CN117577301B - Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest - Google Patents
Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest Download PDFInfo
- Publication number
- CN117577301B CN117577301B CN202311545097.XA CN202311545097A CN117577301B CN 117577301 B CN117577301 B CN 117577301B CN 202311545097 A CN202311545097 A CN 202311545097A CN 117577301 B CN117577301 B CN 117577301B
- Authority
- CN
- China
- Prior art keywords
- blood flow
- cardiac arrest
- unit
- patient
- heart
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 208000010496 Heart Arrest Diseases 0.000 title claims abstract description 161
- 230000017531 blood circulation Effects 0.000 claims abstract description 251
- 238000001228 spectrum Methods 0.000 claims abstract description 151
- 238000002680 cardiopulmonary resuscitation Methods 0.000 claims abstract description 107
- 238000003745 diagnosis Methods 0.000 claims abstract description 75
- 238000011156 evaluation Methods 0.000 claims abstract description 69
- 230000000694 effects Effects 0.000 claims abstract description 67
- 238000004458 analytical method Methods 0.000 claims abstract description 61
- 210000001715 carotid artery Anatomy 0.000 claims abstract description 47
- 206010049418 Sudden Cardiac Death Diseases 0.000 claims abstract description 38
- 208000014221 sudden cardiac arrest Diseases 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000002685 pulmonary effect Effects 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 17
- 210000002216 heart Anatomy 0.000 claims description 129
- 210000004072 lung Anatomy 0.000 claims description 59
- 230000000747 cardiac effect Effects 0.000 claims description 58
- 239000000523 sample Substances 0.000 claims description 58
- 210000001765 aortic valve Anatomy 0.000 claims description 42
- 210000004115 mitral valve Anatomy 0.000 claims description 32
- 238000002604 ultrasonography Methods 0.000 claims description 32
- 230000006835 compression Effects 0.000 claims description 25
- 238000007906 compression Methods 0.000 claims description 25
- 238000010801 machine learning Methods 0.000 claims description 24
- 230000008602 contraction Effects 0.000 claims description 21
- 230000000630 rising effect Effects 0.000 claims description 21
- 230000002861 ventricular Effects 0.000 claims description 21
- 230000033001 locomotion Effects 0.000 claims description 18
- 210000001174 endocardium Anatomy 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000001575 pathological effect Effects 0.000 claims description 14
- 239000008280 blood Substances 0.000 claims description 13
- 210000004369 blood Anatomy 0.000 claims description 13
- 230000002792 vascular Effects 0.000 claims description 11
- 208000010378 Pulmonary Embolism Diseases 0.000 claims description 9
- 201000003144 pneumothorax Diseases 0.000 claims description 9
- 230000001154 acute effect Effects 0.000 claims description 7
- 210000005240 left ventricle Anatomy 0.000 claims description 7
- 238000013441 quality evaluation Methods 0.000 claims description 7
- 208000005228 Pericardial Effusion Diseases 0.000 claims description 6
- 208000010125 myocardial infarction Diseases 0.000 claims description 6
- 210000003516 pericardium Anatomy 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000004217 heart function Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000002612 cardiopulmonary effect Effects 0.000 claims description 3
- 210000005241 right ventricle Anatomy 0.000 claims description 3
- 210000001367 artery Anatomy 0.000 claims description 2
- 210000004379 membrane Anatomy 0.000 claims description 2
- 239000012528 membrane Substances 0.000 claims description 2
- 238000012856 packing Methods 0.000 claims description 2
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 238000004148 unit process Methods 0.000 claims 3
- 206010054949 Metaplasia Diseases 0.000 claims 1
- 230000015689 metaplastic ossification Effects 0.000 claims 1
- 238000001303 quality assessment method Methods 0.000 claims 1
- 230000004083 survival effect Effects 0.000 abstract description 6
- 238000004393 prognosis Methods 0.000 abstract description 5
- 210000005036 nerve Anatomy 0.000 abstract description 4
- 238000013145 classification model Methods 0.000 description 13
- 238000012544 monitoring process Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 9
- 230000010412 perfusion Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000003825 pressing Methods 0.000 description 8
- 230000003205 diastolic effect Effects 0.000 description 7
- 230000002269 spontaneous effect Effects 0.000 description 6
- 230000002537 thrombolytic effect Effects 0.000 description 6
- 208000032843 Hemorrhage Diseases 0.000 description 5
- 239000000853 adhesive Substances 0.000 description 5
- 230000001070 adhesive effect Effects 0.000 description 5
- 230000000740 bleeding effect Effects 0.000 description 5
- 230000010354 integration Effects 0.000 description 5
- 238000013146 percutaneous coronary intervention Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 210000000038 chest Anatomy 0.000 description 4
- 230000004087 circulation Effects 0.000 description 4
- 238000001802 infusion Methods 0.000 description 4
- 230000003601 intercostal effect Effects 0.000 description 4
- 230000010349 pulsation Effects 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 230000002441 reversible effect Effects 0.000 description 4
- 208000006017 Cardiac Tamponade Diseases 0.000 description 3
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 3
- 206010052428 Wound Diseases 0.000 description 3
- 238000004159 blood analysis Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 208000014674 injury Diseases 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 229910052700 potassium Inorganic materials 0.000 description 3
- 239000011591 potassium Substances 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 230000033764 rhythmic process Effects 0.000 description 3
- 230000008733 trauma Effects 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 102000001554 Hemoglobins Human genes 0.000 description 2
- 108010054147 Hemoglobins Proteins 0.000 description 2
- 206010021137 Hypovolaemia Diseases 0.000 description 2
- 206010000891 acute myocardial infarction Diseases 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 210000005242 cardiac chamber Anatomy 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000004064 dysfunction Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- JVTAAEKCZFNVCJ-UHFFFAOYSA-N lactic acid Chemical compound CC(O)C(O)=O JVTAAEKCZFNVCJ-UHFFFAOYSA-N 0.000 description 2
- 210000003205 muscle Anatomy 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000005180 public health Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000009885 systemic effect Effects 0.000 description 2
- 238000010863 targeted diagnosis Methods 0.000 description 2
- 210000000534 thyroid cartilage Anatomy 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- CYDQOEWLBCCFJZ-UHFFFAOYSA-N 4-(4-fluorophenyl)oxane-4-carboxylic acid Chemical compound C=1C=C(F)C=CC=1C1(C(=O)O)CCOCC1 CYDQOEWLBCCFJZ-UHFFFAOYSA-N 0.000 description 1
- 208000010444 Acidosis Diseases 0.000 description 1
- 206010014418 Electrolyte imbalance Diseases 0.000 description 1
- 238000012351 Integrated analysis Methods 0.000 description 1
- 206010061307 Neck deformity Diseases 0.000 description 1
- 208000008589 Obesity Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 1
- 230000007950 acidosis Effects 0.000 description 1
