A cardiac surgical post-operative follow-up management system

Abstract

The application relates to the technical field of postoperative follow-up, and discloses a heart surgery postoperative follow-up management system, which comprises the following steps: a data acquisition module is used for acquiring and storing health record information and multi-source medical data of a target patient; a data processing module is used for performing semantic analysis and structural processing on the multi-source medical data to obtain structured medical data; an index identification module is used for determining follow-up indexes of the target patient based on the structured medical data and the health record information; a sequence generation module is used for generating time sequence data of each follow-up index based on the structured medical data; a strategy generation module is used for generating a follow-up management strategy based on the time sequence data; and a first interaction module is used for sending the follow-up management strategy to a target patient terminal. The system provided by the application has a dynamic adjustment mechanism and intelligent updating capability, can effectively determine a follow-up management strategy according to the state of a patient, and has follow-up flexibility and pertinence.

Description

Technical Field

[0001] This invention relates to the field of postoperative follow-up technology, specifically to a postoperative follow-up management system for cardiac surgery. Background Technology

[0002] Post-cardiac surgery patients typically require long-term or even lifelong follow-up management, including anticoagulant or antiplatelet drug management, functional monitoring of prosthetic or repaired valves, assessment of the graft status after coronary artery bypass grafting, cardiac function follow-up, and early warning of post-operative complications. These patients generally have long disease courses, complex treatment pathways, and long follow-up periods, involving multiple follow-up indicators such as echocardiography, coagulation function, medication adherence, and changes in clinical symptoms, making management highly challenging.

[0003] Currently, routine clinical follow-up is difficult to individualize based on the patient's actual postoperative recovery, indicator trends, and risk levels. In the absence of systematic and intelligent follow-up tools, the quality of long-term follow-up heavily relies on the patient's self-management ability and the manual recording and organization by medical staff. Information collection is fragmented, data updates are delayed, and follow-up lacks flexibility and specificity, failing to achieve dynamic matching between follow-up management and the patient's condition. This is detrimental to long-term postoperative risk control and improvement of rehabilitation quality. Summary of the Invention

[0004] This invention provides a follow-up management system for cardiac surgery to solve the problem in the prior art that follow-up and dynamic matching of patient status cannot be achieved after cardiac surgery.

[0005] In a first aspect, the present invention provides a postoperative follow-up management system for cardiac surgery, the system comprising: The data acquisition module is used to acquire and store the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery. The data processing module is used to perform semantic parsing and structuring processing on multi-source medical data to obtain structured medical data. The indicator identification module is used to determine the follow-up indicators for target patients based on structured medical data and health record information. The sequence generation module is used to generate time series data for various follow-up indicators based on structured medical data. The strategy generation module is used to generate follow-up management strategies based on time series data. The first interaction module is used to send follow-up management strategies to the target patient's terminal.

[0006] This invention automatically collects and structures patient data related to cardiac surgery, automatically identifies key indicators specific to cardiac surgery follow-up, and performs trend analysis and complication risk prediction based on long-term data to generate personalized follow-up management strategies. The cardiac surgery postoperative follow-up management system provided in this embodiment is highly systematic, possessing dynamic adjustment mechanisms and intelligent update capabilities. It can effectively determine follow-up management strategies dynamically based on the patient's condition, offering flexibility and targeting to meet the needs of long-term, individualized, and refined postoperative management.

[0007] In one alternative implementation, the health record information includes: basic information and unique identification information of the target patient, and information related to the target patient's cardiac surgery.

[0008] In one alternative implementation, the multi-source medical data includes at least one of the following: Postoperative medical records of cardiac surgery, and / or, postoperative follow-up records of cardiac surgery; Postoperative examination report for cardiac surgery, including at least one of the following: echocardiogram report, laboratory test report, medical imaging report; Information describing symptoms after cardiac surgery, and / or, examination data after cardiac surgery.

[0009] In one alternative implementation, the data processing module is specifically used for: Based on a pre-built semantic parsing model, semantic parsing is performed on multi-source medical data.

[0010] In one alternative implementation, the follow-up indicators include at least one of the following: Functional indicators related to artificial valves; Patency of bypass grafts after coronary artery bypass grafting; Cardiac function assessment indicators; Indicators related to anticoagulation or antiplatelet therapy.

