefficient dataset, and the scale detection result into a pre-constructed neural network model for training to obtain a second prediction model.

[0029] Preferably, the step S102 specifically comprises the following steps:

[0030] Obtain and identify the associated past medical history of the to-be-detected user;

[0031] If there are two or more past medical histories, obtain a perturbation coefficient set of the to-be-detected user under the combination of the reference detection modes, and then input the perturbation coefficient set into the first prediction model for prediction;

[0032] If there is a single past medical history, respectively obtain a perturbation coefficient set of the to-be-detected user under the combination of the reference detection modes and under the fifth to eighth three-electrode detection modes, and input the perturbation coefficient sets into the second prediction model for prediction.

[0033] Preferably, in the fifth three-electrode detection mode, the third electrode patch located on the left side of the brain is used as the excitation transmitting end, the first electrode patch located on the forehead and the sixth electrode patch located on the right side of the brain are used as the excitation receiving end, and correspondingly, the seventh disturbance coefficient set in the fifth three-electrode detection mode includes the fifteenth disturbance coefficient R5' and the sixteenth disturbance coefficient R16 on the propagation path between the third electrode patch and the first electrode patch and the sixth electrode patch respectively.

[0034] Preferably, in the sixth three-electrode detection mode, the fourth electrode patch located on the left side of the brain is used as the excitation transmitting end, the second electrode patch located on the back of the head and the fifth electrode patch located on the right side of the brain are used as the excitation receiving end, and correspondingly, the eighth disturbance coefficient set in the sixth three-electrode detection mode includes the tenth disturbance coefficient R3' and the seventeenth disturbance coefficient R17 on the propagation path between the fourth electrode patch and the second electrode patch and the fifth electrode patch respectively.

[0035] Preferably, in the seventh three-electrode detection mode, the fifth electrode patch located on the right side of the brain is used as the excitation transmitting end, the first electrode patch located on the forehead and the fourth electrode patch located on the left side of the brain are used as the excitation receiving end, and correspondingly, the ninth disturbance coefficient set in the seventh three-electrode detection mode includes the thirteenth disturbance coefficient R6' and the eighteenth disturbance coefficient R18 on the propagation path between the fifth electrode patch and the first electrode patch and the fourth electrode patch respectively.

[0036] Preferably, in the eighth three-electrode detection mode, the sixth electrode patch located on the right side of the brain is used as the excitation transmitting end, the second electrode patch located on the back of the head and the third electrode patch located on the left side of the brain are used as the excitation receiving end, and correspondingly, the tenth disturbance coefficient set in the eighth three-electrode detection mode includes the eleventh disturbance coefficient R4' and the nineteenth disturbance coefficient R19 on the propagation path between the sixth electrode patch and the second electrode patch and the third electrode patch respectively.

[0037] Preferably, if the past medical history of the subject to be tested is stroke, the proportion of the sum of the three disturbance coefficient sets in the first and second three-electrode detection modes in the corresponding disturbance coefficient set is greater than the proportion of the sum of the fifth disturbance coefficient set and the sixth disturbance coefficient set in the third and fourth three-electrode detection modes.

[0038] If the past medical history of the subject to be tested is cerebral infarction, the proportion of the sum of the three disturbance coefficient sets and the five disturbance coefficient sets in the first and third three-electrode detection modes in the corresponding disturbance coefficient set is greater than the proportion of the sum of the four disturbance coefficient sets and the six disturbance coefficient sets in the second and fourth three-electrode detection modes.

[0039] The second aspect of the present application is to provide an early cognitive impairment screening system based on multi-mode electromagnetic field biological detection, which comprises:

[0040] A data acquisition device comprising a data communication module and a user electrode group for obtaining data, the electrode group comprising a first electrode pad and a second electrode pad corresponding to the forehead position and the back of the head position of the brain respectively, a third electrode pad and a fourth electrode pad corresponding to the left side of the brain, and a fifth electrode pad and a sixth electrode pad corresponding to the right side of the brain;

[0041] A screening device in data communication with the data acquisition device for obtaining a set of perturbation coefficients of the data acquisition device under a preset reference detection mode combination, and inputting the set of perturbation coefficients into a pre-trained early cognitive impairment screening model to obtain a prediction probability value of the user under detection developing early cognitive impairment;

[0042] Specifically, the screening device comprises:

[0043] A first data acquisition module for data communication with the data acquisition device to obtain a set of healthy perturbation coefficient data of a plurality of healthy subjects under the reference detection mode combination, and a set of abnormal perturbation coefficient data of a plurality of early cognitive impairment subjects under the reference detection mode combination, and a set of perturbation coefficients of the user under detection under the reference detection mode combination;

[0044] A second data acquisition module for obtaining a scale detection result of the plurality of early cognitive impairment subjects obtained by a specified scale method test;

[0045] A screening model construction module for training a pre-constructed neural network model based on the set of healthy perturbation coefficient data, the set of abnormal perturbation coefficient data, and the scale detection result to obtain the early cognitive impairment screening model;

[0046] A prediction module for predicting based on the early cognitive impairment screening model constructed by the screening model construction module and the set of perturbation coefficients of the user under detection under the reference detection mode combination obtained by the first data acquisition module to obtain a prediction probability value of the user under detection developing early cognitive impairment;

[0047] Wherein, the set of perturbation coefficients under the reference detection mode combination comprises a first set of perturbation coefficients and a second set of perturbation coefficients under a preset first four-electrode detection mode and a second four-electrode detection mode, and a third set of perturbation coefficients to a sixth set of perturbation coefficients under a first to fourth three-electrode detection mode;

[0048] In the first four-electrode detection mode, the first electrode located at the forehead position is taken as the excitation transmitting end, the second electrode located at the back of the head, and the third electrode and the fifth electrode located at the left and right sides of the brain respectively are taken as the excitation receiving end, and correspondingly, the first disturbance coefficient set includes the seventh disturbance coefficient R7, the fifth disturbance coefficient R5 and the sixth disturbance coefficient R6 between the propagation paths of the first electrode and the second electrode, the third electrode and the fifth electrode respectively;

[0049] In the second four-electrode detection mode, the second electrode located at the back of the head is taken as the excitation transmitting end, the first electrode located at the forehead, and the fourth electrode and the sixth electrode located at the left and right sides of the brain respectively are taken as the excitation receiving end, and correspondingly, the second disturbance coefficient set includes the eighth disturbance coefficient R7', the third disturbance coefficient R3 and the fourth disturbance coefficient R4 between the propagation paths of the second electrode and the first electrode, the fourth electrode and the sixth electrode respectively;

[0050] In the first three-electrode detection mode, the third electrode located at the left side of the brain is taken as the excitation transmitting end, the first electrode located at the forehead and the fifth electrode located at the right side of the brain are taken as the excitation receiving end, and correspondingly, the three disturbance coefficient set includes the twelfth disturbance coefficient R5' and the first disturbance coefficient R1 between the propagation paths of the third electrode and the first electrode and the fifth electrode respectively;

[0051] In the second three-electrode detection mode, the fourth electrode located at the left side of the brain is taken as the excitation transmitting end, the second electrode located at the back of the head and the sixth electrode located at the right side of the brain are taken as the excitation receiving end, and correspondingly, the four disturbance coefficient set includes the tenth disturbance coefficient R3' and the second disturbance coefficient R2 between the propagation paths of the fourth electrode and the second electrode and the sixth electrode respectively;

[0052] In the third three-electrode detection mode, the fifth electrode located at the right side of the brain is taken as the excitation transmitting end, the first electrode located at the forehead and the third electrode located at the left side of the brain are taken as the excitation receiving end, and correspondingly, the five disturbance coefficient set includes the thirteenth disturbance coefficient R6' and the eighth disturbance coefficient R1' between the propagation paths of the fifth electrode and the first electrode and the third electrode respectively;

[0053] In the fourth three-electrode detection mode, the sixth electrode located at the right side of the brain is taken as the excitation transmitting end, the second electrode located at the back of the head and the fourth electrode located at the left side of the brain are taken as the excitation receiving end, and correspondingly, the six disturbance coefficient set includes the eleventh disturbance coefficient R4' and the ninth disturbance coefficient R2' between the propagation paths of the sixth electrode and the second electrode and the fourth electrode respectively.

