Emergency intelligent triage system

Abstract

The invention relates to the technical field of medical treatment, and particularly discloses an intelligent triage system for emergency treatment, which comprises a user side, a cloud side and a medical care side: the user side is used for receiving patient condition information uploaded by an accompanying person; the illness state information comprises illness state description voice and illness state video; the cloud end is used for acquiring illness state information, performing pre-triage on a patient according to illness state description voice, and generating a pre-triage result; the triage results comprise grade I, grade II and grade III; if the grade is I grade, the cloud terminal is also used for acquiring an illness state video, identifying the state of the patient according to the illness state video, judging whether the state of the patient accords with the I grade, if so, judging the distance between the patient and the hospital according to the corresponding position information, and when the distance is smaller than a distance preset value, sending an illness state summary and a pre-triage result to the medical care terminal. By adopting the technical scheme of the invention, the response speed and efficiency of emergency medical treatment can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to an emergency intelligent triage system. Background Art

[0002] Pre-examination and triage refers to the rapid assessment of emergency patients and the prioritization of their severity. As the first checkpoint for emergency patients, triage uses scientific methods to classify patients and quickly identify emergency, critical, and serious patients, which helps to make full use of emergency resources, maintain the order of emergency patients, and ensure the safety of emergency patients. Effective triage can not only identify truly critical patients and reduce the incidence of adverse events in patients while waiting for treatment, but also help to reasonably arrange limited emergency medical resources and improve the quality and efficiency of emergency medical care.

[0003] Currently, the emergency department of a hospital generally needs to wait for the patient to arrive at the hospital, and then medical staff will conduct a preliminary assessment of his or her condition and conduct triage. This process will consume a certain amount of time and may delay the patient's rescue opportunity.

[0004] Therefore, there is an urgent need for an emergency intelligent triage system that can perform triage identification in advance before the patient arrives 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] The present invention provides an emergency intelligent triage system, which can effectively improve the response speed and efficiency of emergency medical treatment.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] An emergency intelligent triage system, including a user end, a cloud end, and a medical end:

[0008] The user end is used to receive patient condition information and transportation information uploaded by accompanying personnel, and is also used to obtain location information in real time and send the condition information and transportation location information to the cloud; the condition information includes voice description of the condition and video of the condition;

[0009] The cloud is used to obtain information about the patient's condition, pre-triage the patient based on the voice description of the condition, 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 the patient's condition video, identify the patient's condition based on the condition video, and determine whether the patient's condition meets level I. If it does, the distance between the patient and the hospital is determined based on the corresponding location information. When the distance is less than the preset distance value, the condition summary and pre-triage results are sent to the medical care end;

[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, the medical condition summary and 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 process description and send the emergency process description and pre-triage results to the user end.

[0013] Furthermore, the cloud is also used to receive treatment measures of medical staff from the medical end when the classification is level I, and send the treatment measures to the user end.

[0014] Furthermore, the cloud is also used to determine whether the user terminal receives the uploaded medical information for the second time when the classification is level III. If the medical information uploaded for the second time 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 is also used to identify the emotions of the accompanying person according to the voice description of the condition when maintaining level III, and determine whether the accompanying person's emotions are angry. If angry, activate the soothing mode;

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

[0017] Furthermore, in the soothing mode, the cloud is also used to estimate the time when the patient arrives at the hospital based on the location information and transportation information of the patient classified as Level III, as the reception time; to determine whether there are other patients classified as Level I who have arrived at the hospital or are receiving treatment at the reception time, and if so, to obtain the video clip of the corresponding Level I patient, to blur the patient's face and the part containing blood in the video clip, and to send the blurred video clip to the security end.

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

[0019] Furthermore, the medical end is also used to obtain 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 condition information is marked and an audit item is generated.

[0020] Furthermore, the medical end is also used to obtain the current reception situation, determine the busyness according to the reception situation, and dynamically adjust the preset distance value according to the busyness.