[0011] In one alternative implementation, the sequence generation module is specifically used for: Determine the time information corresponding to each follow-up indicator in structured medical data; Each follow-up indicator is mapped to a time series according to its corresponding time information to obtain time series data.

[0012] In one alternative implementation, the sequence generation module is further specifically used for: A trend chart is generated based on time series data, which is then sent to the target patient's terminal for visualization via an interactive module.

[0013] In one alternative implementation, the policy generation module is specifically used for: Based on time series data, determine the change values ​​of each follow-up indicator at adjacent time points; When the change in an indicator exceeds a preset threshold, a follow-up management strategy is generated. Follow-up management strategies include at least one of the following: follow-up reminder information, medication management tips, and re-examination recommendations.

[0014] In one alternative implementation, the system further includes: The data management module is used to acquire data from the data acquisition module, data processing module, indicator identification module, sequence generation module, and strategy generation module.

[0015] Secondly, a postoperative follow-up management system for cardiac surgery, suitable for target patient terminals, includes: The page display module is used to display the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery. The second interaction module is used to upload health record information and multi-source medical data to the data acquisition module of the first aspect or any corresponding embodiment; it is also used to receive follow-up management strategies and time series data sent by the first interaction module of the first aspect or any corresponding embodiment.

[0016] This invention enables continuous collection, semantic parsing, structured management, trend analysis, and follow-up strategy generation of postoperative follow-up data in cardiac surgery, transforming follow-up management from a method reliant on manual recording to a continuous, dynamic, and intelligent follow-up process. Attached Figure Description

[0017] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a structural block diagram of a cardiac surgery postoperative follow-up management system according to an embodiment of the present invention; Figure 2 This is another structural block diagram of the cardiac surgery postoperative follow-up management system according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the first page of a health record according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a page for uploading multi-source medical data according to an embodiment of the present invention; Figure 5This is a schematic diagram of the second page of a health record according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the third page of a health record according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the fourth page of a health record according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the fifth page of a health record according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the sixth page of a health record according to an embodiment of the present invention; Figure 10 This is a schematic diagram of time series data according to an embodiment of the present invention; Figure 11 This is a schematic diagram of scale management according to an embodiment of the present invention; Figure 12 This is a schematic diagram of medication management prompts according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0021] Currently, existing technologies for postoperative follow-up in cardiac surgery mainly fall into four categories: traditional manual follow-up methods (such as telephone follow-up, outpatient follow-up, and paper follow-up book registration), which rely on patient self-reporting, leading to information bias; time-consuming and labor-intensive process for medical staff to review medical records; non-standard follow-up content; and inability to accumulate data for scientific research and disease modeling. General chronic disease management tools based on apps or WeChat mini-programs lack a specialized knowledge system for postoperative cardiac surgery, making it unable to identify core follow-up indicators or conduct personalized risk assessments. Single OCR technology can only digitize paper medical records, recognizing characters but lacking medical semantic understanding capabilities, thus failing to extract specialized indicators, analyze the significance of follow-up, or provide... Medication reminders cannot meet the needs of intelligent follow-up; rule-based or template-based follow-up systems, due to their use of fixed question sets and lack of generalization ability, cannot adjust follow-up content according to individual patient conditions, nor can they automatically extract structured follow-up points or conduct cross-time point data analysis and risk prediction. These existing technologies share five core defects: they cannot achieve automated collection and structured organization of long-term postoperative follow-up data, cannot identify key follow-up indicators specific to cardiac surgery, cannot conduct long-term trend analysis based on historical medical records and health records, and lack intelligent and personalized postoperative management and interaction capabilities, making it difficult to meet the long-term, accurate, and intelligent follow-up management needs of cardiac surgery.

[0022] Therefore, this embodiment provides a postoperative follow-up management system for cardiac surgery, which can be implemented using a local hospital server, a cloud computing environment, or a hybrid deployment combining local and cloud environments. The system can interact with the hospital information system via a secure communication interface. The hospital information system includes at least a Hospital Information System (HIS), an Electronic Medical Record System (EMR), a Laboratory Information System (LIS), and a Picture Archiving and Communication System (PACS). Simultaneously, the system can also establish a communication connection with patient follow-up terminals via a network to achieve remote collection and feedback of follow-up data. Figure 1 This is a schematic diagram of the structure of a cardiac surgery postoperative follow-up management system according to an embodiment of the present invention, including a data acquisition module, a data processing module, an indicator recognition module, a sequence generation module, a strategy generation module, and a first interaction module, as detailed below.