- 208000026545 acidosis disease Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000010009 beating Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 230000036471 bradycardia Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 210000003109 clavicle Anatomy 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 210000002808 connective tissue Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003748 differential diagnosis Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000010247 heart contraction Effects 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 230000023597 hemostasis Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 208000028867 ischemia Diseases 0.000 description 1
- 239000004310 lactic acid Substances 0.000 description 1
- 235000014655 lactic acid Nutrition 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 210000004165 myocardium Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 235000020824 obesity Nutrition 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 239000001540 sodium lactate Substances 0.000 description 1
- 229940005581 sodium lactate Drugs 0.000 description 1
- 235000011088 sodium lactate Nutrition 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000007371 visceral function Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30048—Heart; Cardiac
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Business, Economics & Management (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to the technical field of digital medical treatment, and discloses an off-hospital emergency system for automatic identification and intelligent auxiliary decision of cardiac arrest, wherein an intelligent identification unit for cardiac arrest firstly judges whether cardiac arrest occurs according to carotid artery blood flow spectrum images of patients acquired by a carotid artery blood flow spectrum acquisition unit, then an intelligent analysis unit for cardiac arrest analyzes possible reasons of cardiac arrest of the patients according to ultrasonic images and pulmonary ultrasonic images of the patients acquired by an ultrasonic image acquisition unit, and a diagnosis and treatment suggestion unit generates and outputs diagnosis and treatment suggestions according to the possible reasons output by the cardiac arrest analysis unit; and simultaneously, in the process of first aid, the cardiopulmonary resuscitation effect evaluation unit can evaluate the cardiopulmonary resuscitation effect in real time. The invention can rapidly and accurately rescue patients suffering from sudden cardiac arrest outside the hospital, and greatly improve the survival rate and the prognosis of the nerve function of the patients.
Description
Technical Field
The invention relates to the technical field of digital medical treatment, in particular to an off-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest.
Background
Sudden cardiac arrest (CARDIAC ARREST, CA) is a serious public health problem seriously threatening the life health of people, has the characteristics of high incidence rate, high death rate and high disability rate, directly affects the stability of families, and seriously increases social burden and resource consumption. According to the report 2022 edition of Chinese cardiac arrest and cardiopulmonary resuscitation, the overall incidence rate of the cardiac arrest in China has an ascending trend compared with the incidence rate before 10 years, the incidence rate of the cardiac arrest in hospital is 105 ten thousand per year, the discharge survival rate is only 1.15%, and particularly the on-site spontaneous circulation recovery (return of spontaneous circulation, ROSC) rate is only 12.1%. The reasons for influencing the success rate of the cardiopulmonary resuscitation outside the hospital are mainly as follows: 1) The capability of on-site emergency personnel is greatly different; 2) The accuracy of manually identifying the sudden cardiac arrest is not high; 3) The quality of chest cardiac compressions is difficult to ensure, or high quality compressions are difficult to sustain; 4) On site, it is difficult to rapidly identify the cause of reversible sudden cardiac arrest.
The invention patent publication CN110459328a discloses a clinical decision support system for assessing cardiac arrest, comprising: the information acquisition module is used for acquiring clinical or non-clinical data of a patient in real time; the input/output module is used for providing a user interface for a user, receiving a user instruction or displaying content to the user; the information processing module is used for switching a plurality of input units in the information acquisition module to acquire clinical or non-clinical data of a patient according to an input instruction of the input/output module; the method comprises the steps of using an electronic health record of a patient to carry out data cleaning on structured data; the method is used for constructing a neural network model based on a genetic algorithm, and performing prospective queue verification on the neural network model; the system is used for evaluating the patient data acquired in real time based on the training of the existing hospital cardiac arrest training data and outputting early warning information to the input/output module. The device has high early warning precision, and can be used as auxiliary equipment for more effectively and accurately executing differential diagnosis of the sudden cardiac arrest in the hospital by rescue personnel.
The patient for which the above-mentioned comparison document aims at is a patient suffering from sudden cardiac arrest in a hospital, and the cause of sudden cardiac arrest is judged by combining the patient history information, case information, cardiac CT and the like, but the comparison document is not applicable to a patient suffering from sudden cardiac arrest outside a hospital, has limited conditions outside a hospital, cannot obtain complete medical history information and automatically extract, and is more unlikely to implement cardiac CT for the patient. Therefore, the application range and the application scene of the technology have larger limitations.
Disclosure of Invention
In order to solve the problems and the defects in the prior art, the invention provides an external hospital emergency system for automatic identification and intelligent auxiliary decision of cardiac arrest, which is used for collecting carotid blood flow spectrum, cardiac ultrasound and pulmonary ultrasound of a patient in real time, firstly rapidly identifying whether the cardiac arrest occurs or not based on the carotid blood flow spectrum of the patient, then identifying the cause of the cardiac arrest through the cardiac ultrasound and the pulmonary ultrasound of the patient, and finally timely providing corresponding diagnosis and treatment advice according to the cause of the cardiac arrest. The whole emergency system is suitable for patients suffering from sudden cardiac dysfunction in or out of a hospital, has no limit requirement on the use scene, can rapidly and accurately rescue the patients, and greatly improves the survival rate and the nerve function prognosis of the patients suffering from sudden cardiac arrest.
In order to achieve the above object, the technical scheme of the present invention is as follows:
The invention provides an extra-hospital first-aid system for automatic identification and intelligent auxiliary decision-making of cardiac arrest, which mainly comprises a carotid artery blood flow spectrum acquisition unit, an ultrasonic image acquisition unit, an intelligent cardiac arrest identification unit, an intelligent cardiac arrest analysis unit, a diagnosis and treatment suggestion unit, a cardiopulmonary resuscitation effect evaluation unit and a diagnosis and treatment diversion unit; the main functions and roles of each functional module in the system will be further explained below.
