A regional integrated emergency stroke unit

Abstract

The present invention discloses a regional integrated emergency stroke unit, which relates to the medical field. The regional integrated emergency stroke unit includes an information interaction area, an imaging examination area and a thrombolytic therapy area; wherein the information interaction area is provided with a doctor's workstation, a comprehensive information monitoring display and a process support AI assistant; the imaging examination area is provided with detection equipment, a first TV display screen, a low-field movable magnetic resonance imaging device and an AI-assisted decision-making system; the process support AI assistant performs automatic consultation and auxiliary neurological scale scoring through voice interaction or touch screen typing interaction, and also provides retrieval support for real-time knowledge base and clinical guidelines; the AI-assisted decision-making system assists in decision-making based on the automatic consultation results, scale scoring results, test results and head and neck magnetic resonance imaging results, generates and displays a treatment plan. The present invention concentrates all diagnosis and treatment activities involved in acute ischemic stroke patients after they arrive at the hospital into one space, which can significantly shorten the time for diagnosis and treatment.

Description

Technical Field

[0001] The invention relates to the field of medical technology, and in particular to a regional integrated emergency stroke unit. Background Art

[0002] Currently, it is known that about 70% of stroke patients suffer from ischemic stroke, the main cause of which is thrombosis or embolism in the responsible blood vessel. A large number of studies have shown that the earlier the thrombus is dissolved or cleared and the reperfusion of brain tissue in the ischemic area is restored, the more brain tissue can be saved and the better the clinical prognosis. However, the proportion of patients who receive endovascular treatment within 6 hours of acute ischemic stroke is only 2.17%. In this regard, some scholars have proposed to significantly reduce pre-hospital and in-hospital delays for stroke patients by building an organized stroke medical system such as stroke centers and promoting mobile stroke units.

[0003] Previous studies have suggested that hospitals that treat stroke patients should establish stroke units whenever possible, and all patients with acute ischemic stroke should be admitted to stroke units for treatment as early as possible and whenever possible. For in-hospital delays in acute ischemic stroke, organizational management is emphasized. However, it is still common for patients in stroke units to travel back and forth between consulting rooms, laboratories, imaging examination rooms, and treatment rooms, which delays precious treatment time. There is room for further optimization. Summary of the invention

[0004] The purpose of the present invention is to provide a regional integrated emergency stroke unit, which concentrates all diagnosis and treatment activities involved in acute ischemic stroke patients after they arrive at the hospital into one space, so as to significantly shorten the diagnosis and treatment time.

[0005] To achieve the above object, the present invention provides the following solution.

[0006] The present invention provides a regional integrated emergency stroke unit, comprising: an information exchange area, an imaging examination area, and a thrombolytic therapy area;

[0007] The information interaction area is provided with a doctor's workstation, a comprehensive information monitoring display, and a process support AI assistant; the doctor's workstation includes a computer, a file rack, and a folding table; the computer is used for doctors to input information; the file rack is used to place documents; the folding table is used for temporary placement and storage of medical equipment and documents; the comprehensive information monitoring display is used to display the patient's basic information, arrival time, arrival time in the consulting room, and vital signs; the process support AI assistant is used to perform automatic medical consultation and assist in neurological scale scoring through voice interaction or touch screen typing interaction, and is also used to provide retrieval support for real-time knowledge base and clinical guidelines;

[0008] The imaging examination area is provided with a detection device, a first television display screen, a low-field movable magnetic resonance imager and an AI-assisted decision-making system; the detection device is used to perform electrocardiogram examinations, drug gene testing, and monitor the patient's blood oxygen saturation, blood pressure, and peripheral blood glucose to obtain test results; the first television display screen is used to enlarge and display the content of the comprehensive information monitoring display; the low-field movable magnetic resonance imager is used to perform head and neck magnetic resonance imaging of the patient; the AI-assisted decision-making system is respectively communicated with the comprehensive information monitoring display, the process support AI assistant, the detection device, the first television display screen and the low-field movable magnetic resonance imager; the AI-assisted decision-making system is used to make auxiliary decisions based on the automatic consultation results, scale scoring results, test results and head and neck magnetic resonance imaging results, generate and display treatment plans;

[0009] The thrombolytic therapy area is equipped with a small refrigerator, an emergency medicine cabinet and a storage cabinet for storing medicines, reagents and emergency medicines with different temperature requirements; the thrombolytic therapy area is also equipped with an ambulance and a vital signs monitoring system; the ambulance is used to rescue patients in emergency medical situations; the vital signs monitoring system is used to monitor and display the patient's vital signs in real time.