[0054] Preferably, the screening device further comprises:

[0055] a third data acquisition module configured to acquire and identify associated past medical history of the plurality of subjects with early cognitive impairment, the associated past medical history including at least one of hypertension, stroke, cerebral infarction and genetic factors;

[0056] a fourth data acquisition module configured to, when the subject has two or more associated past medical history, acquire a set of perturbation coefficients of the subject under the combination of the reference detection modes, and when the subject has a single past medical history, acquire a set of perturbation coefficients of the subject under the fifth to eighth three-electrode detection modes respectively,

[0057] Correspondingly, the screening model construction module is further configured to, when the subject has two or more associated past medical history, train the set of perturbation coefficients of the subject under the combination of the reference detection modes and the healthy perturbation coefficient dataset and the scale detection result input model to obtain a first prediction model, and when the subject has a single past medical history, train the set of perturbation coefficients of the subject under the fifth to eighth three-electrode detection modes and the set of perturbation coefficients obtained under the combination of the reference detection modes, and the healthy perturbation coefficient dataset and the scale detection result input model to obtain a second prediction model.

[0058] The principles and beneficial technical effects of the present application are as follows:

[0059] In the prior art (see CN117688430A), electrode pieces are arranged at the forehead position, the back of the head position, the left front side of the brain, the left back side of the brain, the right front side of the brain and the right back side of the brain respectively, perturbation coefficients are generated between the electrode pieces, and prediction is performed in combination with a default detection mode combination to obtain the probability of cerebral infarction of the user to be detected; however, due to the complexity and clear division of the human brain tissue, the lesion positions (i.e. detection positions) of different brain diseases are different, and the above device is not suitable for screening early cognitive impairment, in addition, the scheme performs non-discriminatory detection on the user through a fixed mode (default detection mode combination), and is not suitable for large-scale detection.

[0060] Based on this, the present application proposes a multi-mode electromagnetic field biological detection early cognitive impairment screening method and system with parallel collection points for early cognitive impairment, which has high accuracy and strong universality.

[0061] On the one hand, the present application sets two groups of electrode pieces in parallel corresponding to the left brain and the right brain, sets multiple detection modes based on multiple electrode pieces (corresponding to electrode pieces at different positions and different electrode propagation paths), and detects the user to be detected to obtain a set of multi-element perturbation data, thereby predicting the probability of the user suffering from early cognitive impairment, which is rich in samples and has high reliability of prediction results.

[0062] In another aspect, possible influencing factors of early cognitive impairment (associated with previous medical history; the elderly population often accompanied by or suffered from, for example, hypertension, stroke, genetic history, etc., has a higher risk of early cognitive impairment) are introduced into the model training process, the model is divided into a first model and a second model, and for users with more previous medical history with higher risk of disease, the first model with less data (measured by fewer detection modes) is used for prediction, which can effectively reduce the calculation amount, and for users with single medical history with lower disease rate, the second model with larger data (measured by more detection modes) is used for prediction, which improves the accuracy of prediction. That is, the present application effectively improves the working efficiency of the prediction process by classifying user categories and quickly matching the corresponding prediction model, and compared with CT, ultrasound and nuclear magnetic resonance devices, it has almost no negative impact on the user's body, and can be continuously monitored (for example, for several hours, or even for several days), so it can be widely used in community and other public medical systems. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual proportion. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0064] Figure 1 Flow chart of the early cognitive impairment screening method in the embodiment of the present application;

[0065] Figure 2a Schematic diagram of the first four-electrode detection mode in the embodiment of the present application;

[0066] Figure 2b Schematic diagram of the second four-electrode detection mode in the embodiment of the present application;

[0067] Figure 3a Schematic diagram of the first three-electrode detection mode in the embodiment of the present application;

[0068] Figure 3b Schematic diagram of the second three-electrode detection mode in the embodiment of the present application;

[0069] Figure 3c Schematic diagram of the third three-electrode detection mode in the embodiment of the present application;

[0070] Figure 3d Schematic diagram of the fourth three-electrode detection mode in the embodiment of the present application;

[0071] Figure 3e Schematic diagram of the fifth three-electrode detection mode in the first embodiment of the present application;

[0072] Figure 3f Schematic diagram of the sixth three-electrode detection mode in the first embodiment of the present application;

[0073] Figure 3g Schematic diagram of the seventh three-electrode detection mode in the first embodiment of the present application;

[0074] Figure 3h Schematic diagram of the eighth three-electrode detection mode in the first embodiment of the present application;

[0075] Figure 4a Schematic diagram of the first four-electrode ground detection mode in the second embodiment of the present application;

[0076] Figure 4b Schematic diagram of the second four-electrode ground detection mode in the second embodiment of the present application;

[0077] Figure 5a Schematic diagram of the first three-electrode ground detection mode in the second embodiment of the present application;

[0078] Figure 5b Schematic diagram of the second three-electrode ground detection mode in the second embodiment of the present application;

[0079] Figure 5c Schematic diagram of the third three-electrode ground detection mode in the second embodiment of the present application;

[0080] Figure 5d Schematic diagram of the fourth three-electrode ground detection mode in the second embodiment of the present application;

[0081] Figure 6 Schematic diagram of the modular structure of the early cognitive impairment screening system in the third embodiment of the present application;

[0082] Figures 7 to 12 Predictive results obtained by clinical trials using the early cognitive impairment screening system based on multi-mode electromagnetic field biological detection of the present application, and corresponding verification clinical cases obtained by CT diagnosis / MRI diagnosis.

[0083] Markings in the figure: 1, first electrode sheet; 2, second electrode sheet; 3, third electrode sheet; 4, fourth electrode sheet; 5, fifth electrode sheet; 6, sixth electrode sheet. DETAILED DESCRIPTION

[0084] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0085] Herein, the suffix such as "module", "component" or "unit" used for representing an element is only for facilitating the description of the present application, and has no specific meaning by itself. Therefore, "module", "component" or "unit" can be mixedly used. Herein, the terms "upper", "lower", "inner", "outer", "front", "back", "one end", "the other end" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0086] Herein, unless otherwise explicitly specified and limited, the terms "mount", "provided with", "connected" and the like should be understood in a broad sense, for example, "connected" can be fixedly connected, or detachably connected, or integrally connected; can be mechanically connected, can be directly connected, or indirectly connected through an intermediate medium, can be the communication inside two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances. Herein, "a plurality of" means two or more, that is, it includes two, three, four, five and the like.

[0087] Herein, "abnormality" means that when an excitation signal of a specific frequency is transmitted from a transmitting end, and reaches a receiving end through a specific transmission path (i.e. the propagation path between the transmitting end and the receiving end), due to the existence of a lesion corresponding to a certain disease in the transmission path, the detection signal received by the receiving end is different from the detection signal (i.e. electromagnetic field biological signal, including received impedance, transmission differential impedance and disturbance coefficient, etc.) received when there is no lesion or there is a lesion corresponding to other diseases in the transmission path, so it is called abnormality.

