Neurology disease analysis method and system based on deep learning, and medium

Abstract

The invention provides a neurology disease analysis method and system based on deep learning and a medium. The method comprises the following steps: obtaining clinical examination data and image examination image information, processing to obtain a lesion magnitude evaluation index, obtaining self-described symptom information, extracting illness state high-correlation parameter data in combination with the clinical examination data, processing to obtain an illness state evaluation index, and processing to obtain an illness state development evaluation index in combination with the lesion magnitude evaluation index. Operation data of each detection device and medical ability evaluation data of doctors are obtained and processed to obtain detection accuracy influence factors, family medical history data, gene detection data and personal data are obtained and processed to obtain disease development correlation factors; according to the disease development evaluation index, the detection accuracy influence factor and the disease development correlation factor, processing is carried out to obtain a disease risk evaluation index, and the disease prediction level is determined through threshold comparison, so that the timeliness and accuracy of disease prediction are improved based on deep learning according to the examination data and multiple influence factors.

Description

Technical Field

[0001] The present application relates to the technical field of medical data analysis, and specifically, to a method, system and medium for analyzing neurological conditions based on deep learning. Background Art

[0002] With the development of artificial intelligence technology, deep learning is being used more and more widely in the medical field, providing new ideas and methods for neurological disease analysis. Neurological diseases are diverse and complex, and accurate disease analysis is crucial to developing effective treatment plans. Traditional disease analysis methods mainly rely on doctors' experience and clinical examinations, and have problems such as strong subjectivity and low efficiency. They are also unable to combine influencing factors other than test data for comprehensive evaluation and accurate prediction.

[0003] In view of the above problems, effective technical solutions are urgently needed. Summary of the invention

[0004] The purpose of the present application is to provide a neurological disease analysis method, system and medium based on deep learning. The method can obtain the patient's clinical examination data and imaging image information, obtain the disease level assessment index based on the imaging image information processing, extract the disease-related parameter data based on the patient's self-reported symptom information in combination with the clinical examination data to obtain the disease assessment index, and then obtain the disease progression assessment index in combination with the disease level assessment index processing, obtain the detection accuracy influencing factor based on the operation data of each detection equipment and the physician's medical ability assessment data processing, obtain the disease progression correlation factor based on the family medical history data, genetic detection data and personal data processing, and finally obtain the disease risk assessment index based on the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor processing, and determine the disease estimation level through threshold comparison, thereby realizing the improvement of the timeliness and accuracy of disease prediction based on deep learning based on the examination data combined with multiple influencing factors.

[0005] The present application also provides a method for analyzing neurological conditions based on deep learning, comprising the following steps:

[0006] Obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information;

[0007] Processing the lesion data to obtain a lesion magnitude assessment index;

[0008] Obtaining the patient's self-reported symptom information, and generating a patient's disease information feature portrait in combination with the clinical examination data, and extracting highly relevant disease parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the highly relevant disease parameter data;

[0009] Obtaining a disease progression assessment index according to the disease level assessment index and the disease condition assessment index;

[0010] Obtaining the operating data of each detection device and the medical ability assessment data of the physician, obtaining the operating status evaluation index of the detection device according to the operating data processing, obtaining the physician's ability evaluation index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor by processing the operating status evaluation index and the ability evaluation index;

[0011] Obtain the patient's family medical history data, genetic test data and personal data, and process the family medical history data, genetic test data and personal data to obtain factors associated with the development of the disease;

[0012] Obtain a disease risk assessment index by processing the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor;

[0013] The disease risk assessment index is compared with a preset disease onset risk assessment threshold, and the disease prediction level is determined according to the threshold range to which the disease risk assessment index belongs.

[0014] Optionally, in the neurological disease analysis method based on deep learning described in the present application, the step of obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information, includes:

[0015] Obtain clinical examination data of patients, including laboratory test data and physical examination data;

[0016] Obtain the patient's imaging examination image information, and extract lesion data based on the imaging examination image information.

[0017] Optionally, in the neurological disease analysis method based on deep learning described in the present application, the processing according to the lesion data to obtain the lesion magnitude assessment index includes:

[0018] The lesion data includes lesion characteristic data and lesion type data;

[0019] The lesion characteristic data and lesion type data are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index.

[0020] Optionally, in the neurology condition analysis method based on deep learning described in the present application, the patient's self-reported symptom information is obtained, and a characteristic portrait of the patient's condition information is generated in combination with the clinical examination data, and highly relevant parameter data of the condition is extracted according to the characteristic portrait of the patient's condition information, and the condition assessment index is obtained according to the highly relevant parameter data of the condition, including:

[0021] Obtain information on self-reported symptoms from patients;

[0022] Generate a patient's disease information feature portrait based on the patient's self-reported symptom information combined with the laboratory test data and physical sign test data;

[0023] Extracting highly relevant parameter data of the disease condition according to the characteristic portrait of the patient's disease information, including blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data;

[0024] The blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data are input into a preset disease assessment model for processing to obtain a disease assessment index.

[0025] Optionally, in the neurology condition analysis method based on deep learning described in the present application, the operation data of each detection device and the medical ability assessment data of the physician are obtained, the operation status evaluation index of the detection device is obtained according to the operation data processing, the ability evaluation index of the physician is obtained according to the medical ability assessment data processing, and the operation status evaluation index and the ability evaluation index are processed to obtain the detection accuracy influencing factor, including:

[0026] Obtain the operating data of each testing device, including testing accuracy data, sensor efficiency data and image processing efficiency data;

[0027] Obtain physicians' medical competence assessment data, including diagnostic accuracy data and cure rate data;

[0028] Obtaining an operation status evaluation index according to the detection accuracy data, sensor effectiveness data and image processing efficiency data;

[0029] Obtaining a capability assessment index based on the diagnostic accuracy data and cure rate data;

[0030] The detection accuracy influencing factor is obtained by processing the operating status evaluation index and the capability evaluation index.

