An immune status quantitative assessment system for patients with thymoma complicated with myasthenia gravis

Abstract

The present invention belongs to the technical field of immune status assessment for thymoma patients, and specifically relates to a quantitative assessment system for the immune status of thymoma patients complicated with myasthenia gravis. By comprehensively analyzing the quantitative scores and abnormal confidence levels of the patients' immune indicators, the invention can more accurately assess the immune status of the patients. Compared with traditional assessment methods, the present invention not only considers the quantitative scores, but also introduces the parameter of abnormal confidence level, thereby improving the accuracy and reliability of the assessment results. In addition, by dynamically adjusting the assessment threshold, the assessment system can be made more flexible to adapt to the individual differences of different patients, further improving the accuracy and practicality of the assessment. At the same time, the present invention also constructs an immune status database to track and analyze the immune status data of patients for a long time, providing doctors with more comprehensive information on the immune status of patients.

Description

Technical Field

[0001] The present invention belongs to the technical field of immune status assessment for thymoma patients, and particularly relates to a quantitative assessment system for the immune status of thymoma patients complicated with myasthenia gravis. Background Art

[0002] With the increasing incidence of myasthenia gravis caused by thymoma year by year, it has brought serious impacts on the quality of life of patients. Although it has been proven that surgical resection of the thymus is the key to treating thymoma and myasthenia gravis, even with the most novel and minimally invasive "three-hole" anterior mediastinal tumor resection under the xiphoid costal margin, it still causes great trauma to patients, changes the body's immunity, and is prone to induce myasthenic crisis and cause fatal danger after surgery. At present, there is a lack of accurate and stable quantitative indicators for the immune status of patients after thymectomy, and there is no reported research on the immune molecular mechanism of the treatment and improvement of thymectomy for patients complicated with myasthenia gravis. Therefore, it is particularly important to develop and study a system that can accurately quantitatively evaluate the immune status of thymoma patients complicated with myasthenia gravis after surgery.

[0003] At present, evaluation algorithms have been introduced for immune status assessment, and machine computing power is used to output evaluation results. However, there are many limitations in the current evaluation methods. For example, the evaluation results are generally reflected in the form of scores. However, since the immune status is related to various factors, even through the fusion of various data and then the output of the evaluation value, there are still great drawbacks. Especially for the evaluation value close to the threshold, although it meets the evaluation requirements, there is a large degree of uncertainty. Considering it as a normal value and not dealing with the patient will pose a certain risk. Based on this, the present invention proposes a computer-aided quantitative assessment system aimed at solving the above problems. Summary of the Invention

[0004] The purpose of the present invention is to provide a quantitative assessment system for the immune status of thymoma patients complicated with myasthenia gravis, which can accurately and comprehensively evaluate the immune status of patients, so as to provide more reliable diagnostic basis and treatment suggestions for doctors.

[0005] The technical solutions adopted by the present invention are specifically as follows:

[0006] A quantitative assessment system for the immune status of thymoma patients complicated with myasthenia gravis, comprising:

[0007] A multimodal data acquisition module for collecting immune index data of patients, wherein the immune index data includes the proportion of T cell subsets, the number of B cells, and the autoantibody titer;

[0008] A feature extraction module for extracting key features from the collected immune index data, synchronously adding feature codes, and outputting them as basal feature parameters;

[0009] An evaluation module for quantitatively scoring the immune status of a patient based on basal characteristic parameters and outputting an abnormal confidence level;

[0010] An intervention module for triggering a differential intervention strategy according to the quantitative score and the abnormal confidence level. The differential intervention strategy includes trend prediction of the normal state, outputting intervention data based on the prediction deviation degree, abnormal level classification of the abnormal state, risk verification based on the abnormal level, and dynamically adjusting the acquisition frequency of the multimodal data acquisition module.

[0011] In a preferred embodiment, the data acquisition module includes a preprocessing unit for preprocessing the immune index data, including:

[0012] Obtaining the immune index data and performing denoising processing to eliminate outliers and noise in the immune index data;

[0013] Performing normalization processing on the denoised immune index data to unify the magnitude of the immune index data;

[0014] Performing classification and summarization processing on the normalized immune index data and outputting it as multiple immune index data subsets.