[0088] The "excitation signal" herein includes a sinusoid with a frequency selected from a specified frequency range; or a pulse or pulse sequence with a pulse width and a pulse repetition frequency selected from a specified pulse width range and a specified pulse repetition frequency range; or a coded signal such as a chirp signal with a frequency varying over time to obtain a tissue response in a specified frequency range and minimize interference, multipath effects, and radio frequency (RF) noise and other noise.

[0089] The "detection mode" herein refers to the electrode sheet at a specified position as an excitation transmitting end to transmit an excitation signal of a specific frequency range to the subject's brain to obtain the perturbation coefficient of a specific region.

[0090] Embodiment I: The embodiment provides a method for screening early cognitive impairment by multi-mode electromagnetic field biological detection, referring to Figures 1-3h , comprising:

[0091] S101: A first electrode sheet 1 and a second electrode sheet 2 are respectively arranged in advance on the forehead position and the occiput position of the brain of a user to be detected, a third electrode sheet 3 and a fourth electrode sheet 4 are arranged side by side on the left side of the brain, and a fifth electrode sheet 5 and a sixth electrode sheet 6 are arranged side by side on the right side of the brain.

[0092] S102: Obtain the perturbation coefficient set of the user to be detected under the reference detection mode combination, and input it into the pre-trained early cognitive impairment screening model to obtain the prediction probability value of the user to be detected to have early cognitive impairment.

[0093] In the embodiment, the perturbation coefficient set under the reference detection mode combination includes: a first perturbation coefficient set and a second perturbation coefficient set under a preset first four-electrode detection mode and a second four-electrode detection mode, and a third to sixth perturbation coefficient set under a first to fourth three-electrode detection mode.

[0094] In the first four-electrode detection mode, the first electrode at the forehead position is the excitation transmitting end, and the second electrode sheet at the occiput position and the third electrode sheet and the fifth electrode sheet on the left side and the right side of the brain are the excitation receiving end. Correspondingly, the first perturbation coefficient set includes: the seventh perturbation coefficient R7, the fifth perturbation coefficient R5 and the sixth perturbation coefficient R6 on the propagation path between the first electrode sheet and the second electrode sheet, the third electrode sheet and the fifth electrode sheet, respectively.

[0095] In the second four-electrode detection mode, the second electrode patch located at the occiput position serves as the excitation transmitting end, and the first electrode patch located at the forehead position and the fourth and sixth electrode patches located at the left and right sides of the brain respectively serve as the excitation receiving end. Correspondingly, the second disturbance coefficient set includes the eighth disturbance coefficient R7', the third disturbance coefficient R3, and the fourth disturbance coefficient R4 between the propagation paths of the second electrode patch and the first, fourth, and sixth electrode patches respectively.

[0096] In the first three-electrode detection mode, the third electrode patch located at the left side of the brain serves as the excitation transmitting end, and the first electrode located at the forehead position and the fifth electrode patch located at the right side of the brain serve as the excitation receiving end. Correspondingly, the three disturbance coefficient set includes the twelfth disturbance coefficient R5' and the first disturbance coefficient R1 between the propagation paths of the third electrode patch and the first and fifth electrode patches respectively.

[0097] In the second three-electrode detection mode, the fourth electrode patch located at the left side of the brain serves as the excitation transmitting end, and the second electrode located at the occiput position and the sixth electrode patch located at the right side of the brain serve as the excitation receiving end. Correspondingly, the four disturbance coefficient set includes the tenth disturbance coefficient R3' and the second disturbance coefficient R2 between the propagation paths of the fourth electrode patch and the second and sixth electrode patches respectively.

[0098] In the third three-electrode detection mode, the fifth electrode patch located at the right side of the brain serves as the excitation transmitting end, and the first electrode located at the forehead position and the third electrode patch located at the left side of the brain serve as the excitation receiving end. Correspondingly, the five disturbance coefficient set includes the thirteenth disturbance coefficient R6' and the eighth disturbance coefficient R1' between the propagation paths of the fifth electrode patch and the first and third electrode patches respectively.

[0099] In the fourth three-electrode detection mode, the sixth electrode patch located at the right side of the brain serves as the excitation transmitting end, and the second electrode located at the occiput position and the fourth electrode patch located at the left side of the brain serve as the excitation receiving end. Correspondingly, the six disturbance coefficient set includes the eleventh disturbance coefficient R4' and the ninth disturbance coefficient R2' between the propagation paths of the sixth electrode patch and the second and fourth electrode patches respectively.

[0100] The step of training the early cognitive impairment screening model includes:

[0101] S201 obtaining a plurality of healthy subjects in the baseline detection mode combination Health disturbance coefficient data set;

[0102] S202 obtaining a plurality of early cognitive impairment subjects in the baseline detection mode combination Abnormal disturbance coefficient data set;

[0103] S203 obtaining scale detection results of the plurality of early cognitive impairment subjects through a specified scale method;

[0104] S204 inputting the health disturbance coefficient data set, the abnormal disturbance coefficient data set and the scale detection results into a pre-constructed neural network model for learning to obtain the early cognitive impairment screening model.

[0105] It is worth noting that for different brain diseases, the lesion or pathological tissue occurs in different positions, and in the process of electromagnetic field biological detection, different positions of emission and reception will produce different detection data, therefore, the subtle differences in detection position may greatly affect the detection results.

[0106] The present application selects the upper forehead position and the back occipital position of the brain to set two electrode pieces, and simultaneously sets two electrode pieces on the left side of the brain and the right side of the brain, respectively, and pre-constructs a model according to the interference coefficient of the early cognitive impairment population, so that in subsequent detection, only the preset reference detection mode is used to detect the user to be detected to obtain the corresponding interference coefficient set, and the prediction probability of the user suffering from early cognitive impairment can be obtained, so that the user who may suffer from early cognitive impairment can be screened out according to the prediction probability, and the user is reminded to go to a medical institution for timely treatment for diagnosis. For example, if the prediction probability is greater than a preset threshold range, the user is marked and reminded to go to a medical institution for timely treatment for diagnosis. Specifically, for example, if the prediction probability is greater than or equal to 90%, it means that the user has a risk of early cognitive impairment; if it is less than the minimum value of the first preset threshold range, it means that the user has no risk.

[0107] Further, if the prediction probability is less than the minimum value of the first preset threshold range, and the difference between the prediction probability and the minimum value is less than a preset difference value, it means that the user may actually suffer from early cognitive impairment, but it is difficult to be detected, therefore, the user is tested for multiple days in succession to obtain multiple test results, and the average value of the multiple test results is compared with the first preset threshold range, if it belongs to the first preset threshold range, it means that the user has a risk of early cognitive impairment; if it is less than the minimum value of the first preset threshold range, it means that the user has no risk. Preferably, if the fluctuation rate of the multiple test results is greater than a preset fluctuation rate threshold, the average value is compared with the first preset threshold range, otherwise, it is determined that the user has no risk.

[0108] In some embodiments, the step of training the early cognitive impairment screening model further comprises:

[0109] S205 acquiring and identifying the associated past medical history of the plurality of early cognitive impairment subjects; the associated past medical history includes at least one of hypertension, stroke, cerebral infarction and genetic factors;

[0110] S206a if there are two or more past medical histories, acquiring the perturbation coefficient set of the subject under the combination of the baseline detection modes, and inputting the same into a pre-constructed neural network model together with the healthy perturbation coefficient data set and the scale detection result for training, to obtain a first prediction model;

[0111] S206b if there is a single past medical history, acquiring the perturbation coefficient set of the subject under the fifth to eighth three-electrode detection modes, and the perturbation coefficient set obtained under the combination of the baseline detection modes, and inputting the same into a pre-constructed neural network model together with the healthy perturbation coefficient data set and the scale detection result for training, to obtain a second prediction model.

