Neurosurgery data recording management system based on data monitoring

Abstract

The invention discloses a neurosurgery data recording management system based on data monitoring, and particularly relates to the technical field of data recording, which comprises the following steps: constructing a data fusion map according to the actual use condition of neurosurgery data, connecting two kinds of neurosurgery data with correlation in the data fusion map through edges, and establishing a data fusion map; the method comprises the steps of obtaining identity information of a patient, determining a medical record of the patient, extracting checked neurosurgical data in the medical record of the patient, determining the integrity of the neurosurgical data of the patient, generating an analysis signal, collecting time information and expression information of the neurosurgical data of the patient when the analysis signal is generated, and constructing a data record evaluation model. And generating a data record evaluation coefficient, comparing the data record evaluation coefficient with a preset threshold value, and determining whether to generate an additional recording signal, so that a guidance scheme can be provided before the patient sees a doctor, and the patient is guided in a self-service manner to carry out additional recording on the data, so that the treatment effect is prevented from being influenced by incomplete or outdated data.

Description

Technical Field

[0001] The present invention relates to the technical field of data recording, and more specifically, to a neurosurgery data recording management system based on data monitoring. Background Art

[0002] Neurosurgery data is about the human brain and usually involves the structure, function, and interaction between the brain and other parts of the body. Neurosurgery data includes not only routine clinical information (such as patient symptoms, signs, and examination results), but also imaging, neurophysiology, and laboratory examination data specifically for the brain.

[0003] At present, the medical industry has promoted the standardization of neurosurgery data between different hospitals to a certain extent. For example, electronic medical records (EMR) and standardized data exchange formats (such as HL7, FHIR, etc.) are used to ensure that patient information can be communicated between different medical institutions. However, during the patient registration, consultation and treatment process, medical records are not updated in a timely manner, and it is not easy to comprehensively consider the synchronization and timeliness of neurosurgery data.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a neurosurgery data record management system based on data monitoring to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A neurosurgery data record management system based on data monitoring, specifically including a data fusion atlas module, a data analysis module, a data acquisition module and a data record evaluation module, and signal connections between the modules;

[0008] The data fusion graph module is used to construct a data fusion graph based on the actual usage of neurosurgery data, and connect two related neurosurgery data through edges in the data fusion graph;

[0009] A data analysis module, for obtaining the patient's identity information, determining the patient's medical history, extracting the examined neurosurgery data in the patient's medical history, determining the completeness of the patient's neurosurgery data, and generating an analysis signal;

[0010] A data acquisition module, used for acquiring time information and performance information of the patient's neurosurgery data when generating the analysis signal, wherein the time information includes a synchronization time coordination coefficient and a timeliness deviation index, and the performance information includes a data abnormality deviation coefficient;

[0011] The data record evaluation module is used to construct a data record evaluation model, generate a data record evaluation coefficient, compare the data record evaluation coefficient with a preset threshold, and determine whether to generate a supplementary recording signal.

[0012] In a preferred embodiment, constructing a data fusion graph includes:

[0013] In the data fusion graph, two types of related neurosurgery data are connected by edges, and the nodes in the data fusion graph represent different types of neurosurgery data;

[0014] To ensure the combined use of different neurosurgical data, the data fusion map is fused according to the time synchronization rules, including determining the unified time base for all data, setting the time point of the preoperative neurosurgical data as the initial time point, and setting the time interval. Through the time points of different neurosurgical data, the lag relationship of the neurosurgical data is obtained.

[0015] In a preferred embodiment, determining the completeness of the patient's neurosurgery data includes:

[0016] The completeness of the patient's neurosurgery data was determined by data coverage, which was calculated as follows: ;in, The data coverage of patients, The number of existing neurosurgery records for the patient, The number of neurosurgery data required for hospital physician standards;

[0017] A data coverage threshold is set. If the data coverage of the neurosurgery data in the patient's medical record is greater than the data coverage threshold, an analysis signal is generated and the patient's neurosurgery data is further analyzed. If the data coverage of the neurosurgery data in the patient's medical record is less than the data coverage threshold, no analysis signal is generated and the patient is required to re-record the neurosurgery data.