[0023] The data acquisition module is used to acquire and store the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery.

[0024] The data processing module is used to perform semantic parsing and structuring processing on multi-source medical data to obtain structured medical data.

[0025] The indicator identification module is used to determine follow-up indicators for target patients based on structured medical data and health record information.

[0026] The sequence generation module is used to generate time series data for various follow-up indicators based on structured medical data.

[0027] The strategy generation module is used to generate follow-up management strategies based on time series data.

[0028] The first interaction module is used to send follow-up management strategies to the target patient's terminal.

[0029] Specifically, the data acquisition module can be used to acquire raw medical data related to postoperative follow-up of cardiac surgery from multi-source medical systems or patient terminals; the data acquisition module can also be used to store and maintain long-term health record information corresponding to the patient's unique identifier; the data processing module can also be used to perform semantic-level parsing on the raw medical data and convert it into a unified structured data format; the indicator identification module can be used to identify key indicators related to postoperative follow-up of cardiac surgery from structured data based on the patient's surgical type and postoperative status; the sequence generation module can be used to align and serialize the data of follow-up indicators at different follow-up time points; the strategy generation module can be used to evaluate the patient's postoperative status based on time series data and generate corresponding follow-up management strategies; the strategy generation module can also be used for complication risk prediction; the first interaction module is used to send follow-up reminders, medication reminders, risk warnings, follow-up visit suggestions, complication prediction results or management suggestions to the patient terminal or medical staff terminal.

[0030] In this embodiment, by automatically collecting and structuring patient data related to cardiac surgery, key indicators specific to cardiac surgery follow-up are automatically identified. Based on long-term data, trend analysis and complication risk prediction are performed to generate personalized follow-up management strategies. The cardiac surgery postoperative follow-up management system provided in this embodiment is highly systematic, possessing dynamic adjustment mechanisms and intelligent update capabilities. It can effectively determine follow-up management strategies dynamically based on the patient's condition, offering flexibility and targeting to meet the needs of long-term, individualized, and refined postoperative management.

[0031] This embodiment also provides a postoperative follow-up management system for cardiac surgery, which can be used on a local hospital server, in a cloud computing environment, or implemented using a hybrid deployment method combining local and cloud environments. Details are as follows.

[0032] The data acquisition module is used to acquire and store the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery.

[0033] The target patients are those who have undergone cardiac surgery, and this invention is mainly for the follow-up management of patients after cardiac surgery.

[0034] This embodiment uses a cardiac surgery postoperative follow-up management system deployed on a hospital's local server as an example. Health record information and multi-source medical data can be obtained manually, retrieved from the hospital's local database, or uploaded by the patient on a terminal device such as a mobile phone or computer and sent to the hospital's local server. After obtaining the health record information, a health record corresponding to the patient's unique identifier can be further established as an index basis for subsequent follow-up processing.

[0035] In some alternative implementations, a simplified health record can be constructed by selecting only the core information directly related to postoperative follow-up; in contrast, constructing a health record containing complete postoperative information can provide higher accuracy in subsequent risk assessment and follow-up strategy generation.

[0036] In some optional implementations, the health record information includes: basic information and unique identification information of the target patient, and information related to the target patient's cardiac surgery. The cardiac surgery information includes the type of surgery, the surgery time, and information on the implanted or treated objects during the surgery, including the type and model of the artificial valve, the number and corresponding location of the bypass grafts, etc.; it may also include baseline examination indicators at the first postoperative follow-up or discharge and their corresponding time information, etc.

[0037] The cardiac surgery information in the patient's health record is used to provide surgical background information to the subsequent cardiac surgery follow-up indicator identification module, so as to limit the identification scope of the follow-up indicators. This ensures that the follow-up data collected and processed in the future corresponds to the patient's specific surgical background, thereby avoiding the problem of follow-up data being out of sync with surgical information.

