A care management system for multi-party information sharing

Abstract

The application discloses a kind of nursing management systems for multi-party information sharing, it is related to information sharing technical field, the system includes patient information management module, nursing plan management module, nursing record management module, nursing quality evaluation module and information sharing determination module;Patient information management module uses distributed database technology, the basic information of patient, medical history and treatment scheme are stored and managed in concentration, synchronous support data retrieval and query, the sensitive data of patient is encrypted processing;Its technical key points are: introduce nursing difficulty coefficient as correction value, can be more fair, objectively evaluate nursing quality, it helps to distinguish the nursing quality under different nursing difficulties, also encourages nursing staff to pay more attention to difficult nursing patient, strive to improve their nursing quality, to improve the level of nursing service as a whole;And according to the idle condition of nursing agency, nursing staff is intelligently dispatched, realizes the optimal allocation of nursing resources.

Description

Technical Field

[0001] This invention relates to the field of information sharing technology, specifically to a nursing management system for multi-party information sharing. Background Technology

[0002] Information sharing refers to the exchange and sharing of information and information products between information systems at different levels and in different departments;

[0003] In hospital nursing management, information sharing specifically refers to the sharing and transmission of work-related information between the hospital's internal nursing department and other departments, as well as among nursing staff. This includes patient information, nursing plans, and nursing records, aiming to break down information barriers and achieve the free flow and full utilization of information. For example, through a nursing information system, nursing staff can obtain real-time information such as the patient's latest condition, medical orders, and examination results, thereby enabling them to respond quickly and adjust nursing plans. At the same time, information sharing also helps promote interdisciplinary collaboration between the nursing team and other medical team members, jointly providing patients with more comprehensive and high-quality medical services.

[0004] An existing application with application number 202311231719.1, entitled "A Nursing Management System for Multi-Party Information Sharing," describes a system comprising a cloud information sharing platform that is communicatively connected to multiple regional medical terminals. Each regional medical terminal includes a central medical node and multiple sub-nodes. These regional medical terminals are used to obtain nursing information and nursing characteristic information, and to grant primary and secondary authorizations for information sharing within the region. The cloud information sharing platform is used to store nursing information and nursing characteristic information in the cloud, obtain overall nursing characteristic information, grant primary and secondary authorizations for cross-regional information sharing, determine the existence of damaged information, and repair damaged information. This invention's technical solution can effectively improve the integrity and security of nursing information and nursing characteristic information, effectively enhance the privacy protection of patients across regions, and reduce the risk of unauthorized leakage of nursing information. However, it does not consider how to assess the nursing quality of nursing staff, which hinders subsequent adjustments.

[0005] In light of the aforementioned documents and existing technology:

[0006] When establishing a nursing management system that shares information among multiple parties, for specific departments within a hospital, such as orthopedics, information sharing facilitates the sharing of relevant information about nursing staff, such as staffing, availability, and nursing quality. This allows for the deployment and allocation of personnel through the nursing management system. However, currently, the evaluation of nursing quality often results in unfair assessments of nursing staff due to differences in patients. Furthermore, the deployment or allocation of nursing staff is often done manually, which is not conducive to the optimal allocation of nursing resources. Summary of the Invention

[0007] (a) Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a nursing management system for multi-party information sharing. By introducing a nursing difficulty coefficient as a correction value, it can more fairly and objectively assess nursing quality. This helps to differentiate the quality of nursing care under different levels of difficulty and encourages nursing staff to pay more attention to patients requiring difficult care and strive to improve their nursing quality, thereby enhancing the overall level of nursing services. Furthermore, it intelligently dispatches nursing staff based on the availability of nursing facilities, achieving optimized allocation of nursing resources and solving the problems mentioned in the background technology.

[0009] (II) Technical Solution

[0010] To achieve the above objectives, the present invention provides the following technical solution:

[0011] A nursing management system for multi-party information sharing includes:

[0012] The patient information management module uses distributed database technology to centrally store and manage patients' basic information, medical history, and treatment plans, while simultaneously supporting data retrieval and query, and encrypting sensitive patient data.

[0013] The nursing plan management module, based on big data analytics, develops corresponding nursing plans according to the patient's condition and needs.

[0014] The nursing record management module records the nursing process, generates nursing records, and extracts key information from the nursing records through natural language processing technology. It also retrieves the condition parameter set of the target patient, constructs a weighted calculation model, and generates the nursing difficulty coefficient of the target patient.

[0015] The nursing quality assessment module obtains the nursing service response time and the proportion of rehabilitation training time under the conditions of the day. Based on the patient satisfaction in the key information in the nursing record, combined with the nursing difficulty coefficient of the target patient, a function calculation model is constructed to generate the corresponding nursing quality prediction index under the conditions of the day.

