An auxiliary decision system and terminal for a pre-hospital trauma emergency scene

Abstract

This invention discloses an auxiliary decision-making system and terminal for pre-hospital trauma emergency care, relating to the field of trauma emergency technology. The system includes: a pre-screening module that determines whether a trauma patient is in a critical condition based on injury information; if the patient is in a critical condition, the system designates the patient as the highest-level transport recipient and initiates ambulance blood transfusion preparation; a pre-hospital injury assessment module, used to determine a transport priority score based on basic vital signs information and corresponding weighted first basic vital signs parameters, and a bleeding risk score based on basic vital signs information and corresponding weighted second basic vital signs parameters, when the patient is not in a critical condition; and a decision support module, used to determine transport decision recommendations based on the transport priority score and blood transfusion decision recommendations based on the bleeding risk score. This system overcomes the limitations of traditional scoring methods that cannot guide specific clinical resource allocation, improving the timeliness of pre-hospital trauma emergency care.

Description

Technical Field

[0001] This application relates to the field of trauma emergency technology, and in particular to an auxiliary decision-making system and terminal for pre-hospital trauma emergency scenarios. Background Technology

[0002] Trauma patients, especially those at risk of active bleeding or hemorrhagic shock, are characterized by rapid changes in their condition, a short window for effective treatment, and a high reliance on timeliness in treatment decisions during the pre-hospital phase. Pre-hospital emergency personnel typically need to assess the patient's condition within a limited time based on vital signs, level of consciousness, respiratory and circulatory status, and signs of bleeding, and determine the mode of transport, the level of the receiving hospital, and whether to initiate relevant treatment preparations in advance.

[0003] In specific pre-hospital trauma assessment techniques, existing methods mostly employ simplified scoring tools such as the Prehospital Index (PHI), which primarily rely on four vital signs—systolic blood pressure, heart rate, respiratory rate, and patient consciousness—to rapidly quantify the severity of the patient's injury. However, while these assessment methods are convenient and suitable for rapid pre-hospital application, their output mainly remains at a preliminary quantification of the patient's physiological disturbances. This results in current pre-hospital trauma assessment techniques only providing a general risk level and failing to directly guide clinical resource allocation. Summary of the Invention

[0004] Therefore, it is necessary to provide an auxiliary decision-making system and terminal for pre-hospital trauma emergency care to address the aforementioned technical issues.

[0005] The following technical solution is adopted in this specification: This manual provides an auxiliary decision-making system for pre-hospital trauma emergency care scenarios. The system includes a vital signs and injury information collection module, a pre-screening module, a pre-hospital injury assessment module, and a decision support module. The vital signs information collection module is used to collect basic vital signs and injury information of trauma patients in pre-hospital trauma emergency scenarios. The injury information includes bleeding site, bleeding degree, injury mechanism, limb injury status, and other on-site information that can reflect the patient's current injury status. The pre-screening module is used to determine whether the trauma patient is in a critical condition based on the injury information. If the trauma patient is in a critical condition, the trauma patient is determined to be the highest priority for transfer, and preparations for ambulance blood transfusion are initiated. The pre-hospital injury assessment module is used to determine the transport priority score and the bleeding risk score based on basic vital signs information and corresponding weights of the first basic vital signs parameter when the trauma patient is not in a critical condition. The weights of the first and second basic vital signs parameters are different; these values ​​are obtained after multiple rounds of optimization based on multiple evaluation indicators. The decision support module is used to determine transport decision recommendations based on transport priority scores and to determine transfusion decision recommendations based on bleeding risk scores.

[0006] Optionally, the vital signs information collection module can collect basic vital signs information and injury information in various ways, including manual entry by emergency personnel, automatic collection by vehicle-mounted monitoring equipment, or collection of basic vital signs information and injury information by mobile terminals, tablet devices, or pre-hospital electronic medical record systems.

[0007] Optionally, critical conditions include significant active hemorrhage or projectile bleeding, continued bleeding despite hemostasis measures, complete loss of consciousness, penetrating thoracic or abdominal injuries, and postural abnormalities suggesting severe pelvic injury.

[0008] Optionally, the basic vital signs information includes the values ​​of four parameters: systolic blood pressure, heart rate, respiratory rate, and patient consciousness; the weights of the basic vital signs parameters include the weight of each parameter in the basic vital signs information; the implementation method for determining the transport priority score based on the basic vital signs information and the corresponding first basic vital signs parameter weights is as follows: Score the systolic blood pressure, heart rate, respiratory rate, and patient level of consciousness to determine the score of each parameter in the baseline vital signs information; Based on the weight of each parameter in the basic vital signs information, the score of each item is weighted to obtain the transfer priority score.

[0009] Optionally, multiple evaluation metrics include the area under the receiver operating characteristic (ROC) curve, the optimal threshold of the ROC curve, sensitivity, specificity, and the critical value of the original score; the system also includes a weight optimization module. The weight optimization module is used to fine-tune the initial weight of each parameter multiple times, calculate the evaluation index value after each fine-tuning, comprehensively evaluate the values ​​of multiple evaluation indicators, and determine the weight corresponding to the optimal comprehensive evaluation as the weight of the basic vital sign parameter used in calculating the score.

[0010] Optionally, based on the transshipment priority score, the implementation method for transshipment decision recommendations is determined as follows: When the transfer priority score is less than or equal to the preset first transfer threshold, the transfer decision recommendation is to recommend the nearest transfer. When the transfer priority score is greater than the first transfer threshold and less than the preset second transfer threshold, the transfer decision recommendation is to prioritize the transfer to the nearest tertiary hospital. When the transfer priority score is greater than or equal to the second transfer threshold, the transfer decision recommendation is to prioritize the transfer to the nearest tertiary-level hospital or trauma center to match higher-level medical resources.

[0011] Optionally, based on the bleeding risk score, the method for implementing transfusion decision recommendations is determined as follows: When the bleeding risk score is less than or equal to the preset first transfusion threshold, the transfusion decision recommendation is to recommend continuous routine monitoring, and the pre-hospital transfusion early warning is not activated. When the bleeding risk score is greater than the first transfusion threshold but less than the preset second transfusion threshold, the transfusion decision recommendation is to recommend continuous monitoring, and the hospital is notified to prepare blood in advance. When the bleeding risk score is greater than or equal to the second transfusion threshold, the recommended transfusion decision is to initiate the transfusion in the ambulance, thus advancing the timing of the transfusion.

[0012] Optionally, the system also includes an information synchronization and linkage module and an in-hospital response interface module; The information synchronization and linkage module is used to transmit the basic vital signs information, injury information, critical status, transfer priority score, bleeding risk score, and transfer decision and transfusion decision suggestions of trauma patients to the receiving hospital, 120 emergency command center or other remote linkage terminals. The in-hospital response interface module is used to issue warnings, reminders, or resource preparation instructions to relevant departments within the hospital based on the basic vital signs information, injury information, critical status, transfer priority score, bleeding risk score, and transfer and transfusion decision suggestions transmitted by the information synchronization and linkage module.

[0013] Optionally, the system also includes a terminal doctor review module; The terminal physician review module is used to continue to monitor the vital signs of trauma patients after the physician has performed operations on the trauma patient based on the transfer decision and blood transfusion decision recommendations, and to feed the monitoring results back to the hospital in real time.

[0014] This specification provides an auxiliary decision-making terminal for pre-hospital trauma emergency scenarios, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the functions of the aforementioned auxiliary decision-making system for pre-hospital trauma emergency scenarios.

[0015] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the functions of the aforementioned auxiliary decision-making system for pre-hospital trauma emergency scenarios.

[0016] This specification provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the functions of the aforementioned auxiliary decision-making system for pre-hospital trauma emergency scenarios.