[0018] In a preferred embodiment, the synchronization time coordination coefficient includes:

[0019] The acquisition logic of the synchronization time coordination coefficient is as follows: according to the data fusion map of neurosurgery data, two different types of neurosurgery data with correlation in the data fusion map are extracted, and the optimal cross-correlation and optimal lag value of the two different types of neurosurgery data are determined through the use history of the two different types of neurosurgery data;

[0020] According to the usage history of two different types of neurosurgery data, the time point set of each use of neurosurgery data A and neurosurgery data B by doctors is obtained, and A and B are nodes connected by co-edges in the data fusion graph;

[0021] The time point sets used by the doctors of neurosurgery data A and neurosurgery data B are marked as: and ,in, Number the different time points of neurosurgery data A in the doctor's usage history, Number the different time points of neurosurgery data B in the doctor's usage history;

[0022] Use the nearest neighbor matching method to find the nearest time point in the neurosurgery data B time point set for each time point in the neurosurgery data A time point set, satisfying the expression: ,in, is the time point in the neurosurgery data A time point set, i=1, 2, 3, ..., n, Generate paired data for the time points in the neurosurgery data B time point set, j = 1, 2, 3, ..., m, and mark the paired data as:

[0023] The cross-correlation between neurosurgery data A and neurosurgery data B at different lag values ​​was calculated using the following formula: ;in, is the cross-correlation between neurosurgery data A and neurosurgery data B at a lag value of τ;

[0024] The cross-correlations of neurosurgery data A and neurosurgery data B under different lag values ​​τ are traversed to determine the optimal lag value. The expression of the optimal lag value is: ;in, is the optimal lag value for neurosurgery data A and neurosurgery data B;

[0025] The time points of neurosurgery data A and neurosurgery data B in the patient's medical record are obtained, and the lag values ​​of neurosurgery data A and neurosurgery data B are determined. The calculation formula is: ;in, are the lag values ​​of neurosurgery data A and neurosurgery data B in the actual patient medical records;

[0026] Calculate the lag value deviation of neurosurgery data A and neurosurgery data B using the following formula: ;in, is the lag value deviation between neurosurgery data A and neurosurgery data B, k=1, 2, 3, ..., K, K is a positive integer, k is the number of the nodes in the data fusion graph that are connected by the same edge in the data fusion graph, ;

[0027] Calculate the synchronization time coordination coefficient, the calculation formula is: ;in, is the synchronization time coordination coefficient.

[0028] In a preferred embodiment, the aging deviation index includes:

[0029] The acquisition logic of the time-efficiency deviation index is: according to the usage records of different types of neurosurgery data, the time-efficiency decay models of different types of neurosurgery data are determined, and the time-efficiency decay models of different types of neurosurgery data are marked as: ,in, , is the optimal timeliness of different types of neurosurgery data, q = 1, 2, 3, ..., ,q is the number of different types of neurosurgery data, is the attenuation factor, and t is the time point of neurosurgery data.

[0030] Calculate the timeliness deviation index, the calculation formula is: ;in, is the time deviation index.

[0031] In a preferred embodiment, the data abnormal deviation coefficient includes:

[0032] The logic for obtaining the data abnormal deviation coefficient is: obtaining the neurosurgery data in the patient case, and marking the neurosurgery data in the patient case as: , obtain the neurosurgery data recorded in the historical database, and mark the neurosurgery data recorded in the historical database as: , where r = 1, 2, 3, …, R, R is a positive integer, and r is the number of the total record of neurosurgery data q in the historical database;

[0033] The minimum similarity between the neurosurgery data in the patient case and the neurosurgery data recorded in the historical database is calculated using the following formula: ;in, is the minimum similarity between the neurosurgery data q and the neurosurgery data recorded in the historical database;

[0034] Calculate the data abnormal deviation coefficient, the calculation formula is: ;in, is the data abnormal deviation coefficient.

