A real-time full-course information collection method for orthopedic patients

Through real-time monitoring and dynamic adjustment of data processing strategies, the problem of excessive load on hospital information systems when processing large amounts of orthopedic patient data is solved, ensuring the timely processing of key data and system stability, and improving the efficiency and quality of medical services.

CN118866220BActive Publication Date: 2024-11-29SICHUAN PROVINCIAL ORTHOPEDIC HOSPITAL (CHENGDU SPORTS HOSPITAL CHENGDU SPORTS TRAUMATOLOGY INST)
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411327921.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-24
Publication Date
2024-11-29
Estimated Expiration
2044-09-24

AI Technical Summary

Technical Problem

When processing large amounts of orthopedic patient data, hospital information systems are prone to degradation of system performance due to excessive load, which may lead to loss of key disease course data or processing delays, affecting the timeliness of medical decisions and the efficiency of medical services.

Method used

By monitoring the processing load of the hospital information system in real time, dynamically adjusting the processing strategy of the course data, and adopting a mechanism of dynamic basic data volume and importance weight coefficients, prioritizing the processing and retention of the most critical course data to ensure the accuracy and timeliness of medical decision-making , and reduce unnecessary data storage through data filtering, and improve system resource utilization.

Benefits of technology

Improve the processing efficiency of hospital information systems in the big data environment, avoid the risk of system overload and crashes, ensure the security and integrity of key data, improve the efficiency and quality of medical services, reduce redundant data storage, and optimize System resource use.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118866220B_ABST
    Figure CN118866220B_ABST
Patent Text Reader

Abstract

The present invention discloses a real-time full-course information collection method for orthopedic patients, which specifically relates to the technical field of medical information processing, and comprises the following steps: configuring a plurality of preset collection devices when the patient is admitted to the hospital, continuously collecting data at each stage of the course of the disease, and transmitting the data to the hospital information system through the network; analyzing the system processing capacity based on the amount of collected data, and judging whether there is information overload pressure; in the case of overload pressure, dynamically analyzing and determining the amount of basic data, filtering according to the data type and importance, and retaining key data in the hospital information system; if there is no overload pressure, all initial course of disease data will be retained in the system; the present invention can dynamically adjust the processing strategy of course of disease data according to the current load situation of the system by real-time monitoring the processing load of the hospital information system, thereby greatly improving the processing efficiency of the hospital information system in the face of big data environment, and avoiding the risk of system overload and collapse.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of medical information processing technology, and more specifically, to a real-time full-course information collection method for orthopedic patients. Background Art

[0002] With the rapid development of modern medicine and the continuous advancement of medical equipment, the amount of data in orthopedic surgery has exploded. Patients will generate a large amount of medical data from preoperative, intraoperative, postoperative to rehabilitation stages, including patients' vital signs, imaging data, surgical records, drug reactions, etc. These data are of great significance to doctors' clinical decision-making and patients' postoperative rehabilitation management. However, when dealing with such a large amount of data, hospital information systems are prone to overload due to limited processing capabilities, which in turn affects the efficiency and quality of medical services.

[0003] Existing hospital information systems often rely on simple data storage and query functions, lacking a dynamic adjustment mechanism for real-time data processing capabilities. Once the system load is too high and a large amount of data cannot be processed in time, it may lead to the loss or processing delay of key course data, affecting the timeliness of medical decision-making. Therefore, a real-time full course information collection method for orthopedic patients is proposed. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A method for collecting real-time full-course information of orthopedic patients, comprising the following steps:

[0006] When a patient is admitted to the hospital, multiple preset real-time full-course information collection devices are configured to continuously collect the initial course data of the patient at each stage of the course of the disease, and the collected course data is transmitted to the hospital information system in real time through the data transmission network;

[0007] Analyze the processing capacity of the hospital information system based on the amount of data collected in real time, and determine whether the hospital information system is under information overload pressure based on the analysis results;

[0008] In the case of information overload pressure on hospital information systems, dynamic analysis operations are performed to determine the amount of dynamic basic data;

[0009] Data filtering is performed according to the amount of dynamic basic data and the type of initial medical data. The medical data after filtering is retained in the hospital information system. When the hospital information system is not under information overload pressure, all initial medical data are retained in the hospital information system.