1. Carotid blood flow spectrum acquisition unit
The carotid blood flow spectrum acquisition unit mainly comprises a paste type vascular ultrasonic probe, and the probe is stuck to the level position of the patient's thyroid cartilage and the inner side of the sternocleidomastoid muscle of a patient when in use, is used for acquiring carotid blood flow spectrum images of the patient in real time and transmitting acquired image data to the intelligent cardiac arrest identification unit.
2. Ultrasonic image acquisition unit
The ultrasonic image acquisition unit mainly comprises a heart ultrasonic image acquisition module and a lung ultrasonic image acquisition module; the heart ultrasonic image acquisition module comprises a transthoracic heart ultrasonic probe or a transesophageal heart ultrasonic probe, when the heart ultrasonic image acquisition module is a transthoracic heart ultrasonic probe, the heart ultrasonic image acquisition module can be fixed on a patient in a pasting or wearable mounting mode, and if the pasting type probe is used in general, the probe is pasted at a fifth intercostal position of a left collarbone midline; when the patient is a patient with an artificial airway established, the probe is typically a transesophageal heart ultrasound probe that is secured to the patient using an esophageal placement type of mounting. By the heart ultrasonic probe, ultrasonic images of a plurality of different sections of a heart of a patient can be dynamically obtained;
the lung ultrasonic image acquisition module generally comprises a paste type lung ultrasonic probe, and the probe is stuck to a second intercostal position of a double-sided collarbone midline when in use and is used for acquiring an ultrasonic image of the lung.
3. Intelligent identification unit for cardiac arrest
The intelligent heart sudden stop identification unit is connected with the carotid artery blood flow spectrum acquisition unit, and is used for acquiring and transmitting the carotid artery blood flow spectrum image of the patient according to the carotid artery blood flow spectrum acquisition unit, processing and analyzing the image, calculating to obtain the current blood flow parameter of the patient, judging the heart output condition of the patient, carrying out severity risk classification according to the heart output condition of the patient, and identifying whether the heart sudden stop of the patient occurs according to the classified risk classification; and then the intelligent cardiac arrest identification unit sends the judged risk level of the current cardiac output condition of the patient to the diagnosis and treatment suggestion unit and the cardiopulmonary resuscitation effect evaluation unit respectively, and simultaneously sends the current blood flow parameters of the patient to the cardiopulmonary resuscitation effect evaluation unit.
4. Intelligent analysis unit for cardiac arrest
The intelligent cardiac arrest analysis unit is connected with the cardiac and pulmonary ultrasonic image acquisition unit, processes and analyzes the images according to the ultrasonic images of the patient's heart and the pulmonary ultrasonic images acquired and transmitted by the cardiac and pulmonary ultrasonic image acquisition unit, calculates corresponding motion conditions, blood flow rate, velocity time integral values and basic pathological feature results of the lung of the patient's heart intima and required specific parts, further analyzes possible causes of cardiac arrest of the patient based on the parameters and the basic pathological feature results of the lung, and outputs the causes to the diagnosis and treatment suggestion unit.
5. Diagnosis and treatment suggestion unit
The diagnosis and treatment suggestion unit is respectively connected with the cardiac arrest intelligent recognition unit and the cardiac arrest intelligent analysis unit, and generates and outputs corresponding diagnosis and treatment suggestions according to the patient risk level sent by the cardiac arrest intelligent recognition unit and the cardiac arrest possible reasons output by the cardiac arrest intelligent analysis unit.
6. Cardiopulmonary resuscitation effect evaluation unit
The cardiopulmonary resuscitation effect evaluation unit is connected with the cardiac arrest intelligent recognition unit, evaluates the cardiopulmonary resuscitation effect according to the risk level and the current blood flow parameters of the patient sent by the cardiac arrest intelligent recognition unit, and outputs an evaluation result.
7. Diagnosis and treatment shunt unit
The diagnosis and treatment shunt unit is connected with the diagnosis and treatment suggestion unit, and shunts patients to a medical institution for treatment capable of executing the diagnosis and treatment suggestion according to the diagnosis and treatment suggestion output by the diagnosis and treatment suggestion unit.
In the invention, the emergency system can be externally connected with equipment such as an electrocardiograph monitor, a blood analyzer, a POC ultrasonic probe and the like, and can assist in realizing automatic identification of cardiac arrest of a patient, analysis of reasons of cardiac arrest, evaluation of cardiopulmonary resuscitation effect and the like by monitoring and collecting indexes such as physiological parameters, blood pH value parameters and the like of the patient in real time, screening non-open wound bleeding parts of the patient and the like.
The invention has the beneficial effects that:
the invention has wide application prospect and market potential as an innovative medical technology, and is mainly embodied in the following aspects:
(1) The invention can realize rapid identification of cardiac arrest and analysis of possible causes of cardiac arrest based on carotid artery blood flow spectrum images and heart and lung ultrasonic images of patients after processing and analyzing the images, can play a role in guiding behaviors, and can provide guidance for medical staff, especially medical staff with insufficient experience. Specifically, for the continuous monitoring of high risk crowd or under the high risk state, this system can help medical personnel to judge whether the patient takes place the sudden cardiac arrest and send out the alarm in the first time to can help the first time to start cardiopulmonary resuscitation, reduce the time spent on judging because of experience difference leads to, avoid delaying the start of cardiopulmonary resuscitation, thereby improve the person's of being examined prognosis. Meanwhile, the cause can be judged by the cause to help medical staff find the cause at the first time, and a treatment thought is provided for the corresponding medical staff.
(2) The invention can realize rapid identification of cardiac arrest and analysis of possible causes of cardiac arrest by directly collecting carotid artery blood flow spectrum images and heart and lung ultrasonic images of patients in real time and processing and analyzing the images without depending on the medical history information, case information, heart CT and other data of the patients. Therefore, the whole emergency system has no limit requirement on the use scene, is particularly suitable for the hospital-external cardiac arrest patients who do not know the medical history information and case information and cannot obtain cardiac CT, is expected to improve the on-site emergency success rate of OHC (hospital-external cardiac arrest) patients, reduces the subsequent treatment difficulty, thereby reducing the death rate and disability rate of OHC and greatly improving the survival rate and the nerve function prognosis of the cardiac arrest patients.