[0031] Optionally, in the neurology condition analysis method based on deep learning described in the present application, the condition risk assessment index is compared with a preset disease onset risk assessment threshold, and the condition estimation level is determined according to the threshold range to which the condition risk assessment index belongs, including:

[0032] Comparing the disease risk assessment index with a preset disease risk assessment threshold;

[0033] If the disease risk assessment index is less than the first preset disease risk assessment threshold, the disease prediction level is level one;

[0034] If the disease risk assessment index is greater than or equal to the first preset disease risk assessment threshold and less than the second preset disease risk assessment threshold, the disease prediction level is level 2;

[0035] If the disease risk assessment index is greater than or equal to the second preset disease risk assessment threshold, the disease prediction level is level three.

[0036] In a second aspect, the present application provides a neurological disease analysis system based on deep learning, the system comprising: a memory and a processor, the memory comprising a program of a neurological disease analysis method based on deep learning, the program of the neurological disease analysis method based on deep learning being executed by the processor to implement the following steps:

[0037] Obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information;

[0038] Processing the lesion data to obtain a lesion magnitude assessment index;

[0039] Obtaining the patient's self-reported symptom information, and generating a patient's disease information feature portrait in combination with the clinical examination data, and extracting highly relevant disease parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the highly relevant disease parameter data;

[0040] Obtaining a disease progression assessment index according to the disease condition assessment index and the disease progression assessment index;

[0041] Obtaining the operating data of each detection device and the medical ability assessment data of the physician, obtaining the operating status evaluation index of the detection device according to the operating data processing, obtaining the physician's ability evaluation index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor by processing the operating status evaluation index and the ability evaluation index;

[0042] Obtain the patient's family medical history data, genetic test data and personal data, and process the family medical history data, genetic test data and personal data to obtain factors associated with the development of the disease;

[0043] Obtain a disease risk assessment index by processing the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor;

[0044] The disease risk assessment index is compared with a preset disease onset risk assessment threshold, and the disease prediction level is determined according to the threshold range to which the disease risk assessment index belongs.

[0045] Optionally, in a neurology disease analysis system based on deep learning described in the present application, the step of obtaining clinical examination data and imaging image information of a patient, and extracting lesion data based on the imaging image information, includes:

[0046] Obtain clinical examination data of patients, including laboratory test data and physical examination data;

[0047] Obtain the patient's imaging examination image information, and extract lesion data based on the imaging examination image information.

[0048] Optionally, in the neurology disease analysis system based on deep learning described in the present application, the processing according to the lesion data to obtain the lesion level assessment index includes:

[0049] The lesion data includes lesion characteristic data and lesion type data;

[0050] The lesion characteristic data and lesion type data are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index.

[0051] In a third aspect, the present application also provides a computer-readable storage medium, which stores a neurological disease analysis method program based on deep learning. When the neurological disease analysis method program based on deep learning is executed by a processor, the steps of the neurological disease analysis method based on deep learning as described in any one of the above items are implemented.

[0052] From the above, it can be seen that the present application provides a method, system and medium for analyzing neurological conditions based on deep learning, which obtains the patient's clinical examination data and imaging image information, obtains the disease level assessment index based on the imaging image information processing, extracts the disease-related parameter data based on the patient's self-reported symptom information in combination with the clinical examination data to obtain the disease assessment index, and then obtains the disease progression assessment index in combination with the disease level assessment index processing, obtains the detection accuracy influencing factor based on the operating data of each detection equipment and the physician's medical ability assessment data processing, obtains the disease progression correlation factor based on the family medical history data, genetic detection data and personal data processing, and finally obtains the disease risk assessment index based on the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor, and determines the disease estimation level through threshold comparison, thereby realizing the improvement of the timeliness and accuracy of disease prediction based on deep learning based on the examination data combined with multiple influencing factors.

[0053] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the embodiments of the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A flowchart of a neurological disease analysis method based on deep learning provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of obtaining a lesion magnitude assessment index for a neurological disease analysis method based on deep learning provided in an embodiment of the present application;

[0057] Figure 3 A flowchart of obtaining a disease assessment index for a neurological disease analysis method based on deep learning provided in an embodiment of the present application;

[0058] Figure 4 A flow chart of obtaining factors affecting detection accuracy in the neurological disease analysis method based on deep learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0060] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0061] Please refer to Figure 1 , Figure 1 This is a flowchart of a neurological disease analysis method based on deep learning in some embodiments of the present application. The neurological disease analysis method based on deep learning is used in a terminal device, such as a computer, a mobile phone terminal, etc. The neurological disease analysis method based on deep learning includes the following steps:

[0062] S11, obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information;

[0063] S12, processing the lesion data to obtain a lesion magnitude assessment index;

[0064] S13, obtaining the patient's self-reported symptom information, and generating a characteristic portrait of the patient's disease information in combination with the clinical examination data, and extracting highly relevant parameter data of the disease condition according to the characteristic portrait of the patient's disease condition information, and obtaining a disease condition assessment index according to the highly relevant parameter data of the disease condition;

[0065] S14, obtaining a disease progression assessment index according to the disease level assessment index and the disease condition assessment index;

[0066] S15, obtaining the operation data of each detection device and the medical ability assessment data of the physician, obtaining the operation status assessment index of the detection device according to the operation data processing, obtaining the physician's ability assessment index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor according to the operation status assessment index and the ability assessment index;

[0067] S16, obtaining the patient's family medical history data, genetic test data and personal data, and processing the family medical history data, genetic test data and personal data to obtain disease progression correlation factors;

[0068] S17, performing processing according to the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor to obtain a disease risk assessment index;

[0069] S18, comparing the disease risk assessment index with a preset disease onset risk assessment threshold, and determining the disease estimation level according to the threshold range to which the disease risk assessment index belongs.