[0038] In some optional implementations, the multi-source medical data includes at least one of the following: postoperative cardiac surgery medical records, and / or postoperative cardiac surgery follow-up visit records; postoperative cardiac surgery examination reports, which include at least one of the following: echocardiogram reports, laboratory test reports, and medical imaging reports; postoperative cardiac surgery symptom description information, and / or postoperative cardiac surgery examination data. The postoperative cardiac surgery symptom description information may be symptom description information actively submitted by the patient through a follow-up terminal during the follow-up process.

[0039] The sources of multi-source medical data include, but are not limited to, automatic synchronous collection through data interfaces with hospital information systems or patient follow-up terminals. Data can also be collected manually or by batch importing historical follow-up data. Among these methods, interface synchronization can reduce manual intervention and improve the real-time performance of data collection, while batch import is more suitable for scenarios involving centralized follow-up management of patients who have previously undergone surgery.

[0040] In some alternative implementations, regarding the selection of data sources, postoperative follow-up data can be obtained only from the hospital information system without collecting data submitted by the patient; however, in comparison, collecting both hospital system data and patient follow-up data can more comprehensively reflect the changes in the patient's postoperative condition.

[0041] In some alternative implementations, regarding the granularity of data processing, the medical data acquisition module may simply collect and transmit the raw data, or it may perform preliminary cleaning or field classification processing on the data during the acquisition stage; in particular, performing data classification processing in advance can reduce the processing complexity of the subsequent semantic parsing module.

[0042] By choosing the different implementation methods described above, a flexible balance can be struck between system complexity, real-time performance, and data integrity.

[0043] The acquired medical data can be unstructured text, semi-structured data, or structured data. After data acquisition, the data processing module will perform preliminary data format identification and classification on the collected data, and then transfer the corresponding raw data to the medical semantic analysis and structuring processing module for use in subsequent semantic analysis steps. This enables centralized collection of postoperative cardiac follow-up data, providing a complete data foundation for subsequent follow-up indicator identification and trend analysis.

[0044] The data processing module is used to perform semantic parsing and structuring processing on multi-source medical data to obtain structured medical data.

[0045] In some alternative implementations, the data processing module is specifically used for: Based on a pre-built semantic parsing model, semantic parsing is performed on multi-source medical data.

[0046] In this embodiment, semantic parsing is not a simple character recognition of text, but rather a semantic parsing model trained or optimized in the medical field to perform semantic understanding processing on the content of the original multi-source medical data in order to identify and extract the following information: medical entity information related to postoperative follow-up of cardiac surgery; the name, corresponding value and unit of measurement of examination or test indicators; the time information of the medical data generation and the follow-up node information to which it belongs.

[0047] After completing the semantic parsing described above, the parsing results are converted into a unified data structure and transmitted as structured medical data to the cardiac surgery follow-up indicator identification step. This approach overcomes the limitations of traditional character-level recognition or rule-based template methods, which heavily rely on medical record formats and presentation styles, enabling follow-up information extraction based on medical semantic understanding.

[0048] In some alternative implementations, medical data can be parsed using rule-based templates or keyword matching. This approach is simple to implement and has low computational overhead, but it is less adaptable to variations in medical record formats and complex semantic expressions. In contrast, semantic parsing based on language models maintains higher parsing accuracy across different hospitals, text structures, and expressions, making it more suitable for long-term follow-up scenarios after cardiac surgery.

[0049] In this embodiment, by introducing medical semantic parsing based on a large language model into the follow-up management system, unified semantic understanding and structured extraction can be achieved for postoperative medical record texts, examination reports, and patient follow-up descriptions from heterogeneous sources and with inconsistent formats, thereby forming a patient-centered long-term follow-up data set. Compared with existing methods that rely on manual processing or simple OCR recognition, this embodiment can automatically identify core postoperative elements such as surgical procedures, prosthetic valve types, and bypass graft information; uniformly archive follow-up data according to patient, indicator, and time dimensions; and significantly reduce the risk of omissions and misfilling during manual follow-up. This technology directly solves the problems of fragmented and unreusable follow-up data in existing technologies. It realizes the automatic, structured collection and long-term unified management of postoperative follow-up data in cardiac surgery.

[0050] The indicator identification module is used to determine follow-up indicators for target patients based on structured medical data and health record information.

