Multi-campus data intercommunication management method and system

Abstract

This invention relates to a data interoperability management method and system for multiple hospital campuses, comprising the following steps: verifying the uniqueness of patient master index data from each hospital campus to obtain standardized patient identification codes; mapping historical medical records from each hospital campus based on the standardized patient identification codes to obtain a cross-hospital campus medical relationship table; generating image retrieval instructions based on the cross-hospital campus medical relationship table and retrieving DICOM images from the PACS systems of each hospital campus based on the image retrieval instructions; extracting keyframes from the DICOM images to obtain structured image summaries; and displaying the cross-hospital campus medical relationship table and the structured image summaries on terminals in multiple hospital campuses to obtain an interactive cross-hospital data interface. This invention solves the technical problem that when a patient has undergone examinations in other hospital campuses, newly attending physicians often find it difficult to quickly access previous imaging data, requiring repeated examinations, which increases the burden on patients and poses health risks due to cumulative radiation.

Description

Technical Field

[0001] This invention relates to the field of data interoperability management technology, and in particular to a data interoperability management method and system for multiple campuses. Background Technology

[0002] Medical imaging is a crucial basis for disease diagnosis and treatment assessment, but currently, most hospital PACS systems are still limited to operation within a single hospital campus. When a patient has undergone examinations at other campuses, newly admitted doctors often struggle to quickly access previous imaging data, frequently requiring repeated examinations. This increases the burden on patients and may also pose health risks due to cumulative radiation exposure. Even when some institutions attempt to share image files through manual copying or network transmission, issues such as inconsistent formats, cumbersome access procedures, and varying image quality are prevalent, severely hindering the efficiency of collaborative diagnosis and treatment. Summary of the Invention

[0003] The main technical problem addressed in this application is to provide a data interoperability management method and system for multiple hospital campuses. This solves the problem that when a patient has undergone examinations at other hospital campuses, newly admitted doctors often find it difficult to quickly access previous imaging data, requiring repeated examinations, which increases the burden on patients and can also lead to health risks due to cumulative radiation.

[0004] To address the aforementioned technical issues, this application employs a multi-campus data interoperability management method, comprising the following steps: The uniqueness of the patient master index data obtained from each hospital area is verified to obtain a standardized patient identification code. Based on the standardized patient identification code, the historical medical records of each hospital area are associated and mapped to obtain a cross-hospital medical relationship table. Based on the cross-hospital visitation relationship table, an image retrieval instruction is generated, and DICOM images are retrieved from the PACS systems of each hospital based on the image retrieval instruction; Keyframes are extracted from the DICOM image to obtain a structured image summary, which is then displayed on multi-hospital terminals based on the cross-hospital visitation relationship table and the structured image summary, resulting in an interactive cross-hospital data interface.

[0005] Furthermore, the step of verifying the uniqueness of patient identity in the master index data of each hospital area to obtain a standardized patient identification code includes: The patient master index data of each hospital area is processed by field extraction and cleaning to obtain standardized master index fields including patient name, ID number, date of birth and medical card number. The standardized master index fields are then matched and redundant data is removed using preset field rules to obtain deduplicated master index data. Based on the deduplicated master index data, identity feature association matching is performed to obtain the multi-hospital master index association records of the same patient, and the multi-hospital master index association records are uniquely identified and encoded to obtain a standardized patient identification code.

[0006] Furthermore, the process of mapping historical medical records across different hospital districts based on the standardized patient identification code to obtain a cross-hospital district medical relationship table includes: Data is extracted from the historical medical records of each hospital area to obtain a set of medical information including medical time, department, diagnosis result and examination items. The medical time field in the medical information set is then processed to standardize the time format to obtain standard time medical information. Based on the standardized patient identification code, the standard time medical visit information is associated and matched, and all standard time medical visit information corresponding to the same standardized patient identification code is collected together to obtain the cross-hospital medical visit information set of the same patient. The cross-hospital medical visit information set of the same patient is sorted according to the order of medical visit time to generate a cross-hospital medical visit relationship table.

[0007] Furthermore, the step of generating image retrieval instructions based on the cross-hospital visitation relationship table, and retrieving DICOM images from the PACS systems of each hospital based on the image retrieval instructions, includes: Task information is extracted from the cross-hospital visit relationship table to obtain a set of key task information containing standardized patient identification codes, examination items, and examination hospital. The field format of the examination items in the set of key task information is converted to obtain examination item codes that conform to the PACS system interface specifications. Based on the patient's standardized identification code and examination item code, an image retrieval instruction is generated according to a preset instruction generation rule; Based on the image retrieval command, and in accordance with the communication protocol of each hospital's PACS system, a retrieval request is sent to the corresponding hospital's PACS system, and DICOM images returned by each hospital's PACS system are received.

