Personalized intelligent real-time follow-up response system and method for radiotherapy and chemotherapy patients

Abstract

The invention relates to a personalized intelligent real-time follow-up response system and method for radiotherapy and chemotherapy patients, and relates to the field of intelligent follow-up visit. Detection data of a user side is received and compared with reference data for analysis to obtain a deviation vector, and the deviation vector is corrected by obtaining a first-level personalized correction parameter matrix in combination with disease duration and treatment records; the abnormal fluctuation period of the user sample group meeting the corrected matrix is further retrieved, if the period meets the condition, multi-dimensional information deep analysis is combined, a second-level personalized correction parameter matrix is obtained, the deviation vector is corrected again, finally, a risk coefficient is calculated according to the corrected deviation vector and the period, and the risk coefficient is matched with a follow-up response statement. The problems that follow-up visit neglects patient individual differences, medical resource distribution is uneven and follow-up visit precision is low are solved, personalization and intelligence of follow-up visit are achieved, follow-up visit precision and effectiveness are improved, and medical resource distribution is optimized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent follow-up, and in particular to a personalized intelligent real-time follow-up response system and method for radiotherapy and chemotherapy patients. Background Art

[0002] During chemoradiotherapy, a patient's physical condition and treatment outcomes change over time. Therefore, regular follow-up is crucial for monitoring the patient's condition, adjusting treatment plans, and improving treatment outcomes. However, existing follow-up protocols often employ a universal response strategy, ignoring individual patient differences and leading to a series of problems.

[0003] Existing follow-up plans lack individualized consideration. Patients vary in physical condition, disease severity, treatment response, and lifestyle, directly impacting the frequency and content of follow-up visits. However, existing follow-up plans often adopt a one-size-fits-all approach, applying the same follow-up period and response content to all patients, failing to meet their individual needs. Secondly, existing follow-up plans suffer from uneven allocation of medical resources. Due to a lack of consideration for individual patient differences, high-risk patients may miss optimal treatment opportunities due to extended follow-up intervals, leading to worsening of their condition. Meanwhile, low-risk patients may waste medical resources and incur unnecessary medical burdens due to overly frequent follow-up visits. This irrational resource allocation not only impacts patient treatment outcomes but also reduces the overall efficiency of the healthcare system. Furthermore, follow-up plans also lack sufficient data processing and analysis. Chemoradiotherapy and radiotherapy generate a large amount of test data, which contains crucial information about patient disease progression. However, existing follow-up plans often lack effective utilization and analysis of this data, failing to dynamically adjust follow-up strategies based on actual patient data. This results in insufficiently targeted and effective follow-up. Summary of the Invention

[0004] The present invention addresses the technical problem that follow-up responses in the prior art ignore individual differences among patients, resulting in uneven distribution of medical resources and insufficient follow-up accuracy and effectiveness. It provides a personalized intelligent real-time follow-up response system and method for chemotherapy patients to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a personalized intelligent real-time follow-up response system for radiotherapy and chemotherapy patients, comprising: a data receiving module for receiving radiotherapy and chemotherapy index detection data from a user end, performing deviation analysis with predefined radiotherapy and chemotherapy index benchmark data, and obtaining a detection item deviation vector; a first correction module for performing correlation analysis on a detection item set in combination with illness duration and treatment records, obtaining a first-level personalized correction parameter matrix, correcting the detection item deviation vector, and obtaining a first corrected detection item deviation vector matrix; a first retrieval module for retrieving a first abnormal fluctuation period of a detection item of a first user sample group that satisfies the first corrected detection item deviation vector matrix; a second correction module for retrieving a first abnormal fluctuation period of a detection item when the first abnormal fluctuation period of the detection item is greater than or equal to the detection item deviation vector matrix. When the project presets a follow-up period, a correlation analysis is performed on the detection item set in combination with the duration of illness, treatment records, medical history records, living behaviors and living environment to obtain a secondary personalized correction parameter matrix, and the detection item deviation vector is corrected to obtain a second corrected detection item deviation vector matrix; a second retrieval module is used to retrieve the second abnormal fluctuation period of the detection item of the second user sample group that meets the second corrected detection item deviation vector matrix; a response reply module is used to calculate the ratio of the first cycle threshold predefined by the medical end to the second abnormal fluctuation period of the detection item when the second abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, set it as the risk coefficient, and reply based on the response statement table matching the follow-up response statement in combination with the risk coefficient.

[0006] In a second aspect, the present invention provides a personalized intelligent real-time follow-up response method for radiotherapy and chemotherapy patients, the method comprising: receiving radiotherapy and chemotherapy index detection data from a user end, performing deviation analysis on the detection item deviation vector with predefined radiotherapy and chemotherapy index benchmark data, and obtaining a detection item deviation vector; combining the illness duration and treatment records, performing correlation analysis on the detection item set, obtaining a first-level personalized correction parameter matrix, correcting the detection item deviation vector, and obtaining a first corrected detection item deviation vector matrix; retrieving the first abnormal fluctuation period of the detection item of the first user sample group that meets the first corrected detection item deviation vector matrix; when the first abnormal fluctuation period of the detection item is greater than or equal to the preset follow-up period of the detection item During the period, a correlation analysis is performed on the detection item set in combination with the duration of illness, treatment records, medical history records, living behaviors and living environment to obtain a secondary personalized correction parameter matrix, and the detection item deviation vector is corrected to obtain a second corrected detection item deviation vector matrix; the second abnormal fluctuation period of the detection item of the second user sample group that meets the second corrected detection item deviation vector matrix is retrieved; when the second abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, the ratio of the first cycle threshold predefined by the medical end to the second abnormal fluctuation period of the detection item is calculated and set as the risk coefficient. In combination with the risk coefficient, the follow-up response statement is matched based on the response statement table to reply.

[0007] The beneficial effects of the present invention are as follows: a deviation vector is obtained by receiving radiotherapy and chemotherapy index detection data from the user end and performing deviation analysis with the benchmark data; a first-level personalized correction parameter matrix is obtained in combination with the illness duration and treatment records to correct the deviation vector; abnormal fluctuation cycles of user sample groups that meet the corrected deviation vector matrix are further retrieved; when the abnormal fluctuation cycle meets the conditions, a more in-depth correlation analysis is performed in combination with multi-dimensional information to obtain a second-level personalized correction parameter matrix, and the deviation vector is corrected again; finally, a risk coefficient is calculated based on the corrected deviation vector and the abnormal fluctuation cycle of the user sample group, and a follow-up response statement is matched for reply, thereby realizing personalized and intelligent follow-up of radiotherapy and chemotherapy patients, improving the accuracy and effectiveness of follow-up, and optimizing the allocation of medical resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a structural schematic diagram of a personalized intelligent real-time follow-up response system for radiotherapy and chemotherapy patients provided by the present invention.

