Non-small cell lung cancer clinical data analysis method and system based on MPNFS theory

Abstract

The invention belongs to the technical field of non-small cell lung cancer data analysis, and particularly relates to a non-small cell lung cancer clinical data analysis method and system based on an MPNFS theory. According to the invention, comprehensive patient state evaluation can be provided, the scientificity and accuracy of a nursing mode can be improved, an individualized nursing report can be generated, nursing intervention measures are ensured to be highly matched with the specific condition of the patient, the treatment experience and life quality of the patient can be improved, and the treatment experience and life quality of the patient can be improved by regularly acquiring the nursing state data and the curative effect change information of the patient. According to the method, the defects in treatment and nursing can be recognized in time, the nursing mode is adjusted, patient management is optimized, and the treatment compliance of a patient is enhanced, the disease control effect and prognosis are improved, and the satisfaction degree of the patient is improved through real-time monitoring and dynamic optimization of the nursing mode.

Description

Technical Field

[0001] The present invention belongs to the technical field of non-small cell lung cancer data analysis, and in particular relates to a non-small cell lung cancer clinical data analysis method and system based on MPNFS theory. Background Art

[0002] Non-small cell lung cancer (NSCLC) is the most common type of lung cancer worldwide, accounting for about 85% of all lung cancer cases. Due to its high morbidity and mortality, NSCLC has always been the focus of medical research and clinical treatment. With the continuous advancement of medical technology, the diagnosis and treatment of NSCLC are also constantly developing and improving.

[0003] MPNFS theory is a comprehensive nursing model based on medication (M), psychological intervention (P), nursing (Nursing), family care (F) and social support (S). The theory emphasizes that in addition to medication, attention should also be paid to the patient's mental state, family and social support in the process of patient treatment to comprehensively improve the patient's treatment effect and quality of life.

[0004] Existing clinical treatment and nursing management methods are mostly based on traditional medical data of patients, such as imaging examination results, tumor staging, and pathological type. Although these data can help doctors make treatment decisions to a certain extent, they often ignore the multi-dimensional nursing needs and individual differences of patients, resulting in inaccurate treatment plans and nursing interventions. Especially during the treatment process, there is a lack of dynamic tracking and real-time adjustment of nursing models, making it difficult to identify changes in patients' conditions in a timely manner and conduct targeted interventions. Summary of the invention

[0005] The purpose of the present invention is to provide a clinical data analysis method for non-small cell lung cancer based on MPNFS theory, which can quantitatively evaluate the patient's condition, monitor the nursing effect in real time, and dynamically optimize the nursing model, so as to provide personalized and accurate nursing plans and effectively improve the patient's treatment effect and quality of life.

[0006] The technical solution adopted by the present invention is as follows:

[0007] A clinical data analysis method for non-small cell lung cancer based on MPNFS theory, comprising:

[0008] Obtain clinical data of patients with non-small cell lung cancer and obtain corresponding treatment plans based on the clinical data;

[0009] Obtain corresponding initial condition information according to clinical data, and obtain corresponding initial condition level according to the initial condition information;

[0010] Obtain multimodal nursing data according to the treatment plan, obtain information on changes in efficacy of patients with non-small cell lung cancer according to the multimodal nursing data, and obtain information on adverse reactions of patients with non-small cell lung cancer according to the multimodal nursing data;

[0011] Construct a detection cycle, obtain nursing status data within the detection cycle, and obtain corresponding nursing status change information based on the nursing status data;

[0012] Obtain a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

[0013] In a preferred embodiment, the steps of obtaining corresponding initial condition information according to clinical data and obtaining corresponding initial condition level according to the initial condition information include:

[0014] Obtain corresponding initial condition information based on clinical data;

[0015] Obtaining a corresponding initial condition vector according to the initial condition information;

[0016] Obtain a disease table, wherein the disease table includes a plurality of disease interval vectors and a disease level corresponding to each disease interval vector;

[0017] Obtaining a corresponding target disease interval vector according to the initial disease vector;

[0018] Obtain the disease level from the disease table according to the target disease interval vector.

[0019] In a preferred embodiment, the steps of obtaining multimodal nursing data according to the treatment plan, obtaining efficacy change information of patients with non-small cell lung cancer according to the multimodal nursing data, and obtaining adverse reactions of patients with non-small cell lung cancer according to the multimodal nursing data include:

[0020] Capture multimodal care data based on treatment plans;

[0021] Obtain treatment effect information for corresponding non-small cell lung cancer patients based on multimodal nursing data;

[0022] Acquire corresponding multiple efficacy status values ​​according to the treatment effect information;

[0023] Obtaining a therapeutic effect change value according to multiple therapeutic effect status values, and marking it as therapeutic effect change information;

[0024] Obtaining adverse event information for patients with non-small cell lung cancer based on multimodal nursing data.