[0021] Through real-time uploading and cloud processing of medical information, this solution can accurately classify the patient's condition before the patient arrives at the hospital, providing the hospital's emergency department with more time to prepare medical resources, greatly improving the emergency response speed and rescue efficiency, especially shortening the treatment time for critically ill patients, thereby reducing the risk of patients during the rescue process. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The present invention is a logic block diagram of an embodiment 1 of an emergency intelligent triage system. DETAILED DESCRIPTION

[0023] The following is further described in detail through specific implementation methods:

[0024] Embodiment 1

[0025] like Figure 1 As shown, an emergency intelligent triage system of this embodiment includes a user end, a cloud end, a medical end, and a security end. In this embodiment, the user end is for the patient's accompanying person or the patient, the cloud end is a server, the medical end is for the medical staff, and the security end is for the security staff. The user end and the security end use applications running on a smartphone, and the medical end uses applications running on a smartphone or a computer.

[0026] The user end is used to receive patient condition information and transportation information uploaded by accompanying personnel, and is also used to obtain location information in real time and send the condition information and transportation location information to the cloud; the condition information includes voice description of the condition and video of the condition;

[0027] The cloud is used to obtain information about the condition, pre-triage the patient based on the voice description of the condition, and generate pre-triage results. Specifically, the cloud converts the voice description of the condition into text information, extracts the content of the text information through a preset AI model, obtains a summary of the condition, and grades the patient's condition based on the summary and preset grading standards, including Grade I, Grade II, and Grade III.

[0028] In this embodiment, the disease summary includes keywords such as cardiac / respiratory arrest, airway obstruction / suffocation, shock, acute massive bleeding, 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, extremely severe burns, signs of brain herniation, and severe abdominal pain in pregnant women, which are classified as Level I and need to be treated immediately after arriving 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 (sleepiness, disorientation, syncope), diabetic ketoacidosis, mental disorders (tendency to hurt oneself or others), vaginal bleeding, and ectopic pregnancy. It is classified as Level II and is recommended to be handled within 10 minutes after arriving at the hospital.

[0030] Other situations are classified as Level III and are recommended to be handled within 30 to 120 minutes.

[0031] If the classification is Level I, it is used to obtain the medical condition video, identify the patient's condition based on the medical condition video, and determine whether the patient's condition meets Level I. If it does, the distance between the patient and the hospital is determined based on the corresponding location information. When the distance is less than the preset distance value, the medical condition summary and pre-triage results are sent to the medical care end.

[0032] In this embodiment, the medical video is analyzed by an image recognition model, and video clips containing the patient's body and face are cut out. The patient's consciousness is analyzed based on the image frames of the patient's face in the video clips. If not, it is judged to meet Level I.

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

[0034] If the classification is level II, it is 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, the medical condition summary and pre-triage results will be sent to the medical staff.

[0035] If the classification is level III, it is used to obtain the pre-stored emergency process description, and send the emergency process description and pre-triage results to the user end; it is also used to determine whether the user end receives the uploaded medical condition information for the second time. If the medical condition information uploaded for the second time is obtained, the patient is pre-triaged again according to the first and second uploaded medical condition information. If the result is greater than level III, the classification is level II, otherwise it maintains level III. If it maintains level III, the emotion of the accompanying person is identified according to the voice recognition of the medical condition description, and it is determined whether the emotion of the accompanying person is angry. If it is angry, the soothing mode is enabled; in this embodiment, the training data including the start-up emotion is collected and calibrated in advance, and then the emotion recognition model is trained through the training set to accurately identify the corresponding emotion. The emotion recognition model outputs the probability values ​​of different emotions, and the emotion of the probability value is used as the current emotion.

[0036] The cloud is also used to send location information, transportation information, and pre-triage results to the security end in the soothing mode. Transportation information includes vehicle type and license plate number, such as online car-hailing, Chongqing A XXXXX. In the case that the patient's companion is angry, the location information is sent to the security end in advance. The security personnel can guide the corresponding patient to see a doctor when he arrives at the hospital, and explain the relevant classification rules to soothe the emotions of the companion and ensure the normal order of the hospital.

[0037] The emergency intelligent triage system of this embodiment realizes rapid pre-triage of emergency patients through the collaborative work of the user end, the cloud end, and the medical end, and improves the efficiency of emergency medical response. The user end can receive the medical condition information and transportation information uploaded by the accompanying personnel, and obtain the patient's location information in real time and send it to the cloud. The cloud end analyzes the medical condition information through the AI ​​model, generates a medical condition summary, and pre-triages the patient's condition according to the grading standards, which are divided into level I, level II, and level III, to identify critically ill patients in advance, thereby optimizing the allocation of emergency resources.