[0009] Figure 2 A flow chart of a personalized intelligent real-time follow-up response method for patients undergoing radiotherapy and chemotherapy provided by the present invention.

[0010] Description of the accompanying drawings: data receiving module 11, first correction module 12, first retrieval module 13, second correction module 14, second retrieval module 15, response reply module 16. DETAILED DESCRIPTION

[0011] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0012] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0013] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0014] Example 1: like Figure 1 As shown, an embodiment of the present invention provides a personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy, comprising: The data receiving module 11 is used to receive radiotherapy and chemotherapy index detection data from the user end, perform deviation analysis with predefined radiotherapy and chemotherapy index benchmark data, and obtain a detection item deviation vector.

[0015] For example, in a personalized intelligent real-time follow-up response system for patients undergoing chemotherapy and radiotherapy, the system first receives chemotherapy and radiotherapy index test data from the user end. The user end refers to the device or platform used by the patient. Through this end, the patient transmits their chemotherapy and radiotherapy index test data, such as white blood cell count, hemoglobin level, tumor marker concentration, and other key physiological indicators, to the system, which uses this data to assess the patient's physical condition and treatment efficacy. Chemotherapy and radiotherapy index test data is an important basis for evaluating the patient's current physical condition and treatment efficacy.

[0016] The system then analyzes the actual test data for deviations against predefined baseline data for chemotherapy and radiotherapy indicators on the medical side. These baseline data are based on extensive clinical research and practical experience, establishing normal ranges or reference values for various chemotherapy and radiotherapy indicators, such as the normal range for white blood cell counts and tumor marker concentration thresholds. By comparing the actual test data with these baseline data, the system accurately calculates the degree of deviation for each test item, thereby forming a test item deviation vector.

[0017] The above steps provide a data foundation for subsequent personalized follow-up responses, enabling the system to develop more precise and effective follow-up strategies based on the patient's actual physical condition rather than generalized standards, thereby improving the relevance and effectiveness of follow-up. For example, if a patient's white blood cell count is significantly lower than the baseline range, the system will identify this deviation and give special attention in subsequent follow-up visits, allowing for timely adjustments to the follow-up plan.

[0018] The first correction module 12 is used to perform correlation analysis on the detection item set in combination with the illness duration and treatment records, obtain a first-level personalized correction parameter matrix, correct the detection item deviation vector, and obtain a first corrected detection item deviation vector matrix.

[0019] Optionally, the system further performs correlation analysis on the set of test items based on the patient's illness duration and treatment records. Illness duration refers to the time span since the patient's diagnosis and is an important time dimension for assessing disease progression and treatment effectiveness. Treatment records detail the patient's chemotherapy and radiotherapy regimens, dose adjustments, adverse reactions, and other information, and are key data for understanding the patient's treatment process and physical response. By comprehensively considering this information, the system uses statistical and machine learning algorithms to conduct in-depth correlation mining on the set of test items to reveal potential connections between different test items and between test items and illness duration and treatment records. During this process, the system may discover that certain test items show stronger correlations at specific illness durations or treatment stages, or that certain treatment measures have a significant impact on specific test items. Based on these findings, the system is able to generate a first-level personalized correction parameter matrix, each element of which reflects the correction coefficient for a specific test item given the illness duration and treatment records. The correction coefficient reflects the adjustment coefficient for a specific test item given the illness duration and treatment records.

[0020] The system then uses the correction parameter matrix to correct the obtained test item deviation vectors, thereby obtaining the first corrected test item deviation vector matrix. This allows the system to more accurately reflect the patient's current physical condition and treatment response, providing more personalized and accurate data support for subsequent follow-up responses. For example, if the system finds that a patient's tumor marker test value has abnormally fluctuated after receiving a specific radiotherapy or chemotherapy regimen, and this fluctuation is closely related to the patient's illness duration and treatment records, the system will use the first-level personalized correction parameter matrix to make appropriate adjustments to the deviation vector of this test item, thereby more accurately assessing changes in the patient's condition and providing a strong basis for formulating more personalized follow-up strategies.

[0021] The first retrieval module 13 is configured to retrieve a first abnormal fluctuation period of a detection item of a first user sample group that satisfies the first corrected detection item deviation vector matrix.

[0022] Specifically, after the system completes the first personalized correction of the detection item deviation vector and obtains the first corrected detection item deviation vector matrix, it will perform a key step, namely, retrieving the first user sample group that meets the characteristics of the correction vector matrix, and further analyzing the first abnormal fluctuation cycle of the detection items in these user sample groups.

[0023] Based on the deviations of various indicators in the first-corrected test item deviation vector matrix, the system screens user sample groups with similar deviation characteristics from the database. These user sample groups not only show consistency with the current patient in terms of test item deviations, but are also comparable in terms of illness duration and treatment stage. Subsequently, the test item data of these user sample groups is analyzed, with particular attention paid to test items that exhibit abnormal fluctuations. The cyclical pattern of these abnormal fluctuations is calculated, namely the first abnormal fluctuation cycle of the test item. This cycle reflects the average time interval between abnormal fluctuations in test items in patients with similar conditions and treatment backgrounds.

[0024] Through this step, the system can obtain clues about the trend of changes in the condition that the current patient may face. For example, if the system finds that a certain type of corrected test item deviation vector matrix mainly corresponds to a group of patients who receive a specific radiotherapy and chemotherapy regimen and are in a certain stage of treatment, and a key test indicator of these patients shows periodic abnormal fluctuations for a period of time after treatment, then the system can use this information as a reference to infer that the current patient may also experience similar changes in the condition. The above steps provide the system with predictive capabilities based on big data analysis, allowing the system to predict the trend of changes in the patient's condition in advance, thereby providing more timely and effective guidance and intervention during the follow-up process, further improving the accuracy and personalization of follow-up.

[0025] The second correction module 14 is used to perform correlation analysis on the detection item set in combination with the duration of illness, treatment records, medical history records, life behaviors and living environment when the first abnormal fluctuation period of the detection item is greater than or equal to the preset follow-up period of the detection item, obtain a secondary personalized correction parameter matrix, correct the detection item deviation vector, and obtain a second corrected detection item deviation vector matrix.

[0026] Furthermore, when the system determines that the first abnormal fluctuation period of a test item is greater than or equal to the pre-set test item follow-up period, it will trigger a further analysis process. The pre-set test item follow-up period refers to a pre-set time period standard for the test item. When the system determines that the first abnormal fluctuation period of a test item is greater than or equal to this pre-set time period, it will trigger a more in-depth analysis process. For example, the follow-up period of a certain type of test item may be pre-set to 30 days. If the first abnormal fluctuation period of the test item reaches or exceeds 30 days, the system will conduct subsequent multi-dimensional analysis according to the process.

