Tumor nursing data processing system based on cloud computing

Abstract

The invention relates to the technical field of medical data processing, in particular to a tumor nursing data processing system based on cloud computing, and the system comprises a multi-scale feature analysis module which obtains tumor nursing data, splits the tumor nursing data into a plurality of time dimensions, extracts multi-scale features of the tumor nursing data, and sends the multi-scale features to a cloud computing module; and carrying out importance sorting on the multi-scale features of the tumor nursing data to obtain a preliminary tumor nursing data feature alignment result. According to the method, feature decomposition and analysis of multiple time scales are carried out on the tumor nursing data, feature changes in different time dimensions are effectively captured, and the comprehensiveness of feature recognition is enhanced. According to the method, important features are sorted, the matching relation is dynamically adjusted, feature combinations with high relevance are subjected to weighted fusion, meanwhile, the large-scale data processing efficiency is improved through distributed optimization, and the accuracy and adaptability of data integration are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a tumor nursing data processing system based on cloud computing. Background Art

[0002] Medical data processing technology covers methods for collecting, storing, analyzing and visualizing large amounts of medical-related data. This field mainly includes electronic health records (EHR), medical image processing, clinical decision support systems, remote monitoring, artificial intelligence-assisted diagnosis, and personalized treatment plan formulation. Its core goal is to improve the efficiency, accuracy, and personalization of medical services through data-driven methods, and ultimately improve patient health management.

[0003] Among them, the tumor nursing data processing system is a data processing and management system specifically used in the field of tumor nursing, which optimizes the data flow, analysis and application related to tumor patient care. Its main uses include collecting patients' treatment and nursing records, analyzing nursing effects, and providing data support to assist in the formulation of personalized nursing plans.

[0004] Existing technologies have difficulty in fully capturing the characteristics of nursing data at different time scales, and ignore the changing patterns of short-term and long-term characteristics. For example, when analyzing patient nursing responses, short-term indicator fluctuations may be regarded as noise, and long-term trends may not be accurately reflected, limiting the accurate evaluation of nursing effects. In cross-patient data integration, the correlation and importance ranking of features are not fully considered, which easily leads to the difficulty of feature fusion results in supporting the accurate analysis of complex nursing data. For example, the correlation of key indicators between different patients may be diluted, affecting the scientific nature of feature combination. In terms of storage, existing technologies do not reasonably stratify according to data types and feature importance, which often leads to uneven resource allocation, inefficient storage of key data, and non-key data occupying more storage space, resulting in inefficient data management. The dynamic changes of nursing data are not updated in real time, which makes it difficult to capture new response patterns in the nursing process in a timely manner, ultimately affecting the timeliness and accuracy of nursing decisions. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose a tumor nursing data processing system based on cloud computing.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A tumor nursing data processing system based on cloud computing includes:

[0007] The multi-scale feature analysis module obtains tumor nursing data, decomposes the tumor nursing data into multiple time dimensions, extracts the multi-scale features of the tumor nursing data, sorts the importance of the multi-scale features of the tumor nursing data, and obtains preliminary tumor nursing data feature alignment results;

[0008] The dynamic feature alignment adjustment module selects matching feature combinations based on the preliminary tumor nursing data feature alignment result according to a preset correlation threshold, dynamically updates the matching relationship between features, and obtains cross-patient feature fusion results;

[0009] The non-uniform grid storage module analyzes the multi-scale features of the fused tumor nursing data based on the cross-patient feature fusion result, maps the data of inconsistent types to a matching storage layer, and obtains the data storage hierarchical division result;

[0010] The adaptive data partitioning and optimization module monitors the real-time changes of tumor nursing data based on the data storage level division results, identifies the response patterns of patients during the nursing process, dynamically updates the data storage level, and generates tumor nursing data processing results.

[0011] As a further solution of the present invention, the steps of acquiring the multi-scale features of the tumor nursing data are specifically as follows:

[0012] Based on patient monitoring data and nursing records, the data is broken down according to the time dimension, the change range of monitoring data, the frequency of nursing intervention and the duration of treatment response are extracted, and the corresponding feature data table is generated;

[0013] Based on the corresponding feature data table, the range of each feature value is sorted, the features are normalized, the magnitude of the feature values ​​is adjusted, and a standardized feature data set is obtained.

[0014] As a further solution of the present invention, the steps for obtaining the preliminary tumor nursing data feature alignment result are specifically as follows:

[0015] For the standardized feature data set, the formula is used:

[0016]

[0017] Calculate the importance score I of a single feature i i , get the feature importance analysis results;

[0018] Among them, f i is the normalized value of feature i, r i is the correlation factor, indicating the strength of the relevance of feature i to the nursing goal, d i is the sampling interval of feature i;

[0019] Based on the feature importance analysis results, the features are sorted from high to low according to the scores, and the arrangement order of the corresponding features in the data table is adjusted synchronously to obtain the preliminary tumor nursing data feature alignment results.