(3) The invention integrates the cardiopulmonary resuscitation effect evaluation unit for evaluating the quality of cardiopulmonary resuscitation in the rescue process, so as to ensure the effectiveness of each cardiopulmonary resuscitation as much as possible, ensure enough organ perfusion, and meet the perfusion of the whole body organs, especially heart and brain, so as to reduce disability rate and reduce social burden.
(4) According to the invention, various parameters and characteristics are obtained through the acquisition, identification and calculation of the heart ultrasonic image, the blood flow Doppler image and the lung ultrasonic image, and the possible cause of the cardiac arrest is comprehensively analyzed through the mutual coordination of the parameters and the characteristics, so that the identification accuracy is high. Particularly in the analysis process of possible causes of sudden cardiac arrest, lung ultrasonic is utilized to judge the pathological physiological performance of the lung to identify whether the pulmonary is tension pneumothorax and assist in judging acute pulmonary embolism, so that the etiology analysis is more comprehensive and accurate, large-scale pulmonary imaging equipment such as chest CT and chest radiography is not relied on, related information can be acquired in real time, the real-time judgment can be realized, and classification of severity of illness and patient diversion can be assisted.
(5) In the process of identifying whether the heart of a patient is suddenly stopped or not and evaluating the cardiopulmonary resuscitation effect by using ultrasound, the comprehensive judgment can be performed by using the main evaluation parameters, when the main evaluation parameters cannot be identified, the auxiliary judgment can be performed by using the auxiliary evaluation parameters, the phenomenon that the heart of the patient cannot be identified or evaluated is avoided, and the identification result and the evaluation are more accurate.
Drawings
The foregoing and the following detailed description of the invention will become more apparent when read in conjunction with the following drawings in which:
FIG. 1 is a diagram of the system of the present invention.
Detailed Description
In order for those skilled in the art to better understand the technical solution of the present invention, the technical solution for achieving the object of the present invention will be further described through several specific embodiments, and it should be noted that the technical solution claimed in the present invention includes, but is not limited to, the following embodiments. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, based on the embodiments of the present invention shall fall within the scope of protection of the present invention.
Sudden cardiac arrest (CARDIAC ARREST, CA) is a serious public health problem seriously threatening the life health of people, has the characteristics of high incidence rate, high death rate and high disability rate, directly affects the stability of families, and seriously increases social burden and resource consumption. According to the report 2022 edition of Chinese cardiac arrest and cardiopulmonary resuscitation, the overall incidence rate of the cardiac arrest in China has an ascending trend compared with the incidence rate before 10 years, the incidence rate of the cardiac arrest in hospital is 105 ten thousand per year, the discharge survival rate is only 1.15%, and particularly the on-site spontaneous circulation recovery (return of spontaneous circulation, ROSC) rate is only 12.1%.
The reasons that affect the success rate of off-hospital cardiac arrest CARDIAC ARREST (OHCA) on-site resuscitation are mainly:
1) The accuracy of manually identifying cardiac arrest is not high. Carotid pulse and spontaneous respiratory status are the primary means of judging cardiac arrest at present, but the report of the european resuscitation council shows that the emergency personnel has only 60% accuracy in recognizing the disappearance of pulse pulses within 10 seconds. The medical staff can judge the carotid artery experience, touching carotid artery position, depth and tension, and the factors such as weak pulse, obesity, too short neck, edema and too slow heart rate of the patient can lead to inaccurate carotid artery pulsation judgment by the medical staff, and delay the starting time of CPR (CPR) implementation on the patient.
2) On site, it is difficult to rapidly identify the cause of reversible sudden cardiac arrest. The etiology of the sudden cardiac arrest is complex, including cardiac and non-cardiac, with acute myocardial infarction, large area pulmonary embolism, tension pneumothorax, severe hypovolemia and pericardial tamponade being reversible etiologies, rapid identification and treatment of reversible etiology being key to improving resuscitation effects. For example, if the etiology of the tension pneumothorax and the pericardium filling can be rapidly identified on site, the effective resuscitation can be realized by simple drainage; and the rapid identification of the causes of acute myocardial infarction, pulmonary embolism and the like is also helpful for on-site transportation decision. Under the prior art, effective information for judging the etiology of the OHC patients is difficult to obtain on site due to the stop of the heartbeat and the respiration of the patients.
3) The pressing effect is difficult to monitor in real time, and the pressing effect is poor possibly due to insufficient pressing depth, deviation of pressing parts and the like.
The existing emergency decision system for patients suffering from sudden cardiac arrest is mainly aimed at patients suffering from sudden cardiac arrest in a hospital, and the cause analysis and judgment of the sudden cardiac arrest are carried out by combining the medical history information, case information, cardiac CT and the like of the patients, and corresponding emergency means are implemented. Therefore, the application range and the application field of the existing technology have larger limitations.
Based on this, the embodiment of the invention particularly provides an external hospital emergency system for automatic identification and intelligent auxiliary decision of cardiac arrest, which is used for collecting carotid blood flow spectrum, cardiac ultrasound and pulmonary ultrasound of a patient in real time, firstly rapidly identifying whether the patient suffers from cardiac arrest or not according to the carotid blood flow spectrum of the patient, then identifying the cause of cardiac arrest through the cardiac ultrasound and pulmonary ultrasound of the patient, and finally timely providing corresponding diagnosis and treatment advice according to the cause of cardiac arrest. The whole emergency system is suitable for patients suffering from sudden cardiac dysfunction in or out of a hospital, has no limit requirement on the use scene, is particularly suitable for patients suffering from sudden cardiac arrest outside the hospital, is expected to improve the on-site emergency success rate of OHC (sudden cardiac arrest outside the hospital) patients, reduces the subsequent treatment difficulty, thereby reducing the death rate and disability rate of OHC, and greatly improving the survival rate and the nerve function prognosis of the patients suffering from sudden cardiac arrest.