[0112] Correspondingly, S102 specifically includes:

[0113] acquiring and identifying the associated past medical history of the user to be detected;

[0114] if there are two or more past medical histories, acquiring the perturbation coefficient set of the user to be detected under the combination of the baseline detection modes, and then inputting the same into the first prediction model for prediction.

[0115] In some embodiments, when the prediction probability value detected by the user with two or more past medical histories meets the first preset threshold range, the detection is ended. Of course, if the prediction probability value is not within the preset threshold range, the perturbation coefficient set of the user to be detected under the fifth to eighth three-electrode detection modes can also be acquired, and inputted into the second prediction model together with the perturbation coefficient set under the combination of the baseline detection modes for secondary prediction, to obtain a prediction probability value predicted based on the second prediction model, and determine the prediction value as the prediction result. For example, if the predicted probability value is greater than 90% (the minimum value in the first preset threshold range), it is determined that the user has the risk of suffering from the disease, and thus needs to be further diagnosed for diagnosis.

[0116] The preset range threshold can be obtained according to the probability of the elderly population with past medical histories suffering from early cognitive impairment calculated from a pre-statistical medical database. Different past medical histories correspond to different probability ranges, and when there are multiple past medical histories, the probability range of early cognitive impairment with multiple past medical histories is obtained by combining the probabilities of multiple past medical histories, and different combinations of past medical histories correspond to different probability ranges. Generally speaking, the more types of past medical histories, the higher the probability of early cognitive impairment.

[0117] If it is a single previous medical history, the disturbance coefficient set of the to-be-detected user under the combination of the reference detection modes and the disturbance coefficient set under the fifth to eighth three-electrode detection modes are obtained respectively and input into the second prediction model for prediction.

[0118] The associated previous medical history of the to-be-detected user can be directly extracted from a database previously counted by a hospital or other institutions, or directly obtained from the to-be-detected user through a questionnaire survey or on-site inquiry.

[0119] The present scheme divides the users into a single previous medical history group and a multiple medical history group in advance, and constructs a corresponding prediction model according to the user type, which can effectively reduce the calculation amount while ensuring the prediction accuracy.

[0120] In some embodiments, in the fifth three-electrode detection mode, the third electrode patch located on the left side of the brain is used as the excitation transmitting end, and the first electrode located on the forehead and the sixth electrode patch located on the right side of the brain are used as the excitation receiving end. Correspondingly, the seventh disturbance coefficient set under the fifth three-electrode detection mode includes the fifteenth disturbance coefficient R5' and the sixteenth disturbance coefficient R16 on the propagation path between the third electrode patch and the first electrode patch and the sixth electrode patch, respectively.

[0121] In some embodiments, in the sixth three-electrode detection mode, the fourth electrode patch located on the left side of the brain is used as the excitation transmitting end, and the second electrode patch located on the back of the head and the fifth electrode patch located on the right side of the brain are used as the excitation receiving end. Correspondingly, the eighth disturbance coefficient set under the sixth three-electrode detection mode includes the tenth disturbance coefficient R3' and the seventeenth disturbance coefficient R17 on the propagation path between the fourth electrode patch and the second electrode patch and the fifth electrode patch, respectively.

[0122] In some embodiments, in the seventh three-electrode detection mode, the fifth electrode patch located on the right side of the brain is used as the excitation transmitting end, and the first electrode located on the forehead and the fourth electrode patch located on the left side of the brain are used as the excitation receiving end. Correspondingly, the ninth disturbance coefficient set under the seventh three-electrode detection mode includes the thirteenth disturbance coefficient R6' and the eighteenth disturbance coefficient R18 on the propagation path between the fifth electrode patch and the first electrode patch and the fourth electrode patch, respectively.

[0123] In some embodiments, in the eighth three-electrode detection mode, the sixth electrode patch located on the right side of the brain is used as the excitation transmitting end, and the second electrode located on the back of the head and the third electrode patch located on the left side of the brain are used as the excitation receiving end. Correspondingly, the tenth disturbance coefficient set under the eighth three-electrode detection mode includes the eleventh disturbance coefficient R4' and the nineteenth disturbance coefficient R19 on the propagation path between the sixth electrode patch and the second electrode patch and the third electrode patch, respectively.

[0124] In some embodiments, if the subject to be tested has a history of stroke, the proportion of the sum of the three disturbance coefficient sets and the four disturbance coefficient sets in the first and third three-electrode detection modes is greater than the proportion of the sum of the five disturbance coefficient sets and the six disturbance coefficient sets in the second and fourth three-electrode detection modes.

[0125] If the subject to be tested has a history of cerebral infarction, the proportion of the sum of the three disturbance coefficient sets and the five disturbance coefficient sets in the first and third three-electrode detection modes is greater than the proportion of the sum of the four disturbance coefficient sets and the six disturbance coefficient sets in the second and fourth three-electrode detection modes.

[0126] According to the different proportion of the data set in different modes according to the high-risk lesion of different history, the detection rate can be effectively improved; for example, the risk of cognitive impairment of the brain stroke lesion occurring in the left side of the brain is high, therefore, the detection proportion of the first and second three-electrode detection modes is greater than that of the third and fourth electrode detection modes; for example, the brain infarction occurs in the left hemisphere and the front hemisphere, and the risk of cognitive impairment of the front side of the brain is high; therefore, when collecting data, the detection proportion of the first and third three-electrode detection modes is greater than that of the second and fourth three-electrode detection modes.

[0127] Embodiment two: different from embodiment one, based on the early cognitive impairment screening method provided in embodiment one, this embodiment is for people without history or with less history (for example, less than or equal to 2 kinds), and proposes a grounded reference detection mode combination, specifically, see Figures 4a-5d , the grounded reference detection mode combination includes:

[0128] The first four-electrode grounded detection mode takes the first electrode sheet as the excitation transmitting end, takes the second electrode sheet opposite to the first electrode sheet as the grounding end, takes the third electrode sheet and the fifth electrode sheet as the excitation receiving end, and obtains the eleventh disturbance coefficient set, the eleventh disturbance coefficient set includes: the fifth disturbance coefficient R5 and the sixth disturbance coefficient R6 between the first electrode sheet and the third electrode sheet and the fifth electrode sheet, respectively;

[0129] The second four-electrode grounded detection mode takes the second electrode sheet as the excitation transmitting end, takes the first electrode sheet as the grounding end, takes the fourth electrode sheet and the sixth electrode sheet as the excitation receiving end, and obtains the twelfth disturbance coefficient set, the twelfth disturbance coefficient set includes: the third disturbance coefficient R3 and the fourth disturbance coefficient R4 between the second electrode sheet and the fourth electrode sheet and the sixth electrode sheet, respectively;

[0130] a first three-electrode ground detection mode, taking the third electrode as the excitation transmitting end, taking the fifth electrode opposite to the third electrode as the ground end, and taking the first electrode as the excitation receiving end, to obtain a thirteenth disturbance coefficient set, the thirteenth disturbance coefficient set comprising: a twelfth disturbance coefficient R5' on a propagation path between the third electrode and the first electrode;

[0131] a second three-electrode ground detection mode, taking the fourth electrode as the excitation transmitting end, taking the sixth electrode as the ground end, and taking the second electrode as the excitation receiving end, to obtain a fourteenth disturbance coefficient set, the fourteenth disturbance coefficient set comprising: a tenth disturbance coefficient R3' on a propagation path between the fourth electrode and the second electrode;

[0132] a third three-electrode ground detection mode, taking the fifth electrode as the excitation transmitting end, taking the third electrode as the ground end, and taking the first electrode as the excitation receiving end, to obtain a fifteenth disturbance coefficient set, the fifteenth disturbance coefficient set comprising: a fifteenth disturbance coefficient R6' on a propagation path between the fifth electrode and the first electrode;

[0133] a fourth three-electrode ground detection mode, taking the sixth electrode as the excitation transmitting end, taking the fourth electrode as the ground end, and taking the second electrode as the excitation receiving end, to obtain a sixteenth disturbance coefficient set, the sixteenth disturbance coefficient set comprising: an eleventh disturbance coefficient R4' on a propagation path between the sixth electrode and the second electrode.