[0015] In a preferred embodiment, the feature extraction module includes a feature extraction unit and a feature encoding unit. A required feature template is preset in the feature extraction unit. By comparing the required feature template with the preprocessed immune index data, key features that match the required feature template are extracted from the preprocessed immune index data. The feature encoding unit is used to encode the extracted key features, generate corresponding feature encodings, and output them as reference characteristic parameters;

[0016] Among them, the feature encoding is numerical data.

[0017] In a preferred embodiment, the evaluation module includes an evaluation unit and a confidence level calculation unit. The evaluation unit is used to receive the reference characteristic parameters, input them into a preset evaluation comparison table for matching analysis of the patient's immune status, and simultaneously output the quantitative scores of each of the reference characteristic parameters. The status determination unit determines the patient's immune status based on the quantitative scores and simultaneously outputs a corresponding evaluation report;

[0018] Among them, the immune status includes a normal state and an abnormal state. The evaluation report includes a normal evaluation report corresponding to the normal state and an abnormal evaluation report corresponding to the abnormal state;

[0019] The evaluation module further includes a confidence measurement unit, which is used to evaluate the confidence level of the abnormal degree of the patient's immune status based on the quantitative score and output the abnormal confidence level, where the abnormal confidence level is used to represent the credibility of the abnormal immune status of the patient.

[0020] In a preferred solution, the evaluation module further includes a status determination unit, which is used to collect all quantitative scores reflecting the patient's immune status within a preset sampling period;

[0021] Perform weighted fusion of the quantitative scores within the sampling period and the abnormal confidence level, and output a comprehensive score;

[0022] By comparing a preset dynamic evaluation threshold with the comprehensive score, output the immune status type of the patient;

[0023] Among them, when the comprehensive score is greater than the dynamic evaluation threshold, it indicates that the corresponding base feature parameter is normal, and the immune status of the corresponding patient is recorded as the normal status;

[0024] When the comprehensive score is less than or equal to the dynamic evaluation threshold, it indicates that the corresponding base feature parameter is abnormal, and the immune status of the corresponding patient is recorded as the abnormal status.

[0025] In a preferred solution, the intervention module includes a normal intervention unit, which is used to perform trend prediction in the normal state;

[0026] And, a summary unit and a statistical analysis unit, the summary unit is used to construct an immune status database, summarize the base feature parameters in the normal state into the immune status database, and add a timestamp identifier to each of the base feature parameters, and the statistical analysis unit is used to perform statistical analysis on the base feature parameters with the timestamp identifier added to determine the immune status parameter range in the normal state.

[0027] In a preferred solution, the normal intervention unit is used to record the base feature parameter with the timestamp identifier as the base condition parameter, input the base condition parameter into a preset trend calculation function, record the output result of the trend calculation function as the trend condition parameter, output a trend prediction curve based on the trend condition parameter, and then calculate the safe duration of the patient in the normal state according to the trend condition parameter. When the trend condition parameter deviates from the baseline, trigger an alarm, increase the acquisition frequency of the multi-modal data acquisition module, and synchronously update the safe duration.

[0028] In a preferred embodiment, the intervention module further includes an abnormal intervention unit, which includes a difference calculation subunit and an abnormal level determination subunit. The difference calculation subunit is configured to receive the basal characteristic parameters in the abnormal state, calculate the difference between the basal characteristic parameters in the abnormal state and the standard characteristic parameters, and output it as an abnormal difference. The abnormal level determination subunit determines the abnormal level of the patient's immune state according to the magnitude of the abnormal difference with reference to the preset abnormal level standard.

[0029] In a preferred embodiment, the abnormal intervention unit further includes a risk verification subunit, which is configured to compare and analyze the current immune state data with the historical immune state data, and output the similarity between the current abnormal state and the historical abnormal state;

[0030] If the similarity between the current abnormal state and the historical abnormal state exceeds the preset similarity threshold, it is determined as a known risk type, and the acquisition frequency of the multi-modal data acquisition module is adjusted to the acquisition frequency in the historical abnormal state;

[0031] If the similarity between the current abnormal state and the historical abnormal state does not exceed the preset similarity threshold, it is determined as an unknown risk type, and the high-risk acquisition mode is started, increasing the acquisition frequency of the multi-modal data acquisition module to the maximum.

