Portable multifunctional integrated transfer platform for pre-hospital first aid

Abstract

The invention discloses a portable multifunctional integrated transfer platform for pre-hospital first aid, and relates to the technical field of medical treatment. According to the method, the task type and the equipment list are accurately matched through multi-dimensional analysis of the out-call instruction, the temporary diagnosis and treatment station is set up, the equipment ready verification and alternative recommendation mechanism is matched, the pre-hospital service preparation process is simplified, the service suitability and reliability are improved, and based on the differentiated vital sign threshold value and the multi-level anomaly judgment system, the service quality is improved. The method has the advantages that abnormal data can be accurately identified, graded and early-warned, standardized disposal schemes can be synchronously pushed, high-priority data can be directionally transmitted to a hospital and a dispatching center in advance, medical staff can be assisted to quickly respond, the diagnosis and treatment decision time can be shortened, and the first-aid timeliness can be guaranteed; safe and continuous diagnosis and treatment data transmission is ensured; a standardized report is generated and is associated with hospital archives of patients, a complete medical information chain is constructed, pre-hospital and hospital information barriers are broken, and diagnosis and treatment collaboration and patient data privacy are improved.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to a portable, multifunctional integrated transport platform for pre-hospital emergency care. Background Technology

[0002] Currently, pre-hospital emergency services cover a range of tasks, including emergency treatment, routine physical examinations, and chronic disease follow-ups. However, existing equipment configurations rely on human experience, which can easily lead to equipment redundancy or the absence of critical equipment. Furthermore, setting up temporary treatment stations is cumbersome and difficult to adapt to different dispatch locations and task requirements. For example, Chinese patent application CN117637190A discloses a 5G interconnected transport system and method for medical emergency care. The system includes a smart emergency and critical care transport platform, an emergency command cabin, a 5G pre-hospital emergency command system, and a 5G ambulance. The 5G ambulance includes a network communication module, an intelligent task terminal, a real-time ambulance location transmission module, a patient vital parameter module, and an in-vehicle panoramic high-definition video module. Through 5G technology, the system improves the timeliness and efficiency of pre-hospital emergency care, achieves integrated pre-hospital and in-hospital emergency treatment, and innovates the pre-hospital emergency care and out-of-hospital transport medical service model.

[0003] However, while the aforementioned patent applications have enabled information interaction between pre-hospital and in-hospital settings, remote consultations, and coordinated emergency resources, the following problems still exist: 1. Existing technologies do not dynamically screen medical equipment configurations based on the specific characteristics of outpatient tasks. They rely on manual presets or experience-based matching, which can easily lead to equipment redundancy or missing key auxiliary equipment for different task types, and cannot flexibly adapt to diverse pre-hospital service needs. 2. The medical equipment is only mounted as an independent component in the ambulance, without adjustable support structures or equipment fixing components. This makes it inconvenient for temporary medical operations and cannot meet the operational needs of different scenarios such as on-site emergency treatment and physical examination sampling. 3. There are no differentiated judgment criteria adapted to different ages, genders, and disease types, nor is there a hierarchical early warning system based on multiple dimensions such as the degree of data deviation and duration. Furthermore, there is no connection to a standardized emergency response knowledge base, which makes it difficult to assist medical staff in quickly identifying high-risk conditions and taking accurate measures, potentially affecting the pertinence and standardization of emergency response. Summary of the Invention

[0004] The purpose of this invention is to provide a portable, multi-functional integrated transport platform for pre-hospital emergency care. This platform parses dispatch instructions to accurately match equipment lists, simplifies preparation processes, and relies on differentiated thresholds and a multi-level judgment system to accurately identify and issue graded warnings of abnormal data. It simultaneously pushes standardized treatment plans and transmits high-priority data in advance to facilitate rapid decision-making. This not only improves the adaptability and accuracy of pre-hospital services but also ensures the collaboration and privacy of medical information, comprehensively optimizing the pre-hospital emergency care service process and solving the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: A portable, multi-functional integrated transport platform for pre-hospital emergency care includes a portable multi-functional main body, and integrated into the portable multi-functional main body are a device screening module, a temporary diagnosis and treatment adapter module, a patient data collection module, a touch terminal, a data transmission module, and a report generation module; The equipment filtering module is used to generate a suitable equipment list based on the corresponding task type of the received emergency or outpatient instructions, and to match and filter medical equipment based on the equipment list. Based on the screened medical equipment, temporary treatment stations are set up through a temporary treatment adaptation module. The patient data acquisition module is used to collect patients' vital signs data in real time through various medical devices based on the temporary treatment station, and to display the data in real time on the touch terminal. The report generation module is used to integrate the acquired vital signs data, emergency treatment information, and medication list to generate a home visit summary report for the patient. The data transmission module is used to establish a data transmission link with the hospital's medical system based on vital sign data, on-site treatment information, medication list, and outpatient summary report, and to perform point-to-point targeted encrypted transmission based on the data transmission link.

[0006] Furthermore, the equipment screening module specifically includes: Acquire emergency or house call command signals, parse the emergency or house call command signals, extract the task urgency, patient basic medical information, house call location environment type and estimated transport time from the command, and generate task feature dataset; Based on the task feature dataset, a pre-defined task type classification rule is matched to determine the corresponding task type. Based on the task weight of each task type, the priority of the emergency rescue task to be performed is determined. Based on the priority ranking results and the corresponding task types, the corresponding level of equipment screening process is triggered, and the equipment matching needs of high-priority tasks are responded to first. Retrieve the preset compatible device database, extract the set of basic devices associated with this task type from the preset compatible device database, and at the same time obtain the device carrying capacity data of the portable multi-functional subject and the status data of the currently carried devices to build a device carrying evaluation model. The basic equipment set is evaluated and optimized based on the equipment-equipment evaluation model to generate a candidate equipment list. The correlation of each equipment in the candidate equipment list is analyzed, and auxiliary equipment with high correlation to the target equipment is added to form a complete equipment list. Connect each device in the complete device list to the touch terminal for display, and obtain the real-time readiness status of each device. Generate a device matching completion signal based on the real-time readiness status.

[0007] Furthermore, obtaining the real-time readiness status of each device also includes: If there are unready devices, generate a list of device malfunctions, unreadiness prompts, and recommended alternative devices, and obtain the corresponding list adjustment or replacement instructions; Medical staff make secondary confirmations based on the list of fine-tuning or replacement instructions fed back by the touch terminal, adjust the complete equipment list until all equipment is in a ready state, and generate an equipment matching completion signal; If, after multiple adjustments, there are still unready devices that cannot be replaced, a task adaptation anomaly warning signal will be generated, fed back to the emergency dispatch center, and synchronized to the touch terminal.

[0008] Furthermore, the real-time data display function of the touch terminal also includes: Acquire real-time vital sign data, including the patient's electrocardiogram data, blood oxygen data, blood pressure data, and heart rate data, and visualize the vital sign data through a touch terminal to generate a continuous stream of patient vital sign data; At the same time, the real-time collected vital sign data is compared with the corresponding preset vital sign thresholds. Abnormal data that exceeds the preset vital sign thresholds is judged. If the vital sign data exceeds the corresponding preset vital sign threshold, it is judged as abnormal data. Abnormal data is highlighted and alerted with sound and light in real time, and the corresponding vital sign data type and risk level are displayed simultaneously.

[0009] Furthermore, the determination of abnormal data exceeding preset vital sign thresholds also includes: Retrieve the basic judgment parameters corresponding to the abnormal data, including the difference between the abnormal data and the preset threshold, the duration of the abnormal data, and the frequency of the abnormal data. The difference, duration of abnormal data and frequency of abnormal data are weighted and calculated to obtain the first abnormality judgment coefficient, and the first abnormality judgment coefficient is compared with the preset first-level abnormality judgment coefficient threshold. When the first anomaly determination coefficient exceeds the preset first-level anomaly determination coefficient threshold, it is determined to be high-risk anomaly data; When the first abnormality judgment coefficient does not exceed the preset first-level abnormality judgment coefficient threshold, but exceeds the preset second-level abnormality judgment coefficient threshold, the associated judgment parameters corresponding to the abnormal data are retrieved, including the fluctuation range of associated vital sign data within the same period, the specific data association threshold corresponding to the patient's underlying disease, and the impact coefficient of the current diagnosis and treatment operation on the data. The second abnormality judgment coefficient is obtained based on the fluctuation range of associated vital sign data, the specific data association threshold corresponding to the patient's underlying disease, and the impact coefficient of the current diagnosis and treatment operation on the data. The second abnormality judgment coefficient is then compared with the preset third-level abnormality judgment coefficient threshold. When the second anomaly determination coefficient exceeds the preset third-level anomaly determination coefficient threshold, it is determined to be medium-risk anomaly data; When the second anomaly determination coefficient does not exceed the preset threshold of the third-level anomaly determination coefficient, it is determined to be low-risk anomaly data; The weights for calculating the first and second abnormality determination coefficients are dynamically adjusted based on the patient's age, gender, and disease type.