[0070] It should be noted that in order to obtain the patient's estimated condition level, it is necessary to comprehensively consider clinical examination data, imaging image information and other influencing factors. Therefore, the patient's clinical examination data and imaging image information are first obtained, and the lesion data is extracted based on the imaging image information. The clinical examination data includes laboratory examination and verification data and physical sign examination data, among which the laboratory examination and verification data are the comprehensive evaluation data of various laboratory examination items, and the physical sign examination data are the human physical examination data. The lesion data includes lesion characteristic data and lesion type data. The lesion data is processed to obtain a lesion variable grade assessment index, among which the lesion variable grade assessment index is an assessment of the severity of the lesion. Different patients experience different symptoms, and the importance of the test data is also different. Therefore, the patient's self-reported symptom information is obtained, and the patient's disease information feature portrait is generated in combination with the obtained clinical examination data, and the disease highly relevant parameter data is extracted based on the patient's disease information feature portrait, and the disease highly relevant parameter data is processed to obtain the disease assessment index, which will be obtained. The obtained lesion level assessment index and condition assessment index are input into the preset condition progression assessment model for processing to obtain the condition progression assessment index; the test results of patients at different times and by different physicians will fluctuate to a certain extent, and the operation status assessment index of the test equipment and the physician's ability assessment index are obtained according to the obtained operation data of each test device and the physician's medical ability assessment data, and the test accuracy influencing factor is obtained according to the operation status assessment index and the ability assessment index; the patient's family medical history, genetic information and personal situation all have a correlation with the condition assessment, and therefore, the patient's family medical history data, genetic test data and personal data are processed to obtain the condition risk assessment index; finally, the obtained condition progression assessment index, the test accuracy influencing factor and the condition progression correlation factor are comprehensively analyzed and processed to obtain the condition risk assessment index; then the threshold is compared with the preset disease onset risk assessment threshold, and the condition estimation level is determined according to the threshold range to which the condition risk assessment index belongs, and the corresponding warning is output for the physician and the patient to view.

[0071] According to an embodiment of the present invention, obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information, includes:

[0072] Obtain clinical examination data of patients, including laboratory test data and physical examination data;

[0073] Obtain the patient's imaging examination image information, and extract lesion data based on the imaging examination image information.

[0074] It should be noted that clinical examination and imaging examination of patients are common examination methods in neurology. Laboratory test data and physical sign examination data in clinical examination data are the main basis for neurology to conduct disease analysis. In order to determine the specific situation of the lesion, it is necessary to extract lesion data based on imaging examination image information.

[0075] Please refer to Figure 2 , Figure 2 The flowchart of the method for analyzing neurological disease based on deep learning in some embodiments of the present application is to obtain recommended article information. According to the embodiment of the present invention, the processing according to the lesion data to obtain the lesion grade evaluation index includes:

[0076] S21, the lesion data includes lesion characteristic data and lesion type data;

[0077] S22, inputting the lesion characteristic data and lesion type data into a preset lesion level assessment model for processing to obtain a lesion level assessment index.

[0078] It should be noted that, in order to accurately judge the lesion condition, the lesion data including the lesion characteristic data and the lesion type data extracted are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index;

[0079] The calculation formula of the morbidity level assessment index in the morbidity level assessment model is:

[0080]

[0081] Among them, s e is the disease level assessment index, p c ,t o are lesion characteristic data and lesion type data respectively, and α, χ1, and χ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform).

[0082] Please refer to Figure 3 , Figure 3 This is a flowchart of obtaining a disease assessment index of a neurology disease analysis method based on deep learning in some embodiments of the present application. According to an embodiment of the present invention, the patient's self-reported symptom information is obtained, and a patient disease information feature portrait is generated in combination with the clinical examination data, and highly relevant disease parameter data is extracted based on the patient disease information feature portrait, and the disease assessment index is obtained based on the highly relevant disease parameter data, including:

[0083] S31. Obtaining patient-reported symptom information;

[0084] S32, generating a patient's disease information characteristic portrait based on the patient's self-reported symptom information combined with the laboratory test data and physical sign examination data;

[0085] S33, extracting highly relevant parameter data of the disease condition according to the characteristic portrait of the patient's disease information, including blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data;

[0086] S34, inputting the blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data into a preset disease assessment model for processing to obtain a disease assessment index.