[0008] Furthermore, the keyframe extraction of the DICOM image to obtain a structured image summary includes: The DICOM image is subjected to frame sequence analysis to obtain an image frame sequence, and the image frame sequence is filtered according to a preset frame filtering rule to obtain a key frame candidate set; wherein, the preset frame filtering rule includes a threshold set based on the clarity of the image frame sequence and key lesion features; Image features are extracted from each frame in the candidate keyframe set to obtain image feature information including lesion location, lesion morphology, and image grayscale value. The image feature information is then structured to obtain a structured image summary.

[0009] Furthermore, the cross-hospital visitation relationship table and the structured image summary are displayed on multi-hospital terminals to obtain an interactive cross-hospital data interface, including: The cross-hospital visitation relationship table is converted into a data format to obtain visitation data adapted for terminal display. At the same time, the structured image summary is converted into an image format to obtain image data adapted for terminal display. Based on the medical data and image data, the layout of the interface of the multi-hospital terminal is planned to obtain an adjustable layout interface, and the medical data and image data in the adjustable layout interface are associated and marked to obtain an associated and marked interface. By setting interactive interface elements in the associated marker interface according to preset interaction rules, an interactive cross-department data interface is formed.

[0010] Furthermore, based on the medical data and image data, the layout planning of the interface on the multi-hospital terminal is performed to obtain an adjustable layout interface, including: The medical data is divided into display areas to obtain a medical information layout table, and the image data is configured for display based on the medical information layout table to obtain an image display layout diagram. The scaling ratio of the image display layout is calculated to obtain adaptive layout parameters including image scaling ratio, display resolution, and margin settings. Based on the patient information layout table and adaptive layout parameters, a layout plan is performed on the interface of the multi-hospital terminal to obtain a preliminary layout interface. Based on the preliminary layout interface, a data scroll bar and an image scaling control are set to obtain an adjustable layout interface.

[0011] The present invention also provides a data interoperability management device for multiple hospital campuses, comprising: The acquisition module is used to verify the uniqueness of the patient master index data of each hospital area, obtain a standardized patient identification code, and perform association mapping on the historical medical records of each hospital area based on the standardized patient identification code to obtain a cross-hospital medical relationship table. The retrieval module is used to generate image retrieval instructions based on the cross-hospital visitation relationship table, and retrieve DICOM images from the PACS systems of each hospital based on the image retrieval instructions; The display module is used to extract keyframes from the DICOM image to obtain a structured image summary, and display it on multi-hospital terminals based on the cross-hospital visitation relationship table and the structured image summary to obtain an interactive cross-hospital data interface.

[0012] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above methods.

[0013] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the above methods.

[0014] The above solution verifies the uniqueness of patient identity in the master index data of each hospital area to obtain standardized patient identification codes. Based on these standardized patient identification codes, it maps the historical medical records of each hospital area to obtain a cross-hospital medical relationship table. Based on this table, it generates image retrieval instructions and retrieves DICOM images from the PACS systems of each hospital area. Keyframes are extracted from the DICOM images to obtain structured image summaries. These summaries are then displayed on terminals across multiple hospital areas, providing an interactive cross-hospital data interface. This solution addresses the technical problem that when a patient has undergone examinations at other hospitals, newly attending physicians often struggle to quickly access past imaging data, requiring repeated examinations, which increases the burden on patients and poses health risks due to cumulative radiation. Furthermore, it addresses the challenges of large volumes of medical image data and time-consuming browsing by introducing intelligent keyframe filtering technology. This extracts the truly valuable images from a single CT or MRI scan to form a summary, which is then displayed along with a timeline and diagnostic conclusions. In this way, clinicians can grasp the key points of disease changes without having to go through hundreds of images from beginning to end. Especially in the fast-paced outpatient clinic, this greatly improves the efficiency of image reading and the continuity of diagnosis and treatment. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram illustrating the steps of a multi-campus data interoperability management method in one embodiment of the present invention; Figure 2 This is a structural block diagram of a multi-campus data interoperability management device according to an embodiment of the present invention; Figure 3 This is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0017] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0019] Specifically, the multi-campus data interoperability management method of this embodiment includes the following steps: like Figure 1 As shown, Figure 1 This invention provides a method for managing data interoperability across multiple hospital campuses, comprising the following steps: Step S1: Verify the uniqueness of the patient master index data obtained from each hospital area to obtain a standardized patient identification code. Based on the standardized patient identification code, perform an association mapping on the historical medical records of each hospital area to obtain a cross-hospital medical relationship table.