[0032] And, an electronic device, the electronic device includes:

[0033] At least one processor;

[0034] And a memory communicatively connected to the at least one processor;

[0035] Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned immune state quantitative evaluation system for patients with thymoma complicated with myasthenia gravis.

[0036] The technical effects achieved by the present invention are:

[0037] By comprehensively analyzing the quantitative scores and abnormal confidence levels of patients' immune indicators, the present invention can more accurately evaluate the immune status of patients. Compared with traditional evaluation methods, the present invention not only considers the quantitative scores but also introduces the parameter of abnormal confidence level, thereby improving the accuracy and reliability of the evaluation results. In addition, by dynamically adjusting the evaluation threshold, the evaluation system can be made more flexible to adapt to the individual differences of different patients, further improving the accuracy and practicality of the evaluation. At the same time, the present invention also constructs an immune status database to track and analyze the immune status data of patients for a long time, providing doctors with more comprehensive information on the immune status of patients, which helps doctors formulate more accurate and personalized treatment plans. At the same time, the evaluation of the immune status under abnormal conditions and the determination of the abnormal level help to timely detect the immune abnormalities of patients, take corresponding intervention measures, and improve the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a schematic diagram of the system modules of the present invention;

[0039] Figure 2 is a schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0040] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be made with reference to the accompanying drawings of the specification.

[0041] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0042] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in a preferred embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selectively exclusive embodiment from other embodiments.

[0043] Please refer to Figure 1 as shown, the present invention provides a quantitative evaluation system for the immune status of patients with thymoma complicated with myasthenia gravis, including:

[0044] A multi-modal data acquisition module for collecting the immune indicator data of patients, wherein the immune indicator data includes the proportion of T cell subsets, the number of B cells, and the titer of autoantibodies;

[0045] A feature extraction module, which is used to extract key features from the collected immune index data, synchronously add feature codes, and output basal feature parameters;

[0046] An evaluation module, which is used to quantitatively score the immune status of the patient according to the basal feature parameters and output the abnormal confidence level;

[0047] An intervention module, which is used to trigger a differential intervention strategy according to the quantitative score and the abnormal confidence level. The differential intervention strategy includes trend prediction of the normal state, outputting intervention data based on the prediction deviation degree, and abnormal level classification of the abnormal state, and performing risk verification based on the abnormal level, and dynamically adjusting the collection frequency of the multimodal data collection module.

[0048] The present invention relates to an immune status quantitative evaluation system for patients with thymoma combined with myasthenia gravis. The system is composed of multiple modules, including a multimodal data collection module, a feature extraction module, an evaluation module, and an intervention module. The main function of the multimodal data collection module is to collect the immune index data of the patient. The immune index data covers key indicators such as the proportion of T cell subsets, the number of B cells, and the autoantibody titer. The feature extraction module is responsible for extracting key features from the collected immune index data, adding corresponding feature codes to the extracted key features, and finally outputting a set of basal feature parameters. The role of the evaluation module is to accurately evaluate the immune status of the patient according to the basal feature parameters, and then distinguish the immune status of the patient according to the evaluation results. In this embodiment, the immune status includes a normal state and an abnormal state. The purpose of the intervention module is to collect the corresponding basal feature parameters when the patient is in the normal state, and perform corresponding statistical analysis to establish a detailed immune status database under the normal state, and calculate the abnormal difference according to the basal feature parameters under the abnormal state, and then determine the abnormal level of the patient's immune status according to the abnormal difference, so as to provide a scientific basis for the clinical treatment of the patient.

[0049] In a preferred embodiment, the data collection module includes a preprocessing unit, and the preprocessing unit is used to perform data preprocessing on the immune index data, including:

[0050] Obtain the immune index data and perform denoising processing to eliminate outliers and noise in the immune index data;

[0051] Perform normalization processing on the denoised immune index data to unify the magnitude of the immune index data;

[0052] Perform classification and summary processing on the normalized immune index data and output it as multiple immune index data subsets.