[0010] Furthermore, after the abnormal data is highlighted in real time and given an audible and visual warning, it also includes: Retrieve the preset knowledge base for emergency response to abnormal vital signs, match the corresponding emergency response plan based on the type and risk level of the current abnormal data, and display it on the touch terminal; Abnormal data and corresponding early warning information are treated as high-priority data and transmitted to the hospital's diagnosis and treatment system and emergency dispatch center in advance. At the same time, the time node, duration and data change trend of abnormal data and the corresponding early warning response operations are recorded to generate a special record of abnormal data. Abnormal data is recorded in real time and synchronized to the patient's vital signs data stream, and then transmitted to the report generation module. If multiple abnormal data points overlap or the abnormal data continues to worsen, the level of the audible and visual warning will be increased. The touch terminal will prominently display the corresponding abnormal vital signs data and emergency response plan, and the intensity of the audible and visual warning will be increased until medical staff confirm the response and treatment procedures.

[0011] Furthermore, the data transmission module specifically includes: Construct a two-way data transmission link between the touch terminal and the in-hospital diagnosis and treatment system and the emergency dispatch center, monitor the data transmission quality of each data transmission link in real time, and determine the main link and backup link for two-way data transmission based on the data transmission quality; Based on task priority, data type, and diagnostic and treatment needs, the data to be transmitted is divided into different priorities, and data transmission is carried out based on the priority division results. The data to be transmitted is segmented, a unique identifier and integrity check code are generated for each segment, and the data segments are encrypted. At the same time, the encryption key is encrypted to generate an encrypted data packet. The encrypted data packet is sent to the target receiving end through a bidirectional data transmission link. After receiving the encrypted data packet, the target receiving end performs decryption processing and integrity verification, generates a data reception confirmation signal, and obtains transmission status feedback data.

[0012] Furthermore, the data transmission module also includes: The data transmission completion status is determined based on the transmission status feedback data and the data reception confirmation signal. Based on the judgment result of data transmission completion, the local temporary medical data is cleaned up and deleted. At the same time, the encrypted medical data backup file is obtained, stored in the target encrypted storage area, and access permissions for retrieving the medical data backup file are established. Based on the need for synchronous outpatient summary reports, the outpatient summary reports will be transmitted to the hospital's medical records database to establish a data exchange mechanism between pre-hospital and in-hospital medical information. The system obtains the unique patient identifier associated with the patient data collection module, matches the outpatient summary report with the unique patient identifier in the hospital's medical records database, and synchronizes the content of the outpatient summary report to the corresponding patient's medical records based on the matching results, thereby generating a patient medical information chain.

[0013] Furthermore, the data transmission based on the priority partitioning result specifically includes: The system can obtain the current available bandwidth value of the data transmission link in real time, and obtain the remaining transfer time for the portable multi-functional main body to navigate to the target hospital. The total amount of data to be transmitted in the current cache is counted, and the first or second abnormal judgment coefficient corresponding to the abnormal data obtained by the judgment is called and normalized into the disease risk weight. Based on the total data volume, current available bandwidth, remaining transfer time, and disease risk weights, a transmission urgency calculation model is constructed to calculate the data transmission urgency index at the current moment. The calculation formula is as follows:

[0014] in: This is a data transmission urgency index, and it is a dimensionless value. The total amount of data to be transmitted, in megabits (MB). This represents the currently available bandwidth, in megabits per second. The remaining transit time is in seconds. This represents the risk weight for the disease, with a value ranging from 0 to 1. A preset risk adjustment sensitivity factor is used to balance the impact of the urgency of the illness on the transmission strategy; The data transmission module is based on the calculated... Implement dynamic transmission strategy: when When it is determined that the current link status cannot transmit all data losslessly within the remaining transit time, the semantic feature extraction and compression algorithm is automatically triggered to transmit non-abnormal vital sign data after lossy compression, and bandwidth is allocated first to transmit abnormal data losslessly. when At the same time, the original data is transmitted in a lossless encoding format.

[0015] Furthermore, before synchronizing the outpatient summary report to the corresponding patient's in-hospital medical record, the process also includes performing an artifact removal step based on multi-source data attribution: The system acquires vehicle vibration acceleration data recorded by the built-in sensors of the touch terminal during the transportation process and extracts the drug injection time recorded in the medication list. The timestamps of the abnormal vital signs data in the outpatient summary report are matched with the peak times of the vehicle vibration acceleration data and the times of drug injection. When the timestamp of abnormal vital signs data coincides with the peak time of vehicle vibration acceleration data, and the expected change in pharmacological response caused by drug injection is not matched at that time, the abnormal vital signs data is determined to be a transport vibration artifact, and an artifact interference mark is added to the data. When the timestamp of abnormal vital signs data coincides with the expected effective window of pharmacological response after drug injection, the abnormal vital signs data is determined to be valid diagnostic and treatment response data, and the abnormality mark of the data is retained. The data transmission module only synchronizes the outpatient summary report and effective treatment response data after the artifact removal step to the hospital's medical records, and attaches a filtered log with artifact interference markers during synchronization.

[0016] Compared with the prior art, the beneficial effects of the present invention are: This invention precisely matches task types and equipment lists by analyzing outpatient instructions from multiple dimensions. Combined with a foldable support structure, it constructs temporary treatment stations adaptable to diverse scenarios such as emergency care and physical examinations. With equipment readiness verification and alternative recommendation mechanisms, it avoids equipment redundancy or shortages, simplifies pre-hospital service preparation processes, and improves service adaptability and reliability. Based on differentiated vital sign thresholds and a multi-level abnormality judgment system, it accurately identifies and issues graded warnings for abnormal data, simultaneously pushing standardized treatment plans. High-priority data is pre-transmitted to the hospital and dispatch center, assisting medical staff in rapid response, shortening treatment decision time, and ensuring the timeliness of emergency care. Through graded data transmission, dual encryption, and automatic switching between primary and backup links, it ensures the secure and continuous transmission of treatment data. It automatically generates standardized reports and links them to patient hospital records, constructing a complete medical information chain, breaking down information barriers between pre-hospital and in-hospital care, and improving treatment collaboration and patient data privacy. Attached Figure Description

[0017] Figure 1 This is a block diagram of the portable multifunctional integrated transfer platform of the present invention; Figure 2 This is a flowchart illustrating the intelligent matching and dynamic adjustment process of the device screening module of the present invention. Figure 3 This is a flowchart of the multi-dimensional hierarchical determination process for abnormal physical signs in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, 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.

[0019] To address the technical issues in existing technologies, such as the lack of intelligent adaptation capabilities in medical equipment configuration (relying on manual presets or experience-based matching, failing to dynamically select based on the specific characteristics of outpatient tasks, lacking solutions for setting up temporary treatment workstations adapted to different scenarios, insufficient support for anomaly detection and emergency response for vital sign data, lack of individualized and tiered early warning mechanisms, and incomplete information integration between pre-hospital and in-hospital settings, please refer to [link to relevant documentation]. Figures 1-3 This embodiment provides the following technical solution: A portable, multi-functional integrated transport platform for pre-hospital emergency care includes a portable multi-functional main body, and integrated into the portable multi-functional main body are a device screening module, a temporary diagnosis and treatment adapter module, a patient data collection module, a touch terminal, a data transmission module, and a report generation module; The equipment filtering module is used to associate the received emergency or outpatient instructions with the corresponding task type, such as emergency treatment, routine physical examination, chronic disease follow-up, etc., and generate a suitable equipment list. Based on the equipment list, medical equipment such as first aid kits, monitors, and sampling tools are matched and filtered. Based on the screened medical equipment, a temporary treatment workstation is built using a temporary treatment adaptation module. This module includes a foldable support structure and equipment fixing components. The height of the workstation can be adjusted according to the size and usage requirements of the screened medical equipment using the foldable support structure, and the equipment fixing components enable rapid positioning and fixation of the medical equipment. This creates a temporary treatment workstation suitable for emergency treatment, routine nursing care, or physical examination sampling. It is used to carry out diversified operations such as emergency treatment, routine nursing care, and physical examination sampling, adapting to the pre-hospital medical service needs in different scenarios. The patient data acquisition module is used to collect patients' vital signs data in real time through various medical devices based on the temporary treatment station. This includes electrocardiogram waveforms, blood oxygen saturation, blood pressure values, and heart rate changes. The data is displayed in real time on the touch terminal. The data is updated in real time and presented in a visual format, which makes it easier for medical staff to predict the patient's condition in advance and prepare for subsequent on-site treatment. The report generation module integrates the acquired vital signs data, emergency treatment information, and medication list to generate a home visit summary report for the patient. The report includes basic patient information, pre-hospital emergency treatment process records, patient vital signs data stream, medication details, and transfer handover suggestions. It automatically fills in the data based on a preset treatment report template and generates a standardized home visit summary report. The data transmission module is used to establish a data transmission link with the hospital's medical system based on vital sign data, on-site treatment information, medication list, and outpatient summary report, and to perform point-to-point targeted encrypted transmission based on the data transmission link.