[0020] Specifically, after obtaining the patient master index data from each hospital, the first step is to verify the uniqueness of the identity. This step relies on comparing fields such as name, gender, date of birth, ID number, and mobile phone number, using a fuzzy matching algorithm to handle input errors. For example, "Zhang Wei" and "Zhang Wei" are considered similar. Then, a weighted score is used to determine whether they are the same person. After confirmation, a unique standardized patient identification code is generated, such as a globally unique UUID. Then, this code is used to retrieve all the patient's historical medical records from the databases of each hospital, and they are strung together in chronological order to form a cross-hospital medical relationship table. For example, a lung CT scan done by someone at Hospital A in 2023 and a follow-up report at Hospital B in 2024 are automatically grouped onto the same timeline to achieve data linking.

[0021] Step S2: Generate an image retrieval instruction based on the cross-hospital visitation relationship table, and retrieve DICOM images from the PACS systems of each hospital based on the image retrieval instruction.

[0022] Specifically, after establishing the cross-hospital visitation relationship table, the system will read the recorded visitation information one by one. For each record involving imaging examinations, such as a patient's cranial MRI performed at Hospital B in March 2024, the system will automatically generate a retrieval command with parameters such as the target PACS address, patient ID, and examination number. These commands will be sent to the corresponding hospital's PACS server via HL7 or DICOM WADO-URI protocol, triggering image data return and pulling the original DICOM file to the unified access platform to prepare for subsequent processing.

[0023] Step S3: Extract keyframes from the DICOM image to obtain a structured image summary, and display it on a multi-hospital terminal based on the cross-hospital visitation relationship table and the structured image summary to obtain an interactive cross-hospital data interface.

[0024] Specifically, after obtaining the DICOM image, a pre-trained deep learning model is used to scan each frame, identifying key layers containing lesions or anatomical landmarks, such as the largest cross-section of a lung nodule on a CT axial image. These frames are then extracted to form a structured image summary. Combined with the time sequence information in the cross-hospital visit relationship table, the summary images of each examination are arranged and displayed on the terminal interface according to the timeline. Doctors can click on a thumbnail to bring up the complete image, realizing the linkage and browsing of cross-hospital data.

[0025] In a specific embodiment, the step of performing identity uniqueness verification on the obtained patient master index data from each hospital area to obtain a standardized patient identification code includes: The patient master index data of each hospital area is processed by field extraction and cleaning to obtain standardized master index fields including patient name, ID number, date of birth and medical card number. The standardized master index fields are then matched and redundant data is removed using preset field rules to obtain deduplicated master index data. Based on the deduplicated master index data, identity feature association matching is performed to obtain the multi-hospital master index association records of the same patient, and the multi-hospital master index association records are uniquely identified and encoded to obtain a standardized patient identification code.

[0026] Specifically, after extracting patient master index data from the HIS systems of each hospital, the first step is field extraction and cleaning. This step corresponds to the specific implementation of "extracting and cleaning fields from the patient master index data of each hospital." In practice, the original data table is read, and core fields such as name, ID number, date of birth, and medical card number are extracted. At the same time, issues such as null values, garbled characters, or inconsistent formats are handled. For example, "2023-01-01" and "2023 / 01 / 01" are unified into a standard date format, or full-width characters in names are converted to half-width characters to ensure that no errors occur due to differences in writing during subsequent comparisons. This standardized information constitutes the so-called standardized master index fields.

[0027] The next step is the matching and deduplication process, which involves matching and removing redundancy from the standardized main index fields using preset field rules. A multi-level matching strategy is employed, prioritizing the ID number as the precise matching criterion; if they match, they are considered the same person. When the ID number is missing, a fuzzy matching mechanism is used, such as using an edit distance algorithm to determine if two names are similar (e.g., "Zhang Wei" and "Zhang Wei's"), combined with conditions such as birth date error within ±7 days and gender consistency. The system also excludes cases where the medical card number is the same but other information is clearly inconsistent, preventing false connections due to duplicate card number allocation. The final dataset containing unique and credible identities is the deduplicated main index data.