[0017] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects: The decision support system for pre-hospital trauma emergency care provided in this manual uses a pre-screening module to quickly assess injury information such as bleeding sites and injury mechanisms. Once a critical condition is identified, the patient is immediately designated as a top-priority transport candidate, and ambulance blood transfusion preparation is initiated. This allows for the most critical treatment time for trauma patients whose conditions change rapidly and whose treatment window is short. For non-critical patients, the pre-hospital injury assessment module uses different parameter weights obtained through multiple rounds of optimization to calculate transport priority scores and bleeding risk scores. The decision support module then outputs specific transport decision suggestions (such as transport method and receiving hospital level) and blood transfusion decision suggestions. This overcomes the limitations of traditional scoring systems that cannot guide specific clinical resource allocation, enabling pre-hospital emergency personnel to make accurate and actionable decisions based on quantified dual-score results within a limited time, significantly improving the timeliness of pre-hospital trauma emergency care. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This specification provides a schematic diagram of the structure of an auxiliary decision-making system for pre-hospital trauma emergency care scenarios. Figure 2 This manual provides a schematic diagram of a pre-hospital trauma triage and transfer decision-making process. Figure 3 This is a schematic diagram of a computer device that enables an auxiliary decision-making system for pre-hospital trauma emergency care, as provided in this specification. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0021] Trauma patients are characterized by rapid changes in their condition, a short window for effective treatment, and a high dependence on timeliness in treatment decisions during the pre-hospital stage. If high-risk patients cannot be identified in a timely manner and key information cannot be synchronized to the hospital in the pre-hospital stage, it can easily lead to delays in in-hospital blood preparation, bed preparation, and the activation of the trauma team, thereby affecting the efficiency of rescue and the prognosis of patients.

[0022] In existing technologies, pre-hospital injury assessment typically relies on the experience and judgment of emergency responders or uses simplified scoring tools such as the PHI (Performance-Based Injury Assessment). The application of the PHI score in pre-hospital trauma triage is a rapid injury assessment method based on pre-hospital physiological indicators. Its core idea is as follows: before the patient arrives at the hospital, emergency responders collect several easily accessible physiological indicators of the patient at the scene, during transport, or in the ambulance, assigning scores according to preset grading rules. The scores are then directly added together to form a total score, which is used to roughly stratify the patient's injury and assist in decisions such as on-site triage, transport priority determination, and in-hospital early warning. The PHI was initially proposed by Koehler et al. in 1986, designed to provide an objective, rapid, and standardized triage scoring tool for pre-hospital trauma patients, distinguishing between patients with minor injuries and those with severe injuries who may die within 72 hours of injury or require emergency surgical / neurosurgery.

[0023] The specific implementation details of the existing solution are as follows: PHI primarily collects four pre-hospital available vital signs: systolic blood pressure, heart rate, respiratory rate, and patient level of consciousness. Each vital sign parameter is classified into different levels and assigned a corresponding score based on the degree of abnormality at the time of the patient's visit; a higher score generally indicates a more severe physiological disturbance. According to publicly available information, the typical scoring method for traditional PHI (Pulsed Heart Injury) includes: 0 points for systolic blood pressure >100 mmHg, 1 point for 86–100 mmHg, 2 points for 75–85 mmHg, and 5 points for 0–74 mmHg; 0 points for heart rate 51–119 bpm, 3 points for ≥120 bpm, and 5 points for <50 bpm; 0 points for normal breathing, 3 points for shallow, rapid, or labored breathing, and 5 points for respiratory rate <10 breaths / min or requiring intubation; 0 points for clear consciousness, 3 points for confused / agitation, and 5 points for inability to speak comprehensible language; additionally, some PHI implementations include penetrating chest or abdominal injuries as an additional bonus, worth 4 points. The higher the final total score, the more severe the injury. This scoring system typically defines minor trauma as 0–3 points and major trauma as 4–20 points. It is used to guide pre-hospital emergency personnel in making triage decisions such as whether to prioritize transfer to a high-level trauma center and whether to activate the in-hospital trauma team in advance.

[0024] In practical implementation, traditional PHI typically uses two methods. The first is a paper-based scoring card or emergency procedure sheet, where emergency responders manually check off items and sum the results. The second is an electronic scoring module integrated into vehicle monitoring systems, mobile tablets, emergency apps, or electronic medical record terminals, where the system automatically calculates the total score and outputs the risk level based on the entered data. Regardless of the method used, the underlying logic remains consistent: using fixed indicators, fixed grading, fixed weights, and a simple linear summation method to assess injury. The advantages of this approach are its clear structure, ease of operation, and low training costs, making it suitable for rapid application in time-sensitive pre-hospital scenarios. Furthermore, subsequent multi-center validation studies have demonstrated the effectiveness of PHI in predicting short-term post-traumatic mortality and the need for emergency life-saving surgeries, thus making it one of the earliest and most typical pre-hospital trauma triage tools.

[0025] The limitations of existing technologies: While these scoring tools offer advantages such as fewer indicators, ease of operation, and suitability for pre-hospital applications in rapid triage, they generally suffer from fixed scoring weights, limited ability to identify traumatic blood loss risks, and insufficient integration with critical treatment decisions such as pre-hospital blood transfusion and in-hospital resource pre-allocation. In other words, most existing scoring methods can only provide a rough indication of the severity of the injury and are insufficient to provide standardized support for specific actions such as pre-hospital blood transfusion, transport priority assessment, and in-hospital blood preparation. Existing PHI scoring and related pre-hospital scoring technologies mostly only serve pre-hospital injury assessment and lack a direct, standardized, and interconnected mechanism with in-hospital emergency procedures, making it difficult to further translate pre-hospital scoring results into specific treatment measures such as in-hospital blood preparation, trauma team early warning, surgical resource preparation, and green channel activation.

[0026] First, traditional PHI scores typically employ a fixed scoring system and simple linear summation. The weights of each indicator are primarily derived from existing rules and are not recalibrated for specific patient populations, regional treatment characteristics, or specific emergency scenarios. Therefore, they fail to adequately reflect the varying contributions of different indicators to the actual severity of a patient's injury and the risk of blood loss. Under the same total score, different combinations of vital signs may correspond to different true risk levels, and traditional PHI struggles to effectively distinguish these differences. Consequently, its quantification of injury severity remains relatively crude, and the explanatory power of the scoring results is limited.

[0027] Secondly, the traditional Pre-hospital Severity Index (PHI) is primarily used for rapid pre-hospital triage. Its original design and subsequent validation focused more on screening high-risk patients, indicating mortality risk, or assessing the need for emergency life-saving surgeries, rather than specifically optimizing the connection between pre-hospital scoring results and in-hospital objective injury severity assessment systems. Therefore, when it is necessary to further transform pre-hospital scoring results into in-hospital injury assessment criteria, resource early warning criteria, or patient reception preparation criteria, the consistency and persuasiveness of the traditional PHI remain insufficient. For example, the correlation between the traditional PHI and the commonly used in-hospital injury severity assessment index (ISS) is relatively limited. In this invention, the correlation coefficient between the original PHI and ISS is only 0.439, which, although statistically significant, is still at a moderate level, suggesting that its ability to represent the actual severity of patients' injuries still has room for improvement.

[0028] Furthermore, traditional PHI (Pre-Hospital Injury Assessment) outputs are typically coarse stratification results based on the total score, which are more suitable for rapid assessment of "critical condition." However, their quantitative support capabilities are insufficient for higher-level application scenarios required by pre-hospital emergency injury systems, such as refined transport priorities, triggering more proactive pre-hospital intervention strategies, adjusting the intensity of in-hospital blood preparation warnings, controlling the timing of trauma team activation, and setting green channel response levels. In other words, the problem with existing technology is not simply "whether it can complete the scoring," but that the scoring results cannot be stably and standardizedly embedded into subsequent treatment processes, making it difficult to serve as an effective basis for pre-hospital-in-hospital collaborative decision-making.

[0029] On the other hand, although some existing pre-hospital emergency care equipment has the functions of vital sign monitoring and information transmission, most are still limited to single parameter collection or simple data uploading. A complete technical process has not yet been formed to comprehensively analyze multi-source pre-hospital information, automatically generate risk classification and treatment suggestions, and establish a coordinated response with the hospital receiving end. Current pre-hospital and in-hospital coordination still relies heavily on telephone reporting and manual descriptions, resulting in insufficient information standardization, poor dynamic updating capabilities, and inadequate proactive decision-making. This makes it difficult to meet the actual needs of trauma emergency care, especially for patients at high risk of blood loss, where "information arrives before the patient, and contingency plans are implemented before the patient's arrival."

[0030] Furthermore, most existing pre-hospital scoring technologies remain at the independent application level at the hospital level. Different hospitals and 120 emergency centers often lack uniformity in emergency procedures, scoring standards, and information interpretation rules. This results in pre-hospital vital sign information and injury assessment results being difficult for hospitals to directly identify, accurately interpret, and quickly access after being transmitted to the hospital. This further leads to poor pre-hospital information exchange, delayed in-hospital treatment preparation, and insufficient coordination efficiency. This indicates that the core deficiency of existing technologies lies not only in the fixed weights and crude quantification of traditional PHI scoring itself, but also in the lack of a pre-hospital emergency injury assessment system that can integrate pre-hospital vital sign collection, injury assessment, risk stratification, treatment triggering, and in-hospital emergency response procedures.

