Emergency pre-examination and sorting system

Abstract

The invention provides an emergency pre-examination and sorting system which comprises an information registration module used for registering basic information and medical history symptom information of a patient; the pre-evaluation module is used for establishing a symptom data set according to the basic information of the patient and the medical history symptom information, establishing a total data set according to the symptom data set and related triage rules in medical data literature, performing classifier training according to the total data set, performing triage category probability analysis by using a naive Bayesian algorithm according to the condition of the patient, and obtaining a triage classification probability result; a preliminary treatment examination department and a doctor are recommended; the grading module is used for grading the patients according to the critical degrees of the illness states according to the pre-evaluation result; the post-processing module is used for filing and storing the doctor-seeing record of the patient, the preliminary treatment examination department and doctor and the grading information, the disease data set of the patient is automatically analyzed through an algorithm, the preliminary treatment department and doctor are quickly recommended, the patient is prevented from being mistakenly guided to an improper department, and unnecessary examination and treatment are reduced.

Description

Technical Field

[0001] The present invention relates to the field of sorting systems, and in particular to an emergency pre-examination sorting system. Background Art

[0002] Emergency refers to the emergency department of a hospital, which means treatment in an emergency. It is divided into emergency treatment and rescue. Its existence ensures that in the event of sudden illness or accidental injury, professional and scientific treatment can be obtained in the shortest time. Consultation refers to the process of doctors asking questions to understand the cause, course of disease, related symptoms and other disease-related conditions of the user's disease. The main purpose of the consultation is for doctors to obtain useful information about the patient's illness in order to determine the direction and strategy of treatment. It is the basis for subsequent work and is of great significance in disease diagnosis. In the process of medical diagnosis and treatment, doctors hope to fully understand the user's condition in order to develop accurate treatment methods. For users, they hope to receive treatment as quickly and effectively as possible.

[0003] The existing emergency pre-examination and triage system generally requires waiting for medical staff to arrive at the emergency center before gradually starting to use the system through various functions of the system. However, time is very precious in emergency situations. Emergency physicians also need to understand the patient's medical history and clinical condition before performing rescue. If they wait until the patient arrives at the hospital before observing him, a large part of the rescue time may be wasted, resulting in untimely rescue.

[0004] Therefore, it is necessary to provide a new emergency pre-examination and sorting system to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides an emergency pre-examination and triage system.

[0006] The emergency pre-examination and triage system provided by the present invention includes an information registration module for registering basic information and medical history and symptom information of patients;

[0007] The pre-evaluation module is used to establish a disease data set based on the patient's basic information and medical history and symptom information, and to establish a total data set based on the disease data set and the triage rules related to the medical literature. The classifier is trained based on the total data set, and the naive Bayes algorithm is used to perform triage category probability analysis based on the patient's condition, and the initial treatment and examination department and doctor are recommended based on the analysis results;

[0008] A classification module, based on the results of the pre-assessment, classifies the patient according to the severity of the condition, wherein the severity is classified into five levels, corresponding to non-urgent, sub-urgent, urgent, very urgent and immediate treatment;

[0009] The post-processing module is used to archive and save the patient's medical records, preliminary treatment and examination departments and doctors, and classification information;

[0010] An alarm module is provided, wherein the alarm module will immediately sound an alarm when encountering two situations that require urgent and immediate processing.

[0011] Furthermore, the classifier training includes the following steps: S1, reading a triage rule data set to be trained, each set of data including a symptom combination and a corresponding classification label;

[0012] S2, loop training all the data in the triage rule dataset to generate a symptom vocabulary list containing all symptom feature words;

[0013] S3, based on the symptom vocabulary list, cyclically train all the data in the triage rule data set to generate a feature vector corresponding to each piece of data;

[0014] S4, loop through the classification and triage category set, and use the multinomial model to calculate the prior probability and class conditional probability of each classification label;

[0015] S5. Calculate the inverse document frequency of each feature word in the symptom vocabulary table, and generate a corresponding adjustment factor based on the number of subject classifications involved in the current symptom feature.

[0016] Furthermore, the Naive Bayes algorithm includes: Among them, c is the triage category set of the sample, p(c) is the probability of the category appearing, p(w|c) is the class conditional probability of sample w relative to the category label c, that is, the probability of the feature vector w relative to the sample category c, and P(w) is the probability of the feature vector appearing.