[0028] With this foundation, cross-hospital association begins, which involves "matching identity features based on the deduplicated master index data to obtain multi-hospital master index association records for the same patient." For example, if a patient registered at Hospital A with their ID card but only left their phone number and name at Hospital B, the system associates them using a combination of name similarity and matching phone number, forming a complete record chain covering information from both hospitals. All entries from different hospitals that are confirmed to belong to the same individual are merged together, forming multi-hospital master index association records.

[0029] The final step is to generate a globally unique code for these associated records, completing the operation of "uniquely identifying and encoding records associated with the master index across multiple hospital areas to obtain a standardized patient identification code." This typically involves using an auto-incrementing database ID combined with a hash algorithm to generate an irreversible string, such as SHA-256 encryption followed by truncating the first 16 characters, which serves as the patient's unique identifier within the entire group. All subsequent related medical activities, whether registration, prescriptions, or imaging examinations, are then bound to this code, providing accurate indexing support for subsequent cross-hospital data retrieval.

[0030] In a specific embodiment, the step of mapping historical medical records of each hospital area based on the standardized patient identification code to obtain a cross-hospital area medical relationship table includes: Data is extracted from the historical medical records of each hospital area to obtain a set of medical information including medical time, department, diagnosis result and examination items. The medical time field in the medical information set is then processed to standardize the time format to obtain standard time medical information. Based on the standardized patient identification code, the standard time medical visit information is associated and matched, and all standard time medical visit information corresponding to the same standardized patient identification code is collected together to obtain the cross-hospital medical visit information set of the same patient. The cross-hospital medical visit information set of the same patient is sorted according to the order of medical visit time to generate a cross-hospital medical visit relationship table.

[0031] Specifically, raw patient visit entries are extracted from the HIS databases of each branch hospital, and key information, including visit time, department name, diagnosis description, and ordered examinations, is extracted to form a preliminary collection of patient visit information. Due to the different construction dates of the systems in different hospital areas, the time field formats vary. Some use a complete timestamp like "2023-05-12 08:30," while others only record the date "2023 / 05 / 12," and some even use text fields for storage. Therefore, standardization is necessary. The system recognizes various input formats and converts them into a standard time format, such as "YYYY-MM-DD HH:MM:SS" under the ISO8601 standard. Missing hours, minutes, and seconds are padded with "00:00:00," ensuring that subsequent sorting is not disrupted due to format confusion. This standardized data is the standard time patient visit information.

[0032] The next step is the core matching phase, which involves "matching the standardized patient identification code with the standard time-based medical records." The system uses the standardized patient identification code as the primary key and retrieves all standard time-based medical records associated with that code from the global data table. Regardless of whether these records originate from Hospital A, Hospital B, or Hospital C, if the identification code is the same, they are considered to belong to the same patient. For example, a patient with the unique identification code "PAT2023XXXXXX" who had a lung CT scan at Hospital A's respiratory department in June 2023 and a follow-up visit at Hospital B in January 2024 for a cough and a blood test, can now have these two previously separate pieces of information accurately retrieved and aggregated into the same data container, forming a so-called cross-hospital medical record set for the same patient.

[0033] Next, a chronological arrangement is performed, corresponding to the specific implementation of "sorting according to the order of visit time." The system calls a sorting algorithm to arrange the records from smallest to largest based on the standard time field, presenting a clear timeline of the entire medical process. This allows doctors to intuitively see which hospital a patient first underwent which examinations, and then why they were transferred to other hospitals due to specific symptoms, avoiding the risk of misjudgment caused by fragmented information. Ultimately, this structured dataset organized along a timeline is what is known as the cross-hospital visit relationship table.

[0034] In a specific embodiment, the step of generating image retrieval instructions based on the cross-hospital visitation relationship table, and retrieving DICOM images from the PACS systems of each hospital based on the image retrieval instructions, includes: Task information is extracted from the cross-hospital visit relationship table to obtain a set of key task information containing standardized patient identification codes, examination items, and examination hospital. The field format of the examination items in the set of key task information is converted to obtain examination item codes that conform to the PACS system interface specifications. Based on the patient's standardized identification code and examination item code, an image retrieval instruction is generated according to a preset instruction generation rule; Based on the image retrieval command, and in accordance with the communication protocol of each hospital's PACS system, a retrieval request is sent to the corresponding hospital's PACS system, and DICOM images returned by each hospital's PACS system are received.

