Multi-disease integrated information management system for emergency treatment

Abstract

The invention relates to the technical field of emergency treatment information management, and discloses an emergency treatment-oriented multi-disease integrated information management system, which comprises a patient information management module used for configuring multi-disease inspection items and recording standardized time nodes; the inter-hospital referral cooperation module is used for dynamically selecting a referral doctor and recording referral key time; the first-aid time axis module is used for automatically generating a visual record of a treatment process based on a time sequence; and the quality control analysis platform module quantitatively evaluates the treatment efficiency through medical indexes. Through real-time data transmission between the patient information module and the data interaction module, instant sharing of key medical data before and in a hospital is realized, information incompleteness or inaccuracy caused by telephone communication is avoided, time waste of repeated examination after a patient arrives at the hospital is reduced, and treatment delay is effectively shortened.

Description

Technical Field

[0001] This invention relates to the field of emergency and critical care information management technology, specifically to an integrated information management system for multiple diseases in emergency and critical care. Background Technology

[0002] The development of the emergency greenway project stems from the urgent need for treatment of acute cardiovascular and cerebrovascular diseases. For patients with these diseases, "time is heart muscle" and "time is brain." Opening blocked blood vessels in the shortest possible time is the most valuable treatment to save the heart muscle and brain. The National Health and Family Planning Commission has vigorously promoted the "chest pain center" and "stroke center" models for the treatment of acute cardiovascular and cerebrovascular diseases through policy documents such as the "Notice on Improving the Medical Treatment Capacity for Acute Cardiovascular and Cerebrovascular Diseases" and the "Notice on Issuing the Guiding Principles for the Construction and Management of Stroke Centers (Trial Implementation)," aiming to continuously optimize the pre-hospital and in-hospital treatment processes and efficiently connect all aspects of treatment. These policies all emphasize the establishment of information sharing mechanisms to improve emergency treatment capabilities.

[0003] In the field of emergency care for acute cardiovascular and cerebrovascular diseases, several solutions have been developed to address the issues of information gaps and time delays. However, each solution has its limitations. The traditional telephone early warning system is the most common method, where pre-hospital emergency personnel inform the target hospital of the patient's condition by telephone, providing early warnings. This method is low-cost, simple to operate, and not limited by network conditions, making it widely used in primary healthcare institutions. However, the information reported by telephone is often incomplete and prone to missing key details. Verbal descriptions are also difficult to accurately convey complex information such as medical images. Furthermore, complete records cannot be saved, which is not conducive to subsequent quality control analysis. Hospitals also need to manually record the information after receiving it, which is prone to errors. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a multi-disease integrated information management system for emergency and critical care, which solves the problem of low efficiency in information exchange between pre-hospital emergency personnel and hospitals, resulting in inaccurate or incomplete information transmission and affecting treatment time.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a multi-disease integrated information management system for emergency and critical care, comprising: The patient information management module is used to configure multiple disease-specific testing items and record standardized time points; The inter-hospital referral collaboration module is used to dynamically select the attending physician and record key referral times; The emergency timeline module automatically generates a visual record of the treatment process based on chronological order; The quality control analysis platform module uses medical indicators to quantitatively assess treatment efficiency.

[0006] Through the aforementioned technical means, and by utilizing an intelligent integrated information system that efficiently connects pre-hospital and in-hospital continuous treatment systems for multiple diseases in emergency care, the system achieves dynamic adaptation of testing processes and accurate capture of time data through a patient information management module that configures multiple disease-specific testing items and records standardized time nodes. The inter-hospital referral collaboration module dynamically selects attending physicians and records key referral times, improving inter-hospital collaboration efficiency and referral timeliness. The emergency timeline module automatically generates visual records of the treatment process based on chronological order, making the entire process traceable. The quality control analysis platform module quantifies and evaluates treatment efficiency using medical indicators, providing data support for process optimization. This system comprehensively solves problems such as information gaps and time delays in traditional emergency care models, efficiently connecting pre-hospital and in-hospital treatment, and significantly improving the efficiency and quality of emergency care, especially for the treatment of acute cardiovascular and cerebrovascular diseases and other diseases.

[0007] Preferably, the patient information management module includes: Configurable test item units are available for pre-configuring blood routine and D-dimer test items, and support dynamic addition and deletion of disease test procedures; The image compression and uploading unit processes medical images using segmented compression technology and uploads the processed medical images to the emergency timeline module. The time node recording unit captures specimens and generates reports at specific time points using a time selector, and labels the disease category.

[0008] Preferably, the configurable inspection item unit includes: Disease template library, used to pre-store combinations of test items for chest pain centers and stroke centers; The rules engine automatically loads coagulation function test items when a disease is selected; The anomaly ranking unit generates a dynamic leaderboard based on the pass rate of FMC2D≤90 minutes; FMC2D is the time interval between the first medical contact and the start of device treatment.