[0020] As a further solution of the present invention, the step of obtaining the feature combination for screening matching is specifically:

[0021] Based on the preliminary tumor nursing data feature alignment results, extract the features of the trend change rate, nursing intervention frequency change rate and treatment response duration of the cross-patient data according to the importance ranking, interpolate the missing feature values ​​and perform data alignment to generate a cross-patient feature integration set;

[0022] Based on the integrated set of features across patients, the formula is used:

[0023]

[0024] Calculate the Pearson correlation coefficient between feature i1 and i2 in a feature pair Get matching feature combinations;

[0025] where i 1j ,i 2j are the values ​​of features i1 and i2 in the jth sample, is the mean of features i1 and i2, and n is the total number of patients or data points.

[0026] As a further solution of the present invention, the step of obtaining the cross-patient feature fusion result is specifically:

[0027] Extracting feature data of multiple periods based on the highly correlated feature pairs selected from the matching feature combination, classifying and weighting the features according to time characteristics, and dynamically adjusting the feature matching relationship to generate a dynamically updated cross-time scale feature matching result;

[0028] Based on the dynamically updated cross-time scale feature matching results, combined with the cloud computing environment, the feature data is distributed to multiple nodes for parallel processing, local optimization and global integration are performed, and feature matching verification and result optimization are performed to obtain cross-patient feature fusion results.

[0029] As a further solution of the present invention, the step of obtaining the data storage hierarchical division result is specifically as follows:

[0030] Based on the cross-patient feature fusion results, physiological indicators, treatment plans, monitoring data, and nursing records of tumor nursing data are classified and extracted, and the data are mapped to inconsistent storage layers according to data characteristics and storage requirements, and mapping verification is performed to obtain matching storage layer mapping information;

[0031] Based on the matching storage layer mapping information, a corresponding storage mapping relationship is constructed, the storage rules and resource allocation of the storage layer are optimized, abnormal allocation is adjusted, and a data storage hierarchy division result is generated.

[0032] As a further solution of the present invention, the step of obtaining the reaction pattern of the patient during the nursing process is specifically:

[0033] Based on the data storage hierarchical division result, extract real-time tumor nursing data, including physiological indicators, monitoring data and nursing records, and obtain real-time tumor nursing data change analysis results by real-time monitoring and analyzing the dynamic changes of the data;

[0034] Based on the real-time tumor nursing data change analysis results, the formula is used:

[0035]

[0036] Calculate the change amplitude B of the patient's physiological indicators and the change rate F of the nursing intervention frequency respectively to generate the analysis results of the patient's response pattern;

[0037] Where T is the total number of data points in the time period, V t is the physiological index value at the tth time point, is the mean value of the physiological index during the monitoring period, ΔN is the change in the number of nursing interventions during the period, and ΔT represents the time difference between two adjacent records.

[0038] As a further solution of the present invention, the steps of obtaining the tumor nursing data processing results are specifically as follows:

[0039] Based on the analysis results of the patient response pattern, extract and re-analyze the patient data that has been divided into multiple storage levels, dynamically adjust the patient data according to the latest changes in the heart rate fluctuation amplitude and the nursing frequency, re-divide the storage levels, and obtain updated storage level data;

[0040] Based on the updated storage hierarchy data, the real-time data of patients in various priority categories are integrated, individual and group care status is analyzed, and tumor care data processing results are generated.

[0041] Compared with the prior art, the advantages and positive effects of the present invention are:

[0042] In the present invention, by performing multi-time scale feature decomposition and analysis on tumor nursing data, the feature changes in different time dimensions are effectively captured, and the comprehensiveness of feature recognition is enhanced. By normalizing and adjusting the features of different patient data, the comparability and consistency of cross-patient data are improved, and the interference of feature magnitude differences on the analysis results is eliminated. The important features are sorted and the matching relationship is dynamically adjusted, and the feature combinations with high correlation are weighted and fused. At the same time, distributed optimization is used to improve the efficiency of large-scale data processing, which significantly improves the accuracy and adaptability of data integration. The storage mapping relationship is constructed in combination with data type and importance, which optimizes storage efficiency and resource utilization, so that the storage of nursing data is highly consistent with actual application requirements. By real-time identification of reaction patterns in the nursing process and dynamic adjustment of data storage levels, data processing and updating can respond to nursing needs in a timely manner, providing data support for tumor nursing. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a system flow chart of the present invention;

[0044] Figure 2 A flowchart for obtaining multi-scale features of tumor nursing data for the present invention;

[0045] Figure 3 A flowchart for obtaining preliminary tumor nursing data feature alignment results for the present invention;

[0046] Figure 4 A flow chart for screening matching feature combinations for the present invention;

[0047] Figure 5 A flow chart for obtaining cross-patient feature fusion results for the present invention;

[0048] Figure 6 A flow chart of the result of obtaining the data storage hierarchy division in the present invention;

[0049] Figure 7 A flow chart for identifying the response patterns exhibited by patients during the nursing process for the present invention;

[0050] Figure 8 This is a flow chart of the tumor nursing data processing results obtained by the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0053] See also Figure 1 , the cloud computing-based tumor nursing data processing system includes:

[0054] The multi-scale feature analysis module obtains tumor nursing data, breaks down the tumor nursing data into multiple time dimensions, extracts local features for different time scales, including the changing trend of patient monitoring data, the frequency of nursing intervention, and the duration of treatment response, and normalizes the extracted features, adjusts the feature magnitude of nursing events between patients, extracts multi-scale features of tumor nursing data, sorts the importance of multi-scale features of tumor nursing data, and obtains preliminary tumor nursing data feature alignment results;

[0055] Based on the preliminary tumor nursing data feature alignment results, the dynamic feature alignment adjustment module integrates the tumor nursing data features across patients according to the multi-scale features of the tumor nursing data sorted by importance, screens the matching feature combinations according to the preset correlation threshold, dynamically updates the matching relationship between features, performs weighted fusion on the matching relationships at different time scales, and performs distributed optimization on the weighted fusion process in combination with the cloud computing environment to obtain the cross-patient feature fusion results;

[0056] The non-uniform grid storage module analyzes the multi-scale features of the fused tumor nursing data based on the cross-patient feature fusion results, considering the importance of the multi-scale features of tumor nursing data in the nursing process, as well as the types of tumor nursing data, including the patient's physiological indicators, treatment plans, monitoring data, and nursing records. It maps inconsistent data types to matching storage layers, optimizes data storage efficiency and resource utilization by building corresponding storage mapping relationships, and obtains data storage hierarchical division results.

[0057] The adaptive data partitioning and optimization module monitors the real-time changes of tumor nursing data based on the data storage hierarchy division results, identifies the response patterns of patients during the nursing process, including the fluctuation of physiological indicators and the changes in the frequency of nursing interventions, and dynamically updates the data storage hierarchy through continuous analysis of the patient group data to reflect the latest nursing information and generate tumor nursing data processing results;

[0058] The preliminary results of tumor nursing data feature alignment include the normalized characteristics of the changing trend of patient monitoring data, the time scale characteristics of the nursing intervention frequency and the distribution characteristics of the duration of treatment response. The cross-patient feature fusion results include the matching feature groups of different patients in treatment response, the integrated distribution after feature weight adjustment and the time scale adaptation results based on weighted processing. The data storage hierarchical division results include the high-priority storage data layer, the second-priority data cache layer and the low-frequency data storage layer. The tumor nursing data processing results include the data partition adjustment results reflecting the latest patient care status, the real-time updated hierarchical storage distribution and the dynamically identified patient group feature patterns.

[0059] See also Figure 2 ,The steps to obtain the multi-scale features of tumor nursing data are as follows:

[0060] Based on patient monitoring data and nursing records, the data is broken down according to the time dimension, the change range of monitoring data, the frequency of nursing intervention and the duration of treatment response are extracted, and the corresponding feature data table is generated;

[0061] Obtain tumor nursing data, break it down into multiple time dimensions, and process it based on a cloud computing platform. First, upload the patient's monitoring data to cloud storage. For example, a patient's vital signs data within one week include heart rate, blood pressure, and blood oxygen concentration, which are recorded 24 times a day and once an hour, for a total of 168 data points. Nursing intervention data are recorded as 1-3 interventions per day, for a total of 15 times. Treatment response data are recorded as treatment response duration, and the duration of response after each intervention is between 2-4 hours. Through the hierarchical processing module of the cloud computing platform, the above data are disassembled according to the time scale: hourly level: calculate the fluctuation amplitude of heart rate, blood pressure and blood oxygen per hour, for example, the fluctuation range of heart rate in the first hour is 72-85bpm, and the amplitude is 13bpm; daily level: calculate the average of vital signs data every day, for example, the daily average of heart rate is 78bpm, the average of blood pressure is 120 / 80mmHg, and the average of blood oxygen concentration is 96%; count the frequency of nursing intervention, for example, the frequency of intervention is 2 times on a certain day; weekly level: summarize the duration of treatment response and calculate the average duration of treatment response per week, for example, the total treatment response time is 45 hours, and the average duration of each response is 3 hours; at the same time, record the total frequency of nursing intervention within a week and its changing trend. Through the above steps, a data table containing hourly, daily and weekly scale features is finally formed and stored in the analysis database of the cloud platform for subsequent processing and analysis.

[0062] Based on the corresponding feature data table, sort out the range of each feature value, normalize the features, adjust the magnitude of the feature value, and obtain a standardized feature data set;

[0063] The extracted multi-scale feature data are processed. For example, the fluctuation amplitude of the hourly data center heart rate is recorded as 13bpm, 10bpm, 15bpm, etc., the fluctuation amplitude of blood pressure is 20mmHg, 25mmHg, 22mmHg, and the fluctuation amplitude of blood oxygen concentration is 2%, 3%, and 4%; in the daily data, the average heart rate range is 70-85bpm, the average blood pressure range is 110-130mmHg, and the average blood oxygen concentration range is 95%-98%; in the weekly data, the average duration of the treatment response ranges from 2.5 to 3.5 hours. In order to adjust the magnitude of each feature, the hourly, daily, and weekly data are normalized in each dimension respectively, and the fluctuation amplitude of the heart rate is adjusted to a relative range (for example, between 0 and 1). The fluctuation amplitude of blood pressure and blood oxygen concentration are also scaled to a relative value range. Through this process, the feature magnitudes of different patients are aligned, thereby forming a unified multi-scale feature set for subsequent analysis. Finally, the processed feature set is saved as a standardized format file in the cloud platform.