[0035] Specifically, each record in the table involving imaging examinations is parsed, and content containing fields such as the patient's standardized identification code, the examination item name (e.g., "chest CT plain scan"), and the hospital where the examination occurred is selected to form a set of key task information. Since different hospital PACS systems require the use of a standard coding system for interfacing, and the examination items in the original records are mostly described in Chinese, they cannot be directly used for interface calls; therefore, format conversion is necessary. The system uses a pre-set mapping dictionary to convert natural language expressions into standard codes. For example, it maps "head MRI enhancement" to the specific code "163109007" in SNOMED or LOINC, or the hospital's internally defined examination type code "MRBRAINENH," ensuring that the target PACS can correctly recognize the requested content. This process completes the "conversion of field formats for examination items in the aforementioned set of key task information to obtain examination item codes that conform to the PACS system interface specifications."

[0036] With standardized patient identifiers and examination codes in place, the system proceeds to the instruction generation stage. This involves "generating image retrieval instructions based on the standardized patient identifier and examination item code, according to preset instruction generation rules." The system assembles request messages according to a predetermined template, typically using XML or JSON structures to encapsulate data packets. These packets include fields such as patient ID, examination code, request time, and retrieval purpose marker, and are accompanied by a digital signature to ensure secure transmission. For example, if the system detects that a patient has had two lung CT scans at Hospital B, it will generate two separate retrieval instructions, each carrying the corresponding examination time range and sequence number to avoid confusion. These instructions are not issued arbitrarily but are driven by a pre-configured rule engine. Only entries that meet certain conditions (such as examination time within the last five years and status "completed") will trigger the retrieval action.

[0037] Finally, in the actual communication and image acquisition phase, the system "sends retrieval requests to the PACS systems of each hospital campus and receives the returned DICOM images." Based on the hospital campus information, the system determines the network address and service port of the target PACS and initiates a connection request using standard communication protocols such as DICOM WADO-URI, WADO-RS, or the traditional DICOM C-MOVE. If the other system verifies the connection, the system begins streaming the original DICOM file; if the connection fails due to network interruption or permission issues, the system logs the request and attempts to resend. All successfully received images are archived and stored at the central access node according to patient identification for subsequent keyframe extraction and interface display.

[0038] In a specific embodiment, the step of extracting keyframes from the DICOM image to obtain a structured image summary includes: The DICOM image is subjected to frame sequence analysis to obtain an image frame sequence, and the image frame sequence is filtered according to a preset frame filtering rule to obtain a key frame candidate set; wherein, the preset frame filtering rule includes a threshold set based on the clarity of the image frame sequence and key lesion features; Image features are extracted from each frame in the candidate keyframe set to obtain image feature information including lesion location, lesion morphology, and image grayscale value. The image feature information is then structured to obtain a structured image summary.

[0039] Specifically, keyframe extraction from acquired DICOM images is the core technical step in achieving "structured image summarization." The entire process begins with frame sequence analysis, which involves organizing hundreds of consecutive slices from a complete imaging examination, such as a chest CT scan, into an ordered sequence of image frames, each corresponding to the location information of a specific anatomical layer. This is followed by a screening stage, where the image frame sequence is filtered according to preset frame screening rules to obtain a candidate set of keyframes. The system automatically evaluates the quality and clinical value of each frame based on set technical standards. For example, it calculates image sharpness indicators such as the average gradient amplitude, eliminating layers blurred due to respiratory motion or artifacts; it also considers the examination type to determine the presence of typical lesion areas, such as searching for slices containing nodules or ground-glass opacities in lung CT scans, or identifying the most significantly enhanced lesion segment in brain MRI. These thresholds based on sharpness and key lesion characteristics constitute the preset frame screening rules; only frames that simultaneously meet the minimum resolution requirements and contain suspicious pathological features are retained in the candidate set.

[0040] Taking a patient who had undergone a lung CT scan at Hospital B as an example, the examination generated 320 axial images. After preliminary analysis, the system found that about 40 of these images contained sub-centimeter nodules with relatively clear boundaries or areas with surrounding spiculation. These frames, meeting the condition of "significant lesion features," were included in the keyframe candidate set. The remaining layers without obvious abnormalities or with poor image quality were filtered out, thus significantly reducing the amount of data for subsequent processing. The next step is in-depth analysis of the candidate frames, implementing "image feature extraction for each image in the keyframe candidate set." The system calls the built-in medical image analysis module to independently run the detection algorithm on each frame in the set, locating the lesion center coordinates, outlining the contour range, calculating morphological parameters such as major and minor axes and area, and recording grayscale statistics such as the mean HU value and standard deviation. These raw outputs are not directly usable and require further processing.