Example 1
The embodiment discloses an extra-hospital first-aid system for automatic identification and intelligent auxiliary decision-making of cardiac arrest, which mainly comprises a carotid artery blood flow spectrum acquisition unit, an ultrasonic image acquisition unit, an intelligent cardiac arrest identification unit, an intelligent cardiac arrest analysis unit, a diagnosis and treatment suggestion unit, a diagnosis and treatment diversion unit and a cardiopulmonary resuscitation effect evaluation unit; wherein,
The carotid blood flow spectrum acquisition unit is used for acquiring carotid blood flow spectrum images of patients;
the heart and lung ultrasonic image acquisition unit is used for acquiring heart ultrasonic images and lung ultrasonic images of patients;
The heart sudden stop intelligent identification unit is connected with the carotid artery blood flow acquisition unit and is used for obtaining current blood flow parameters of a patient according to the carotid artery blood flow spectrum image of the patient, judging the heart output condition of the patient, carrying out severity risk classification according to the heart output condition of the patient, identifying whether the patient suffers from heart sudden stop or not, sending the corresponding risk classification to the diagnosis and treatment suggestion unit and the cardiopulmonary resuscitation effect evaluation unit, and simultaneously sending the current blood flow parameters of the patient to the cardiopulmonary resuscitation effect evaluation unit;
The intelligent cardiac arrest analysis unit is connected with the cardiac and pulmonary ultrasonic image acquisition unit and is used for acquiring corresponding motion conditions, blood flow rate, speed time integral values and basic pathological feature results of the lungs of the patient according to the cardiac ultrasonic image and the pulmonary ultrasonic image of the patient obtained by the cardiac and pulmonary ultrasonic image acquisition unit, analyzing possible causes of cardiac arrest of the patient based on the data and the pathological feature results of the lungs and outputting the possible causes to the diagnosis and treatment suggestion unit;
The diagnosis and treatment suggestion unit is connected with the cardiac arrest intelligent identification unit and the cardiac arrest intelligent analysis unit and is used for generating and outputting diagnosis and treatment suggestions of the heart of a patient according to the risk level sent by the cardiac arrest intelligent identification unit and the cardiac arrest reason output by the cardiac arrest intelligent analysis unit;
The cardiopulmonary resuscitation effect evaluation unit is connected with the cardiac arrest intelligent recognition unit and is used for evaluating the cardiopulmonary resuscitation effect according to the risk level sent by the cardiac arrest intelligent recognition unit and the current blood flow parameters of a patient and outputting an evaluation result;
The diagnosis and treatment shunting unit is connected with the diagnosis and treatment suggestion unit, and based on the diagnosis and treatment suggestions output by the diagnosis and treatment suggestion unit, medical institutions capable of implementing the corresponding diagnosis and treatment suggestions are output and patients are shunted to different medical institutions for treatment.
In some embodiments, the carotid blood flow spectrum acquisition unit generally includes a plurality of adhesive vascular ultrasonic probes, the probes are respectively adhered to the level of the patient's thyroid cartilage and the inner side of the sternocleidomastoid muscle, that is, the body surface position of the patient's carotid artery pulsation, collect ultrasonic carotid blood flow spectrum information of the patient in real time, and send the collected ultrasonic carotid blood flow spectrum information to the cardiac arrest intelligent recognition unit, where the cardiac arrest intelligent recognition unit displays the collected information in real time in the form of an image.
In the prior art, common vascular probe equipment is bigger, and when the image is acquired, the inspector needs to hold the probe for monitoring, if the real-time monitoring is needed, the inspector needs to hold the probe for inspection, and in the cardiopulmonary resuscitation process, the head and neck part needs to establish an artificial airway, keep the body position, observe and breathe, and the inspector occupies rescue space, so that the practicability is poor. If the monitoring is not performed in real time, the effect of cardiopulmonary resuscitation cannot be continuously monitored, and the intermittent examination can cause rescue interruption to influence the rescue effect. The adhesive probe can avoid the risks, can realize judgment of cardiac arrest of patients and evaluation of resuscitation quality by monitoring carotid artery frequency spectrum in a portable, real-time and continuous manner, and can avoid occupation of manpower and space, thereby being beneficial to implementation of cardiopulmonary resuscitation. However, the existing adhesive probe equipment can be used for collecting carotid frequency spectrum in real time, but cannot be used for carrying out artificial intelligent analysis and decision on the frequency spectrum.
In some embodiments, the ultrasound image acquisition unit comprises a cardiac ultrasound image acquisition module and a pulmonary ultrasound image acquisition module; the heart ultrasonic image acquisition module comprises a transthoracic heart ultrasonic probe or a transesophageal heart ultrasonic probe. When the heart ultrasonic image acquisition module is a transthoracic heart ultrasonic probe, the transthoracic heart ultrasonic image acquisition module can be fixed on a patient in a pasting type or wearable type installation mode, and if a pasting type probe is used in general, the probe is pasted at a fifth intercostal position of a left collarbone midline; when the heart ultrasonic image acquisition module is a transesophageal heart ultrasonic probe, the transesophageal heart ultrasonic probe can be fixed on a patient in an esophageal imbedded mounting mode. Through the heart ultrasonic probe, ultrasonic images of a plurality of different sections of a heart of a patient can be dynamically obtained, corresponding one-dimensional, two-dimensional, three-dimensional or four-dimensional heart images and blood flow Doppler images of aortic valves and mitral valves are obtained after frame-by-frame processing, and the images are classified and stored and then are transmitted to an ultrasonic image automatic identification and parameter calculation module. In this embodiment, a two-dimensional heart image is mainly formed. When a one-dimensional heart ultrasonic probe is adopted, namely a simple mode, the functions are further simplified. If the three-dimensional heart ultrasonic probe or the four-dimensional heart ultrasonic probe is used, the functions can be upgraded.
The one-dimensional heart ultrasound mainly identifies the contraction movement condition of the left chamber wall in real time; two-dimensional, three-dimensional and four-dimensional heart ultrasound mainly identifies the endocardium and the required specific part and the corresponding movement condition in real time; the heart ultrasonic probe is used for acquiring and detecting the blood flow Doppler of the aortic valve and the mitral valve, comprises the detection of a regular frequency spectrum and the measurement of a blood flow velocity and a velocity time integral value, and is combined with the opening and closing condition of the valve and the ventricular wall movement condition to form an index system so as to achieve the aim of monitoring.