[0087] It should be noted that there are many examination items, indicators or types for patients, and the correlation with the disease is different. Therefore, the patient's self-reported symptom information is first obtained, and the patient's disease information feature portrait is generated in combination with the laboratory test data and physical sign test data. Then, according to the generated patient disease information feature portrait, highly relevant parameter data of the disease are extracted, including blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data, among which the blood test data is a comprehensive assessment of various indicators of the blood test, and the cerebrospinal fluid test data is a comprehensive assessment of various indicators of the cerebrospinal fluid test. The extracted highly relevant parameter data of the disease are input into the preset disease assessment model for processing to obtain the disease assessment index;

[0088] The calculation formula of the condition assessment index in the condition assessment model is:

[0089]

[0090] Among them, d a is the disease assessment index, b o 、c f 、f e 、s p 、r e They are blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data, and φ1, φ2, φ3, δ1, δ2 and δ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform).

[0091] Please refer to Figure 4 , Figure 4 The present invention is a flowchart of obtaining the detection accuracy influencing factor of the neurology disease analysis method based on deep learning in some embodiments of the present application. According to the embodiment of the present invention, the operation data of each detection device and the medical ability assessment data of the physician are obtained, the operation status evaluation index of the detection device is obtained according to the operation data processing, the ability evaluation index of the physician is obtained according to the medical ability assessment data processing, and the operation status evaluation index and the ability evaluation index are processed to obtain the detection accuracy influencing factor, including:

[0092] S41, obtaining the operation data of each detection device, including detection accuracy data, sensor efficiency data and image processing efficiency data;

[0093] S42. Obtaining the physician's medical competence assessment data, including diagnostic accuracy data and cure rate data;

[0094] S43, obtaining an operation status evaluation index according to the detection accuracy data, sensor efficiency data and image processing efficiency data;

[0095] S44, obtaining a capability assessment index according to the diagnostic accuracy data and the cure rate data;

[0096] S45. Obtain a detection accuracy influencing factor based on the operation status evaluation index and the capability evaluation index.

[0097] It should be noted that the status of the instruments and the level of the doctors used in various examinations of patients are different, and there will be certain fluctuations and errors in the examination results. In order to make a more accurate assessment, the operating data of the testing equipment and the medical ability assessment data of the doctors are obtained respectively, and the operating data is processed to obtain the operating status assessment index, and the medical ability assessment data is processed to obtain the ability assessment index;

[0098] The calculation formula of the operating status evaluation index is:

[0099]

[0100] Among them, r s is the operating status evaluation index, d ay 、c ra They are the diagnostic accuracy data and the cure rate data, γ1 and γ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform);

[0101] The calculation formula of the capability evaluation index is:

[0102]

[0103] Among them, c p is the capability assessment index, c ta 、s en 、m a They are detection accuracy data, sensor efficiency data and image processing efficiency data, respectively; λ1, λ2, λ3, η1 and η2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform);

[0104] The calculation formula of the detection accuracy influencing factor is:

[0105]

[0106] Among them, f t is the factor affecting detection accuracy, r e 、c p are the operating status evaluation index and capability evaluation index, μ, It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the neurology disease analysis platform).

[0107] According to an embodiment of the present invention, the threshold comparison of the disease risk assessment index with a preset disease onset risk assessment threshold, and determining the disease prediction level according to the threshold range to which the disease risk assessment index belongs, includes:

[0108] Comparing the disease risk assessment index with a preset disease risk assessment threshold;

[0109] If the disease risk assessment index is less than the first preset disease risk assessment threshold, the disease prediction level is level one;

[0110] If the disease risk assessment index is greater than or equal to the first preset disease risk assessment threshold and less than the second preset disease risk assessment threshold, the disease prediction level is level 2;

[0111] If the disease risk assessment index is greater than or equal to the second preset disease risk assessment threshold, the disease prediction level is level three.

[0112] It should be noted that a threshold comparison is performed based on the obtained disease risk assessment index and the preset disease risk assessment threshold, wherein the preset disease risk assessment threshold includes a first preset disease risk assessment threshold and a second preset disease risk assessment threshold, and the second preset disease risk assessment threshold is greater than the first preset disease risk assessment threshold, the first preset disease risk assessment threshold is greater than 0, and the second preset disease risk assessment threshold is less than or equal to 1. In this embodiment, the first preset disease risk assessment threshold is set to 0.45, and the second preset disease risk assessment threshold is set to 0.7. For example, if the obtained disease risk assessment index is 0.3, the disease prediction level is level one; if the obtained disease risk assessment index is 0.5, the disease prediction level is level two; if the obtained disease risk assessment index is 0.85, the disease prediction level is level three, and a corresponding warning is output.

[0113] It is worth mentioning that, according to an embodiment of the present invention, the processing according to the lesion level assessment index and the condition assessment index to obtain the condition progression assessment index includes:

[0114] Inputting the lesion level assessment index and the disease condition assessment index into a preset disease condition progression assessment model for processing to obtain a disease condition progression assessment index;

[0115] The calculation formula of the disease progression assessment index in the disease progression assessment model is:

[0116]

[0117] Among them, p r is the disease progression assessment index, s e d a They are the pathological variable level assessment index and the condition assessment index, θ1 and θ2 are the preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology condition analysis platform).

[0118] It should be noted that, in order to obtain the disease progression, the obtained lesion level assessment index and disease progression assessment index are input into a preset disease progression assessment model for processing to obtain the disease progression assessment index.