[0041] Then comes the structured processing stage, where the unstructured values ​​such as lesion location, shape and size, and grayscale distribution extracted above are converted into machine-readable and easy-to-display data formats, such as JSON objects or database records, according to a unified template. Each entry contains fields such as "slice location", "nodule diameter", "density type (solid / partially solid)" and "edge features", ultimately forming a refined structured image summary.

[0042] In a specific embodiment, the step of displaying the cross-hospital visitation relationship table and the structured image summary on multi-hospital terminals to obtain an interactive cross-hospital data interface includes: The cross-hospital visitation relationship table is converted into a data format to obtain visitation data adapted for terminal display. At the same time, the structured image summary is converted into an image format to obtain image data adapted for terminal display. Based on the medical data and image data, the layout of the interface of the multi-hospital terminal is planned to obtain an adjustable layout interface, and the medical data and image data in the adjustable layout interface are associated and marked to obtain an associated and marked interface. By setting interactive interface elements in the associated marker interface according to preset interaction rules, an interactive cross-department data interface is formed.

[0043] Specifically, the time-series records originally stored in the database, such as a patient's visit to the respiratory department of Hospital A in June 2023, diagnosis of pneumonia, and order of a CT scan, are converted into a lightweight format that the front-end interface can parse, such as a JSON array. Each item contains fields such as timestamp, department name, and diagnosis text. At the same time, "image format conversion of the structured image summary" is also performed. The original DICOM keyframes are resampled into JPEG or PNG format and downsized to a resolution suitable for screen display (such as 512×512), preserving key lesion areas while reducing transmission load, forming image data adapted for terminal display.

[0044] Next, we move to the interface construction phase, which involves "layout planning for the interface across multiple hospital campuses based on the aforementioned patient visit data and image data." A responsive design framework is typically used, dividing the screen into two main areas: one side displays a time-ordered stream of patient visits, while the other side displays a summary image associated with the selected event. Doctors can adjust the proportions of the two parts by dragging the divider according to their viewing habits, creating a so-called adjustable layout interface. For example, when clicking on a follow-up visit record from Hospital B in January 2024, the right side immediately loads a thumbnail of the corresponding lung CT scan keyframe. If there are multiple examinations, they are presented side-by-side in a stacked card format, supporting horizontal scrolling.

[0045] Based on this, the system implements association tagging to achieve the specific implementation of "associating and tagging the medical data and image data in the adjustable layout interface". The system establishes bidirectional links through shared timestamps or examination numbers, binding each image thumbnail to its source medical record. Simultaneously, a visual icon is added next to the text record to indicate the presence of imaging data. Clicking any thumbnail not only allows users to zoom in but also allows them to navigate back to the corresponding diagnosis and treatment node, enabling data jumps and linkages, thus forming the association tagging interface. Finally, interactive functions are embedded. Based on "setting interface elements through preset interaction rules", window width and level adjustment sliders and measurement tool buttons are added to the image area. A diagnostic remarks input box is provided on the text side, and a function entry point for double-clicking to view the complete DICOM sequence is set. All controls are arranged according to the human-computer interaction specifications for medical software, ultimately forming a logically clear, operationally coherent, and interactive cross-hospital data interface, allowing clinicians to efficiently trace the entire lifecycle of patient medical information.

[0046] In a specific embodiment, the step of planning the layout of the interface on the multi-hospital terminal based on the medical data and image data to obtain an adjustable layout interface includes: The medical data is divided into display areas to obtain a medical information layout table, and the image data is configured for display based on the medical information layout table to obtain an image display layout diagram. The scaling ratio of the image display layout is calculated to obtain adaptive layout parameters including image scaling ratio, display resolution, and margin settings. Based on the patient information layout table and adaptive layout parameters, a layout plan is performed on the interface of the multi-hospital terminal to obtain a preliminary layout interface. Based on the preliminary layout interface, a data scroll bar and an image scaling control are set to obtain an adjustable layout interface.

[0047] Specifically, the system divides the display area for the medical data itself. Based on information density and reading habits, the left side is set as the text information area, and the medical records are presented in a list format. Each record contains fields such as time, hospital area, department, and diagnosis summary, forming the so-called medical information layout table. This layout structure is usually stored in the form of a configuration table, i.e., the medical information layout table, which defines display attributes such as font size, row height, and color coding.