The lung ultrasonic image acquisition module generally comprises a paste type lung ultrasonic probe, mainly a two-dimensional ultrasonic probe, wherein the probe is pasted at the second intercostal position of the central line of the double-side clavicle during use and is used for acquiring an ultrasonic image of the lung, and after frame-by-frame processing, a corresponding lung ultrasonic image is obtained, stored and then transmitted to the intelligent cardiac arrest analysis unit.
In some embodiments, for patients establishing an artificial airway, the transthoracic adhesive cardiac ultrasound probe may be supplemented with an oral placement miniTEE (transesophageal cardiac ultrasound probe) to provide poor monitoring, and during CPR, miniTEE may monitor compression effects continuously and visually, and instruct adjustment of the optimal compression site.
In some embodiments, the severity risk classification sequentially includes a first risk, a second risk, a third risk and a fourth risk from light to heavy, where the first risk to the third risk indicate that the patient is not currently suffering from cardiac arrest, but the cardiac output is reduced, and at this time, continuous observation of the patient is required, and the cause of the reduced patient output is screened omnidirectionally, so as to prevent the patient from developing cardiac arrest; the four-level risk indicates that the patient has experienced sudden cardiac arrest. The diagnosis and treatment suggestion unit can trigger work based on the risk early warning level information sent by the cardiac arrest intelligent identification unit, for example, when the system detects cardiac arrest of a patient, the diagnosis and treatment suggestion unit can immediately output diagnosis and treatment suggestions of cardiopulmonary resuscitation, medical staff needs to immediately implement cardiopulmonary resuscitation operation on the patient, and then the diagnosis and treatment suggestion unit can further output more targeted diagnosis and treatment suggestions to emergency personnel on site for emergency treatment according to possible reasons of the cardiac arrest output by the cardiac arrest intelligent analysis unit, so that targeted treatment and treatment of the patient are realized.
In some embodiments, the system may further include an early warning unit, where the early warning unit is connected to the cardiac arrest intelligent recognition unit, and the early warning unit includes four kinds of indicator lights with green, blue, yellow, and red colors, where the four kinds of indicator lights respectively correspond to the first-level risk, the second-level risk, the third-level risk, and the fourth-level risk output by the cardiac arrest intelligent recognition unit. The current state of the patient can be quickly and intuitively known by the green, blue, yellow and red color lamps of the early warning unit.
The system provided by the embodiment can be used for monitoring in an emergency state, in an intensive care process or under high risk. The method can rapidly analyze the ultrasonic frequency spectrum of the carotid artery of a patient and the identification results of the heart and the lung ultrasonic, comprehensively judge whether the heart is suddenly stopped and analyze the possible reasons of the sudden cardiac arrest according to the identification results, further output corresponding diagnosis and treatment suggestions and provide corresponding guidance for clinicians with insufficient experience.
Example 2
As a preferred embodiment of the present invention, the present embodiment is further detailed supplemented and explained on the basis of example 1, specifically as follows.
The heart sudden stop intelligent recognition unit generally comprises a carotid blood flow spectrum automatic recognition module, a comprehensive analysis risk classification module and a corresponding carotid blood flow spectrum image display module; the carotid blood flow spectrum image display module displays acquired information in real time in an image form after receiving ultrasonic carotid blood flow spectrum information of a patient transmitted by the vascular ultrasonic probe, and then the carotid blood flow spectrum automatic identification module identifies and processes the image according to the received carotid blood flow spectrum image of the patient to obtain relevant blood flow parameters and sends the relevant blood flow parameters to the comprehensive analysis risk classification module;
The comprehensive analysis risk classification module is used for assisting in judging the carotid artery pulsation condition and the blood flow state according to the related blood flow parameters, so that the heart output condition of a patient is judged, the severity risk classification is carried out, and whether the patient suffers from sudden cardiac arrest or not is automatically identified.
Further, the relevant blood flow parameters include systolic blood flow peak velocity, end diastole blood flow velocity, area under the blood flow spectrum curve, curve rising slope, curve falling slope and resistance index.
The above blood flow parameters are specifically as follows:
Peak systolic flow velocity refers to the fastest speed of the carotid artery when it is contracting. This is used for blood flow parameters because heart rhythm and heart output states can be objectively presented when the blood vessels are free of obvious structural abnormalities.
End diastole blood flow velocity refers to the velocity of the carotid artery at end diastole. This is used for blood flow parameters because heart rhythm and heart output states can be objectively presented when the blood vessels are free of obvious structural abnormalities.
The area under the blood flow spectrum curve is to measure the carotid blood flow velocity time integral VTI from the arterial spectrum corresponding to a plurality of continuous cardiac cycles of the carotid artery in a set period of time according to the velocity time integral of boundary trace of the carotid artery spectrum, and calculate the peripheral arterial forward blood flow vti×csa by combining the carotid artery cross-sectional area CSA. This is used for blood flow parameters because it can determine cardiac output by assessing carotid blood flow.
The rising slope of the curve refers to the ratio of the difference in velocity to the difference in time during the rise in blood flow velocity. It is used for blood flow parameters because it can assess the vascular resistance of the carotid artery. The specific calculation formula is as follows:
The curve falling slope refers to the ratio of the speed difference to the time difference during the blood flow speed falling. It is used for blood flow parameters because it can assess the vascular resistance of the carotid artery. The specific calculation formula is as follows:
The resistance index refers to a parameter representing vascular resistance calculated from carotid blood flow velocity. The blood flow parameters are used because they can evaluate vascular resistance when the vessel is free of obvious structural abnormalities. The specific calculation formula is as follows:
The severity of a condition of cardiac output in a patient is graded, typically according to the blood flow parameters of the patient: the method for classifying risk comprises six parameters including systolic blood flow peak speed, end diastole blood flow speed, area under a blood flow spectrum curve, curve rising slope, curve falling slope and resistance index, and specifically comprises the following steps:
First-order risk: the heart output is shown by the fact that the blood flow is 30% or more lower than the normal value and the blood flow frequency spectrum is irregular in the systolic period and the diastolic period, the cardiac output is 30% or less lower than the normal value, the rising slope of the curve and the falling slope of the curve are 30% or less lower than the normal value, the resistance index is 30% or less higher than the normal value, the carotid frequency spectrum is needed to be monitored in real time, and the reason for the reduction of the cardiac output is screened.
Secondary risk: the heart output is shown to be obviously less than normal heart output, special assessment on heart functions is needed to be carried out immediately, and if necessary, intervention is carried out.