[0119] It is worth mentioning that, according to an embodiment of the present invention, the step of obtaining the patient's family medical history data, genetic test data, and personal data, and processing the family medical history data, genetic test data, and personal data to obtain disease progression-associated factors includes:

[0120] Obtain the patient's family medical history data, including incidence data and disease grade data;

[0121] Obtain the patient's genetic testing data, including gene mutation data and gene polymorphism data;

[0122] Obtain the patient's personal data, including age data, dietary health data, exercise health data, smoking and drinking history data, and sleep monitoring data;

[0123] The incidence data, disease level data, gene mutation data, gene polymorphism data, age data, dietary health data, exercise health data, smoking and drinking history data, and sleep monitoring data are input into a preset disease progression association assessment model for processing to obtain disease progression association factors.

[0124] It should be noted that the possibility of the same examination data leading to the onset of the disease may not be the same due to different family medical history, genetic factors and basic personal conditions. Therefore, it is necessary to comprehensively consider various influencing factors, obtain the patient's family medical history data, genetic test data and personal data for processing, and obtain the factors associated with the development of the disease;

[0125] The calculation formula of the disease progression correlation factor is:

[0126]

[0127] Among them, a s is the disease progression-related factor, m r 、m b are the incidence data and the disease grade data, respectively. e , g n are gene mutation data and gene polymorphism data, respectively. g d i 、s o ,t a 、s l They are age data, dietary health data, exercise health data, smoking and drinking history data, and sleep monitoring data. ρ1, ρ2, and ρ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform).

[0128] It is worth mentioning that, according to an embodiment of the present invention, the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor are processed to obtain the disease risk assessment index, including:

[0129] The disease progression assessment index, the detection accuracy influencing factor and the disease progression associated factor are input into a preset disease risk assessment model for processing to obtain a disease risk assessment index.

[0130] It should be noted that in order to accurately obtain the disease risk assessment results, the obtained disease progression assessment index, detection accuracy influencing factors and disease progression correlation factors are input into the preset disease risk assessment model for processing to obtain the disease risk assessment index;

[0131] The calculation formula of the disease risk assessment index in the disease risk assessment model is:

[0132] r s =υ×(p r +f t +a s );

[0133] Among them, r s is the disease risk assessment index, p r 、f t 、a s They are respectively the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor, and υ is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the neurology disease analysis platform).

[0134] The present invention also discloses a neurological disease analysis system based on deep learning, comprising a memory and a processor, wherein the memory comprises a neurological disease analysis method program based on deep learning, and when the neurological disease analysis method program based on deep learning is executed by the processor, the following steps are implemented:

[0135] Obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information;

[0136] Processing the lesion data to obtain a lesion magnitude assessment index;

[0137] Obtaining the patient's self-reported symptom information, and generating a patient's disease information feature portrait in combination with the clinical examination data, and extracting highly relevant disease parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the highly relevant disease parameter data;

[0138] Obtaining a disease progression assessment index according to the disease level assessment index and the disease condition assessment index;

[0139] Obtaining the operating data of each detection device and the medical ability assessment data of the physician, obtaining the operating status evaluation index of the detection device according to the operating data processing, obtaining the physician's ability evaluation index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor by processing the operating status evaluation index and the ability evaluation index;

[0140] Obtain the patient's family medical history data, genetic test data and personal data, and process the family medical history data, genetic test data and personal data to obtain factors associated with the development of the disease;

[0141] Obtain a disease risk assessment index by processing the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor;

[0142] The disease risk assessment index is compared with a preset disease onset risk assessment threshold, and the disease prediction level is determined according to the threshold range to which the disease risk assessment index belongs.

[0143] It should be noted that in order to obtain the patient's estimated condition level, it is necessary to comprehensively consider clinical examination data, imaging image information and other influencing factors. Therefore, the patient's clinical examination data and imaging image information are first obtained, and the lesion data is extracted based on the imaging image information. The clinical examination data includes laboratory examination and verification data and physical sign examination data, among which the laboratory examination and verification data are the comprehensive evaluation data of various laboratory examination items, and the physical sign examination data are the human physical examination data. The lesion data includes lesion characteristic data and lesion type data. The lesion data is processed to obtain a lesion variable grade assessment index, among which the lesion variable grade assessment index is an assessment of the severity of the lesion. Different patients experience different symptoms, and the importance of the test data is also different. Therefore, the patient's self-reported symptom information is obtained, and the patient's disease information feature portrait is generated in combination with the obtained clinical examination data, and the disease highly relevant parameter data is extracted based on the patient's disease information feature portrait, and the disease highly relevant parameter data is processed to obtain the disease assessment index, which will be obtained. The obtained lesion level assessment index and condition assessment index are input into the preset condition progression assessment model for processing to obtain the condition progression assessment index; the test results of patients at different times and by different physicians will fluctuate to a certain extent, and the operation status assessment index of the test equipment and the physician's ability assessment index are obtained according to the obtained operation data of each test device and the physician's medical ability assessment data, and the test accuracy influencing factor is obtained according to the operation status assessment index and the ability assessment index; the patient's family medical history, genetic information and personal situation all have a correlation with the condition assessment, and therefore, the patient's family medical history data, genetic test data and personal data are processed to obtain the condition risk assessment index; finally, the obtained condition progression assessment index, the test accuracy influencing factor and the condition progression correlation factor are comprehensively analyzed and processed to obtain the condition risk assessment index; then the threshold is compared with the preset disease onset risk assessment threshold, and the condition estimation level is determined according to the threshold range to which the condition risk assessment index belongs, and the corresponding warning is output for the physician and the patient to view.

[0144] According to an embodiment of the present invention, obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information, includes:

[0145] Obtain clinical examination data of patients, including laboratory test data and physical examination data;

[0146] Obtain the patient's imaging examination image information, and extract lesion data based on the imaging examination image information.