[0064] See also Figure 3,The steps to obtain the preliminary tumor nursing data feature alignment results are as follows:

[0065] For the standardized feature data set, the formula is used:

[0066]

[0067] Calculate the importance score I of a single feature i i , get the feature importance analysis results;

[0068] Among them, f i is the normalized value of feature i, which represents the dimensionless value of a specific feature after normalization. i It is the correlation factor, which indicates the correlation of feature i to the nursing goal. It ranges from 0 to 1 and is determined by data analysis. The larger the value, the higher the correlation between the feature and the goal. It is determined by analyzing the correlation between feature changes and key patient indicators (such as treatment effects). i It is the sampling interval of feature i, which indicates the collection period of specific feature data and is directly determined by the collection plan or data recording frequency.

[0069] For example, there are the following characteristic data: trend change rate f1=0.6, correlation factor r1=0.9, sampling interval d1=1 hour, nursing intervention frequency change rate f2=0.8, correlation factor r2=0.7, sampling interval d2=24 hours, treatment response duration f3=0.4, correlation factor r3=0.5, sampling interval d3=168 hours.

[0070] Calculate the importance score for the rate of change of trend:

[0071]

[0072] Calculate the importance score for the rate of change in nursing intervention frequency:

[0073]

[0074] Calculate the importance score for duration of treatment response:

[0075]

[0076] The results showed that the importance score of trend change rate was 0.54, the importance score of nursing intervention frequency change rate was 0.0233, and the importance score of treatment response duration was 0.0012.

[0077] Based on the feature importance analysis results, the features were sorted from high to low by score, and the order of the corresponding features in the data table was adjusted simultaneously to obtain the preliminary tumor nursing data feature alignment results;

[0078] The importance of multi-scale features of tumor nursing data was sorted. Based on the calculated single feature importance score, the trend change rate I1 = 0.54, the nursing intervention frequency change rate I2 = 0.0233, and the treatment response duration I3 = 0.0012 were arranged in descending order. The result was: trend change rate (0.54) > nursing intervention frequency change rate (0.0233) > treatment response duration (0.0012). According to the sorting results, the original feature set was rearranged in the above order, the index information corresponding to each feature was recorded, and the column order of the data table was adjusted synchronously.

[0079] See also Figure 4 , the specific steps for obtaining the feature combination for screening matching are:

[0080] Based on the preliminary alignment results of tumor nursing data features, the features of trend change rate, nursing intervention frequency change rate and treatment response duration across patient data were extracted in order of importance, missing feature values ​​were interpolated and data were aligned to generate a feature integration set across patients;

[0081] First, extract the features with the highest importance, such as trend change rate, nursing intervention frequency change rate and treatment response duration. For each feature, extract the corresponding feature values ​​from the data of different patients one by one. For example, for patients A, B and C, the extracted trend change rates are 0.6, 0.8 and 0.7, the nursing intervention frequency change rates are 0.3, 0.4 and 0.2, and the treatment response durations are 5 hours, 4 hours and 6 hours, respectively. Arrange these feature values ​​in order of trend change rate, nursing intervention frequency change rate and treatment response duration as follows: 0.6, 0.3, 5 (patient A), 0.8, 0.4, 4 (patient B), 0.7, 0.2, 6 (patient C); during the integration process, for patients with missing feature values ​​(such as patient D missing the nursing intervention frequency change rate), interpolation is performed through the mean of adjacent patients (patients A and B). For example, the mean of the nursing intervention frequency change rate is calculated to be 0.35, and this value is added to the nursing intervention frequency change rate field of patient D to ensure the integrity of all patient feature sets. Finally, the integrated patient feature set is saved as aligned multi-patient feature data.

[0082] Based on the integrated set of features across patients, the formula is used:

[0083]

[0084] Calculate the Pearson correlation coefficient between feature i1 and i2 in a feature pair Get matching feature combinations;

[0085] in, The value range is -1, 1, positive value indicates positive correlation, negative value indicates negative correlation, and the absolute value close to 1 indicates strong correlation. 1j ,i 2j are the values ​​of features i1 and i2 in the jth sample (such as the patient), is the mean of features i1 and i2, which respectively represent the average level of features i1 and i2 in all samples. The calculation formula is: n is the total number of patients or data points, The deviation of the eigenvalue from the mean is used to measure the fluctuation of the eigenvalue relative to the overall level. The square of the deviation of the eigenvalue from the mean, which is used to measure the squared contribution of the deviation.

[0086] For example, the characteristic data of 5 patients are as follows: trend change rate (feature x): 0.6, 0.7, 0.8, 0.5, 0.9, nursing intervention frequency change rate (feature y): 0.3, 0.4, 0.5, 0.2, 0.6.