[0051] The generated structured medical data can be further filtered and categorized based on information related to cardiac surgery found in health records. Specifically, follow-up indicators can be automatically identified from the structured medical data based on the patient's specific surgical type and postoperative condition.

[0052] In some alternative implementations, the follow-up indicators include at least one of the following: functional indicators related to the prosthetic valve; patency of the bypass graft or related assessment indicators after coronary artery bypass grafting; indicators related to cardiac function assessment; and indicators related to anticoagulation or antiplatelet therapy.

[0053] The identified follow-up indicators are linked and stored with the patient's health record and then transmitted to the follow-up sequence generation module. This allows the determination of follow-up indicators to be dynamically matched with the patient's specific surgical procedure, thereby improving the relevance and clinical relevance of postoperative follow-up content.

[0054] In some alternative implementations, a fixed set of follow-up indicators can be used to conduct uniform follow-up for all postoperative patients. This approach is simple to implement, but it cannot distinguish the differences in follow-up between different surgical types. In contrast, dynamically identifying follow-up indicators based on the patient's specific surgical procedure is more suitable for application scenarios in cardiac surgery where there are diverse surgical procedures and significant differences in follow-up focus.

[0055] In this embodiment, by combining postoperative health record information from cardiac surgery with semantic analysis results, key follow-up indicators related to the patient's specific surgical procedure can be automatically identified from follow-up data. These indicators include, but are not limited to, artificial valve functional parameters, bypass vessel-related indicators, and cardiac function parameters. Compared to general chronic disease management systems that only support basic vital sign records, the follow-up indicators in this embodiment are not preset fixed fields but are dynamically determined based on the patient's surgical procedure. The same indicator can be automatically associated and continuously tracked at different time points; it can distinguish between "numerical existence" and "numerical significance for clinical follow-up." This achieves true specialist follow-up capability after cardiac surgery. It realizes the automatic identification and continuous tracking of key follow-up indicators at the specialist level in cardiac surgery.

[0056] The sequence generation module is used to generate time series data for various follow-up indicators based on structured medical data.

[0057] In some optional implementations, the sequence generation module is specifically used to: determine the time information corresponding to each follow-up indicator in the structured medical data; map each follow-up indicator to a time series according to the corresponding time information to obtain time series data.

[0058] Based on the time information and follow-up node identifiers corresponding to the follow-up data in structured medical data, the follow-up indicators are sorted and aligned, and corresponding time-series data structures are constructed to represent the changes of the follow-up indicators during the postoperative follow-up period. The constructed time-series data is used for subsequent trend analysis, anomaly identification, and risk assessment. This approach enables the system to model and analyze the long-term changes of key postoperative indicators in cardiac surgery, moving beyond static judgments based on single follow-up results and providing a data foundation for dynamic follow-up and risk assessment.

[0059] In some alternative implementations, only the most recent follow-up data can be stored and analyzed without constructing a complete time series; this approach is simple to implement but cannot reflect long-term trends in postoperative condition. In contrast, constructing a time series data structure across follow-up nodes can support long-term trend analysis and is more suitable for the long-term management needs after cardiac surgery.

[0060] In this embodiment, by introducing timestamps and follow-up node identifiers into the structured follow-up data, automatic alignment and time series modeling of the same indicator across different follow-up periods are achieved. Based on this technology, the system can automatically generate the changing trends of key indicators; identify abnormal fluctuations or long-term deviations from the reference range; and provide a continuous data foundation for subsequent risk assessment modules. Compared with existing systems that can only make judgments based on a single follow-up visit, this solution technically achieves a computer-processable representation of long-term state evolution, providing a technical foundation for the early detection of complications. It enables trend analysis and dynamic risk assessment of follow-up data across time points.

[0061] The strategy generation module is used to generate follow-up management strategies based on time series data.

[0062] In this embodiment, based on data parsing and trend analysis, a combination of rule-based and statistical models can be used to generate follow-up reminders, medication management tips, and re-examination suggestions tailored to the patient's specific situation. This makes the follow-up content less fixed and more relevant to the patient's surgical type and follow-up status; the reminder logic originates from changes in the patient's own data, rather than a uniform template; significantly improving patient compliance and reducing the follow-up burden on medical staff. This technological effect is unattainable by existing methods based on fixed questionnaires or manual telephone follow-ups. It enables the automatic generation of individualized postoperative management strategies and intelligent follow-up interaction.