[0020] In this embodiment, through integrated management and adaptation of pre-hospital medical equipment, combined with a foldable support structure and equipment fixing components, temporary treatment stations adaptable to diverse scenarios can be flexibly set up. This eliminates the need to carry various medical devices separately, simplifying the preparation process for pre-hospital medical services. It adapts to the needs of pre-hospital medical services in different scenarios such as emergency treatment, routine physical examinations, and chronic disease follow-up, improving the scenario adaptability and operational convenience of pre-hospital medical services. By collecting patients' vital signs data in real time and visually presenting it on a touch terminal, medical staff can intuitively grasp the dynamics of the patient's condition, providing timely and comprehensive data support for on-site treatment and helping medical staff accurately predict the disease. This system ensures the targeted and adequate preparation of pre-hospital emergency care; it automatically integrates various treatment-related data and generates standardized outpatient summary reports, eliminating the need for medical staff to manually organize and integrate data, simplifying the report preparation process, standardizing the content and format of outpatient records, providing clear and complete treatment information for transfer and handover, and facilitating the connection between pre-hospital and in-hospital treatment information; it establishes a targeted encrypted data transmission link with the in-hospital treatment system to achieve secure and smooth transmission of pre-hospital treatment-related data, enabling the in-hospital treatment system to obtain patients' pre-hospital treatment information in advance, promoting the coordinated connection between pre-hospital medical services and in-hospital treatment services, and ensuring the continuity and security of treatment information transmission.

[0021] In this embodiment, the device screening module specifically includes: The system acquires emergency or house call command signals, parses these signals, and extracts the task urgency, patient's basic medical condition information, location environment type, and estimated transport time from the commands. This generates a task feature dataset. Task urgency is categorized into Level 1, Level 2, and Level 3 urgency, with corresponding weights of 0.8, 0.5, and 0.3, respectively. Location environment types include complex outdoor terrain, flat indoor environments, and inside vehicles. Estimated transport time is categorized as: short duration ≤ 1 hour, medium duration 1-3 hours, and long duration ≥ 3 hours. Based on the task feature dataset, a pre-defined task type classification rule is matched to determine the corresponding task type. Based on the task weight of each task type, the priority of the emergency rescue task to be performed is determined. Based on the priority ranking results and the corresponding task types, the corresponding level of equipment screening process is triggered, and the equipment matching needs of high-priority tasks are responded to first. The screening response time for Level 1 emergency tasks is ≤10 seconds, Level 2 is ≤20 seconds, and Level 3 is ≤30 seconds. The preset compatible equipment database is retrieved. The preset compatible equipment database contains equipment compatibility rules and equipment performance parameter thresholds corresponding to different diseases, environments and transport durations. For example, long-duration transport requires portable oxygen supply equipment with an oxygen flow rate adjustment range of 1-10L / min; outdoor complex terrain requires portable folding stretchers with a load-bearing capacity of ≥150kg. Extract the set of basic devices associated with this task type from the preset compatible device database, and at the same time obtain the device load capacity data of the portable multi-functional subject and the status data of the currently loaded devices. Construct a device load evaluation model. The maximum device load capacity is 20 units. Device load capacity = maximum capacity - number of currently loaded devices. For example: 12 units are currently loaded, and there is a reserve of 8 units. The basic equipment set is evaluated and optimized based on the equipment-equipment evaluation model to generate a candidate equipment list. The correlation of each equipment in the candidate equipment list is analyzed, and auxiliary equipment with high correlation to the target equipment is added to form a complete equipment list. Connect each device in the complete device list to the touch terminal for display, and obtain the real-time readiness status of each device. Based on the real-time readiness status, generate a device matching completion signal, lock the device list, and synchronize it to the temporary diagnosis and treatment adaptation module.

[0022] In this embodiment, by analyzing emergency or home visit command signals from multiple dimensions, key information such as the urgency of the task and the patient's underlying symptoms is extracted to form a task feature dataset. Combined with preset rules, the task type is accurately matched and the task priority is determined. This ensures that the equipment selection process aligns with the core needs of the task, prioritizing the equipment matching needs of high-priority tasks and guaranteeing the timeliness of equipment preparation for emergency medical tasks. The basic equipment set is evaluated and optimized, and highly relevant auxiliary equipment is added to form a complete equipment list. This list not only meets the core equipment requirements of the task type but also makes full use of the equipment space, avoiding equipment redundancy or missing equipment and improving the scientific and complete nature of equipment configuration. This ensures that all equipment in the final locked equipment list is in a usable state, reducing the interference of on-site equipment failures on pre-hospital medical services, ensuring the smooth conduct of diagnosis and treatment operations, and improving the reliability of pre-hospital medical services.

[0023] In this embodiment, obtaining the real-time readiness status of each device further includes: If there are unready devices, generate a list of device malfunctions, unreadiness prompts, and recommended alternative devices, and obtain the corresponding list adjustment or replacement instructions; Medical staff make secondary confirmations based on the list adjustment or replacement instructions fed back by the touch terminal, adjust the complete equipment list, re-retriev the preset adaptation equipment database to verify the compatibility of the adjusted equipment with the task type, and at the same time obtain the real-time readiness status of each equipment after adjustment until all equipment is in the ready state, generate a equipment matching completion signal and lock the final equipment list to synchronize to the temporary diagnosis and treatment adaptation module. If, after multiple adjustments, there are still unreplaceable, non-ready devices, a task adaptation anomaly warning signal will be generated, fed back to the emergency dispatch center, and simultaneously transmitted to the touch terminal, so that medical staff can collaboratively develop an emergency response plan.

[0024] In this embodiment, for equipment incompatibility issues that cannot be resolved despite multiple adjustments, a task adaptation anomaly warning signal is generated and synchronized to the emergency dispatch center and touch terminal. This helps medical staff and the dispatch center to collaboratively develop emergency response plans, avoid task stagnation due to equipment problems, and ensure the continuity of pre-hospital medical services and the coordination of emergency response.

[0025] In this embodiment, the real-time data display of the touch terminal further includes: Acquire real-time vital sign data, including the patient's electrocardiogram data, blood oxygen data, blood pressure data, and heart rate data, and visualize the vital sign data through a touch terminal to generate a continuous stream of patient vital sign data; At the same time, the real-time collected vital sign data is compared with the corresponding preset vital sign thresholds. Abnormal data that exceeds the preset vital sign thresholds are judged. If the vital sign data exceeds the corresponding preset vital sign threshold, it is judged as abnormal data. The preset vital sign thresholds include differentiated vital sign safety thresholds corresponding to different ages, genders, and disease types. In this embodiment, the preset vital sign thresholds are as follows: Adult males: heart rate 60-100 beats / min, blood oxygen saturation 95%-100%, systolic blood pressure 90-140 mmHg, diastolic blood pressure 60-90 mmHg; Adult females: heart rate 55-95 beats / min, blood oxygen saturation 95%-100%, systolic blood pressure 85-135 mmHg, diastolic blood pressure 55-85 mmHg; Elderly individuals over 60 years of age: heart rate 50-90 beats / min... Blood oxygen saturation 93%-100%, systolic blood pressure 90-150 mmHg, diastolic blood pressure 60-90 mmHg. Abnormal data exceeding the preset vital sign thresholds are judged. If the vital sign data exceeds the corresponding preset vital sign threshold (such as heart rate >130 beats / min or <50 beats / min, blood oxygen saturation <90%, systolic blood pressure >160 mmHg or <80 mmHg, diastolic blood pressure >100 mmHg or <50 mmHg); Abnormal data is highlighted and alerted with sound and light in real time, and the corresponding vital sign data type and risk level are displayed simultaneously.