[0147] It should be noted that clinical examination and imaging examination of patients are common examination methods in neurology. Laboratory test data and physical sign examination data in clinical examination data are the main basis for neurology to analyze the disease. In order to determine the specific situation of the lesion, it is necessary to extract the lesion data based on the imaging examination image information.

[0148] According to an embodiment of the present invention, the step of processing the lesion data to obtain a lesion level assessment index includes:

[0149] The lesion data includes lesion characteristic data and lesion type data;

[0150] The lesion characteristic data and lesion type data are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index.

[0151] It should be noted that, in order to accurately judge the lesion condition, the lesion data including the lesion characteristic data and the lesion type data extracted are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index;

[0152] The calculation formula of the morbidity level assessment index in the morbidity level assessment model is:

[0153]

[0154] Among them, s e is the disease level assessment index, p c ,t o are lesion characteristic data and lesion type data respectively, and α, χ1, and χ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform).

[0155] According to an embodiment of the present invention, the step of obtaining the patient's self-reported symptom information and generating a patient's disease information feature portrait in combination with the clinical examination data, extracting disease-related parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the disease-related parameter data, includes:

[0156] Obtain information on self-reported symptoms from patients;

[0157] Generate a patient's disease information feature portrait based on the patient's self-reported symptom information combined with the laboratory test data and physical sign test data;

[0158] Extracting highly relevant parameter data of the disease condition according to the characteristic portrait of the patient's disease information, including blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data;

[0159] The blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data are input into a preset disease assessment model for processing to obtain a disease assessment index.

[0160] It should be noted that there are many examination items, indicators or types for patients, and the correlation with the disease is different. Therefore, the patient's self-reported symptom information is first obtained, and the patient's disease information feature portrait is generated in combination with the laboratory test data and physical sign test data. Then, according to the generated patient disease information feature portrait, highly relevant parameter data of the disease are extracted, including blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data, among which the blood test data is a comprehensive assessment of various indicators of the blood test, and the cerebrospinal fluid test data is a comprehensive assessment of various indicators of the cerebrospinal fluid test. The extracted highly relevant parameter data of the disease are input into the preset disease assessment model for processing to obtain the disease assessment index;

[0161] The calculation formula of the condition assessment index in the condition assessment model is:

[0162]

[0163] Among them, d a is the disease assessment index, b o 、c f 、f e 、s p 、r e They are blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data, and φ1, φ2, φ3, δ1, δ2 and δ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform).

[0164] According to an embodiment of the present invention, the operation data of each detection device and the medical ability assessment data of the physician are obtained, the operation status assessment index of the detection device is obtained according to the operation data processing, the ability assessment index of the physician is obtained according to the medical ability assessment data processing, and the detection accuracy influencing factor is obtained according to the operation status assessment index and the ability assessment index. The processing includes:

[0165] Obtain the operating data of each testing device, including testing accuracy data, sensor efficiency data and image processing efficiency data;

[0166] Obtain physicians' medical competence assessment data, including diagnostic accuracy data and cure rate data;

[0167] Obtaining an operation status evaluation index according to the detection accuracy data, sensor effectiveness data and image processing efficiency data;

[0168] Obtaining a capability assessment index based on the diagnostic accuracy data and cure rate data;

[0169] The detection accuracy influencing factor is obtained by processing the operating status evaluation index and the capability evaluation index.

[0170] It should be noted that the status of the instruments and the level of the doctors used in various examinations of patients are different, and there will be certain fluctuations and errors in the examination results. In order to make a more accurate assessment, the operating data of the testing equipment and the medical ability assessment data of the doctors are obtained respectively, and the operating data is processed to obtain the operating status assessment index, and the medical ability assessment data is processed to obtain the ability assessment index;

[0171] The calculation formula of the operating status evaluation index is:

[0172]

[0173] Among them, r s is the operating status evaluation index, d ay 、c ra They are the diagnostic accuracy data and the cure rate data, γ1 and γ2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform);

[0174] The calculation formula of the capability evaluation index is:

[0175]

[0176] Among them, c p is the capability assessment index, c ta 、s en 、m a They are detection accuracy data, sensor efficiency data and image processing efficiency data, respectively; λ1, λ2, λ3, η1 and η2 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform);

[0177] The calculation formula of the detection accuracy influencing factor is:

[0178]

[0179] Among them, f t is the factor affecting detection accuracy, r e 、c p are the operating status evaluation index and capability evaluation index, μ, It is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the neurology disease analysis platform).

[0180] According to an embodiment of the present invention, the threshold comparison of the disease risk assessment index with a preset disease onset risk assessment threshold, and determining the disease prediction level according to the threshold range to which the disease risk assessment index belongs, includes:

[0181] Comparing the disease risk assessment index with a preset disease risk assessment threshold;

[0182] If the disease risk assessment index is less than the first preset disease risk assessment threshold, the disease prediction level is level one;

[0183] If the disease risk assessment index is greater than or equal to the first preset disease risk assessment threshold and less than the second preset disease risk assessment threshold, the disease prediction level is level 2;

[0184] If the disease risk assessment index is greater than or equal to the second preset disease risk assessment threshold, the disease prediction level is level three.

