Medical care data management system based on big data calculation

Abstract

The invention discloses a medical care data management system based on big data calculation, and relates to the technical field of data management, and the system comprises a data collection module, a data security module, a data storage module, a care quality analysis module, a care aid decision support module and a data visualization module. According to the medical care data management system based on big data calculation, by integrating and analyzing massive medical care data, more scientific and accurate decision support is provided for nursing personnel, multi-dimensional nursing data of a patient is collected and is compared and analyzed with a standardized nursing knowledge base, differences and defects in a nursing plan are quickly identified, and the medical care data management system is suitable for medical care. And the deviation of the nursing plan of the patient is determined through data analysis, and prospective decision-making suggestions are provided for nursing personnel, so that the subjectivity and uncertainty of manual judgment are reduced, and the efficiency and accuracy of nursing decision-making are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a medical care data management system based on big data computing. Background Art

[0002] In the field of medical care, the individual differences of patients and the wide variety of diseases require the nursing process to be more personalized and refined. With the continuous development of information technology, the types and scale of medical data are growing rapidly. The emergence of big data technology has made it possible to process and analyze massive amounts of data, enabling medical institutions to manage and utilize these data resources more effectively. Medical institutions can develop personalized care plans based on the patient's medical history, physical characteristics, treatment needs and other information, and track and record the nursing process in real time.

[0003] Medical care data contains data from multiple sources, which makes the results of big data calculation more complicated, making it difficult for medical staff to fully understand and utilize the data analysis results, and then analyze the deviation of the nursing plan and adjust the nursing plan as needed. For this reason, a medical care data management system based on big data calculation is proposed to realize the intuitive analysis and display of patient medical care data. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: a medical care data management system based on big data computing, the system includes a data collection module, a data security module, a data storage module, a nursing quality analysis module, a nursing auxiliary decision support module and a data visualization module, wherein the modules are connected by electrical signals; The data collection module is used to collect medical care data from multiple sources such as patient information systems, electronic medical records, medical equipment, and nursing records. Through comprehensive data collection, it ensures that the system can obtain complete and accurate patient information, provides a basis for subsequent data analysis and display, and performs pre-processing operations on the collected medical care data to improve data quality and consistency; The data security module protects the security of medical care data during transmission, storage and processing through encryption, access control and data backup, and prevents data leakage and illegal access; The data storage module uses an efficient distributed database to store pre-processed data, and through reasonable storage design, it can realize rapid retrieval and access of data, thereby improving the response speed and performance of the system; The nursing quality analysis module performs nursing assessment on patients based on pre-processed medical nursing data, analyzes the patient's current treatment status and deviations from the nursing plan, and ensures the completeness and accuracy of nursing records; The nursing auxiliary decision support module, combined with the nursing quality assessment results, identifies the defects in the nursing plan, provides decision support, optimizes the nursing plan, achieves homogeneous nursing, improves the quality of nursing services, ensures patient safety, and improves the scientificity and accuracy of nursing decisions; The data visualization module displays the analysis results to medical staff in the form of charts, images, and animations, presenting the relationships and trends between the data, and assisting medical staff in quickly understanding the data analysis results.

[0005] Preferably, in the data collection module, the collection and preprocessing process of medical care data includes: The sources of medical care data collection are clarified, namely, patient information system, electronic medical records, medical equipment, and nursing records. Among them, the patient information system includes the patient's personal information, medical records, and allergy history. The electronic medical record records the patient's detailed medical history, diagnostic information, examination results, and treatment plan. Medical equipment is used to output real-time monitoring data generated by electrocardiographs and ultrasound machines. Nursing records are data recorded by nurses during daily care for patients, including vital signs, diet, and medication records. Connect to various data sources through API interfaces and use ETL tools to extract medical care data from various data sources in real time; Preprocess the extracted medical care data, including data cleaning, data conversion, data integration and data standardization steps; Conduct a quality assessment on the pre-processed medical care data, evaluate the accuracy, completeness and consistency indicators of the data, calculate the data quality score, and analyze the quality level of medical care after pre-processing.