[0009] Preferably, the inter-hospital referral collaboration module includes: The doctor dynamic synchronization unit is used to connect to the hospital's HIS system in real time to update the doctor's on-call status. Multiple communication units can be selected, supporting the simultaneous selection of ≥3 attending physicians and activation of the call link; The referral time tracking unit records the time of patient explanation. Time of consent to transfer to another hospital Time of leaving the hospital Three types of nodes; Wherein, time difference ΔT= The referral delay coefficient is uploaded to the quality control analysis platform module.

[0010] Preferably, the referral time tracking unit performs the following steps: Time compliance verification, if If the time exceeds 10 minutes, it will be marked as a timeout event; The route optimization algorithm generates the optimal referral route based on historical ΔT data.

[0011] Preferably, the emergency rescue timeline module includes: The status coding unit maps the operation type to a color identifier; The event association unit links pre-hospital electrocardiogram data with in-hospital thrombolysis records using patient IDs; The node editing unit allows manual correction of FMC2D timestamps, and the modification records are stored in a trace.

[0012] Preferably, the event association unit implements the following steps: Multi-source data fusion to determine the arrival time of ambulances based on GPS location. Preparation time for in-hospital medical equipment Alignment; Time window analysis to calculate outpatient visit time (DNT) = And it alerted cases that exceeded 90 minutes.

[0013] Preferably, the quality control analysis platform module includes: Indicator calculation engine for real-time calculation of core medical indicators; The hospital ranking unit generates a dynamic ranking list based on the achievement rate of FMC2D≤90 minutes; The time parameter is derived from the standardized records of the emergency rescue timeline module.

[0014] Preferably, the indicator calculation engine includes: Trend prediction model, based on ARIMA algorithm to model FMC2D index; The quality control feedback loop pushes cases with a prediction deviation >15% to the emergency timeline module for recalibration.

[0015] Preferably, the system further includes: The system integrates a power supply and connects to the hospital's EMR system via the HL7 protocol to obtain patients' historical medical records in real time. The security audit unit employs role-based access control to restrict unauthorized modification of time-based data. A multi-terminal adaptation layer ensures that the user interface remains consistent between the mobile app and the PC data management platform.

[0016] This invention provides an integrated information management system for multiple diseases in emergency and critical care. It has the following beneficial effects: 1. This invention enables real-time data transmission between the patient information module and the data interaction module, achieving instant sharing of key medical data before and during hospitalization. This avoids incomplete or inaccurate information caused by telephone communication, reduces the time wasted on repeated examinations after patients arrive at the hospital, and effectively shortens the delay in treatment.

[0017] 2. This invention optimizes the inter-hospital referral process, enabling rapid selection of target hospitals and attending physicians, accurate transmission of patient information, and standardized recording of key referral nodes. This improves the efficiency of referrals between primary hospitals and higher-level hospitals and reduces the risk of delayed treatment due to poor information transmission.

[0018] 3. This invention integrates and presents information such as the operation, time nodes, and participants of each link in the pre-hospital and in-hospital process. Combined with real-time monitoring, trend analysis and hospital efficiency ranking of key indicators such as FMC2D, it provides medical institutions with an objective basis for evaluating the treatment process, which helps to continuously optimize the emergency process and improve the success rate of treatment for multiple diseases such as acute cardiovascular and cerebrovascular diseases and trauma. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the operational framework of the present invention; Figure 2 This is a schematic diagram showing the APP interface of the present invention; Figure 3 This is a schematic diagram of the system framework of the present invention. Detailed Implementation

[0020] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Please see the appendix Figure 1 -Appendix Figure 3 This invention provides a multi-disease integrated information management system for emergency and critical care, comprising: The patient information management module is used to configure multiple disease-specific testing items and record standardized time points; The inter-hospital referral collaboration module is used to dynamically select the attending physician and record key referral times; The emergency timeline module automatically generates a visual record of the treatment process based on chronological order; The quality control analysis platform module uses medical indicators to quantitatively assess treatment efficiency.