[0010] In a preferred embodiment, all stages of the disease course include preoperative, intraoperative, postoperative, and recovery stages.

[0011] In a preferred embodiment, analyzing the processing capacity of a hospital information system based on the amount of data collected in real time refers to:

[0012] In a fixed time window, the average data processing time and the average data generation time are obtained, and the ratio of the average data processing time to the average data generation time is calculated to obtain indicator 1;

[0013] Obtain the amount of data processed by the system under the standard state and the amount of data actually required to be processed in the unit time corresponding to the fixed time window, and then calculate the ratio of the amount of data processed by the system under the standard state to the amount of data actually required to be processed to obtain the second indicator;

[0014] In a fixed time window, the average data update frequency and the average data response frequency received by the system are obtained, and then the ratio of the average data update frequency to the average data response frequency is calculated to obtain indicator three;

[0015] In a fixed time window, the average utilization rate of the system's data storage space and the total data storage space are obtained, and then the ratio of the average utilization rate of the data storage space to the total data storage space is calculated to obtain indicator 4;

[0016] Summarize indicators one, two, three and four to obtain the hospital information system processing capacity analysis indicator combination.

[0017] Judging whether the hospital information system has information overload pressure based on the analysis results means: using logical reasoning to infer based on the combination of hospital information system processing capacity analysis indicators to judge whether the hospital information system has information overload pressure.

[0018] In a preferred embodiment, the logic of logical reasoning is:

[0019] Indicator 1, indicator 2, indicator 3 and indicator 4 in the hospital information system processing capacity analysis indicator combination are obtained respectively and used as input variables together, and whether the hospital information system has information overload pressure is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the degree of information overload of the hospital information system under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to determine whether the hospital information system has information overload pressure or not.

[0020] In a preferred embodiment, the dynamic analysis operation refers to:

[0021] Get the amount of data that the hospital information system can process in the current unit time and mark it as , the average processing efficiency of the hospital information system in the most recent n time windows and marked as , the average amount of data received by the hospital information system in the most recent n time windows and marked as , the current amount of unprocessed data in the hospital information system is marked as , the maximum data processing capacity preset by the hospital information system and marked as ;

[0022] First calculate the data congestion coefficient: ; Indicates the data congestion coefficient;

[0023] Then calculate the dynamic basic data volume:

[0024] ; Indicates the amount of dynamic basic data, , are preset adjustment coefficients, and , The sum of is one, is the preset time decay factor.

[0025] In a preferred embodiment, the average processing efficiency The acquisition logic is:

[0026] The processing efficiency of the hospital information system in the most recent n time windows is obtained respectively. The processing efficiency in each time window is obtained by dividing the amount of data successfully processed in the time window by the total amount of data generated in the history. Then, the processing efficiency in the n time windows is averaged to obtain the average processing efficiency. .

[0027] In a preferred embodiment, data filtering according to the amount of dynamic basic data and the type of initial course of disease data refers to:

[0028] The importance weight coefficients corresponding to the types of initial medical course data are obtained respectively, and the sum of the importance weight coefficients corresponding to all types is one. Then, the product of the dynamic basic data volume and the importance weight coefficient corresponding to the type of initial medical course data is calculated to obtain the retention volume of medical course data of this type and perform data filtering.

[0029] Technical effects and advantages of the present invention:

[0030] The present invention can dynamically adjust the processing strategy of medical history data according to the current load of the system by monitoring the processing load of the hospital information system in real time. By introducing a calculation mechanism for the dynamic basic data volume and importance weight coefficient, the system can prioritize and retain the most critical medical history data under high load conditions to ensure the accuracy and timeliness of medical decision-making. This greatly improves the processing efficiency of the hospital information system in the face of big data environments and avoids the risk of system overload and crash.

