An intelligent triage system for emergency departments

Abstract

This invention relates to the field of medical technology, specifically disclosing an intelligent triage system for emergency departments, comprising a user terminal, a cloud terminal, and a medical staff terminal: the user terminal receives patient condition information uploaded by accompanying persons; the condition information includes a voice description of the condition and a video of the condition; the cloud terminal acquires the condition information, performs pre-triage of the patient based on the voice description of the condition, and generates a pre-triage result; the triage result includes Level I, Level II, and Level III; if the level is Level I, the cloud terminal also acquires the video of the condition, identifies the patient's status based on the video, determines whether the patient's status meets Level I, and if so, determines the patient's distance from the hospital based on the corresponding location information; if the distance is less than a preset distance value, a summary of the condition and the pre-triage result are sent to the medical staff terminal. The technical solution of this invention can effectively improve the response speed and efficiency of emergency medical care.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and in particular to an intelligent triage system for emergency care. Background Technology

[0002] Triage and triage refer to the rapid assessment of emergency patients and their prioritization based on the severity of their condition. As the first line of defense in emergency care, triage uses scientific methods to classify patients, quickly identifying those in critical, urgent, and severe condition. This helps to fully utilize emergency resources, maintain order in the emergency patient flow, and ensure patient safety. Effective triage not only identifies truly critical patients and reduces the incidence of adverse events during the waiting process, but also helps to rationally allocate limited emergency medical resources, improving the quality and efficiency of emergency care.

[0003] Currently, hospital emergency departments generally need to wait for patients to arrive at the hospital before medical staff conduct an initial assessment of their condition and triage them. This process takes time and may delay the patient's chances of receiving timely treatment.

[0004] Therefore, there is an urgent need for an emergency intelligent triage system that can pre-identify and triage patients before they arrive at the hospital, so as to intervene in the patient's treatment process earlier and improve the response speed and efficiency of emergency medical care. Summary of the Invention

[0005] This invention provides an intelligent triage system for emergency departments, which can effectively improve the response speed and efficiency of emergency medical care.

[0006] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0007] An intelligent triage system for emergency departments includes a user terminal, a cloud terminal, and a medical staff terminal:

[0008] The client is used to receive patient condition information and transportation information uploaded by accompanying persons, and also to obtain location information in real time and send the condition information and transportation location information to the cloud; the condition information includes voice descriptions of the condition and video of the condition.

[0009] The cloud is used to obtain medical information, perform pre-triage of patients based on their voice descriptions of their symptoms, and generate pre-triage results; the triage results include Level I, Level II, and Level III.

[0010] If the classification is Level I, the cloud is also used to obtain video of the patient's condition, identify the patient's status based on the video, and determine whether the patient's status meets Level I. If it does, the distance between the patient and the hospital is determined based on the corresponding location information. If the distance is less than the preset distance value, the summary of the condition and the pre-triage results are sent to the medical staff.

[0011] If the classification is Level II, it is also used to determine whether the patient has arrived at the hospital based on the corresponding location information. If the patient has arrived at the hospital, a summary of the condition and the pre-triage results are sent to the medical staff.

[0012] If the classification is Level III, it is also used to obtain the pre-stored emergency procedure description and send the emergency procedure description and pre-triage results to the user terminal.

[0013] Furthermore, the cloud platform is also used to receive treatment measures from medical staff when the classification is Level I, and then send the treatment measures to the user terminal.

[0014] Furthermore, the cloud platform is also used to determine whether the user terminal receives the uploaded medical information a second time when the classification is Level III. If the second uploaded medical information is obtained, the patient is pre-triaged again based on the first and second uploaded medical information. If the result is greater than Level III, the classification is Level II; otherwise, Level III is maintained.

[0015] Furthermore, the cloud-based system is also used to, when maintaining Level III, recognize the emotions of the accompanying person based on the voice description of the illness, determine whether the accompanying person's emotions are angry, and if so, activate the soothing mode.

[0016] It also includes the security terminal; the cloud is also used to send location information, transportation information and pre-triage results to the security terminal in the reassurance mode.