[0022] Furthermore, the output of the patient information management module is connected to the input of the inter-hospital referral collaboration module, the output of the inter-hospital referral collaboration module is connected to the input of the emergency timeline module, and the output of the emergency timeline module is connected to the input of the quality control analysis platform module, forming a closed-loop data flow. Each module achieves real-time synchronization across institutions through the medical data bus, supporting collaborative treatment of chest pain, stroke, trauma, and high-risk pregnant women. Specifically, the patient information management module includes a configurable test item unit, which pre-sets common tests such as complete blood count and D-dimer to meet the basic testing needs of various emergency and critical illnesses. It also supports dynamic addition and deletion of test items to adapt to changes in different conditions and the emergence of new diseases. The configurable test item unit has a disease template library, which pre-stores test item combinations for common and critical diseases such as chest pain centers and stroke centers, making it convenient for medical staff to quickly access them. At the same time, it is equipped with a rule engine. When a doctor selects a specific disease in the system, the rule engine can automatically load necessary test items such as coagulation function tests related to that disease, improving the efficiency and accuracy of test item configuration. The test item unit also has a built-in abnormality ranking unit. The abnormality ranking unit generates a dynamic ranking list based on the achievement rate of FMC2D≤90 minutes. In this way, the hospital can intuitively understand the timeliness of treatment for specific diseases in different departments or at different time periods, which facilitates targeted improvements and optimizations. FMC2D is the time interval from the first medical contact to the start of instrument treatment. Through the aforementioned technical means, this system ensures that adding or deleting diseases does not affect other core functions by interacting with the disease management, test item, and rule engine modules using a standardized interface. The disease management module can independently store basic disease information such as disease name, ICD code, and applicable scenarios, and establish a mapping relationship with test items through an association table. Adding or deleting diseases only requires operating this module and the association table, without modifying the underlying code. The test item module supports adding special test items such as "brain natriuretic peptide detection" for stroke and "lactate dehydrogenase detection" for trauma through a preset basic test item library such as complete blood count, D-dimer, and coagulation. These special test items are associated with diseases through unique identifiers. The disease template library in the configurable test item unit can preset templates for common acute and critical illnesses such as chest pain, stroke, trauma, and high-risk pregnant women. Each combination includes a standardized test procedure. For example, the chest pain template includes mandatory test items such as "electrocardiogram, troponin, and coagulation function" by default. Disease templates are also available in the backend interface. The specific operation is as follows: fill in the disease name, select the applicable department, select mandatory and optional test items from the test item library, set the test item order, such as blood routine test and blood type identification for trauma. After saving, the test procedure template for the new disease will be automatically generated. The built-in logic of the rules engine is as follows: when a new disease is added, the administrator can configure trigger conditions, such as automatically loading associated test items after selecting the disease. For example, when adding a critical pneumonia disease, the administrator can configure the rule to automatically load blood routine, procalcitonin, and chest CT test items after selecting critical pneumonia. When a disease is deleted, the rules engine automatically removes the association between the disease and the test items to avoid invalid data residue. If the disease has generated historical cases, the system will retain the historical test process records (saved to the historical database) without affecting the integrity of the existing data. In summary, the system provides a dedicated entry point for configuring disease-specific testing workflows. The interface supports adding workflows by clicking the "Add Disease" button, filling in disease information, selecting testing items from the testing item library, setting the required and optional attributes and order of the testing items, previewing the workflow, and confirming and saving. The new workflow takes effect immediately. Deleting a workflow involves selecting the target disease, the system automatically checking for any incomplete current cases (if any, prompting the user to complete the current case before deletion), prompting confirmation for deletion if no incomplete cases exist, and deleting the disease is irreversible. After confirmation, the disease is removed from the selectable list, and its associated testing workflows are no longer loaded. Modifying workflows allows editing of existing disease-specific testing workflows, such as adding or removing testing items and adjusting their order. Modifications are automatically synchronized to all scenarios using the disease, such as the patient information module and the quality control analysis platform module. After adding a new disease category, medical staff can select it when creating a patient's file. The system automatically loads the configured testing process and supports recording standardized time nodes for the disease. The testing operations for the newly added disease category will be automatically linked to the timeline and displayed visually in chronological order. After deleting a disease category, the timeline records of historical cases will not be affected. Furthermore, after adding a disease category, the system will automatically include it in the quality control scope and support statistical analysis of its testing process time indicators, such as testing time. After deleting a disease category, its historical quality control data will be archived and saved without affecting the overall statistical results. This allows the system to flexibly support the dynamic addition and deletion of disease testing processes, enabling rapid response to the emergency needs of new diseases and optimization of existing disease testing processes based on clinical practice, ensuring the adaptability and efficiency of emergency care. The image compression and uploading unit processes medical images using segmented compression technology. This technology can significantly reduce the size of image files while ensuring image quality, thereby improving upload speed. Segmented compression technology is widely used in various fields and is relatively mature, so its specific principles will not be elaborated on here. The processed medical images are uploaded to the cloud database of the emergency timeline module, allowing medical staff to access relevant image data at any time when reviewing the patient's treatment process, providing a more comprehensive basis for diagnosis and treatment.