[0134] Further, compared with patients with a history, patients without a history are more difficult to be screened out, and therefore, in order to avoid missing to a certain extent, when the prediction probability value obtained by the above screening method meets the second preset threshold range, secondary screening is performed, specifically, it comprises the above various detection modes, except that it further comprises an alternative mode:

[0135] a fifth three-electrode ground detection mode, taking the sixth electrode as the excitation transmitting end, taking the second electrode as the ground end, and taking the third electrode as the excitation receiving end, to obtain a seventeenth disturbance coefficient set, the seventeenth disturbance coefficient set comprising: a nineteenth disturbance coefficient R19 on a propagation path between the sixth electrode and the third electrode;

[0136] a sixth three-electrode ground detection mode, taking the fourth electrode as the excitation transmitting end, taking the second electrode as the ground end, and taking the fifth electrode as the excitation receiving end, to obtain an eighteenth disturbance coefficient set, the eighteenth disturbance coefficient set comprising: a seventeenth disturbance coefficient R17 on a propagation path between the fourth electrode and the fifth electrode;

[0137] The seventh three-electrode grounding detection mode takes the third electrode sheet as the excitation transmitting end, the first electrode sheet as the grounding end, and the sixth electrode sheet as the excitation receiving end to obtain a nineteenth disturbance coefficient set, and the nineteenth disturbance coefficient set includes a sixteenth disturbance coefficient R16 on a propagation path between the third electrode sheet and the sixth electrode sheet.

[0138] The eighth three-electrode grounding detection mode takes the fifth electrode sheet as the excitation transmitting end, the first electrode sheet as the grounding end, and the fourth electrode sheet as the excitation receiving end to obtain a twentieth disturbance coefficient set, and the twentieth disturbance coefficient set includes an eighteenth disturbance coefficient R18 on a propagation path between the fifth electrode sheet and the fourth electrode sheet.

[0139] Specifically, the second preset threshold range is smaller than the first preset threshold range. For example, the first preset threshold range is ≥ 90%, and the second preset threshold range is [85%, 90%].

[0140] Correspondingly, the training of the early cognitive impairment screening model further includes:

[0141] The disturbance coefficient set of the plurality of early cognitive impairment subjects without a medical history under the grounding reference detection mode combination is obtained, and the disturbance coefficient set is input into the neural network model constructed in advance together with the healthy disturbance coefficient data set and the scale detection result to obtain a third prediction model.

[0142] The grounding reference detection mode combination with the above mode can meet the whole brain detection while having a small amount of data and being capable of being used and popularized on a large scale.

[0143] Embodiment three: see Figure 6 The application further provides an early cognitive impairment screening system based on a multi-mode electromagnetic field biological detection, which comprises:

[0144] The data acquisition device comprises a data communication module and an electrode group for obtaining data of a user, and the electrode group comprises a first electrode sheet and a second electrode sheet corresponding to a forehead position and a back occipital position of a brain, respectively, a third electrode sheet and a fourth electrode sheet arranged side by side on a left side of the brain, and a fifth electrode sheet and a sixth electrode sheet arranged side by side on a right side of the brain.

[0145] The screening device is in data communication with the data acquisition device, is used for obtaining a disturbance coefficient set of the data acquisition device under a preset reference detection mode combination, and inputs the disturbance coefficient set into a pre-trained early cognitive impairment screening model to obtain a prediction probability value of the user to be detected to have early cognitive impairment.

[0146] Specifically, the screening device comprises:

[0147] a first data acquisition module, configured to communicate with the data acquisition device to respectively acquire a plurality of health disturbance coefficient data sets of a plurality of healthy subjects under the combination of the reference detection modes, and respectively acquire a plurality of abnormal disturbance coefficient data sets of a plurality of early cognitive impairment subjects under the combination of the reference detection modes, and acquire a disturbance coefficient set of the to-be-detected user under the combination of the reference detection modes;

[0148] a second data acquisition module, configured to acquire scale detection results of the plurality of early cognitive impairment subjects obtained through a specified scale method;

[0149] a screening model construction module, configured to train a pre-constructed neural network model based on the health disturbance coefficient data sets, the abnormal disturbance coefficient data sets, and the scale detection results, to obtain the early cognitive impairment screening model.

[0150] a prediction module, configured to perform prediction based on the early cognitive impairment screening model constructed by the screening model construction module, and the disturbance coefficient set of the to-be-detected user under the combination of the reference detection modes acquired by the first data acquisition module, to obtain a prediction probability value of the to-be-detected user developing early cognitive impairment;

[0151] wherein the disturbance coefficient set under the combination of the reference detection modes includes a first disturbance coefficient set and a second disturbance coefficient set under a preset first four-electrode detection mode and a second four-electrode detection mode, and a third disturbance coefficient set, a fourth disturbance coefficient set, a fifth disturbance coefficient set, and a sixth disturbance coefficient set under a first three-electrode detection mode, a second three-electrode detection mode, a third three-electrode detection mode, and a fourth three-electrode detection mode;

[0152] In the first four-electrode detection mode, a first electrode located at a forehead position serves as an excitation transmitting end, and a second electrode located at a back occipital position and a third electrode and a fifth electrode located at left and right sides of the brain respectively serve as excitation receiving ends. Correspondingly, the first disturbance coefficient set includes a seventh disturbance coefficient R7, a fifth disturbance coefficient R5, and a sixth disturbance coefficient R6 on a propagation path between the first electrode and the second electrode, the third electrode, and the fifth electrode respectively;

[0153] In the second four-electrode detection mode, the second electrode located at the back occipital position serves as the excitation transmitting end, and the first electrode located at the forehead position and the fourth electrode and the sixth electrode located at the left and right sides of the brain respectively serve as the excitation receiving ends. Correspondingly, the second disturbance coefficient set includes an eighth disturbance coefficient R7', a third disturbance coefficient R3, and a fourth disturbance coefficient R4 on a propagation path between the second electrode and the first electrode, the fourth electrode, and the sixth electrode respectively;

[0154] In the first three-electrode detection mode, the third electrode patch on the left side of the brain is used as the excitation transmitting end, the first electrode on the forehead and the fifth electrode patch on the right side of the brain are used as the excitation receiving end, and correspondingly, the three disturbance coefficient set includes: the twelfth disturbance coefficient R5' and the first disturbance coefficient R1 between the third electrode patch and the first electrode patch and the fifth electrode patch, respectively.

[0155] In the second three-electrode detection mode, the fourth electrode patch on the left side of the brain is used as the excitation transmitting end, the second electrode on the back of the head and the sixth electrode patch on the right side of the brain are used as the excitation receiving end, and correspondingly, the four disturbance coefficient set includes: the tenth disturbance coefficient R3' and the second disturbance coefficient R2 between the fourth electrode patch and the second electrode patch and the sixth electrode patch, respectively.