[0185] It should be noted that a threshold comparison is performed based on the obtained disease risk assessment index and the preset disease risk assessment threshold, wherein the preset disease risk assessment threshold includes a first preset disease risk assessment threshold and a second preset disease risk assessment threshold, and the second preset disease risk assessment threshold is greater than the first preset disease risk assessment threshold, the first preset disease risk assessment threshold is greater than 0, and the second preset disease risk assessment threshold is less than or equal to 1. In this embodiment, the first preset disease risk assessment threshold is set to 0.45, and the second preset disease risk assessment threshold is set to 0.7. For example, if the obtained disease risk assessment index is 0.3, the disease prediction level is level one; if the obtained disease risk assessment index is 0.5, the disease prediction level is level two; if the obtained disease risk assessment index is 0.85, the disease prediction level is level three, and a corresponding warning is output.

[0186] It is worth mentioning that, according to an embodiment of the present invention, the processing according to the lesion level assessment index and the condition assessment index to obtain the condition progression assessment index includes:

[0187] Inputting the lesion level assessment index and the disease condition assessment index into a preset disease condition progression assessment model for processing to obtain a disease condition progression assessment index;

[0188] The calculation formula of the disease progression assessment index in the disease progression assessment model is:

[0189]

[0190] Among them, p r is the disease progression assessment index, s e d aThey are the pathological variable level assessment index and the condition assessment index, θ1 and θ2 are the preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology condition analysis platform).

[0191] It should be noted that, in order to obtain the disease progression, the obtained lesion level assessment index and disease progression assessment index are input into a preset disease progression assessment model for processing to obtain the disease progression assessment index.

[0192] It is worth mentioning that, according to an embodiment of the present invention, the step of obtaining the patient's family medical history data, genetic test data, and personal data, and processing the family medical history data, genetic test data, and personal data to obtain disease progression-associated factors includes:

[0193] Obtain the patient's family medical history data, including incidence data and disease grade data;

[0194] Obtain the patient's genetic testing data, including gene mutation data and gene polymorphism data;

[0195] Obtain the patient's personal data, including age data, dietary health data, exercise health data, smoking and drinking history data, and sleep monitoring data;

[0196] The incidence data, disease level data, gene mutation data, gene polymorphism data, age data, dietary health data, exercise health data, smoking and drinking history data, and sleep monitoring data are input into a preset disease progression association assessment model for processing to obtain disease progression association factors.

[0197] It should be noted that the possibility of the same examination data leading to the onset of the disease may not be the same due to different family medical history, genetic factors and basic personal conditions. Therefore, it is necessary to comprehensively consider various influencing factors, obtain the patient's family medical history data, genetic test data and personal data for processing, and obtain the factors associated with the development of the disease;

[0198] The calculation formula of the disease progression correlation factor is:

[0199]

[0200] Among them, a s is the disease progression-related factor, m r 、m b are the incidence data and the disease grade data, respectively. e , g n are gene mutation data and gene polymorphism data, respectively. g d i 、s o ,t a 、s lThey are age data, dietary health data, exercise health data, smoking and drinking history data, and sleep monitoring data. ρ1, ρ2, and ρ3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the neurology disease analysis platform).

[0201] It is worth mentioning that, according to an embodiment of the present invention, the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor are processed to obtain the disease risk assessment index, including:

[0202] The disease progression assessment index, the detection accuracy influencing factor and the disease progression associated factor are input into a preset disease risk assessment model for processing to obtain a disease risk assessment index.

[0203] It should be noted that in order to accurately obtain the disease risk assessment results, the obtained disease progression assessment index, detection accuracy influencing factors and disease progression correlation factors are input into the preset disease risk assessment model for processing to obtain the disease risk assessment index;

[0204] The calculation formula of the disease risk assessment index in the disease risk assessment model is:

[0205] r s =υ×(p r +f t +a s );

[0206] Among them, r s is the disease risk assessment index, p r 、f t 、a s They are respectively the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor, and υ is the preset characteristic coefficient (the characteristic coefficient is obtained by querying the neurology disease analysis platform).

[0207] A third aspect of the present invention provides a readable storage medium, which stores a neurological disease analysis method program based on deep learning. When the neurological disease analysis method program based on deep learning is executed by a processor, the steps of the neurological disease analysis method based on deep learning as described in any one of the above items are implemented.

[0208] The present invention discloses a neurological disease analysis method, system and medium based on deep learning, which obtains the patient's clinical examination data and imaging image information, obtains the disease level assessment index according to the imaging image information processing, extracts the disease highly relevant parameter data based on the patient's self-reported symptom information in combination with the clinical examination data to obtain the disease assessment index, and then obtains the disease progression assessment index in combination with the disease level assessment index processing, obtains the detection accuracy influencing factor based on the operation data of each detection equipment and the medical ability assessment data of the physician, obtains the disease progression correlation factor based on the family medical history data, genetic detection data and personal data processing, and finally obtains the disease risk assessment index based on the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor, and determines the disease estimation level through threshold comparison, thereby realizing the improvement of the timeliness and accuracy of disease prediction based on deep learning according to the examination data combined with multiple influencing factors.

[0209] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0210] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0211] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0212] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0213] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A neurological disease analysis method based on deep learning, characterized in that: The following steps are involved: Obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information; Processing the lesion data to obtain a lesion magnitude assessment index; Obtaining the patient's self-reported symptom information, and generating a patient's disease information feature portrait in combination with the clinical examination data, and extracting highly relevant disease parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the highly relevant disease parameter data; Obtaining a disease progression assessment index according to the disease level assessment index and the disease condition assessment index; Obtaining the operating data of each detection device and the medical ability assessment data of the physician, obtaining the operating status evaluation index of the detection device according to the operating data processing, obtaining the physician's ability evaluation index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor by processing the operating status evaluation index and the ability evaluation index; Obtain the patient's family medical history data, genetic test data and personal data, and process the family medical history data, genetic test data and personal data to obtain factors associated with the development of the disease; Obtain a disease risk assessment index by processing the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor; The disease risk assessment index is compared with a preset disease onset risk assessment threshold, and the disease prediction level is determined according to the threshold range to which the disease risk assessment index belongs.