[0010] Optionally, the process supports the provision of an intelligent interaction module in the AI ​​assistant; the intelligent interaction module uses the structured medical records of the emergency department as a basis, asks structured questions about the patient's key medical information such as onset time, onset symptoms, accompanying symptoms, past medical history, and allergy history, performs voice recognition on the patient's and / or their family's answers, and performs structured entry of key medical information.

[0011] Optionally, the intelligent interaction module is also used to perform auxiliary neurological scale NIHSS scoring, ABCD2 scoring and pre-onset mRS scoring through voice interaction or touch screen typing interaction with the patient and / or his / her family members to obtain scale scoring results.

[0012] Optionally, a large language model is also stored in the intelligent interaction module; the large language model is provided with a knowledge base related to the clinical diagnosis and treatment of stroke, including clinical scales, acute phase guidelines for cerebral infarction, secondary prevention guidelines for cerebral infarction, diagnosis and treatment guidelines for cerebral hemorrhage, and clinical diagnosis and treatment guidelines for subarachnoid hemorrhage; during the diagnosis and treatment process, the knowledge base and clinical guidelines can be retrieved through voice interaction with the doctor or touch screen typing interaction.

[0013] Optionally, the intelligent interaction module is also used to provide medical procedure explanations and treatment plan instructions as well as to sign an informed consent form through voice interaction or touch screen typing interaction with the patient and / or his / her family members.

[0014] Optionally, the detection equipment includes an electrocardiograph, a wearable electrocardiograph monitor, a finger-clip oximeter, a sphygmomanometer, a blood glucose meter, and a non-invasive rapid genotyping detector.

[0015] Optionally, a mobile magnetic resonance imaging system is integrated into the low-field movable magnetic resonance imager; the mobile magnetic resonance imaging system uses a deep learning-based image reconstruction method to achieve image super-resolution reconstruction using the patient's low-field and high-field MRI data sets to obtain head and neck magnetic resonance imaging results.

[0016] Optionally, the AI-assisted decision-making system is used to use a deep learning method to identify the site of acute cerebral infarction lesions in the head and neck magnetic resonance imaging results and automatically calculate the infarction volume; the AI-assisted decision-making system is also used to determine whether the patient has intracranial large artery occlusion / stenosis through the MRA sequence of mobile magnetic resonance imaging; the AI-assisted decision-making system is also used to use automatic registration technology to align different sequences to a standard space, to achieve automated identification of DWI / FLAIR mismatches in acute cerebral infarction lesions, to determine the approximate onset time of stroke after awakening, and to guide reperfusion therapy.

[0017] Optionally, the AI-assisted decision-making system is also used to combine the image interpretation information with the scale scoring results to determine whether the patient has a clinical-imaging mismatch, and combined with the infarct volume, to assist in deciding whether the patient needs intravascular treatment to achieve intracranial reperfusion.

[0018] Optionally, the thrombolytic therapy area is further provided with a second television display screen and a trash can; the second television display screen is used to display the contents of the comprehensive information monitoring display; the trash can is used to temporarily place medical or domestic waste.

[0019] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0020] The present invention proposes a regional integrated emergency stroke unit by sorting out the medical process of acute ischemic stroke, integrating the information exchange area, imaging examination area and thrombolytic treatment area into one consulting room, that is, all diagnosis and treatment activities involved in acute ischemic stroke patients after arriving at the hospital are concentrated in one space, and the medical treatment, examination and thrombolysis of ischemic stroke patients are spatially integrated and organized and systematically managed, so that ischemic stroke can obtain a one-stop solution, and solves the problem that the triage, medical consultation, physical examination, laboratory test, and examination items currently faced by acute ischemic stroke patients after arriving at the hospital are scattered in different emergency departments, and the diagnosis and treatment involve many disciplines and specialties, resulting in a significantly prolonged time from the patient's arrival at the hospital to the treatment, and significantly shortens the patient's medical treatment time. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of three-dimensional modeling of a regional integrated emergency stroke unit of the present invention;

[0023] Figure 2 It is a schematic diagram of three-dimensional modeling of the information interaction area;

[0024] Figure 3 It is a schematic diagram of three-dimensional modeling of the imaging examination area;

[0025] Figure 4 A schematic diagram of three-dimensional modeling of the thrombolytic treatment area;

[0026] Figure 5 An overview of the items stored in a small emergency vehicle. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The purpose of the present invention is to provide a regional integrated emergency stroke unit, which concentrates all diagnosis and treatment activities involved in acute ischemic stroke patients after they arrive at the hospital into one space, so as to significantly shorten the diagnosis and treatment time.