[0031] Therefore, the core shortcomings of existing technologies can be summarized as follows: while maintaining the advantage of pre-hospital convenience, a complete technical system that can simultaneously take into account rapid assessment, risk stratification, key decision support, and pre-hospital-in-hospital information linkage has not yet been established. The fixed weights, coarse injury quantification, and insufficient connection with the objective injury severity assessment in hospitals of traditional PHI scores are only one specific manifestation of this systemic defect in the assessment process. The present invention does not aim to simply make local corrections to the PHI score, but rather to provide an auxiliary decision-making system for pre-hospital trauma emergency care scenarios. While retaining the characteristics of rapid pre-hospital data collection and easy application, it incorporates the corrected PHI score as one of the injury assessment steps, further enabling rapid injury assessment, risk stratification, triage, transfer priority determination, and coordinated early warning of in-hospital treatment resources for trauma patients. This overcomes the problems of insufficient integration between scoring tools and in-hospital emergency procedures, coarse injury quantification, and limited support for risk stratification and critical treatment decisions in existing pre-hospital trauma assessment technologies. As a result, it improves the ability to represent the actual severity of patients' injuries and the support for key pre-hospital decisions and in-hospital emergency preparation, enhancing the systematicness and practicality of pre-hospital-in-hospital collaborative treatment.

[0032] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0033] Figure 1 This is a schematic diagram of the structure of an auxiliary decision-making system for pre-hospital trauma emergency care, as described in this specification. The system includes a vital signs and injury information collection module, a pre-screening module, a pre-hospital injury assessment module, and a decision support module.

[0034] The vital signs information collection module is used to collect basic vital signs and injury information of trauma patients in pre-hospital trauma emergency scenarios. The injury information includes bleeding site, bleeding degree, injury mechanism, limb injury status, and other on-site information that can reflect the patient's current injury status.

[0035] The methods for collecting basic vital signs and injury information in the vital signs information collection module include manual entry by emergency personnel, automatic collection by vehicle-mounted monitoring equipment, or collection by mobile terminals, tablet devices, and pre-hospital electronic medical record systems.

[0036] Basic vital signs information includes the values ​​of four parameters: systolic blood pressure, heart rate, respiratory rate, and patient level of consciousness. This vital signs information collection module can be manually entered by emergency personnel, automatically collected by vehicle-mounted monitoring equipment, or implemented through mobile terminals, tablet devices, pre-hospital electronic medical record systems, etc., providing basic data for subsequent injury assessment and decision support.

[0037] The pre-screening module is used to determine whether a trauma patient is in a critical condition based on injury information. If the trauma patient is in a critical condition, the trauma patient is identified as the highest priority for transfer, and preparations for ambulance blood transfusion are initiated.

[0038] The pre-screening module is primarily designed for the rapid identification of the most critically ill patients who require immediate intervention.

[0039] Optionally, determining whether a trauma patient is in a critical condition based on injury information includes: inputting injury information into a pre-built neural network model to obtain a determination result on whether the trauma patient is in a critical condition; wherein, a critical condition includes obvious active hemorrhage or spurting hemorrhage, continued bleeding after hemostasis measures, complete loss of consciousness of the patient, penetrating injury to the chest or abdomen, and postural abnormalities indicating severe pelvic injury, such as obvious deformity or external rotation of both legs.

[0040] Once a patient exhibits any of the above critical signs, the pre-screening module directly identifies the trauma patient as the highest-level transport target and simultaneously initiates ambulance blood transfusion preparation to ensure that the patient can receive a blood transfusion immediately upon boarding, maximizing the chances of rescue.

[0041] The pre-hospital injury assessment module is used to determine the transport priority score based on basic vital signs information and the corresponding weights of the first basic vital signs parameter when the trauma patient is not in a critical condition, and to determine the bleeding risk score based on basic vital signs information and the corresponding weights of the second basic vital signs parameter. The values ​​of the weights of the first and second basic vital signs parameters are different. The values ​​of the weights of the first and second basic vital signs parameters are obtained after multiple rounds of optimization based on multiple evaluation indicators.

[0042] This invention constructs two improved scoring systems based on the PHI: Transport Priority PHI (T-PHI), used to assess patient transport priority and guide transport destination; and Bleeding Risk PHI (B-PHI), used to assess patient bleeding risk and guide blood preparation and pre-hospital transfusion decisions. Both are based on the four core indicators of PHI, and through reweighting and hierarchical optimization, they are made more suitable for coordinated transport and transfusion decisions in pre-hospital emergency care scenarios for trauma patients.

[0043] To evaluate the effectiveness of the scoring system, this invention employs multiple evaluation indicators, including the area under the Receiver Operating Characteristic (ROC) curve, the optimal threshold of the ROC curve (the ROC curve is an evaluation curve plotted with sensitivity as the ordinate and 1-specificity as the abscissa, and its optimal threshold is the judgment threshold determined based on the analysis of the curve, which optimizes the overall performance of the scoring system in terms of sensitivity and specificity), sensitivity, specificity, and the cut-off value of the original score (referring to the actual score threshold used to distinguish different risk levels or judgment results after mapping the optimal threshold of the ROC curve to the original scoring system).

[0044] The ROC curve can be understood as a "comprehensive evaluation chart" used to observe the scoring system's ability to distinguish between high-risk and low-risk patients at different cutoff points. AUC is the area under the ROC curve; the larger the value, the stronger the overall recognition ability of the scoring system. An AUC of 0.5 indicates almost no distinguishing ability, while an AUC closer to 1.0 indicates better recognition performance. Sensitivity represents the proportion of truly high-risk patients correctly identified by the system; higher sensitivity means a lower probability of missing high-risk patients. Specificity represents the proportion of truly low-risk patients correctly identified as low-risk; higher specificity means fewer instances of low-risk patients being misclassified as high-risk. In short, sensitivity emphasizes "fewer missed cases," specificity emphasizes "fewer misclassifications," and AUC reflects the overall recognition level of the system.

[0045] The system also includes a weight optimization module; the weight optimization module is used to fine-tune the initial weight of each parameter multiple times, calculate the evaluation index value after each fine-tuning, comprehensively evaluate the multiple evaluation index values, and determine the weight corresponding to the optimal comprehensive evaluation as the weight of the basic vital sign parameter used when calculating the score.

[0046] Specifically, to determine the weights of each basic vital sign parameter in the T-PHI scoring system, this invention first uses the original PHI score as the basic scoring model, assigns scores to systolic blood pressure, heart rate, respiratory rate, and patient consciousness parameters according to the original scoring rules, and calculates the original total PHI score. The calculation formula is as follows:

[0047] in, These represent the original item scores corresponding to systolic blood pressure, heart rate, respiratory rate, and patient consciousness status, respectively.

[0048] Based on this, the present invention introduces weighting coefficients into the transport priority scoring, and performs a weighted summation of the scores of each parameter to obtain the T-PHI scores under different weight combinations: in, These are the weighting coefficients of systolic blood pressure, heart rate, respiratory rate, and patient consciousness in the T-PHI scoring system, i.e., the weights of the first baseline vital signs parameters.

[0049] Subsequently, using the actual transport outcome or the preset transport priority result as the judgment standard, ROC curve analysis was performed on the T-PHI score calculated for each weight combination to obtain AUC, optimal ROC threshold, sensitivity, specificity, and original score cut-off. The optimal ROC threshold was determined using the principle of maximizing the Youden index.

[0050] in, For sensitivity, For specificity; when The score threshold corresponding to the maximum value is the optimal ROC threshold for that weight combination. Sensitivity and specificity are calculated using the following formulas:

[0051] in, Indicates the number of true positive cases. Indicates the number of false negatives. Indicates the number of true negative cases. This indicates the number of false positives.

[0052] This invention, based on the original PHI weighting, performs seven iterative fine-tuning of the weights for each vital sign parameter. After each adjustment, the total T-PHI score for all samples is recalculated, and ROC curve analysis is repeated to compare the AUC, optimal ROC threshold, sensitivity, specificity, and cut-off under different weight combinations. Weight selection prioritizes higher AUC while also considering the balance between sensitivity and specificity, as well as the interpretability and operability of the scoring system in pre-hospital emergency settings.

[0053] In one embodiment, in the T-PHI scenario, the evaluation results after 7 fine-tunings of the initial weights of each parameter are shown in Table 1.