[0023] The time node recording unit can use a time selector to accurately capture the specimen collection time and report generation time, and mark the disease category. In subsequent treatment process analysis and quality control, it is possible to clearly understand the time node of each test item under different diseases, which helps to discover potential time delay problems and thus optimize the treatment process. The system embeds time selectors in the specimen collection and entry interface and the test report submission interface. When pre-hospital medical staff or in-hospital laboratory staff complete specimen collection and laboratory technicians complete report review and click submit, the time selector is automatically activated. This facilitates the recording of standardized time nodes. In scenarios where the system is connected to testing equipment such as blood routine analyzers and coagulation analyzers, the system captures the time when the equipment completes specimen testing in real time through the interface and automatically fills it into the time selector, reducing human operation errors. In scenarios where there is no equipment connection, such as manual specimen collection in pre-hospital, the operator selects a specific time point by clicking the calendar control and time slider of the time selector and clicks confirm to complete the time entry. In practical applications, operators select the corresponding patient information in the system, such as the patient ID or visit number, enter the specimen management submodule, select the specific test item, and click the "Collection Complete" button. The system automatically invokes the time selector, which defaults to displaying the current operation time. Operators can adjust the time according to the actual collection time. The system performs compliance verification on the entered time. If the collection time is later than the current system time, such as if a future time was mistakenly selected, a prompt will appear stating that the collection time cannot be later than the current time, and requesting a reselection. This forces a correction. After successful verification, the system associates the specimen collection time with the patient ID and test item ID and stores it in the database. The specimen time recording table generates a unique time node ID. When the testing equipment completes the test and uploads the electronic report to the system, the system automatically records the original report generation time and the equipment output time. This time is displayed on the report interface when the operator logs into the system to view the report. After the staff verifies the report and clicks the "Approval" button, the system reactivates the time selector and defaults to filling in the approval completion time as the final report generation time. After the report generation time is confirmed, the system binds it with the corresponding test report, test item, and patient ID, stores it in the test report timeline table, and associates it with the previously recorded specimen collection time, thus forming a complete record. The testing process timeline and disease category labeling process are as follows: During patient registration, medical staff need to select the disease category in the preliminary diagnosis field. The disease category information is stored in the patient's basic information table, generating a unique disease identifier. When the time node recording unit captures the specimen collection time or report generation time, the system automatically associates the disease category information in the patient's basic information table with the patient ID, synchronizing the disease identifier to the specimen time record table and the test report timeline table. In practical application, if a patient is labeled as having a stroke, the collection time record of their blood routine specimen will be tagged with "stroke," and the corresponding report generation time record will also be associated with this tag. The captured time points and disease-specific markers are pushed to the emergency timeline module via a real-time data synchronization mechanism. The data is automatically arranged chronologically to form a visualized record of the treatment process, including disease type, time, and procedures. Simultaneously, the data is synchronized to the quality control analysis platform module, providing standardized time data for calculating core indicators such as FMC2D and D2N. Grouped statistical analysis is also performed according to disease category. Through this process, the time node recording unit achieves accuracy in time point capture and relevance in disease category markers, ensuring the traceability of key time data during emergency care. This provides a data foundation for efficient connection and quality control optimization of pre-hospital and in-hospital treatment processes.

[0024] The inter-hospital referral collaboration module includes: The doctor dynamic synchronization unit is used to connect to the hospital's HIS system in real time to update the doctor's on-call status. Multiple communication units can be selected, supporting the simultaneous selection of ≥3 attending physicians and activation of the call link; The referral time tracking unit records the time of patient explanation. Time of consent to transfer to another hospital Time of leaving the hospital Three types of nodes; Wherein, time difference ΔT= The referral delay coefficient is uploaded to the quality control analysis platform module.