[0016] The information sharing and judgment module receives the daily nursing quality prediction indicators for the target patient, builds a rule engine, and issues an early warning signal when the nursing quality prediction indicators are lower than the preset standard threshold. If the number of early warning signals issued exceeds M / 10 within a preset time period M, a replacement instruction is triggered, and a strategy to replace nursing staff is executed.

[0017] Furthermore, the patient's basic information includes the patient's age, gender, and ID number; the patient's sensitive data includes the patient's ID number and medical record content.

[0018] Furthermore, the process of developing a corresponding nursing care plan is as follows:

[0019] Data collection and integration: Collect patients' diagnostic information, rehabilitation progress data, and basic patient information. After data cleaning and integration, data warehouse technology is used for data storage.

[0020] Data mining and analysis: Using association rule mining techniques, identify the relationships between different stored data items; group patients with similar rehabilitation needs through cluster analysis; predict patients' rehabilitation time based on their historical rehabilitation data and machine learning algorithms;

[0021] Nursing plan development: Based on the patient's nutritional needs and dietary preferences, and combined with nutritional recommendations obtained from big data analysis, a dietary plan is developed for the patient; based on the patient's condition and medication history data, and combined with medication recommendations obtained from big data analysis, a medication plan is developed for the patient; based on the patient's lifestyle habits and health data, and combined with lifestyle recommendations obtained from big data analysis, a lifestyle management plan is developed for the patient.

[0022] Furthermore, the conditional parameters retrieved simultaneously for the target patient include: Barthel Index, age, and wound area.

[0023] Furthermore, the formula used to construct the weighted calculation model is as follows:

[0024]

[0025] In the formula, Ndc represents the nursing difficulty coefficient, α, β, and γ are all weighting coefficients, each ranging from [0, 1], Bi represents the Barthel index, A represents age, and A max Sa represents the maximum age threshold set, and Sa represents the area of ​​the trauma. max This indicates the maximum area of ​​the trauma set.

[0026] Furthermore, the nursing service response time is as follows: from the moment the target patient presses the demand button (t0) to the moment the corresponding nursing staff arrives at the target patient's vicinity (t1), the time required from t0 to t1 is collected, which is the nursing service response time; the rehabilitation training time ratio is as follows: the total time of rehabilitation training for the target patient on that day is recorded, and then the total time is divided by the total time of the day, and the ratio is the rehabilitation training time ratio; the patient satisfaction is the service rating of the target patient for the corresponding nursing staff on that day, with a rating range of [0, 10].

[0027] Furthermore, the formula used to construct the function computation model is as follows:

[0028]

[0029] In Equation (1), Ig represents the nursing quality prediction index, f(R) represents the decreasing function, g(T) represents the increasing function, and S represents patient satisfaction; in Equation (2), R represents the nursing service response time; in Equation (3), T represents the proportion of rehabilitation training time.

[0030] Furthermore, the strategy for changing caregivers is as follows:

[0031] If the current nursing facility is short of nursing staff, the replacement instruction will be shared with other nursing facilities;

[0032] When the number of nursing facilities with available caregivers is 0, manual reassignment will be carried out.

[0033] When there is only 1 nursing facility with available nursing staff, nursing staff will be transferred from the corresponding nursing facility with available nursing staff.

[0034] When the number of nursing facilities with available caregivers exceeds one, an identification mechanism is implemented.

[0035] Furthermore, the process of implementing the identification mechanism is as follows: screening nursing staff in several nursing institutions and prioritizing the deployment of nursing staff with the most nursing experience; among them, the nursing staff with the most nursing experience are those who have cared for patients whose nursing difficulty coefficient exceeds the threshold the most times.

[0036] (III) Beneficial Effects

[0037] This invention provides a nursing management system for multi-party information sharing, which has the following beneficial effects:

[0038] (1) This solution can significantly improve the efficiency and quality of nursing work, while effectively protecting the privacy and security of patients; the fast entry function of the electronic medical record system, combined with template selection and shortcut key operation, significantly improves the speed and accuracy of nursing staff in recording nursing information, reduces the time and errors of manual input, and makes nursing records more standardized and complete;

[0039] (2) This scheme constructs a weighted calculation model by simultaneously retrieving the patient's Barthel index, age and wound area, and generates a nursing difficulty coefficient, which provides nursing staff with an objective and quantitative assessment basis, helps to rationally allocate nursing resources and improve nursing quality, and also provides data correction guidance for subsequent nursing quality assessment.

[0040] (3) This solution integrates electronic medical record system, natural language processing technology, data desensitization technology and scientific weighted calculation model, which not only improves the efficiency and quality of nursing records, but also strengthens the ability to retrieve and utilize information, intelligent analysis to assist nursing decision-making, effectively protect patient privacy and scientifically assess nursing difficulty, providing strong support for improving the quality and efficiency of nursing services in orthopedic nursing and even the entire medical industry.