[0054] Table 1 Evaluation results under T-PHI After seven fine-tunings, the final relative weighting ratio of systolic blood pressure, heart rate, respiratory rate, and patient consciousness was selected as 1:4:4:1.5. Therefore, the weights of the first baseline vital signs parameters are as follows: Systolic blood pressure: 0.38, Heart Rate: 1.52. Respiratory rate: 1.52. Patient's state of consciousness: 0.58.

[0055] Therefore, the final T-PHI score calculation formula is: ROC analysis results of the original PHI and the multi-weighted optimized T-PHI in identifying severely traumatized patients (with ISS ≥16 as the outcome). The table compares the AUC, sensitivity, specificity, and optimal cut-off of each version of the score to evaluate the discriminative ability and screening performance of different T-PHI schemes. Among them, the fourth-generation T-PHI, highlighted in red, maintains a high AUC level while having higher sensitivity, which better meets the application needs of prioritizing the identification of high-risk patients and reducing missed screenings in pre-hospital emergency scenarios, and is therefore selected as the final T-PHI scoring scheme.

[0056] In one embodiment, to determine the weights of each vital sign parameter in the B-PHI scoring system, this invention first uses the original PHI score as the base scoring model, assigning scores to parameters such as systolic blood pressure, heart rate, respiratory rate, and patient consciousness status according to the original scoring rules, and then calculating the original total PHI score. The calculation formula is as follows:

[0057] in, , , , These represent the original item scores corresponding to systolic blood pressure, heart rate, respiratory rate, and patient consciousness status, respectively.

[0058] Based on this, the present invention introduces weighting coefficients into the bleeding risk score, and performs a weighted summation of the scores of each parameter to obtain the B-PHI score under different weight combinations: in, , , , These are the weighting coefficients of systolic blood pressure, heart rate, respiratory rate, and patient consciousness in the B-PHI scoring system, i.e., the weighting of the second baseline vital signs parameters.

[0059] Subsequently, using actual transfusion outcomes or preset transfusion priority results as the judgment criteria, ROC curve analysis was performed on the total B-PHI score calculated for each weighted combination to obtain AUC, optimal ROC threshold, sensitivity, specificity, and raw score cut-off. The optimal ROC threshold was determined using the principle of maximizing the Youden index.

[0060] when The score threshold corresponding to the maximum value is the optimal ROC threshold for that weight combination. Sensitivity and specificity are calculated using the following formulas:

[0061] in, Indicates the number of true positive cases. Indicates the number of false negatives. Indicates the number of true negative cases. This indicates the number of false positives.

[0062] This invention, based on the original PHI weighting, performs five iterative fine-tuning of the weights for each vital sign parameter. After each adjustment, the total B-PHI score for all samples is recalculated, and ROC curve analysis is repeated to compare AUC, optimal ROC threshold, sensitivity, specificity, and cut-off under different weight combinations. Weight selection prioritizes higher AUC, while also considering sensitivity, specificity, pre-hospital transfusion demand identification ability, and the clinical interpretability of the scoring system.

[0063] Specifically, in the B-PHI scenario, the evaluation results after five fine-tunings of the initial weights of each parameter are shown in Table 2.

[0064] Table 2 Evaluation results under B-PHI Based on the results of five rounds of weight fine-tuning, the fourth-generation B-PHI scoring model was finally selected. The relative weights of systolic blood pressure, heart rate, respiratory rate, and patient consciousness in this model are as follows:

[0065] To facilitate scoring calculations, the relative weights mentioned above are converted into actual weight coefficients proportionally, resulting in: Therefore, the final B-PHI score calculation formula is: Systolic blood pressure, heart rate, respiratory rate, and patient consciousness were weighted at 2.56, 0.64, 0.16, and 0.64, respectively, in the final score calculation. The B-PHI score calculated based on this weighted combination was then subjected to ROC curve analysis to determine the final transfusion priority threshold.

[0066] The original PHI and the optimized B-PHI bleeding risk score are compared using ROC analysis to predict the severity of blood loss in patients (based on whether the amount of red blood cells transfused within 24 hours of admission is ≥4 units). The table compares the AUC, sensitivity, specificity, and optimal cut-off of each version of the score to evaluate the ability of different B-PHI weighting schemes to identify patients with high transfusion needs. The results show that the optimized B-PHI has improved overall predictive performance compared to the original PHI. The fourth-generation B-PHI, highlighted in red, maintains a high AUC while exhibiting high sensitivity and specificity, better aligning with the application goal of prioritizing the identification of high-bleeding-risk patients and reducing missed screenings in pre-hospital emergency settings. Therefore, it was selected as the final B-PHI scoring scheme.

[0067] In one embodiment, the weights of the basic vital signs parameters include the weight of each parameter in the basic vital signs information. The method for determining the transport priority score based on the basic vital signs information and the corresponding weights of the first basic vital signs parameters is as follows: systolic blood pressure, heart rate, respiratory rate, and patient consciousness are scored to determine the score of each parameter in the basic vital signs information; each score is weighted according to the weight of each parameter in the basic vital signs information to obtain the transport priority score.

[0068] It should be noted that the bleeding risk score and the transfer priority score differ only in the weighting of the basic vital signs parameters used in their calculation; their calculation methods are essentially the same, and will not be repeated here in this embodiment.

[0069] The revised PHI score is used as one of the methods for injury assessment in this module to improve the ability of pre-hospital injury assessment results to represent the actual severity of the patient's injury and to support subsequent clinical decision-making. Furthermore, since the revised PHI score has a higher correlation with the ISS score, it can enhance the consistency between pre-hospital scoring results and in-hospital injury assessment standards, and improve the objectivity and persuasiveness of the pre-hospital-in-hospital injury assessment link.

[0070] Validated by actual case data, as shown in Table 3, both B-PHI and T-PHI demonstrated good discriminative ability and a clear risk gradient in their stratification effects. B-PHI stratification results showed that the proportions of patients with ≥4 units of red blood cells transfused within 24 hours were 17.70%, 28.10%, and 66.70% in the low-risk, medium-risk, and high-risk groups, respectively, with a significant increase in the proportion of patients with higher transfusion needs as the risk level increased. T-PHI stratification results showed that the proportions of patients with ISS ≥16 were 32.30%, 75.70%, and 91.00% in the low-priority, medium-priority, and high-priority groups, respectively, also showing a significant increasing trend with increasing stratification. These results indicate that the B-PHI and T-PHI scoring systems constructed in this invention can effectively achieve stratified identification of patient risk and can effectively transform the scoring results into corresponding pre-hospital transport and transfusion decision-making criteria, demonstrating good practical application value.

[0071] Table 3. Validation results of stratification effect In one embodiment, more indicators can be included when calculating the transport priority score and the bleeding risk priority score. For example, in addition to the original vital signs information, information such as blood oxygen saturation, bleeding location, bleeding degree, and injury mechanism can be added to form the transport priority score and the bleeding risk priority score.

[0072] The pre-hospital injury assessment module can be implemented using different carriers, including but not limited to: (1) paper scoring sheet; (2) ambulance vehicle terminal; (3) emergency mobile APP; (4) tablet device; (5) pre-hospital electronic medical record system; (6) emergency dispatch platform; (7) trauma treatment auxiliary decision system; (8) built-in scoring module in wearable terminal or portable emergency equipment.

[0073] The decision support module is used to determine transport decision recommendations based on transport priority scores and to determine transfusion decision recommendations based on bleeding risk scores.

[0074] B-PHI is primarily used to assess a patient's transfusion needs and priority, answering the question, "Does this patient need blood prepared and transfused as soon as possible?" T-PHI is primarily used to assess a patient's transport priority and destination selection, answering the question, "Where should this patient be sent and with what priority?" By assessing "transfusion decisions" and "transport decisions" separately, the system avoids the problem that traditional single scoring tools can only provide a general risk level but are difficult to directly guide clinical resource allocation.

[0075] The decision support module can generate treatment recommendations corresponding to the pre-hospital emergency care process based on transport priority scores and bleeding risk scores. These recommendations include at least patient transport priority information, pre-hospital transfusion demand assessment information, and in-hospital blood preparation assessment or early warning information. They may further include key monitoring prompts, pre-hospital active intervention prompts, and other auxiliary decision-making information related to traumatic blood loss risk. Through this module, the system can further transform pre-hospital injury assessment results into actionable procedural recommendations, enabling emergency personnel and receiving hospitals to make advance judgments and coordinated arrangements regarding patient transport sequence, pre-hospital transfusion feasibility, and in-hospital blood preparation, thereby improving pre-hospital emergency care decision support capabilities and pre-hospital-in-hospital collaboration efficiency.