[0006] Preferably, the calculation process of the data quality score is: Collect the accuracy score, consistency score, and completeness score of each data source, and determine the baseline accuracy score and maximum accuracy score of each data source; For each data source, based on its accuracy score, the baseline accuracy score and the maximum accuracy score, calculate its accuracy deviation, obtain the accuracy deviation function, and calculate the root mean square error of the accuracy deviations of all data sources; Based on the integrity score of the data source, calculate the impact of the integrity score on data quality, and use the logistic function (Sigmoid function) to calculate the impact of the consistency score on data quality; The data quality score is obtained by combining the calculation results of the accuracy score, completeness score and consistency score.

[0007] Preferably, the calculation formula for the data quality score is: ; in, is the data quality score, For the The accuracy score of each data source, For the The baseline accuracy scores of the data sources, For the The maximum accuracy score of the data sources is used to normalize the accuracy score. For the The consistency score of each data source, For the The integrity score of the data source is the total number of data sources, The value range is [0,1].

[0008] Preferably, the data security module specifically includes: Use symmetric and asymmetric encryption algorithms to encrypt sensitive data. For fast encryption of large amounts of data, symmetric encryption algorithms use the same key for encryption and decryption. For key distribution and digital signature scenarios, asymmetric encryption algorithms use public and private key pairs, with the public key used for encryption and the private key used for decryption. During the data transmission process, the SSL security protocol is used to encrypt the data to ensure the security of the data during transmission. When storing medical care data, the sensitive fields of patient personal information and diagnosis results are encrypted and stored; The multi-factor authentication method of username / password combination and biometric recognition is used to authenticate the user identity to ensure the authenticity of the user identity. Different access rights are granted to each role according to the division of labor among doctors, nurses and managers to ensure that users can only access the minimum range of data they need, thus improving the flexibility and security of permission management. At the same time, all access behaviors are monitored and recorded for post-review and tracking to detect abnormal access behaviors. Develop a regular backup plan to ensure that the backup content is synchronized with the source data, and perform multiple backups of medical care data and store the data in different locations to prevent single points of failure and emergencies; After the backup is completed, verify the backup medical care data, perform recovery tests on the backup data regularly, and verify the availability and restoreability of the backup.

[0009] Preferably, in the data storage module, the storage process of the pre-processed data includes: The pre-processed medical care data is written in batches into a distributed database system based on Hadoop HDFS, and the medical care data is sharded and distributed to multiple nodes to improve the parallel processing capability and access speed of the data; Create indexes for frequently queried fields in medical care data to speed up data retrieval, compress stored medical care data, reduce storage space usage to improve I / O performance, optimize SQL query statements based on query requirements, avoid unnecessary full table scans, and use indexes to speed up queries; Use the monitoring tools provided by the distributed database system to monitor the performance indicators of database throughput, response time, CPU usage, and memory usage. Based on the monitoring results, tune the database configuration, indexing, and partitioning strategies to improve the overall performance of the system.

[0010] Preferably, in the nursing quality analysis module, the nursing assessment process includes: Traverse the pre-processed medical care data, including nursing records, doctor's orders, examination results, and vital signs data, integrate all the patient's medical care information to form a complete nursing medical record; Match the patient's nursing records with the standard nursing plan to check whether the nursing operations are carried out in accordance with the nursing plan, and then evaluate whether the nursing activities received by the patient are sufficient, timely, and meet the nursing standards; According to the nursing standards, the associated nursing indicators for nursing quality evaluation are determined, namely patient satisfaction, nursing error rate, nursing response time and nursing expected recovery deviation. The nursing indicators of patient satisfaction and nursing expected recovery deviation are quantitatively scored, and the nursing quality evaluation coefficient is calculated by comprehensive analysis combined with nursing error rate and nursing response time to reflect the overall situation of nursing quality. According to the nursing quality evaluation coefficient, different nursing quality levels are preset, namely low nursing quality level, medium nursing quality level and high nursing quality level, and the corresponding evaluation threshold is matched for each nursing quality level; Based on the determined nursing quality level and the value of the nursing quality evaluation coefficient, analyze the problems and deficiencies in the nursing process, and evaluate the deviations between the patient's current treatment status and nursing quality.