[0017] Furthermore, in the reassurance mode, the cloud also estimates the arrival time of patients at the hospital based on the location and transportation information of patients classified as Level III, and uses this as the receiving time; it determines whether other patients classified as Level I have arrived at the hospital or are receiving treatment at the receiving time. If so, it obtains the video clip of the corresponding Level I patient, blurs the patient's face and bloodstains in the video clip, and sends the blurred video clip to the security terminal.

[0018] Furthermore, the security terminal is also used to receive reception feedback information, determine whether the reception is completed based on the reception feedback information, and delete the video clip if the reception is completed.

[0019] Furthermore, the medical staff terminal is also used to obtain the actual triage results and upload them to the cloud. The cloud is also used to determine whether the actual triage results are consistent with the pre-triage results. If they are inconsistent, the corresponding medical information is marked and review items are generated.

[0020] Furthermore, the medical staff terminal is also used to obtain the current patient reception status, determine the level of busyness based on the patient reception status, and dynamically adjust the preset distance value according to the level of busyness.

[0021] This solution, through real-time uploading and cloud processing of patient information, can accurately classify a patient's condition before they arrive at the hospital, providing the hospital's emergency department with more time to prepare medical resources. This greatly improves the speed of emergency response and the efficiency of rescue, especially shortening the treatment time for critically ill patients, thereby reducing the risks to patients during the rescue process. Attached Figure Description

[0022] Figure 1 This is a logic block diagram of an embodiment of an emergency intelligent triage system. Detailed Implementation

[0023] The following detailed description illustrates the specific implementation method:

[0024] Example 1

[0025] like Figure 1 As shown in this embodiment, an emergency intelligent triage system includes a user terminal, a cloud terminal, a medical staff terminal, and a security terminal. In this embodiment, the user terminal is used by the patient's companion or the patient, the cloud terminal is a server, the medical staff terminal is used by medical staff, and the security terminal is used by security personnel. The user terminal and the security terminal use applications running on smartphones, while the medical staff terminal uses applications running on smartphones or computers.

[0026] The client is used to receive patient condition information and transportation information uploaded by accompanying persons, and also to obtain location information in real time and send the condition information and transportation location information to the cloud; the condition information includes voice descriptions of the condition and video of the condition.

[0027] The cloud is used to obtain medical information, perform pre-triage of patients based on the voice description of the medical condition, and generate pre-triage results. Specifically, the cloud converts the voice description of the medical condition into text information, extracts the content of the text information through a pre-built AI model to obtain a summary of the medical condition, and classifies the patient's condition according to the summary of the medical condition and the pre-built grading standards. The grading includes Level I, Level II, and Level III.

[0028] In this embodiment, the medical condition summary includes keywords such as cardiac / respiratory arrest, airway obstruction / asphyxia, shock, acute massive hemorrhage, sudden loss of consciousness, persistent convulsions, chest pain / chest tightness (suspected acute myocardial infarction / suspected aortic dissection / suspected pulmonary embolism / suspected tension pneumothorax), acute poisoning, severe burns, signs of brain herniation, and severe abdominal pain in pregnant women, and is classified as Level I, requiring immediate treatment upon arrival at the hospital.

[0029] It includes keywords such as active chest pain, abdominal pain, poisoning (but not meeting the criteria for Level 1), sudden changes in consciousness (drowsiness, disorientation, syncope), diabetic ketoacidosis, mental disorders (with self-harm or harming tendencies), vaginal bleeding, ectopic pregnancy, etc., and is classified as Level II. It is recommended to treat it within 10 minutes of arriving at the hospital.

[0030] In other cases, it is divided into Grade III, and it is recommended to be disposed of within 30 to 120 minutes.

[0031] If the grading is Grade I, it is used to obtain the disease condition video, identify the patient's status based on the disease condition video, determine whether the patient's status meets Grade I. If it meets, judge the distance between the patient and the hospital according to the corresponding location information. When the distance is less than the preset value, send the disease summary and pre-triage result to the medical staff terminal.

[0032] In this embodiment, the disease condition video is analyzed by an image recognition model, and the video segment containing the patient's body and face is cropped. Whether the patient is conscious is analyzed based on the image frames of the patient's face in the video segment. If not, it is judged to meet Grade I.