[0076] In one embodiment, the transfer decision recommendation based on the transfer priority score is determined as follows: when the transfer priority score is less than or equal to a preset first transfer threshold, the transfer decision recommendation is to recommend transfer to the nearest hospital; when the transfer priority score is greater than the first transfer threshold and less than a preset second transfer threshold, the transfer decision recommendation is to recommend priority transfer to the nearest tertiary hospital; when the transfer priority score is greater than or equal to the second transfer threshold, the transfer decision recommendation is to recommend priority transfer to the nearest tertiary-level A hospital or trauma treatment center to match higher-level medical resources.

[0077] Optionally, the first transfer threshold can be 4, and the second transfer threshold can be 12.

[0078] In one embodiment, the method for determining transfusion decision recommendations based on bleeding risk scores is as follows: when the bleeding risk score is less than or equal to a preset first transfusion threshold, the transfusion decision recommendation is to continue routine monitoring without initiating pre-hospital transfusion early warning; when the bleeding risk score is greater than the first transfusion threshold but less than a preset second transfusion threshold, the transfusion decision recommendation is to continue monitoring and simultaneously notify the hospital to prepare blood in advance; when the bleeding risk score is greater than or equal to the second transfusion threshold, the transfusion decision recommendation is to initiate transfusion in the ambulance, thus advancing the transfusion timing.

[0079] Optionally, the first transfusion threshold can be 4, and the second transfusion threshold can be 9.

[0080] In one embodiment, please see [link to previous article]. Figure 1 The system also includes an information synchronization and linkage module and an in-hospital response interface module.

[0081] The information synchronization and linkage module is used to transmit basic vital signs, injury information, critical status, transport priority score, bleeding risk score, and transport and transfusion decision recommendations of trauma patients to the receiving hospital, the 120 emergency command center, or other remote linkage terminals. The transmitted content can be synchronized in the form of structured data, charts, early warning prompts, or electronic medical records, so that the receiving end in the hospital can obtain the patient's pre-hospital injury status and corresponding risk level before the patient arrives. This module enables the early transmission of pre-hospital information to in-hospital processes, reducing problems such as information lag, inconsistent expression, and misunderstandings that exist in traditional manual verbal reporting methods.

[0082] The in-hospital response interface module is used to issue warnings, reminders, or resource preparation instructions to relevant departments within the hospital based on the basic vital signs information, injury information, critical status, transfer priority score, bleeding risk score, and transfer and transfusion decision suggestions transmitted by the information synchronization and linkage module.

[0083] The in-hospital response interface module enables hospital emergency, trauma care, blood transfusion preparation, surgical preparation, and green channel processes to be initiated or adjusted in advance based on pre-hospital synchronous information. This module can issue warnings, prompts, or resource preparation instructions to relevant departments or systems within the hospital based on pre-hospital transmitted basic vital signs information, injury information, critical status, transport priority score, bleeding risk score, and transport and blood transfusion decision recommendations. This supports the hospital in completing tasks such as blood preparation, trauma team notification, adjustment of admission priorities, and green channel preparation in advance. Through this module, pre-hospital emergency injury assessment results can be further embedded into in-hospital emergency procedures, achieving effective linkage between pre-hospital assessment, pre-hospital decision-making, and in-hospital treatment preparation.

[0084] In one embodiment, the system further includes a terminal physician review module. This module is used to continue monitoring the vital signs of the trauma patient after the physician has performed procedures based on transfer and transfusion decisions, and to feed the monitoring results back to the hospital in real time.

[0085] After the scoring is completed, the system will set up a terminal doctor review mechanism, whereby doctors will review the system's output to ensure that the intelligent assisted decision-making is both efficient and meets medical safety requirements. After the review is passed, the system will continue to monitor the patient's vital signs dynamically and feed the relevant information back to the hospital in real time. This allows the hospital's emergency department, blood transfusion department, and trauma treatment team to know the patient's status in advance and prepare for admission, thus achieving true pre-hospital-hospital information integration.

[0086] Optionally, the auxiliary decision-making system for pre-hospital trauma emergency scenarios provided by the present invention can be implemented in various forms, including but not limited to: vehicle-mounted emergency terminal; (1) Emergency mobile app; (2) Flat panel devices; (3) Pre-hospital electronic medical record system; (4) Emergency medical information platform; (5) A remote linkage platform that connects with the hospital information system, emergency system or 120 dispatch system.

[0087] In a systematic implementation, equipment or software can automatically read the patient's measured sub-indicator data, automatically generate injury scores, risk levels, and corresponding decision support prompts, and simultaneously send the results to the hospital receiving end. The hospital can make advance preparations based on preset rules regarding patient priority, blood preparation procedures, trauma team response, and green channel activation conditions. All of the above implementation methods fall within the protection scope of the pre-hospital emergency injury assessment system described in this invention.

[0088] like Figure 2 As shown, Figure 2 This is a pre-hospital trauma triage and transport decision-making process, which includes: First, pre-screening to determine if the trauma patient's injury meets the criteria for high-risk rapid screening. These criteria include: significant active or projectile bleeding, continued bleeding after hemostasis measures, complete loss of consciousness, penetrating chest / abdomen injuries, and significant pelvic deformities or obvious external rotation of the legs. If any one of these criteria is met, the highest level of transport is initiated by default, and blood transfusion is prepared in the ambulance to ensure immediate transfusion upon boarding. If none of these criteria are met, B-PHI and T-PHI scores are used to assess transfusion and transport priorities, respectively. Then, a terminal physician review mechanism is implemented. After successful review, the system continues to dynamically monitor the patient's vital signs and provides real-time feedback to the hospital terminal.

[0089] Specifically, transfusion priorities include: B-PHI less than or equal to 4: low risk, continuous routine monitoring, no pre-hospital transfusion warning; B-PHI greater than 4 and less than 9: medium risk, continuous monitoring, blood prepared in the hospital; B-PHI greater than or equal to 9: continuous monitoring, transfusion immediately upon boarding. Transport priorities include: T-PHI less than or equal to 4: low risk, transported to the nearest facility; T-PHI greater than 4 and less than 12: medium risk, priority transport to the nearest tertiary hospital; T-PHI greater than or equal to 12, priority transport to the nearest tertiary hospital / trauma treatment center.

[0090] In one embodiment, the present invention also provides a method for implementing an auxiliary decision-making system for pre-hospital trauma emergency care scenarios, specifically including: S1: Collecting Pre-hospital Vital Signs and Injury Information: After a trauma patient is transferred to an ambulance or enters the pre-hospital emergency treatment phase, the first step is to collect basic vital signs and injury-related information. This includes collecting basic vital signs such as systolic blood pressure, pulse, and respiratory rate, as well as injury information such as bleeding site, degree of bleeding, mechanism of injury, limb injury, presence of ongoing active bleeding, and whether hemostasis measures have been taken. This information can be manually entered into the system by emergency personnel, or automatically acquired by onboard monitoring equipment, mobile terminals, tablets, pre-hospital electronic medical record systems, or other data collection devices.

[0091] S2: Preprocessing and standardizing the collected data: After collecting vital signs and injury information, the system organizes and standardizes the acquired data. Specifically, this may include standardizing units for various vital signs, identifying outliers, marking missing items, recording timestamps, and using structured coding; for injury description information, it can be converted into standard fields or tags that the system can recognize according to preset classification methods.

[0092] S3: Pre-hospital injury assessment based on preset assessment rules: After quantifying the patient's injury, the system uses the modified PHI scoring method as one of the injury assessment steps. That is, it still uses the systolic blood pressure, pulse, respiratory rate and consciousness status involved in the traditional PHI as the basic indicators. First, it obtains the scores of each item according to the existing PHI rules, and then performs weighted calculation according to the preset modified weights to obtain the modified pre-hospital injury score result.

[0093] S4: Risk stratification and critical treatment decisions based on injury assessment results: (This step is the biggest difference between our approach and existing scoring standards) After obtaining the pre-hospital injury assessment results, the system further classifies patients into risk levels based on preset stratification thresholds, judgment rules, or risk level standards, and forms key treatment judgments that directly correspond to the pre-hospital emergency care process.

[0094] Specifically, the system can determine, based on the assessment results, whether a patient is a high-risk trauma patient, whether there is a high risk of blood loss, whether the patient needs to be prioritized for transport, whether there is a possibility of needing pre-hospital blood transfusion, and whether it is necessary to coordinate with the hospital in advance to conduct blood preparation assessment, trauma team preparation, or green channel preparation.