[0025] In a preferred embodiment, the step of acquiring multimodal nursing data according to the treatment plan includes:

[0026] Obtain corresponding multiple treatment vectors according to the treatment plan;

[0027] Obtain multiple nursing tables, wherein each nursing table includes multiple treatment interval vectors and a nursing method corresponding to each treatment interval vector;

[0028] According to each treatment vector, a corresponding target treatment interval vector is obtained from the corresponding nursing table;

[0029] Obtain the nursing method from the corresponding nursing table according to the target treatment interval vector;

[0030] The nursing methods corresponding to multiple treatment vectors are summarized, and the summary results are marked as multimodal nursing data.

[0031] In a preferred embodiment, the step of obtaining adverse reaction information of patients with non-small cell lung cancer based on multimodal nursing data includes:

[0032] Obtain the adverse reaction vector corresponding to each nursing mode of patients with non-small cell lung cancer based on multimodal nursing data;

[0033] Obtaining adverse reaction values ​​according to a plurality of adverse reaction vectors;

[0034] Obtaining an adverse reaction table, wherein the adverse reaction table includes multiple adverse reaction intervals and an adverse reaction status value corresponding to each adverse reaction interval;

[0035] Obtain target adverse reaction interval according to adverse reaction value;

[0036] According to the target adverse reaction interval, the corresponding adverse reaction status value is obtained from the adverse reaction table and marked as adverse reaction information.

[0037] In a preferred solution, the steps of constructing a detection cycle, obtaining nursing status data within the detection cycle, and obtaining corresponding nursing status change information according to the nursing status data include:

[0038] Building a testing cycle;

[0039] Obtain nursing status data of non-small cell lung cancer patients based on multimodal nursing data during the detection cycle;

[0040] Acquire corresponding multiple nursing status vectors according to the nursing status data;

[0041] Obtaining a nursing state value according to a plurality of nursing state vectors;

[0042] Get the nursing status interval;

[0043] Determine whether the nursing status value is within the nursing status range;

[0044] If the nursing status value is within the nursing status interval, the nursing status change information is determined to be stable;

[0045] If the nursing status value is not within the nursing status interval and is greater than the upper limit of the nursing status interval, the nursing status change information is determined to be improved;

[0046] If the nursing status value is not within the nursing status interval and is less than the lower limit of the nursing status interval, it is determined that the nursing status change information is deteriorating.

[0047] In a preferred embodiment, the step of constructing a detection cycle includes:

[0048] Obtain the acquisition time of multimodal nursing data and mark it as the start time;

[0049] Obtain a duration table, wherein the duration table includes multiple disease levels and the detection duration corresponding to each disease level;

[0050] Obtain the corresponding testing duration from the duration table according to the initial disease level;

[0051] Get the end time based on the detection duration and start time;

[0052] Get the detection period based on the start time and end time.

[0053] In a preferred embodiment, the steps of obtaining a comprehensive nursing score according to the initial condition level, nursing status change information, efficacy change information, and adverse reaction information, generating a nursing report according to the comprehensive nursing score, and adjusting the comprehensive nursing model according to the nursing report include:

[0054] Obtaining corresponding nursing status values ​​according to nursing status change information;

[0055] Obtaining corresponding efficacy change value according to efficacy change information;

[0056] Obtaining corresponding adverse reaction values ​​according to adverse reaction information;

[0057] Obtain comprehensive nursing scores based on initial disease level, nursing status value, efficacy change value, and adverse reaction value;

[0058] Generate nursing reports based on comprehensive nursing scores and adjust comprehensive nursing models based on nursing reports.

[0059] The present invention also provides a non-small cell lung cancer clinical data analysis system based on the MPNFS theory, which is used for the above-mentioned non-small cell lung cancer clinical data analysis method based on the MPNFS theory, comprising:

[0060] The treatment plan module is used to obtain clinical data of patients with non-small cell lung cancer and obtain corresponding treatment plans based on the clinical data;

[0061] An initial condition module is used to obtain corresponding initial condition information according to clinical data, and obtain corresponding initial condition level according to the initial condition information;

[0062] A multimodal nursing module, used to obtain multimodal nursing data according to a treatment plan, obtain information on changes in efficacy of non-small cell lung cancer patients according to the multimodal nursing data, and obtain information on adverse reactions of non-small cell lung cancer patients according to the multimodal nursing data;

[0063] The nursing status module is used to construct a detection cycle, obtain nursing status data within the detection cycle, and obtain corresponding nursing status change information based on the nursing status data;

[0064] The nursing adjustment module is used to obtain a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

[0065] And, a non-small cell lung cancer clinical data analysis terminal based on MPNFS theory, including:

[0066] one or more processors;

[0067] a storage device having one or more programs stored thereon;

[0068] When one or more programs are executed by one or more processors, the one or more processors implement a non-small cell lung cancer clinical data analysis method based on the MPNFS theory.