Three-level risk: the heart flow has systolic blood flow only, diastolic blood flow/blood flow frequency spectrum is irregular, cardiac output is 50% or more lower than normal value, curve rising slope and curve falling slope are 50% or more lower than normal value, resistance index is equal to 1, cardiac output is represented, but the phenomenon of insufficient cardiac output is represented, cardiac muscle further ischemia can be caused due to the fact that diastolic heart does not output and coronary artery blood supply is insufficient, cardiac arrest can occur at any time, cardiac function needs to be further evaluated and intervention needs to be carried out, and carotid blood flow frequency spectrum needs to be closely concerned.
Four-stage risk: the heart-lung resuscitation device comprises no blood flow in both systolic phase and diastolic phase, and the rising slope, the falling slope and the resistance index of the curve can not be measured, so that the heart of a patient has no effective beat, cardiac arrest has occurred, and cardiopulmonary resuscitation is required to be immediately carried out.
In some embodiments, screening for decreased cardiac output may also be accomplished with the aid of a cardiac ultrasound probe that can visually see if cardiac function is normal (observe heart beating) to determine if decreased cardiac output is due to decreased cardiac output; the heart ultrasonic probe can also judge whether the cardiac output is reduced due to insufficient capacity according to the size of the heart cavity; the heart ultrasonic probe can also see whether the cardiac output is reduced due to the reasons such as pericardial effusion; the pulmonary ultrasound probe can assess whether there is a tension pneumothorax, resulting in a decrease in cardiac output.
The cardiac arrest intelligent recognition unit adopts a machine learning mode to process data, and the machine learning comprises the following steps:
The adhesive vascular ultrasonic probe collects ultrasonic carotid artery blood flow spectrum information of a patient and sends the ultrasonic carotid artery blood flow spectrum information to the intelligent cardiac arrest identification unit, and a qualified doctor marks the collected carotid artery blood flow spectrum boundary and calculates systolic blood flow peak speed, end diastole blood flow speed, area under a blood flow spectrum curve, curve rising slope, curve falling slope and resistance index;
The carotid blood flow spectrum automatic identification module performs machine learning by comparing the artificially marked spectrum picture and original image, automatically identifies carotid blood flow spectrum, and automatically calculates systolic blood flow peak speed, end diastole blood flow speed, area under a blood flow spectrum curve, curve rising slope, curve falling slope and resistance index;
The comprehensive analysis risk classification module judges the cardiac output condition of the patient according to the calculated data and further classifies the severity risk according to the cardiac output condition;
Expert auditing is carried out on the effect of machine learning, and the machine learning is corrected by adopting a correction algorithm, so that a carotid blood flow spectrum automatic identification module for automatically identifying carotid blood flow spectrum and a comprehensive analysis risk classification module for automatically classifying the heart output reduction severity are formed.
In this embodiment, the carotid blood flow spectrum image display module not only can display the collected carotid blood flow spectrum image in real time, but also can output and display the blood flow parameters obtained by calculation of the carotid blood flow spectrum automatic identification module and the risk level output by the comprehensive analysis risk classification module in real time.
In this embodiment, for machine learning, a conventional machine learning method in the prior art, such as CNN image classification, is used to extract a desired image by subtracting frames from a video, cutting, and setting a region of interest. The correction algorithm of the same principle can also be used in the correction algorithm in the prior art. The main innovation point of the invention is not the study of machine learning and related algorithm, and all the main innovation points can adopt the prior art.
The carotid blood flow spectrum automatic identification module and the comprehensive analysis risk classification module perform data processing in a machine learning mode, wherein the machine learning comprises normal carotid blood flow spectrum learning, and the normal carotid blood flow spectrum learning comprises:
Collecting carotid artery blood flow spectrum of healthy volunteers for machine learning, training a machine to identify normal blood flow spectrum, and automatically generating systolic blood flow peak velocity, end diastole blood flow velocity, area under a blood flow spectrum curve, curve rising slope, curve falling slope and resistance index parameters; and checking the accuracy of the normal carotid blood flow learning parameters through expert examination.
The carotid blood flow spectrum automatic identification module and the comprehensive analysis risk classification module perform data processing in a machine learning mode, the machine learning comprises abnormal carotid blood flow spectrum learning, and the abnormal carotid blood flow spectrum learning comprises:
The clinical abnormal carotid blood flow spectrum is collected for machine learning, the machine is trained to identify the abnormal carotid blood flow spectrum, the heartbeat state of a patient is automatically identified according to abnormal conditions of systolic blood flow peak speed, end diastole blood flow speed, blood flow spectrum curve lower area, curve rising slope, curve falling slope and resistance index parameters, classification according to the spectrum severity is automatically identified and carried out, comparison is carried out with expert identification results and severity classification, and the accuracy of identification and severity classification of abnormal carotid blood flow is checked.
The intelligent identification unit for sudden cardiac arrest can process and automatically identify the image based on the carotid artery blood flow spectrum image of the patient transmitted by the carotid artery blood flow spectrum acquisition unit, and carry out risk classification on the severity of the current cardiac output condition of the patient according to the identification result, so that a doctor is assisted in rapidly identifying, analyzing and judging sudden cardiac arrest of the patient, on one hand, the diagnosis time is saved, the diagnosis efficiency is improved, the risk of the patient is reduced, on the other hand, the workload of the doctor is also reduced, the diagnosis quality is improved, interpretation errors caused by insufficient individual experience, special condition of the patient and objective condition limitation are avoided, the rescuing time of the patient is delayed, and the life of the patient is saved to the greatest extent.
Example 3
As another preferred implementation of the present invention, this example is based on example 1, and further detailed supplements and describes the intelligent analysis unit for cardiac arrest, as follows.
The heart sudden stop intelligent analysis unit generally comprises a heart and lung ultrasonic image automatic identification and parameter calculation module, a data integration analysis module and a corresponding heart and lung ultrasonic image display module; wherein,
The automatic heart and lung ultrasonic image recognition and parameter calculation module mainly has three functions, and is used for recognizing the endocardium and the required specific part and the corresponding movement condition in real time according to the heart ultrasonic image acquired by the heart ultrasonic probe; on the other hand, according to the blood flow Doppler images of the aortic valve and the mitral valve obtained by the heart ultrasonic probe, detection of a regular frequency spectrum and measurement of a blood flow rate and a velocity time integral value are realized; the last aspect is to identify the basic pathological feature result of the lung according to the lung ultrasonic image obtained by the lung ultrasonic probe;
the data integration analysis module is used for analyzing possible reasons for cardiac arrest of patients mainly according to corresponding motion conditions, blood flow rates, velocity time integral values and basic pathological feature results of lungs of the endocardium and required specific parts.