[0027] Multidimensional analysis involves comprehensively considering multiple dimensions of information, including the duration of the patient's illness, detailed treatment records, comprehensive medical history, and the patient's lifestyle patterns and living environment, to perform correlation analysis on the collection of test items. The duration of illness reflects the time span of the patient's disease development and is an important indicator for assessing the stability and rate of disease progression. Treatment records detail the various treatments the patient has received and their effectiveness, providing a direct basis for understanding the current condition. Medical history records include the patient's past medical history, surgical history, etc., which help to reveal potential disease risk factors. Information on lifestyle and living environment, such as dietary habits, exercise levels, and living environment, may also have an indirect impact on the patient's condition. The system uses an algorithmic model to deeply explore the inherent connections between this information and the test items, thereby obtaining a secondary personalized correction parameter matrix. The secondary personalized correction parameter matrix further refines the correction rules for the deviation vectors of the test items, making the correction process more tailored to the individual characteristics of the patient.

[0028] Subsequently, the initially obtained test item deviation vector is corrected again using the secondary personalized correction parameter matrix to obtain the second corrected test item deviation vector matrix. Through the above steps, the system can further incorporate more dimensions of patient information on the basis of the first personalized correction, and achieve more accurate correction of the test item deviation vector. For example, if the first abnormal fluctuation period of a patient's test item is long, and the system analysis finds that there are certain factors in the patient's living environment that may affect the condition (such as long-term exposure to harmful substances), then the system will take these factors into consideration when generating the secondary personalized correction parameter matrix, thereby making more detailed adjustments to the test item deviation vector. Through this processing method, not only the accuracy of follow-up is improved, but also the system's adaptability to individual differences in patients is enhanced, providing strong support for the formulation of more personalized follow-up strategies.

[0029] The second retrieval module 15 is configured to retrieve a second abnormal fluctuation period of the detection item of a second user sample group that satisfies the second corrected detection item deviation vector matrix.

[0030] In detail, the system then performs data retrieval tasks based on the obtained second-corrected test item deviation vector matrix. Specifically, the system accurately locates and filters user sample groups with similar second-corrected test item deviation vector matrix characteristics to the current patient from the vast user database, namely the second user sample group. This screening process relies on highly accurate algorithm matching to ensure that the selected user sample group has a high degree of consistency with the current patient in terms of test item deviation.

[0031] The system then conducts an in-depth analysis of the historical data for these secondary user sample groups, focusing specifically on the timing of abnormal fluctuations. The system then calculates the periodic patterns of these fluctuations, known as the second abnormal fluctuation cycle for the test items. This information reflects the average time interval between abnormal fluctuations in test items for patients with similar disease characteristics and treatment backgrounds, providing valuable insights for predicting future trends in the patient's condition.

[0032] The second abnormal fluctuation cycle differs from the first in that the first is calculated based on the initial test item deviation vector matrix, which has not yet been deeply corrected by incorporating multidimensional information (such as illness duration, treatment records, medical history, lifestyle behaviors, and living environment). Therefore, it reflects the abnormal fluctuation characteristics of the patient's condition at a basic level. The second abnormal fluctuation cycle, on the other hand, is calculated based on the second-corrected test item deviation vector matrix. This matrix further incorporates multidimensional patient information based on the first correction. Therefore, the second abnormal fluctuation cycle better reflects the impact of individual patient characteristics on condition fluctuations, and the corrected data is more accurate.

[0033] Through the above steps, the system can provide current patients with more accurate and personalized disease predictions and follow-up recommendations based on big data analysis and pattern recognition, thereby optimizing follow-up strategies and improving treatment outcomes and patient quality of life.

[0034] The response reply module 16 is used to calculate the ratio of the first cycle threshold predefined by the medical end to the second abnormal fluctuation cycle of the detection item when the second abnormal fluctuation cycle of the detection item is less than the preset follow-up cycle of the detection item, set it as a risk coefficient, and combine the risk coefficient to match the follow-up response statement based on the response statement table to reply.

[0035] Specifically, when the system determines that the second abnormal fluctuation period of the test item is less than the preset follow-up period of the test item, it will extract the first cycle threshold predefined by the medical end. This threshold is set based on clinical experience and medical knowledge, and is used as a reference standard to measure the fluctuation speed of the patient's condition.

[0036] The system then calculates the ratio of the first cycle threshold to the second abnormal fluctuation cycle of the test item and sets this ratio as the risk coefficient. The risk coefficient is a quantitative indicator that intuitively reflects the degree of deviation of the patient's condition fluctuation rate compared to the normal range. The larger the value, the faster the patient's condition fluctuates and the higher the potential risk. For example, if the first cycle threshold is set to 30 days, and the second abnormal fluctuation cycle of a patient's test item is only 15 days, the calculated risk coefficient is 2, which means that the patient's condition is fluctuating rapidly and requires high attention.

[0037] Next, the calculated risk factor is intelligently matched against a pre-built response statement table. This table contains standardized follow-up response statements for different risk factor levels, designed to provide appropriate and professional follow-up advice and guidance based on the severity of the patient's condition and potential risks. Through precise matching, the system selects the response statement that corresponds to the current risk factor and generates a personalized follow-up response.

[0038] Through these steps, the system dynamically adjusts follow-up strategies based on real-time fluctuations in the patient's condition, providing timely and effective follow-up services. By quantifying risk factors and matching corresponding response statements, this not only improves the accuracy and personalization of follow-up, but also enhances communication efficiency between doctors and patients, helping to promptly identify and address potential health issues, thereby improving patients' treatment outcomes and quality of life.

[0039] In a preferred embodiment, the second correction module also includes: when the first abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, calculating the ratio of the first period threshold predefined by the medical end to the first abnormal fluctuation period of the detection item, setting it as the risk coefficient, and combining the risk coefficient to match the follow-up response statement based on the response statement table to reply.

[0040] Preferably, when the system recognizes that the first abnormal fluctuation period of the test item is less than the preset follow-up period of the test item, it means that once the abnormal fluctuation rate of the test item is faster, the abnormality occurs before the preset follow-up period. The system immediately responds accordingly and enters the process of patient condition risk assessment and providing matching response content, so as to deal with changes in the patient's condition in a timely manner, and thus directly starts the risk assessment and response matching mechanism.

[0041] Specifically, a predefined first-cycle threshold is obtained from the medical end. This threshold serves as a benchmark for evaluating the speed of fluctuation of the patient's condition and is usually set based on clinical experience and medical research. Subsequently, the ratio of the first-cycle threshold to the first abnormal fluctuation cycle of the test item is calculated. This ratio is defined as a risk coefficient, which is used to quantify the abnormal degree of the patient's condition fluctuation speed. The larger the risk coefficient, the more severe the patient's condition fluctuates and the higher the potential risk. For example, if the first-cycle threshold is 28 days, and the first abnormal fluctuation cycle of a patient's test item is 14 days, the risk coefficient is calculated to be 2, indicating that the patient's condition fluctuates rapidly and requires close attention.