[0038] For level I patients, the system further identifies the patient's condition through the medical video. If the patient meets the level I standard, the system will monitor the patient's location and the distance from the hospital in real time. When the distance is close enough, the system will immediately send the medical summary and pre-triage results to the medical staff to ensure that the patient can be treated quickly. Level II patients determine whether they have arrived at the hospital through positioning. If they have arrived, the system will also send the medical summary and pre-triage results to the medical staff to ensure timely treatment. For level III patients, the system provides emergency process instructions to guide the accompanying personnel to handle the situation, and triages again based on the accompanying personnel's supplementary content to improve the accuracy of triage. In addition, when the accompanying personnel are angry, the system starts the soothing mode and sends patient information to the security end, including location information and transportation information, to ensure that the security personnel can guide the patient to see a doctor in time and soothe the accompanying personnel's emotions. Through this intelligent triage and soothing mechanism, the system not only improves the efficiency of emergency medical care, but also effectively maintains the order of the hospital and provides more humane services for patients and accompanying personnel.

[0039] Embodiment 2

[0040] The difference between this embodiment and the first embodiment is that in the comfort mode of this embodiment, the cloud is also used to estimate the time when the patient arrives at the hospital based on the location information and transportation information of the patient classified as level III as the receiving time, and to determine whether there are other patients classified as level I who have arrived at the hospital or are receiving treatment at the receiving time. If so, obtain the video clip corresponding to the level I patient, code the patient's face and the part containing blood in the video clip, and send the coded video clip to the security end;

[0041] The security terminal is also used to receive reception feedback information, and determine whether the reception is completed based on the reception feedback information. If the reception is completed, the video clip will be deleted.

[0042] This embodiment further optimizes the function of the comfort mode. The cloud sends the processed video clips to the security terminal, so that the security personnel can intuitively show the accompanying personnel that the hospital is urgently treating other critically ill patients to prove the rationality of the graded judgment, thereby effectively comforting the emotions of the accompanying personnel and avoiding the impact of emotional intensification on the order of the hospital. In addition, the video clips are coded to protect the privacy of patients and avoid the leakage of sensitive information. The video clips are only used temporarily during the reception process and are deleted immediately after the reception is completed, ensuring the security of the patient's privacy.

[0043] Embodiment 3

[0044] The difference between this embodiment and embodiment one is that in this embodiment, the medical end is also used to obtain 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 condition information is marked and an audit item is generated.

[0045] By generating audit items, subsequent maintenance personnel can analyze the specific reasons for inconsistencies. For example, the accompanying person may lack key information when describing the condition, resulting in a low pre-triage result; or the system's AI model may have errors in text or video analysis. This targeted feedback mechanism helps to discover and solve problems in the system and continuously improve the accuracy and reliability of pre-triage.

[0046] Embodiment 4

[0047] The difference between this embodiment and the first embodiment is that in this embodiment, the medical end is also used to obtain the current reception situation, judge the busyness according to the reception situation, and dynamically adjust the preset distance value according to the busyness. The higher the busyness, the lower the preset distance value. Specifically, in this embodiment, according to the number of all patients to be treated in the emergency department, the busyness is divided into high (more than 5 people), medium (2-3 people), and low (1 person or less), and the corresponding preset distance values ​​are near (500m), medium (1km), and far (2km).

[0048] When medical staff are not busy, push the medical condition summary and pre-triage results as early as possible to facilitate medical staff to prepare in advance.

[0049] When medical staff are busy, the system shortens the preset distance value and only pushes relevant information about Class I patients who are close to the hospital, avoiding information overload and improving the response efficiency of medical staff. When medical staff are relatively idle, the system appropriately extends the preset distance value and pushes patient information as early as possible, so that medical staff can prepare for the reception plan in advance. This not only relieves the pressure of medical staff during peak hours, but also provides patients with more timely treatment preparations, improving the resource utilization efficiency and medical service quality of the emergency department.

[0050] Embodiment 5

[0051] The difference between this embodiment and the second embodiment is that, in this embodiment, the security terminal is also used to shoot the reception video during the reception and upload the reception video to the cloud;

[0052] The cloud is used to identify the emotions of the reception object (accompanying personnel or the patient himself) from the uploaded reception video and obtain the probability value of anger;

[0053] The cloud is also used to judge the emotions of accompanying personnel of patients who have not arrived at the hospital and obtain the anger probability value of the accompanying personnel.