[0053] In this embodiment, a preprocessing unit is provided in the data acquisition module. The preprocessing unit is responsible for preliminarily processing the immune index data. Its main workflow is as follows: First, obtain the immune index data. The obtained immune index data often contains various noises and outliers, which may all have an adverse impact on subsequent analysis. Therefore, it is necessary to denoise the immune index data to eliminate the outliers and noises in the data and ensure the accuracy and reliability of the data. After the denoising process is completed, it is necessary to normalize the cleaned immune index data. The purpose of normalization is to unify the magnitudes of different immune index data so that they can be compared and analyzed under the same standard, thereby improving the efficiency and accuracy of data processing. For the normalized immune index data, a classification and summarization process will be performed on the immune index data. Through classification and summarization, the data can be organized into multiple immune index data subsets, and each immune index data subset contains data of a specific category, facilitating targeted analysis and research.

[0054] In a preferred embodiment, the feature extraction module includes a feature extraction unit and a feature encoding unit. A required feature template is preset in the feature extraction unit. By comparing the required feature template with the preprocessed immune index data, key features that match the required feature template are extracted from the preprocessed immune index data. The feature encoding unit is used to encode the extracted key features to generate corresponding feature encodings and output them as reference feature parameters.

[0055] Among them, the feature encoding is numerical data.

[0056] In this embodiment, the feature extraction module mainly includes a feature extraction unit and a feature encoding unit. In the feature extraction unit, a series of required feature templates are preset in advance. The required feature templates are designed according to specific requirements to accurately identify and extract corresponding data features. When the preprocessed immune index data is input into the feature extraction unit, the system will perform corresponding comparative analysis on the immune index data and the required feature templates. Through this comparison, the system can identify and extract the key features that match the required feature templates to reflect the core information of the immune index data. The extracted key features will then be transmitted to the feature encoding unit. The role of the feature encoding unit is to encode the extracted key features. The encoding process involves converting the key features into a standardized numerical data format, that is, the feature encoding. The generation of the feature encoding is to facilitate subsequent data processing and analysis work, simplifying complex feature information into a set of quantifiable numerical values for the computer system to read and process, and finally serving as reference feature parameters for subsequent analysis. In addition, it should be noted that during the entire process of feature extraction and encoding, the generated feature encoding is numerical data, meaning that the encoded features can be represented by numbers, facilitating mathematical operations and statistical analysis.

[0057] In a preferred embodiment, the evaluation module includes an evaluation unit and a confidence calculation unit. The evaluation unit is configured to receive basal characteristic parameters and input them into a preset evaluation comparison table for matching analysis of the patient's immune status, and simultaneously output a quantitative score for each basal characteristic parameter.

[0058] The confidence calculation unit is used to evaluate the confidence level of the degree of abnormality of the patient's immune status based on the quantitative score and output an abnormal confidence level, where the abnormal confidence level is used to represent the credibility of the abnormality of the patient's immune status.

[0059] Specifically, the evaluation module consists of an evaluation unit and a confidence calculation unit. The main responsibility of the evaluation unit is to receive basal characteristic parameters from different sources, and then the basal characteristic parameters are input into a preset evaluation comparison table, which is constructed based on a large amount of clinical data and medical research and can perform precise matching analysis on the patient's immune status. Through this analysis, the evaluation unit can simultaneously output a quantitative score for each basal characteristic parameter. The quantitative score reflects the relative importance and influence degree of each parameter in evaluating the patient's immune status. The confidence calculation unit is responsible for performing a corresponding confidence evaluation on the degree of abnormality of the patient's immune status based on the quantitative score output by the evaluation unit. First, it will collect the difference between the quantitative score and the preset evaluation threshold and record it as the deviation amplitude of the quantitative score, and then input it into a preset confidence calculation function to calculate the corresponding abnormal confidence level:

[0060]

[0061] In the formula, C represents the abnormal confidence level, and ΔS represents the deviation amplitude of the quantitative score ( S t quantitative score, S y represents the preset evaluation threshold), S max represents the maximum allowable deviation (the value ranges from 0.25 to 0.3), CV represents the coefficient of variation ( In the formula, μ represents the arithmetic mean of the proportion of T cell subsets, the absolute count of B cells, and the antibody titer test value, and σ represents the variance), H current represents the correlation degree between the current quantitative score and the historical quantitative score CV crit represents the historical normal range, α represents the mutation correction factor (the penalty coefficient for antibody titer mutation). Based on this, a comprehensive abnormal confidence level can be obtained to represent the credibility of the abnormality of the patient's immune status, that is, the higher the abnormal confidence level, the greater the possibility that the patient's immune status is abnormal, and vice versa.