[0069] The technical effects achieved by the present invention are:

[0070] The present invention can provide a comprehensive assessment of patient status, improve the scientificity and accuracy of the nursing model, generate individualized nursing reports, ensure that nursing intervention measures are highly matched with the patient's specific situation, and help improve the patient's treatment experience and quality of life. By regularly acquiring nursing status data and patient efficacy change information, it can timely identify deficiencies in treatment and care, adjust the nursing model, and optimize patient management. Through real-time monitoring and dynamic optimization of nursing models, it helps to enhance patients' treatment compliance, improve disease control effects and prognosis, and improve patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 is a flow chart of the method provided by the present invention;

[0072] Figure 2 It is a system module diagram provided by the present invention. DETAILED DESCRIPTION

[0073] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0074] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0075] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0076] Secondly, the present invention is described in detail in conjunction with schematic diagrams. When describing the embodiments of the present invention in detail, for the convenience of explanation, the schematic diagrams are only examples and should not limit the scope of protection of the present invention.

[0077] Please refer to the attached Figure 1 As shown, a clinical data analysis method for non-small cell lung cancer based on MPNFS theory is provided, including:

[0078] S1. Obtain clinical data of patients with non-small cell lung cancer and obtain corresponding treatment plans based on the clinical data;

[0079] S2. Obtain corresponding initial condition information according to the clinical data, and obtain corresponding initial condition level according to the initial condition information;

[0080] S3. Obtain multimodal nursing data according to the treatment plan, obtain information on changes in efficacy of patients with non-small cell lung cancer according to the multimodal nursing data, and obtain information on adverse reactions of patients with non-small cell lung cancer according to the multimodal nursing data;

[0081] S4. Construct a detection cycle, obtain nursing status data within the detection cycle, and obtain corresponding nursing status change information according to the nursing status data;

[0082] S5. Obtain a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

[0083] As in the above steps S1 to S5, clinical data of patients with non-small cell lung cancer are collected, including the patient's diagnostic information, tumor stage, pathological type, gene mutation status, etc., and individualized treatment plans are matched based on these data. Initial disease information, such as tumor size, metastasis status, functional score, etc., are extracted based on the patient's clinical data to generate an initial disease level, quantify the severity of the patient's disease, and use the multimodal nursing data generated during the patient's treatment process (including drug treatment data, psychological intervention data, nursing data, family care data, social support data, and patient complaints, etc.) to obtain treatment effects (such as tumor reduction rate, prolonged survival, etc.) and adverse reactions (such as nausea, fatigue, etc.). Within the set detection period, by monitoring nursing status data (such as nursing intervention measures, changes in patient quality of life, etc.), nursing status change information is obtained, and a dynamic tracking method is used to evaluate the patient's disease in real time. It can evaluate the effect of nursing intervention and the changing trend of patient condition, quantify and integrate the initial disease level, efficacy change information, adverse reaction information and nursing status change information, generate a comprehensive nursing score, generate individualized nursing reports based on the scoring results, put forward optimization suggestions and adjust the comprehensive nursing model to better meet the needs of patients. It can provide a full range of patient status assessments, improve the scientificity and accuracy of the nursing model, generate individualized nursing reports, ensure that nursing intervention measures are highly matched with the patient's specific situation, and help improve the patient's treatment experience and quality of life. By regularly obtaining nursing status data and patient efficacy change information, it can promptly identify deficiencies in treatment and care, adjust the nursing model, and optimize patient management. Through real-time monitoring and dynamic optimization of nursing models, it helps to enhance patients' treatment compliance, improve disease control effects and prognosis, and improve patient satisfaction.

[0084] In a preferred embodiment, the steps of obtaining corresponding initial condition information according to clinical data and obtaining corresponding initial condition level according to the initial condition information include:

[0085] S201, obtaining corresponding initial condition information according to clinical data;

[0086] S202, obtaining a corresponding initial condition vector according to the initial condition information;

[0087] S203, obtaining a disease state table, wherein the disease state table includes a plurality of disease state interval vectors and a disease state grade corresponding to each disease state interval vector;

[0088] S204, obtaining a corresponding target disease interval vector according to the initial disease vector;

[0089] S205. Obtain the disease level from the disease table according to the target disease interval vector.