[0042] Furthermore, based on the calculated risk factor, the system intelligently searches and matches the response statement table. This pre-built response statement table contains standardized follow-up response statements for different risk factor levels. It is designed to provide accurate and professional follow-up recommendations based on the severity of the patient's condition and potential risks. By mapping the risk factor with the response statement table, the system automatically selects and generates personalized follow-up responses, ensuring that patients receive timely medical guidance and advice tailored to their condition.

[0043] Through the above steps, not only the accuracy and efficiency of follow-up are improved, but also the personalization level of follow-up is enhanced, which helps doctors to promptly detect and deal with changes in patients' conditions, optimize the allocation of medical resources, and enhance patients' treatment experience and rehabilitation effects.

[0044] In a preferred embodiment, in combination with the risk factor, a follow-up response statement is matched based on the response statement table to respond, including: When the risk coefficient is greater than or equal to a first risk coefficient threshold, a reply is made based on the matching detection item medical consultation prompt information in the response statement table.

[0045] When the risk coefficient is less than a first risk coefficient threshold, a reply is made based on matching the detection item follow-up period prompt information and the detection item low-risk prompt information in the response statement table.

[0046] Among them, when the detection item follow-up period prompt information is generated, the detection item first abnormal fluctuation period or the detection item second abnormal fluctuation period is used to replace the detection item preset follow-up period, and the clock timing is started at the same time.

[0047] When the clock timing meets the preset time length and the detection item consultation reminder message still appears, the follow-up period is restored to the preset follow-up period of the detection item, and the normal reminder message of the detection item is generated for reply.

[0048] Specifically, the system evaluates the risk factor based on the first risk factor threshold predefined by the medical side (this threshold is set based on the doctor's experience, with a lower classification when the expectation is strict and a higher classification when the expectation is loose, and there is no specific limitation). When the risk factor is greater than or equal to the first risk factor threshold, it is determined that the patient's condition fluctuates significantly and abnormally, and there is a high risk. At this time, the system will match and generate a test item medical reminder based on the response statement table, and directly recommend that the patient seek medical treatment as soon as possible to ensure that the condition is under timely and effective control. When the risk factor is less than the first risk factor threshold, the system determines that the patient's condition fluctuates relatively steadily and the risk is low. At this time, the system will match and generate a test item follow-up period reminder information and a test item low-risk reminder information based on the response statement table.

[0049] After generating the detection item follow-up cycle prompt information, the first abnormal fluctuation cycle of the detection item or the second abnormal fluctuation cycle of the detection item is further used to replace the original detection item preset follow-up cycle, so as to dynamically adjust the follow-up frequency and ensure that closer attention is given during the stage when the patient's condition fluctuates relatively frequently. At the same time, the system will start the clock timing function to monitor the execution of the adjusted follow-up cycle. If the clock timing reaches the preset duration and the detection item consultation prompt information is not triggered again during this period, it is determined that the patient's condition is relatively stable and the risk has been reduced. At this time, the follow-up cycle will be restored to the original detection item preset follow-up cycle, and the detection item normal prompt information will be generated for reply, informing the patient that the current condition is stable and can be carried out according to the regular follow-up plan.

[0050] Through the above steps, the system can dynamically adjust the follow-up strategy according to the real-time fluctuations of the patient's condition, ensuring that timely medical advice can be given to patients when the condition fluctuates greatly, and restoring the regular follow-up frequency when the condition stabilizes, thereby improving the accuracy and efficiency of follow-up, while optimizing the allocation of medical resources and enhancing the patient's treatment experience and rehabilitation effect.

[0051] In a preferred embodiment, the predefined process of the chemoradiotherapy index benchmark data includes: The detection item attributes are configured, wherein the benchmark data attributes include tumor ontology data attributes, molecular marker data attributes, host factor data attributes, and treatment response data attributes.

[0052] The tumor ontology data attributes, the molecular marker data attributes, the host factor data attributes, and the treatment response data attributes are sent to the medical end, and feedback information from the medical end is received, wherein the medical end feedback information includes a reference interval for the tumor ontology data attributes, a reference interval for the molecular marker data attributes, a reference interval for the host factor data attributes, and a reference interval for the treatment response data attributes.

[0053] The tumor ontology data attribute reference interval, the molecular marker data attribute reference interval, the host factor data attribute reference interval, and the treatment response data attribute reference interval are added to the radiotherapy and chemotherapy indicator reference data.

[0054] In detail, in the process of constructing the benchmark data for radiotherapy and chemotherapy indicators, the first step to be performed is the configuration step of the detection item attributes. The core of this step is to clarify and define various key data attributes, which include but are not limited to tumor ontology data attributes, molecular marker data attributes, host factor data attributes, and treatment response data attributes. Tumor ontology data attributes usually cover basic information such as tumor type, stage, size and location, which are crucial for understanding the biological behavior of tumors; molecular marker data attributes focus on biological molecules closely related to tumor occurrence and development, such as the expression levels of specific genes or abnormal changes in proteins, which are important indicators for evaluating tumor characteristics and predicting treatment response; host factor data attributes involve the patient's age, gender, physical condition and genetic background, which have a significant impact on the patient's treatment tolerance and prognosis; treatment response data attributes record the patient's response to radiotherapy and chemotherapy, including efficacy evaluation, adverse reaction occurrence, etc., and are an important basis for adjusting treatment plans.

[0055] After completing the attribute configuration, the system sends these defined tumor ontology data attributes, molecular marker data attributes, host factor data attributes, and treatment response data attributes to the medical end to obtain feedback from professional medical personnel. Based on rich clinical experience and professional knowledge, the medical end sets corresponding benchmark intervals for each data attribute. For example, the benchmark interval of the tumor ontology data attribute may specify the standard size range of a specific type of tumor under a certain stage; the benchmark interval of the molecular marker data attribute clarifies the normal and abnormal thresholds of specific biological molecules in healthy people and cancer patients; the benchmark interval of the host factor data attribute takes into account the differences in tolerance to treatment among patients of different ages and genders; the benchmark interval of the treatment response data attribute is used to evaluate the treatment effect, such as the proportion of tumor reduction, the degree of symptom relief, etc.

[0056] After receiving this baseline interval information from the medical side, the system integrates it and adds it to the baseline data for radiotherapy and chemotherapy indicators. This process ensures the scientific and authoritative nature of the baseline data, providing solid data support for subsequent radiotherapy and chemotherapy effect evaluation and treatment plan adjustments.

[0057] By pre-defining baseline data for chemoradiotherapy indicators, the system can more accurately assess changes in a patient's condition, promptly identify abnormalities during treatment, and provide doctors with personalized treatment recommendations, thereby optimizing chemoradiotherapy plans, improving treatment outcomes, and enhancing patients' quality of life. For example, if a patient's molecular marker data exceeds a preset baseline range, the system will immediately issue an alert, prompting the doctor to pay attention to the patient's condition changes and consider adjusting the treatment plan.