[0041] (4) This scheme introduces a nursing difficulty coefficient as a correction value, which can more fairly and objectively assess nursing quality. It helps to distinguish nursing quality under different nursing difficulties and avoid unfair evaluation of nursing staff due to differences in patients themselves. At the same time, it also encourages nursing staff to pay more attention to patients who are difficult to care for and strive to improve their nursing quality, thereby improving the overall level of nursing services.

[0042] (5) This solution can monitor nursing quality prediction indicators in real time and issue an early warning signal when the indicators are lower than the standard threshold, providing timely decision support for managers; the preset threshold for the number of early warnings within the time period further ensures the scientific and rational nature of the decision; when the nursing quality is not up to standard, the system can automatically trigger a replacement instruction and intelligently dispatch nursing staff according to the availability of nursing institutions, thereby achieving optimized allocation of nursing resources; by using the highest nursing experience as the basis for dispatch priority, nursing staff are motivated to continuously improve their nursing skills and experience. Attached Figure Description

[0043] Figure 1 This is a modular schematic diagram of the nursing management system in this invention;

[0044] Figure 2 This is a schematic diagram illustrating the sharing of the nursing management system with other nursing institutions in this invention;

[0045] Figure 3 This is a flowchart of the operation of the nursing management system in this invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0047] Example 1:

[0048] Please see Figures 1 to 2This embodiment provides a nursing management system for multi-party information sharing. The system is primarily used in hospital orthopedics departments for the nursing management of various orthopedic patients.

[0049] The system overview and research and development direction are as follows:

[0050] This nursing management system aims to leverage big data services and data mining technologies to enable multi-party information sharing within a hospital department (e.g., orthopedics), thereby improving nursing efficiency, ensuring patient safety, and optimizing the quality of nursing services. The system integrates multiple functional modules, including patient information management, nursing plan management, nursing record management, and nursing quality assessment, and provides a scientific basis for nursing decisions through data integration and mining.

[0051] Therefore, the nursing management system includes a patient information management module, a nursing plan management module, a nursing record management module, a nursing quality assessment module, and an information sharing determination module that run sequentially.

[0052] Among them, the nursing record management module and the nursing quality assessment module are the core functional modules of this system;

[0053] The following is a description of each of the sequentially running functional modules:

[0054] Patient Information Management Module:

[0055] Distributed database technology is used to centrally store and manage patients' basic information, medical history, and treatment plans, while simultaneously supporting data retrieval and query. Sensitive patient data is encrypted using encryption technology.

[0056] Basic patient information should include at least the patient's age, gender, and ID number;

[0057] Sensitive patient data includes the patient's ID number and medical record content;

[0058] Among them, the core advantages of distributed database technology are:

[0059] Distributed data storage: Distributed databases distribute patient data (i.e., basic patient information, medical history, and treatment plans) across multiple physical nodes, which may be located in different geographical locations. This distribution improves the system's scalability and fault tolerance; even if one node fails, other nodes can continue to provide services, ensuring data availability and system stability. Load balancing: By intelligently allocating query and storage tasks to different nodes, distributed databases can utilize resources more effectively, improving system response speed and throughput. Data consistency: Although the data is stored in a distributed manner, distributed databases ensure that the data on all nodes is up-to-date and consistent through replication and synchronization mechanisms, avoiding data conflicts and errors.

[0060] Implementation method:

[0061] Distributed NoSQL databases such as MongoDB and Cassandra can be used to handle large amounts of unstructured data and provide high availability and scalability; sharding technology can be used to divide data into multiple parts according to certain rules and store them on different nodes; replication technology can be used to create multiple copies of the data to improve data reliability and read speed.

[0062] Technical features of fast data retrieval and query:

[0063] Index optimization: Create indexes for frequently used query fields, such as patient ID, name, and appointment date, to speed up the query process; Query optimizer: Utilize the query optimizer to analyze and rewrite SQL query statements and select the optimal execution plan; Caching mechanism: Use caching technologies (such as Redis and Memcached) to store frequently accessed data, reducing the number of direct database accesses and improving query efficiency;

[0064] When using encryption technology for encryption processing, static data encryption methods or technologies are used for sensitive patient data, so that even if the database is illegally accessed, the original data cannot be read directly;

[0065] In addition, encryption processing also includes:

[0066] Data transmission encryption: SSL / TLS protocol is used to encrypt the data transmission process to ensure data security during transmission; Access control: Strict access control policies are implemented, allowing only authorized users to access specific data; Audit logs: All database access operations are recorded for tracing and investigation in the event of a security incident;

[0067] Choice of encryption algorithm:

[0068] Strong encryption algorithms such as AES (Advanced Encryption Standard) can be used, as they are widely recognized as secure and efficient encryption algorithms. For scenarios requiring even higher security, advanced technologies such as homomorphic encryption or quantum encryption can be considered.