[0095] The purpose of this step is to further transform the "assessment results" obtained in the previous step into procedural judgment results with practical emergency rescue significance, rather than simply remaining at the level of a simple score display.

[0096] S5: Generate Pre-hospital Emergency Treatment Recommendations: After completing risk stratification and key treatment assessments, the system generates corresponding pre-hospital emergency treatment recommendations. These recommendations may include at least: patient transfer priority recommendations, pre-hospital blood transfusion demand assessment information, and in-hospital advance blood preparation assessment or early warning information; they may also further include key monitoring prompts, dynamic reassessment prompts, pre-hospital active intervention prompts, and other auxiliary decision-making information related to the risk of traumatic blood loss.

[0097] For example, when the system identifies a patient as belonging to the high-risk blood loss stratification, it can prompt emergency personnel to increase the transport priority and simultaneously issue a pre-hospital blood preparation assessment prompt or directly perform pre-hospital blood transfusion; when the system determines that the patient's condition is changing rapidly, it can prompt for repeated measurements and reassessment during transport. Through this step, the pre-hospital injury assessment results are further transformed into actionable and referable procedural recommendations.

[0098] S6: Synchronize pre-hospital information and treatment results to the hospital or emergency response team: After generating treatment suggestions, the system will synchronize the patient's vital signs, injury assessment results, risk stratification results, and treatment suggestions to the receiving hospital, 120 emergency command center, cloud-based linkage platform, or other remote terminals in real time or near real time.

[0099] Synchronized content can be output in the form of structured data, charts, risk tags, early warning prompts, or pre-hospital electronic medical records, so that hospitals can obtain more complete pre-hospital injury information before the patient arrives. This step can reduce the problems of information lag, inconsistent expression, and misunderstanding that exist in traditional manual verbal reporting methods, and to some extent, compensate for the information gaps caused by inconsistent scoring standards between hospitals and 120 emergency centers.

[0100] S7: Trigger in-hospital emergency response procedures Upon receiving pre-hospital synchronous information, the hospital can initiate corresponding in-hospital emergency response procedures in advance based on the patient's injury assessment results, risk level, and treatment recommendations. These response procedures may include emergency room reception preparation, trauma team notification, blood transfusion preparation, advance blood preparation assessment, emergency surgery preparation, activation of green channels, adjustment of reception priorities, and preparation of other relevant resources.

[0101] The innovation of the system provided by this invention lies in: First, the overall technical architecture and process value of the auxiliary decision-making system for pre-hospital trauma emergency care scenarios: The core object of this invention is not a specific scoring formula, judgment model, or independent module, but rather a holistic process-oriented technical solution built around the pre-hospital emergency care scenario. This solution includes multiple functional links such as vital sign and injury information collection, pre-hospital injury assessment, decision support, information synchronization and linkage, and in-hospital response interfaces, forming a complete closed loop through a continuous link of "collection—assessment—decision—synchronization—response." This overall process itself constitutes the important value of this invention, because it solves not simply the problem of "how to score," but the problem of "how to effectively embed pre-hospital injury assessment results into the in-hospital emergency care process." It is precisely because of the establishment of this overall process that the information collected pre-hospital can be further transformed into the basis for initiating processes such as triage, transfer priority, pre-hospital intervention prompts, and in-hospital blood preparation, trauma team, and green channel, thereby demonstrating the systematic technical value of this invention in pre-hospital-in-hospital collaborative treatment.

[0102] Secondly, the linkage mechanism for converting pre-hospital assessment results into in-hospital emergency procedures: Compared to existing technologies that mainly focus on pre-hospital scoring or triage, the more important protection point of this invention lies in: further transforming the vital signs information, injury assessment results, and risk stratification results collected pre-hospital into triage and diversion suggestions, transfer priority suggestions, pre-hospital intervention prompts, and in-hospital resource early warning information in a structured manner, and simultaneously transmitting this information to the receiving hospital or emergency command center, enabling the hospital to complete tasks such as blood preparation, trauma team notification, emergency surgery preparation, and green channel activation before the patient arrives. In other words, this invention focuses on protecting a standardized connection mechanism between pre-hospital assessment results and in-hospital emergency procedures.

[0103] Third, the technical value of the closed-loop process of "collection-assessment-decision-synchronization-response" and its inherent sequence: This invention does not merely protect a single isolated step, but rather the combined relationships, execution order, and collaborative logic between these steps. The technical solution described in this invention requires pre-hospital emergency information processing to proceed sequentially in the order of "collection-assessment-decision-synchronization-response": First, patient vital signs and injury information are collected; second, injury quantification and risk assessment are completed; third, based on the assessment results, decision-making suggestions such as triage, transfer priority, and pre-hospital intervention are generated; subsequently, the relevant results are synchronized to the hospital or emergency command center; and finally, response processes such as in-hospital blood preparation, trauma teams, and green channels are triggered. This sequence is not arbitrary but a key condition for effectively extending pre-hospital assessment results to in-hospital emergency procedures; therefore, this process sequence itself constitutes an important protected content of this invention. This closed-loop process design distinguishes this invention from traditional technical solutions that only provide scoring results, and also from existing solutions that only complete data uploads without subsequent linkage.

[0104] Fourth, the selection scheme of vital signs and injury information incorporated into the pre-hospital emergency injury assessment system: The present invention also aims to protect the selection scheme of vital sign parameters and related injury information in the pre-hospital emergency injury assessment system. The said information is not randomly selected, but is screened in view of the rapid availability in the pre-hospital scenario, the ability to characterize the severity of the injury and the risk of blood loss, and the support for subsequent triage, transport priority determination and in-hospital linkage warning. Therefore, what the present invention aims to protect is not only the processing flow for assessment and linkage based on the above information, but also the types of vital signs and injury information incorporated into the system as basic inputs, as well as their combination and application methods.

[0105] Fifth, the implementation method of the revised PHI score as one of the system assessment links: In the present invention, the revised PHI score is not the only core that is separately applied for protection, but is used as an implementation method in the pre-hospital injury assessment module to improve the ability of the pre-hospital injury determination result to characterize the actual severity of the patient's injury and enhance the consistency with the in-hospital injury evaluation criteria. In other words, what the present invention aims to protect is to introduce an optimized injury quantification method in the pre-hospital emergency injury assessment system to improve the accuracy of subsequent stratification, decision-making and linkage, rather than only protecting a certain weighted formula itself.

[0106] Sixth, various system implementation forms and information technology implementation methods: The present invention is not limited to a certain device carrier or a certain software form, but can be integrated into vehicle-mounted emergency terminals, emergency mobile APPs, tablet devices, pre-hospital electronic medical record systems, emergency information platforms, and remote linkage platforms docked with hospital information systems, emergency systems or 120 dispatching systems for implementation. Therefore, what the present invention aims to protect is not only the theoretical process, but also the specific implementation methods of this process in different hardware devices, software platforms and information interaction systems.

[0107] The advantages of the present invention are as follows: 1. The systematization and full-process of pre-hospital emergency injury assessment are realized: The prior art mostly stays at a single scoring tool or a single information transmission link, and it is difficult to form a complete closed loop from vital sign collection, injury assessment, risk stratification, decision support to in-hospital linkage response. The present invention constructs a full-process technical link of "collection - assessment - decision - synchronization - response" around the pre-hospital emergency scenario, enabling the pre-hospital assessment result to further serve subsequent disposal and in-hospital preparation, and enhancing the systematicness and integrity of the pre-hospital emergency process.

[0108] 2. Effective integration of pre-hospital assessment results with in-hospital emergency procedures: Existing pre-hospital scoring technologies typically only complete rapid triage at the hospital entrance, making it difficult to directly integrate into in-hospital processes such as blood preparation, trauma team activation, and green channel preparation. This invention, through information synchronization and linkage mechanisms, transmits vital signs, injury assessment results, and decision-making suggestions collected pre-hospital to the hospital in real-time or near real-time. This allows the hospital to prepare resources and initiate procedures before the patient arrives, thereby facilitating the achievement of the goal of "information arriving before the patient, and procedures starting before the patient's arrival"—a proactive approach to treatment.