[0035] In a preferred embodiment, constructing a data record evaluation model includes:

[0036] Through comprehensive analysis of the time information and performance information of the patient's neurosurgery data, the synchronization time coordination coefficient, timeliness deviation index and data abnormality deviation coefficient are weighted and calculated to construct a data record evaluation model and a data record evaluation coefficient. The calculation formula of the data record evaluation coefficient is: ;in, is the data record evaluation coefficient, , , They are the proportional coefficients of synchronization time coordination coefficient, timeliness deviation index, and data anomaly deviation coefficient. , , Both are greater than 0.

[0037] In a preferred embodiment, determining whether to generate a make-up recording signal includes:

[0038] Setting a data record evaluation coefficient threshold, and comparing the data record evaluation coefficient with the data record evaluation coefficient threshold;

[0039] If the data record evaluation coefficient is greater than the data record evaluation coefficient threshold, a supplementary recording signal is generated;

[0040] If the data record evaluation coefficient is less than the data record evaluation coefficient threshold, no signal is generated.

[0041] Technical effects and advantages of the present invention:

[0042] The present invention integrates and associates neurosurgery data in the hospital, determines the correlation between neurosurgery data, determines the synchronization time points of different types of neurosurgery data based on the correlation between neurosurgery data, quantifies the deviation of the synchronization time points of neurosurgery data in the patient's medical record, and determines whether the patient needs to supplement the neurosurgery data by collecting the timeliness and abnormal value of the neurosurgery data in the patient's medical record. The present invention, through an automated evaluation mechanism, helps to provide guidance plans for patients before they see a doctor, and guides patients to supplement the data by themselves, thereby reducing the workload of manual operations and avoiding the impact of incomplete or outdated data on the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0044] Figure 1 The present invention is a structural schematic diagram of a neurosurgery data record management system based on data monitoring. DETAILED DESCRIPTION

[0045] 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.

[0046] Example 1

[0047] like Figure 1 A structural diagram of a neurosurgery data record management system based on data monitoring is given, which specifically includes a data fusion atlas module, a data analysis module, a data acquisition module, and a data record evaluation module, and the signal connections between the modules;

[0048] The data fusion graph module is used to construct a data fusion graph based on the actual usage of neurosurgery data, and connect two related neurosurgery data through edges in the data fusion graph;

[0049] A data analysis module, for obtaining the patient's identity information, determining the patient's medical history, extracting the examined neurosurgery data in the patient's medical history, determining the completeness of the patient's neurosurgery data, and generating an analysis signal;

[0050] A data acquisition module, used for acquiring time information and performance information of the patient's neurosurgery data when generating the analysis signal, wherein the time information includes a synchronization time coordination coefficient and a timeliness deviation index, and the performance information includes a data abnormality deviation coefficient;

[0051] The data record evaluation module is used to construct a data record evaluation model, generate a data record evaluation coefficient, compare the data record evaluation coefficient with a preset threshold, and determine whether to generate a supplementary recording signal.

[0052] In the field of neurosurgery, doctors usually rely on various clinical data in medical records. They determine which neurosurgery data in the patient's electronic medical record needs to be updated based on the doctor's usage records, diagnosis and treatment behaviors and the data in the patient's electronic medical record.

[0053] According to the frequency and time preference of doctors' use of neurosurgical data and the impact on decisions, a neurosurgical data model based on doctors' usage records was constructed to quantify the frequency of doctors' use of different neurosurgical data, analyze doctors' time preference for neurosurgical data, evaluate the impact of different data types in key diagnosis and treatment decisions, and construct decision-making influence weights.