2. The method for analyzing neurological conditions based on deep learning according to claim 1, characterized in that: The step of obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information, includes: Obtain clinical examination data of patients, including laboratory test data and physical examination data; Obtain the patient's imaging examination image information, and extract lesion data based on the imaging examination image information.

3. The neurological disease analysis method based on deep learning according to claim 2, characterized in that: The step of processing the lesion data to obtain a lesion magnitude assessment index includes: The lesion data includes lesion characteristic data and lesion type data; The lesion characteristic data and lesion type data are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index.

4. The method for analyzing neurological conditions based on deep learning according to claim 3, characterized in that: The step of obtaining the patient's self-reported symptom information and generating a patient's disease information feature portrait in combination with the clinical examination data, extracting highly disease-related parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the highly disease-related parameter data, includes: Obtain information on self-reported symptoms from patients; Generate a patient's disease information feature portrait based on the patient's self-reported symptom information combined with the laboratory test data and physical sign test data; Extracting highly relevant parameter data of the disease condition according to the characteristic portrait of the patient's disease information, including blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data; The blood test data, cerebrospinal fluid test data, sensory assessment data, motor assessment data and reflex assessment data are input into a preset disease assessment model for processing to obtain a disease assessment index.

5. The method for analyzing neurological conditions based on deep learning according to claim 4, characterized in that: The method of obtaining the operation data of each detection device and the medical ability assessment data of the physician, obtaining the operation status assessment index of the detection device according to the operation data processing, obtaining the physician's ability assessment index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor by processing the operation status assessment index and the ability assessment index, includes: Obtain the operating data of each testing device, including testing accuracy data, sensor efficiency data and image processing efficiency data; Obtain physicians' medical competence assessment data, including diagnostic accuracy data and cure rate data; Obtaining an operation status evaluation index according to the detection accuracy data, sensor effectiveness data and image processing efficiency data; Obtaining a capability assessment index based on the diagnostic accuracy data and cure rate data; The detection accuracy influencing factor is obtained by processing the operating status evaluation index and the capability evaluation index.

6. The method for analyzing neurological conditions based on deep learning according to claim 5, characterized in that: The step of comparing the disease risk assessment index with a preset disease onset risk assessment threshold, and determining the disease prediction level according to the threshold range to which the disease risk assessment index belongs, includes: Comparing the disease risk assessment index with a preset disease risk assessment threshold; If the disease risk assessment index is less than the first preset disease risk assessment threshold, the disease prediction level is level one; If the disease risk assessment index is greater than or equal to the first preset disease risk assessment threshold and less than the second preset disease risk assessment threshold, the disease prediction level is level 2; If the disease risk assessment index is greater than or equal to the second preset disease risk assessment threshold, the disease prediction level is level three.

7. A neurology disease analysis system based on deep learning, characterized in that: The invention comprises a memory and a processor, wherein the memory comprises a program of a neurological disease analysis method based on deep learning, and when the program of the neurological disease analysis method based on deep learning is executed by the processor, the following steps are implemented: Obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information; Processing the lesion data to obtain a lesion magnitude assessment index; Obtaining the patient's self-reported symptom information, and generating a patient's disease information feature portrait in combination with the clinical examination data, and extracting highly relevant disease parameter data based on the patient's disease information feature portrait, and obtaining a disease assessment index based on the highly relevant disease parameter data; Obtaining a disease progression assessment index according to the disease condition assessment index and the disease level assessment index; Obtaining the operating data of each detection device and the medical ability assessment data of the physician, obtaining the operating status evaluation index of the detection device according to the operating data processing, obtaining the physician's ability evaluation index according to the medical ability assessment data processing, and obtaining the detection accuracy influencing factor by processing the operating status evaluation index and the ability evaluation index; Obtain the patient's family medical history data, genetic test data and personal data, and process the family medical history data, genetic test data and personal data to obtain factors associated with the development of the disease; Obtain a disease risk assessment index by processing the disease progression assessment index, the detection accuracy influencing factor and the disease progression correlation factor; The disease risk assessment index is compared with a preset disease onset risk assessment threshold, and the disease prediction level is determined according to the threshold range to which the disease risk assessment index belongs.

8. The deep learning-based neurological disease analysis system according to claim 7, characterized in that: The step of obtaining the patient's clinical examination data and imaging image information, and extracting lesion data based on the imaging image information, includes: Obtain clinical examination data of patients, including laboratory test data and physical examination data; Obtain the patient's imaging examination image information, and extract lesion data based on the imaging examination image information.

9. The neurological disease analysis system based on deep learning according to claim 7, characterized in that: The step of processing the lesion data to obtain a lesion magnitude assessment index includes: The lesion data includes lesion characteristic data and lesion type data; The lesion characteristic data and lesion type data are input into a preset lesion level assessment model for processing to obtain a lesion level assessment index.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a neurological condition analysis program based on deep learning. When the neurological condition analysis program based on deep learning is executed by the processor, the steps of the neurological condition analysis method based on deep learning as described in any one of claims 1 to 6 are implemented.

Images