[0109] 3. Improved the ability of pre-hospital injury assessment to support actual clinical decision-making: Traditional pre-hospital scoring tools primarily provide coarse-level stratification information on "whether the condition is critical," offering limited support for critical decisions such as transport priority, pre-hospital blood transfusion requirements, and in-hospital resource early warning. This invention further transforms injury assessment results into specific information such as triage and patient referral suggestions, transport priority recommendations, key monitoring alerts, auxiliary assessment of pre-hospital blood transfusion needs, and in-hospital advance blood preparation warnings. This allows pre-hospital assessment results to move beyond simple scoring and more directly serve emergency treatment decisions.

[0110] 4. While maintaining the simplicity of pre-hospital care, it improves the objectivity and consistency of injury quantification: This invention, without altering the rapid data collection and ease of application characteristics of pre-hospital care, incorporates a modified PHI score as part of the injury assessment process. By optimizing traditional scoring methods, it improves the ability of pre-hospital assessment results to accurately represent the actual severity of the patient's injury. Compared to the traditional PHI score, the modified PHI score exhibits a better correlation with in-hospital injury severity assessment indicators, thus enhancing the consistency between pre-hospital assessment results and in-hospital injury assessment standards.

[0111] 5. Improved the standardization and usability of pre-hospital information transmission: Current information exchange between pre-hospital and in-hospital settings relies heavily on verbal reporting, which can lead to information delays, inconsistent expression, and misunderstandings. Furthermore, differences in injury scoring standards and procedural response rules between different hospitals and 120 emergency centers often hinder the timely conversion of pre-hospital assessment results into in-hospital preparation. This invention establishes a relatively unified mechanism for outputting pre-hospital injury assessment and risk stratification results through structured information collection, assessment output, and synchronous transmission. This allows pre-hospital information to enter in-hospital processes in a standardized format, thereby addressing the information gaps caused by inconsistencies in pre-hospital and in-hospital scoring standards and improving the efficiency, accuracy, and synergy of pre-hospital and in-hospital information exchange.

[0112] To verify the application value of this system in actual pre-hospital emergency scenarios, this study randomly selected 50 real cases and evaluated them using both the original PHI scoring system and the original PHI scoring system, generating corresponding clinical decision-making suggestions. Subsequently, the head of emergency surgery / trauma surgery at a renowned hospital was invited to review and evaluate the decision-making suggestions output by the two systems on a case-by-case basis. As shown in Table 4, the results show that the original PHI stratification method is relatively simple, only forming two levels of risk classification, and its clinical decision-making suggestions are rather coarse, with a direct usability rate of only 52.3% in real clinical scenarios. In contrast, this system further constructs a dual-scoring and stratified decision-making system of T-PHI and B-PHI based on the original vital signs score, which can simultaneously output more targeted and operable transport and transfusion suggestions. After expert review, the direct usability rate of its clinical decision-making suggestions reached 95.2%. Meanwhile, the discrimination performance of this system is also superior to the original PHI, with specificity increasing from 0.611 to 0.947, an increase of approximately 54.9%, and sensitivity increasing from 0.785 to 0.972, an increase of approximately 23.8%. This indicates that the system can not only more accurately identify high-risk patients, but also more effectively distinguish non-high-risk patients. In summary, this system has better applicability, operability, and clinical application value than the original PHI in pre-hospital emergency decision support.

[0113] Table 4 Evaluation Results The following are some case verifications: Case 1: Original PHI score: 4, clinical recommendation: classified as serious injury.

[0114] Pre-hospital emergency intelligent system: B-PHI: 4.48, T-PHI: 2.12, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0115] Transfer priority assessment: Low risk. The system recommends continued routine monitoring and transfer to the nearest available location.

[0116] Expert assessment: Compared to the original version, the pre-hospital emergency intelligent system effectively saves medical transport resources, and the original version cannot be used directly.

[0117] Case 2: Original PHI score: 5, clinical recommendation: classified as serious injury.

[0118] Pre-hospital emergency intelligent system: B-PHI: 0.8, T-PHI: 7.6, clinical recommendations.

[0119] Transfusion assessment: Low risk, continue routine monitoring, do not activate pre-hospital transfusion early warning; Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0120] Expert assessment: Compared to the original version, the pre-hospital emergency intelligent system effectively saves blood bank transfusion resources, and the original version cannot be used directly.

[0121] Case 3: Original PHI score: 1, clinical recommendation: classified as minor injury.

[0122] Pre-hospital emergency intelligent system: B-PHI: 2.56, T-PHI: 0.38, Clinical recommendations: Transfusion assessment: Low risk, continue routine monitoring, do not activate pre-hospital transfusion early warning.

[0123] Transfer priority assessment: Low risk. The system recommends continued routine monitoring and transfer to the nearest available location.

[0124] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0125] Case 4: Original PHI score: 8, clinical recommendation: classified as serious injury.

[0126] Pre-hospital emergency intelligent system: B-PHI: 8.48, T-PHI: 6.12, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0127] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0128] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0129] Case 5: Original PHI score: 5, clinical recommendation: classified as serious injury.

[0130] Pre-hospital emergency intelligent system: B-PHI: 3.2, T-PHI: 2.9, Clinical recommendations: Transfusion assessment: Low risk, continue routine monitoring, do not activate pre-hospital transfusion early warning.

[0131] Transfer priority assessment: Low risk. The system recommends continued routine monitoring and transfer to the nearest available location.

[0132] Expert assessment: Compared to the original version, the pre-hospital emergency intelligent system effectively saves medical transport resources and blood bank transfusion resources, which the original version cannot be used directly.

[0133] Case 6: Original PHI score: 3, clinical recommendation: classified as minor injury.

[0134] Pre-hospital emergency intelligent system: B-PHI: 1.92, T-PHI: 1.74, Clinical recommendations: Transfusion assessment: Low risk, continue routine monitoring, do not activate pre-hospital transfusion early warning.

[0135] Transfer priority assessment: Low risk. The system recommends continued routine monitoring and transfer to the nearest available location.

[0136] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0137] Case 7: Original PHI score: 7, clinical recommendation: classified as serious injury.

[0138] Pre-hospital emergency intelligent system: B-PHI: 5.92, T-PHI: 8.56, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0139] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0140] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0141] Case 8: Original PHI score: 10, clinical recommendation: classified as serious injury.

[0142] Pre-hospital emergency intelligent system: B-PHI: 7.84, T-PHI: 12.92, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0143] Transfer priority assessment: High risk. The system recommends prioritizing transfer to the nearest tertiary-level hospital or trauma center to match higher-level medical resources.

[0144] Expert assessment: Compared to the original version, the pre-hospital intelligent emergency medical system effectively improves the priority of patient transfer and allocates higher-level medical resources to critically ill patients. The original version cannot be used directly.

[0145] Case 9: Original PHI score: 15, clinical recommendation: classified as serious injury.

[0146] Pre-hospital emergency intelligent system: B-PHI: 11.84, T-PHI: 14.1, Clinical recommendations: Blood transfusion assessment: High risk. The system will further enhance monitoring and early warning, and recommend initiating blood transfusion in the ambulance to bring forward the timing of the transfusion.

[0147] Transfer priority assessment: High risk. The system recommends prioritizing transfer to the nearest tertiary-level hospital or trauma center to match higher-level medical resources.

[0148] Expert assessment: Compared to the original version, the pre-hospital intelligent emergency medical system effectively improves the priority of patient transfer and ensures immediate blood transfusion upon boarding, allocating higher-level medical resources to critically ill patients. The original version cannot be used directly.

[0149] Case 10: Original PHI score: 8, clinical recommendation: classified as serious injury.

[0150] Pre-hospital intelligent emergency medical system: B-PHI: 2.72, T-PHI: 9.34, Clinical recommendations: Transfusion assessment: Low risk. The system recommends continued routine monitoring and does not activate pre-hospital transfusion early warning.

[0151] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0152] Expert assessment: Compared to the original version, the pre-hospital emergency intelligent system effectively saves medical transport resources, and the original version cannot be used directly.

[0153] Case 11: Original PHI score: 6, clinical recommendation: classified as serious injury.

[0154] Pre-hospital intelligent emergency medical system: B-PHI: 3.84, T-PHI: 6.3, Clinical recommendations: Transfusion assessment: Low risk. The system recommends continued routine monitoring and does not activate pre-hospital transfusion early warning.

[0155] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0156] Expert assessment: Compared to the original version, the pre-hospital emergency intelligent system misjudged the patient's blood transfusion strategy, rendering the pre-hospital emergency intelligent system unusable.

[0157] Case 12: Original PHI score: 7, clinical recommendation: classified as serious injury.