[0069] In summary, the patient information management module, by employing distributed database technology, optimizing data retrieval and query mechanisms, and implementing strict encryption and privacy protection measures, ensures efficient, secure, and reliable management of patient information. This not only improves the efficiency and quality of medical services but also enhances patients' trust in and satisfaction with the medical system.

[0070] Nursing plan management module:

[0071] Based on big data analytics, we develop corresponding nursing plans according to the patient's condition and needs.

[0072] Based on the patient's condition and needs, personalized care plans are developed using big data analytics, including nutritional management, medication management, and lifestyle management. The following will explain in detail how big data analytics is used to obtain this personalized care plan, and provide relevant examples:

[0073] I. Application of Big Data Analytics in Personalized Care Planning

[0074] 1. Data collection and integration

[0075] Data Sources: For orthopedic patients, the system collects diagnostic information (such as fracture type, surgical records, etc.) from the electronic medical record system, rehabilitation progress data (such as X-rays, joint range of motion measurements, etc.) from medical testing equipment, daily activity data (such as steps, standing and walking time, etc.) from patient self-monitoring devices, and basic information such as the patient's age, gender, and lifestyle habits. Data Integration: The system cleans and integrates the above data to ensure its accuracy and timeliness. Using data warehouse technology, all relevant patient information is stored uniformly, providing a solid foundation for subsequent data analysis.

[0076] 2. Data Mining and Analysis

[0077] Association analysis: Utilizing association rule mining techniques to discover relationships between different data items; for example, identifying the promoting or detrimental effects of certain activities on fracture healing; Cluster analysis: Grouping orthopedic patients with similar rehabilitation needs or problems, such as by fracture type, age, or rehabilitation stage, to provide more specific rehabilitation recommendations for each group; Predictive analysis: Based on patients' historical rehabilitation data and machine learning algorithms, predicting patients' rehabilitation time and potential rehabilitation obstacles, such as predicting when patients will be able to return to normal walking or work;

[0078] 3. Development of personalized care plans

[0079] Nutritional Management: Based on the patient's nutritional needs and dietary preferences, and combined with nutritional recommendations derived from big data analysis (such as controlling calorie intake and increasing protein intake), a personalized dietary plan is developed for the patient. For example, the system recommends foods rich in nutrients that help bone healing, such as calcium and vitamin D, including milk, eggs, and fish. Medication Management: Based on the patient's condition and medication history data, and combined with medication recommendations derived from big data analysis (such as drug dosage adjustments and drug interaction warnings), a personalized medication plan is developed for the patient. For example, for a patient with a leg fracture, the system can recommend appropriate antihypertensive drugs and dosages based on their blood pressure control and drug tolerance. Lifestyle Management: Based on the patient's lifestyle habits and health data (including BMI, heart rate, and dietary records), and combined with lifestyle recommendations derived from big data analysis (such as increasing exercise and improving sleep quality), a personalized lifestyle management plan is developed for the patient. For example, for obese patients, the system can recommend appropriate exercise methods and intensities based on their physical condition and exercise preferences.

[0080] II. Examples

[0081] Take an elderly orthopedic patient who has just undergone hip replacement surgery as an example:

[0082] Data collection and integration: The system collects patients' surgical records, postoperative rehabilitation progress data (such as fracture healing status shown on X-rays, joint range of motion measurements, etc.), patients' daily activity data (such as steps and standing time monitored by smart devices), and patients' basic information (such as age, gender, weight, etc.).

[0083] Data mining and analysis: System analysis revealed that the slow recovery progress of patients was related to inadequate postoperative pain management, lack of effective rehabilitation exercises, and insufficient nutritional intake.

[0084] Personalized care plan development:

[0085] Nutritional Management: The system recommends that patients increase their intake of protein and vitamin D to promote bone and muscle healing, such as by recommending that patients drink more milk and eat more eggs and fish, and develop a personalized dietary plan; Medication Management: The system advises doctors to adjust the patient's pain medication regimen to ensure that the patient can effectively manage pain during the recovery process while avoiding drug dependence; Lifestyle Management: The system develops a set of rehabilitation exercise plans for the patient, including joint mobility exercises in bed, standing and walking training, etc., and recommends that the patient use a walking aid to reduce the burden on the surgical site; at the same time, the system also reminds the patient to pay attention to maintaining correct sitting and standing postures in daily life and avoid maintaining the same posture for a long time to avoid discomfort.

[0086] Through the above steps, the system uses big data analytics to develop a personalized care plan for this elderly orthopedic patient who underwent hip replacement surgery, aiming to help the patient recover faster, reduce complications, and improve their quality of life.

[0087] Nursing record management module:

[0088] Record the nursing process, generate nursing records, and extract key information from the nursing records using natural language processing technology. Simultaneously retrieve the condition parameter set of the target patient, construct a weighted calculation model, and generate the nursing difficulty coefficient of the target patient.

[0089] The nursing process was recorded using the hospital's electronic medical record system.