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] See also Figure 1 The present invention provides a regional integrated emergency stroke unit (ESU), including: an information exchange area, an imaging examination area, a thrombolytic therapy area, and an entrance and exit. The overall size of the unit can be 8.3m×4m.

[0031] See also Figure 2 The information interaction area is provided with a doctor workstation, a comprehensive information monitoring display 1 and a process support AI assistant 2.

[0032] The doctor workstation specifically includes a computer, a file rack 3 and a folding table 4. The computer includes a host, a dual-screen display 5 and a keyboard 6, which can be used by doctors to enter and view patient information. In some embodiments, the size of a single display in the dual-screen display 5 can be 27 inches. The file rack 3 can be used to place paper documents. The folding table 4 can be a wall-mounted / wall-mounted folding table for temporary placement and storage of small medical equipment, instruments, documents, etc. The symbol " / " is used in the present invention to represent the meaning of "or".

[0033] The comprehensive information monitoring display 1 is used to display the patient's basic information, hospital arrival time, clinic arrival time, and vital signs, and the size can be 50 inches. The process support AI assistant 2 is used to perform automatic medical consultation and assist in neurological scale scoring through voice interaction or touch screen typing interaction, and is also used to provide real-time knowledge base and clinical guideline retrieval support, etc.

[0034] Specifically, the process supports that the AI ​​assistant 2 is an AI intelligent robot. The process supports that an intelligent interaction module is provided in the AI ​​assistant 2. The automatic consultation function of the intelligent interaction module is based on the structured medical records of the emergency department, and structured questions are asked about the patient's onset time, symptoms, concomitant symptoms, past medical history, allergy history and other key information. The patient and / or their family members' answers are input through voice recognition, or the doctor inputs the content based on the information provided by the patient and / or their family members, and stores it as a structured consultation result. The subsequent AI-assisted decision-making system can make recommendations for the next step of diagnosis and treatment based on the consultation results and combined with the images.

[0035] The auxiliary neurological scale scoring function of the intelligent interactive module is to ask questions about each item of the key auxiliary neurological scales, such as the National Institute of Health Stroke Scale (NIHSS) score, ABCD2 (age, blood pressure, clinical features, duration, diabetes) score, and modified Rankin Scale (mRS) score before onset, and obtain the score results of each scale by voice recognition and recording the answers of the patient and / or his / her family members or by the doctor entering the content according to the information provided by the patient and / or his / her family members. The NIHSS score can be used to determine the severity of the patient's neurological deficit, and this score is also an important basis for reperfusion therapy of ischemic cerebrovascular disease (such as cerebral infarction). The ABCD2 score can stratify the risk of cerebral infarction in patients with transient cerebral ischemia, and is an important reference for treatment such as antiplatelet aggregation, which helps to assist doctors in making the next treatment decision. The mRS score before onset can evaluate the functional status of the patient before onset, and is an important basis for reperfusion therapy such as endovascular treatment of ischemic cerebrovascular disease.

[0036] The retrieval support function of the intelligent interactive module is implemented by a large language model. The large language model is equipped with a knowledge base related to the clinical diagnosis and treatment of stroke, including but not limited to the aforementioned clinical scales, international / domestic guidelines for acute phase of cerebral infarction, guidelines for secondary prevention of cerebral infarction, guidelines for diagnosis and treatment of cerebral hemorrhage, and guidelines for clinical diagnosis and treatment of subarachnoid hemorrhage. During the diagnosis and treatment process, when the doctor needs to retrieve the relevant information, he can directly ask by voice, and the intelligent interactive module will give real-time feedback. For example, when a doctor encounters a patient with cerebral infarction within the time window of intravenous thrombolysis, but there are suspected contraindications to thrombolysis, he can ask the intelligent interactive module about the indications and contraindications of intravenous thrombolysis with alteplase, quickly check whether the patient meets the treatment indications, and quickly assist in decision-making.

[0037] The process supports AI assistant 2 to interact efficiently with medical staff, patients and / or their families, and provide functions such as explanation of medical procedures, description of treatment plans, and signing of informed consent. Among them, medical procedures and treatment plans include indications, contraindications, possible risks and benefits of treatments such as reperfusion therapy (intravenous thrombolysis and intravascular thrombectomy), secondary prevention treatment (antiplatelet aggregation, lipid-lowering treatment for ischemic cerebrovascular disease, etc.). For issues related to treatment plans that patients and their families are concerned about, doctors can be assisted in providing corresponding data and existing guideline recommendations to assist doctors in explanations. When the doctor obtains the informed consent of the patient and his family, the patient and his family can be reminded by voice of the signing location and the content that must be signed, and the current medical insurance policy for related drugs can be assisted in explaining.