[0054] In the process of using neurosurgical data, neurosurgical data are often collected at different times and stages. For example, preoperative imaging data (such as MRI and CT) are usually obtained during the surgical planning stage, while intraoperative data (such as intraoperative neuromonitoring data and intraoperative imaging navigation data) are collected in real time during the operation;

[0055] Depending on the type of neurosurgery, different neurosurgery data have different timeliness, including:

[0056] Preoperative data: MRI, CT, PET imaging data, preoperative neurological function assessment (such as cognitive tests, motor function tests). Preoperative data is usually collected a few hours to a few days before surgery, and the data has a long time validity. It is mainly used for surgical navigation and risk assessment. Therefore, it is necessary to ensure that the data is up to date before surgery (usually data collected within 1-3 days);

[0057] Intraoperative data: intraoperative electrophysiological monitoring (EEG, ECoG), real-time image navigation data (real-time MRI, CT), intraoperative neurological monitoring (SEPs, MEPs). Intraoperative data requires real-time analysis and feedback, and is very sensitive to data delays. Intraoperative data is usually only valid during the operation. After the operation, its real-time significance decreases, and it is used as postoperative analysis data instead, which has a shorter timeliness.

[0058] Postoperative data: postoperative imaging examination (MRI, CT), postoperative neurological function assessment (EEG, cognitive testing, rehabilitation progress assessment). The timeliness of postoperative data spans a large range and may require long-term follow-up. Postoperative data are usually reviewed and updated at a certain period (such as one week, one month, three months, etc.).

[0059] According to different types of neurosurgery data, different time decay function models are designed to quantify the timeliness of the data.

[0060] According to the actual use of neurosurgery data, a data fusion map is constructed. The data fusion map represents the neurosurgery data required for different diseases, including:

[0061] According to the different types of neurosurgical diseases, we first need to classify the diseases: craniocerebral injury: such as traumatic brain injury, concussion, etc.; brain tumor: such as glioma, meningioma, etc.; nervous system infection: such as meningitis, brain abscess, etc.; neurodegenerative diseases: such as Parkinson's disease, Alzheimer's disease, etc.; spinal diseases: such as spinal fracture, spinal cord injury, etc.;

[0062] Based on each disease, determine the relevant neurosurgery data, such as imaging (CT, MRI), neuroelectrophysiological data, etc. according to its treatment process and key links;

[0063] For each disease, the dependency relationship between different data is analyzed. Based on the doctor's usage records and the diagnosis results after use, two related neurosurgery data are connected by edges in the data fusion graph. The nodes in the data fusion graph represent different types of neurosurgery data, among which two related neurosurgery data represent two types of neurosurgery data used in combination by the doctor in the usage records.

[0064] In order to ensure the combined use of different neurosurgical data, the data fusion map needs to be fused according to the time synchronization rules, including determining the unified time base for all data, setting the time point of the preoperative neurosurgical data as the initial time point, and setting the time interval. Through the time points of different neurosurgical data, the lag relationship of the neurosurgical data is obtained.

[0065] Historical databases play a vital role in medical data management, especially in areas such as neurosurgery that require detailed tracking and evaluation, including collecting a large number of patients' medical records and related medical data. The collected data should cover different types of patient groups, different types of diseases, and various related diagnosis and treatment processes, and store abnormal data of patient lesions. By comparing the patient's current medical record data with historical data, unusual or abnormal situations can be identified.

[0066] By obtaining the patient's identity information, determining the patient's medical record, extracting the examined neurosurgery data in the patient's medical record, and determining the completeness of the patient's neurosurgery data, if the completeness of the patient's neurosurgery data meets the requirements, generating an analysis signal, and further analyzing the patient's neurosurgery data; if the completeness of the patient's neurosurgery data does not meet the requirements, no analysis signal is generated, and the patient is required to re-enter the neurosurgery data;

[0067] Specifically, the completeness of the patient's neurosurgery data is determined by the data coverage rate, and the calculation formula for the data coverage rate is: ;in, The data coverage of patients, The number of existing neurosurgery records for the patient, The number of neurosurgery data required for hospital physician standards.

[0068] It should be noted that data coverage is an important indicator for evaluating whether the neurosurgery data in the patient's medical record is complete. It is used to quantify the degree of match between the patient's existing data and standard requirements, and to help doctors and systems identify whether there is missing data;

[0069] The number of existing neurosurgery data on patients refers to the number of neurosurgery examination data actually collected in the patient's medical record. The number of existing neurosurgery data on patients is affected by whether the patient has undergone examinations in other hospitals or this hospital;

[0070] The number of neurosurgery data required by the hospital's doctor standards is the number of standard examination items predefined based on the hospital's diagnosis and treatment standards and doctor experience, and is usually set by the hospital's expert team or the attending neurosurgeon.