[0011] Preferably, the calculation process of the nursing quality evaluation coefficient is: Extract data on patient satisfaction, nursing error rate, nursing response time, and nursing expected recovery deviation, and calculate the positive influencing factors of the nursing error rate. The nursing error rate is converted into a positive influencing factor. The lower the error rate, the closer it is to 1, the higher the nursing safety. Calculate the joint impact of patient satisfaction score and nursing error rate, analyze the joint impact of nursing safety and patient satisfaction, and divide the joint impact by nursing response time to calculate the impact of response time and measure the impact of response speed on nursing quality. The shorter the response time, the better the nursing quality. The larger it is, the better the nursing responsiveness; The impact of nursing expected recovery deviation was measured by calculating the square term of the expected recovery deviation score. The larger the deviation, The larger it is, the greater the negative impact on the quality of care, and the impact of response time and the impact of expected recovery deviation are added together to obtain a comprehensive impact value; Take the square root of the comprehensive impact value to get a value between 0 and 1, obtain the preliminary evaluation results of nursing quality, and use the exponential decay function to process the impact of patient satisfaction and calculate the decay effect of patient satisfaction. The higher the satisfaction, the smaller the decay. The preliminary evaluation result obtained by the square root is multiplied by the attenuation effect of patient satisfaction to obtain the final nursing quality evaluation coefficient, which reflects the overall situation of nursing quality and ranges from 0 to 1. The higher the value, the better the nursing quality.

[0012] Preferably, the calculation formula of the nursing quality evaluation coefficient is: ; in, is the nursing quality evaluation coefficient, Rate patient satisfaction. The nursing error rate indicates the rate of errors in the nursing process and is used to measure the safety of nursing. For nursing response time, The expected recovery deviation score is used to measure the deviation between the patient's actual recovery and the expected recovery plan. The value range of is 0 to 1, where 0 indicates very poor quality of care and 1 indicates very good quality of care; The values ​​of the nursing quality evaluation coefficient and the preset evaluation thresholds of the nursing quality levels are obtained to match the three-level nursing quality levels, which are: Low quality of care rating: ; Indicates that there are significant problems in nursing services that require immediate attention and improvement. Possible problems include low patient satisfaction, high nursing error rate, slow response time, and large deviation from nursing expected recovery. It is necessary to conduct a comprehensive review of the nursing process, improve the professional training of nursing staff, optimize the allocation of nursing resources, and improve patient communication and feedback mechanisms; Medium care quality level: ; Indicates that the quality of nursing services is average and there is room for improvement. There may be some room for improvement, such as low satisfaction of some patients, occasional nursing errors, and room for optimization of response time. We should improve the nursing process in a targeted manner, improve the professional skills of nursing staff, strengthen nursing quality monitoring, and improve patient satisfaction; High quality of care level: ; Indicates that the quality of nursing services is good, close to or at high standards, and the overall performance is good, but there may still be some minor problems or room for improvement. We will continue to monitor and optimize the nursing process, maintain high standards of nursing service quality, and encourage nursing innovation and continuous improvement; in, is the nursing quality evaluation coefficient, is the lower threshold corresponding to the medium nursing quality level and the upper threshold corresponding to the low nursing quality level, is the lower threshold corresponding to the high nursing quality level and the upper threshold corresponding to the medium nursing quality level, , .

[0013] Preferably, in the nursing auxiliary decision support module, the process of optimizing the nursing plan includes: Based on nursing needs and patient rehabilitation needs, a standardized nursing knowledge base is established, including evaluation criteria for nursing assessment, nursing problems, and nursing measures; Compare the actual nursing plan with the standardized nursing knowledge base to identify the differences and deficiencies in the nursing plan, and analyze the problems and defects in the implementation of the nursing plan in combination with the results of the nursing quality assessment to determine the nature and severity of the problems; Based on the analysis results, targeted decision-making recommendations are provided to nursing staff, including adjusting nursing assessment methods, modifying nursing goals, optimizing nursing measures, and revising and optimizing nursing plans based on decision-making recommendations.

[0014] The present invention provides a medical care data management system based on big data computing. It has the following beneficial effects: 1. This medical care data management system based on big data computing integrates and analyzes massive amounts of medical care data to provide nursing staff with more scientific and accurate decision-making support, collects patients' multi-dimensional nursing data, compares and analyzes it with the standardized nursing knowledge base, quickly identifies differences and deficiencies in nursing plans, and clarifies deviations in patients' care plans through data analysis, providing nursing staff with forward-looking decision-making suggestions, which not only reduces the subjectivity and uncertainty of human judgment, but also improves the efficiency and accuracy of nursing decisions.