[0058] In a preferred embodiment, a correlation analysis is performed on the test item set in combination with the duration of illness and treatment records to obtain a first-level personalized correction parameter matrix, including: A controllable sample set that meets the illness duration and the treatment record is retrieved, wherein the controllable sample set includes the first detection item record value set to the Nth detection item record value set.

[0059] The first detection item record value set is traversed until the Nth detection item record value set to perform box plot analysis to obtain the first detection item record value box interval until the Nth detection item record value box interval.

[0060] Traverse the first detection item record value box interval until the Nth detection item record value box interval, perform intersection extraction of the same attribute item interval with the radiotherapy and chemotherapy index benchmark data, and obtain the radiotherapy and chemotherapy index update benchmark data.

[0061] The baseline data is updated based on the radiotherapy and chemotherapy indicators to generate the first-level personalized correction parameter matrix.

[0062] Optionally, in the process of building a personalized chemoradiotherapy index evaluation system, a correlation analysis of the test item set is performed based on the patient's illness duration and treatment records, aiming to generate a first-level personalized correction parameter matrix. Specifically, the system first retrieves a controllable sample set that meets the characteristics of the current patient's illness duration and treatment records from the database. The controllable sample set covers comprehensive data from the first test item record value set to the Nth test item record value set. These data record the historical values of patients with similar conditions and treatment experiences on various test items, providing a rich reference basis for subsequent analysis.

[0063] Next, the system performs a box plot analysis on the first set of test item records, up to the Nth set. As a statistical chart, a box plot can intuitively display the distribution of data, including key information such as the median, quartiles, and outliers. Through box plot analysis, the system can obtain the box intervals for each test item record value. These intervals reflect the fluctuations of the data within the normal range, helping to identify outliers or data points that deviate from the normal range.

[0064] Next, the system traverses the bins of test item records and extracts the intersection of the intervals of items with the predefined baseline data for chemotherapy and radiotherapy indicators. This step aims to find the overlap between the bins of test item records in the controlled sample set and the baseline data for chemotherapy and radiotherapy indicators, that is, the common intervals between the two for the same attribute items. Through this intersection extraction, the system can generate updated baseline data for chemotherapy and radiotherapy indicators that is more closely aligned with the patient's actual situation, improving the relevance and accuracy of the baseline data.

[0065] Finally, based on the updated baseline data for chemoradiotherapy indicators, the system generates a first-level personalized correction parameter matrix. This matrix contains personalized correction parameters tailored to the patient's specific condition and treatment history. These parameters will be used to subsequently correct the deviation vector of the test items, achieving a more accurate and personalized evaluation of chemoradiotherapy effects. For example, if a patient has been ill for a long time and has received a specific type of chemoradiotherapy, the system will retrieve a controllable set of samples with similar characteristics and generate a first-level personalized correction parameter matrix for that patient through box plot analysis and interval intersection extraction.

[0066] Through the above steps, the system can dynamically adjust the evaluation standards of radiotherapy and chemotherapy indicators according to the individual differences of patients, improve the accuracy and effectiveness of the evaluation, and provide strong support for doctors to formulate more personalized treatment plans.

[0067] In a preferred embodiment, updating the baseline data based on the chemoradiotherapy index to generate the first-level personalized correction parameter matrix includes: A first attribute update reference interval is extracted from the radiotherapy and chemotherapy index update reference data.

[0068] A first attribute initial benchmark interval is extracted from the radiotherapy and chemotherapy indicator benchmark data.

[0069] When the first attribute detection data belongs to the first attribute update reference interval, the first attribute detection item deviation vector is equal to 0, and the first attribute first-level personalized correction parameter is equal to 1.

[0070] When the first attribute detection data does not fall within the first attribute update reference interval, the first attribute first level personalized correction parameter is determined by the following formula: , in, Characterizes the first attribute first level personalized correction parameter, Characterizes the first attribute detection item deviation correction vector, Characterize the first attribute detection item deviation vector, Characterizes small constants.

[0071] Furthermore, we focus on the updated baseline data for radiotherapy and chemotherapy indicators to generate a first-level personalized correction parameter matrix. First, we extract the first attribute update baseline interval from the updated baseline data. This interval reflects the reasonable fluctuation range of this attribute determined based on the latest data. At the same time, we extract the first attribute initial baseline interval from the radiotherapy and chemotherapy indicator benchmark data. This interval represents the initially set baseline range for this attribute.

[0072] When the first attribute detection data is within the first attribute update benchmark interval, it means that the detection data is within the normal update range. At this time, the first attribute detection item deviation vector is 0, indicating that there is no abnormal deviation. The first attribute first-level personalized correction parameter is set to 1, that is, no additional correction is required.

[0073] When the first attribute detection data exceeds the first attribute update benchmark interval, it indicates that the data is abnormal and the first-level personalized correction parameter needs to be determined. The specific formula is .in, Characterizes the first attribute level one personalized correction parameter, used for personalized adjustment of the test data; Characterizes the deviation correction vector of the first attribute detection item, reflecting the correction direction and degree of the detection item under abnormal circumstances; Characterize the deviation vector of the first attribute test item, reflecting the deviation of the test data from the benchmark interval; It represents a small constant, and its function is to avoid abnormal situations such as the denominator being 0, and to ensure the stability of the formula calculation.

[0074] Through the above steps, a personalized correction parameter matrix can be dynamically generated based on the patient's actual chemoradiotherapy indicators, achieving precise correction of test data, improving the accuracy of chemoradiotherapy effect assessment, and providing a reliable basis for subsequent treatment plan adjustments. For example, during a patient's chemoradiotherapy, if the first attribute test data exceeds the updated baseline range, the formula can be used to calculate the first-level personalized correction parameters to correct the test data, making the evaluation results more accurate and consistent with the patient's actual condition.

[0075] In a preferred embodiment, when the first attribute detection data does not fall within the first attribute update reference interval, the first attribute first level personalized correction parameter determination formula is as follows, including: When the first attribute detection data is less than the minimum value of the first attribute update reference interval, the first attribute detection item deviation correction vector is equal to the first attribute detection data minus the first attribute update reference interval minimum value, and the first attribute detection item deviation vector is equal to the first attribute detection data minus the first attribute initial reference interval minimum value.

[0076] When the first attribute detection data is greater than the minimum value of the first attribute update reference interval, the first attribute detection item deviation correction vector is equal to the first attribute detection data minus the maximum value of the first attribute update reference interval, and the first attribute detection item deviation vector is equal to the first attribute detection data minus the maximum value of the first attribute initial reference interval.