[0156] In the third three-electrode detection mode, the fifth electrode patch on the right side of the brain is used as the excitation transmitting end, the first electrode on the forehead and the third electrode patch on the left side of the brain are used as the excitation receiving end, and correspondingly, the five disturbance coefficient set includes: the thirteenth disturbance coefficient R6' and the eighth disturbance coefficient R1' between the fifth electrode patch and the first electrode patch and the third electrode patch, respectively.

[0157] In the fourth three-electrode detection mode, the sixth electrode patch on the right side of the brain is used as the excitation transmitting end, the second electrode on the back of the head and the fourth electrode patch on the left side of the brain are used as the excitation receiving end, and correspondingly, the six disturbance coefficient set includes: the eleventh disturbance coefficient R4' and the ninth disturbance coefficient R2' between the sixth electrode patch and the second electrode patch and the fourth electrode patch, respectively.

[0158] In some embodiments, the screening device further comprises a third data acquisition module configured to acquire and identify associated past medical history of the plurality of early cognitive impairment subjects, wherein the associated past medical history comprises at least one of hypertension, stroke, cerebral infarction, and genetic factors; a fourth data acquisition module configured to acquire a set of perturbation coefficients of the subject under the combination of the baseline detection modes when the subject has two or more associated past medical history, and to acquire a set of perturbation coefficients of the subject under the fifth to eighth three-electrode detection modes when the subject has a single past medical history, and the screening model construction module is further configured to train a first prediction model by inputting the set of perturbation coefficients of the subject under the combination of the baseline detection modes, the healthy set of perturbation coefficients, and the scale detection result into the model when the subject has two or more associated past medical history, and to train a second prediction model by inputting the set of perturbation coefficients of the subject under the fifth to eighth three-electrode detection modes, the set of perturbation coefficients obtained under the combination of the baseline detection modes, the healthy set of perturbation coefficients, and the scale detection result into the model when the subject has a single past medical history.

[0159] In some embodiments, when the past medical history of the subject to be tested is stroke, the proportion of the sum of the three sets of perturbation coefficients under the first and second three-electrode detection modes to the sum of the five and six sets of perturbation coefficients under the third and fourth three-electrode detection modes in the corresponding set of perturbation coefficients is greater; when the past medical history of the subject to be tested is cerebral infarction, the proportion of the sum of the three and five sets of perturbation coefficients under the first and third three-electrode detection modes to the sum of the four and six sets of perturbation coefficients under the second and fourth three-electrode detection modes in the corresponding set of perturbation coefficients is greater.

[0160] In the fifth three-electrode detection mode, the third electrode patch located on the left side of the brain is used as the excitation transmitting end, and the first electrode located on the forehead and the sixth electrode patch located on the right side of the brain are used as the excitation receiving end, and accordingly, the seventh set of perturbation coefficients under the fifth three-electrode detection mode comprises the fifteenth perturbation coefficient R5’ and the sixteenth perturbation coefficient R16 between the third electrode patch and the first electrode patch and the sixth electrode patch, respectively.

[0161] In the sixth three-electrode detection mode, the fourth electrode patch located on the left side of the brain is used as the excitation transmitting end, and the second electrode patch located on the back of the head and the fifth electrode patch located on the right side of the brain are used as the excitation receiving end, and accordingly, the eighth set of perturbation coefficients under the sixth three-electrode detection mode comprises the tenth perturbation coefficient R3’ and the seventeenth perturbation coefficient R17 between the fourth electrode patch and the second electrode patch and the fifth electrode patch, respectively.

[0162] In the seventh three-electrode detection mode, the fifth electrode patch located on the right side of the brain serves as the excitation transmitting end, and the first electrode located on the forehead and the fourth electrode patch located on the left side of the brain serve as the excitation receiving end. Correspondingly, the ninth disturbance coefficient set in the seventh three-electrode detection mode includes the thirteenth disturbance coefficient R6' and the eighteenth disturbance coefficient R18 between the fifth electrode patch and the first electrode patch and the fourth electrode patch, respectively.

[0163] In the eighth three-electrode detection mode, the sixth electrode patch located on the right side of the brain serves as the excitation transmitting end, and the second electrode located on the back of the head and the third electrode patch located on the left side of the brain serve as the excitation receiving end. Correspondingly, the tenth disturbance coefficient set in the eighth three-electrode detection mode includes the eleventh disturbance coefficient R4' and the nineteenth disturbance coefficient R19 between the sixth electrode patch and the second electrode patch and the third electrode patch, respectively.

[0164] In some embodiments, the data acquisition device described above further includes an excitation generator configured to generate an excitation signal in the corresponding detection mode according to the control signal sent by the host computer, and control the working state of the electrode group (including: as an excitation transmitting end, or as an excitation receiving end, or as a ground end, or as a suspended end; wherein the suspended end means that the electrode patch is neither grounded nor transmits an excitation signal, nor receives an excitation signal, but is suspended).

[0165] Of course, in other embodiments, the excitation generator can also not be arranged in the data acquisition device, that is, the data acquisition device is externally connected with an excitation generator, and the data acquisition device communicates data with the host computer (preferably, the screening device is integrated in the host computer) through the communication module, and the excitation generator is externally connected with the host computer, and the host computer controls the excitation generator to generate a corresponding excitation signal and sends it to the corresponding electrode in the data acquisition device; of course, the host computer generates a corresponding control signal according to the corresponding detection mode and sends it to the data acquisition device to control the working state of each electrode patch.

[0166] In order to verify the effectiveness of the early cognitive impairment screening method and system in the present scheme, the following clinical verification is carried out:

[0167] Specifically, to verify the sensitivity of the screening method and system of the present application, the cognitive function and emotional state of the elderly population were screened by using general condition self-rating scale and community dementia scale (GSI-D), cognitive function self-assessment scale (AD8), activities of daily living assessment scale (ADL), Mini-Cog scale, etc. in mental health centers, welfare homes, elderly service centers and communities, and the screening results obtained by using the above scales were compared with the screening results obtained by using the device. The total number of elderly population screened in this activity was 1502, of which 1023 were cognitive impairment population according to the scale, and 745 were cognitive impairment population detected by using the device, accounting for 72.83%.

[0168] To verify the specificity of the device, 180 young healthy people from related enterprises were also screened by using the device, of which 168 were normal, accounting for 93.33%.

[0169] In summary, the device has high sensitivity and specificity. The following is an example of the prediction of a number of subjects:

[0170] Example one: see Figure 7 Patient I was diagnosed with mild cognitive impairment by a certain health center in Chongqing, and the detection disturbance coefficient measured by the screening method of the present application was 169, which was not within the healthy person disturbance coefficient interval of 120-160, and the probability of early cognitive impairment was predicted to be 93.56% (greater than the preset probability threshold), which was consistent with the actual diagnosis result.

[0171] Example two: see Figure 8 Patient II was diagnosed with mild cognitive impairment by a certain health center in Chongqing, and the detection disturbance coefficient measured by the device was 183, which was not within the healthy person disturbance coefficient interval of 120-160, and the probability of early cognitive impairment was predicted to be 95.51% (greater than the preset probability threshold), which was consistent with the actual diagnosis result.

[0172] Example three: see Figure 9 Patient III was diagnosed with mild cognitive impairment by a certain health center in Chongqing, and the detection disturbance coefficient measured by the device was 114, which was not within the healthy person disturbance coefficient interval of 120-160, and the probability of early cognitive impairment was predicted to be 92.68% (greater than the preset probability threshold), which was consistent with the actual diagnosis result.

[0173] Example four: see Figure 10, patient IV is diagnosed as mild cognitive impairment by a health center in Chongqing, and the detection disturbance coefficient measured by the device is 163, which is not within the healthy person disturbance coefficient interval 120-160, and the prediction probability of early cognitive impairment is 94.61% (greater than the preset probability threshold), which is consistent with the actual diagnosis result.