[0033] Optionally, it is also used to receive the treatment measures of medical staff from the medical staff terminal and send the treatment measures to the user terminal.

[0034] If the grading is Grade II, it is used to judge whether the patient has arrived at the hospital according to the corresponding location information. If the patient has arrived at the hospital, send the disease summary and pre-triage result to the medical staff terminal.

[0035] If the grading is Grade III, it is used to obtain the pre-stored emergency process description, and send the emergency process description and pre-triage result to the user terminal; it is also used to judge whether the user terminal receives the uploaded disease information again. If the second uploaded disease information is obtained, the patient is pre-triaged again according to the first and second uploaded disease information. If the result is higher than Grade III, it is graded as Grade II, otherwise it remains Grade III. If it remains Grade III, the emotion of the accompanying person is recognized by voice according to the disease description, and it is judged whether the emotion of the accompanying person is angry. If it is angry, the soothing mode is enabled; in this embodiment, the training data collection and calibration including the starting emotion are carried out in advance, and then the emotion recognition model is trained through the training set to accurately recognize the corresponding emotion. The emotion recognition model outputs the probability values of different emotions, and the emotion with the probability value is used as the current emotion.

[0036] The cloud is also used to send the location information, vehicle information and pre-triage result to the security terminal in the soothing mode. The vehicle information includes the vehicle type and license plate number, such as a car-hailing service, Yu A XXXXX. In the case that the emotion of the patient's accompanying person is angry, the location information is sent to the security terminal in advance. When the corresponding patient arrives at the hospital, the security personnel can guide the patient to see a doctor and explain the relevant grading rules to soothe the emotion of the accompanying person and ensure the normal order of the hospital.

[0037] This embodiment of the intelligent emergency triage system enables rapid pre-triage of emergency patients through the collaborative work of the user terminal, cloud, and medical staff, thereby improving the efficiency of emergency medical response. The user terminal can receive patient information and transportation information uploaded by accompanying persons, and obtain the patient's location information in real time, sending it to the cloud. The cloud uses an AI model to analyze the patient information, generate a patient summary, and pre-triage the patient's condition according to a grading standard, classifying them into Level I, Level II, and Level III, thus identifying critically ill patients in advance and optimizing the allocation of emergency resources.

[0038] For Level I patients, the system further identifies their condition through video monitoring. If they meet the Level I criteria, the system monitors their location and distance from the hospital in real time. When the distance is sufficiently close, a summary of the patient's condition and the pre-triage result are immediately sent to the medical staff to ensure rapid treatment. For Level II patients, the system determines whether they have arrived at the hospital based on location data. If so, the system also transmits a summary of the patient's condition and the pre-triage result to the medical staff to ensure timely treatment. For Level III patients, the system provides emergency procedure instructions to guide accompanying persons and re-triages based on supplementary information from the accompanying persons to improve triage accuracy. Furthermore, if the accompanying person is emotionally agitated, the system activates a calming mode, sending patient information, including location and transportation information, to security personnel to ensure timely guidance of the patient and calming of the accompanying person. Through this intelligent triage and calming mechanism, the system not only improves the efficiency of emergency medical care but also effectively maintains hospital order, providing more humane services to patients and their accompanying persons.

[0039] Example 2

[0040] The difference between this embodiment and embodiment one is that, in the reassurance mode, the cloud also uses the location information and transportation information of patients classified as level III to estimate the time when the patient arrives at the hospital as the receiving time, and determines whether other patients classified as level I have arrived at the hospital or are receiving treatment at the receiving time. If so, the cloud obtains the video clip of the corresponding level I patient, and blurs the patient's face and the parts containing bloodstains in the video clip, and sends the blurred video clip to the security terminal.

[0041] The security terminal is also used to receive reception feedback information, determine whether the reception is completed based on the feedback information, and delete the video clips if the reception is completed.