[0017] Furthermore, before establishing the disease data set, it is necessary to preprocess the patient's basic information and medical history symptom information. Data preprocessing includes removing meaningless symbols, processing missing values, standardizing data, and normalizing data.

[0018] Furthermore, the basic patient information includes patient name, patient gender, patient age, patient condition, and patient condition duration.

[0019] Furthermore, for special patients, a tracking mechanism is established in the post-processing module to regularly record the patient's treatment progress, disease changes and medication status.

[0020] Compared with the related art, the emergency pre-examination and triage system provided by the present invention has the following beneficial effects:

[0021] The present invention establishes a symptom data set based on the patient's basic information and medical history symptom information, and establishes a total data set based on the symptom data set and related triage rules in medical data documents, performs classifier training based on the total data set, and uses the naive Bayes algorithm to perform triage category probability analysis based on the patient's condition, recommends preliminary treatment and examination departments and doctors based on the analysis results, automatically analyzes the patient's symptom data set through the algorithm, quickly recommends preliminary treatment departments and doctors, reduces the pressure on medical staff, avoids patients being mistakenly directed to inappropriate departments, and reduces unnecessary examinations and treatments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A structural block diagram of the emergency pre-examination and sorting system provided by the present invention;

[0023] Figure 2 A flowchart of the classifier training provided by the present invention. DETAILED DESCRIPTION

[0024] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0025] Please refer to Figure 1 as well as Figure 2 ,in, Figure 1 A structural block diagram of the emergency pre-examination and sorting system provided by the present invention; Figure 2 A flowchart of the classifier training provided by the present invention.

[0026] In the specific implementation process, Figure 1-Figure 2 As shown, the emergency pre-examination and triage system includes an information registration module for registering basic patient information and medical history and symptom information, wherein the basic patient information includes the patient's name, the patient's gender, the patient's age, the patient's symptoms, and the duration of the patient's symptoms;

[0027] The pre-assessment module is used to establish a disease data set based on the patient's basic information and medical history symptom information, and to establish a total data set based on the disease data set and the triage rules related to the medical data literature, to train the classifier based on the total data set, and to use the naive Bayes algorithm to perform triage category probability analysis based on the patient's condition, and to recommend the initial treatment and examination department and doctor based on the analysis results. The algorithm automatically analyzes the patient's disease data set, quickly recommends the initial treatment department and doctor, reduces the pressure on medical staff, prevents patients from being mistakenly directed to inappropriate departments, and reduces unnecessary examinations and treatments;

[0028] The classification module classifies patients according to the severity of their condition based on the results of the pre-assessment. The severity of the condition is divided into five levels, corresponding to non-urgent, sub-urgent, urgent, very urgent and immediate treatment:

[0029] Level V (non-urgent): The patient's condition is mild and can wait for several hours or even make an appointment for consultation, such as minor abrasions, small burns, etc.

[0030] Level IV (non-urgent): The patient's condition is relatively stable and can wait longer (usually no more than 1 hour), such as mild pain, acute onset of chronic disease, etc.

[0031] Level III (urgent): The patient's condition is serious, but can wait for a period of time (usually no more than 30 minutes), such as acute abdominal pain, moderate trauma, mild poisoning, etc.

[0032] Level II (very urgent): The patient is in potential danger of life and needs treatment within 10 minutes, such as acute chest pain, severe dyspnea, severe poisoning, etc.

[0033] Level I (Immediate Treatment): The patient is in a life-threatening condition and requires immediate intervention, such as cardiac arrest, severe trauma bleeding, acute airway obstruction, etc.

[0034] The post-processing module is used to archive and save the patient's medical records, preliminary treatment and examination departments and doctors, and classification information;

[0035] It should be noted that for special patients (such as patients with no medical records, ...