[0063] Time-series data can be used to analyze and evaluate a patient's postoperative condition. Specifically, the system combines medical rules, statistical models, or historical follow-up data to assess the changing trends of follow-up indicators within the follow-up period, and generates a follow-up management strategy that matches the patient's current follow-up status.

[0064] Follow-up management strategies include at least one of the following: follow-up reminder information, medication management tips, and re-examination recommendations.

[0065] Through the above methods, the follow-up system can generate targeted management strategies based on the dynamic changes in follow-up data, thereby achieving proactive management of postoperative risks in cardiac surgery.

[0066] In some optional implementations, the strategy generation module is specifically used to: determine the change values ​​of each follow-up indicator at adjacent times based on time series data; and generate a follow-up management strategy when the change value of the indicator exceeds a preset threshold range. In this embodiment, each follow-up indicator is judged based on a preset threshold, and corresponding reminder information is generated. This method is simple to implement and makes it easier to detect abnormal states.

[0067] It can also be used to comprehensively evaluate changes in follow-up indicators based on time series data, which is more conducive to identifying potential risk changes and is suitable for long-term follow-up management scenarios after cardiac surgery.

[0068] The first interaction module is used to send follow-up management strategies to the target patient's terminal.

[0069] Follow-up management strategies can be dynamically generated based on the patient's current follow-up status, and can provide patients or medical staff with information such as follow-up arrangements, medication management, or follow-up visit suggestions.

[0070] The first interactive module can output the generated follow-up management strategy to the patient's terminal or other medical staff's terminal via a human-computer interaction interface or message push. This enables the timely communication of the follow-up management strategy without increasing the manual follow-up burden on medical staff.

[0071] This embodiment improves the timeliness and consistency of follow-up information transmission through automated information output, making it more suitable for follow-up management scenarios with a large number of patients.

[0072] In this embodiment, the follow-up data of patients after cardiac surgery is automatically collected, semantically parsed, structured, analyzed, and processed interactively. This can effectively determine the follow-up management strategy dynamically based on the patient's status, providing flexibility and targeting, and meeting the needs of long-term, individualized, and refined postoperative management.

[0073] In some optional implementations, the sequence generation module is further specifically used for: Trend charts are generated based on time-series data and sent to the target patient's terminal for visualization via an interactive module. This allows patients to intuitively understand changes in their postoperative indicators, effectively improving follow-up compliance and reducing the follow-up burden on medical staff.

[0074] In some alternative implementations, the system further includes: The data management module is used to acquire data from the data acquisition module, data processing module, indicator identification module, sequence generation module, and strategy generation module.

[0075] Specifically, with authorization, follow-up data is de-identified or anonymized and stored according to a unified data structure standard to support subsequent statistical analysis or research modeling. The data management module supports statistical analysis of follow-up data according to indicator type, follow-up time, or patient characteristics for at least one of the following purposes: statistical analysis of postoperative follow-up in cardiac surgery; construction or validation of postoperative prognostic models; and assessment of follow-up quality or follow-up compliance.

[0076] In this embodiment, data generated by different modules is stored and managed in a unified manner, which enables the natural conversion of clinical follow-up data into scientific research data without adding extra operating procedures, thereby enhancing the reusability of the follow-up system in scientific research applications.

[0077] In some alternative implementations, follow-up data can be stored long-term without statistical analysis; this approach is simple to implement but has limited research value. In contrast, storing follow-up data in a unified structure and supporting statistical analysis can better support relevant scientific research after cardiac surgery.

[0078] In this embodiment, by storing data in a standardized structure during the follow-up process, follow-up management and scientific research data collection can be completed simultaneously without increasing the workload. Follow-up data naturally possesses the conditions for statistical and group analysis, and can be directly used for retrospective studies or model training; it can also avoid data bias caused by subsequent manual reprocessing.

[0079] This embodiment provides a postoperative follow-up management system for cardiac surgery, which can be used on a patient terminal. Figure 2 This is a schematic diagram of the structure of a cardiac surgery postoperative follow-up management system according to an embodiment of the present invention, including a page display module and a second interaction module, as detailed below.