[0031] In the prior art, hospital information systems often use a full data storage method, which easily leads to data redundancy and increases the storage and processing burden of the system. The present invention effectively reduces unnecessary data storage and improves the utilization rate of system storage space by filtering data based on the importance weight coefficient of the course of disease data type. This not only optimizes the resource utilization of the system, but also improves the overall stability and response speed of the system.

[0032] In the medical process, certain course data (such as intraoperative vital signs data and postoperative recovery data) are crucial to clinical decision-making. The present invention sets weight coefficients to ensure that the most important course data is retained first when the system processing capacity is limited, avoiding the loss of key data or processing delays, and ensuring the security and integrity of the data. This is of great significance for improving medical quality and avoiding medical risks.

[0033] By dynamically adjusting the data processing strategy, the present invention can ensure that doctors can obtain the patient's key data in real time at each stage of the disease, so as to make more accurate clinical decisions. Especially in emergency situations, the system can give priority to processing key data to ensure that doctors can intervene and treat in time. This data processing mechanism greatly improves the efficiency and quality of medical services and enhances the overall treatment effect of patients.

[0034] The present invention is applicable to the whole course management of orthopedic patients, but its core dynamic data processing mechanism can be extended to other departments or medical scenarios. Whether it is preoperative evaluation, intraoperative monitoring or postoperative rehabilitation, the present invention can adjust the data processing strategy according to different medical scenarios and adapt to different data load requirements. Its highly flexible design makes the system have a wide range of application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0036] Figure 1 The schematic diagram is a schematic diagram of a method for collecting real-time full-course information of orthopedic patients in the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Reference Figure 1 The following embodiments are obtained:

[0039] Embodiment 1: A method for collecting real-time full-course information of orthopedic patients, comprising the following steps:

[0040] When the patient is admitted to the hospital, a variety of preset real-time full-course information collection devices are configured to continuously collect the initial course data of the patient at each stage of the course of the disease, and the collected course data is transmitted to the hospital information system in real time through the data transmission network; the purpose of this step is to ensure that the health data of orthopedic patients is collected in real time when the patient is admitted to the hospital, so as to provide comprehensive information support for subsequent diagnosis, treatment and rehabilitation. All these data cover the entire treatment and rehabilitation process of the patient, from the pre-admission preparation to the operation period, and then to the postoperative recovery and rehabilitation stage, all health status changes and treatment responses will be recorded. Equipment includes but is not limited to: wearable devices: such as smart bracelets, smart blood pressure monitors, smart oximeters, used to monitor the patient's vital signs (such as heart rate, blood pressure, blood oxygen, etc.). Bedside monitoring equipment: such as multi-parameter monitors, real-time monitoring of patients' breathing, body temperature, heart rate, blood pressure, pain scores, etc. Mobile X-ray machines or MRI equipment: used to regularly obtain preoperative, intraoperative and postoperative imaging data of orthopedic patients to help doctors evaluate the recovery of fractures or surgical sites. Rehabilitation training equipment: such as motion capture equipment, which monitors the patient's postoperative rehabilitation activities (such as joint range of motion, muscle activity) and provides rehabilitation training feedback. Drug infusion equipment: used to record the amount and time of drug infusion and track the patient's response to the drug.

[0041] The processing capacity of the hospital information system is analyzed based on the amount of data collected in real time, and whether the hospital information system is under information overload pressure is determined based on the analysis results; this link ensures the real-time and accessibility of the data. Through the Internet of Things technology and medical network system, the patient's health data, diagnostic data, imaging data, etc. are transmitted to the hospital's central information system in real time, which is convenient for medical staff to access and analyze at any time. This real-time transmission can not only help doctors make diagnoses and decisions faster, but also improve the efficiency and response speed of medical services. The data transmission network usually uses high-speed wireless networks (such as 5G, Wi-Fi) to ensure fast and stable data transmission in hospital and remote environments. In fact, encryption technology (such as SSL / TLS) should also be used during data transmission to protect patient privacy and avoid data leakage.