[0038] See also Figure 3 The imaging examination area is provided with a detection device 7, a first television display screen 8, a low-field movable magnetic resonance imager 9, and an AI-assisted decision-making system.

[0039] The detection equipment 7 includes an electrocardiograph, a wearable electrocardiograph monitor, a finger-clip oximeter, a sphygmomanometer, and a blood glucose meter, which are used to perform electrocardiograph examinations and monitor the patient's blood oxygen saturation, blood pressure, and peripheral blood glucose. The detection equipment also includes a non-invasive rapid genotyping detector for genes such as CYP2C19, which is used to perform drug gene testing to obtain test results.

[0040] The first television display screen 8 is a large-size television display screen of 60 inches or more, and is used to enlarge and display the display content of the comprehensive information monitoring display 1 in the information interaction area.

[0041] A low-field mobile magnetic resonance imaging device is provided in the imaging examination area, which can perform nuclear magnetic resonance scanning for patients and generate magnetic resonance imaging results of the patient's head and neck. The low-field mobile magnetic resonance imaging device of the present invention uses a portable, magnetic shielding-free, easy-to-use low-field strength (0.23T) MRI to perform rapid imaging evaluation of acute stroke patients, distinguish cerebral infarction and cerebral hemorrhage within 10 minutes, and simultaneously evaluate the condition of large blood vessels. On the one hand, it solves the problem that the existing mobile head and neck magnetic resonance imaging system has a small aperture, a relatively high incidence of claustrophobia, and a huge body size. Patients cannot complete magnetic resonance examinations. On the other hand, it solves the shortcomings of poor accessibility of high-field strength nuclear magnetic resonance and long scanning time, which cannot be applied to acute stroke neuroimaging assessment. On the other hand, it also breaks through the bottleneck that stroke patients must undergo head CT scans in a separate CT room, improves the accuracy of patient diagnosis, and greatly shortens the time from the patient's arrival at the hospital to treatment.

[0042] The low-field mobile magnetic resonance imager 9 of the present invention is integrated with a mobile magnetic resonance imaging system. The mobile magnetic resonance imaging system can greatly shorten the detection time by using artificial intelligence image analysis technology, while improving the image quality, assisting doctors in distinguishing ischemia / hemorrhage, identifying the core infarction site and volume, identifying large artery occlusion and stenosis, judging the duration of stroke patients after awakening, and making treatment decisions quickly. Specifically, the mobile magnetic resonance imaging system achieves image super-resolution reconstruction by developing a deep learning image reconstruction method and using a large number of low-field and high-field MRI data sets completed by the same patient, which greatly improves the details and contrast of 0.23T MRI images, improves image quality, and shortens the scanning time.

[0043] The AI ​​decision-making assistance system is respectively connected to the comprehensive information monitoring display 1, the process support AI assistant 2, the detection device 7, the first TV display screen 8 and the low-field movable magnetic resonance imager 9. The AI ​​decision-making assistance system is used to make auxiliary decisions based on the automatic consultation results, the scale scoring results, the detection results and the head and neck magnetic resonance imaging results, generate and display the treatment plan.

[0044] Specifically, the AI-assisted decision-making system develops deep learning methods and uses a large number of manually annotated data sets to quickly and accurately identify the site of acute cerebral infarction lesions and automatically calculate their volumes. The AI-assisted decision-making system also assists doctors in image interpretation by moving the MRA sequence of magnetic resonance imaging to quickly determine whether the patient has intracranial large artery occlusion / stenosis. The AI-assisted decision-making system also uses automatic registration technology to register different sequences (DWI and FLAIR) to the standard space to achieve automatic identification of DWI / FLAIR mismatches in acute cerebral infarction lesions, determine the approximate onset time of stroke after awakening, and guide reperfusion therapy. The above-mentioned image interpretation information is combined with the total NIHSS score obtained by the intelligent interaction module to assist doctors in determining whether the patient has a clinical-image mismatch. Combined with the infarction volume, it can further assist doctors in deciding whether the patient needs intravascular treatment to achieve intracranial reperfusion.