[0048] Next, based on this, the image data is matched and configured to achieve "image data display configuration based on the aforementioned medical information layout table". When a user selects a medical record, the system automatically calculates the available space on the right side based on the current screen width and arranges the image thumbnails accordingly—if the screen is wide, representative frames of multiple examination sequences are displayed side by side; if it is a narrow screen device, they are stacked vertically. This dynamic adjustment based on the context generates the image display layout, ensuring that the text and image content are presented in a coordinated manner.

[0049] The system then proceeds to the adaptive parameter calculation stage, which corresponds to "calculating the scaling ratio of the image display layout". The system takes into account the physical resolution of the terminal device, the browser window size, and the user's preset preferences, and calculates the optimal display parameters in real time, including the image scaling ratio (such as 75% or 100%), the actual rendering resolution, and the margin value of the surrounding white space. This avoids overflow due to the image being too large or affecting the interpretation due to the image being too small. These parameters are collectively referred to as adaptive layout parameters.

[0050] With the above design principles in place, the initial layout interface was constructed. This involved combining the fixed-width patient information area on the left with the flexible image area on the right into a complete view frame, with a draggable separator serving as the boundary between them. Furthermore, operational freedom was added by embedding a vertical scrollbar, allowing users to browse accumulated patient records up and down. Simultaneously, zoom controls were integrated into the image area, supporting gesture-based stretching or button clicks to adjust the viewing scale, thus achieving dynamic adjustment of interface elements. Ultimately, this resulted in an adjustable layout interface that balances compatibility and interactive flexibility, meeting the clinical review needs of different scenarios.

[0051] Please see Figure 2 , Figure 2 This is a schematic diagram of the framework of an embodiment of the data interoperability management device for multiple hospital campuses according to this application. Figure 2 As shown, the multi-hospital data interoperability management device includes an acquisition module 1, which is used to verify the uniqueness of the patient master index data of each hospital, obtain a standardized patient identification code, and perform association mapping on the historical medical records of each hospital based on the standardized patient identification code to obtain a cross-hospital medical relationship table; a retrieval module 2, which is used to generate an image retrieval instruction based on the cross-hospital medical relationship table, and retrieve DICOM images from the PACS system of each hospital based on the image retrieval instruction; and a display module 3, which is used to extract keyframes from the DICOM images to obtain a structured image summary, and display it on the multi-hospital terminal based on the cross-hospital medical relationship table and the structured image summary to obtain an interactive cross-hospital data interface.

[0052] Reference Figure 3 This invention also provides a computer device whose internal structure can be as follows: Figure 3 As shown, the computer device includes a processor, memory, display screen, input device, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores the data corresponding to this embodiment. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements the above-described method.

[0053] Those skilled in the art will understand that Figure 3 The structures shown are merely block diagrams of some structures related to the present invention and do not constitute a limitation on the computer devices on which the present invention is applied.

[0054] An embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0055] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the present invention and embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, etc.

[0056] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0057] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0058] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0059] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0060] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0061] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0062] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the individual through pop-up information or by asking the individual to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

Claims

1. A method for managing data interoperability across multiple hospital campuses, characterized in that, Includes the following steps: The uniqueness of the patient master index data obtained from each hospital area is verified to obtain a standardized patient identification code. Based on the standardized patient identification code, the historical medical records of each hospital area are associated and mapped to obtain a cross-hospital medical relationship table. Based on the cross-hospital visitation relationship table, an image retrieval instruction is generated, and DICOM images are retrieved from the PACS systems of each hospital based on the image retrieval instruction; Keyframes are extracted from the DICOM image to obtain a structured image summary, which is then displayed on multi-hospital terminals based on the cross-hospital visitation relationship table and the structured image summary, resulting in an interactive cross-hospital data interface.

2. The data interoperability management method for multiple hospital campuses according to claim 1, characterized in that, The process of verifying the uniqueness of patient identity in the master index data of each hospital area to obtain standardized patient identification codes includes: The patient master index data of each hospital area is processed by field extraction and cleaning to obtain standardized master index fields including patient name, ID number, date of birth and medical card number. The standardized master index fields are then matched and redundant data is removed using preset field rules to obtain deduplicated master index data. Based on the deduplicated master index data, identity feature association matching is performed to obtain the multi-hospital master index association records of the same patient, and the multi-hospital master index association records are uniquely identified and encoded to obtain a standardized patient identification code.