[0087] Calculate the mean trend rate of change:

[0088]

[0089] Calculate the mean rate of change of nursing intervention frequency:

[0090]

[0091] Substitute into the formula:

[0092]

[0093]

[0094] Calculate the correlation coefficient:

[0095]

[0096] The results show that there is a complete positive correlation between the trend change rate and the nursing intervention frequency change rate (correlation coefficient is 1). is positively correlated, indicating that features i1 and i2 change in the same direction. is negatively correlated, indicating that features i1 and i2 change in opposite directions. The correlation is strong, indicating that the linear relationship between the features is close. There is no obvious linear correlation. For high correlation (strong linear relationship): usually set the threshold Indicates that the correlation between the feature pairs is strong and has analytical value. For weak correlation (weak linear relationship): When , the correlation is low and may have limited contribution to the analysis, it can be considered to be removed. For example, assuming that the correlation coefficients of the three feature pairs are: (Trend change rate and nursing intervention frequency change rate), (Trend rate of change and duration of treatment response), (rate of change in nursing intervention frequency and duration of treatment response), setting thresholds The screening results are: Meet the threshold conditions (positive correlation and strong linear relationship), Meet the threshold condition (negative correlation but strong linear relationship), eliminate: Below the threshold (weak linear relationship). The feature pairs retained by threshold screening can be used as the key data combination for subsequent fusion and optimization, while the eliminated feature pairs are not involved in further analysis due to insufficient correlation, thereby improving the efficiency and accuracy of feature analysis.

[0097] See also Figure 5 , the specific steps for obtaining the cross-patient feature fusion results are:

[0098] Based on the highly correlated feature pairs selected from the matched feature combinations, feature data from multiple periods are extracted, features are classified and weighted according to time characteristics, and feature matching relationships are dynamically adjusted to generate dynamically updated cross-time scale feature matching results.

[0099] Based on the calculated correlation results, the matching relationship between features in the tumor nursing data is dynamically updated. Assuming that the matching between the treatment response and the nursing intervention effect of different patients is monitored, the trend change rate (short-term feature) and the duration of treatment response (long-term feature) are first selected from the screened high-correlation feature pairs, and feature values ​​are extracted for different patients. For example, the short-term trend change rate of patient A is 0.6, and the duration of treatment response is 5 hours; the short-term trend change rate of patient B is 0.8, and the duration of treatment response is 6 hours; the short-term trend change rate of patient C is 0.7, and the duration of treatment response is 4 hours. These data are classified into short-term feature groups and long-term feature groups, respectively, and the feature values ​​are normalized to make the numerical distribution ranges of different features consistent, for example, the short-term trend change rate is normalized to 0.75, 1, and 0.88. After the feature normalization is completed, a weighted value is assigned to each pair of features. The weighted value of the short-term feature is set to 0.7 according to the time characteristics of the feature, and the weighted value of the long-term feature is set to 0.3. The weight allocation is dynamically adjusted according to the real-time demand of nursing. For example, the short-term feature reflects the timeliness of nursing and has a higher weight, while the long-term feature is used to observe the overall trend and has a relatively low weight. Then the weighted fusion value is calculated for each patient. For example, the fusion value of patient A is calculated as 0.75×0.7+5×0.3=1.575, the fusion value of patient B is 1×0.7+6×0.3=1.90, and the fusion value of patient C is 0.88×0.7+4×0.3=1.516. After the weighted fusion value calculation of all patients is completed, the weighted fusion values ​​corresponding to the patients are sorted, and the matching relationship is generated according to the high and low feature matching results. For example, patient B has the highest feature combination score and the highest matching priority, followed by patient A and patient C. The dynamically updated feature matching relationship results provide a quantitative basis for the comprehensive analysis of short-term and long-term features, which is used for subsequent data integration and optimization processing.

[0100] Based on the dynamically updated cross-time scale feature matching results, combined with the cloud computing environment, the feature data is distributed to multiple nodes for parallel processing, local optimization and global integration are performed, and feature matching verification and result optimization are performed to obtain cross-patient feature fusion results;

[0101] Combined with the cloud computing environment, the weighted fusion process is distributedly optimized. Following the dynamic matching results completed in paragraph 1, the weighted fusion value and corresponding feature data of the patient are uploaded to the cloud computing environment. To optimize the distributed processing efficiency, the data is first divided into different computing tasks according to the patient feature groups. For example, the short-term and long-term features of patients A, B, and C are respectively assigned to different nodes for processing; each node performs local optimization on the assigned patient data, including verifying the accuracy of the weighted fusion results, checking whether there are abnormal data points, and further adjusting the weighted values ​​to adapt to the global optimization needs, such as increasing the weights for patients with large fluctuations in short-term features. After the distributed computing nodes complete their local tasks, the system summarizes the intermediate results of each node and integrates them through the central node. During the integration process, the fusion rules are dynamically adjusted according to the weight distribution of the patient feature values. For example, priority fusion rights are given to patient groups with higher short-term feature importance, and the priority list of feature matching is recalculated based on the summarized data. After the integration is completed, the cloud computing environment verifies the overall fusion results, such as using historical data to retrospectively check the matching results, and evaluate the effectiveness of the optimized fusion results in prediction and analysis. Finally, the optimized cross-patient feature fusion results are output for downstream analysis tasks, such as treatment effect evaluation and nursing strategy adjustment.