[0025] Furthermore, the doctor dynamic synchronization unit connects to the hospital's HIS system in real time to obtain doctors' on-call status information and updates it promptly in this system. When inter-hospital referrals are needed, medical staff can accurately know which doctors are on duty, facilitating the selection of a suitable attending physician and improving the efficiency and success rate of referrals. The multi-selection communication unit supports the simultaneous selection of ≥3 attending physicians and can quickly activate the call link. In emergency referral situations, this multi-selection communication function ensures that at least one doctor can respond promptly, while also facilitating thorough communication between the referring hospital and the receiving physician team to explain the patient's condition in detail. The referral time tracking unit records three key nodes: the time of explanation of the patient's condition, the time of consent to transfer, and the time of departure from the hospital. By calculating the time difference ΔT, it tracks the time difference. As a referral delay coefficient uploaded to the quality control analysis platform module, ΔT can intuitively reflect whether there are time delays during the referral process, providing important data support for hospitals to optimize the referral process. Simultaneously, the referral time tracking unit verifies time compliance. If the delay exceeds 10 minutes, it is marked as a timeout event, prompting the hospital to promptly investigate the cause and make improvements. Based on historical ΔT data, a path optimization algorithm is used to generate the optimal referral route, reducing time loss during the referral process and improving the safety and timeliness of patient transfer. The system automatically extracts historical ΔT-related data from inter-hospital referral records. The historical ΔT data collection scope includes basic path information, such as the referral origin and destination road segments, time dimension data, such as referral date, time period, actual travel time and ΔT value, influencing factor data, such as traffic congestion level, weather conditions, road construction status and the time taken for the receiving hospital to prepare for reception, and safety-related data, such as road accident rate, road width, and number of traffic lights. Based on the collected information, the total delay cost of each candidate route is defined as a weight value, calculated using the following formula: ; in, The ΔT value represents the historical average value of this route under similar weather and traffic conditions during the same period, where L is the route length in kilometers, and R is the route risk coefficient. , and These are the weighting coefficients for historical average delay, path length, and path risk, respectively. α is used to measure The weight of historical averages on total delay cost reflects the importance of historical delay patterns under similar path conditions for current decision-making. A larger value for α indicates a more significant impact of historical delay data on optimal path selection. β measures the weight of path length on total delay cost, reflecting the contribution of physical distance to base travel time. A larger value for β indicates a more critical impact of path length on total delay. This is used to measure the weight of the route risk coefficient on the total delay cost, reflecting the importance of route safety to transit reliability. A higher value indicates a higher priority for safety in route selection. The value limit can be determined by rotating and filtering the data sample to include valid referral records within the last 12 months. Each record contains independent variables. α, β, and R, along with the dependent variable actual total delay cost, are input into a multiple linear regression model. The goal is to minimize the error between the predicted and actual total delay costs. This is achieved through iterative optimization using the gradient descent algorithm, yielding α, β, and R. The basic values, α+β+ =1, ensuring the normalization of weight allocation, and in emergency rescue applications, it is possible to adjust α, β, and The base values ​​are adjusted. When transporting patients with acute myocardial infarction or stroke, the shortest possible arrival time is required. The weights of α and β can be increased to prioritize avoiding historical delays and long routes, while the weight of γ can be decreased. Under the premise of safety and compliance, risk restrictions can be appropriately relaxed. When transporting critically ill pregnant women or patients with massive traumatic hemorrhage, transport stability must be ensured. The weight of γ should be increased to prioritize avoiding high-risk routes, while the weights of α and β can be appropriately decreased. Slightly longer routes or slightly higher historical delays are permissible, but must be within safety thresholds. For non-critically ill patients, both timeliness and safety must be considered. The weights of α, β, and γ can be adjusted accordingly. The basic values ​​tend to be balanced, and fine-tuning is performed based on these basic values ​​by adjusting α, β, and... The value of the value can reflect the patterns of historical data and adapt to the core needs of different emergency scenarios. Ultimately, it ensures that the total delay cost weight value generated by the route optimization algorithm is consistent with the actual timeliness and safety goals of the transfer, so as to achieve accurate selection of the optimal transfer route. The calculation process first determines the target route for the current referral and the historical conditions to be matched, including: origin (transferring hospital ID), destination (receiving hospital ID), core road segments traversed (e.g., hospital A - main road B - highway C - hospital D), the current referral time period, date type (e.g., weekday, weekend, or holiday), current real-time weather (e.g., light rain or sunny), and traffic congestion level (obtained from the traffic API). Matching data is then filtered from the historical database. The filtering criteria include: route matching (e.g., the origin, destination, and core road segments traversed in the historical records match the target route), and time condition matching (e.g., the overlap between the historical referral time period and the current time period is ≥80%, and the historical record is a weekday). If the current day is also a weekday, and environmental conditions match (e.g., similar weather, both historical and current weather are without precipitation), and traffic congestion levels match (e.g., the difference between historical and current congestion levels is ≤1), then the selected historical data is further filtered to remove outliers to avoid affecting the accuracy of the average. This filtering removes records where ΔT > 3 times the historical average ΔT. For example, if the historical average ΔT for a certain route is 30 minutes, records where ΔT > 90 minutes are removed. If the number of filtered data points is less than 5, the matching range is automatically expanded, allowing for time period overlap of ≥60%, until the sample size is ≥ 5 to ensure statistical validity. For the cleaned and valid historical ΔT data, a weighted average method is used to calculate... The formula is: ; Where n is the number of valid historical records. Let ΔT be the value of the i-th historical record. The weight of the i-th record is determined by the installation time decay: records from the last 3 months have a weight of 1.0, records from 3-6 months have a weight of 0.8, records from 6-12 months have a weight of 0.5, and records older than 12 months are not included in the calculation to ensure that recent data has a greater impact on the average. In a real-world scenario, if the target road segment is Hospital A - Main Road B - Hospital C, the time period is weekday 09:00-09:30, the weather is light rain, and the traffic congestion level is 3, after filtering, a total of 8 historical records are matched. After removing 6 records, 3 are from the past 3 months, with ΔT values ​​of 25, 28, and 30 minutes respectively (weight 1.0), and 3 are from the past 3-6 months, with ΔT values ​​of 32, 35, and 29 minutes respectively (weight 0.8). = Through the above process It can accurately reflect the historical average delay level of the target path under similar conditions, providing a reliable basis for path weight calculation; Based on the algorithm, the path with the smallest weight value is selected from the candidate path set as the initial optimal route. The optimal route includes starting from Hospital A - via Expressway S1 - bypassing the construction section S2 - entering Highway G1 - arriving at Hospital B. It includes suggestions for avoiding congested times (e.g., departing 10 minutes earlier if the traffic light count is expected to be between 5:00 PM and 7:00 PM). One to two suboptimal routes are generated as alternatives for unforeseen circumstances. After the referral is completed, the system automatically records the actual ΔT value of the referral, the deviation between the travel route and the algorithm's prediction, and adds this data to the referral path ΔT association database to correct the weight coefficients α, β, and β. By employing the aforementioned technical means and based on the path optimization algorithm, the optimal referral route can be generated while minimizing time loss.