[0174] Example five: see Figure 11 , patient V is diagnosed as mild cognitive impairment by a health center in Chongqing, and the detection disturbance coefficient measured by the device is 166, which is not within the healthy person disturbance coefficient interval 120-160, and the prediction probability of early cognitive impairment is 93.88% (greater than the preset probability threshold), which is consistent with the actual diagnosis result.

[0175] Example six: see Figure 12 , patient VI is diagnosed as mild cognitive impairment by a health center in Chongqing, and the detection disturbance coefficient measured by the device is 168, which is not within the healthy person disturbance coefficient interval 120-160, and the prediction probability of early cognitive impairment is 92.73% (greater than the preset probability threshold), which is consistent with the actual diagnosis result.

[0176] In summary, the present scheme constructs a rich prediction model by pre-acquiring data of the subjects (including the disturbance data set collected by the device, and the data set measured by the scale, etc.); then acquires the user type in the specific use process, and matches the corresponding detection mode, then inputs the current user's disturbance data set collected by the corresponding mode into the pre-constructed early cognitive impairment screening model, to obtain the prediction probability value of early cognitive impairment, which has high accuracy and small data processing amount, can be used for large-scale early cognitive impairment screening, has strong universality, and is especially suitable for community, welfare home and other places where the elderly gather.

[0177] It should be noted that in this paper, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0178] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these all belong to the protection of the present application.

Claims

1. A method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection, characterized in that, include: S101 pre-sets a first electrode and a second electrode at the forehead and occipital region of the brain of the user to be tested, respectively, and sets a third electrode and a fourth electrode in parallel on the left side of the brain, and sets a fifth electrode and a sixth electrode in parallel on the right side of the brain. S102 Obtains the set of perturbation coefficients of the user to be detected under the combination of benchmark detection modes, and inputs it into the pre-trained early cognitive impairment screening model to predict the predicted probability value of the user to be detected having early cognitive impairment. The set of perturbation coefficients under the reference detection mode combination includes: the first set of perturbation coefficients and the second set of perturbation coefficients under the preset first four-electrode detection mode and the second four-electrode detection mode, as well as the third to sixth sets of perturbation coefficients under the first to fourth three-electrode detection modes. In the first four-electrode detection mode, the first electrode plate located on the forehead serves as the excitation transmitter, the second electrode plate located at the back of the head, and the third and fifth electrode plates located on the left and right sides of the brain, respectively, serve as the excitation receivers. Correspondingly, the first set of perturbation coefficients includes: the seventh perturbation coefficient R7, the fifth perturbation coefficient R5, and the sixth perturbation coefficient R6 on the propagation path between the first electrode plate and the second, third, and fifth electrode plates, respectively. In the second four-electrode detection mode, the second electrode plate located at the back of the head serves as the excitation transmitter, and the first electrode plate located at the forehead and the fourth and sixth electrode plates located on the left and right sides of the brain, respectively, serve as the excitation receivers. Correspondingly, the second set of perturbation coefficients includes: the eighth perturbation coefficient R7', the third perturbation coefficient R3, and the fourth perturbation coefficient R4 on the propagation path between the second electrode plate and the first, fourth, and sixth electrode plates, respectively. In the first three-electrode detection mode, the third electrode plate located on the left side of the brain serves as the excitation transmitter, and the first electrode plate located on the forehead and the fifth electrode plate located on the right side of the brain serve as the excitation receiver. Accordingly, the third set of perturbation coefficients includes: the twelfth perturbation coefficient R5' and the first perturbation coefficient R1 on the propagation path between the third electrode plate and the first and fifth electrode plates, respectively. In the second and third electrode detection mode, the fourth electrode plate located on the left side of the brain serves as the excitation transmitter, and the second electrode plate located at the back of the head and the sixth electrode plate located on the right side of the brain serve as the excitation receiver. Accordingly, the fourth perturbation coefficient set includes: the tenth perturbation coefficient R3' and the second perturbation coefficient R2 on the propagation path between the fourth electrode plate and the second and sixth electrode plates, respectively. In the third three-electrode detection mode, the fifth electrode plate located on the right side of the brain serves as the excitation transmitter, and the first electrode plate located on the forehead and the third electrode plate located on the left side of the brain serve as the excitation receiver. Accordingly, the fifth perturbation coefficient set includes: the thirteenth perturbation coefficient R6' and the eighth perturbation coefficient R1' on the propagation path between the fifth electrode plate and the first and third electrode plates, respectively. In the fourth three-electrode detection mode, the sixth electrode plate located on the right side of the brain serves as the excitation transmitter, and the second electrode plate located at the back of the head and the fourth electrode plate located on the left side of the brain serve as the excitation receiver. Accordingly, the sixth perturbation coefficient set includes: the eleventh perturbation coefficient R4' and the ninth perturbation coefficient R2' on the propagation path between the sixth electrode plate and the second and fourth electrode plates, respectively. The specific steps for training the early cognitive impairment screening model include: S201 Obtains a dataset of health perturbation coefficients from multiple healthy subjects under the aforementioned combination of benchmark detection modes; S202 Obtains a dataset of abnormal perturbation coefficients from multiple subjects with early cognitive impairment under the aforementioned combination of benchmark detection modes; S203 Obtain the scale test results of the multiple early cognitive impairment subjects after testing with a specified scale method; S204 inputs the health disturbance coefficient dataset, the abnormal disturbance coefficient dataset, and the scale detection results into a pre-built neural network model for learning, thereby obtaining the early cognitive impairment screening model.

2. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 1, characterized in that, The steps for training the early cognitive impairment screening model also include: S205 Obtain and identify the associated medical histories of the plurality of early cognitive impairment subjects; the associated medical histories include at least one of hypertension, stroke, cerebral infarction and genetic factors; If S206a has two or more past medical histories, obtain the perturbation coefficient set of the subject under the combination of the benchmark detection modes, and input it, along with the health perturbation coefficient dataset and the scale detection results, into a pre-built neural network model for training to obtain a first prediction model; If S206b is a single past medical history, the perturbation coefficient set of the subject under the fifth to eighth three-electrode detection modes and the perturbation coefficient set obtained under the combination of the benchmark detection modes are obtained respectively, and the perturbation coefficient set, together with the health perturbation coefficient dataset and the scale detection results, are input into a pre-built neural network model for training to obtain a second prediction model.

3. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 2, characterized in that, S102 specifically includes: Obtain and identify the associated past medical history of the user to be tested; If there are two or more past medical histories, obtain the set of perturbation coefficients of the user to be detected under the combination of the baseline detection modes, and then input it into the first prediction model for prediction; If it is a single past medical history, the perturbation coefficient set of the user to be tested under the benchmark detection mode combination and the perturbation coefficient set under the fifth to eighth three-electrode detection modes are obtained respectively, and then input into the second prediction model for prediction.

4. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 3, characterized in that, In the fifth three-electrode detection mode, the third electrode plate located on the left side of the brain serves as the excitation transmitter, and the first electrode plate located on the forehead and the sixth electrode plate located on the right side of the brain serve as the excitation receiver. Correspondingly, the seventh set of perturbation coefficients in the fifth three-electrode detection mode includes: the fifteenth perturbation coefficient R5' and the sixteenth perturbation coefficient R16 on the propagation path between the third electrode plate and the first and sixth electrode plates, respectively.

5. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 3, characterized in that, In the sixth three-electrode detection mode, the fourth electrode plate located on the left side of the brain serves as the excitation transmitter, and the second electrode plate located at the back of the head and the fifth electrode plate located on the right side of the brain serve as the excitation receiver. Correspondingly, the eighth set of perturbation coefficients in the sixth three-electrode detection mode includes: the tenth perturbation coefficient R3' and the seventeenth perturbation coefficient R17 on the propagation path between the fourth electrode plate and the second and fifth electrode plates, respectively.

6. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 3, characterized in that, In the seventh three-electrode detection mode, the fifth electrode plate located on the right side of the brain serves as the excitation transmitter, and the first electrode plate located on the forehead and the fourth electrode plate located on the left side of the brain serve as the excitation receiver. Correspondingly, the ninth set of perturbation coefficients in the seventh three-electrode detection mode includes: the thirteenth perturbation coefficient R6' and the eighteenth perturbation coefficient R18 on the propagation path between the fifth electrode plate and the first and fourth electrode plates, respectively.

7. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 3, characterized in that, In the eighth three-electrode detection mode, the sixth electrode located on the right side of the brain serves as the excitation transmitter, and the second electrode located at the back of the head and the third electrode located on the left side of the brain serve as the excitation receivers. Correspondingly, the tenth perturbation coefficient set in the eighth three-electrode detection mode includes: the eleventh perturbation coefficient R4' and the nineteenth perturbation coefficient R19 on the propagation path between the sixth electrode and the second and third electrode, respectively.

8. The method for screening early cognitive impairment based on multi-mode electromagnetic field biodetection according to claim 2, characterized in that, If the subject's past medical history is stroke, the proportion of the sum of the third and fourth perturbation coefficient sets in the first and second three-electrode detection modes is greater than the proportion of the sum of the fifth and sixth perturbation coefficient sets in the third and fourth three-electrode detection modes. If the subject's past medical history is cerebral infarction, the proportion of the sum of the third and fifth perturbation coefficient sets in the first and third three-electrode detection modes is greater than the proportion of the sum of the fourth and sixth perturbation coefficient sets in the second and fourth three-electrode detection modes.

9. An early cognitive impairment screening system based on multi-mode electromagnetic field biodetection, characterized in that, include: The data acquisition device includes a data communication module and an electrode group for acquiring data from the user to be tested. The electrode group includes a first electrode and a second electrode corresponding to the frontal and occipital regions of the brain, respectively, a third electrode and a fourth electrode arranged side by side on the left side of the brain, and a fifth electrode and a sixth electrode arranged side by side on the right side of the brain. The screening device communicates with the data acquisition device to obtain the set of perturbation coefficients of the data acquisition device under a preset combination of benchmark detection modes, and inputs the set of perturbation coefficients into a pre-trained early cognitive impairment screening model to predict the predicted probability value of the user to be tested developing early cognitive impairment. Specifically, the screening device includes: The first data acquisition module is used to communicate with the data acquisition device to acquire, respectively, a health perturbation coefficient dataset of multiple healthy subjects under the benchmark detection mode combination; and to acquire, respectively, an abnormal perturbation coefficient dataset of multiple early cognitive impairment subjects under the benchmark detection mode combination; and to acquire the perturbation coefficient set of the user to be tested under the benchmark detection mode combination. The second data acquisition module is used to acquire the scale test results obtained by the multiple early cognitive impairment subjects through a specified scale method test; The screening model construction module is used to train a pre-built neural network model based on the health perturbation coefficient dataset, the abnormal perturbation coefficient dataset, and the scale detection results to obtain the early cognitive impairment screening model; The prediction module is used to predict the early cognitive impairment screening model constructed by the screening model construction module and the set of perturbation coefficients of the user to be tested under the benchmark detection mode combination obtained by the first data acquisition module, so as to obtain the predicted probability value of the user to be tested having early cognitive impairment. The set of perturbation coefficients under the reference detection mode combination includes: the first set of perturbation coefficients and the second set of perturbation coefficients under the preset first four-electrode detection mode and the second four-electrode detection mode, as well as the third to sixth sets of perturbation coefficients under the first to fourth three-electrode detection modes. In the first four-electrode detection mode, the first electrode located on the forehead serves as the excitation transmitter, the second electrode located at the back of the head, and the third and fifth electrode located on the left and right sides of the brain, respectively, serve as the excitation receivers. Correspondingly, the first set of perturbation coefficients includes: the seventh perturbation coefficient R7, the fifth perturbation coefficient R5, and the sixth perturbation coefficient R6 on the propagation path between the first electrode and the second, third, and fifth electrode, respectively. In the second four-electrode detection mode, the second electrode plate located at the back of the head serves as the excitation transmitter, and the first electrode plate located at the forehead and the fourth and sixth electrode plates located on the left and right sides of the brain, respectively, serve as the excitation receivers. Correspondingly, the second set of perturbation coefficients includes: the eighth perturbation coefficient R7', the third perturbation coefficient R3, and the fourth perturbation coefficient R4 on the propagation path between the second electrode plate and the first, fourth, and sixth electrode plates, respectively. In the first three-electrode detection mode, the third electrode plate located on the left side of the brain serves as the excitation transmitter, and the first electrode located on the forehead and the fifth electrode plate located on the right side of the brain serve as the excitation receiver. Accordingly, the third set of perturbation coefficients includes: the twelfth perturbation coefficient R5' and the first perturbation coefficient R1 on the propagation path between the third electrode plate and the first and fifth electrode plates, respectively. In the second and third electrode detection mode, the fourth electrode plate located on the left side of the brain serves as the excitation transmitter, and the second electrode plate located at the back of the head and the sixth electrode plate located on the right side of the brain serve as the excitation receiver. Accordingly, the fourth perturbation coefficient set includes: the tenth perturbation coefficient R3' and the second perturbation coefficient R2 on the propagation path between the fourth electrode plate and the second and sixth electrode plates, respectively. In the third three-electrode detection mode, the fifth electrode plate located on the right side of the brain serves as the excitation transmitter, and the first electrode plate located on the forehead and the third electrode plate located on the left side of the brain serve as the excitation receiver. Accordingly, the fifth perturbation coefficient set includes: the thirteenth perturbation coefficient R6' and the eighth perturbation coefficient R1' on the propagation path between the fifth electrode plate and the first and third electrode plates, respectively. In the fourth three-electrode detection mode, the sixth electrode plate located on the right side of the brain serves as the excitation transmitter, and the second electrode plate located at the back of the head and the fourth electrode plate located on the left side of the brain serve as the excitation receiver. Accordingly, the sixth perturbation coefficient set includes: the eleventh perturbation coefficient R4' and the ninth perturbation coefficient R2' on the propagation path between the sixth electrode plate and the second and fourth electrode plates, respectively.

10. The early cognitive impairment screening system based on multi-mode electromagnetic field biodetection according to claim 9, characterized in that, The screening device also includes: The third data acquisition module is used to acquire and identify the associated medical history of the multiple early cognitive impairment subjects; the associated medical history includes at least one of hypertension, stroke, cerebral infarction and genetic factors; The fourth data acquisition module is used to acquire the perturbation coefficient set of the subject under the baseline detection mode combination when the subject has two or more related past medical histories, and to acquire the perturbation coefficient set of the subject under the fifth to eighth three-electrode detection modes respectively when the subject has a single past medical history. Correspondingly, the screening model construction module is also used to train a first prediction model by inputting the perturbation coefficient set of the subject under the combination of the baseline detection modes, the health perturbation coefficient dataset, and the scale detection results into the model when the subject has two or more related past medical histories; and to train a second prediction model by inputting the perturbation coefficient set of the subject under the combination of the fifth to eighth three-electrode detection modes and the baseline detection mode, the health perturbation coefficient dataset, and the scale detection results into the model when the subject has a single past medical history.

Images