[0090] As in the above steps S201 to S205, key disease information is extracted from the patient's clinical data, including but not limited to tumor size, stage (such as TNM stage), gene mutation, and patient physical status (ECOG score or KPS score). The extracted initial disease information is processed by data normalization and vectorization to construct a multidimensional vector (initial disease vector). Each dimension of the vector corresponds to a specific disease parameter, such as tumor size, stage score, etc., so as to form a structured disease description. The disease table is a pre-constructed mapping model, which includes multiple disease interval vectors, each disease interval vector corresponds to a different disease level (such as Mild: 2, Moderate: 3, Severe: 4), these intervals are determined through clinical research data and expert experience, and are widely applicable and scientific. According to the initial condition vector, the closest condition interval vector is matched in the condition table as the target condition interval vector. Through the target condition interval vector, the corresponding condition level is directly extracted from the condition table, and finally the patient's initial condition level is determined. By constructing the initial condition vector and the condition table, the structuring and quantification of the condition information is achieved, avoiding errors caused by subjective judgment, improving the accuracy and repeatability of the condition assessment, ensuring the scientific basis of each condition level, and improving the reliability of the condition assessment.

[0091] In a preferred embodiment, the steps of obtaining multimodal nursing data according to the treatment plan, obtaining efficacy change information of non-small cell lung cancer patients according to the multimodal nursing data, and obtaining adverse reactions of non-small cell lung cancer patients according to the multimodal nursing data include:

[0092] S301, acquiring multimodal nursing data according to a treatment plan;

[0093] S302, obtaining treatment effect information of corresponding non-small cell lung cancer patients according to the multimodal nursing data;

[0094] S303, acquiring corresponding multiple therapeutic effect status values ​​according to the therapeutic effect information;

[0095] S304, obtaining a therapeutic effect change value according to the multiple therapeutic effect status values, and marking it as therapeutic effect change information;

[0096] S305. Obtain adverse reaction information of patients with non-small cell lung cancer based on multimodal nursing data.

[0097] As in the above steps S301 to S305, according to the patient's treatment plan (such as surgery, chemotherapy, immunotherapy, etc.), multimodal nursing data is collected, including drug treatment data, psychological intervention data, nursing data, family care data, social support data and patient complaints, etc., and information related to the treatment effect is extracted. For example, the tumor shrinkage rate is evaluated by drug treatment (such as RECIST standard), and the treatment effect information is vectorized to generate multiple efficacy status values. Each state value represents the treatment effect at a time point. For example, the tumor volume change, the marker concentration change, etc. are respectively used as independent state values. According to the multiple efficacy state values, the efficacy change value is calculated, such as the percentage change of tumor volume reduction, the relief trend of adverse symptoms, etc., and marked as efficacy change information. The calculation formula of the efficacy change value is: Where, L condition It is represented by the therapeutic effect change value, h is represented by the number of multiple therapeutic effect status values, h=1,2,3…t, L h It is represented as the i-th efficacy status value. According to the multimodal nursing data, the adverse reaction information that the patient may experience (such as nausea, fatigue, anemia, infection, etc.) is extracted. Combined with the patient's self-report and nursing records, the severity and frequency of adverse reactions are evaluated to provide a basis for treatment adjustment. By using the efficacy status values ​​at multiple time points, the patient's treatment effect and condition changes are tracked in real time, providing data support for dynamic adjustment of treatment plans, which can provide patients with more personalized treatment and nursing plans and improve the safety and effectiveness of treatment.

[0098] In a preferred embodiment, the step of acquiring multimodal nursing data according to the treatment plan includes:

[0099] S3011, obtaining corresponding multiple treatment vectors according to the treatment plan;

[0100] S3012, obtaining multiple nursing tables, wherein each nursing table includes multiple treatment interval vectors and a nursing method corresponding to each treatment interval vector;

[0101] S3013, obtaining a corresponding target treatment interval vector from a corresponding nursing table according to each treatment vector;

[0102] S3014, obtaining a nursing method from a corresponding nursing table according to the target treatment interval vector;

[0103] S3015. Summarize the nursing methods corresponding to the multiple treatment vectors, and mark the summary results as multimodal nursing data.

[0104] As in the above steps S3011 to S3015, according to the patient's treatment plan (such as chemotherapy drug dose, radiotherapy schedule, immunotherapy cycle, etc.), key parameters are extracted and vectorized to form multiple treatment vectors, and a nursing table associated with each treatment plan is constructed. The nursing table includes multiple treatment interval vectors (for example, chemotherapy dose interval, radiotherapy frequency interval, etc.) and their corresponding nursing methods (such as nursing plans to prevent nausea or skin management methods). The nursing table is pre-defined through clinical experience and big data analysis. Each treatment vector is matched with the corresponding nursing table to find the target treatment interval vector that best matches the actual treatment situation. According to the target treatment interval vector, the corresponding nursing method is extracted from the nursing table. For example, a certain dose of chemotherapy corresponds to nursing content such as nausea prevention and blood index monitoring. The nursing methods corresponding to different treatment vectors are summarized and integrated to generate comprehensive multimodal nursing data, which are marked as the final nursing data output. These data cover the nursing requirements of the patient throughout the treatment process, provide comprehensive support for personalized nursing, ensure that each patient's nursing plan is highly relevant to its treatment details, and provide personalized and efficient nursing services.