[0042] In the case of information overload pressure on the hospital information system, dynamic analysis operations are performed to determine the amount of dynamic basic data; the core of this step is to evaluate the processing capacity of the hospital information system. With the increase in the amount of orthopedic patient data (especially in the intensive data collection stage after surgery), the hospital information system may face data processing pressure. If the processing capacity cannot keep up with the speed of data generation, it will affect the doctor's ability to obtain real-time information, thereby delaying medical decision-making. Therefore, processing capacity analysis can help the hospital information system determine in advance whether data filtering measures need to be taken to reduce pressure.

[0043] Data filtering is performed based on the amount of dynamic basic data and the type of initial medical course data. The medical course data after data filtering is retained in the hospital information system. When the hospital information system does not have information overload pressure, all initial medical course data is retained in the hospital information system. The purpose of judging information overload pressure is to ensure that the system can still operate normally under high load conditions. Information overload may cause system performance to decline, and even cause problems such as data loss or decision delay. Therefore, real-time monitoring and evaluation of system load can be optimized and adjusted in advance to ensure the normal operation of the system. Whether there is overload pressure is determined by indicators such as data processing time, response time, and data backlog. Combined with load balancing and redundant processing, the system can better cope with peak data flows. When information overload is about to occur, the hospital information system can automatically start the load balancing, i.e., data filtering mechanism.

[0044] When the system detects information overload pressure, dynamically adjusting the priority and retention of data processing is a key step. Through dynamic analysis based on the current system load, low-priority data can be reasonably reduced to ensure that critical data can continue to be processed and stored. The determination of the dynamic basic data volume helps the system maintain normal operation under pressure. The algorithm is used to dynamically adjust the basic data volume, and then when the system is overloaded, unimportant or duplicate data is reduced through data filtering, and key, diagnosis-related data is retained first. Through the classification and filtering mechanism, the system burden can be reduced without affecting treatment. A priority grading strategy is adopted to assign different weights to different types of data. For example, a patient's vital signs data may be more important than postoperative rehabilitation data, so the vital signs data is retained first and the rehabilitation activity records are reduced.

[0045] When the system is not overloaded, retaining all initial data provides a complete record for subsequent medical treatment and research. This helps doctors conduct detailed reviews when needed and provides complete course data support for future clinical research. Different data retention strategies are designed according to different hospital or system requirements. When the system is not overloaded, all collected data can be retained, including those that are not directly used for current diagnosis and treatment decisions, to provide data support for subsequent analysis or research.

[0046] Hospital information system refers to a comprehensive information management system used in hospitals or medical institutions to manage and process patient information, medical processes, and hospital operations. It integrates multiple subsystems, covering various fields such as medical care, finance, and management, helping medical staff and managers improve efficiency, simplify operations, and improve service quality. Examples of the core functions of hospital information systems are:

[0047] Patient information management: record and manage the patient's basic information, medical history, admission, discharge, transfer, diagnosis and treatment records, etc. This information can help medical staff fully understand the patient's condition, diagnosis and treatment process and medical history. Electronic medical record system: including the patient's electronic medical records, surgical records, drug prescriptions, imaging reports, laboratory test results, etc., so that all the patient's diagnosis and treatment records are electronic, which is convenient for doctors to query and share at any time. Since the hospital information system is regarded as a prior art in the present invention, it will not be described in detail here.

[0048] The entire course of the disease includes preoperative, intraoperative, postoperative, and recovery stages.