[0026] In this embodiment, the determination of abnormal data exceeding the preset vital sign threshold also includes: Retrieve the basic judgment parameters corresponding to the abnormal data, including the difference between the abnormal data and the preset threshold, the duration of the abnormal data, and the frequency of the abnormal data. The difference, duration of abnormal data and frequency of abnormal data are weighted and calculated based on a preset weighting algorithm to obtain the first abnormality judgment coefficient, and the first abnormality judgment coefficient is compared with the preset first-level abnormality judgment coefficient threshold. When the first abnormality judgment coefficient exceeds the preset first-level abnormality judgment coefficient threshold, it is judged as high-risk abnormal data, and the highest level of sound and light warning is immediately triggered. The sound decibel is 100-120dB, the light is always red, and the warning is pushed to the hospital's diagnosis and treatment system to start emergency reception preparation. When the first abnormality judgment coefficient does not exceed the preset first-level abnormality judgment coefficient threshold, but exceeds the preset second-level abnormality judgment coefficient threshold, the associated judgment parameters corresponding to the abnormal data are retrieved, including the fluctuation range of associated vital sign data within the same period, the specific data association threshold corresponding to the patient's underlying disease, and the impact coefficient of the current diagnosis and treatment operation on the data. The second abnormality judgment coefficient is obtained based on the fluctuation range of associated vital sign data, the specific data association threshold corresponding to the patient's underlying disease, and the impact coefficient of the current diagnosis and treatment operation on the data. The second abnormality judgment coefficient is then compared with the preset third-level abnormality judgment coefficient threshold. When the second abnormality judgment coefficient exceeds the preset third-level abnormality judgment coefficient threshold, it is judged as medium-risk abnormal data, triggering a medium-level sound and light warning, with the sound decibel 90-100dB, the light flashing red at a frequency of 1 time / second, and pushing targeted disease observation guidance. When the second anomaly judgment coefficient does not exceed the preset third-level anomaly judgment coefficient threshold, it is judged as low-risk anomaly data, and only a high-brightness mark and a mild warning are given, with a sound decibel of 70-80dB, a yellow flashing light, and a frequency of 0.5 times / second, and the data change trend is continuously tracked. The weights for calculating the first and second abnormality determination coefficients are dynamically adjusted based on the patient's age, gender, and disease type. For example, for pediatric patients, the deviation difference weight coefficient is 0.5, the duration weight coefficient is 0.2, and the frequency weight coefficient is 0.3; for diabetic patients, the fluctuation amplitude correlation weight coefficient is 0.5, and the treatment impact correction weight coefficient is 0.5, to adapt to the differentiated treatment determination needs.

[0027] To eliminate dimensional differences between different vital signs (such as heart rate and blood oxygen percentage) and different dimensions (such as "duration" and "frequency"), the system establishes the following dimensionless normalized calculation model to obtain the first anomaly determination coefficient. : in, The vital signs values ​​collected in real time by the sensors; This refers to the preset upper or lower safety threshold corresponding to this vital sign; The preset baseline fluctuation constant for this vital sign (normalized as the denominator), for example, the baseline fluctuation constant for heart rate is set to... times / minute; Duration of the abnormal data (in seconds); The preset critical duration baseline constant, for example, is set to... Second; The frequency of abnormal data occurrences per unit of time; The preset frequency reference constant, for example, is set to Second-rate; , , The weighting coefficients are respectively for the degree of deviation, duration, and frequency of occurrence, and satisfy the following conditions: .

[0028] In this embodiment, the first anomaly determination coefficient is calculated as follows: the difference between the abnormal data and the preset threshold, the duration of the abnormal data, and the frequency of the abnormal data are multiplied by their respective weighting coefficients, and the three products are then added together. The corresponding weighting coefficients are the deviation difference weighting coefficient, the duration weighting coefficient, and the frequency weighting coefficient, and the sum of these three weighting coefficients is 1. For example: if a patient's heart rate is 140 beats / min, exceeding the upper limit of 40 beats / min for an adult male, the difference score is 40 / 30≈1.33; if it lasts for 6 minutes, exceeding the high-risk duration threshold by 1 minute, the duration score is 6 / 5=1.2; if all 5 consecutive collections are abnormal, the frequency score is 5 / 3≈1.67; then the first anomaly determination coefficient = 1.33×0.4+1.2×0.3+1.67×0.3≈0.532+0.36+0.501≈1.393; In this embodiment, the second anomaly determination coefficient is calculated as follows: the fluctuation range of other vital signs data within the same period is compared with the specific data correlation threshold corresponding to the patient's underlying disease. The difference 1 between the current treatment operation's influence coefficient on the data is subtracted from this coefficient. Then, the results of the above two calculations are multiplied by the corresponding weight coefficients respectively. Finally, the two products are added together. The corresponding weight coefficients are the fluctuation range correlation weight coefficient and the treatment influence correction weight coefficient, and the sum of the values ​​of these two weight coefficients is 1. For example: when the heart rate is abnormal, the blood pressure fluctuation is 25 mmHg, 25 / 20=1.25; the patient is a hypertensive patient, the specific threshold is met; no relevant treatment drugs are used, the influence coefficient is 0, then the second anomaly determination coefficient = 1.25×0.6+(1-0)×0.4=0.75+0.4=1.15; In this embodiment, the real-time visualization and continuous data stream presentation of vital sign data enable medical staff to intuitively and clearly grasp the dynamic changes in the patient's condition. Differentiated vital sign safety thresholds adapted to different ages, genders, and disease types are used to determine abnormal data, avoiding the judgment bias caused by uniform thresholds. This makes the initial identification of abnormal data more closely aligned with individual patient characteristics, improving the targeting and rationality of abnormal data judgment, and reducing misjudgments or omissions due to individual differences. Furthermore, a multi-level abnormal judgment system is constructed, comprehensively judging abnormal data based on multiple dimensions such as the degree of deviation, duration, frequency of occurrence, related vital sign fluctuations, underlying disease characteristics, and the impact of diagnostic and treatment operations. This achieves graded early warning of abnormal data, ensuring that the warning level accurately matches the severity of the condition, improving the accuracy and adaptability of abnormal data judgment. This facilitates medical staff in taking corresponding measures based on the warning level, enabling refined management of conditions at different risk levels, improving the accuracy and timeliness of pre-hospital diagnosis and treatment, shortening the treatment connection time after patient transfer, and ensuring the continuity and consistency of emergency treatment.

[0029] In this embodiment, after the abnormal data is highlighted in real time and given an audible and visual warning, the system further includes: Retrieve the preset knowledge base for emergency treatment of abnormal vital signs, including standardized first aid treatment suggestions and medication reference directions corresponding to different types of abnormal vital signs and risk levels. Based on the type of vital signs and risk level of the current abnormal data, match the corresponding emergency treatment plan and display it on the touch terminal. Abnormal data and corresponding early warning information are treated as high-priority data and transmitted to the hospital's diagnosis and treatment system and emergency dispatch center in advance to facilitate the hospital's preparation for diagnosis and treatment and resource allocation. At the same time, the time node, duration and data change trend of abnormal data and the corresponding early warning response operations are recorded to generate a special record of abnormal data. Abnormal data is recorded in real time and synchronized to the patient's vital signs data stream, and simultaneously transmitted to the report generation module, serving as the core data support for the condition assessment section of the outpatient summary report; If multiple abnormal data points overlap or the abnormal data continues to worsen, the level of the audible and visual warning will be increased. The touch terminal will prominently display the corresponding abnormal vital signs data and emergency response plan, and the intensity of the audible and visual warning will be increased until medical staff confirm the response and treatment procedures.