[0090] Rapid data entry: The electronic medical record system provides nurses with a convenient data entry interface, supporting the rapid entry of nursing information for orthopedic patients, such as wound condition, recovery progress, Barthel index, and patient satisfaction, through template selection and shortcut key operations. This helps nurses complete nursing record work efficiently, reducing the time and errors of manual input.

[0091] Query function: The electronic medical record system supports quick queries by patient name, hospital number, diagnosis, nursing date and other conditions, which makes it convenient for nursing staff to view the patient's historical nursing records at any time and understand the changes in the patient's condition and treatment progress;

[0092] Intelligent Analysis: The electronic medical record system can automatically perform intelligent analysis on the data in nursing records, generate statistical reports, trend charts, etc., to help nursing staff assess the patient's recovery effect, identify potential problems in a timely manner, and provide data support for the development of personalized nursing plans;

[0093] The following explains how natural language processing techniques extract key information:

[0094] Natural Language Processing (NLP) technology can automatically parse the text content in nursing records and extract key information, including the patient's chief complaint, the doctor's diagnosis, and the nurse's actions. This is particularly important for orthopedic nursing, as orthopedic nursing records often contain a large amount of technical terminology and descriptive text. NLP technology can help nurses quickly obtain the information they need. For example, in orthopedic nursing records, NLP technology can automatically identify key information such as "good fracture healing," "increased joint mobility," and "patient satisfaction score of 9," providing support for assessing the patient's rehabilitation effect.

[0095] In addition, it also includes secondary data anonymization techniques to process sensitive information.

[0096] In orthopedic nursing records, sensitive information such as patients' names and ID numbers needs to be strictly protected. Data anonymization technology can encrypt or replace this sensitive information to ensure that patient privacy is not leaked during information sharing. For example, the system can replace the patient's name with an anonymous identifier (such as "Patient A") and hash the ID number, so that even if the data is illegally obtained, it cannot be directly associated with a specific patient.

[0097] For example (using orthopedic patients as an example)

[0098] Suppose a patient named "Li Hua" is admitted to the hospital for a right femoral neck fracture. The nursing staff records the patient's care process using an electronic medical record system as follows: Record entry: "November 10, 2024, XX, 3rd day post-operatively for right femoral neck fracture. Wound is clean and dry, no redness, swelling, or oozing. Patient satisfaction score: 9 points. Patient has been instructed to perform joint range of motion exercises in bed." NLP extracts key information: The system automatically extracts key information such as "3rd day post-operatively for right femoral neck fracture," "clean and dry wound," "satisfaction score: 9 points," and "joint range of motion exercises in bed," providing a basis for subsequent nursing assessments and planning. Data anonymization: When sharing this nursing record with other medical staff or external institutions, the system replaces "XX" with an anonymous identifier (e.g., "Patient ID: 001") and performs hash encryption on sensitive information such as the patient's ID number to ensure patient privacy.

[0099] By applying the above technologies, the nursing record management module can significantly improve the efficiency and quality of orthopedic nursing work, while effectively protecting patient privacy and security. The electronic medical record system's rapid entry function, combined with template selection and shortcut key operation, significantly improves the speed and accuracy of nursing staff in recording nursing information, reduces the time and errors of manual input, and makes nursing records more standardized and complete.

[0100] The set of conditional parameters retrieved simultaneously for the target patient includes: Barthel index, age, and wound area;

[0101] It should be noted that the Barthel Index is used to assess a patient's ability to perform daily activities. The lower the index, the higher the patient's dependence and the greater the difficulty of care. Age: Elderly patients are generally more difficult to care for because they may have multiple chronic diseases and declining physical function. Wound area: The larger the wound area, the longer the recovery time and the higher the required care time and quality, and therefore the greater the difficulty of care.

[0102] The formula used to construct the weighted calculation model is as follows:

[0103]

[0104] In the formula, Ndc represents the nursing difficulty coefficient, α, β, and γ are all weighting coefficients, each ranging from [0, 1], Bi represents the Barthel index, ranging from [0, 100], and A represents age. max This represents the maximum age threshold, typically set to 100. Sa represents the area of ​​the wound. max This represents the maximum area of ​​the injury, typically set to 1.7 m², which is the surface area of ​​an adult's skin.

[0105] It's important to note the following: Barthel Index: By subtracting the Barthel Index from 100 and dividing by 100, we convert the Barthel Index into a value between 0 and 1, where 1 represents complete dependence and 0 represents no dependence. This value reflects the patient's self-care ability in daily living activities; the lower the self-care ability, the greater the difficulty of care. Age: Dividing the patient's actual age by a maximum age threshold yields a value between 0 and 1, reflecting the impact of age on the difficulty of care. Generally, the older the patient, the worse their physical function may be, and the greater the difficulty of care. Wound Area: Dividing the patient's actual wound area by a maximum wound area threshold also yields a value between 0 and 1, reflecting the impact of wound area on the difficulty of care; the larger the wound area, the greater the difficulty of care. Weighting Coefficient: By setting different weighting coefficients, we can adjust the relative importance of the Barthel Index, age, and wound area in the calculation of the care difficulty coefficient.