[0049] The goal of the preoperative stage is to prepare for surgery, ensure the patient's safety during surgery, and optimize surgical outcomes. During this stage, the doctor will conduct a detailed examination and evaluation of the patient, develop a surgical plan, and perform necessary preoperative preparations, such as anesthesia evaluation and surgical risk assessment. The collected data includes the patient's basic health information, imaging data (such as X-rays, MRI, CT scans, etc.), blood test results, cardiopulmonary function assessment, etc. Through data collection, doctors can fully understand the patient's physical condition and provide a basis for surgery.

[0050] The intraoperative stage is the actual execution stage of the surgery, which involves real-time monitoring of the patient's vital signs and the surgical process. Ensuring the smooth progress of the surgery and the timely handling of intraoperative complications are the key points of this stage. The collected data includes the patient's real-time vital signs (such as blood pressure, heart rate, blood oxygen saturation, etc.), imaging data during the surgery (such as intraoperative fluoroscopic images), and records of the use of surgical tools. By collecting and monitoring data in real time, medical staff can make timely and effective decisions during surgery.

[0051] The focus of the postoperative stage is to monitor the patient's recovery and rehabilitation process and prevent postoperative complications. Early postoperative monitoring is crucial to ensure patient safety and determine whether there are complications such as postoperative infection and bleeding. The collected data includes postoperative wound healing, patient's vital signs, pain scores, postoperative imaging test results, drug reactions, etc. Through the collection and analysis of these data, doctors can judge the patient's recovery and adjust the treatment plan in time.

[0052] The rehabilitation phase aims to help patients recover their physical functions, especially the joint movement, muscle strength and daily living ability after orthopedic surgery. The rehabilitation phase is crucial for patients to regain mobility and improve their quality of life. The collected data includes the patient's motor function recovery data (such as joint range of motion, gait analysis, etc.), physiological indicators during rehabilitation training, pain conditions and functional assessment results. By collecting this data in real time, rehabilitation therapists and doctors can develop personalized rehabilitation plans based on the recovery progress.

[0053] Analysis of hospital information system processing capacity based on the amount of data collected in real time refers to:

[0054] In a fixed time window, the average data processing time and the average data generation time are obtained, and the ratio of the average data processing time to the average data generation time is calculated to obtain indicator 1; this indicator measures the relationship between the speed at which the system processes data and the speed at which data is generated. If the processing time is much greater than the generation time, it means that the system's processing capacity cannot keep up with the speed at which data is generated, and there is a potential risk of overload.

[0055] Obtain the amount of data processed by the system under the standard state and the amount of data actually required to be processed per unit time corresponding to the fixed time window, and then calculate the ratio of the amount of data processed by the system under the standard state to the amount of data actually required to be processed to obtain indicator 2; this indicator reflects the relationship between the system's processing capacity under the standard workload and the current actual load. The standard state is usually the ideal working state of the system, indicating its maximum processing capacity. If the ratio is small, it indicates that the system load is large and the processing capacity may be insufficient.

[0056] In a fixed time window, the average data update frequency and the average data response frequency received by the system are obtained, and then the ratio of the average data update frequency to the average data response frequency is calculated to obtain indicator three; this indicator reflects the relationship between the speed at which the system receives new data and the speed at which the system responds to the data. If the update frequency is much higher than the response frequency, the system may not be able to process all the received data in time, resulting in data backlog.

[0057] In a fixed time window, the average utilization rate of the system's data storage space and the total data storage space are obtained, and then the ratio of the average utilization rate of the data storage space to the total data storage space is calculated to obtain indicator 4; this indicator reflects the usage of system storage resources. It measures the ratio between the data storage space already used by the system and the total storage space. If the ratio is close to 1, it indicates that the system storage space is close to saturation, and it may be necessary to expand storage resources or clean up redundant data in a timely manner.

[0058] Summarize indicators 1, 2, 3, and 4 to obtain a combination of hospital information system processing capacity analysis indicators. After summarizing the above four indicators, a comprehensive processing capacity analysis indicator combination is formed to fully reflect the processing capacity of the hospital information system within a fixed time window. This combination of indicators can help hospitals to promptly discover potential overload pressures on information systems and take corresponding measures to alleviate the load and optimize resource use.