[0071] A data coverage threshold is set. If the data coverage of the neurosurgery data in the patient's medical record is greater than the data coverage threshold, an analysis signal is generated and the patient's neurosurgery data is further analyzed. If the data coverage of the neurosurgery data in the patient's medical record is less than the data coverage threshold, no analysis signal is generated and the patient is required to re-record the neurosurgery data.

[0072] According to the neurosurgery data in the patient's case, the time information and performance information of the patient's neurosurgery data are collected. After collection, the time information of the patient's neurosurgery data is represented by the synchronization time coordination coefficient and the timeliness deviation index, and the performance information of the patient's neurosurgery data is represented by the data abnormality deviation coefficient.

[0073] The acquisition logic of the synchronization time coordination coefficient is as follows: according to the data fusion map of neurosurgery data, two different types of neurosurgery data with correlation in the data fusion map are extracted, and the optimal cross-correlation and optimal lag value of the two different types of neurosurgery data are determined through the use history of the two different types of neurosurgery data;

[0074] It should be noted that the correlated neurosurgery data in the data fusion atlas indicates that the two neurosurgery data are correlated for the diagnosis of one or more diseases and are used to combine the diagnosis of the disease. For example, the combination of preoperative MRI data and intraoperative DSA data is usually highly correlated for the diagnosis of a certain type of disease.

[0075] According to the usage history of two different types of neurosurgery data, the time point set of each use of neurosurgery data A and neurosurgery data B by doctors is obtained. A and B are nodes connected by the same edge in the data fusion graph, that is, two different types of neurosurgery data with correlation;

[0076] It should be noted that because the chronological relationship between data may be needed to determine changes in the patient's condition when diagnosing a disease, the approximate synchronization time range of two different neurosurgery data can be determined based on the time point used by the doctor each time. Usually, the closer the time point of the data is to the current moment, the better. However, the original data may be outdated or need to be kept updated.

[0077] The time point sets used by the doctors of neurosurgery data A and neurosurgery data B are marked as: and ,in, Number the different time points of neurosurgery data A in the doctor's usage history, Number the different time points of neurosurgery data B in the doctor's usage history;

[0078] Use the nearest neighbor matching method to find the nearest time point in the neurosurgery data B time point set for each time point in the neurosurgery data A time point set, satisfying the expression: ,in, is the time point in the neurosurgery data A time point set, i=1, 2, 3, ..., n, Generate paired data for the time points in the neurosurgery data B time point set, j = 1, 2, 3, ..., m, and mark the paired data as:

[0079] The cross-correlation between neurosurgery data A and neurosurgery data B at different lag values ​​was calculated using the following formula: ;in, is the cross-correlation between neurosurgery data A and neurosurgery data B at a lag value of τ;

[0080] The cross-correlations of neurosurgery data A and neurosurgery data B under different lag values ​​τ are traversed to determine the optimal lag value. The expression of the optimal lag value is: ;in, is the optimal lag value for neurosurgery data A and neurosurgery data B;

[0081] The time points of neurosurgery data A and neurosurgery data B in the patient's medical record are obtained, and the lag values ​​of neurosurgery data A and neurosurgery data B are determined. The calculation formula is: ;in, are the lag values ​​of neurosurgery data A and neurosurgery data B in the actual patient medical records;

[0082] Calculate the lag value deviation of neurosurgery data A and neurosurgery data B using the following formula: ;in, is the lag value deviation between neurosurgery data A and neurosurgery data B, k=1, 2, 3, ..., K, K is a positive integer, k is the number of the nodes in the data fusion graph that are connected by the same edge in the data fusion graph, ;

[0083] Calculate the synchronization time coordination coefficient, the calculation formula is: ;in, is the synchronization time coordination coefficient.