[0030] In this embodiment, the abnormal data is accurately matched with the corresponding vital sign type and risk level, and a standardized treatment plan is pushed. The abnormal data and early warning information are transmitted in advance as high-priority data to the hospital's diagnosis and treatment system and emergency dispatch center, enabling the hospital to prepare diagnosis and treatment resources and plan the reception process in advance, effectively shortening the diagnosis and treatment connection cycle. The warning effect is strengthened by increasing the warning level, highlighting key information, and enhancing the intensity of warning prompts, ensuring that medical staff can promptly detect changes in high-risk conditions and respond and treat them in a timely manner, preventing further deterioration of the condition, protecting the patient's life safety, and improving the risk prevention and control capabilities of pre-hospital emergency care.

[0031] In this embodiment, the data transmission module specifically includes: Construct a two-way data transmission link between the touch terminal and the in-hospital diagnosis and treatment system and emergency dispatch center. Monitor the data transmission quality of each data transmission link in real time, including signal stability, bandwidth utilization and transmission delay status. Determine the main link and backup link for two-way data transmission based on the data transmission quality. When the main link experiences signal interruption or quality degradation, automatically switch to the backup link to ensure the continuity of the transmission link. Based on task priority, data type, and diagnostic and treatment needs, the data to be transmitted is divided into different priorities, and data transmission is carried out based on the priority division results. Among them, abnormal data, early warning information, and handling information related to high-risk tasks are the highest priority data, real-time vital signs data streams of patients and on-site diagnostic and treatment operation records are medium priority data, and outpatient summary reports and historical diagnostic and treatment related data are low priority data. Transmission operations are performed in order of priority from high to low, giving priority to ensuring the timely transmission of critical diagnostic and treatment data. The data to be transmitted is segmented using a dual encryption mechanism. A unique identifier and integrity check code are generated for each segment. The data segments are encrypted using a symmetric encryption algorithm, and the encryption key is encrypted using an asymmetric encryption algorithm to generate encrypted data packets. Based on the point-to-point directional transmission protocol, encrypted data packets are sent to the target receiving end, namely the in-hospital diagnosis and treatment system or emergency dispatch center, through a two-way data transmission link. After receiving the encrypted data packets, the target receiving end performs decryption and integrity verification. It decrypts the data packets using an asymmetric encryption algorithm to obtain the key, and then decrypts the data fragments using the key. It also verifies the integrity of each data fragment by combining the integrity check code. After the verification is successful, the data is reassembled into complete data, a data reception confirmation signal is generated, and transmission status feedback data is obtained. If the data transmission module does not receive a reception confirmation signal within the preset time, or receives feedback of data integrity verification failure, the retransmission mechanism is triggered. Based on the unique identifier of the data fragment, the fragment data that was not successfully transmitted is located, and only that part of the data is retransmitted to avoid the overall data being transmitted repeatedly. The data transmission completion status is determined based on the transmission status feedback data and the data reception confirmation signal. Based on the judgment result of data transmission completion, local temporary medical data is cleaned up and deleted. At the same time, an encrypted backup file of the medical data is obtained and stored in the target encrypted storage area. Access permissions for retrieving the backup file of the medical data are established, which only support authorized terminals to retrieve and access it. Level 1 permission: medical staff, read and write; Level 2 permission: dispatch center, read; Level 3 permission: others, inaccessible. Based on the need for synchronous outpatient summary reports, the outpatient summary reports will be transmitted to the hospital's medical records database to establish a data exchange mechanism between pre-hospital and in-hospital medical information. The system obtains the unique patient identifier associated with the patient data collection module, matches the outpatient summary report with the unique patient identifier in the hospital's medical records database, and synchronizes the content of the outpatient summary report to the corresponding patient's medical records based on the matching results, thereby generating a continuous chain of patient medical information.

[0032] In this embodiment, a two-way data transmission link is established with the in-hospital diagnosis and treatment system and the emergency dispatch center. Priority is given to transmitting critical diagnosis and treatment data such as abnormal data and early warning information to ensure timely delivery of high-value information. This avoids non-critical data consuming transmission resources, improving the targeting and timeliness of data transmission. Layered encryption of data and keys is achieved using symmetric and asymmetric encryption algorithms. Unique identifiers and integrity check codes are configured for fragmented data, and a point-to-point directional transmission protocol is used to ensure the security and integrity of diagnosis and treatment data during transmission. The encrypted diagnosis and treatment data is backed up to a designated storage area with access permissions set to ensure storage security, prevent data leakage or unauthorized access, and maintain the privacy of patient medical information. Furthermore, through a continuous and complete patient medical information chain, the information barriers between pre-hospital and in-hospital care are broken down, providing comprehensive and detailed pre-hospital diagnosis and treatment data support for subsequent in-hospital care, and improving the continuity and synergy of overall diagnosis and treatment services.

[0033] To implement the transmission urgency calculation model, the portable multi-functional unit's hardware architecture integrates dedicated link state awareness units, navigation data interface units, storage queue monitoring units, and risk weight mapping units. These units work collaboratively to provide accurate physical input parameters for the calculation model.

[0034] Parameter: Current available bandwidth value This does not refer to the theoretical peak bandwidth provided by the telecommunications operator, but rather to the actual effective payload bandwidth of the application layer that the data transmission module can utilize at the current moment, in the current geographical location, and under the current base station load.

[0035] In its implementation, the data transmission module has a built-in independent link detection subroutine. This subroutine runs in the background at 200-millisecond intervals and performs the following steps: The system sends a set of ICMP probe packets or UDP datagrams with specific sequence numbers and timestamps to the communication gateway of the hospital's medical system. The size of the probe packets is distributed in a stepped manner (e.g., 64 bytes, 512 bytes, 1KB). The system records the sending time of the probe packets. Arrival time of the acknowledgment (ACK) from the receiving end The system calculates round-trip time (RTT) and arrival jitter. Based on the TCPVegas congestion control principle, the system uses the rate of change of RTT to inversely deduce the bottleneck bandwidth of the current link.

[0036] The system reads the underlying physical layer parameters of the 5G / 4G communication module in real time through the AT command set, including the Reference Received Power (RSRP), Signal-to-Noise Ratio (SNR), and Block Error Rate (BLER). The system maintains a channel quality-bandwidth mapping table based on historical big data. The theoretical bandwidth upper limit is obtained by looking up the table according to the current physical layer parameters, which serves as the correction boundary for the active probing results.

[0037] Because the signal of an ambulance will change drastically when it is traveling at high speed (such as when passing through overpasses, tunnels, or the shadow area of ​​tall buildings), in order to prevent the instantaneous noise of the bandwidth value from interfering with the stability of the model, the system uses a one-dimensional Kalman filter algorithm to smooth the above measurements.

[0038] To smooth bandwidth fluctuations and eliminate transient noise interference, the system executes the complete recursive Kalman filter algorithm, which includes the following five steps: State prediction steps: Based on the optimal bandwidth estimate from the previous time step Predict the prior bandwidth estimate for the current moment. : in, For the current moment The bandwidth prior estimate (in Mbps); The previous moment The posterior optimal estimate of the bandwidth; This is the state transition matrix, which is set as a scalar to account for the continuity of bandwidth changes. .

[0039] Covariance prediction steps: Calculate the covariance of the prediction error. : in, Let the prior error covariance be at the current moment; Let be the posterior error covariance of the previous time step; The process noise covariance represents the random fluctuation range of the actual network bandwidth, and is preset to [value] in this system. to The experience value between them.

[0040] Gain calculation steps: Calculate the optimal Kalman gain : in: The Kalman gain at the current moment (ranging from 0 to 1) determines whether the system trusts the predicted or measured values ​​more. To measure the noise covariance, which represents the uncertainty of physical layer measurement data (such as signal jitter), the system calculates based on the current... (Signal-to-noise ratio) Dynamic adjustment The lower the signal-to-noise ratio, the higher the value. The larger the value.

[0041] Status update steps: Combine current measurement values By correcting the prior estimate, the optimal posterior estimate is obtained. :

[0042] in, The final bandwidth estimate after filtering at the current time (i.e. ); This is the instantaneous bandwidth value directly measured by the physical layer at the current moment.

[0043] Covariance update steps: Update error covariance For use in the next iteration: .

[0044] The final value after filtering is... Its unit is uniformly quantized as megabits per second (Mbps). This value represents the system's objective transmission capacity at the current instant.

[0045] Parameters: Remaining transit time This represents the physical time window or hard cutoff time for data transmission. Obtaining this parameter relies on the deep integration between the high-precision GNSS positioning module (supporting both BeiDou and GPS dual-mode) built into the portable multi-functional unit and the vehicle navigation system.