[0015] 2. This medical care data management system based on big data computing combines the standardized nursing knowledge base with big data computing technology to make the nursing process more standardized and unified. It can generate nursing plans that meet the requirements according to the patient's specific situation and nursing standards, and monitor the implementation of nursing. By comparing and analyzing the differences between the actual nursing plans and the standard nursing plans, it can timely discover and correct deviations in the nursing process and ensure the homogeneity of nursing services, which not only improves the quality of nursing, but also enhances the patients' trust and satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module structure diagram of a medical care data management system based on big data computing according to the present invention; Figure 2 This is a flow chart of the collection and preprocessing of medical care data of the present invention; Figure 3 A flowchart for the nursing assessment of the present invention; Figure 4 The figure is a calculation flow chart of the nursing quality evaluation coefficient of the present invention. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0018] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: a medical care data management system based on big data computing, the system includes a data collection module, a data security module, a data storage module, a nursing quality analysis module, a nursing auxiliary decision support module and a data visualization module, wherein the modules are connected by electrical signals; The data collection module is used to collect medical care data from multiple sources such as patient information systems, electronic medical records, medical equipment, and nursing records. Through comprehensive data collection, it ensures that the system can obtain complete and accurate patient information, providing a basis for subsequent data analysis and presentation, and pre-processing the collected medical care data to improve data quality and consistency. The collection sources of medical care data are clarified, namely, patient information systems, electronic medical records, medical equipment, and nursing records. Among them, the patient information system includes the patient's personal information, medical records, and allergy history. The electronic medical record records the patient's detailed medical history, diagnostic information, examination results, and treatment plans. Medical equipment is used to output real-time monitoring data generated by electrocardiographs and ultrasound machines. Nursing records are data recorded by nurses during daily care of patients, including vital signs, dietary conditions, and medication records. Record, connect with various data sources through API interface, use ETL tools to extract medical care data from various data sources in real time, pre-process the extracted medical care data, including data cleaning, data conversion, data integration and data standardization steps, among which data cleaning is used to remove duplicate records, correct errors and inconsistent data, and handle missing values, data conversion is used to convert data in different formats into a unified format for subsequent processing and analysis, data integration is used to merge information from different data sources to build a complete patient view, data standardization is used to ensure that all data follow the same standards and units to improve data consistency, conduct quality assessment on pre-processed medical care data, evaluate data accuracy, completeness and consistency indicators, calculate data quality scores, and analyze the quality level of medical care after pre-processing; Furthermore, the calculation process of the data quality score is: The accuracy score, consistency score and completeness score of each data source are collected, and the baseline accuracy score and maximum accuracy score of each data source are determined. For each data source, based on its accuracy score, baseline accuracy score and maximum accuracy score, its accuracy deviation is calculated to obtain the accuracy deviation function, and the root mean square error of the accuracy deviations of all data sources is calculated. Based on the completeness score of the data source, the impact of the completeness score on data quality is calculated, and the impact of the consistency score on data quality is calculated using the logistic function (Sigmoid function). The calculation results of the accuracy score, completeness score and consistency score are combined to obtain the data quality score. Furthermore, the calculation formula of the data quality score is: ; in, is the data quality score, For the The accuracy score of each