[0026] The emergency rescue timeline module includes: The status coding unit maps the operation type to a color identifier; The event association unit links pre-hospital electrocardiogram data with in-hospital thrombolysis records using patient IDs; The node editing unit allows manual correction of FMC2D timestamps, and the modification records are stored in a trace.

[0027] Furthermore, the status coding unit maps various operation types to specific color identifiers. For example, green may represent routine examination operations, yellow represents emergency treatment operations, and red represents major operations such as surgery. Through this color coding, medical staff can intuitively see the nature and urgency of operations at different stages on the timeline, quickly understanding the overall situation of patient treatment. The event association unit associates pre-hospital electrocardiogram data with relevant data such as in-hospital thrombolysis records through patient IDs, achieving multi-source data fusion. For example, it aligns the ambulance arrival time obtained from GPS positioning with the in-hospital medical equipment preparation time, enabling medical staff to clearly understand the entire time flow from when the patient is received by the ambulance to when the in-hospital treatment equipment is ready. At the same time, it calculates the outpatient arrival time (DNT) = patient arrival time at the hospital gate - patient start time for diagnosis, and issues warnings for cases exceeding 90 minutes, reminding medical staff to pay attention to whether the treatment time is too long and to adjust the treatment strategy in a timely manner. The node editing unit allows medical staff to manually correct the FMC2D timestamp to ensure the accuracy of time records, and all modification records are logged for easy subsequent query and traceability, ensuring data traceability.

[0028] Specifically, GPS positioning and timestamp synchronization are implemented. Ambulances upload GPS positioning data in real time via onboard terminals or the emergency greenway APP used by pre-hospital medical staff. When the system detects that the ambulance's GPS coordinates have entered the target hospital's preset area, it automatically determines that the ambulance has arrived and records the timestamp as the arrival time. Simultaneously, it associates the patient's unique ID and stores it in the pre-hospital emergency schedule. When the pre-hospital system pushes patient information to the hospital, the hospital's emergency room doctor receives the alert and clicks the "Start Equipment Preparation" button in the system. The system automatically generates an equipment preparation task, and medical staff complete equipment debugging and medication preparation. After preparation, click the "Equipment Readiness Complete" button in the system. The system will automatically record the timestamp at this time, associate it with the same patient ID, and store it in the hospital's preparation schedule. The system uses the built-in network time protocol service to ensure that the ambulance's GPS time, the hospital's server time, and the time of the medical staff's operating terminal are all synchronized with the national time service center's standard time, eliminating time deviations caused by time zone and terminal clock errors. In the emergency timeline module's time dashboard, the two time records are arranged in chronological order, and the logical relationship between the two is indicated by arrows or connecting lines, allowing medical staff to intuitively view the time interval between the ambulance's arrival and the equipment's readiness. The time to diagnosis (DNT) is calculated as the time the patient arrives at the hospital gate minus the time the patient begins receiving diagnosis. Cases exceeding 90 minutes trigger an alert. The 90-minute threshold is set for the following reasons: For patients with acute myocardial infarction, if the time from admission to a definitive diagnosis exceeds 90 minutes, it can lead to an expansion of irreversible myocardial cell necrosis, significantly reducing the success rate of reperfusion therapy and increasing the risk of complications such as heart failure and arrhythmia. For patients with acute stroke, failure to begin diagnosis within 90 minutes will miss the optimal time window for intravenous thrombolysis, leading to worsening neurological damage and increased disability rates. Based on the "Notice on Improving the Medical Treatment Capacity for Acute Cardiovascular and Cerebrovascular Diseases" and the "Guiding Principles for the Construction and Management of Stroke Centers (Trial Implementation)," chest pain centers must complete reperfusion therapy within 90 minutes of the patient's first medical contact after admission. Stroke centers must establish a standardized process from admission to diagnostic assessment of ≤60-90 minutes to ensure rapid initiation of treatment. DNT, as a core indicator of admission to diagnosis, uses the 90-minute threshold to measure whether the emergency procedure is standardized. The system automatically calculates the FMC2D timestamp based on pre-hospital emergency records and in-hospital device treatment records, with an accuracy down to the minute, and synchronizes it to key nodes on the emergency timeline. When medical staff discover errors in the initial timestamp, they can initiate corrections through the node editing unit. Specific scenarios include delayed recording of the first pre-hospital medical contact time, errors in entering in-hospital device treatment times, or conflicts between multiple data sources. When manually correcting the FMC2D timestamp, the system only provides correction access to authorized users. Access is managed through a role-based access control (RBAC) mechanism. Authorized users click the edit button next to the FMC2D timestamp node on the emergency timeline. The system then displays a correction pop-up window showing the current timestamp and the associated original data source. Users can manually modify the first medical contact time or device treatment start time using the time selector in the pop-up window. The system recalculates and displays the FMC2D difference in real time, along with the log count. The system employs a blockchain-based storage structure, generating a unique hash value for each record. Any subsequent modifications will result in a change to the hash value. The system periodically verifies the integrity of the hash chain to ensure the logs are tamper-proof. The log table only supports appending and does not allow deletion or overwriting operations. Even if the record is corrected again later, a new log record will be generated, preserving the complete modification history. The corrected FMC2D timestamp is synchronized to the quality control analysis platform module in real time, automatically updating the patient's FMC2D indicators, hospital ranking data, and patient information module. The time display of the corresponding node is updated in the time dashboard, ensuring data consistency across the entire system. Through these technical means, the node editing unit not only meets the need for correcting time errors in clinical practice but also ensures the accuracy and integrity of the FMC2D timestamps through strict access control, full log traceability, and tamper-proof storage, providing a reliable data foundation for quality control analysis and process optimization.