[0062] In a preferred embodiment, the evaluation module further includes a status determination unit. The status determination unit determines the immune status of the patient based on the quantitative scores and synchronously outputs a corresponding evaluation report.

[0063] Among them, the immune status includes a normal status and an abnormal status. The evaluation report includes a normal evaluation report corresponding to the normal status and an abnormal evaluation report corresponding to the abnormal status.

[0064] When the status determination unit executes, it collects all the quantitative scores reflecting the patient's immune status within a preset sampling period.

[0065] The quantitative scores within the sampling period are weighted and fused with the abnormal confidence level to output a comprehensive score.

[0066] By comparing a preset dynamic evaluation threshold with the comprehensive score, the immune status type of the patient is output.

[0067] Among them, when the comprehensive score is greater than the dynamic evaluation threshold, it indicates that the corresponding basal characteristic parameters are normal, and the immune status of the corresponding patient is recorded as the normal status.

[0068] When the comprehensive score is less than or equal to the dynamic evaluation threshold, it indicates that the corresponding basal characteristic parameters are abnormal, and the immune status of the corresponding patient is recorded as the abnormal status.

[0069] In this embodiment, in the evaluation module, there is also a key component, namely the status determination unit. Its role is to judge the patient's immune status based on a series of quantitative scores and abnormal confidence levels. In this embodiment, the immune status is divided into two major categories, the normal status and the abnormal status. Correspondingly, the evaluation report is also divided into two types. One is the normal evaluation report for the normal status, which records the indicators showing that the patient's immune system is functioning well. The other is the abnormal evaluation report for the abnormal status, which records the possible problems and abnormal indicators of the patient's immune system. When performing status determination, the status determination unit will collect all the quantitative scores that can reflect the patient's immune status within a preset sampling period. The collected quantitative score data will be weighted and fused with a preset abnormal confidence level. The weighted fusion formula is:

[0070]

[0071] In the formula, V represents the comprehensive score, ω1 and ω2 respectively represent the weight factors of the quantitative score and the abnormal confidence level, represents the mean value of the quantitative scores within the sampling period. In this way, the status determination unit can output a comprehensive score, thus more comprehensively reflecting the patient's immune status.

[0072] Here, it should be clear that ω1 and ω2 are dynamic factors, which are automatically adjusted according to the volatility of the patient's historical data. Among them, In the formula, k is the sensitivity coefficient (usually taken as 1 ≤ k ≤ 3 in clinical practice). Generally speaking, when the value of ΔS is close to 0, it indicates that the quantitative score is closer to the evaluation threshold. At this time, its instability is higher, that is, the immune status of the patient has a greater probability of being abnormal. At this time, the value of ω1 is close to 0, and the value of ω2 is close to 1. When outputting the comprehensive score, more attention is paid to the abnormal confidence level. In order to further determine the type of the patient's immune status, the status determination unit will use the preset dynamic evaluation threshold ( In the formula, T represents the dynamic evaluation threshold, T0 represents the initial threshold, λ represents the correction coefficient, usually taken as 0.1 to 0.3, E i represents the improvement rate of immune indexes after the i-th intervention, E target represents the target improvement rate) to compare with the comprehensive score. Through this comparison, it can be judged whether the patient's immune status is within the normal range or has deviated from the normal, so as to output the corresponding immune status type. Specifically, if the comprehensive score is greater than this dynamic evaluation threshold, it indicates that the basal characteristic parameters of the patient are within the normal range, and the immune status of the patient can be recorded as the normal status. Such a result is a positive signal for medical staff, meaning that the current immune system of the patient is operating healthily. On the contrary, if the comprehensive score is less than or equal to the dynamic evaluation threshold, it indicates that there are abnormalities in the basal characteristic parameters of the patient, and the immune status of the patient will be recorded as the abnormal status. In this case, medical staff need to further analyze the evaluation report, find out the specific reasons for the abnormal immune status, and take corresponding treatment measures.