[0102] See also Figure 6 , the specific steps for obtaining the data storage hierarchy division results are:

[0103] Based on the cross-patient feature fusion results, the physiological indicators, treatment plans, monitoring data, and nursing records of tumor nursing data are classified and extracted, and the data is mapped to different storage layers according to data characteristics and storage requirements. The mapping is verified and the matching storage layer mapping information is obtained.

[0104] In the cloud computing environment, the specific process of mapping tumor care data to different storage layers is as follows: By analyzing the fused tumor care data, the data is classified by feature type, for example: Monitoring data: real-time heart rate (80bpm), blood pressure (120 / 80mmHg), body temperature (36.5℃ to 37.2℃). Treatment plan: drug dosage (50mg), administration time (8:00AM). Nursing record: nursing intervention time (2024-11-1915:00) and nursing type (routine examination). Define matching rules according to storage requirements and data characteristics: High-speed storage layer: used to store real-time data, supporting fast access and high-frequency reading, such as monitoring data. Medium-speed storage layer: used to store periodically updated data, such as treatment plans. Low-speed storage layer: used to store archived or long-term preserved data, such as nursing records. Data mapping process: Monitoring data: heart rate (80bpm) and body temperature (36.5℃ to 37.2℃) are real-time data and directly mapped to the high-speed storage layer to quickly respond to nursing needs. Treatment plan: drug dosage (50mg) and administration time (8:00AM) are regularly updated data and are mapped to the medium-speed storage layer to meet the moderate demand for data modification frequency. Nursing records: nursing intervention time and type are historical data and mapped to the low-speed storage layer for subsequent long-term archiving and archiving analysis. The system verifies the consistency of storage mapping, such as checking whether the monitoring data is completely mapped to the high-speed layer, whether the treatment plan is updated on time, and whether the data omission or incorrect storage allocation that occurs in the middle is readjusted; during the verification, if it is found that the nursing record is mistakenly allocated to the high-speed layer, it is remapped to the low-speed layer according to the rules. Assume that the real-time heart rate and body temperature data of patient A are stored in the high-speed storage layer, and the data is subsequently called multiple times in the nursing operation to support real-time nursing decisions; the nursing records of patient B are stored in the low-speed storage layer to evaluate the overall trend of historical nursing interventions; through the reasonable allocation of storage layers, the efficiency of data access and the optimal use of storage resources are ensured, providing support for nursing decisions and data management.

[0105] Based on the matching storage layer mapping information, the corresponding storage mapping relationship is constructed, the storage rules and resource allocation of each storage layer are optimized, the abnormal allocation is adjusted, and the data storage hierarchical division result is generated;

[0106] First, define clear storage rules for each storage layer, such as allocating larger bandwidth and faster access speed to the high-speed storage layer, supporting regular data update functions for the medium-speed storage layer, and focusing on data archiving and long-term preservation for the low-speed storage layer; then, store and allocate each category of data according to the set rules, such as mapping monitoring data to the high-speed storage layer that supports high-frequency reading, mapping treatment plans to the medium-speed storage layer that supports periodic updates, and mapping nursing records to the low-speed storage layer to reduce resource consumption. After the mapping relationship is built, verify and adjust the storage allocation, such as testing whether the real-time access speed of the high-speed storage layer meets the requirements by simulating nursing scenarios, checking whether the update operation of the medium-speed storage layer is accurately executed, and correcting the abnormal allocation or inefficient storage problems found; then analyze the resource utilization of the overall storage system, such as evaluating the capacity utilization and read-write efficiency of each storage layer, dynamically adjusting the storage layer capacity or data allocation rules according to the analysis results, optimizing the resource configuration of the storage layer, and finally outputting accurate storage hierarchy division results to provide efficient storage solutions for the long-term management of tumor nursing data.

[0107] See also Figure 7 , the specific steps to identify the patient's response pattern during the nursing process are:

[0108] Based on the data storage hierarchical division results, real-time tumor nursing data, including physiological indicators, monitoring data and nursing records, are extracted. By real-time monitoring and analyzing the dynamic changes of these data, the real-time tumor nursing data change analysis results are obtained.