[0045] See also Figure 4 , the thrombolytic therapy area is provided with a small refrigerator 10, an emergency medicine cabinet 11 and a storage cabinet 12 for storing medicines, reagents and emergency medicines with different temperature requirements. Among them, the small refrigerator 10 is provided with a temperature display and setting device, which can monitor the storage temperature of the medicine in real time, and the size can be designed to be 0.5m×0.5m×0.8m. The size of the emergency medicine cabinet 11 can be designed to be 1.4m×0.6m×1.7m. For example, tenecteplase needs to be stored away from light at a temperature below 25°C and should be used immediately after dissolution; if it is not used immediately, it should be stored in a dark place at 2~8°C and used within 24h. Alteplase needs to be stored away from light at a temperature below 25°C and should be used immediately after dissolution; if it is not used immediately, it should be stored in a dark place at 2~8°C and used within 24h.

[0046] Furthermore, a small emergency vehicle 13 is provided in the thrombolytic treatment area for rescuing patients in case of emergency. The size of the small emergency vehicle 13 can be designed to be 0.7m×0.5m×1.5m. Figure 5As shown, the medicines contained therein should be kept in a dark and airtight state below 20°C. A second 42-inch TV display screen 14 is also provided in the thrombolytic therapy area, which can display the contents of the comprehensive information monitoring display 1 in the information interaction area. A medical and domestic waste bin 15 is also provided in the thrombolytic therapy area for temporary placement of medical or domestic waste. The size of the waste bin 15 can be designed to be 0.45m×0.3m×0.3m. The thrombolytic therapy area is also provided with vital signs monitoring systems such as ECG monitoring and blood pressure monitoring, as well as genetic testing equipment, and the corresponding parameters can be displayed on the TV display screen / display in each area. A camera can also be installed in the thrombolytic therapy area to cooperate with the second TV display screen to realize online interconnection between doctors and patients and remote monitoring functions.

[0047] The thrombolytic treatment area is also equipped with a new generation of thrombolytic drugs and other necessary medicines, and the medication regimen is quickly confirmed through drug gene testing. Based on the non-invasive rapid gene typing detector for drug metabolism genes such as CYP2C19, doctors or nurses use oral swabs to collect oral mucosal exfoliated cells from patients to detect the typing of genes such as CYP2C19 (key gene for clopidogrel metabolism), CYP2C9 (key gene for warfarin metabolism), and VKORC (key gene for warfarin metabolism). The results are automatically transmitted to the AI-assisted decision-making system. Based on the typing of key genes for drug metabolism, the effectiveness and safety of various medications for patients are preliminarily judged and treatment recommendations are given. For example, the CYP2C19 gene carries or For patients with the allele who need dual antiplatelet therapy, clopidogrel may be metabolized intermediately or slowly, which will affect its effectiveness. In the absence of contraindications to ticagrelor, ticagrelor may need to be used instead.

[0048] The regional integrated emergency stroke unit of the present invention is an original integrated unit for acute stroke treatment. It highly concentrates the traditional organizational management of acute stroke into one space, adds innovative solutions, and forms three major areas: information interaction area, imaging examination area, and thrombolytic treatment area. It is expected to compress the time from the patient's arrival at the hospital to reperfusion treatment to less than 20 minutes, and assist medical staff, patients and their families in obtaining high-quality diagnosis and treatment medical experience. After the patient arrives at the hospital, he or she first enters the imaging examination area of ​​the regional integrated ESU. The imaging examination area is equipped with intelligent wearable devices that can collect key information such as the patient's vital signs in real time. It is also equipped with a new low-field mobile magnetic resonance imaging device, which is small in size, light in weight, and mobile, and has low requirements for metal implants in patients, making it safer. The magnetic resonance operation interface is simple, and the package scanning setting is easy to master. The site requirements are low, and there is no need for patients to travel back and forth between the consulting room, scanning room, laboratory and treatment room, which is better than the traditional CT examination solution. The AI-assisted decision-making system has been added with an innovatively developed identification sequence, which can quickly identify cerebral hemorrhage and cerebral ischemia within one and a half minutes, so that patients with acute ischemic stroke can receive reperfusion therapy in the shortest time, save brain function, reduce disability rate, and improve long-term quality of life; through AI image high-definition processing technology, the resolution of brain images can be further improved, comparable to high-field strength nuclear magnetic images. The information interaction area adopts an integrated information system to realize the rapid entry of fully structured data, realize AI-assisted decision-making based on physical signs and imaging manifestations, and display key data in real time throughout the process, helping the medical team to make quick decisions. The information interaction area is also equipped with AI intelligent robots, which provide functions such as medical process explanation, treatment plan description, and signing of informed consent, assisting medical workers to improve communication efficiency. The thrombolytic treatment area can support online interconnection and remote monitoring between doctors and patients, and is equipped with a new generation of thrombolytic drugs and advanced thrombectomy devices. Bedside genetic testing equipment can quickly confirm antiplatelet treatment plans to maximize the clinical benefits of patients.