[0073] In a preferred embodiment, the intervention module includes a normal intervention unit. The normal intervention unit is used to perform trend prediction under normal conditions. The normal intervention unit is used to record the basal characteristic parameters with time stamp identification as the basal condition parameters, and input the basal condition parameters into a preset trend calculation function, and record the output result of the trend calculation function as the trend condition parameters. Based on the trend condition parameters, a trend prediction curve is output, and then the safe duration of the patient in the normal state is calculated according to the trend condition parameters. When the trend condition parameters deviate from the baseline, an alarm is triggered, the acquisition frequency of the multi-modal data acquisition module is increased, and the safe duration is updated synchronously;

[0074] Specifically, when the normal intervention unit executes, it records the basal characteristic parameters that have been added with time stamp identification and defines them as the basal condition parameters. The basal condition parameters will then be input into a pre-set trend calculation function. Through the calculation and processing of the trend calculation function, an output result recorded as the trend condition parameters can be obtained. The trend condition parameters reflect the development trend of the patient's immune status based on the patient's current and historical health conditions. Among them, the expression of the trend calculation function is: Wherein, q represents the trend condition parameter, T represents the time length covered by the base condition parameter, m represents the number of base condition parameters, C j and C j-1 represent the base condition parameters at adjacent timestamps. Then, based on the trend condition parameter, the safe duration of the patient in the normal state can be further calculated. The involved calculation formula is: Wherein, C b represents the standard feature parameter, C d represents the base feature parameter, and t represents the safe duration. The safe duration refers to the time length that the patient can maintain the normal state under the current health condition. Through the time length of the safe duration, doctors and nursing staff can better formulate corresponding treatment and nursing plans to ensure that the patient receives appropriate intervention and attention within a safe time range, thereby effectively preventing and controlling the deterioration of the condition.

[0075] In addition, there are a summary unit and a statistical analysis unit that cooperate with the normal intervention unit. The summary unit is used to construct an immune status database, summarize the base feature parameters in the normal state into the immune status database, and add a timestamp identifier to each base feature parameter. The statistical analysis unit is used to perform statistical analysis on the base feature parameters with timestamp identifiers to determine the range of immune status parameters in the normal state;

[0076] Specifically, the main responsibility of the summary unit is to construct a comprehensive immune status database, which is responsible for collecting and summarizing the base feature parameters in the normal state into this immune status database to ensure the integrity and traceability of the immune index data. In addition, the summary unit will also add a timestamp identifier to each base feature parameter, so as to record the specific collection time of each base feature parameter for subsequent tracking and analysis. On the other hand, the statistical analysis unit undertakes the corresponding statistical analysis work on the base feature parameters with timestamp identifiers, so as to determine the range of immune status parameters in the normal state.

[0077] In a preferred embodiment, the intervention module further includes an abnormal intervention unit. The abnormal intervention unit includes a difference calculation subunit and an abnormal level determination subunit. The difference calculation subunit is used to receive the base feature parameters in the abnormal state, calculate the difference between the base feature parameters in the abnormal state and the standard feature parameters, and output it as an abnormal difference. The abnormal level determination subunit determines the abnormal level of the patient's immune status according to the size of the abnormal difference with reference to the preset abnormal level standard.

[0078] Specifically, the abnormal intervention unit is jointly composed of a difference calculation subunit and an abnormal level determination subunit. The main responsibility of the difference calculation subunit is to receive the base feature parameters in the abnormal state. The difference calculation subunit will calculate the difference between the base feature parameters and the standard feature parameters preset by the system, so as to obtain the difference between the two, and synchronously record it as the abnormal difference. The abnormal level determination subunit is responsible for determining the abnormal level of the patient's immune status according to the abnormal difference output by the difference calculation subunit. The abnormal level determination subunit will refer to a set of preset abnormal level criteria (the abnormal level criteria are formulated based on medical research and clinical experience, and can help the system accurately evaluate the severity of the abnormality), and then compare the abnormal difference with the abnormal level criteria, and divide the abnormal level into different levels, such as low, medium, high or more detailed divisions.