[0084] It can be seen from the formula that the larger the synchronization time coordination coefficient is, the more asynchronous time points there are in the neurosurgery data in the patient's medical record, the larger the time alignment error between the neurosurgery data is, and the more likely it is that the data in the patient's case needs to be supplemented.

[0085] The acquisition logic of the time-efficiency deviation index is: according to the usage records of different types of neurosurgery data, the time-efficiency decay models of different types of neurosurgery data are determined, and the time-efficiency decay models of different types of neurosurgery data are marked as: ,in, , is the optimal timeliness of different types of neurosurgery data, q = 1, 2, 3, ..., ,q is the number of different types of neurosurgery data, is the attenuation factor, and t is the time point of neurosurgery data.

[0086] It should be noted that the time-attenuation model for different types of neurosurgical data requires analysis of the usage records of different types of neurosurgical data in patient medical records, especially the frequency and timeliness of doctors accessing and using these data at different time points. Each type of neurosurgical data has a different attenuation curve, and the optimal timeliness of neurosurgical data is the time point with the highest frequency of use in doctors' usage records.

[0087] Calculate the timeliness deviation index, the calculation formula is: ;in, is the time deviation index.

[0088] It can be seen from the formula that the larger the timeliness deviation index is, the worse the timeliness of the neurosurgery data in the patient's medical record is, and the less likely it is to be used as a reference value for the patient's actual condition. The more likely it is that the data in the patient's case needs to be supplemented.

[0089] The logic for obtaining the data abnormal deviation coefficient is: obtaining the neurosurgery data in the patient case, and marking the neurosurgery data in the patient case as: , obtain the neurosurgery data recorded in the historical database, and mark the neurosurgery data recorded in the historical database as: , where r = 1, 2, 3, …, R, R is a positive integer, and r is the number of the total record of neurosurgery data q in the historical database;

[0090] It should be noted that the historical database stores a large amount of medical records about patients, including historical cases, diagnosis results, treatment plans, drug use, surgical records, etc. These data can help doctors make more accurate judgments and compare the current patient's condition with similar cases in history, so as to better diagnose, treat and predict.

[0091] The minimum similarity between the neurosurgery data in the patient case and the neurosurgery data recorded in the historical database is calculated using the following formula: ;in, is the minimum similarity between the neurosurgery data q and the neurosurgery data recorded in the historical database;

[0092] Calculate the data abnormal deviation coefficient, the calculation formula is: ;in, is the data abnormal deviation coefficient.

[0093] It can be seen from the formula that the larger the data abnormality deviation coefficient is, the greater the deviation between the neurosurgery data in the patient's case and the neurosurgery data recorded in the historical database is. This is because the historical database has retained the abnormal data of the patient's lesions, but the deviation is still large. In this case, the neurosurgery data in the patient's case may not be used as the patient's actual reference value, and it may be necessary to supplement the data in the patient's case.

[0094] Through comprehensive analysis of the time information and performance information of the patient's neurosurgery data, the synchronization time coordination coefficient, timeliness deviation index and data abnormality deviation coefficient are weighted and calculated to construct a data record evaluation model and a data record evaluation coefficient. The calculation formula of the data record evaluation coefficient is: ;in, is the data record evaluation coefficient, , , They are the proportional coefficients of synchronization time coordination coefficient, timeliness deviation index, and data anomaly deviation coefficient. , , Both are greater than 0.

[0095] It can be seen from the formula that the larger the synchronization time coordination coefficient, the timeliness deviation index and the data abnormality deviation coefficient, the larger the data record evaluation coefficient, which indicates that the neurosurgery data record in the current patient case is poor and may need to be re-recorded. Conversely, the smaller the synchronization time coordination coefficient, the timeliness deviation index and the data abnormality deviation coefficient, the smaller the data record evaluation coefficient, which indicates that the neurosurgery data record in the current patient case is good and may not need to be re-recorded.

[0096] A data record evaluation coefficient threshold is set, and the data record evaluation coefficient is compared with the data record evaluation coefficient threshold. If the data record evaluation coefficient is greater than the data record evaluation coefficient threshold, a re-recording signal is generated, indicating that the data may be incomplete, abnormal, or outdated. If the data record evaluation coefficient is less than the data record evaluation coefficient threshold, no signal is generated, indicating that the neurosurgery data is relatively complete and a more comprehensive assessment of the patient's condition can be made through the patient's medical record.