[0158] Pre-hospital intelligent emergency medical system: B-PHI: 6.4, T-PHI: 6.68, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0159] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0160] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0161] Case 13: Original PHI score: 4, clinical recommendation: classified as serious injury.

[0162] Pre-hospital intelligent emergency medical system: B-PHI: 4.48, T-PHI: 4.94, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0163] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0164] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0165] Case 14: Original PHI score: 10, clinical recommendation: classified as serious injury.

[0166] Pre-hospital intelligent emergency medical system: B-PHI: 9.76, T-PHI: 7.28, Clinical recommendations: Blood transfusion assessment: High risk. The system will further enhance monitoring and early warning, and recommend initiating blood transfusion in the ambulance to bring forward the timing of the transfusion.

[0167] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0168] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0169] Case 15: Original PHI score: 15, clinical recommendation: classified as serious injury.

[0170] Pre-hospital intelligent emergency medical system: B-PHI: 9.6, T-PHI: 16.02, Clinical recommendations: Blood transfusion assessment: High risk. The system will further enhance monitoring and early warning, and recommend initiating blood transfusion in the ambulance to bring forward the timing of the transfusion.

[0171] Transfer priority assessment: High risk. The system recommends prioritizing transfer to the nearest tertiary-level hospital or trauma center to match higher-level medical resources.

[0172] Expert assessment: Compared to the original version, the pre-hospital intelligent emergency medical system effectively improves the priority of patient transfer and ensures immediate blood transfusion upon boarding, allocating higher-level medical resources to critically ill patients. The original version cannot be used directly.

[0173] Case 16: Original PHI score: 4, clinical recommendation is to classify it as serious injury.

[0174] Pre-hospital intelligent emergency medical system: B-PHI: 4, T-PHI: 4, Clinical recommendations: Blood transfusion assessment: medium risk. The system recommends continuous monitoring and notifies the hospital to prepare blood in advance.

[0175] Transfer priority assessment: medium risk, the system recommends prioritizing transfer to the nearest tertiary hospital.

[0176] Expert assessment: Both the original version and the pre-hospital emergency intelligent system can be used directly, but the decision-making suggestions of the pre-hospital emergency intelligent system are more detailed.

[0177] When using the decision support system for pre-hospital trauma emergency care provided in this manual, the specific execution order of each step can be determined as needed, and this manual does not impose any restrictions on this.

[0178] The modules in the aforementioned decision support system for pre-hospital trauma emergency care can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, allowing the processor to invoke and execute the corresponding operations of each module.

[0179] This specification also provides an auxiliary decision-making terminal for pre-hospital trauma emergency scenarios. The terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the aforementioned... Figure 1 The system provides auxiliary decision-making functions for pre-hospital trauma emergency care scenarios.

[0180] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The system provides auxiliary decision-making functions for pre-hospital trauma emergency care scenarios.

[0181] This instruction manual also provides Figure 3 The schematic diagram of the computer device shown is as follows: Figure 3 As shown, at the hardware level, this computer device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it to achieve the above. Figure 1 The system provides auxiliary decision-making functions for pre-hospital trauma emergency care scenarios.

[0182] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the acquisition, storage, use and processing of user information comply with the relevant provisions of national laws and regulations.

[0183] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0184] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A decision support system for pre-hospital trauma emergency care, characterized in that, The system includes a vital signs and injury information collection module, a pre-screening module, a pre-hospital injury assessment module, and a decision support module; The vital signs information collection module is used to collect basic vital signs and injury information of trauma patients in pre-hospital trauma emergency scenarios. The injury information includes bleeding site, bleeding degree, injury mechanism, limb injury status, and other on-site information that can reflect the patient's current injury status. The pre-screening module is used to determine whether the trauma patient is in a critical condition based on the injury information. If the trauma patient is in a critical condition, the trauma patient is determined to be the highest priority for transfer, and preparations for ambulance blood transfusion are initiated. The pre-hospital injury assessment module is used to determine the transport priority score based on basic vital sign information and the corresponding weight of the first basic vital sign parameter when the trauma patient is not in a critical condition, and to determine the bleeding risk score based on basic vital sign information and the corresponding weight of the second basic vital sign parameter. The weights of the first basic vital signs parameter and the weights of the second basic vital signs parameter are different; The weights of the first and second basic vital signs parameters were obtained after multiple rounds of optimization based on multiple evaluation indicators. The decision support module is used to determine transport decision recommendations based on transport priority scores and to determine transfusion decision recommendations based on bleeding risk scores.

2. The system according to claim 1, characterized in that, The methods for collecting basic vital signs and injury information by the vital signs information collection module include manual entry by emergency personnel, automatic collection by vehicle-mounted monitoring equipment, or collection by mobile terminals, tablet devices, and pre-hospital electronic medical record systems.

3. The system according to claim 1, characterized in that, Critical conditions include significant active hemorrhage or projectile bleeding, continued bleeding after hemostasis measures have been taken, complete loss of consciousness of the patient, penetrating thoracic or abdominal injuries, and abnormal postures suggesting severe pelvic injury.

4. The system according to claim 1, characterized in that, Basic vital signs information includes the values ​​of four parameters: systolic blood pressure, heart rate, respiratory rate, and patient consciousness status; the weights of basic vital signs parameters include the weight of each parameter in the basic vital signs information. Based on basic vital sign information and the corresponding weights of the first basic vital sign parameters, the implementation method for determining the transfer priority scoring is as follows: Score the systolic blood pressure, heart rate, respiratory rate, and patient level of consciousness to determine the score of each parameter in the baseline vital signs information; Based on the weight of each parameter in the basic vital signs information, the score of each item is weighted to obtain the transfer priority score.

5. The system according to claim 4, characterized in that, Multiple evaluation metrics include the area under the receiver operating characteristic (ROC) curve, the optimal threshold of the ROC curve, sensitivity, specificity, and the critical value of the raw score; the system also includes a weight optimization module. The weight optimization module is used to fine-tune the initial weight of each parameter multiple times, calculate the evaluation index value after each fine-tuning, comprehensively evaluate the values ​​of multiple evaluation indicators, and determine the weight corresponding to the optimal comprehensive evaluation as the weight of the basic vital sign parameter used in calculating the score.

6. The system according to claim 1, characterized in that, Based on the transshipment priority score, the implementation method for transshipment decision recommendations is determined as follows: When the transfer priority score is less than or equal to the preset first transfer threshold, the transfer decision recommendation is to recommend the nearest transfer. When the transfer priority score is greater than the first transfer threshold and less than the preset second transfer threshold, the transfer decision recommendation is to prioritize the transfer to the nearest tertiary hospital. When the transfer priority score is greater than or equal to the second transfer threshold, the transfer decision recommendation is to prioritize the transfer to the nearest tertiary-level hospital or trauma center to match higher-level medical resources.

7. The system according to claim 1, characterized in that, Based on the bleeding risk score, the implementation method for blood transfusion decision recommendations is determined as follows: When the bleeding risk score is less than or equal to the preset first transfusion threshold, the transfusion decision recommendation is to recommend continuous routine monitoring, and the pre-hospital transfusion early warning is not activated. When the bleeding risk score is greater than the first transfusion threshold but less than the preset second transfusion threshold, the transfusion decision recommendation is to recommend continuous monitoring, and the hospital is notified to prepare blood in advance. When the bleeding risk score is greater than or equal to the second transfusion threshold, the recommended transfusion decision is to initiate the transfusion in the ambulance, thus advancing the timing of the transfusion.

8. The system according to claim 1, characterized in that, The system also includes an information synchronization and linkage module and an in-hospital response interface module; The information synchronization and linkage module is used to transmit the basic vital signs information, injury information, critical status, transfer priority score, bleeding risk score, and transfer decision and transfusion decision suggestions of trauma patients to the receiving hospital, 120 emergency command center or other remote linkage terminals. The in-hospital response interface module is used to issue warnings, reminders, or resource preparation instructions to relevant departments within the hospital based on the basic vital signs information, injury information, critical status, transfer priority score, bleeding risk score, and transfer and transfusion decision suggestions transmitted by the information synchronization and linkage module.

9. The system according to claim 1, characterized in that, The system also includes a terminal doctor review module; The terminal physician review module is used to continue to monitor the vital signs of trauma patients after the physician has performed operations on the trauma patient based on the transfer decision and blood transfusion decision recommendations, and to feed the monitoring results back to the hospital in real time.

10. An auxiliary decision-making terminal for pre-hospital trauma emergency care, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the functions of the system described in any one of claims 1 to 9.

Images