[0079] In addition, the abnormal intervention unit further includes a risk verification subunit, which is used to compare and analyze the current immune status data with the historical immune status data, and output the similarity between the current abnormal state and the historical abnormal state;

[0080] If the similarity between the current abnormal state and the historical abnormal state exceeds the preset similarity threshold, it is determined as a known risk type, and the acquisition frequency of the multimodal data acquisition module is adjusted to the acquisition frequency in the historical abnormal state;

[0081] If the similarity between the current abnormal state and the historical abnormal state does not exceed the preset similarity threshold, it is determined as an unknown risk type, and the high-risk acquisition mode is started, and the acquisition frequency of the multimodal data acquisition module is increased to the maximum;

[0082] Specifically, the abnormal intervention unit also includes a risk verification subunit. The main responsibility of the risk verification subunit is to evaluate and output the similarity level between the current immune status data and the historical immune status data by comparing and analyzing them (which can be specifically implemented through cosine similarity or other appropriate algorithms). When conducting this comparative analysis, if it is found that the similarity level between the current abnormal status and the historical abnormal status exceeds a pre-set similarity threshold (not less than 95%), then it is considered that the current abnormality belongs to a known risk type. At this time, the acquisition frequency of the multi-modal data acquisition module will be adjusted to the same acquisition frequency as when the historical abnormal status occurred to ensure that key data can be captured in a timely manner. On the contrary, if the similarity level between the current abnormal status and the historical abnormal status does not exceed the preset similarity threshold, then it is determined that the current abnormality belongs to an unknown risk type. In this case, a high-risk acquisition mode will be activated to cope with potential unknown threats. In the high-risk acquisition mode, the acquisition frequency of the multi-modal data acquisition module will be increased to the maximum value to ensure that as much data as possible can be collected for in-depth analysis and research to identify and understand this new risk type.

[0083] Please refer to Figure 2 , an electronic device, the electronic device includes:

[0084] At least one processor;

[0085] And a memory communicatively connected to the at least one processor;

[0086] Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to implement the above-mentioned immune status quantitative assessment system for patients with thymoma combined with myasthenia gravis.

[0087] The processor of the above-mentioned electronic device can be a central processing unit (CPU), a graphics processing unit (GPU) or an application specific integrated circuit (ASIC), and the memory can be a random access memory (RAM), a read-only memory (ROM) or other forms of non-volatile memory. The electronic device can also include an arithmetic unit, an input device and an output device. The arithmetic unit is used to execute instructions in the computer program, the input device is used to receive user operation instructions, and the output device is used to display the processing result or provide a user interaction interface.

[0088] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, device, article or method. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, device, article or method comprising that element.

[0089] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. Structures, devices and operation methods not specifically described and explained in the present invention are implemented according to conventional means in the art without special description and limitation.

Claims

1. A quantitative evaluation system for the immune status of patients with thymoma and myasthenia gravis, characterized by: include: A multimodal data collection module, used to collect immune index data of patients, wherein the immune index data includes T cell subset ratio, B cell number and autoantibody titer; The feature extraction module is used to extract key features from the collected immune index data, add feature codes simultaneously, and output them as base feature parameters; An evaluation module is used to quantitatively score the patient's immune status based on the baseline characteristic parameters and output abnormal confidence; The intervention module is used to trigger differentiated intervention strategies based on the quantitative score and abnormal confidence. The differentiated intervention strategies include trend prediction of normal state, output of intervention data based on prediction deviation, abnormal level classification of abnormal state, risk verification based on abnormal level, and dynamic adjustment of the collection frequency of the multimodal data collection module; The evaluation module includes an evaluation unit and a confidence calculation unit. The evaluation unit is used to receive the basal characteristic parameters, input them into a preset evaluation comparison table to perform matching analysis on the patient's immune status, and synchronously output the quantitative scores of each basal characteristic parameter. The confidence calculation unit is used to perform confidence evaluation on the abnormality of the patient's immune status according to the quantitative score, and output the abnormality confidence, wherein the abnormality confidence is used to indicate the credibility of the abnormality of the patient's immune status. The confidence calculation unit first collects the difference between the quantitative score and the preset evaluation threshold, and records it as the deviation amplitude of the quantitative score, and then inputs it into the preset confidence measurement function to calculate the corresponding abnormality confidence; The intervention module also includes an abnormal intervention unit, which includes a difference calculation subunit and an abnormal level determination subunit. The difference calculation subunit is used to receive the basal feature parameters under abnormal conditions, calculate the difference between the basal feature parameters under abnormal conditions and the standard feature parameters, and output the difference as an abnormal difference. The abnormal level determination subunit determines the abnormal level of the patient's immune status according to the size of the abnormal difference and with reference to a preset abnormal level standard. The abnormal intervention unit also includes a risk verification subunit, which is used to compare and analyze the current immune status data with the historical immune status data, and output the similarity between the current abnormal state and the historical abnormal state; If the similarity between the current abnormal state and the historical abnormal state exceeds the preset similarity threshold, it is determined to be a known risk type, and the collection frequency of the multimodal data collection module is adjusted to the collection frequency under the historical abnormal state; If the similarity between the current abnormal state and the historical abnormal state does not exceed the preset similarity threshold, it is determined to be an unknown risk type, and the high-risk collection mode is started, increasing the collection frequency of the multimodal data collection module to the maximum.