[0077] Exemplarily, in the process of determining the first-level personalized correction parameter of the first attribute, there is a specific calculation logic for the case where the first attribute detection data does not belong to the first attribute update benchmark interval. If the first attribute detection data is less than the minimum value of the first attribute update benchmark interval, at this time, the calculation method of the first attribute detection item deviation correction vector is to subtract the first attribute detection data from the minimum value of the first attribute update benchmark interval. The calculation result reflects the degree of deviation of the detection data compared with the lower limit of the update benchmark interval and provides a key value for subsequent corrections; at the same time, the calculation of the first attribute detection item deviation vector is to subtract the first attribute detection data from the minimum value of the first attribute initial benchmark interval. This result reflects the gap between the detection data and the lower limit of the initial benchmark interval. For example, assuming that the first attribute update benchmark interval is [10, 20] and the first attribute initial benchmark interval is [5, 25], when the first attribute detection data is 8, the first attribute detection item deviation correction vector is 8-10=-2, and the first attribute detection item deviation vector is 8-5=3.

[0078] When the first attribute test data is greater than the maximum value of the first attribute update benchmark interval, the calculation of the first attribute test item deviation correction vector becomes the first attribute test data minus the maximum value of the first attribute update benchmark interval, which is used to measure the extent to which the test data exceeds the upper limit of the update benchmark interval; the calculation of the first attribute test item deviation vector is the first attribute test data minus the maximum value of the first attribute initial benchmark interval, reflecting the difference between the test data and the upper limit of the initial benchmark interval. For example, in the above example, if the first attribute test data is 22, then the first attribute test item deviation correction vector is 22-20=2, and the first attribute test item deviation vector is 22-25=-3. Through this calculation method, the deviation of the test data from the boundaries of different benchmark intervals can be accurately quantified, providing an accurate data basis for the subsequent generation of first-level personalized correction parameters, thereby realizing personalized correction of radiotherapy and chemotherapy test data, improving the accuracy of the evaluation of the effect of radiotherapy and chemotherapy on patients, and helping to formulate a treatment plan that is more in line with the actual situation of the patient.

[0079] In a preferred embodiment, searching for the first abnormal fluctuation period of the detection item of the first user sample group that satisfies the first modified detection item deviation vector matrix includes: A set of abnormal fluctuation period detection values of the detection items of the first user sample group is counted.

[0080] Performing a central tendency analysis on the abnormal fluctuation period detection value set of the detection item to obtain the first abnormal fluctuation period of the detection item.

[0081] Specifically, in the process of retrieving the first abnormal fluctuation period of the detection item of the first user sample group that meets the first corrected detection item deviation vector matrix, we first focus on counting the detection item abnormal fluctuation period detection value set of the first user sample group. This step is intended to comprehensively collect the specific numerical values of the abnormal fluctuation period of the detection item of each user in the sample group to form a complete data set. For example, assuming that the first user sample group contains 100 users, for each user, the cycle value of the abnormal fluctuation of its detection item is recorded, such as the abnormal fluctuation period of user 1 is 5 days, and that of user 2 is 7 days, etc., and finally a detection item abnormal fluctuation period detection value set containing 100 numerical values is obtained.

[0082] Subsequently, a central tendency analysis is performed on the set of abnormal fluctuation period detection values of the test items. Central tendency analysis is an important method in statistics, which is used to explore the typical value or center position of a set of data. Through this analysis, the most representative value can be extracted from the numerous abnormal fluctuation period detection values, that is, the first abnormal fluctuation period of the test item. Common central tendency analysis indicators include mean, median, etc., and the specific selection depends on the distribution characteristics of the data. If the data distribution is relatively symmetrical, the mean can better reflect the overall situation; if there are extreme values, the median is more robust. For example, if the mean of the above 100 abnormal fluctuation period detection values is 6 days, and the data distribution is relatively symmetrical, then it can be considered that the first abnormal fluctuation period of the test item is 6 days.

[0083] Through this process, the first abnormal fluctuation cycle of the test item can be accurately determined, providing a key basis for the subsequent risk factor calculation and follow-up response statement matching based on this cycle.

[0084] Through the above steps, the system can objectively and accurately grasp the abnormal fluctuation patterns of the detection items based on the actual data of the user sample group, thereby achieving accurate assessment and timely intervention of the patient's condition fluctuations, and improving the accuracy and effectiveness of follow-up of patients undergoing radiotherapy and chemotherapy.

[0085] The embodiment of the present invention provides a personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy, which has at least the following technical effects: 1. By combining multi-dimensional information such as illness duration and treatment records, a two-level personalized correction is performed on the deviation vector of the test item, generating first- and second-level personalized correction parameter matrices. This multi-level correction mechanism can fully account for individual differences among patients, such as different stages of illness and treatment experience, so that the evaluation of radiotherapy and chemotherapy index test data is more in line with the patient's actual situation. For example, data deviations on the same test item for different patients may have different meanings due to individual factors. By adjusting the personalized correction parameter matrix, changes in the patient's condition can be judged more accurately, and dynamic and personalized evaluation of radiotherapy and chemotherapy effects can be achieved, providing strong support for doctors to formulate precise treatment plans.

[0086] 2. Based on the comparison between the abnormal fluctuation cycle of the test items and the preset follow-up cycle, as well as the calculated risk coefficient, different follow-up response statements are intelligently matched based on the response statement table. When the risk coefficient is high, timely medical treatment is prompted; when it is low, the follow-up cycle is adjusted and corresponding prompts are given. This intelligent risk warning and follow-up strategy adjustment mechanism can automatically adjust the follow-up frequency and content according to the real-time changes in the patient's condition, ensuring timely intervention when the condition is abnormal, and avoiding excessive follow-up when the condition is stable, thereby improving the utilization efficiency of medical resources and enhancing the patient's treatment experience and rehabilitation effect.

[0087] 3. In the pre-defined process of chemoradiotherapy indicator benchmark data, comprehensive consideration is given to multiple data attributes such as the tumor itself, molecular markers, host factors, and treatment response. The baseline intervals for each attribute are determined through interaction with the medical end, and the chemoradiotherapy indicator benchmark data are constructed. In addition, the benchmark data is updated through interval intersection extraction with a controllable sample set. This scientific baseline data construction and update method ensures the accuracy and authority of the benchmark data, and can be continuously optimized with the accumulation of clinical data and the development of medical knowledge. It provides a solid and reliable foundation for subsequent deviation analysis and personalized correction of detection items, and helps to improve the accuracy and effectiveness of the entire chemoradiotherapy patient follow-up response system.

[0088] Example 2: like Figure 2 As shown, based on the same inventive concept as the personalized intelligent real-time follow-up response system for radiotherapy and chemotherapy patients provided in Example 1, an embodiment of the present invention further provides a personalized intelligent real-time follow-up response method for radiotherapy and chemotherapy patients, the method comprising: From the user side, the radiotherapy and chemotherapy index detection data is received, and the deviation analysis is performed with the predefined radiotherapy and chemotherapy index benchmark data to obtain the detection item deviation vector.