[0059] Judging whether the hospital information system has information overload pressure based on the analysis results means: using logical reasoning to infer according to the hospital information system processing capacity analysis indicator combination to judge whether the hospital information system has information overload pressure. The logic of logical reasoning is: respectively obtaining indicator 1, indicator 2, indicator 3 and indicator 4 in the hospital information system processing capacity analysis indicator combination as input variables, taking whether the hospital information system has information overload pressure as the output variable, fuzzifying the input variables, converting the values ​​of the input variables into fuzzy sets, fuzzifying the output variables, converting the output variables into fuzzy sets, formulating fuzzy rules to describe the degree of information overload of the hospital information system under different data type combinations, and reasoning the fuzzified input variables through fuzzy rules to judge whether the hospital information system has information overload pressure or not.

[0060] Four main indicators are obtained from the processing capacity analysis of the hospital information system as input variables. Indicator 1 measures the comparison between data processing speed and generation speed. Indicator 2 measures the comparison between the amount of data processed by the system under standard conditions and the amount of data actually required to be processed. Indicator 3 measures the comparison between data update frequency and response frequency. Indicator 4 measures the use of data storage space. These indicators can reflect the working status of each dimension of the hospital information system and serve as key inputs in the reasoning process.

[0061] Perform fuzzification on each input indicator. Fuzzification refers to converting precise numerical values ​​into concepts in fuzzy sets. For example, indicator one can be fuzzified into "fast", "moderate" or "slow". Indicator two can be fuzzified into "low load", "moderate load" or "high load". Indicator three can be fuzzified into "fast update", "moderate response" or "slow response". Indicator four can be fuzzified into "sufficient storage space", "moderate storage space" or "tight storage space". The category definitions of these fuzzy sets depend on the set thresholds in the actual system.

[0062] The output variable is whether the hospital information system has information overload pressure. This variable also needs to be fuzzified. The output can be fuzzified as follows: No overload pressure: The system load is within the normal range, and the processing capacity is sufficient to cope with the current amount of data. Overload pressure exists: The system is overloaded, and the processing capacity cannot keep up with the data generation, and measures need to be taken to alleviate it.

[0063] According to different combinations of input variables, corresponding fuzzy rules are formulated. Fuzzy rules are used to describe how input variables affect output results. For example: if indicator one is "slow", indicator two is "high load", indicator three is "slow response", and indicator four is "tight storage space", it is judged that there is overload pressure. If indicator one is "moderate", indicator two is "moderate load", indicator three is "moderate response", and indicator four is "moderate storage space", it is judged that there is no overload pressure. These fuzzy rules are set according to specific system requirements and operating environment.

[0064] The fuzzified input variables are inferred through fuzzy rules. The inference process gradually deduces the load status of the hospital information system based on the fuzzified state of each input variable and the fuzzy rule base. The final result of the inference is whether the hospital information system has information overload pressure.

[0065] Dynamic analysis operation refers to: obtaining the amount of data that the hospital information system can process in the current unit time and marking it as , the average processing efficiency of the hospital information system in the most recent n time windows and marked as , the average amount of data received by the hospital information system in the most recent n time windows and marked as , the current amount of unprocessed data in the hospital information system is marked as , the maximum data processing capacity preset by the hospital information system and marked as ; Calculate the data congestion coefficient first: ; Indicates the data congestion coefficient; the data congestion coefficient helps the system adjust the basic data volume by reflecting the backlog of unprocessed data in the current system. If the congestion is serious, the system will automatically reduce the basic data volume to avoid overload. Then calculate the dynamic basic data volume: ; Indicates the dynamic basic data volume, which is the data retention volume that the system adjusts when facing different processing capabilities and load pressures. , are preset adjustment coefficients, and , The sum is one, indicating how to balance the impact of processing capacity and historical processing efficiency under different conditions. It is a preset time decay factor used to control the impact of data congestion on the basic data volume.