[0046] The specific acquisition process is as follows: The system obtains the real-time latitude and longitude coordinates and heading angle of the ambulance, calls the preset vector map data or online map API, and plans the best route to the emergency center of the target hospital.

[0047] The system incorporates real-time traffic information (TMC) and V2X (vehicle-to-everything) signals. If there is severe traffic congestion or an accident ahead, the system will automatically adjust the estimated time of arrival (ETA). For example, if the system detects that the average speed of vehicles on the road ahead is below 20 km / h, it will extend the ETA accordingly.

[0048] The system subtracts the current system time from the ETA to obtain the absolute remaining time. (Unit: seconds). It should be noted that, to allow time for decompression and deployment at the receiving end within the hospital, the system will deduct a buffer window (e.g., 60 seconds) from the physical remaining time. Furthermore, when the actual remaining time is less than the minimum threshold (e.g., 30 seconds), the system will forcibly lock it at 30 seconds to prevent the denominator from approaching zero and causing the calculation result to overflow.

[0049] This parameter specifies the final deadline for completing the transmission, representing a rigid constraint in the time dimension.

[0050] Parameters: Total amount of data to be transmitted This reflects the current task load. The data transmission module maintains a multi-level priority circular transmit buffer.

[0051] The system performs a full scan of the buffer every 50 milliseconds. The scanned objects include: Real-time streaming data: Vital sign waveform data that has been collected but not yet sent (such as 12-lead electrocardiogram, continuous blood pressure waveform, and blood oxygen volume waveform).

[0052] Large file data: high-resolution ultrasound image frames (DICOM format) that have been captured but not yet uploaded, and photos of injuries at the scene.

[0053] Text data: Electronic medical record texts entered by medical staff and texts transcribed from voice notes.

[0054] The system reads the header information of each data packet, extracts its payload length field, and sums the number of bytes of all data to be transmitted. For uncompressed raw data, the system directly calculates its raw size. The final result is converted to megabits (Mbit). This value directly determines the workload.

[0055] Parameters of disease risk weights This is the key interface for introducing the urgency of the medical dimension into the physical transmission model. This parameter is derived from the calculated first or second anomaly determination coefficient.

[0056] Since the original anomaly determination coefficients are calculated based on different physiological parameters, their value ranges may not be uniform (for example, the heart rate anomaly coefficient may be between 1 and 5, while the blood pressure anomaly coefficient may be between 10 and 20). In order to incorporate them into a unified transmission model, the system has a built-in risk normalization mapping module.

[0057] This module uses a sigmoid function to map the input anomaly determination coefficients to a closed interval [0,1]. The specific mapping rules are as follows:

[0058] in, For the parameter disease risk weight, The input is the anomaly detection coefficient. This is the curve slope control factor. This is the center offset.

[0059] In the preferred parameter settings of this embodiment: Slope control factor The optimal value range is 0.5 to 0.8. This parameter controls the sensitivity of the risk weight to changes in the condition; the larger the value, the steeper the curve, and the more drastic the system's response to changes in the abnormal coefficient.

[0060] center offset The preferred value range is 2.0 to 3.0. This parameter defines the critical point of qualitative change in risk; when the input anomaly determination coefficient... achieve When the value is calculated, the risk weight is... It is exactly 0.5. This means that when a patient's overall abnormal score reaches 2 to 3 times the baseline value, the system will determine that the risk of the condition has entered a significantly critical state.

[0061] When the patient's vital signs are stable (low abnormality coefficient), Approaching 0; When a patient is in a high-risk resuscitation state (such as experiencing ventricular fibrillation or shock, with an extremely high abnormality rate), Approaching 1.

[0062] Through this mapping, the system quantifies the severity of the illness into the priority of transmission.

[0063] Based on the above four core parameters, the data transmission module executes the transmission urgency index in the floating-point unit of the local processor. Calculation:

[0064] In this formula: The data transmission urgency index is a dimensionless value used to quantitatively characterize the urgency of completing the remaining data transmission tasks in the current network environment. The total amount of data to be transmitted is the sum of the effective payloads of all data to be sent in the current cache (including vital sign waveforms, image files, and text records) as statistically recorded by the system, in megabits (Mbit). The current available bandwidth value refers to the actual effective payload rate of the data transmission link after filtering and smoothing, in megabits per second (Mbps). The remaining transfer time refers to the estimated remaining time to reach the target hospital, calculated based on the navigation system, and is expressed in seconds (s). The disease risk weight is a normalized value reflecting the severity of a patient's condition, obtained by mapping the anomaly determination coefficient through an S-shaped function. The value ranges from 0 to 1. The preset risk adjustment sensitivity factor is a dimensionless constant (preferred range 0.5 to 1.5) used to balance the influence of the urgency of the illness on the transmission strategy.

[0065] The left half of the formula is the benchmark supply-demand ratio ( This describes the supply and demand relationship at the physical level. The denominator... The dimensions are This represents the upper limit of link capacity, that is, the maximum amount of data that can be held in the transmission channel under the premise that the current network speed remains unchanged and the vehicle arrives on time. (Molecule) This refers to the actual amount of data to be transmitted. If... This means that there aren't enough physical pipelines, and the data is destined to be transmitted indefinitely.

[0066] The right half of the formula is the medical gain factor ( This is a medical correction to a physical conclusion. This is the risk adjustment sensitivity factor, a preset dimensionless constant, preferably ranging from 0.5 to 1.5. It represents the weighting degree of the system on the severity of the patient's condition.

[0067] For example: Suppose the physical supply-demand ratio is 0.8 (that is, the bandwidth is just enough to transmit 80% of the margin).

[0068] Scenario A: The patient's condition is stable ( At this point, the data transmission urgency index is... The system determines that there is no urgency and the status quo can be maintained.

[0069] Scenario B: The patient suddenly experiences a malignant arrhythmia ( At this point, the data transmission urgency index is... (Assuming) ).

[0070] Although the physical bandwidth seemed sufficient (0.8 < 1), due to the extreme severity of the patient's condition, the system artificially amplified the exponent to 1.6, thereby forcibly triggering the system to enter emergency mode. This forced the system to adopt compression strategies in advance, freeing up bandwidth for redundant data transmission (such as doubling the number of packets), or simply to transmit data faster, giving the hospital's doctors more time to think.

[0071] The data transmission module calculates the data transmission urgency index in real time. .

[0072] Furthermore, seamless switching is possible between the following two transmission modes: Mode 1: Semantic feature extraction and compressed transmission mode (when the data transmission urgency index is high) hour); Triggering conditions: Severe network bandwidth shortage, or the vehicle is about to arrive at the hospital (time window closed), or the patient is in an extremely high-risk condition requiring immediate attention.

[0073] Execution logic: In this mode, the system follows the principle of prioritizing core values ​​and automatically triggers a semantic feature extraction and compression algorithm. This algorithm is not a general file compression algorithm (such as ZIP), but rather an intelligent dimensionality reduction technique based on medical signal processing.

[0074] For vital sign data segments determined to be non-abnormal (such as a continuous 5-minute segment of normal sinus rhythm), the system will no longer transmit the original ADC sampling points.

[0075] The system invokes the built-in feature extraction DSP operator to perform dimensionality reduction processing on the vital sign waveforms within the time window, generating feature vectors. Taking electrocardiogram (ECG) data as an example, the feature vector... Its structure is as follows:

[0076] in, For feature vectors; This represents the average heart rate during that time period. It represents the standard deviation of the RR interval (the time interval between adjacent R waves), used to reflect heart rate variability; The average time limit width of the QRS group (in milliseconds); The average voltage offset of the ST segment relative to the equipotential line (unit: millivolts); This is the normalized energy integral value of the waveform segment.

[0077] The system only needs to transmit this feature vector. The receiving end can then reconstruct a trend waveform with the same clinical diagnostic characteristics using a generation algorithm.

[0078] The system only packages and sends this metadata to the hospital. The receiving end inside the hospital uses this metadata and a generative adversarial network (GAN) or spline interpolation algorithm to reconstruct a visually similar trend waveform.

[0079] The original waveform may require 100KB, while the metadata only requires 0.5KB, resulting in a compression ratio of up to 200:1, which greatly frees up the congested bandwidth.

[0080] For data segments identified as abnormal (such as identified premature ventricular bigeminy or ST segment elevation), the system marks them as regions of interest (ROI).