data source, For the The baseline accuracy scores of the data sources, For the The maximum accuracy score of the data sources is used to normalize the accuracy score. For the The consistency score of each data source, For the The integrity score of the data source is the total number of data sources, The value range is [0,1], where 0 indicates extremely poor data quality and 1 indicates extremely good data quality. Close to benchmark score When , the value of the square root part will decrease, thus increasing , when the completeness score As it increases, the value of the exponential function tends to 1, which also helps to improve , when the consistency score As the value increases, the value of the logic function tends to 1, and further increase ; The data security module protects the security of medical care data during transmission, storage and processing through encryption, access control and data backup measures, prevents data leakage and illegal access, and uses symmetric encryption and asymmetric encryption algorithms to encrypt sensitive data. For the rapid encryption of large amounts of data, a symmetric encryption algorithm is used to use the same key for encryption and decryption. For key distribution and digital signature scenarios, an asymmetric encryption algorithm is used to use a public key and a private key pair. The public key is used for encryption and the private key is used for decryption. During data transmission, the SSL security protocol is used to encrypt data to ensure the security of data during transmission. When storing medical care data, sensitive fields of patient personal information and diagnosis results are encrypted and stored, and username / password combinations and biometric recognition are used. Other multi-factor authentication methods authenticate user identities to ensure the authenticity of user identities, and grant different access rights to each role based on the division of roles of doctors, nurses, and managers to ensure that users can only access the minimum range of data they need, thereby improving the flexibility and security of permission management. At the same time, all access behaviors are monitored and recorded for post-review and tracking to detect abnormal access behaviors, and regular backup plans are formulated to ensure that the backup content is synchronized with the source data. Multiple backups of medical care data are performed and stored in different locations to resist single point failures and emergencies. After the backup is completed, the backup medical care data is verified to ensure the restoreability and integrity of the backup data. The backup data recovery test is performed regularly to verify the availability and restoreability of the backup. The data storage module uses an efficient distributed database to store pre-processed data, and through reasonable storage design, it realizes fast retrieval and access of data, improves the response speed and performance of the system, writes the pre-processed medical care data in batches into a distributed database system based on Hadoop HDFS, and shards and distributes the medical care data to multiple nodes to improve the parallel processing capability and access speed of the data. It creates indexes for frequently queried fields in the medical care data to speed up the retrieval speed of the data, compresses the stored medical care data, reduces the use of storage space to improve I / O performance, optimizes SQL query statements according to query requirements, avoids unnecessary full table scans, uses indexes to speed up queries, uses the monitoring tools that come with the distributed database system to monitor the performance indicators of database throughput, response time, CPU usage, and memory usage, and tunes the database configuration, indexes, and partitioning strategies based on the monitoring results to improve the overall performance of the system; The nursing quality analysis module conducts nursing assessment on patients based on pre-processed medical care data, analyzes the patient's current treatment status and deviations from the nursing plan, and ensures the completeness and accuracy of nursing records; The nursing auxiliary decision support module combines the nursing quality assessment results to identify the defects in the nursing plan and provide decision support to optimize the nursing plan, achieve homogeneous nursing, improve the quality of nursing services, ensure patient safety, and improve the scientificity and accuracy of nursing decisions; The data visualization module displays the analysis results to medical staff in the form of charts, images, and animations, presenting the relationships and trends between the data, and helping medical staff quickly understand the data analysis results.