[0105] In a preferred embodiment, the step of obtaining adverse reaction information of non-small cell lung cancer patients according to multimodal nursing data includes:

[0106] S3051. Obtain the adverse reaction vector corresponding to each nursing method of patients with non-small cell lung cancer based on multimodal nursing data;

[0107] S3052, obtaining an adverse reaction value according to a plurality of adverse reaction vectors;

[0108] S3053, obtaining an adverse reaction table, wherein the adverse reaction table includes multiple adverse reaction intervals and an adverse reaction status value corresponding to each adverse reaction interval;

[0109] S3054, obtaining a target adverse reaction interval according to the adverse reaction value;

[0110] S3055. Obtain the corresponding adverse reaction status value from the adverse reaction table according to the target adverse reaction interval, and mark it as adverse reaction information.

[0111] As in the above steps S3051 to S3055, the adverse reactions (such as nausea, rash, anemia, etc.) that may be caused by each nursing method are vectorized according to the multimodal nursing data. Each adverse reaction vector contains the association information between the nursing method and the possible adverse reactions, such as the reaction type, probability of occurrence, severity, etc. An overall adverse reaction value is calculated based on all adverse reaction vectors. The calculation formula of the adverse reaction value is: In the formula, F badIt is represented by the adverse reaction value, g is represented by the number of multiple adverse reaction vectors, g = 2, 3, 4...j, F g Represented as the g-th adverse reaction vector, F g-1 It is represented as the g-1th adverse reaction vector. The adverse reaction table is a predefined standard database, which includes multiple adverse reaction intervals (such as reaction value ranges) and their corresponding adverse reaction status values ​​(such as "mild", "moderate" and "severe"). The table is generated based on a large amount of clinical data training to ensure its scientificity and applicability. According to the calculated adverse reaction value, it is matched with the interval in the adverse reaction table to find the target adverse reaction interval that best matches the patient's actual status. The corresponding adverse reaction status value is extracted from the target adverse reaction interval and marked as the patient's adverse reaction information to form a complete evaluation report. It can carefully quantify the potential impact of each nursing method on adverse reactions, provide accurate adverse reaction risk assessment, and dynamically track the patient's status changes at different stages of care, providing a basis for real-time adjustment of nursing strategies.

[0112] In a preferred embodiment, the steps of constructing a detection cycle, obtaining nursing status data within the detection cycle, and obtaining corresponding nursing status change information according to the nursing status data include:

[0113] S401, constructing a detection cycle;

[0114] S402, obtaining nursing status data of nursing patients with non-small cell lung cancer according to multimodal nursing data within a detection period;

[0115] S403, acquiring corresponding multiple nursing status vectors according to the nursing status data;

[0116] S404, obtaining a nursing status value according to a plurality of nursing status vectors;

[0117] S405, obtaining a nursing status interval;

[0118] S406, determining whether the nursing status value is within the nursing status range;

[0119] If the nursing status value is within the nursing status interval, the nursing status change information is determined to be stable;

[0120] If the nursing status value is not within the nursing status interval and is greater than the upper limit of the nursing status interval, the nursing status change information is determined to be improved;

[0121] If the nursing status value is not within the nursing status interval and is less than the lower limit of the nursing status interval, it is determined that the nursing status change information is deteriorating.

[0122] As in the above steps S401 to S406, a reasonable detection cycle is set according to the patient's nursing needs and treatment plan, for example, relevant data is recorded daily, weekly or after each nursing. During the detection cycle, the patient's nursing status data is collected according to the multimodal nursing data, including physical signs (such as body temperature, blood oxygen saturation), symptom feedback (such as pain level, fatigue) and nursing response (such as the frequency and implementation of nursing measures). The collected nursing status data is converted into a standardized multi-dimensional nursing state vector, which includes key parameters of the patient's current nursing state. The nursing state value is calculated based on multiple nursing state vectors. The calculation formula of the nursing state value is: In the formula, B condition It is represented by the nursing status value, i is represented by the number of multiple nursing status vectors, i = 1, 2, 3...n, B i It is represented as the i-th nursing state vector. The nursing state interval is a predefined standard range used to divide the nursing evaluation results of different states. The interval is obtained based on a large amount of clinical data analysis, including upper and lower limits, defining the "normal", "preference" or "deviation" range. If the nursing state value is within the nursing state interval, the nursing state change information is judged to be "stable", that is, the patient's nursing effect meets expectations. If the nursing state value is higher than the upper limit of the nursing state interval, it means that the patient's nursing effect is better than expected and is judged to be "improved". If the nursing state value is lower than the lower limit of the nursing state interval, it means that the patient's nursing effect is lower than expected or the nursing measures need to be adjusted, which is judged to be "deteriorated". It can dynamically track the patient's nursing status, promptly discover fluctuations in nursing effects, and provide a basis for adjusting the nursing plan.