[0029] The quality control analysis platform module includes: Indicator calculation engine for real-time calculation of core medical indicators; The hospital ranking unit generates a dynamic ranking list based on the achievement rate of FMC2D≤90 minutes; The time parameter is derived from the standardized records of the emergency rescue timeline module.

[0030] Furthermore, the indicator calculation engine is used to calculate core medical indicators in real time, such as FMC2D. It includes a trend prediction model, which models the FMC2D indicator based on the ARIMA algorithm. By analyzing and predicting historical data, it can predict the possible trend of future treatment time. If the prediction deviation is >15%, these cases are pushed to the emergency timeline module for recalibration through the quality control feedback loop to ensure the accuracy of treatment time records and the optimization of treatment process. The hospital ranking unit generates a dynamic ranking list based on the achievement rate of FMC2D ≤ 90 minutes. Each hospital can use this ranking list to understand the gap between itself and other hospitals in terms of treatment efficiency, thereby learning from advanced experience, improving its own treatment process, and improving the overall level of emergency care. Specifically, the system connects in real time to the Emergency Greenway APP, in-hospital HIS, EMR system, testing equipment system, and timeline module to collect the raw time node data required for indicator calculation. The collected data includes: FMC2D related data (first medical contact time, device treatment start time), D2N related data (patient admission time, first medication time), and D2W related data (patient admission time, ward admission time). Time node data from different sources are bound together by the patient's unique ID to form a single patient's full-process time chain, which is stored in the core indicator raw database. Calculations are performed based on the collected data, such as FMC2D = device treatment start time - first medical contact time, D2N = first medication time - patient admission time, and D2W = ward admission time - patient admission time. The calculation results are synchronized in real time to the indicator dashboard of the quality control analysis platform module and displayed by disease type. ARIMA (Autoregressive Integral Moving Average) is a classic algorithm for time series forecasting. The indicator calculation engine uses this algorithm to model the FMC2D indicator, predicting future treatment time trends. Specifically, it extracts nearly 12 months of FMC2D data from the core indicator database, aggregates it at a daily granularity (e.g., taking the average FMC2D of all chest pain patients daily), forming a time series {y_1, y_2, ..., y_n}, where n is 365 days and y_n is the average FMC2D value on day i. If the number of patients on a certain day is ≤3, the data for that day is filled with the average of the three days before and after. This is then analyzed using an ADF (Advanced Decision Function) single... The positional root test determines whether a sequence is stationary. If the p-value is < 0.05, it is considered a stationary sequence. FMC2D time series often exhibit trends, such as lower values ​​from Monday to Friday and slightly higher values ​​on weekends. Differentiation is required: First-order differencing calculates Δy'_i = y'_i - y'_{i-1} to eliminate linear trends; seasonal differencing, if weekly seasonality exists, calculates Δ7y'_i = y'_i - y'_{i-7} to eliminate seasonal fluctuations. Repeat the test until the sequence is stationary, determining the differencing order d. The autoregressive order p is determined through the autocorrelation function (ACF) plot, taking the lag order at which the ACF plot first falls into the confidence interval. The moving average order q is determined using the partial autocorrelation function (PACF) plot. The lag order at which the PACF plot first falls into the confidence interval is taken. Models with different combinations of p, d, and q are constructed. The optimal model is selected using the AIC (Akaike Information Criterion). Data from the previous 10 months is used as the training set, and data from the last 2 months as the validation set. The optimal ARIMA model is trained using the training set data to obtain the model parameters. The model's predictive performance is tested using the validation set data. The mean squared error (MSE) between the predicted and actual values ​​is calculated. If the MSE > a preset threshold, the p and q values ​​are readjusted until the model meets the criteria. Based on the trained model, predictions are made for the next 7 days or... The 30-day average FMC2D value generates a trend curve. If the predicted value exceeds the threshold, the system automatically issues a pop-up warning on the quality control platform, noting possible causes. The predicted trend is synchronized to the inter-hospital referral collaboration module, prompting managers to allocate resources in advance. The deviation between the actual and predicted values ​​after intervention is tracked for model iteration. Through these technical means, the indicator calculation engine achieves real-time and accurate calculation of core medical indicators. Furthermore, by modeling and predicting the FMC2D indicator using the ARIMA algorithm, it provides data support for medical institutions to identify the risk of treatment delays in advance and optimize the allocation of emergency resources, thereby improving the efficiency of emergency care.