[0019] The second embodiment is based on the first embodiment. Figure 3 , Figure 4 As shown in the nursing quality analysis module, the nursing assessment process includes: Traverse the pre-processed medical care data, including nursing records, doctor's orders, examination results, and vital signs data, integrate all the patient's medical care information to form a complete nursing medical record, match the patient's nursing record with the standard nursing plan, check whether the nursing operation is carried out according to the nursing plan, and then evaluate whether the nursing activities received by the patient are sufficient and timely, and whether they meet the nursing standards. According to the nursing standards, determine the associated nursing indicators for nursing quality evaluation, which are patient satisfaction, nursing error rate, nursing response time, and nursing expected recovery deviation, and quantitatively score the nursing indicators of patient satisfaction and nursing expected recovery deviation. Combined with the nursing error rate and nursing response time, the nursing quality evaluation coefficient is calculated through comprehensive analysis to reflect the overall situation of nursing quality. According to the nursing quality evaluation coefficient, different nursing quality levels are preset, which are low nursing quality level, medium nursing quality level, and high nursing quality level, and the corresponding evaluation threshold is matched for each nursing quality level. Based on the determined nursing quality level and the value of the nursing quality evaluation coefficient, analyze the problems and deficiencies in the nursing process, and evaluate the current treatment situation of the patient and the deviation of nursing quality. Furthermore, the calculation process of the nursing quality evaluation coefficient is: Data on patient satisfaction, nursing error rate, nursing response time, and nursing expected recovery deviation were extracted, and the positive influencing factors of the nursing error rate were calculated. The nursing error rate was converted into a positive influencing factor. The lower the error rate, the closer it is to 1, the higher the nursing safety. The joint impact of patient satisfaction score and nursing error rate was calculated. The joint impact of nursing safety and patient satisfaction was analyzed, and the joint impact was divided by the nursing response time. The impact of response time was calculated to measure the impact of response speed on nursing quality. The shorter the response time, the The larger the value, the better the nursing responsiveness. The square term of the expected recovery deviation score is calculated to measure the impact of the nursing expected recovery deviation. The larger the deviation, The larger the value is, the greater the negative impact on the nursing quality. The impact of response time and the impact of expected recovery deviation are added to obtain a comprehensive impact value. The square root of the comprehensive impact value is taken to obtain a value between 0 and 1. The preliminary evaluation results of nursing quality are obtained, and the exponential decay function is used to process the impact of patient satisfaction. The decay effect of patient satisfaction is calculated. The higher the satisfaction, the smaller the decay. The preliminary evaluation results obtained by the square root are multiplied by the decay effect of patient satisfaction to obtain the final nursing quality evaluation coefficient, which reflects the overall situation of nursing quality. The range is between 0 and 1. The higher the value, the better the nursing quality. Furthermore, the calculation formula of the nursing quality evaluation coefficient is: ; in, is the nursing quality evaluation coefficient, Rate patient satisfaction. The nursing error rate indicates the rate of errors in the nursing process and is used to measure the safety of nursing. For nursing response time, The expected recovery deviation score is used to measure the deviation between the patient's actual recovery and the expected recovery plan. The value range is from 0 to 1, where 0 indicates very poor nursing quality and 1 indicates very good nursing quality. increase, reduction, The reduction and of reduction, The value of tends to 1, indicating an improvement in the quality of care; Get the value of the nursing quality evaluation coefficient and the preset evaluation threshold of the nursing quality level to match the three-level nursing quality level, which are: Low quality of care rating: ; Indicates that there are significant problems in nursing services that require immediate attention and improvement. Possible problems include low patient satisfaction, high nursing error rate, slow response time, and large deviation from nursing expected recovery. It is necessary to conduct a comprehensive review of the nursing process, improve the professional training of nursing staff, optimize the allocation of nursing resources, and improve patient communication and feedback mechanisms; Medium care quality level: ; Indicates that the quality of nursing services is average and there is room for improvement. There may be some room for improvement, such as low satisfaction of some patients, occasional nursing errors, and room for optimization of response time. We should improve the nursing process in a targeted manner, improve the professional skills of nursing staff, strengthen nursing quality monitoring, and improve patient satisfaction; High quality of care level: ; Indicates that the quality of nursing services is good, close to or at high standards, and the overall performance is good, but there may still be some minor problems or room for improvement. We will continue to monitor and optimize the nursing process, maintain high standards of nursing service quality, and encourage nursing innovation and continuous improvement; in, is the nursing quality evaluation coefficient, is the lower threshold corresponding to the medium nursing quality level and the upper threshold corresponding to the low nursing quality level, is the lower threshold corresponding to the high nursing quality level and the upper threshold corresponding to the medium nursing quality level, , ; In the nursing decision support module, the process of optimizing nursing plans includes: Based on the nursing needs and rehabilitation needs of patients, a standardized nursing knowledge base is established, which includes evaluation criteria for nursing assessment, nursing problems, and nursing measures. The actually implemented nursing plans are compared with the standardized nursing knowledge base to identify differences and deficiencies in nursing plans. Combined with the results of nursing quality assessment, the problems and defects in the implementation of nursing plans are analyzed to determine the nature and severity of the problems. Based on the analysis results, targeted decision-making suggestions are provided to nursing staff. The suggestions include adjusting nursing assessment methods, modifying nursing goals, and optimizing nursing measures. Based on the decision-making suggestions, the nursing plans are revised and optimized to ensure that the optimized nursing plans are more in line with patient needs, nursing standards, and nursing knowledge base requirements.