[0123] In a preferred embodiment, the step of constructing a detection cycle includes:

[0124] S4011, obtaining the acquisition time of the multimodal nursing data and marking it as the start time;

[0125] S4012, obtaining a duration table, wherein the duration table includes multiple disease levels and the detection duration corresponding to each disease level;

[0126] S4013, obtaining the corresponding detection duration from the duration table according to the initial disease level;

[0127] S4014, obtaining the end time according to the detection duration and the start time;

[0128] S4015. Obtain a detection period according to the start time and the end time.

[0129] As in the above steps S4011 to S4015, the time of the first data collection is extracted from the multimodal nursing data and marked as the start time of the detection cycle. This time point is used as the starting point of the cycle. The duration table is a standard database constructed based on a large amount of clinical data and expert experience, which contains detection durations (such as 6 hours, 24 hours, and 72 hours) corresponding to different disease levels (such as mild, moderate, and severe). According to the patient's initial disease level (determined by early diagnosis or disease assessment), the corresponding detection duration is extracted from the duration table. For example, the more severe the disease, the shorter the detection duration and the more frequent the monitoring to ensure that problems are discovered in time. The detection duration is added to the start time to obtain the end time of the detection cycle. For example, if the start time is The start time is 12:00 on December 1, 2024, and the detection duration is 24 hours, then the end time is 12:00 on December 2, 2024. Combined with the start time and end time, the complete detection cycle range is determined to guide data collection and nursing status monitoring. For example, the detection cycle can be defined as "12:00 on December 1, 2024 to 12:00 on December 2, 2024". The detection cycle is flexibly adjusted according to the patient's initial condition level, and appropriate monitoring plans are formulated for different conditions to ensure that high-risk patients receive more intensive monitoring and care, avoiding the waste of resources due to too frequent monitoring, while ensuring the timely collection of important data, and effectively balancing the quality of care and resource utilization efficiency.

[0130] In a preferred embodiment, the steps of obtaining a comprehensive nursing score according to the initial condition level, nursing status change information, efficacy change information, and adverse reaction information, generating a nursing report according to the comprehensive nursing score, and adjusting the comprehensive nursing model according to the nursing report include:

[0131] S501, obtaining a corresponding nursing status value according to nursing status change information;

[0132] S502, obtaining a corresponding therapeutic effect change value according to the therapeutic effect change information;

[0133] S503, obtaining a corresponding adverse reaction value according to the adverse reaction information;

[0134] S504. Obtain a comprehensive nursing score according to the initial disease level, nursing status value, efficacy change value, and adverse reaction value;

[0135] S505. Generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

[0136] As in the above steps S501 to S505, the corresponding nursing status value is obtained according to the nursing status change information (such as "stable", "improved", "worse"), the corresponding efficacy change value is obtained according to the efficacy change information (such as the patient's clinical indicator changes, the achievement of treatment goals, etc.), and the corresponding adverse reaction value is obtained according to the adverse reaction information (such as the frequency and severity of adverse reactions). The initial disease level, nursing status value, efficacy change value, and adverse reaction value are used as input to calculate the comprehensive nursing score. The calculation formula of the comprehensive nursing score is P=L condition ·F bad ·B condition , where P represents the comprehensive nursing score, L condition Expressed as the therapeutic effect change value, F bad Expressed as adverse reaction value, B condition It is expressed as the nursing status value. A nursing report is generated based on the comprehensive nursing score, which includes the patient's nursing status, efficacy, adverse reaction summary and improvement suggestions. The nursing report provides a comprehensive decision-making basis for doctors and nursing teams. If the comprehensive score is high, it means that the nursing effect is good and the current nursing model can be maintained. If the comprehensive score is medium, it means that some nursing measures need to be optimized, such as increasing the nursing frequency or adjusting the treatment plan. If the comprehensive score is low, it means that the current nursing model needs to be significantly adjusted, such as strengthening the monitoring frequency or changing the nursing method. By calculating the comprehensive nursing score, the complex nursing effect is converted into a quantifiable indicator, which is convenient for objective evaluation and tracking of the nursing quality. The comprehensive nursing score and the generated nursing report provide comprehensive and accurate data support for the medical team, help formulate a more scientific nursing plan, and optimize the nursing model. The nursing model can be dynamically adjusted with the changes in the score and report to ensure that the nursing effect is optimized synchronously with the changes in the patient's condition and improve the efficiency of nursing resource utilization.