[0066] Average processing efficiency The acquisition logic is as follows: obtain the processing efficiency of the hospital information system in the most recent n time windows respectively. The processing efficiency in each time window is obtained by dividing the amount of historically successfully processed data in the time window by the total amount of historically generated data. Then, the processing efficiency in the n time windows is averaged to obtain the average processing efficiency. The historical average processing efficiency reflects the overall processing performance of the hospital information system over a period of time. By reviewing multiple time windows, it can help determine the processing capacity and efficiency fluctuations of the system under normal conditions.

[0067] Data filtering based on the amount of dynamic basic data and the type of initial course data refers to:

[0068] The importance weight coefficients corresponding to the types of initial medical course data are obtained respectively, and the sum of the importance weight coefficients corresponding to all types is one. Then, the product of the dynamic basic data volume and the importance weight coefficient corresponding to the type of initial medical course data is calculated to obtain the retention volume of medical course data of this type and perform data filtering.

[0069] First, for each type of disease course data (such as preoperative, intraoperative, postoperative, and rehabilitation data), an importance weight coefficient is assigned to it. Each type of data can be weighted by experts according to its importance in clinical decision-making. The weight coefficient usually ranges from 0 to 1, and the sum of the weight coefficients of all types of data is equal to 1. For example, intraoperative vital signs data may be assigned a higher weight coefficient, such as 0.4, while daily monitoring data in the rehabilitation stage may be assigned a lower weight coefficient, such as 0.2.

[0070] Based on the calculated retention amount, the system filters and screens the initial course of disease data. For data types with higher importance, more are retained; for data types with lower importance, relatively fewer are retained or even completely filtered. This ensures that the system can prioritize the most critical data even when processing capacity is limited.

[0071] Data at different stages of the disease course have different importance in clinical decision-making, so their respective weight coefficients may vary greatly. Preoperative data: including basic information of the patient, diagnostic data, preoperative examination reports, etc. Although preoperative data is important for decision-making, the importance of these data may be lower after the operation begins, so their weight coefficient may be smaller. Intraoperative data: vital signs monitoring, anesthesia records, and real-time data generated during the operation. These data directly affect the decision-making during the operation, so the weight coefficient is usually higher. Postoperative data: data during the postoperative recovery process (such as wound healing, pain management, vital signs monitoring, etc.) may be inferior to intraoperative data, but it is also very important in monitoring postoperative complications, so its weight coefficient is generally medium. Rehabilitation stage data: data in the rehabilitation stage is used to track the patient's long-term recovery, but its importance is usually lower than that of intraoperative and postoperative data, so the weight coefficient is relatively low.

[0072] By filtering the course of disease data in different levels, the hospital information system can prioritize the processing and storage of the most critical course of disease data when resources are limited or the system load is heavy, ensuring that the system operates efficiently while avoiding overload. The dynamic adjustment of the amount of basic data ensures that the system can flexibly respond to different data volumes and processing loads, while the weight coefficient ensures that the most important data can be retained first during filtering to avoid negative impacts on medical decisions. Data at different stages of the course of disease may have different importance for different patients. Through reasonable weight settings, the system can dynamically adjust the data retention strategy to respond to the actual needs of specific clinical scenarios in a personalized manner. In the case of huge amounts of data, the use of this data filtering strategy can improve the efficiency of data management, reduce the storage and processing burden of irrelevant or redundant data, and provide more efficient support for subsequent data analysis and medical decision-making.