[0097] The present invention integrates and associates neurosurgery data in the hospital, determines the correlation between neurosurgery data, determines the synchronization time points of different types of neurosurgery data based on the correlation between neurosurgery data, quantifies the deviation of the synchronization time points of neurosurgery data in the patient's medical record, and determines whether the patient needs to supplement the neurosurgery data by collecting the timeliness and abnormal value of the neurosurgery data in the patient's medical record. The present invention, through an automated evaluation mechanism, helps to provide guidance plans for patients before they see a doctor, and guides patients to supplement the data by themselves, thereby reducing the workload of manual operations and avoiding the impact of incomplete or outdated data on the treatment effect.

[0098] 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.

[0099] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0105] 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 neurosurgery data record management system based on data monitoring, characterized in that: Specifically, it includes data fusion graph module, data analysis module, data acquisition module and data recording evaluation module, and signal connection between modules; The data fusion graph module is used to construct a data fusion graph based on the actual usage of neurosurgery data, and connect two related neurosurgery data through edges in the data fusion graph; A data analysis module, for obtaining the patient's identity information, determining the patient's medical history, extracting the examined neurosurgery data in the patient's medical history, determining the completeness of the patient's neurosurgery data, and generating an analysis signal; A data acquisition module, used for acquiring time information and performance information of the patient's neurosurgery data when generating the analysis signal, wherein the time information includes a synchronization time coordination coefficient and a timeliness deviation index, and the performance information includes a data abnormality deviation coefficient; The data record evaluation module is used to construct a data record evaluation model, generate a data record evaluation coefficient, compare the data record evaluation coefficient with a preset threshold, and determine whether to generate a supplementary recording signal.

2. A neurosurgery data record management system based on data monitoring according to claim 1, characterized in that: Construct a data fusion graph, including: In the data fusion graph, two types of related neurosurgery data are connected by edges, and the nodes in the data fusion graph represent different types of neurosurgery data; To ensure the combined use of different neurosurgical data, the data fusion map is fused according to the time synchronization rules, including determining the unified time base for all data, setting the time point of the preoperative neurosurgical data as the initial time point, and setting the time interval. Through the time points of different neurosurgical data, the lag relationship of the neurosurgical data is obtained.

3. A neurosurgery data record management system based on data monitoring according to claim 2, characterized in that: Determine the completeness of the patient's neurosurgical data, including: The completeness of the patient's neurosurgery data was determined by data coverage, which was calculated as follows: ;in, The data coverage of patients, The number of existing neurosurgery records for the patient, The number of neurosurgery data required for hospital physician standards; A data coverage threshold is set. If the data coverage of the neurosurgery data in the patient's medical record is greater than the data coverage threshold, an analysis signal is generated and the patient's neurosurgery data is further analyzed. If the data coverage of the neurosurgery data in the patient's medical record is less than the data coverage threshold, no analysis signal is generated and the patient is required to re-record the neurosurgery data.