3. The data interoperability management method for multiple hospital campuses according to claim 1, characterized in that, The process of mapping historical medical records from each hospital area based on the standardized patient identification code yields a cross-hospital medical relationship table, including: Data is extracted from the historical medical records of each hospital area to obtain a set of medical information including medical time, department, diagnosis result and examination items. The medical time field in the medical information set is then processed to standardize the time format to obtain standard time medical information. Based on the standardized patient identification code, the standard time medical visit information is associated and matched, and all standard time medical visit information corresponding to the same standardized patient identification code is collected together to obtain the cross-hospital medical visit information set of the same patient. The cross-hospital medical visit information set of the same patient is sorted according to the order of medical visit time to generate a cross-hospital medical visit relationship table.

4. The data interoperability management method for multiple hospital campuses according to claim 1, characterized in that, The process of generating image retrieval instructions based on the cross-hospital visitation relationship table, and retrieving DICOM images from the PACS systems of each hospital based on the image retrieval instructions, includes: Task information is extracted from the cross-hospital visit relationship table to obtain a set of key task information containing standardized patient identification codes, examination items, and examination hospital. The field format of the examination items in the set of key task information is converted to obtain examination item codes that conform to the PACS system interface specifications. Based on the patient's standardized identification code and examination item code, an image retrieval instruction is generated according to a preset instruction generation rule; Based on the image retrieval command, and in accordance with the communication protocol of each hospital's PACS system, a retrieval request is sent to the corresponding hospital's PACS system, and DICOM images returned by each hospital's PACS system are received.

5. The data interoperability management method for multiple hospital campuses according to claim 1, characterized in that, The keyframe extraction of the DICOM image to obtain a structured image summary includes: The DICOM image is subjected to frame sequence analysis to obtain an image frame sequence, and the image frame sequence is filtered according to a preset frame filtering rule to obtain a key frame candidate set; wherein, the preset frame filtering rule includes a threshold set based on the clarity of the image frame sequence and key lesion features; Image features are extracted from each frame in the candidate keyframe set to obtain image feature information including lesion location, lesion morphology, and image grayscale value. The image feature information is then structured to obtain a structured image summary.

6. The data interoperability management method for multiple hospital campuses according to claim 1, characterized in that, The method of displaying cross-hospital visitation relationship tables and structured image summaries on multi-hospital terminals results in an interactive cross-hospital data interface, including: The cross-hospital visitation relationship table is converted into a data format to obtain visitation data adapted for terminal display. At the same time, the structured image summary is converted into an image format to obtain image data adapted for terminal display. Based on the medical data and image data, the layout of the interface of the multi-hospital terminal is planned to obtain an adjustable layout interface, and the medical data and image data in the adjustable layout interface are associated and marked to obtain an associated and marked interface. By setting interactive interface elements in the associated marker interface according to preset interaction rules, an interactive cross-department data interface is formed.

7. The data interoperability management method for multiple hospital campuses according to claim 6, characterized in that, Based on the medical visit data and image data, the layout planning of the interface on the multi-hospital terminal is performed to obtain an adjustable layout interface, including: The medical data is divided into display areas to obtain a medical information layout table, and the image data is configured for display based on the medical information layout table to obtain an image display layout diagram. The scaling ratio of the image display layout is calculated to obtain adaptive layout parameters including image scaling ratio, display resolution, and margin settings. Based on the patient information layout table and adaptive layout parameters, a layout plan is performed on the interface of the multi-hospital terminal to obtain a preliminary layout interface. Based on the preliminary layout interface, a data scroll bar and an image scaling control are set to obtain an adjustable layout interface.

8. A data interoperability management device for multiple hospital campuses, characterized in that, include: The acquisition module is used to verify the uniqueness of the patient master index data of each hospital area, obtain a standardized patient identification code, and perform association mapping on the historical medical records of each hospital area based on the standardized patient identification code to obtain a cross-hospital medical relationship table. The retrieval module is used to generate image retrieval instructions based on the cross-hospital visitation relationship table, and retrieve DICOM images from the PACS systems of each hospital based on the image retrieval instructions; The display module is used to extract keyframes from the DICOM image to obtain a structured image summary, and display it on multi-hospital terminals based on the cross-hospital visitation relationship table and the structured image summary to obtain an interactive cross-hospital data interface.

9. A computer device, characterized in that, The method includes a memory and a processor that are coupled to each other. The memory stores program instructions, and the processor executes the program instructions to implement the multi-campus data interoperability management method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The system stores program instructions that can be executed by a processor, the program instructions being used to implement the data interoperability management method for multiple campuses as described in any one of claims 1 to 7.

Images