[0036] The tracking mechanism includes: 1. Hospitalization and treatment: After the patient is admitted to the hospital, emergency treatment is immediately carried out, and the tracking mechanism is activated at the same time to collect patient information and establish information files;

[0037] 2. Identity confirmation and family contact: For patients with no identity, no relatives, etc., their identity information and family members should be found through various channels such as public security departments and social media. For patients with group injuries, timely communication should be made with the accident handling department to obtain the list of injured persons and family contact information;

[0038] 3. Treatment process tracking: regularly record the patient's treatment progress, condition changes and medication, and adjust the treatment plan in a timely manner;

[0039] 4. Discharge arrangements and follow-up: Before the patient is discharged, a detailed discharge plan is formulated, including follow-up treatment, rehabilitation training and reexamination arrangements. For patients with no medical care, no medical care and no medical care, assistance is provided to solve their financial resources and placement issues. For patients with group injuries, ensure that each patient has clear discharge instructions and follow-up plans;

[0040] Alarm module,The alarm module will immediately issue an alarm when encountering two situations that are extremely urgent and need to be handled immediately.

[0041] Functions of post-processing module

[0042] 1. Data archiving:

[0043] Archiving of medical records: Organize and archive the patient's medical records, including the patient's personal information, medical history and symptom information, diagnosis results, treatment recommendations, etc.

[0044] Archiving of initial treatment and examination department and doctor information: Save the information of the initial treatment and examination department and doctor recommended by the triage system.

[0045] Archiving of classification information: According to the severity of the patient's condition, classification information is recorded to facilitate subsequent tracking and management.

[0046] 2. Data analysis and reporting:

[0047] Statistical analysis: Regularly conduct statistical analysis of patients' medical records to identify common diseases, epidemic trends, etc.

[0048] Quality control: Evaluate the quality and efficiency of medical services by analyzing data and identify areas for improvement.

[0049] 3. Patient tracking:

[0050] Follow-up reminders: Set follow-up reminders based on the patient's condition and treatment progress to ensure that beneficiaries can return for follow-up visits on time.

[0051] Efficacy evaluation: Evaluate the treatment effect by tracking the patient's treatment progress.

[0052] 4. Data security and privacy protection:

[0053] Data encryption: Encrypt sensitive information to ensure data security.

[0054] Access control: Set different access rights to ensure that only authorized personnel can access the patient's medical records

[0055] 5. Interface and integration:

[0056] Integration with electronic medical record system: ensure that the post-processing module can be seamlessly connected with the hospital's existing electronic medical record system. Data export: support the export of archived data into a standard format for further analysis or sharing with other systems.

[0057] Effects of post-processing modules

[0058] 1. Improve medical quality:

[0059] Continuity of care: By keeping detailed visit records, doctors can better understand the patient's medical history and provide continuity of care.

[0060] Treatment effect tracking: track the patient's treatment effect and adjust the treatment plan in time

[0061] 2. Improve work efficiency:

[0062] Automated archiving: Automatically archive patients’ medical records to reduce the burden of manual data entry for medical staff.

[0063] Data sharing: Simplify the data sharing process and improve the efficiency of collaboration among multiple departments.

[0064] 3. Improve patient experience:

[0065] Personalized service: Provide personalized medical services based on the patient's medical history and treatment records. Reduce waiting time: Reduce patient waiting time through an efficient filing and query system.

[0066] 4. Promote scientific research:

[0067] Data accumulation: Long-term accumulated medical records can provide valuable data resources for clinical research.

[0068] Trend analysis: Identify disease trends and potential public health issues through analysis of historical data.

[0069] 5. Strengthen regulatory compliance:

[0070] Data integrity: Ensure that all medical records are properly maintained and comply with legal and regulatory requirements.

[0071] Privacy protection: Comply with relevant privacy protection laws and regulations to ensure the security of patient information.

[0072] It should be noted that classifier training includes the following steps:

[0073] S1. Read the triage rule dataset T to be trained. Each set of data includes a symptom combination and a corresponding classification label.

[0074] S2, loop training all the data in the triage rule data set T to generate a symptom vocabulary table K containing all symptom feature words;

[0075] S3, based on the symptom vocabulary table K, cyclically train all the data in the triage rule data set T to generate the feature vector w corresponding to each data;

[0076] S4, loop through the classification and triage category set C, use the polynomial model to calculate the prior probability p(c) and class conditional probability p(w|c) of each classification label;

[0077] S5. Calculate the inverse document frequency d of each feature word in the symptom vocabulary table K, and generate the corresponding adjustment factor according to the number of subject classifications involved in the current symptom feature. The more subject classifications the symptom involves, the lower its significance and importance in distinguishing subjects, and the smaller its corresponding weight.