[0106] The weighting coefficients are determined using the coefficient of variation method, which assigns weights to each indicator based on the degree of variation between the current value and the target value. If the numerical difference of an indicator is large, it can clearly distinguish each evaluated object, indicating that the indicator has rich discriminative information and should therefore be given a larger weight. Conversely, if the numerical difference of each evaluated object on a certain indicator is small, then the indicator's ability to distinguish each evaluated object is weak, and therefore it should be given a smaller weight. This method directly utilizes the information contained in each indicator to calculate the weight of the indicator, thus possessing objectivity.

[0107] By simultaneously retrieving patients' Barthel Index, age, and wound area, a weighted calculation model is constructed to generate a nursing difficulty coefficient. This provides nursing staff with an objective and quantitative assessment basis, which helps to rationally allocate nursing resources and improve nursing quality. It also provides data correction guidance for subsequent nursing quality assessments.

[0108] The nursing record management module integrates electronic medical record systems, natural language processing technology, data anonymization technology, and scientific weighted calculation models. This not only improves the efficiency and quality of nursing records but also enhances capabilities in information retrieval and utilization, intelligent analysis to assist nursing decisions, effective protection of patient privacy, and scientific assessment of nursing difficulty. It provides strong support for improving the quality and efficiency of nursing services in orthopedic nursing and even the entire medical industry.

[0109] Nursing quality assessment module:

[0110] The system obtains the nursing service response time, the proportion of rehabilitation training time, and the patient satisfaction based on key information in the nursing records, combined with the nursing difficulty coefficient of the target patient, to construct a function calculation model and generate the corresponding nursing quality prediction indicators under the conditions of the day.

[0111] Among them, the response time for nursing services is:

[0112] The time from when the target patient presses the demand button is recorded as t0, and the time when the corresponding nursing staff arrives near the target patient is recorded as t1. The time required from t0 to t1 is the nursing service response time. The demand button is the button located by the bedside in the hospital for making a call. The method for determining the arrival of the nursing staff near the target patient is to use existing monitoring cameras to monitor the time when the nursing staff enters the room where the target patient is located, which is represented as t1.

[0113] Rehabilitation training time percentage: Record the total time of rehabilitation training for the target patient on the same day, and then divide the total time by the day's duration, i.e., 24 hours. The ratio obtained is the rehabilitation training time percentage; Patient satisfaction: Indicates the target patient's service rating for the corresponding nursing staff on the same day, usually 0-10 points, with 10 points indicating very satisfied;

[0114] The formulas used to construct the function computation model are as follows:

[0115]

[0116] In Equation (1), Ig represents the nursing quality prediction index, f(R) represents the decreasing function, g(T) represents the increasing function, and S represents patient satisfaction; in Equation (2), R represents the nursing service response time; in Equation (3), T represents the proportion of rehabilitation training time.

[0117] The logic is explained as follows:

[0118] f(R) is a function that adjusts the response time R of nursing services. The addition of 1 avoids a denominator of 0. A shorter response time indicates higher nursing staff efficiency, thus leading to a higher nursing quality assessment value. Adjusting the response time using f(R) reflects this relationship. A higher proportion of rehabilitation training time indicates more time nurses invest in patient rehabilitation, resulting in a higher nursing quality assessment value. Adjusting the proportion of rehabilitation training time using g(T) reflects this relationship. Patient satisfaction is a crucial indicator directly reflecting nursing quality; higher satisfaction leads to a higher nursing quality assessment value. Different patients require different levels of nursing care. The nursing difficulty coefficient Ndc serves as a correction value, making the assessment value more fair and accurate. Higher difficulty results in a larger Ndc, leading to a relatively lower predicted nursing quality index.

[0119] The above formula design can comprehensively evaluate the nursing quality of nurses by taking into account multiple factors, including objective indicators (such as response time and the proportion of rehabilitation training time) as well as subjective indicators (such as patient satisfaction), and also corrected by the nursing difficulty coefficient, making the evaluation results more comprehensive and accurate.

[0120] This scheme, by constructing a function computation model, comprehensively considers multiple factors such as nursing service response time, the proportion of rehabilitation training time, patient satisfaction, and nursing difficulty coefficient, providing a comprehensive and objective basis for the assessment of nursing quality.

[0121] When assessing the quality of nursing care, it is indeed necessary to consider multiple factors, among which the patient's nursing difficulty coefficient serves as an important correction value when assessing the quality of nursing care.