2. A quantitative evaluation system for the immune status of patients with thymoma and myasthenia gravis according to claim 1, characterized in that: The data acquisition module includes a preprocessing unit, which is used to preprocess the immune index data, including: Acquire the immune index data, and perform denoising processing to eliminate abnormal values ​​and noise in the immune index data; Normalizing the denoised immune index data to unify the magnitude of the immune index data; The normalized immune index data are classified and summarized, and output as multiple immune index data subsets.

3. The quantitative evaluation system for the immune status of patients with thymoma and myasthenia gravis according to claim 2, characterized in that: The feature extraction module includes a feature extraction unit and a feature encoding unit. The feature extraction unit is preset with a demand feature template. By comparing the demand feature template with the preprocessed immune index data, key features that are consistent with the demand feature template are extracted from the preprocessed immune index data. The feature encoding unit is used to encode the extracted key features, generate corresponding feature codes, and output them as reference feature parameters. Wherein, the feature code is numerical data.

4. The quantitative evaluation system for the immune status of patients with thymoma and myasthenia gravis according to claim 1, characterized in that: The evaluation module also includes a status determination unit, which determines the patient's immune status according to the quantitative score and synchronously outputs a corresponding evaluation report; Wherein, the immune status includes a normal status and an abnormal status, and the evaluation report includes a normal evaluation report corresponding to the normal status and an abnormal evaluation report corresponding to the abnormal status; When the state determination unit is executed, all quantitative scores reflecting the patient's immune status are collected within a preset sampling period; The quantitative score within the sampling period is weighted and integrated with the anomaly confidence level to output a comprehensive score. By comparing the preset dynamic assessment threshold with the comprehensive score, the patient's immune status type is output; Wherein, when the comprehensive score is greater than the dynamic assessment threshold, it indicates that the corresponding basal characteristic parameter is normal, and the immune status of the corresponding patient is recorded as normal; When the comprehensive score is less than or equal to the dynamic evaluation threshold, it indicates that the corresponding basal characteristic parameter is abnormal, and the immune status of the corresponding patient is recorded as an abnormal state.

5. The quantitative evaluation system for the immune status of patients with thymoma and myasthenia gravis according to claim 1, characterized in that: The intervention module includes a normal intervention unit, which is used to perform trend prediction in a normal state; And, a summary unit and a statistical analysis unit, the summary unit is used to construct an immune status database, and summarize the basal characteristic parameters under normal conditions into the immune status database, and add a timestamp identifier to each of the basal characteristic parameters, the statistical analysis unit is used to perform statistical analysis on the basal characteristic parameters after adding the timestamp identifier, and determine the range of the immune status parameters under normal conditions.

6. A quantitative evaluation system for the immune status of patients with thymoma and myasthenia gravis according to claim 5, characterized in that: The normal intervention unit is used to record the baseline characteristic parameters with timestamp identifiers as baseline condition parameters, input the baseline condition parameters into a preset trend measurement function, and record the output result of the trend measurement function as trend condition parameters, output a trend prediction curve based on the trend condition parameters, and then calculate the safe time for the patient to be in a normal state based on the trend condition parameters. When the trend condition parameters deviate from the baseline, an early warning is triggered, the acquisition frequency of the multimodal data acquisition module is increased, and the safety time is updated synchronously.

7. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the quantitative assessment system for the immune status of patients with thymoma and myasthenia gravis according to any one of claims 1 to 6.

Images