[0080] The page display module is used to display the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery. The second interaction module is used to upload health record information and multi-source medical data to the data acquisition module in any of the above embodiments or the implementation corresponding to the embodiments; it is also used to receive follow-up management strategies and time series data sent by the first interaction module in any of the above embodiments or the implementation corresponding to the embodiments.

[0081] The following is a complete application example: This embodiment uses a patient who has undergone cardiac surgery as an example to illustrate the specific application process of the postoperative cardiac surgery follow-up management system in the form of a mobile terminal applet. This embodiment is only used to illustrate the technical solution of the present invention and does not constitute a limitation on the scope of protection of the present invention.

[0082] Application environment and system deployment: In this embodiment, the cardiac surgery postoperative follow-up management system is deployed in a cloud computing environment and establishes a communication connection with a mobile terminal applet through a secure communication interface. The mobile terminal applet serves as the patient-side follow-up interaction portal, allowing patients to upload postoperative follow-up-related data, view follow-up information, and receive follow-up management prompts.

[0083] The mini-program serves as the front-end interactive carrier of the system, and its functions correspond to the medical data acquisition module and the follow-up interaction and information output module in the aforementioned system structure; while the parsing, management, analysis of follow-up data and the generation of follow-up strategies are all completed by the back-end computer program.

[0084] Postoperative health record initialization: After a patient completes cardiac surgery and is discharged, the system creates a health record in the background based on the patient's postoperative medical records, corresponding to that patient's unique identifier. The health record records the patient's basic information, surgery type, surgery time, information on intraoperative procedures such as prosthetic valves or bypass grafts, and baseline examination indicators at discharge or first follow-up. Patients can view their corresponding health record content and refer to it through a mobile app. Figure 3 As shown, this forms the basis for long-term follow-up management centered on the patient's surgical procedure.

[0085] Multi-source medical data acquisition: During patient follow-up, the system acquires multi-source medical data related to postoperative follow-up through the data acquisition module. In this embodiment, the multi-source medical data is mainly obtained by patients actively uploading data via a mobile terminal applet, as described above. Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 , Figure 9 As shown.

[0086] Specifically, patients can upload postoperative examination reports, test result images, symptom descriptions during follow-up, or other postoperative management-related information via the mini-program. Upon receiving the uploaded data, the system transmits it as raw medical data to the backend system for subsequent medical semantic parsing and structured processing.

[0087] Using the above methods, the system can continuously collect postoperative follow-up data for cardiac surgery without directly connecting to the hospital's information system.

[0088] Medical semantic parsing and structured processing: The system performs medical semantic parsing on the raw medical data uploaded by patients. Through the medical semantic parsing and structured processing module, the system performs semantic understanding processing on follow-up data in text or image form, automatically identifying medical entities, examination indicator names, corresponding values ​​and units of measurement related to postoperative follow-up of cardiac surgery, and extracting the time information of data generation and follow-up node information.

[0089] The parsed data is converted into a unified data structure format, which serves as input data for subsequent follow-up indicator identification and time series modeling.

[0090] Identification of cardiac surgery follow-up indicators: The system combines surgical type information recorded in the patient's health record to further filter and classify structured follow-up data. For example, for patients who have undergone artificial valve replacement surgery, the system automatically identifies and associates indicators related to artificial valve function and anticoagulation therapy; for patients who have undergone coronary artery bypass grafting, the system automatically identifies follow-up indicators related to bypass vessel patency. In this way, the system generates a set of follow-up indicators dynamically matched to the patient's specific surgical procedure.

[0091] Follow-up node management and time series modeling: The system aligns and sorts data collected at different follow-up time points for the same follow-up indicator based on the time information and follow-up node identifiers, and constructs the corresponding time series data structure, referring to... Figure 10 As shown.

[0092] In the mobile app, patients can view trend charts of various follow-up indicators over time to intuitively understand the changes in postoperative indicators; the time series data also serves as an important input for subsequent risk assessment.

[0093] Risk assessment and follow-up strategy generation: The system analyzes and evaluates patients' postoperative status based on the constructed follow-up indicator time series data. When the system detects abnormal fluctuations or long-term deviations from the normal range in the follow-up indicators, it automatically generates corresponding follow-up management strategies.