[0137] Please refer to the attached Figure 2 As shown, the present invention also provides a non-small cell lung cancer clinical data analysis system based on the MPNFS theory, which is used for the above-mentioned non-small cell lung cancer clinical data analysis method based on the MPNFS theory, comprising:

[0138] The treatment plan module is used to obtain clinical data of patients with non-small cell lung cancer and obtain corresponding treatment plans based on the clinical data;

[0139] An initial condition module is used to obtain corresponding initial condition information according to clinical data, and obtain corresponding initial condition level according to the initial condition information;

[0140] A multimodal nursing module, used to obtain multimodal nursing data according to a treatment plan, obtain information on changes in efficacy of non-small cell lung cancer patients according to the multimodal nursing data, and obtain information on adverse reactions of non-small cell lung cancer patients according to the multimodal nursing data;

[0141] The nursing status module is used to construct a detection cycle, obtain nursing status data within the detection cycle, and obtain corresponding nursing status change information based on the nursing status data;

[0142] The nursing adjustment module is used to obtain a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

[0143] As mentioned above, the treatment plan module receives the clinical data of patients with non-small cell lung cancer, including diagnostic information, physical examination data, genetic test results, etc., and generates a treatment plan suitable for the patient. The initial condition module extracts the initial condition information based on the patient's clinical data, and quantifies the condition through a vectorization method, and maps it to a specific initial condition level in combination with the condition interval vector in the condition table. The multimodal nursing module derives multimodal nursing data through the treatment plan, covering drug management, psychological counseling, life care, etc. During the nursing process, the patient's efficacy change information and adverse reaction data are collected and updated in real time. The nursing status module analyzes the status change trend based on the nursing status data collected during the detection cycle, and updates it through a preset status interval. The rules determine the stability, improvement or deterioration of the nursing status, and adjust the nursing module to calculate the comprehensive nursing score based on the comprehensive information (initial disease level, nursing status changes, efficacy changes, adverse reactions), generate standardized nursing reports, and automatically adjust the nursing mode according to the report recommendations, such as changing the nursing frequency, optimizing medication or adjusting the treatment plan, providing personalized treatment plans and nursing suggestions, reducing blindness, and improving treatment effects. It can track the patient's nursing status changes in real time, identify disease trends through dynamic changes in nursing status values, and provide data support for early intervention. Through scientific and quantitative evaluation methods and personalized nursing plans, it improves the patient's treatment compliance and nursing satisfaction, while reducing the psychological burden on patients and their families.

[0144] And, a non-small cell lung cancer clinical data analysis terminal based on MPNFS theory, including:

[0145] one or more processors;

[0146] a storage device having one or more programs stored thereon;

[0147] When one or more programs are executed by one or more processors, the one or more processors implement a non-small cell lung cancer clinical data analysis method based on the MPNFS theory.

[0148] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A clinical data analysis method for non-small cell lung cancer based on MPNFS theory, characterized in that: include: Obtain clinical data of patients with non-small cell lung cancer and obtain corresponding treatment plans based on the clinical data; Obtain corresponding initial condition information according to clinical data, and obtain corresponding initial condition level according to the initial condition information; Obtain multimodal nursing data according to the treatment plan, obtain information on changes in efficacy of patients with non-small cell lung cancer according to the multimodal nursing data, and obtain information on adverse reactions of patients with non-small cell lung cancer according to the multimodal nursing data; Construct a detection cycle, obtain nursing status data within the detection cycle, and obtain corresponding nursing status change information based on the nursing status data; Obtain a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

2. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 1, characterized in that: The steps of obtaining corresponding initial condition information according to clinical data and obtaining corresponding initial condition level according to the initial condition information include: Obtain corresponding initial condition information based on clinical data; Obtaining a corresponding initial condition vector according to the initial condition information; Obtain a disease table, wherein the disease table includes a plurality of disease interval vectors and a disease level corresponding to each disease interval vector; Obtaining a corresponding target disease interval vector according to the initial disease vector; Obtain the disease level from the disease table according to the target disease interval vector.

3. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 1, characterized in that: The steps of obtaining multimodal nursing data according to a treatment plan, obtaining efficacy change information of a patient with non-small cell lung cancer according to the multimodal nursing data, and obtaining adverse reactions of the patient with non-small cell lung cancer according to the multimodal nursing data include: Capture multimodal care data based on treatment plans; Obtain treatment effect information for corresponding non-small cell lung cancer patients based on multimodal nursing data; Acquire corresponding multiple efficacy status values ​​according to the treatment effect information; Obtaining a therapeutic effect change value according to multiple therapeutic effect status values, and marking it as therapeutic effect change information; Obtaining adverse event information for patients with non-small cell lung cancer based on multimodal nursing data.

4. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 3, characterized in that: The steps to obtain multimodal care data based on treatment plans include: Obtain corresponding multiple treatment vectors according to the treatment plan; Obtain multiple nursing tables, wherein each nursing table includes multiple treatment interval vectors and a nursing method corresponding to each treatment interval vector; According to each treatment vector, a corresponding target treatment interval vector is obtained from the corresponding nursing table; Obtain the nursing method from the corresponding nursing table according to the target treatment interval vector; The nursing methods corresponding to multiple treatment vectors are summarized, and the summary results are marked as multimodal nursing data.

5. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 3, characterized in that: Steps to obtain adverse reaction information for patients with non-small cell lung cancer based on multimodal nursing data include: Obtain the adverse reaction vector corresponding to each nursing mode of patients with non-small cell lung cancer based on multimodal nursing data; Obtaining adverse reaction values ​​according to a plurality of adverse reaction vectors; Obtaining an adverse reaction table, wherein the adverse reaction table includes multiple adverse reaction intervals and an adverse reaction status value corresponding to each adverse reaction interval; Obtain target adverse reaction interval according to adverse reaction value; According to the target adverse reaction interval, the corresponding adverse reaction status value is obtained from the adverse reaction table and marked as adverse reaction information.

6. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 1, characterized in that: The steps of constructing a detection cycle, obtaining nursing status data within the detection cycle, and obtaining corresponding nursing status change information according to the nursing status data include: Building a testing cycle; Obtain nursing status data of non-small cell lung cancer patients based on multimodal nursing data during the detection cycle; Acquire corresponding multiple nursing status vectors according to the nursing status data; Obtaining a nursing state value according to a plurality of nursing state vectors; Get the nursing status interval; Determine whether the nursing status value is within the nursing status range; If the nursing status value is within the nursing status interval, the nursing status change information is determined to be stable; If the nursing status value is not within the nursing status interval and is greater than the upper limit of the nursing status interval, the nursing status change information is determined to be improved; If the nursing status value is not within the nursing status interval and is less than the lower limit of the nursing status interval, it is determined that the nursing status change information is deteriorating.

7. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 1, characterized in that: The steps to build a detection cycle include: Obtain the acquisition time of multimodal nursing data and mark it as the start time; Obtain a duration table, wherein the duration table includes multiple disease levels and the detection duration corresponding to each disease level; Obtain the corresponding testing duration from the duration table according to the initial disease level; Get the end time based on the detection duration and start time; Get the detection period based on the start time and end time.

8. The method for analyzing clinical data of non-small cell lung cancer based on MPNFS theory according to claim 1, characterized in that: The steps of obtaining a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generating a nursing report based on the comprehensive nursing score, and adjusting the comprehensive nursing model based on the nursing report include: Obtaining corresponding nursing status values ​​according to nursing status change information; Obtaining corresponding efficacy change value according to efficacy change information; Obtaining corresponding adverse reaction values ​​according to adverse reaction information; Obtain comprehensive nursing scores based on initial disease level, nursing status value, efficacy change value, and adverse reaction value; Generate nursing reports based on comprehensive nursing scores and adjust comprehensive nursing models based on nursing reports.

9. A non-small cell lung cancer clinical data analysis system based on MPNFS theory, applied to the non-small cell lung cancer clinical data analysis method based on MPNFS theory according to any one of claims 1 to 8, characterized in that: include: The treatment plan module is used to obtain clinical data of patients with non-small cell lung cancer and obtain corresponding treatment plans based on the clinical data; An initial condition module is used to obtain corresponding initial condition information according to clinical data, and obtain corresponding initial condition level according to the initial condition information; A multimodal nursing module, used to obtain multimodal nursing data according to a treatment plan, obtain information on changes in efficacy of non-small cell lung cancer patients according to the multimodal nursing data, and obtain information on adverse reactions of non-small cell lung cancer patients according to the multimodal nursing data; The nursing status module is used to construct a detection cycle, obtain nursing status data within the detection cycle, and obtain corresponding nursing status change information based on the nursing status data; The nursing adjustment module is used to obtain a comprehensive nursing score based on the initial disease level, nursing status change information, efficacy change information, and adverse reaction information, generate a nursing report based on the comprehensive nursing score, and adjust the comprehensive nursing model based on the nursing report.

10. A non-small cell lung cancer clinical data analysis terminal based on MPNFS theory, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When one or more programs are executed by one or more processors, the one or more processors implement the non-small cell lung cancer clinical data analysis method based on MPNFS theory as described in any one of claims 1 to 8.

Images