[0049] The regional integrated emergency stroke unit of the present invention, on the one hand, uses an intelligent interactive module to realize the rapid entry of fully structured information / data; on the other hand, uses an AI-assisted decision-making system to realize AI-assisted decision-making based on physical signs and imaging manifestations; on the other hand, it also displays key medical data in real time throughout the whole process through the TV display screen / display of each area. Through the seamless connection between the AI-assisted decision-making system and medical equipment, key medical data can be automatically collected and updated to reflect the patient's condition in real time. Among them, the key medical data include: wearable devices or point-of-care detection (Point-of-care) equipment, such as electrocardiographs, rapid blood glucose meters, blood pressure meters, and the test results of non-invasive rapid genotyping detectors for genes such as CYP2C19. Doctors or nurses connect chest lead and limb lead electrodes for patients to collect electrocardiograms. Doctors or nurses collect peripheral blood for patients to quickly test blood sugar. Doctors or nurses tie cuffs for patients to collect blood pressure values. Doctors or nurses collect oral mucosal exfoliated cells for patients to perform rapid typing tests on genes such as CYP2C19.

[0050] Among them, the full structured information / data is collected based on structured questions (multiple-choice questions) of the detection equipment and intelligent interactive modules, including: the test results of wearable devices or point-of-care detection equipment, such as electrocardiographs, rapid blood glucose meters, blood pressure meters, and CYP2C19 rapid genotyping detectors; the patient's symptoms of this illness (limb weakness, slurred speech, unclear vision, etc.), physical signs (whether there is muscle weakness, visual field loss, dysarthria, aphasia, etc.), and past medical history (whether there is a history of hypertension, a history of diabetes, etc.). The doctor collects the patient's medical history with the assistance of the intelligent interactive module, narrates and records the voice when collecting physical signs for the patient during the physical examination, and quickly enters the full structured information / data.

[0051] Physical signs refer to information obtained through physical examination. Imaging manifestations include whether there are intracranial ischemic lesions, whether there are intracranial hemorrhagic lesions, whether there is DWI / FLAIR imaging mismatch, whether there is intracranial large artery occlusion, etc. The AI-assisted decision-making system is used to automatically classify the causes of clinical diagnosis and treatment of cerebrovascular diseases, and provide recommendations for the next step of examination and treatment to assist doctors in making decisions.

[0052] The present invention uses artificial intelligence technology to build an integrated medical AI decision-making system. Doctors can get analysis results within a few minutes and quickly determine the treatment plan. The analysis results include: the patient's preliminary diagnosis (based on symptoms, signs, imaging manifestations, etc.), etiology classification (based on signs, past history, imaging manifestations, etc.), whether there is imaging mismatch (based on imaging manifestations), whether there is clinical-imaging mismatch (based on signs, scale scores, imaging manifestations, etc.), whether there is intracranial large artery occlusion (based on imaging manifestations), etc.

[0053] The AI-assisted decision-making system is also used to make treatment recommendations for various acute phase treatments in the clinical diagnosis and treatment of cerebrovascular diseases, especially the matching of indications and contraindications for reperfusion therapy.

[0054] The AI-assisted decision-making system can also automatically remind doctors that patients who meet the thrombolytic indications should be given rtPA or TNK treatment immediately and their vital signs should be continuously monitored. Patients who meet the indications for intravenous thrombolysis should immediately enter the informed consent process, and after obtaining the informed consent of the patient and their family members, they should be immediately given intravenous thrombolytic treatment under vital sign monitoring. Patients who are eligible for intravascular treatment should immediately enter the instructions for the intravascular treatment and rescue process. At the same time, the intelligent interactive module will immediately call the on-duty physician in the interventional department, and after the physician arrives, assist the physician in obtaining the informed consent of the patient and his family members, and transfer them to the catheterization room for intravascular treatment.

[0055] The present invention innovatively integrates the emergency room, laboratory, imaging examination room, pharmacy, etc. into a single space, and proposes the concept of integrated acute stroke unit. By integrating the information exchange area, imaging examination area and thrombolytic therapy area, the diagnosis and treatment route of acute ischemic stroke patients is highly centralized, and the delay of ischemic stroke patients after arriving at the hospital is compressed to the minimum. Of course, in actual application, the regional integration of acute stroke units can be expanded or reduced according to demand.