[0094] Follow-up management strategies include follow-up reminders, medication management tips, and suggestions for follow-up visits or check-ups, used to guide patients in subsequent follow-up management. (Refer to...) Figure 11 and Figure 12 As shown.

[0095] Follow-up interaction and information output: The system outputs the generated follow-up management strategy to the mobile terminal applet through the follow-up interaction and information output module, prompting patients to view relevant follow-up information.

[0096] Patients can use the mini-program to view their current follow-up status, follow-up reminders, and management suggestions, thus completing the follow-up interaction process with the system.

[0097] Scientific research data management and analysis: The structured follow-up data generated during the follow-up management process is de-identified with authorization and stored uniformly in the scientific research data management module.

[0098] The system supports statistical analysis of follow-up data according to follow-up indicator type, follow-up time, or patient characteristics, which can be used for postoperative prognosis research, follow-up quality assessment, or model building.

[0099] Through this embodiment, the system realizes the continuous collection, semantic parsing, structured management, trend analysis, and follow-up strategy generation of postoperative follow-up data in the form of a mobile terminal applet, transforming follow-up management from a method that relies on manual recording to a continuous, dynamic, and intelligent follow-up process; at the same time, it achieves the synchronous accumulation of follow-up data into scientific research data without increasing the additional clinical operation burden.

[0100] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A follow-up management system for cardiac surgery, characterized in that, The system includes: The data acquisition module is used to acquire and store the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery. The data processing module is used to perform semantic parsing and structuring processing on the multi-source medical data to obtain structured medical data; The indicator identification module is used to determine the follow-up indicators of the target patient based on the structured medical data and the health record information. The sequence generation module is used to generate time series data of each of the follow-up indicators based on the structured medical data; The strategy generation module is used to generate follow-up management strategies based on the time series data; The first interaction module is used to send the follow-up management strategy to the target patient's terminal.

2. The system according to claim 1, characterized in that, The health record information includes: the target patient's basic information and unique identifier, and information related to the target patient's cardiac surgery.

3. The system according to claim 1, characterized in that, The multi-source medical data includes at least one of the following: Postoperative medical records of cardiac surgery, and / or, postoperative follow-up records of cardiac surgery; Postoperative examination report for cardiac surgery, wherein the examination report includes at least one of the following: echocardiogram report, laboratory test report, medical imaging report; Information describing symptoms after cardiac surgery, and / or, examination data after cardiac surgery.

4. The system according to claim 1, characterized in that, The data processing module is specifically used for: Based on a pre-built semantic parsing model, semantic parsing is performed on the multi-source medical data.

5. The system according to claim 1, characterized in that, The follow-up indicators include at least one of the following: Functional indicators related to artificial valves; Patency of bypass grafts after coronary artery bypass grafting; Cardiac function assessment indicators; Indicators related to anticoagulation or antiplatelet therapy.

6. The system according to claim 1, characterized in that, The sequence generation module is specifically used for: Determine the time information corresponding to each follow-up indicator in the structured medical data; Each of the follow-up indicators is mapped to a time series according to the corresponding time information to obtain the time series data.

7. The system according to claim 1, characterized in that, The sequence generation module is also specifically used for: A trend chart is generated based on time series data, which is then sent to the target patient's terminal for visualization via the interactive module.

8. The system according to claim 1, characterized in that, The strategy generation module is specifically used for: Based on the time series data, determine the change values ​​of each follow-up indicator at adjacent time points; When the change value of the indicator exceeds a preset threshold range, a follow-up management strategy is generated; The follow-up management strategy includes at least one of the following: follow-up reminder information, medication management prompts, and re-examination recommendations.

9. The system according to claim 1, characterized in that, The system also includes: The data management module is used to acquire data obtained by the data acquisition module, the data processing module, the indicator identification module, the sequence generation module, and the strategy generation module.

10. A follow-up management system for cardiac surgery, characterized in that, The system, applicable to a target patient terminal, includes: The page display module is used to display the target patient's health record information and multi-source medical data; the multi-source medical data includes data related to postoperative and follow-up cardiac surgery. The second interaction module is used to upload the health record information and the multi-source medical data to the data acquisition module of the system according to any one of claims 1 to 9; and is also used to receive the follow-up management strategy and time series data sent by the first interaction module of the system according to any one of claims 1 to 9.

Images