[0042] This embodiment further optimizes the functionality of the reassurance mode. The cloud sends processed video clips to the security system, allowing security personnel to visually demonstrate to accompanying persons that the hospital is urgently treating other critically ill patients, thus demonstrating the rationality of the triage assessment and effectively calming the emotions of accompanying persons, preventing emotional escalation from impacting hospital order. Furthermore, patient privacy is protected by blurring the video clips, preventing the leakage of sensitive information. The video clips are only used temporarily during the reception process and are deleted immediately afterward, ensuring the security of patient privacy.

[0043] Example 3

[0044] The difference between this embodiment and Embodiment 1 is that in this embodiment, the medical staff terminal is also used to obtain the actual triage results and upload the actual triage results to the cloud. The cloud is also used to determine whether the actual triage results are consistent with the pre-triage results. If they are inconsistent, the corresponding medical information is marked and review items are generated.

[0045] By generating review items, maintenance personnel can analyze the specific reasons for inconsistencies. For example, the accompanying person might lack key information when describing the symptoms, leading to a lower pre-triage result; or the system's AI model might have errors in text or video analysis. This targeted feedback mechanism helps identify and resolve problems in the system, continuously improving the accuracy and reliability of pre-triage.

[0046] Example 4

[0047] The difference between this embodiment and Embodiment 1 is that in this embodiment, the medical staff also obtains the current patient reception status, determines the level of busyness based on the reception status, and dynamically adjusts the preset distance value according to the level of busyness. The higher the level of busyness, the lower the preset distance value. Specifically, in this embodiment, based on the number of all patients awaiting treatment in the emergency department, the level of busyness is divided into high (more than 5 people), medium (2-3 people), and low (1 person or less), with corresponding preset distance values ​​of near (500m), medium (1km), and far (2km).

[0048] When medical staff are not busy, send out a summary of the patient's condition and pre-triage results as early as possible to facilitate their preparation.

[0049] When medical staff are busy, the system shortens the preset distance threshold, only pushing relevant information to nearby Level I patients to avoid information overload and improve the response efficiency of medical staff. Conversely, when medical staff are less busy, the system appropriately extends the preset distance threshold, pushing patient information earlier to allow medical staff to prepare treatment plans in advance. This not only alleviates the pressure on medical staff during peak periods but also provides patients with more timely treatment preparation, improving the resource utilization efficiency and quality of medical services in the emergency department.

[0050] Example 5

[0051] The difference between this embodiment and embodiment two is that in this embodiment, the security terminal is also used to record reception videos and upload the reception videos to the cloud.

[0052] The cloud is used to identify the emotions of the person being received (accompanying person or patient) from the uploaded reception videos and obtain the probability value of anger;

[0053] The cloud platform is also used to assess the emotions of companions to patients who have not yet arrived at the hospital, obtaining a probability value of anger from the companions.

[0054] The cloud-based system is also used to determine if the number of patients who have not yet arrived at the hospital exceeds a threshold. If it does, it filters out accompanying persons with a lower probability of anger than the person being treated and marks them as individuals requiring reassurance. It also blurs faces and bloodstains in the treatment video, adds preset reminder text, the anger probability of the person being treated, and the anger probability of the individuals requiring reassurance to the video frame, and sends the processed video to the user terminal corresponding to the individual requiring reassurance. In this embodiment, the reminder text includes: "The hospital strictly follows regulations for receiving patients; please queue in an orderly manner to improve treatment efficiency," etc.

[0055] Emergency rooms often face a shortage of medical staff due to an overwhelming number of patients. Similarly, security personnel also face a shortage of staff, making it impossible to calm down every angry accompanying person.

[0056] In this embodiment, security personnel record video of the reception process with patients and their companions using their security devices. This video is archived and, when the number of patients waiting to be treated exceeds a certain threshold, the video is processed and sent to the user's device for viewing. This two-way information sharing helps eliminate misunderstandings and improves transparency. The person seeking reassurance can hear the security personnel's explanation of the hospital's tiered treatment rules and see that even those with a higher probability of anger still need to queue for treatment according to regulations. This helps them understand that arguing will not speed up the process, and that cooperation with security / medical staff is essential for receiving treatment quickly. In summary, this solution effectively explains the rules and provides reassurance when manpower is insufficient.