[0020] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A medical care data management system based on big data computing, characterized in that: The system includes a data collection module, a data security module, a data storage module, a nursing quality analysis module, a nursing auxiliary decision support module and a data visualization module, wherein the modules are connected by electrical signals; The data collection module is used to collect medical care data from multiple sources such as patient information systems, electronic medical records, medical equipment, and nursing records, and to perform preprocessing operations on the collected medical care data; The data security module protects the security of medical care data during transmission, storage and processing through encryption, access control and data backup; The data storage module uses a distributed database to store preprocessed data; The nursing quality analysis module performs nursing assessment on the patient based on the pre-processed medical nursing data, and analyzes the patient's current treatment status and deviations from the nursing plan; The nursing auxiliary decision support module, combined with the nursing quality assessment results, identifies the deficiencies in the nursing plan, provides decision support, and optimizes the nursing plan; The data visualization module displays the analysis results to medical staff in the form of charts, images, and animations.

2. A medical care data management system based on big data computing according to claim 1, characterized in that: In the data collection module, the collection and preprocessing process of medical care data includes: The sources of medical care data collection are clarified, namely, patient information system, electronic medical records, medical equipment, and nursing records. Among them, the patient information system includes the patient's personal information, medical records, and allergy history. The electronic medical record records the patient's detailed medical history, diagnostic information, examination results, and treatment plan. Medical equipment is used to output real-time monitoring data generated by electrocardiographs and ultrasound machines. Nursing records are data recorded by nurses during daily care for patients, including vital signs, diet, and medication records. Connect to various data sources through API interfaces and use ETL tools to extract medical care data from various data sources in real time; Preprocess the extracted medical care data, including data cleaning, data conversion, data integration and data standardization steps; Conduct a quality assessment on the pre-processed medical care data, evaluate the accuracy, completeness and consistency indicators of the data, calculate the data quality score, and analyze the quality level of medical care after pre-processing.

3. A medical care data management system based on big data computing according to claim 2, characterized in that: The calculation process of the data quality score is as follows: Collect the accuracy score, consistency score, and completeness score of each data source, and determine the baseline accuracy score and maximum accuracy score of each data source; For each data source, based on its accuracy score, the baseline accuracy score and the maximum accuracy score, calculate its accuracy deviation, obtain the accuracy deviation function, and calculate the root mean square error of the accuracy deviations of all data sources; Based on the integrity score of the data source, calculate the impact of the integrity score on data quality, and use a logical function to calculate the impact of the consistency score on data quality; The data quality score is obtained by combining the calculation results of the accuracy score, completeness score and consistency score.

4. A medical care data management system based on big data computing according to claim 3, characterized in that: The calculation formula of the data quality score is: ； in, is the data quality score, For the The accuracy score of each data source, For the The baseline accuracy scores of the data sources, For the The maximum accuracy score of the data sources is used to normalize the accuracy score. For the The consistency score of each data source, For the The integrity score of the data source is the total number of data sources, The value range is [0,1].

5. A medical care data management system based on big data computing according to claim 4, characterized in that: The data security module specifically includes: Use symmetric and asymmetric encryption algorithms to encrypt sensitive data. For fast encryption of large amounts of data, symmetric encryption algorithms use the same key for encryption and decryption. For key distribution and digital signature scenarios, asymmetric encryption algorithms use public and private key pairs, with the public key used for encryption and the private key used for decryption. During the data transmission process, the SSL security protocol is used to encrypt the data, and when the medical care data is stored, the sensitive fields of the patient's personal information and diagnosis results are encrypted and stored; The multi-factor authentication method of username / password combination and biometric recognition is used to authenticate the user's identity, and different access rights are granted to each role according to the division of labor among doctors, nurses and managers. At the same time, all access behaviors are monitored and recorded; Develop a regular backup plan and perform multiple backups of healthcare data, storing the data in different locations; After the backup is completed, verify the backed up medical care data and perform recovery tests of the backup data regularly.

6. A medical care data management system based on big data computing according to claim 5, characterized in that: In the data storage module, the storage process of the pre-processed data includes: Write the pre-processed medical care data in batches into a distributed database system based on Hadoop HDFS, and shard and distribute the medical care data to multiple nodes; Create indexes for frequently queried fields in medical care data, compress stored medical care data, and optimize SQL query statements based on query requirements; Use the monitoring tools provided by the distributed database system to monitor the performance indicators of database throughput, response time, CPU usage, and memory usage, and tune the database configuration, indexing, and partitioning strategies based on the monitoring results.