[0081] The system forcibly allocates channels within the current limited bandwidth, maintains lossless encoding of ROI region data, and even adds forward error correction (FEC) redundancy to ensure that this critical data can be delivered completely even under a poor network with a packet loss rate of 30%.

[0082] The system suspends the transmission of all non-medical data (such as device status logs and background videos) and allocates all bandwidth resources to vital sign data.

[0083] Mode 2: Full Lossless Transmission Mode (when the data transmission urgency index is high) hour); Triggering conditions: The current network environment is good, there is sufficient time remaining, and the patient's condition risk is within a controllable range.

[0084] Execution logic: In this mode, the system follows the principle of prioritizing data fidelity.

[0085] For electrocardiogram (ECG) data, lossless differential pulse code modulation (DPCM) or FLAC-type lossless compression algorithms are used to preserve the original precision of all sampling points (e.g., 24-bit resolution) and ensure that minute features such as P-wave notches and U-waves are clearly visible. For ultrasound images, the original DICOM files are transmitted.

[0086] Enable TCP or a reliable UDP-based transport protocol (such as QUIC), and enable full ACK confirmation and retransmission mechanisms to ensure data packet integrity.

[0087] In-hospital doctors obtain high-precision raw data that is completely consistent with that of on-site instruments, enabling them to perform refined waveform measurements and retrospective analyses (such as heart rate variability (HRV) analysis), supporting high-precision medical assessments.

[0088] The foundation of artifact removal lies in understanding the spatiotemporal distribution of interference and physiological sources. A portable, multi-functional unit acts as a central hub, aggregating the following three types of data streams in real time and using a high-precision system clock (RTC) for millisecond-level timestamp alignment.

[0089] The touch terminal integrates a highly sensitive six-axis inertial measurement unit (IMU), which includes a three-axis accelerometer and a three-axis gyroscope.

[0090] The system reads IMU data at a sampling rate of 100Hz. To filter out high-frequency vibrations from the vehicle engine (typically above 50Hz), the system first performs a low-pass filter on the raw data with a cutoff frequency of 20Hz.

[0091] The system primarily monitors the Z-axis acceleration perpendicular to the ground. A vibration threshold (e.g., 0.3g) is set for the system. When the change in Z-axis acceleration exceeds this threshold, the system records the start time of the event. End time and peak intensity This generates vehicle vibration acceleration data logs. This represents the background noise of the physical world.

[0092] The system connects to the vehicle-mounted smart infusion pump and electronic medicine cabinet via Bluetooth or Wi-Fi, or allows medical staff to obtain a medication list through a "one-click medication" operation on a touch terminal.

[0093] The system extracts the precise time of each drug injection record. .

[0094] More importantly, the system has a built-in emergency drug pharmacology database. This database stores the pharmacokinetic parameters of commonly used emergency drugs (such as adrenaline, dopamine, atropine, lidocaine, etc.). Based on the name of the injected drug, the system automatically retrieves the onset delay time and peak effect time of that drug.

[0095] Based on these parameters, the system calculates the expected window of effectiveness for the pharmacological response of this administration. For example, for intravenous bolus injection of epinephrine, the effective window is defined as... .in, This is the precise time recorded for drug injection.

[0096] Before generating the outpatient summary report, the system will iterate through all vital sign data, and based on threshold judgment logic, lock all data segments marked as abnormal and extract their timestamps. And duration.

[0097] The system uses the aforementioned 3D data to perform logical cross-validation to determine the true attributes of each anomaly. Specifically, this includes the following scenarios: Scenario A: Identification and labeling of vibration artifacts; System checks abnormal data timestamps .

[0098] like Completely falling within the time range of a certain vehicle vibration event If the time deviation from the peak vibration time is less than the preset tolerance (e.g., 500ms), it indicates that the anomaly is highly synchronized with the vehicle's bumps in time.

[0099] The system further compares the spectrum of the abnormal waveform with the spectrum of the vibration data. If both show large low-frequency fluctuations at the same frequency, then physical interference is highly suspected.

[0100] The system queries the pharmacological background at that moment. If that moment is not within the expected pharmacological response window of any drug, and no defibrillation, intubation, or other procedure signals are detected before or after that moment.

[0101] The system has a confidence level of over 95% that the anomaly is not a change in the patient's condition, but rather a transport vibration artifact caused by the instantaneous displacement of the electrode pads, changes in contact impedance, or shaking of the blood oxygen probe due to vehicle bumps.

[0102] The system does not physically delete the data (preserving the original evidence), but adds a special artifact interference tag (e.g., ArtifactTag:Type=Vibration) to its header.

[0103] When synchronizing with the hospital's records, the system includes an instruction to the hospital's display terminal to gray out or display the waveform as a dashed line, and a pop-up window will appear with the message: "Suspected vehicle vibration interference (Z-axis acceleration: 1.2g), it is recommended to ignore it." This mechanism effectively prevents hospital doctors from misdiagnosing ventricular fibrillation by seeing turbulent waves caused by bumps, thus avoiding unnecessary remote defibrillation commands.

[0104] Scenario B: Confirmation of effective treatment response; System checks abnormal data timestamps .

[0105] like It falls precisely within the expected window of pharmacological response for a given dose. For example, the record shows that atropine was injected at 10:05, and the patient's heart rate rose from 40 beats / min to 80 beats / min at 10:06.

[0106] At this point, even if the vehicle sensors detect slight vibrations (e.g., while the vehicle is in motion), the system will prioritize medical logic and determine that the change is direct evidence of drug efficacy, rather than vibration interference. This data is then considered valid diagnostic and treatment response data.

[0107] The system retains a high-risk anomaly marker for the data and removes any possible artifacts.

[0108] In the metadata of the data packet, the system automatically associates the corresponding medication ID. When synchronizing to the hospital's records, the system automatically generates an automated nursing record: "10:06 Heart rate rises to 80 bpm, associated operation: 10:05 Atropine injection".

[0109] After the above two rounds of logical screening, the data transmission module performs the final data entry operation.

[0110] The system establishes an encrypted tunnel with the hospital's medical records database (HIS / EMR system).

[0111] The system only writes outpatient summary reports and valid data streams that have been verified through artifact removal steps and have clinical empirical value into the official medical record database. For data with artifact interference markers, the system removes them and does not include them in the calculation of vital sign trend graphs (e.g., they are not included in the average heart rate statistics), but instead stores them in a separate quality control log database or original waveform backup database.

[0112] The system generates a filtering log, detailing how many artifacts were removed during the transfer and the criteria for removal (e.g., successful vibration peak matching). This log is archived along with the medical record for subsequent quality control analysis or tracing medical disputes.

[0113] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A portable, multi-functional integrated transport platform for pre-hospital emergency care, characterized in that: It includes a portable multi-functional main unit, as well as a device screening module, a temporary diagnosis and treatment adapter module, a patient data acquisition module, a touch terminal, a data transmission module, and a report generation module integrated into the portable multi-functional main unit; The equipment filtering module is used to generate a suitable equipment list based on the corresponding task type of the received emergency or outpatient instructions, and to match and filter medical equipment based on the equipment list. Based on the screened medical equipment, temporary treatment stations are set up through a temporary treatment adaptation module. The patient data acquisition module is used to collect patients' vital signs data in real time through various medical devices based on the temporary treatment station, and to display the data in real time on the touch terminal. The report generation module is used to integrate the acquired vital signs data, emergency treatment information, and medication list to generate a home visit summary report for the patient. The data transmission module is used to establish a data transmission link with the hospital's medical system based on vital sign data, on-site treatment information, medication list, and outpatient summary report, and to perform point-to-point targeted encrypted transmission based on the data transmission link.

2. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 1, characterized in that, The equipment screening module specifically includes: Acquire emergency or house call command signals, parse the emergency or house call command signals, extract the task urgency, patient basic medical information, house call location environment type and estimated transport time from the command, and generate task feature dataset; Based on the task feature dataset, a pre-defined task type classification rule is matched to determine the corresponding task type. Based on the task weight of each task type, the priority of the emergency rescue task to be performed is determined. Based on the priority ranking results and the corresponding task types, the corresponding level of equipment screening process is triggered, and the equipment matching needs of high-priority tasks are responded to first. Retrieve the preset compatible device database, extract the set of basic devices associated with this task type from the preset compatible device database, and at the same time obtain the device carrying capacity data of the portable multi-functional subject and the status data of the currently carried devices to build a device carrying evaluation model. The basic equipment set is evaluated and optimized based on the equipment-equipment evaluation model to generate a candidate equipment list. The correlation of each equipment in the candidate equipment list is analyzed, and auxiliary equipment with high correlation to the target equipment is added to form a complete equipment list. Connect each device in the complete device list to the touch terminal for display, and obtain the real-time readiness status of each device. Generate a device matching completion signal based on the real-time readiness status.

3. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 2, characterized in that, Obtaining the real-time readiness status of each device also includes: If there are unready devices, generate a list of device malfunctions, unreadiness prompts, and recommended alternative devices, and obtain the corresponding list adjustment or replacement instructions; Medical staff make secondary confirmations based on the list of fine-tuning or replacement instructions fed back by the touch terminal, adjust the complete equipment list until all equipment is in a ready state, and generate an equipment matching completion signal; If, after multiple adjustments, there are still unready devices that cannot be replaced, a task adaptation anomaly warning signal will be generated, fed back to the emergency dispatch center, and synchronized to the touch terminal.

4. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 1, characterized in that, The touch terminal displays data in real time and also includes: Acquire real-time vital sign data, including the patient's electrocardiogram data, blood oxygen data, blood pressure data, and heart rate data, and visualize the vital sign data through a touch terminal to generate a continuous stream of patient vital sign data; At the same time, the real-time collected vital sign data is compared with the corresponding preset vital sign thresholds. Abnormal data that exceeds the preset vital sign thresholds is judged. If the vital sign data exceeds the corresponding preset vital sign threshold, it is judged as abnormal data. Abnormal data is highlighted and alerted with sound and light in real time, and the corresponding vital sign data type and risk level are displayed simultaneously.

5. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 4, characterized in that, The determination of abnormal data exceeding preset vital sign thresholds also includes: Retrieve the basic judgment parameters corresponding to the abnormal data, including the difference between the abnormal data and the preset threshold, the duration of the abnormal data, and the frequency of the abnormal data. The difference, duration of abnormal data and frequency of abnormal data are weighted and calculated to obtain the first abnormality judgment coefficient, and the first abnormality judgment coefficient is compared with the preset first-level abnormality judgment coefficient threshold. When the first anomaly determination coefficient exceeds the preset first-level anomaly determination coefficient threshold, it is determined to be high-risk anomaly data; When the first abnormality judgment coefficient does not exceed the preset first-level abnormality judgment coefficient threshold, but exceeds the preset second-level abnormality judgment coefficient threshold, the associated judgment parameters corresponding to the abnormal data are retrieved, including the fluctuation range of associated vital sign data within the same period, the specific data association threshold corresponding to the patient's underlying disease, and the impact coefficient of the current diagnosis and treatment operation on the data. The second abnormality judgment coefficient is obtained based on the fluctuation range of associated vital sign data, the specific data association threshold corresponding to the patient's underlying disease, and the impact coefficient of the current diagnosis and treatment operation on the data. The second abnormality judgment coefficient is then compared with the preset third-level abnormality judgment coefficient threshold. When the second anomaly determination coefficient exceeds the preset third-level anomaly determination coefficient threshold, it is determined to be medium-risk anomaly data; When the second anomaly determination coefficient does not exceed the preset threshold of the third-level anomaly determination coefficient, it is determined to be low-risk anomaly data; The weights for calculating the first and second abnormality determination coefficients are dynamically adjusted based on the patient's age, gender, and disease type.

6. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 4, characterized in that, After the abnormal data is highlighted in real time and given an audible and visual warning, it also includes: Retrieve the preset knowledge base for emergency response to abnormal vital signs, match the corresponding emergency response plan based on the type and risk level of the current abnormal data, and display it on the touch terminal; Abnormal data and corresponding early warning information are treated as high-priority data and transmitted to the hospital's diagnosis and treatment system and emergency dispatch center in advance. At the same time, the time node, duration and data change trend of abnormal data and the corresponding early warning response operations are recorded to generate a special record of abnormal data. Abnormal data is recorded in real time and synchronized to the patient's vital signs data stream, and then transmitted to the report generation module. If multiple abnormal data points overlap or the abnormal data continues to worsen, the level of the audible and visual warning will be increased. The touch terminal will prominently display the corresponding abnormal vital signs data and emergency response plan, and the intensity of the audible and visual warning will be increased until medical staff confirm the response and treatment procedures.

7. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 1, characterized in that, The data transmission module specifically includes: Construct a two-way data transmission link between the touch terminal and the in-hospital diagnosis and treatment system and the emergency dispatch center, monitor the data transmission quality of each data transmission link in real time, and determine the main link and backup link for two-way data transmission based on the data transmission quality; Based on task priority, data type, and diagnostic and treatment needs, the data to be transmitted is divided into different priorities, and data transmission is carried out based on the priority division results. The data to be transmitted is segmented, a unique identifier and integrity check code are generated for each segment, and the data segments are encrypted. At the same time, the encryption key is encrypted to generate an encrypted data packet. The encrypted data packet is sent to the target receiving end through a bidirectional data transmission link. After receiving the encrypted data packet, the target receiving end performs decryption processing and integrity verification, generates a data reception confirmation signal, and obtains transmission status feedback data.

8. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 7, characterized in that, The data transmission module also includes: The data transmission completion status is determined based on the transmission status feedback data and the data reception confirmation signal. Based on the judgment result of data transmission completion, the local temporary medical data is cleaned up and deleted. At the same time, the encrypted medical data backup file is obtained, stored in the target encrypted storage area, and access permissions for retrieving the medical data backup file are established. Based on the need for synchronous outpatient summary reports, the outpatient summary reports will be transmitted to the hospital's medical records database to establish a data exchange mechanism between pre-hospital and in-hospital medical information. The system obtains the unique patient identifier associated with the patient data collection module, matches the outpatient summary report with the unique patient identifier in the hospital's medical records database, and synchronizes the content of the outpatient summary report to the corresponding patient's medical records based on the matching results, thereby generating a patient medical information chain.

9. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 7, characterized in that, The data transmission based on priority partitioning results specifically includes: The system can obtain the current available bandwidth value of the data transmission link in real time, and obtain the remaining transfer time for the portable multi-functional main body to navigate to the target hospital. The total amount of data to be transmitted in the current cache is counted, and the first or second abnormal judgment coefficient corresponding to the abnormal data obtained by the judgment is called and normalized into the disease risk weight. Based on the total data volume, current available bandwidth, remaining transfer time, and disease risk weights, a transmission urgency calculation model is constructed to calculate the data transmission urgency index at the current moment. The calculation formula is as follows: in: This is a data transmission urgency index, and it is a dimensionless value. The total amount of data to be transmitted, in megabits (MB). This represents the currently available bandwidth, in megabits per second. The remaining transit time is in seconds. This represents the risk weight for the disease, with a value ranging from 0 to 1. A preset risk adjustment sensitivity factor is used to balance the impact of the urgency of the illness on the transmission strategy; The data transmission module is based on the calculated... Implement dynamic transmission strategy: when When it is determined that the current link status cannot transmit all data losslessly within the remaining transit time, the semantic feature extraction and compression algorithm is automatically triggered to transmit non-abnormal vital sign data after lossy compression, and bandwidth is allocated first to transmit abnormal data losslessly. when At the same time, the original data is transmitted in a lossless encoding format.

10. The portable multi-functional integrated transport platform for pre-hospital emergency care as described in claim 8, characterized in that, Before synchronizing the outpatient summary report to the corresponding patient's in-hospital medical record, the process also includes performing an artifact removal step based on multi-source data attribution: The system acquires vehicle vibration acceleration data recorded by the built-in sensors of the touch terminal during the transportation process and extracts the drug injection time recorded in the medication list. The timestamps of the abnormal vital signs data in the outpatient summary report are matched with the peak times of the vehicle vibration acceleration data and the times of drug injection. When the timestamp of abnormal vital signs data coincides with the peak time of vehicle vibration acceleration data, and the expected change in pharmacological response caused by drug injection is not matched at that time, the abnormal vital signs data is determined to be a transport vibration artifact, and an artifact interference mark is added to the data. When the timestamp of abnormal vital signs data coincides with the expected effective window of pharmacological response after drug injection, the abnormal vital signs data is determined to be valid diagnostic and treatment response data, and the abnormality mark of the data is retained. The data transmission module only synchronizes the outpatient summary report and effective treatment response data after the artifact removal step to the hospital's medical records, and attaches a filtered log with artifact interference markers during synchronization.

Images