[0054] The cloud is also used to determine whether the number of patients who have not yet arrived at the hospital exceeds the threshold number of people. If the threshold number of people is exceeded, the accompanying personnel whose anger probability value is lower than that of the reception object are screened out and marked as the person to be appeased; it is also used to code the faces of the people in the reception video and the parts containing bloodstains, add preset reminder text, the anger probability value of the reception object, and the anger probability value of the person to be appeased in the screen of the reception video; and send the processed reception video to the user end corresponding to the person to be appeased. In this embodiment, the reminder text content includes: the hospital strictly follows the regulations to receive patients, please queue up in an orderly manner to improve the efficiency of medical treatment, etc.

[0055] The emergency department often encounters a situation where there are too many patients and a shortage of medical staff. For security personnel, there is also a shortage of staff and they are unable to comfort every angry accompanying person.

[0056] In this embodiment, when receiving patients and accompanying persons, the security personnel shoot a reception video through the security terminal, which can be kept as a record. When the number of patients is too large (the number of patients who have not yet arrived at the hospital exceeds the threshold number), the reception video is processed and sent to the user terminal of the person to be appeased for viewing by the person to be appeased, thereby realizing two-way information sharing to eliminate misunderstandings and improve transparency. The person to be appeased can hear the security personnel's explanation of the hospital's relevant grading rules, and see that people with a higher anger probability value than themselves still need to queue up for medical treatment according to regulations, so that the person to be appeased understands that disputes will not speed up the speed of medical treatment, and only by cooperating with the arrangements of the security personnel / medical staff can they see the doctor as soon as possible. In summary, this solution can play an effective role in explaining the rules and appeasing when there is a shortage of staff.

[0057] The above are only embodiments of the present invention. The invention is not limited to the fields involved in this implementation case. The common sense such as the known specific structures and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or the priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to explain the content of the claims.

Claims

1. An intelligent emergency triage system, characterized in that: Including user side, cloud side and medical side: The user end is used to receive patient condition information and transportation information uploaded by accompanying personnel, and is also used to obtain location information in real time and send the condition information and transportation location information to the cloud; the condition information includes voice description of the condition and video of the condition; The cloud is used to obtain information about the patient's condition, pre-triage the patient based on the voice description of the condition, 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 the patient's condition video, identify the patient's condition based on the condition video, and determine whether the patient's condition meets level I. If it does, the distance between the patient and the hospital is determined based on the corresponding location information. When the distance is less than the preset distance value, the condition summary and pre-triage results are sent to the medical care end; 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, the medical condition summary and 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 process description and send the emergency process description and pre-triage results to the user end.

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

3. The intelligent emergency triage system according to claim 2, characterized in that: The cloud is also used to determine whether the user terminal receives the uploaded medical information for the second time when the classification is level III. If the medical information uploaded for the second time 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.

4. The intelligent emergency triage system according to claim 3, characterized in that: The cloud is also used to identify the emotions of the accompanying person according to the voice description of the condition when maintaining level III, and determine whether the accompanying person is angry. If so, activate the soothing mode; It also includes a security terminal; the cloud is also used to send location information, transportation information and pre-triage results to the security terminal in the comfort mode.

5. The intelligent emergency triage system according to claim 4, characterized in that: In the soothing mode, the cloud is also used to estimate the time when the patient arrives at the hospital based on the location information and transportation information of the patient classified as Level III, as the reception time; to determine whether there are other patients classified as Level I who have arrived at the hospital or are receiving treatment at the reception time, and if so, to obtain the video clip of the corresponding Level I patient, to blur the patient's face and the part containing blood in the video clip, and to send the blurred video clip to the security end.

6. The intelligent emergency triage system according to claim 5, characterized in that: The security terminal is also used to receive reception feedback information, and determine whether the reception is completed based on the reception feedback information. If the reception is completed, the video clip is deleted.

7. The intelligent emergency triage system according to claim 6, characterized in that: The medical end is also used to obtain 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 condition information is marked and an audit item is generated.

8. The intelligent emergency triage system according to claim 7, characterized in that: The medical end is also used to obtain the current reception situation, determine the busyness according to the reception situation, and dynamically adjust the preset distance value according to the busyness.

Images