7. A medical care data management system based on big data computing according to claim 6, characterized in that: In the nursing quality analysis module, the nursing assessment process includes: Traverse the pre-processed medical care data, including nursing records, doctor's orders, examination results, and vital signs data, integrate all the patient's medical care information to form a complete nursing medical record; Match the patient's nursing records with the standard care plan to check whether the nursing operations are carried out in accordance with the care plan, and then evaluate whether the nursing activities received by the patient meet the nursing standards; According to the nursing standards, the associated nursing indicators for nursing quality evaluation are determined, namely patient satisfaction, nursing error rate, nursing response time and nursing expected recovery deviation. The nursing indicators of patient satisfaction and nursing expected recovery deviation are quantitatively scored, and the nursing quality evaluation coefficient is calculated by comprehensive analysis combined with nursing error rate and nursing response time to reflect the overall situation of nursing quality. According to the nursing quality evaluation coefficient, different nursing quality levels are preset, namely low nursing quality level, medium nursing quality level and high nursing quality level, and the corresponding evaluation threshold is matched for each nursing quality level; Based on the determined nursing quality level and the value of the nursing quality evaluation coefficient, analyze the problems and deficiencies in the nursing process, and evaluate the deviations between the patient's current treatment status and nursing quality.

8. A medical care data management system based on big data computing according to claim 7, characterized in that: The calculation process of the nursing quality evaluation coefficient is: Extract data on patient satisfaction, nursing error rate, nursing response time, and nursing expected recovery deviation, and calculate the positive influencing factor of the nursing error rate, and transform the nursing error rate into a positive influencing factor; Calculate the joint impact of patient satisfaction score and nursing error rate to analyze the joint impact of nursing safety and patient satisfaction, and divide the joint impact by nursing response time to calculate the impact of response time and measure the impact of response speed on nursing quality; The impact of nursing expected recovery deviation was measured by calculating the square term of expected recovery deviation score, and the impact of response time and expected recovery deviation were added together to obtain a comprehensive impact value. Take the square root of the comprehensive impact value to obtain the preliminary evaluation results of nursing quality, and use the exponential decay function to process the impact of patient satisfaction and calculate the decay impact of patient satisfaction; The preliminary evaluation result obtained by the square root is multiplied by the attenuation effect of patient satisfaction to obtain the final nursing quality evaluation coefficient, which reflects the overall situation of nursing quality.

9. A medical care data management system based on big data computing according to claim 8, characterized in that: The calculation formula of the nursing quality evaluation coefficient is: ； in, is the nursing quality evaluation coefficient, Rate patient satisfaction. The nursing error rate indicates the rate of errors in the nursing process and is used to measure the safety of nursing. For nursing response time, The expected recovery deviation score is used to measure the deviation between the patient's actual recovery and the expected recovery plan. The value range of is 0 to 1, where 0 indicates very poor quality of care and 1 indicates very good quality of care; The values ​​of the nursing quality evaluation coefficient and the preset evaluation thresholds of the nursing quality levels are obtained to match the three-level nursing quality levels, which are: Low quality of care rating: ; Medium care quality level: ; High quality of care level: ; in, is the nursing quality evaluation coefficient, is the lower threshold corresponding to the medium nursing quality level and the upper threshold corresponding to the low nursing quality level, is the lower threshold corresponding to the high nursing quality level and the upper threshold corresponding to the medium nursing quality level, , .

10. A medical care data management system based on big data computing according to claim 9, characterized in that: In the nursing auxiliary decision support module, the process of optimizing the nursing plan includes: Based on nursing needs and patient rehabilitation needs, a standardized nursing knowledge base is established, including evaluation criteria for nursing assessment, nursing problems, and nursing measures; Compare the actual nursing plan with the standardized nursing knowledge base to identify the differences and deficiencies in the nursing plan, and analyze the problems and defects in the implementation of the nursing plan in combination with the results of the nursing quality assessment to determine the nature and severity of the problems; Based on the analysis results, targeted decision-making recommendations are provided to nursing staff, including adjusting nursing assessment methods, modifying nursing goals, optimizing nursing measures, and revising and optimizing nursing plans based on decision-making recommendations.

Images