[0031] The system also includes: The system integrates a power supply and connects to the hospital's EMR system via the HL7 protocol to obtain patients' historical medical records in real time. The security audit unit employs role-based access control to restrict unauthorized modification of time-based data. A multi-terminal adaptation layer ensures that the mobile app and the PC data management platform maintain a consistent user interface. Furthermore, the system integrates power supplies: By connecting to the hospital's EMR system via the HL7 protocol, it can obtain patients' historical medical records in real time. This allows medical staff to quickly understand important information such as patients' past medical history, allergies, and treatment during emergency care, providing strong support for accurate diagnosis and the development of reasonable treatment plans. The security audit unit employs role-based access control, strictly limiting unauthorized personnel from modifying important information such as time-node data. For example, only administrators and relevant medical staff with specific permissions can operate on time-node data, and all operations are recorded in the security audit log for subsequent querying and auditing, ensuring data security and integrity. The multi-terminal adaptation layer ensures consistency between the mobile app and the PC data management platform. Whether medical staff use the mobile app in the ward or the PC data management platform, they can obtain the same information in real time, facilitating the querying, recording, and management of patient information and improving work efficiency.

[0032] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-disease integrated information management system for emergency and first aid, characterized by, The system comprises: a patient information management module for configuring multiple disease test items and recording standardized time nodes; an inter-hospital referral coordination module for dynamically selecting a receiving doctor and recording a referral key time; an emergency time axis module for automatically generating a visual record of a rescue process based on time sequence; a quality control analysis platform module for quantitatively evaluating rescue efficiency through medical indicators.

2. The multi-disease integrated information management system for emergency and first aid according to claim 1, characterized in that, The patient information management module comprises: a configurable test item unit for preparing blood routine test and D-dimer detection items and supporting dynamic addition and deletion of disease test processes; an image compression upload unit for processing medical images through a fragmentation compression technology and uploading the processed medical images to the emergency time axis module; a time node recording unit for capturing specimen and report generation time points through a time selector and marking disease categories.

3. The multi-disease integrated information management system for emergency and first aid according to claim 2, characterized in that, The configurable test item unit comprises: a disease template library for pre-storing test item combinations of a chest pain center and a stroke center; a rule engine for automatically loading coagulation function detection items when a disease is selected; an abnormal ranking unit for generating a dynamic ranking list according to a compliance rate of FMC2D≤90 minutes. FMC2D is a time interval from first medical contact to start of instrument treatment.

4. The multi-disease integrated information management system for emergency and first aid according to claim 1, characterized in that, The inter-hospital referral coordination module comprises: a doctor dynamic synchronization unit for updating a doctor on-duty state in real time through real-time docking of a hospital HIS system; a multi-selection communication unit for supporting simultaneous selection of ≥3 receiving doctors and activating a call link; Referral time tracking unit, records handover time , agreed referral time , leaving hospital time Three types of nodes; wherein the time difference ΔT = T2-T1 is uploaded to the quality control analysis platform as a referral delay coefficient.

5. The multi-disease integrated information management system for emergency and first aid according to claim 4, characterized in that, The referral time tracking unit performs the following steps: Time compliance check, if > 10 minutes, then mark as timeout event; a path optimization algorithm for generating an optimal referral route based on historical ΔT data.

6. The multi-disease integrated information management system for emergency and first aid according to claim 1, characterized in that, The emergency time axis module comprises: a state coding unit for mapping operation types to color identifiers; an event association unit for associating pre-hospital ECG data with in-hospital thrombolysis records through a patient ID; a node editing unit for allowing manual correction of FMC2D timestamps and storing modification records as traces.

7. The multi-disease integrated information management system for emergency and first aid according to claim 6, characterized in that, The event association unit performs the following steps: Multi-source data fusion, ambulance arrival time with GPS positioning with in-hospital medical device preparation time alignment; Time window analysis, calculate door to diagnosis time DNT And alert cases over 90 minutes.

8. The multi-disease integrated information management system for emergency and first aid according to claim 1, characterized in that, The quality control analysis platform module comprises: an indicator calculation engine for real-time operation of medical core indicators; a hospital ranking unit for generating a dynamic ranking list according to a compliance rate of FMC2D≤90 minutes. The time parameter is derived from standardized records of the emergency time axis module.

9. The multi-disease integrated information management system for emergency and first aid according to claim 1, characterized in that, The indicator calculation engine comprises: a trend prediction model for modeling FMC2D indicators based on an ARIMA algorithm; a quality control feedback loop for pushing cases with a prediction deviation >15% to the emergency time axis module for recalibration.

10. The multi-disease integrated information management system for emergency and first aid according to claim 1, characterized in that, The system further comprises: a system integrated power supply for real-time acquisition of patient historical medical records through docking of a hospital EMR system through an HL7 protocol; a security audit unit for limiting unauthorized modification of time node data through role-based access control; a multi-terminal adaptation layer for maintaining operation interface consistency between a mobile terminal APP and a PC data management platform.

Images