[0122] For patients who are easy to care for, the nursing difficulty coefficient is lower. Therefore, when assessing the quality of care, the data should be combined with a small correction value. This does not mean that the quality of care for these patients is not important. Rather, it means that under the same conditions, patients who are easy to care for tend to get higher nursing quality scores, but this does not fully reflect the actual level of nursing staff.

[0123] Conversely, for patients who are difficult to care for, the nursing difficulty coefficient is higher. Therefore, a larger correction value needs to be given when assessing the quality of care. This is because patients who are difficult to care for often have more health problems and more complex nursing needs, which increases the difficulty and complexity of nursing work. In this case, even if the nursing quality score is relatively low, it may not mean that the nursing staff is not skilled, but rather that it is due to the difficulty of caring for the patient.

[0124] Therefore, introducing a nursing difficulty coefficient as a correction value can more fairly and objectively assess nursing quality. It helps to differentiate the quality of nursing care under different levels of difficulty, avoiding unfair evaluations of nursing staff due to differences in patients themselves. At the same time, it also encourages nursing staff to pay more attention to patients who are difficult to care for and strive to improve the quality of their care, thereby improving the overall level of nursing services.

[0125] In conclusion, using the patient's nursing difficulty coefficient as a correction value when assessing nursing quality is a scientific and reasonable approach. It helps to achieve a fair assessment of nursing quality and promotes the continuous improvement and development of nursing services.

[0126] Information sharing determination module:

[0127] The system receives the daily nursing quality prediction indicators for the target patient, builds a rule engine, and issues an early warning signal when the nursing quality prediction indicators are lower than the preset standard threshold. If the number of early warning signals issued exceeds M / 10 within a preset time period M, a replacement instruction is triggered, and a strategy to replace nursing staff is executed.

[0128] If the current nursing facility is short of nursing staff, the replacement instruction will be shared with other nursing facilities;

[0129] When the number of nursing facilities with available caregivers is 0, manual reassignment will be carried out.

[0130] When there is only 1 nursing facility with available nursing staff, nursing staff will be transferred from the corresponding nursing facility with available nursing staff.

[0131] When the number of nursing facilities with available nursing staff exceeds one, an identification mechanism is implemented to screen nursing staff within several nursing facilities and prioritize the deployment of nursing staff with the highest nursing experience; among them, the nursing staff with the highest nursing experience are those who have cared for the most patients whose nursing difficulty coefficient exceeds the threshold.

[0132] It should be noted that the standard threshold is set dynamically based on historical data. Historical data from medical institutions equipped with this nursing management system can be collected, and nursing quality prediction indicators for each nurse who achieves patient satisfaction of 8 points or above can be extracted. Several nursing quality prediction indicators can be selected, and the highest value among them can be used as the standard threshold. Alternatively, it can be set independently according to the actual situation.

[0133] The preset time period M is usually 30 days, or one month, and the value of M is a positive integer.

[0134] The threshold value is set independently based on the actual situation. It is used to determine whether the nursing difficulty coefficient exceeds the standard, that is, to determine the difficulty of nursing care for the corresponding patient. Exceeding the standard indicates that it is more difficult, while not exceeding it indicates that it is more simple.

[0135] Specifically, the information sharing and judgment module can monitor nursing quality prediction indicators in real time and issue early warning signals when the indicators are below the standard threshold, providing timely decision support for managers. The preset threshold for the number of early warnings within a time period further ensures the scientific and rational nature of the decision-making. When nursing quality fails to meet the standards, the system can automatically trigger a replacement instruction and intelligently dispatch nursing staff based on the availability of nursing facilities, achieving optimized allocation of nursing resources. By using the highest nursing experience as the basis for dispatch priority, nursing staff are motivated to continuously improve their nursing skills and experience, forming a good competitive atmosphere.

[0136] Example 2:

[0137] Please see Figure 3 Based on Example 1, this embodiment also provides a method for operating a nursing management system, including the following specific steps:

[0138] S1. It adopts distributed database technology to centrally store and manage patients' basic information, medical history and treatment plans, and supports data retrieval and query synchronously. It also encrypts sensitive patient data.

[0139] S2. Based on big data analysis technology, develop corresponding nursing plans according to the patient's condition and needs;

[0140] S3. Record the nursing process, generate nursing records, and extract key information from the nursing records through natural language processing technology. Simultaneously retrieve the condition parameter set of the target patient, construct a weighted calculation model, and generate the nursing difficulty coefficient of the target patient.

[0141] S4. Obtain the nursing service response time, rehabilitation training time ratio, and patient satisfaction based on key information in the nursing records, combined with the nursing difficulty coefficient of the target patient, construct a function calculation model, and generate the corresponding nursing quality prediction index under the conditions of the day.

[0142] S5. Receive the daily nursing quality prediction indicators for the target patient, build a rule engine, and issue an early warning signal when the nursing quality prediction indicators are lower than the preset standard threshold. If the number of early warning signals issued exceeds M / 10 within the preset time period M, a replacement instruction is triggered to execute the strategy of replacing nursing staff.