[0073] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0074] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0075] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0076] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0077] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A real-time full-course information collection method for orthopedic patients, characterized in that: The following steps are involved: When a patient is admitted to the hospital, multiple preset real-time full-course information collection devices are configured to continuously collect the initial course data of the patient at each stage of the course of the disease, and the collected course data is transmitted to the hospital information system in real time through the data transmission network; Analyze the processing capacity of the hospital information system based on the amount of data collected in real time, and determine whether the hospital information system is under information overload pressure based on the analysis results; In the case of information overload pressure on hospital information systems, dynamic analysis operations are performed to determine the amount of dynamic basic data; Data filtering is performed according to the amount of dynamic basic data and the type of initial medical course data. The medical course data after data filtering is retained in the hospital information system. When the hospital information system does not have information overload pressure, all initial medical course data are retained in the hospital information system; Analysis of hospital information system processing capacity based on the amount of data collected in real time refers to: In a fixed time window, the average data processing time and the average data generation time are obtained, and the ratio of the average data processing time to the average data generation time is calculated to obtain indicator 1; Obtain the amount of data processed by the system under the standard state and the amount of data actually required to be processed in the unit time corresponding to the fixed time window, and then calculate the ratio of the amount of data processed by the system under the standard state to the amount of data actually required to be processed to obtain the second indicator; In a fixed time window, the average data update frequency and the average data response frequency received by the system are obtained, and then the ratio of the average data update frequency to the average data response frequency is calculated to obtain indicator three; In a fixed time window, the average utilization rate of the system's data storage space and the total data storage space are obtained, and then the ratio of the average utilization rate of the data storage space to the total data storage space is calculated to obtain indicator 4; Summarize indicators one, two, three and four to get the hospital information system processing capacity analysis indicator combination; Judging whether the hospital information system has information overload pressure based on the analysis results means: using logical reasoning to infer based on the combination of hospital information system processing capacity analysis indicators to judge whether the hospital information system has information overload pressure; The logic of logical reasoning is: Indicators 1, 2, 3 and 4 in the hospital information system processing capacity analysis indicator combination are obtained respectively and taken as input variables, whether the hospital information system has information overload pressure is taken as the output variable, the input variables are fuzzified, the values ​​of the input variables are converted into fuzzy sets, the output variables are fuzzified, the output variables are converted into fuzzy sets, fuzzy rules are formulated to describe the information overload degree of the hospital information system under different data type combinations, the fuzzified input variables are inferred through fuzzy rules, and it is judged whether the hospital information system has information overload pressure or not; Dynamic analysis operations refer to: Get the amount of data that the hospital information system can process in the current unit time and mark it as , the average processing efficiency of the hospital information system in the most recent n time windows and marked as , the average amount of data received by the hospital information system in the most recent n time windows and marked as , the current amount of unprocessed data in the hospital information system is marked as , the maximum data processing capacity preset by the hospital information system is marked as ; First calculate the data congestion coefficient: ; Indicates the data congestion coefficient; Then calculate the dynamic basic data volume: ; Indicates the amount of dynamic basic data, , are preset adjustment coefficients, and , The sum of is one, is the preset time decay factor; Average processing efficiency The acquisition logic is: The processing efficiency of the hospital information system in the most recent n time windows is obtained respectively. The processing efficiency in each time window is obtained by dividing the amount of data successfully processed in the time window by the total amount of data generated in the history. Then, the processing efficiency in the n time windows is averaged to obtain the average processing efficiency. ; Data filtering based on the amount of dynamic basic data and the type of initial course data refers to: The importance weight coefficients corresponding to the types of initial medical course data are obtained respectively, and the sum of the importance weight coefficients corresponding to all types is one. Then, the product of the dynamic basic data volume and the importance weight coefficient corresponding to the type of initial medical course data is calculated to obtain the retention volume of medical course data of this type and perform data filtering.

2. A method for collecting real-time full-course information of orthopedic patients according to claim 1, characterized in that: The entire course of the disease includes preoperative, intraoperative, postoperative, and recovery stages.

Citation Information

Patent Citations

  • Real-time whole-course information acquisition system and method for orthopedic patients

    CN117373587A

  • Multi-department cross-hospital outpatient service and off-hospital patient whole course tracking management system

    CN118213091A