[0056] The regional integrated emergency stroke unit proposed in the present invention integrates the three major areas of information interaction area, imaging examination area and thrombolytic therapy area, integrates real-time vital signs monitoring, intelligent consultation, neurological specialist examination scoring, mobile magnetic resonance imaging, drug gene rapid detection and other functions, and creates an innovative and optimized in-hospital diagnosis and treatment system for acute ischemic stroke. Specifically, the ESU of the present invention uses the concept of acute stroke unit integration, integrates the various links of acute ischemic stroke patient triage, consultation, physical examination, laboratory tests, examinations, diagnosis and treatment plan formulation, and treatment, and is patient-centered, greatly reducing the patient's range of movement after the emergency. Suspected acute stroke patients enter the ESU and first come to the information interaction area, where the process support AI assistant 2 performs information entry, consultation, neurological examination and scale assessment; then come to the imaging examination area, where doctors or nurses complete electrocardiogram examinations, measure blood pressure, blood oxygen saturation, and peripheral blood sugar. The relevant information is entered into the process support AI assistant 2 of the information interaction area via voice or touch screen, and displayed on the TV display screen / display in each area. After the doctor confirms again that the patient has no contraindications to low-field mobile MRI scanning, the doctor performs a low-field mobile MRI scan on the patient, reads the film in real time during the scan, and makes a preliminary judgment on the condition. For patients who meet the indications for intravenous thrombolytic treatment, the doctor obtains preliminary informed consent for intravenous thrombolytic treatment from the patient's legal representative (family members, etc.). If the patient is conscious, after the scan is completed, the doctor introduces the risks and benefits of intravenous thrombolytic treatment to the patient himself to obtain informed consent. If the patient or his legal representative signs the informed consent for intravenous thrombolysis, the patient will be placed on the treatment bed (equipped for direct use when the patient visits the hospital; a treatment bed is required for patients who walk or enter in a wheelchair) and parked in the thrombolytic treatment area for intravenous thrombolytic treatment under ECG, blood pressure and clinical monitoring. Patients who do not meet the indications for intravenous thrombolytic treatment or refuse intravenous thrombolytic treatment will enter the routine diagnosis and treatment process, and the images and reports of the low-field mobile MRI scan can be queried in the medical PACS system.

[0057] The AI-assisted decision-making system used in the present invention improves the accuracy and speed of doctors' diagnosis, and provides a solution for quickly formulating accurate treatment plans. The mobile magnetic resonance imaging system uses artificial intelligence image analysis technology to significantly shorten the detection time, while improving the image quality, assisting doctors in distinguishing ischemia / hemorrhage, identifying the core infarction site and volume, identifying large artery occlusion and stenosis, and judging the duration of stroke patients after waking up, so as to quickly make treatment decisions. By integrating independent operating units, a complete set of regional integration of the examination, thrombolysis and further treatment processes of ischemic stroke patients is achieved, which minimizes the delay of ischemic stroke patients after arriving at the hospital, dissolves or removes thrombi as soon as possible, and restores reperfusion of brain tissue in the ischemic area, which can save more brain tissue and improve clinical prognosis. It has broad application prospects.