[0078] In a specific embodiment, the Naive Bayes algorithm includes: Where c is the triage category set of the sample, p(c) is the probability of the category appearing, p(w|c) is the class conditional probability of sample w relative to the category label c, that is, the probability of the feature vector w relative to the sample category c, P(w) is the probability of the feature vector appearing, a weight factor d is introduced for the feature vector w, and w'=wd is defined, w' is the feature vector after the weight factor d is introduced, where d is the weight factor matrix trained from the sample data based on the IDF algorithm;

[0079] The IDF calculation formula is: Where D is the total data set, which is divided into the disease condition data set U and the triage rule data set T.

[0080] Before establishing the disease data set, it is necessary to preprocess the patient's basic information and medical history symptom information. Data preprocessing includes removing meaningless symbols, processing missing values, data standardization and data normalization.

[0081] Data preprocessing details:

[0082] 1. Remove meaningless symbols, such as "", line breaks, and space symbols in the data;

[0083] 2. Missing value processing: mark the data and further complete the information if there are duplicate names

[0084] 3. Data standardization: Based on the patient’s description, gender characteristics were standardized, using “0” for female and “1” for male;

[0085] 4. Data normalization: The age characteristics are normalized using the formula:

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0087] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention, and any figure mark in the claims should not be regarded as limiting the claims involved.

[0088] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. An emergency pre-examination and triage system, characterized in that: It includes an information registration module, which is used to register the patient's basic information and medical history and symptom information; The pre-evaluation module is used to establish a disease data set based on the patient's basic information and medical history and symptom information, and to establish a total data set based on the disease data set and the triage rules related to the medical literature. The classifier is trained based on the total data set, and the naive Bayes algorithm is used to perform triage category probability analysis based on the patient's condition, and the initial treatment and examination department and doctor are recommended based on the analysis results; The classification module classifies patients according to the severity of their condition based on the results of the pre-assessment; The post-processing module is used to archive and save the patient's medical records, preliminary treatment and examination departments and doctors, and classification information.

2. The emergency pre-examination and triage system according to claim 1, characterized in that: The classifier training comprises the following steps: S1, reading a triage rule data set to be trained, each set of data comprising a symptom combination and a corresponding classification label; S2, loop training all the data in the triage rule dataset to generate a symptom vocabulary list containing all symptom feature words; S3, based on the symptom vocabulary list, cyclically train all the data in the triage rule data set to generate a feature vector corresponding to each piece of data; S4, loop through the classification and triage category set, and use the multinomial model to calculate the prior probability and class conditional probability of each classification label; S5. Calculate the inverse document frequency of each feature word in the symptom vocabulary table, and generate a corresponding adjustment factor based on the number of subject classifications involved in the current symptom feature.

3. The emergency pre-examination and triage system according to claim 2, characterized in that: The Naive Bayes algorithm includes: Among them, c is the triage category set of the sample, p(c) is the probability of the category appearing, p(w|c) is the class conditional probability of sample w relative to the category label c, that is, the probability of the feature vector w relative to the sample category c, and P(w) is the probability of the feature vector appearing.

4. The emergency pre-examination and triage system according to claim 3, characterized in that: Before establishing the disease data set, it is necessary to preprocess the patient's basic information and medical history symptom information. Data preprocessing includes removing meaningless symbols, processing missing values, data standardization and data normalization.

5. The emergency pre-examination and triage system according to claim 4, characterized in that: The basic patient information includes patient name, patient gender, patient age, patient condition, and patient condition duration.

6. The emergency pre-examination and triage system according to claim 5, characterized in that: For special patients, a tracking mechanism is established in the post-treatment module to regularly record the patient's treatment progress, changes in condition and medication.

7. The emergency pre-examination and triage system according to claim 6, characterized in that: The emergency level is classified into five levels, corresponding to non-emergency, sub-emergency, emergency, very urgent and immediate processing.

8. The emergency pre-examination and triage system according to claim 7, characterized in that: The system also includes an alarm module, which can immediately issue an alarm when encountering two situations that are extremely urgent and need to be dealt with immediately.

Images