[0089] Combined with the duration of illness and treatment records, a correlation analysis is performed on the detection item set to obtain a first-level personalized correction parameter matrix, and the detection item deviation vector is corrected to obtain a first corrected detection item deviation vector matrix.

[0090] A first abnormal fluctuation period of a detection item of a first user sample group that satisfies the first modified detection item deviation vector matrix is retrieved.

[0091] When the first abnormal fluctuation period of the detection item is greater than or equal to the preset follow-up period of the detection item, a correlation analysis is performed on the detection item set in combination with the duration of illness, treatment records, medical history records, living behaviors and living environment to obtain a secondary personalized correction parameter matrix, and the detection item deviation vector is corrected to obtain a second corrected detection item deviation vector matrix.

[0092] A second abnormal fluctuation period of the detection item of the second user sample group that satisfies the second modified detection item deviation vector matrix is retrieved.

[0093] When the second abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, the ratio of the first period threshold predefined by the medical end to the second abnormal fluctuation period of the detection item is calculated and set as the risk coefficient. Combined with the risk coefficient, the follow-up response statement is matched based on the response statement table to reply.

[0094] Furthermore, the method also includes: when the first abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, calculating the ratio of the first period threshold predefined by the medical end to the first abnormal fluctuation period of the detection item, setting it as the risk coefficient, and combining the risk coefficient to match the follow-up response statement based on the response statement table to reply.

[0095] Furthermore, in combination with the risk coefficient, a reply is made based on matching the follow-up response statement in the response statement table, including: when the risk coefficient is greater than or equal to the first risk coefficient threshold, a reply is made based on matching the detection item medical consultation prompt information in the response statement table; when the risk coefficient is less than the first risk coefficient threshold, a reply is made based on matching the detection item follow-up period prompt information and the detection item low-risk prompt information in the response statement table; wherein, after the detection item follow-up period prompt information is generated, the detection item first abnormal fluctuation period or the detection item second abnormal fluctuation period is used to replace the detection item preset follow-up period, and the clock timing is started at the same time; when the clock timing meets the preset time length and the detection item medical consultation prompt information still appears, the follow-up period is restored to the detection item preset follow-up period, and the detection item normal prompt information is generated for reply.

[0096] Furthermore, the predefined process of the chemoradiotherapy indicator benchmark data includes: configuring the detection item attributes, wherein the benchmark data attributes include tumor entity data attributes, molecular marker data attributes, host factor data attributes and treatment response data attributes; sending the tumor entity data attributes, the molecular marker data attributes, the host factor data attributes and the treatment response data attributes to the medical end, and receiving feedback information from the medical end, wherein the medical end feedback information includes the tumor entity data attribute benchmark interval, the molecular marker data attribute benchmark interval, the host factor data attribute benchmark interval and the treatment response data attribute benchmark interval; adding the tumor entity data attribute benchmark interval, the molecular marker data attribute benchmark interval, the host factor data attribute benchmark interval and the treatment response data attribute benchmark interval to the chemoradiotherapy indicator benchmark data.

[0097] Furthermore, in combination with the duration of illness and the treatment records, a correlation analysis is performed on the detection item set to obtain a first-level personalized correction parameter matrix, including: retrieving a controllable sample set that meets the duration of illness and the treatment records, wherein the controllable sample set includes a first detection item record value set up to an Nth detection item record value set; traversing the first detection item record value set up to the Nth detection item record value set to perform box plot analysis to obtain the first detection item record value box interval up to the Nth detection item record value box interval; traversing the first detection item record value box interval up to the Nth detection item record value box interval, performing intersection extraction of the same attribute item interval with the radiotherapy and chemotherapy indicator benchmark data, and obtaining the radiotherapy and chemotherapy indicator update benchmark data; generating the first-level personalized correction parameter matrix based on the radiotherapy and chemotherapy indicator update benchmark data.

[0098] Furthermore, based on the radiotherapy and chemotherapy indicator update benchmark data, the first-level personalized correction parameter matrix is generated, including: extracting the first attribute update benchmark interval from the radiotherapy and chemotherapy indicator update benchmark data; extracting the first attribute initial benchmark interval from the radiotherapy and chemotherapy indicator benchmark data; when the first attribute detection data belongs to the first attribute update benchmark interval, the first attribute detection item deviation vector is equal to 0, and the first attribute first-level personalized correction parameter is equal to 1; when the first attribute detection data does not belong to the first attribute update benchmark interval, the first attribute first-level personalized correction parameter is determined by the following formula: ,in, Characterizes the first attribute first level personalized correction parameter, Characterizes the first attribute detection item deviation correction vector, Characterize the first attribute detection item deviation vector, Characterizes small constants.

[0099] Furthermore, when the first attribute detection data does not belong to the first attribute update benchmark interval, the formula for determining the first attribute first-level personalized correction parameter is as follows, including: when the first attribute detection data is less than the minimum value of the first attribute update benchmark interval, the first attribute detection item deviation correction vector is equal to the first attribute detection data minus the minimum value of the first attribute update benchmark interval, and the first attribute detection item deviation vector is equal to the first attribute detection data minus the minimum value of the first attribute initial benchmark interval; when the first attribute detection data is greater than the minimum value of the first attribute update benchmark interval, the first attribute detection item deviation correction vector is equal to the first attribute detection data minus the maximum value of the first attribute update benchmark interval, and the first attribute detection item deviation vector is equal to the first attribute detection data minus the maximum value of the first attribute initial benchmark interval.

[0100] Furthermore, the first abnormal fluctuation period of the detection item of the first user sample group that satisfies the first corrected detection item deviation vector matrix is retrieved, including: counting the detection value set of the abnormal fluctuation period of the detection item of the first user sample group; performing central trend analysis on the detection value set of the abnormal fluctuation period of the detection item to obtain the first abnormal fluctuation period of the detection item.

[0101] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0103] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy, characterized by: include: The data receiving module is used to receive radiotherapy and chemotherapy index detection data from the user end, perform deviation analysis with predefined radiotherapy and chemotherapy index benchmark data, and obtain the detection item deviation vector; A first correction module is configured to perform a correlation analysis on the test item set based on the duration of illness and the treatment record to obtain a first-level personalized correction parameter matrix, and correct the test item deviation vector to obtain a first corrected test item deviation vector matrix; A first retrieval module is configured to retrieve a first abnormal fluctuation period of a detection item of a first user sample group that satisfies the first modified detection item deviation vector matrix; A second correction module is configured to, when the first abnormal fluctuation period of the test item is greater than or equal to the preset follow-up period of the test item, perform a correlation analysis on the test item set based on the duration of illness, treatment records, medical history records, living behavior and living environment to obtain a secondary personalized correction parameter matrix, and correct the test item deviation vector to obtain a second corrected test item deviation vector matrix; A second retrieval module is configured to retrieve a second abnormal fluctuation period of a detection item of a second user sample group that satisfies the second modified detection item deviation vector matrix; The response reply module is used to calculate the ratio of the first cycle threshold predefined by the medical end to the second abnormal fluctuation cycle of the detection item when the second abnormal fluctuation cycle of the detection item is less than the preset follow-up cycle of the detection item, set it as the risk coefficient, and match the follow-up response statement based on the response statement table to reply in combination with the risk coefficient.

2. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 1, characterized in that: The second correction module also includes: when the first abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, calculating the ratio of the first period threshold predefined by the medical end to the first abnormal fluctuation period of the detection item, setting it as the risk coefficient, and combining the risk coefficient to match the follow-up response statement based on the response statement table to reply.

3. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 1 or 2, characterized in that: Combined with the risk factor, the follow-up response statement is matched based on the response statement table and responded to, including: When the risk coefficient is greater than or equal to a first risk coefficient threshold, replying based on the matching test item consultation prompt information in the response statement table; When the risk coefficient is less than a first risk coefficient threshold, a reply is made based on matching the test item follow-up period prompt information and the test item low-risk prompt information in the response statement table; Wherein, when the detection item follow-up period prompt information is generated, the detection item first abnormal fluctuation period or the detection item second abnormal fluctuation period is used to replace the detection item preset follow-up period, and the clock timing is started at the same time; When the clock timing meets the preset time length and the detection item consultation reminder message still appears, the follow-up period is restored to the preset follow-up period of the detection item, and the normal reminder message of the detection item is generated for reply.

4. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 1, characterized in that: The predefined process for benchmarking chemoradiation indicators includes: Configuring detection item attributes, wherein the benchmark data attributes include tumor ontology data attributes, molecular marker data attributes, host factor data attributes, and treatment response data attributes; Sending the tumor ontology data attributes, the molecular marker data attributes, the host factor data attributes, and the treatment response data attributes to a medical end, and receiving feedback information from the medical end, wherein the medical end feedback information includes a reference interval for the tumor ontology data attributes, a reference interval for the molecular marker data attributes, a reference interval for the host factor data attributes, and a reference interval for the treatment response data attributes; The tumor ontology data attribute reference interval, the molecular marker data attribute reference interval, the host factor data attribute reference interval, and the treatment response data attribute reference interval are added to the radiotherapy and chemotherapy indicator reference data.

5. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 1, characterized in that: Combined with the duration of illness and treatment records, correlation analysis is performed on the test item set to obtain a first-level personalized correction parameter matrix, including: Retrieving a controllable sample set that meets the illness duration and the treatment record, wherein the controllable sample set includes a first detection item record value set to an Nth detection item record value set; Traversing the first detection item record value set until the Nth detection item record value set to perform box plot analysis, and obtaining the first detection item record value box interval until the Nth detection item record value box interval; Traversing the first detection item record value box interval until the Nth detection item record value box interval, performing intersection extraction of the same attribute item interval with the radiotherapy and chemotherapy index benchmark data, and obtaining the radiotherapy and chemotherapy index update benchmark data; The baseline data is updated based on the radiotherapy and chemotherapy indicators to generate the first-level personalized correction parameter matrix.

6. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 5, characterized in that: Updating the benchmark data based on the radiotherapy and chemotherapy indicators to generate the first-level personalized correction parameter matrix includes: Extracting a first attribute from the chemotherapy index update benchmark data to update the benchmark interval; Extracting a first attribute initial benchmark interval from the radiotherapy and chemotherapy indicator benchmark data; When the first attribute detection data belongs to the first attribute update reference interval, the first attribute detection item deviation vector is equal to 0, and the first attribute first level personalized correction parameter is equal to 1; When the first attribute detection data does not fall within the first attribute update reference interval, the first attribute first level personalized correction parameter is determined by the following formula: ， in, Characterizes the first attribute first level personalized correction parameter, Characterizes the first attribute detection item deviation correction vector, Characterize the first attribute detection item deviation vector, Characterizes small constants.

7. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 6, characterized in that: When the first attribute detection data does not fall within the first attribute update reference interval, the first attribute first level personalized correction parameter determination formula is as follows, including: When the first attribute detection data is less than the minimum value of the first attribute update reference interval, the first attribute detection item deviation correction vector is equal to the first attribute detection data minus the first attribute update reference interval minimum value, and the first attribute detection item deviation vector is equal to the first attribute detection data minus the first attribute initial reference interval minimum value; When the first attribute detection data is greater than the minimum value of the first attribute update reference interval, the first attribute detection item deviation correction vector is equal to the first attribute detection data minus the maximum value of the first attribute update reference interval, and the first attribute detection item deviation vector is equal to the first attribute detection data minus the maximum value of the first attribute initial reference interval.

8. The personalized intelligent real-time follow-up response system for patients undergoing radiotherapy and chemotherapy according to claim 1, characterized in that: Retrieving a first abnormal fluctuation period of a detection item of a first user sample group that satisfies the first modified detection item deviation vector matrix includes: Counting a set of abnormal fluctuation period detection values of the detection items of the first user sample group; Performing a central tendency analysis on the abnormal fluctuation period detection value set of the detection item to obtain the first abnormal fluctuation period of the detection item.

9. A personalized intelligent real-time follow-up response method for patients undergoing radiotherapy and chemotherapy, characterized in that: The method is applied to the personalized intelligent real-time follow-up response system for radiotherapy and chemotherapy patients according to any one of claims 1 to 8, and the method comprises: Receive radiotherapy and chemotherapy index detection data from the user end, perform deviation analysis with predefined radiotherapy and chemotherapy index benchmark data, and obtain the detection item deviation vector; Combined with the duration of illness and treatment records, correlation analysis is performed on the test item set to obtain a first-level personalized correction parameter matrix, and the test item deviation vector is corrected to obtain a first corrected test item deviation vector matrix; Retrieving a first abnormal fluctuation period of a detection item of a first user sample group that satisfies the first modified detection item deviation vector matrix; When the first abnormal fluctuation period of the test item is greater than or equal to the preset follow-up period of the test item, a correlation analysis is performed on the test item set in combination with the duration of illness, treatment records, medical history records, living behavior and living environment to obtain a secondary personalized correction parameter matrix, and the test item deviation vector is corrected to obtain a second corrected test item deviation vector matrix; Retrieving a second abnormal fluctuation period of a detection item of a second user sample group that satisfies the second modified detection item deviation vector matrix; When the second abnormal fluctuation period of the detection item is less than the preset follow-up period of the detection item, the ratio of the first period threshold predefined by the medical end to the second abnormal fluctuation period of the detection item is calculated and set as the risk coefficient. Combined with the risk coefficient, the follow-up response statement is matched based on the response statement table to reply.

Images