[0058] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A regional integrated emergency stroke unit, characterized in that: include: Information interaction area, imaging examination area and thrombolytic therapy area; The information interaction area is provided with a doctor's workstation, a comprehensive information monitoring display, and a process support AI assistant; the doctor's workstation includes a computer, a file rack, and a folding table; the computer is used for doctors to input information; the file rack is used to place documents; the folding table is used for temporary placement and storage of medical equipment and documents; the comprehensive information monitoring display is used to display the patient's basic information, arrival time, arrival time in the consulting room, and vital signs; the process support AI assistant is used to perform automatic medical consultation and assist in neurological scale scoring through voice interaction or touch screen typing interaction, and is also used to provide retrieval support for real-time knowledge base and clinical guidelines; The process supports the provision of an intelligent interaction module in the AI ​​assistant; the intelligent interaction module uses the structured medical records of the emergency department as a basis to ask structured questions about the patient's key medical information such as the onset time, symptoms, accompanying symptoms, past medical history, and allergy history, perform voice recognition on the patient's and / or his / her family's answers, and perform structured entry of key medical information; The intelligent interaction module is also used to perform auxiliary nervous system scale NIHSS scoring, ABCD2 scoring and pre-onset mRS scoring through voice interaction or touch screen typing interaction with the patient and / or his / her family members to obtain the scale scoring results; The intelligent interaction module also stores a large language model; the large language model is provided with a knowledge base related to clinical diagnosis and treatment of stroke, including clinical scales, acute phase guidelines for cerebral infarction, secondary prevention guidelines for cerebral infarction, diagnosis and treatment guidelines for cerebral hemorrhage, and clinical diagnosis and treatment guidelines for subarachnoid hemorrhage; during the diagnosis and treatment process, the knowledge base and clinical guidelines can be retrieved through voice interaction with the doctor or touch screen typing interaction; The imaging examination area is provided with a detection device, a first television display screen, a low-field movable magnetic resonance imager and an AI-assisted decision-making system; the detection device is used to perform electrocardiogram examinations, drug gene testing, and monitor the patient's blood oxygen saturation, blood pressure, and peripheral blood glucose to obtain test results; the first television display screen is used to enlarge and display the content of the comprehensive information monitoring display; the low-field movable magnetic resonance imager is used to perform head and neck magnetic resonance imaging of the patient; the AI-assisted decision-making system is respectively communicated with the comprehensive information monitoring display, the process support AI assistant, the detection device, the first television display screen and the low-field movable magnetic resonance imager; the AI-assisted decision-making system is used to make auxiliary decisions based on the automatic consultation results, scale scoring results, test results and head and neck magnetic resonance imaging results, generate and display treatment plans; The thrombolytic therapy area is equipped with a small refrigerator, an emergency medicine cabinet and a storage cabinet for storing medicines, reagents and emergency medicines with different temperature requirements; the thrombolytic therapy area is also equipped with an emergency vehicle and a vital signs monitoring system; the emergency vehicle is used to rescue patients in emergency medical situations; the vital signs monitoring system is used to monitor and display the patient's vital signs in real time; The thrombolytic treatment area is also equipped with a new generation of thrombolytic drugs and essential medicines, and the medication plan is confirmed through drug gene testing; based on a non-invasive rapid gene typing detector, the typing of CYP2C19, CYP2C9, and VKORC genes is detected, and the results are automatically transmitted to the AI-assisted decision-making system. According to the typing of key genes for drug metabolism, the effectiveness and safety of various medications for patients are preliminarily judged and treatment recommendations are given.

2. The regional integrated emergency stroke unit according to claim 1, characterized in that: The intelligent interaction module is also used to provide medical process explanations and treatment plan instructions and to sign informed consent forms through voice interaction or touch screen typing interaction with the patient and / or his / her family members.

3. The regional integrated emergency stroke unit according to claim 1, characterized in that: The detection equipment includes an electrocardiograph, a wearable electrocardiograph monitor, a finger-clip oximeter, a sphygmomanometer, a blood glucose meter, and a non-invasive rapid genotyping detector.

4. The regional integrated emergency stroke unit according to claim 1, characterized in that: The low-field movable magnetic resonance imager is integrated with a mobile magnetic resonance imaging system; the mobile magnetic resonance imaging system is based on a deep learning image reconstruction method, and utilizes the patient's low-field and high-field MRI data sets to achieve image super-resolution reconstruction to obtain head and neck magnetic resonance imaging results.

5. The regional integrated emergency stroke unit according to claim 4, characterized in that: The AI-assisted decision-making system is used to use a deep learning method to identify the site of acute cerebral infarction lesions in the head and neck magnetic resonance imaging results and automatically calculate the infarction volume; the AI-assisted decision-making system is also used to determine whether the patient has intracranial large artery occlusion / stenosis through the MRA sequence of mobile magnetic resonance imaging; the AI-assisted decision-making system is also used to use automatic registration technology to align different sequences to a standard space, to achieve automated identification of DWI / FLAIR mismatches in acute cerebral infarction lesions, to determine the approximate onset time of stroke after awakening, and to guide reperfusion therapy.

6. The regional integrated emergency stroke unit according to claim 5, characterized in that: The AI-assisted decision-making system is also used to combine the image interpretation information with the scale scoring results to determine whether the patient has a clinical-imaging mismatch, and combined with the infarct volume, to assist in deciding whether the patient needs intravascular treatment to achieve intracranial reperfusion.

7. The regional integrated emergency stroke unit according to claim 1, characterized in that: The thrombolytic therapy area is also provided with a second TV display screen and a trash can; the second TV display screen is used to display the contents of the comprehensive information monitoring display; the trash can is used to temporarily place medical or domestic waste.

Images