[0057] The above are merely embodiments of the present invention. The invention is not limited to the fields covered by these embodiments. Commonly known structures and characteristics in the solutions are not described in detail here. Those skilled in the art are aware of all common technical knowledge in the field prior to the application date or priority date, are able to access all existing technologies in that field, and have the ability to apply conventional experimental methods prior to that date. Those skilled in the art can, based on the guidance provided in this application, improve and implement this solution in combination with their own capabilities. Some typical known structures or methods should not be obstacles for those skilled in the art to implement this application. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention. These should also be considered within the scope of protection of the present invention, and will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. An emergency intelligent triage system, characterized in that, Including the user end, cloud end, and healthcare end: The client is used to receive patient condition information and transportation information uploaded by accompanying persons, and also to obtain location information in real time and send the condition information and transportation location information to the cloud; the condition information includes voice descriptions of the condition and video of the condition. The cloud is used to obtain medical information, perform pre-triage of patients based on their voice descriptions of their symptoms, and generate pre-triage results; the triage results include Level I, Level II, and Level III. If the classification is Level I, the cloud is also used to obtain video of the patient's condition, identify the patient's status based on the video, and determine whether the patient's status meets Level I. If it does, the distance between the patient and the hospital is determined based on the corresponding location information. If the distance is less than the preset distance value, the summary of the condition and the pre-triage results are sent to the medical staff. If the classification is Level II, it is also used to determine whether the patient has arrived at the hospital based on the corresponding location information. If the patient has arrived at the hospital, a summary of the condition and the pre-triage results are sent to the medical staff. If the classification is Level III, it is also used to obtain the pre-stored emergency procedure description and send the emergency procedure description and pre-triage results to the user terminal. The cloud platform is also used to determine whether the user terminal has received the uploaded medical information a second time when the classification is Level III. If the second uploaded medical information is obtained, the patient is pre-triaged again based on the first and second uploaded medical information. If the result is greater than Level III, the classification is Level II; otherwise, Level III is maintained. The cloud-based system is also used to, when maintaining Level III, recognize the emotions of the accompanying person based on the voice description of the illness, determine whether the accompanying person's emotions are angry, and if so, activate the soothing mode. It also includes the security terminal; the cloud is also used to send location information, transportation information and pre-triage results to the security terminal in the reassurance mode; In the aforementioned reassurance mode, the cloud also uses the location and transportation information of patients classified as Level III to estimate the time when the patient arrives at the hospital, which is used as the receiving time; it determines whether other patients classified as Level I have arrived at the hospital or are receiving treatment at the receiving time. If so, it obtains the video clip of the corresponding Level I patient, blurs the patient's face and bloodstains in the video clip, and sends the blurred video clip to the security terminal. The medical staff terminal is also used to obtain the current patient reception status, determine the level of busyness based on the patient reception status, and dynamically adjust the preset distance value according to the level of busyness. The security system is also used to film reception videos and upload them to the cloud. The cloud is used to identify the emotions of the guests from the uploaded reception videos and obtain a probability value of anger; The cloud is also used to assess the emotions of companions to patients who have not yet arrived at the hospital, obtaining a probability value of anger from the companions. The cloud-based system is also used to determine whether the number of patients who have not yet arrived at the hospital exceeds the threshold. If it does, it filters out the accompanying persons whose anger probability is lower than that of the person being received and marks them as people to be comforted. It is also used to blur the faces of people and bloodstains in the reception video. The processed reception video is then sent to the user terminal corresponding to the person to be comforted.

2. The emergency intelligent triage system according to claim 1, characterized in that: The cloud platform is also used to receive treatment measures from medical staff when the classification is Level I, and then send the treatment measures to the user terminal.

3. The emergency intelligent triage system according to claim 2, characterized in that: The security terminal is also used to receive reception feedback information, determine whether the reception is completed based on the reception feedback information, and delete the video clip if the reception is completed.

4. The emergency intelligent triage system according to claim 3, characterized in that: The medical staff terminal is also used to obtain the actual triage results and upload them to the cloud. The cloud is also used to determine whether the actual triage results are consistent with the pre-triage results. If they are inconsistent, the corresponding medical information is marked and review items are generated.

Images