[0109] First, the patient's physiological indicators, monitoring data and nursing intervention records are extracted from the high-speed storage layer in real time. For example, the heart rate data extracted from the high-speed storage layer of patient A is: 80bpm (0 minutes), 85bpm (5 minutes), 90bpm (10 minutes). The nursing record shows that 5 nursing interventions were completed within 1 hour. Then, during the monitoring process, the system automatically identifies the dynamic changes of these data and marks abnormalities. For example, the speed of the heart rate rising from 85bpm to 90bpm is 1bpm / min, which is within the normal range. However, if the heart rate fluctuation rate increases to 3bpm / min, the system marks it as a high-risk state and records the abnormal change time. In addition, the frequency of nursing intervention is monitored. For example, the nursing frequency of patient B increases from 2 times / hour to 5 times / hour, indicating that the density of nursing operations has increased. During the monitoring process, the system compares the change data in real time, analyzes the trend in combination with historical data, and generates a monitoring report. At the same time, it records relevant logs for subsequent analysis of the source and dynamic change rules of abnormal data, providing support for subsequent nursing intervention optimization and data adjustment.

[0110] Based on the analysis results of real-time tumor nursing data changes, the formula is used:

[0111]

[0112] Calculate the change amplitude B of the patient's physiological indicators and the change rate F of the nursing intervention frequency respectively to generate the analysis results of the patient's response pattern;

[0113] Where T is the total number of data points in the time period, indicating the number of samples of monitoring data, V t is the physiological index value at the tth time point, which is recorded in real time by physiological monitoring equipment, such as monitoring heart rate or blood pressure changes. is the mean value of physiological indicators during the monitoring period, and the calculation formula is: ΔN is the change in the number of nursing interventions within a time period. The number of interventions in each time period is extracted from the nursing log and obtained by calculating the change in adjacent time periods. ΔT represents the time difference between two adjacent records.

[0114] For calculating the variation range B of the patient's physiological index, for example, the heart rate data of patient A is collected through a monitoring device, and the data are 80, 85, 90, 88, and 92 bpm respectively within 10 minutes.

[0115] Calculate the mean:

[0116] Calculate the sum of squared deviations:

[0117] Fluctuation Range:

[0118] The results showed that the variation range B of the patient's physiological index was 4.19 bpm.

[0119] For the rate of change F of the nursing intervention frequency, for example, if the nursing log shows that patient B completed 5 nursing interventions in the first hour and 3 nursing interventions in the second hour.

[0120] Change in the number of nursing care times ΔN = 3-5 = -2 times;

[0121] Time period length ΔT = 1 hour;

[0122] Changes in frequency of care times / hour.

[0123] The results showed that the frequency of nursing care was reduced by 2 times / hour.

[0124] See also Figure 8 ,The specific steps for obtaining the tumor nursing data processing results are:

[0125] Based on the analysis results of the patient response patterns, the patient data that has been divided into multiple storage levels is extracted and re-analyzed. According to the latest changes in the heart rate fluctuation amplitude and the nursing frequency, the patient data is dynamically adjusted, the storage levels are re-divided, and the updated storage level data is obtained;

[0126] By continuously analyzing the data of the patient group and dynamically updating the data storage level, the patient data that has been divided into different storage layers are firstly extracted and analyzed again. For example, the heart rate fluctuation of patient A is 4.19bpm, and it is initially classified into the medium-speed storage layer. However, it is found in continuous monitoring that the fluctuation of his heart rate increases from 4.19bpm to 6bpm, and the rate of decrease of nursing frequency is -2 times / hour. According to the latest changes, the system adjusts the data of patient A to the high-speed storage layer for further real-time analysis. Meanwhile, for patient B, he was initially assigned to the high-speed storage layer because of the large fluctuation of his heart rate (6bpm) and the high rate of increase of nursing frequency (+3 times / hour). However, it is observed in continuous monitoring that the fluctuation of his heart rate decreases to 3bpm, and the nursing frequency tends to be stable. The system adjusts his data to the medium-speed storage layer as periodic data. The whole dynamic update process is executed through data monitoring, classification rule comparison, and storage layer transfer, and the update log of the adjusted data is recorded to ensure that the dynamic changes of data can reflect the latest status and meet the needs of hierarchical storage.

[0127] Based on the updated storage hierarchy data, real-time patient data of various priority categories are integrated to analyze individual and group care status and generate tumor care data processing results;

[0128] Integrate high-priority patient data that is adjusted in real time with periodically updated medium- and low-priority data. For example, in response to the continuous increase in heart rate fluctuations and the increase in nursing frequency for patient B, generate personalized nursing strategy optimization suggestions. Combined with patient A's stable nursing data, generate a comparative analysis report on group nursing status. During the data integration process, the system dynamically analyzes the impact of the new data on the overall trend, and uses nursing records and changes in the fluctuations of physiological indicators to display the latest nursing status of each patient. Ultimately, it outputs nursing data processing results covering multi-level patient groups to provide support for real-time decision-making and strategy adjustments.

[0129] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A tumor nursing data processing system based on cloud computing, characterized in that: The system comprises: The multi-scale feature analysis module obtains tumor nursing data, decomposes the tumor nursing data into multiple time dimensions, extracts the multi-scale features of the tumor nursing data, sorts the importance of the multi-scale features of the tumor nursing data, and obtains preliminary tumor nursing data feature alignment results; The dynamic feature alignment adjustment module selects matching feature combinations based on the preliminary tumor nursing data feature alignment result according to a preset correlation threshold, dynamically updates the matching relationship between features, and obtains cross-patient feature fusion results; The non-uniform grid storage module analyzes the multi-scale features of the fused tumor nursing data based on the cross-patient feature fusion result, maps the data of inconsistent types to a matching storage layer, and obtains the data storage hierarchical division result; The adaptive data partitioning and optimization module monitors the real-time changes of tumor nursing data based on the data storage level division results, identifies the response patterns of patients during the nursing process, dynamically updates the data storage level, and generates tumor nursing data processing results.