4. A neurosurgery data record management system based on data monitoring according to claim 3, characterized in that: Synchronous time coordination coefficient, including: The acquisition logic of the synchronization time coordination coefficient is as follows: according to the data fusion map of neurosurgery data, two different types of neurosurgery data with correlation in the data fusion map are extracted, and the optimal cross-correlation and optimal lag value of the two different types of neurosurgery data are determined through the use history of the two different types of neurosurgery data; According to the usage history of two different types of neurosurgery data, the time point set of each use of neurosurgery data A and neurosurgery data B by doctors is obtained, and A and B are nodes connected by co-edges in the data fusion graph; The time point sets used by the doctors of neurosurgery data A and neurosurgery data B are marked as: and ,in, Number the different time points of neurosurgery data A in the doctor's usage history, Number the different time points of neurosurgery data B in the doctor's usage history; Use the nearest neighbor matching method to find the nearest time point in the neurosurgery data B time point set for each time point in the neurosurgery data A time point set, satisfying the expression: ,in, is the time point in the neurosurgery data A time point set, i=1, 2, 3, ..., n, Generate paired data for the time points in the neurosurgery data B time point set, j = 1, 2, 3, ..., m, and mark the paired data as: ; The cross-correlation between neurosurgery data A and neurosurgery data B at different lag values ​​was calculated using the following formula: ;in, is the cross-correlation between neurosurgery data A and neurosurgery data B at a lag value of τ; The cross-correlations of neurosurgery data A and neurosurgery data B under different lag values ​​τ are traversed to determine the optimal lag value. The expression of the optimal lag value is: ;in, is the optimal lag value for neurosurgery data A and neurosurgery data B; The time points of neurosurgery data A and neurosurgery data B in the patient's medical record are obtained, and the lag values ​​of neurosurgery data A and neurosurgery data B are determined. The calculation formula is: ;in, are the lag values ​​of neurosurgery data A and neurosurgery data B in the actual patient medical records; Calculate the lag value deviation of neurosurgery data A and neurosurgery data B using the following formula: ;in, is the lag value deviation between neurosurgery data A and neurosurgery data B, k=1, 2, 3, ..., K, K is a positive integer, k is the number of the nodes in the data fusion graph that are connected by the same edge in the data fusion graph, ; Calculate the synchronization time coordination coefficient, the calculation formula is: ;in, is the synchronization time coordination coefficient.

5. A neurosurgery data record management system based on data monitoring according to claim 4, characterized in that: Timeliness deviation index, including: The acquisition logic of the time-efficiency deviation index is: according to the usage records of different types of neurosurgery data, the time-efficiency decay models of different types of neurosurgery data are determined, and the time-efficiency decay models of different types of neurosurgery data are marked as: ,in, , is the optimal timeliness of different types of neurosurgery data, q = 1, 2, 3, ..., ,q is the number of different types of neurosurgery data, is the attenuation factor, t is the time point of neurosurgery data, Calculate the timeliness deviation index, the calculation formula is: ;in, is the time deviation index.

6. A neurosurgery data record management system based on data monitoring according to claim 5, characterized in that: Data anomaly deviation coefficient, including: The logic for obtaining the data abnormal deviation coefficient is: obtaining the neurosurgery data in the patient case, and marking the neurosurgery data in the patient case as: , obtain the neurosurgery data recorded in the historical database, and mark the neurosurgery data recorded in the historical database as: , where r = 1, 2, 3, …, R, R is a positive integer, and r is the number of the total record of neurosurgery data q in the historical database; The minimum similarity between the neurosurgery data in the patient case and the neurosurgery data recorded in the historical database is calculated using the following formula: ;in, is the minimum similarity between the neurosurgery data q and the neurosurgery data recorded in the historical database; Calculate the data abnormal deviation coefficient, the calculation formula is: ;in, is the data abnormal deviation coefficient.

7. A neurosurgery data record management system based on data monitoring according to claim 6, characterized in that: Construct a data record assessment model, including: Through comprehensive analysis of the time information and performance information of the patient's neurosurgery data, the synchronization time coordination coefficient, timeliness deviation index and data abnormality deviation coefficient are weighted and calculated to construct a data record evaluation model and a data record evaluation coefficient. The calculation formula of the data record evaluation coefficient is: ;in, is the data record evaluation coefficient, , , They are the proportional coefficients of synchronization time coordination coefficient, timeliness deviation index, and data anomaly deviation coefficient. , , Both are greater than 0.

8. A neurosurgery data record management system based on data monitoring according to claim 7, characterized in that: Determine whether to generate a make-up signal, including: Setting a data record evaluation coefficient threshold, and comparing the data record evaluation coefficient with the data record evaluation coefficient threshold; If the data record evaluation coefficient is greater than the data record evaluation coefficient threshold, a supplementary recording signal is generated; If the data record evaluation coefficient is less than the data record evaluation coefficient threshold, no signal is generated.

Images