[0143] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0145] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A nursing management system for multi-party information sharing, the system comprising: The patient information management module uses distributed database technology to centrally store and manage patients' basic information, medical history, and treatment plans, while simultaneously supporting data retrieval and query, and encrypting sensitive patient data. The nursing plan management module, based on big data analytics, develops corresponding nursing plans according to the patient's condition and needs; its key feature is that it also includes: The nursing record management module records the nursing process, generates nursing records, and extracts key information from the nursing records through natural language processing technology. It also retrieves the condition parameter set of the target patient, constructs a weighted calculation model, and generates the nursing difficulty coefficient of the target patient. The nursing quality assessment module obtains the nursing service response time and the proportion of rehabilitation training time under the conditions of the day. Based on the patient satisfaction in the key information in the nursing record, combined with the nursing difficulty coefficient of the target patient, a function calculation model is constructed to generate the corresponding nursing quality prediction index under the conditions of the day. The information sharing and judgment module receives the daily nursing quality prediction indicators for the target patient, builds a rule engine, and issues an early warning signal when the nursing quality prediction indicators are lower than the preset standard threshold. If the number of early warning signals issued exceeds M / 10 within a preset time period M, a replacement instruction is triggered, and a strategy to replace nursing staff is executed.

2. The nursing management system for multi-party information sharing according to claim 1, characterized in that: Basic patient information includes the patient's age, gender, and ID number; sensitive patient data includes the patient's ID number and medical record content.

3. The nursing management system for multi-party information sharing according to claim 1, characterized in that: The process of developing a corresponding nursing care plan is as follows: Data collection and integration: Collect patients' diagnostic information, rehabilitation progress data, and basic patient information. After data cleaning and integration, data warehouse technology is used for data storage. Data mining and analysis: Using association rule mining techniques, identify the relationships between different stored data items; group patients with similar rehabilitation needs through cluster analysis; predict patients' rehabilitation time based on their historical rehabilitation data and machine learning algorithms; Nursing plan development: Based on the patient's nutritional needs and dietary preferences, and combined with nutritional recommendations obtained from big data analysis, a dietary plan is developed for the patient; based on the patient's condition and medication history data, and combined with medication recommendations obtained from big data analysis, a medication plan is developed for the patient; based on the patient's lifestyle habits and health data, and combined with lifestyle recommendations obtained from big data analysis, a lifestyle management plan is developed for the patient.

4. A nursing management system for multi-party information sharing according to claim 1, characterized in that: The set of conditional parameters retrieved simultaneously for the target patient includes: Barthel index, age, and wound area.

5. A nursing management system for multi-party information sharing according to claim 4, characterized in that: The formula used to construct the weighted calculation model is as follows: In the formula, Ndc represents the nursing difficulty coefficient, α, β, and γ are all weighting coefficients, each ranging from [0, 1], Bi represents the Barthel index, A represents age, and A max Sa represents the maximum age threshold set, and Sa represents the area of ​​the trauma. max This indicates the maximum area of ​​the trauma set.

6. A nursing management system for multi-party information sharing according to claim 5, characterized in that: Nursing service response time: The time from when the target patient presses the demand button is recorded as t0, and the time when the corresponding nursing staff arrives at the target patient's vicinity is recorded as t1. The time required from t0 to t1 is the nursing service response time. Rehabilitation training time percentage: Record the total time of rehabilitation training for the target patient on the same day, and then divide the total time by the time of the day. The ratio is the rehabilitation training time percentage; Patient satisfaction: The service rating of the target patient for the corresponding nursing staff on the same day. The rating range is [0, 10].

7. A nursing management system for multi-party information sharing according to claim 6, characterized in that: The formula used to construct the function computation model is as follows: In Equation (1), Ig represents the nursing quality prediction index, f(R) represents the decreasing function, g(T) represents the increasing function, and S represents patient satisfaction; in Equation (2), R represents the nursing service response time; in Equation (3), T represents the proportion of rehabilitation training time.

8. A nursing management system for multi-party information sharing according to claim 1, characterized in that: The strategy for changing caregivers is as follows: If the current nursing facility is short of nursing staff, the replacement instruction will be shared with other nursing facilities; When the number of nursing facilities with available caregivers is 0, manual reassignment will be carried out. When there is only 1 nursing facility with available nursing staff, nursing staff will be transferred from the corresponding nursing facility with available nursing staff. When the number of nursing facilities with available caregivers exceeds one, an identification mechanism is implemented.

9. A nursing management system for multi-party information sharing according to claim 8, characterized in that: The process of implementing the identification mechanism is as follows: screening nursing staff in several nursing institutions and prioritizing the deployment of nursing staff with the most nursing experience; among them, the nursing staff with the most nursing experience are those who have cared for patients whose nursing difficulty coefficient exceeds the threshold the most times.

Images