2. The cloud computing-based tumor nursing data processing system according to claim 1, characterized in that: The steps for obtaining the multi-scale features of the tumor nursing data are specifically as follows: Based on patient monitoring data and nursing records, the data is broken down according to the time dimension, the change range of monitoring data, the frequency of nursing intervention and the duration of treatment response are extracted, and the corresponding feature data table is generated; Based on the corresponding feature data table, the range of each feature value is sorted, the features are normalized, the magnitude of the feature values ​​is adjusted, and a standardized feature data set is obtained.

3. The cloud computing-based tumor nursing data processing system according to claim 2, characterized in that: The steps for obtaining the preliminary tumor nursing data feature alignment result are specifically as follows: For the standardized feature data set, the formula is used: Calculate the importance score I of a single feature i i , get the feature importance analysis results; Among them, f i is the normalized value of feature i, r i is the correlation factor, indicating the strength of the relevance of feature i to the nursing goal, d i is the sampling interval of feature i; Based on the feature importance analysis results, the features are sorted from high to low according to the scores, and the arrangement order of the corresponding features in the data table is adjusted synchronously to obtain the preliminary tumor nursing data feature alignment results.

4. The cloud computing-based tumor nursing data processing system according to claim 3, characterized in that: The steps for obtaining the feature combination for screening matching are specifically as follows: Based on the preliminary tumor nursing data feature alignment results, extract the features of the trend change rate, nursing intervention frequency change rate and treatment response duration of the cross-patient data in order of importance, interpolate the missing feature values ​​and perform data alignment to generate a cross-patient feature integration set; Based on the integrated set of features across patients, the formula is adopted: Calculate the Pearson correlation coefficient ρ between features i1 and i2 in a feature pair i1i2 , get the matching feature combination; where i 1j ,i 2j are the values ​​of features i1 and i2 in the jth sample, is the mean of features i1 and i2, and n is the total number of patients or data points.

5. The cloud computing-based tumor nursing data processing system according to claim 4, characterized in that: The steps for obtaining the cross-patient feature fusion result are specifically as follows: Extracting feature data of multiple periods based on the highly correlated feature pairs selected from the matching feature combination, classifying and weighting the features according to time characteristics, and dynamically adjusting the feature matching relationship to generate a dynamically updated cross-time scale feature matching result; Based on the dynamically updated cross-time scale feature matching results, combined with the cloud computing environment, the feature data is distributed to multiple nodes for parallel processing, local optimization and global integration are performed, and feature matching verification and result optimization are performed to obtain cross-patient feature fusion results.

6. The cloud computing-based tumor nursing data processing system according to claim 5, characterized in that: The steps for obtaining the data storage hierarchical division result are specifically as follows: Based on the cross-patient feature fusion results, physiological indicators, treatment plans, monitoring data, and nursing records of tumor nursing data are classified and extracted, and the data are mapped to inconsistent storage layers according to data characteristics and storage requirements, and mapping verification is performed to obtain matching storage layer mapping information; Based on the matching storage layer mapping information, a corresponding storage mapping relationship is constructed, the storage rules and resource allocation of the storage layer are optimized, abnormal allocation is adjusted, and a data storage hierarchy division result is generated.

7. The cloud computing-based tumor nursing data processing system according to claim 6, characterized in that: The steps of obtaining the reaction pattern of the patient during the nursing process are specifically as follows: Based on the data storage hierarchical division result, extract real-time tumor nursing data, including physiological indicators, monitoring data and nursing records, and obtain real-time tumor nursing data change analysis results by real-time monitoring and analyzing the dynamic changes of the data; Based on the real-time tumor nursing data change analysis results, the formula is used: Calculate the change amplitude B of the patient's physiological indicators and the change rate F of the nursing intervention frequency respectively to generate the analysis results of the patient's response pattern; Where T is the total number of data points in the time period, V t is the physiological index value at the tth time point, is the mean value of the physiological index during the monitoring period, ΔN is the change in the number of nursing interventions during the period, and ΔT represents the time difference between two adjacent records.

8. The cloud computing-based tumor nursing data processing system according to claim 7, characterized in that: The steps for obtaining the tumor nursing data processing results are specifically as follows: Based on the analysis results of the patient response pattern, extract and re-analyze the patient data that has been divided into multiple storage levels, dynamically adjust the patient data according to the latest changes in the heart rate fluctuation amplitude and the nursing frequency, re-divide the storage levels, and obtain updated storage level data; Based on the updated storage hierarchy data, the real-time data of patients in various priority categories are integrated, individual and group care status is analyzed, and tumor care data processing results are generated.

Images