The heart and lung ultrasonic image display module can display ultrasonic images acquired by the heart ultrasonic probe and the lung ultrasonic probe in real time, and synchronously display parameters obtained by the ultrasonic image automatic identification and parameter calculation module and the cause of the cardiac arrest output by the data integration analysis module.
Further, the automatic heart and lung ultrasonic image recognition and parameter calculation module can also comprise an image preprocessing sub-module, an image classification sub-module and a parameter calculation sub-module; wherein,
The image preprocessing unit respectively preprocesses the heart images, the blood flow Doppler images and the lung ultrasonic images which are acquired in different sections to obtain heart ultrasonic images, blood flow Doppler images and lung ultrasonic images to be identified, and transmits the heart ultrasonic images, the blood flow Doppler images and the lung ultrasonic images to the image classification sub-module.
The pretreatment may be performed by conventional methods in the art, which is not limited in the present invention. For example, the heart ultrasound image and the blood flow Doppler image may be subjected to noise reduction and data enhancement processing, and the like. The noise reduction and data enhancement processing are performed by conventional technical means in the art, and the description of this embodiment is omitted. The lung ultrasonic image can be subjected to graying, normalization and the like.
The image classification submodule receives the heart ultrasonic image, the blood flow Doppler image and the lung ultrasonic image to be identified, and completes the setting, extraction and final classification identification of the region of interest through the built-in classification model. The classification model can be a neural network model, such as Inception V, resNet, leNet-5, and the like. The invention is not limited in this regard. The training method is also a conventional technical means in the field, and the invention is not limited thereto.
In this embodiment, the image classification sub-module may include a first classification model, a second classification model, and a third classification model. The first classification model is used for identifying endocardium and required specific parts according to input heart ultrasonic images to be identified, wherein the heart ultrasonic images comprise the edge of the endocardium of the left ventricle, the edge of the endocardium of the right ventricle, the epicardium, the root of the valve annulus of the free wall of the pericardium and the mitral valve, the outflow tract of the main artery, the mitral valve and the aortic valve. The second classification model may identify an aortic outflow tract in the blood flow doppler from the input blood flow doppler image to be identified. The third classification model can identify the basic pathological feature result of the lung, namely the identification of the basic pathological physiological change of the lung under ultrasonic representation, such as disappearance of A line, B line and pleural slip sign and lung actual change sign, according to the input lung ultrasonic image to be identified.
The first classification model and the second classification model may be integrated into one classification model, or may be separately applied to two classification models, which may be integrated or have information interaction (e.g., the identification of the first classification model to the aortic outflow tract may help the automatic positioning of blood flow detection), or separately applied (the blood flow detection position is manually positioned).
The parameter calculation sub-module is used for calculating the left endocardial area and the right endocardial area according to the marked endocardial border and the marked endocardial border in the left heart chamber and the right heart chamber, calculating the corresponding left endocardial shrinkage rate, and calculating the end diastole right ventricular area of the same cardiac cycle at the end diastole: ratio of left ventricular area. Wherein, left endocardial contraction rate= (left endocardial maximum area-left endocardial minimum area) in the same cardiac cycle/left endocardial maximum area x 100%.
The parameter calculation sub-module is also used for calculating the longitudinal contraction rate of the root of the mitral valve annulus according to the marked root of the mitral valve free wall annulus and is used as an auxiliary index for judging the later contraction state. The mitral valve opening rate is calculated according to the mitral valve opening condition, and the aortic valve opening rate is calculated according to the aortic valve opening condition. Wherein, mitral valve opening rate= (mitral valve cusp maximum distance-mitral valve root maximum distance) ×100%. Aortic valve opening ratio= (maximum aortic valve cusp distance-maximum aortic valve root distance) ×100%.
The parameter calculation sub-module is further used for detecting and obtaining an aortic valve forward blood flow spectrum and a mitral valve forward blood flow spectrum according to the aortic outflow tract and the mitral valve, and calculating blood flow rate and velocity time integral values of the aortic valve forward blood flow spectrum and the mitral valve forward blood flow spectrum respectively.
In this embodiment, possible causes of sudden cardiac arrest in patients include myocardial infarction, trauma, acute pulmonary embolism, tension pneumothorax, pericardial tamponade, low volume/blood loss, etc. The specific analysis method for the possible reasons for the cardiac arrest comprises the following steps:
If one or more indexes in the velocity time integral value VT of the left ventricular endocardial contraction rate and the aortic valve forward blood flow frequency spectrum are lower than corresponding thresholds and the left ventricular endocardial contraction movement mode is a segment obstacle, the cardiac arrest intelligent analysis unit judges that the possible cause of the cardiac arrest is myocardial infarction.
If the left ventricular endocardial contraction rate and the velocity-time integral VT of the aortic valve forward blood flow spectrum are both lower than the corresponding threshold values, and the left ventricular endocardial contraction movement pattern is a non-segmental obstacle, the cardiac arrest intelligent analysis unit determines that the cardiac arrest is likely to be caused by trauma related cardiac arrest (possibly combined with different scenes and different other indexes).
If the areas of the left endocardium and the right endocardium are smaller than the corresponding threshold values, the intelligent analysis unit for cardiac arrest judges that the possible cause of the cardiac arrest is low volume/blood loss.
Right ventricular area: the ratio of the left ventricular area is obviously increased (the right ventricular area is larger than 1 or a set threshold value obtained through clinical research), the velocity time integral value VT of the aortic valve forward blood flow frequency spectrum is lower than a corresponding threshold value, and the pulmonary ultrasonic image identifies that A line or B line or pleural slip sign exists, so that the intelligent analysis unit for cardiac arrest judges that the possible cause of cardiac arrest is acute pulmonary embolism.
Right ventricular area: the ratio of the left ventricular area is increased (the right ventricular area is larger than 0.6 or a set threshold value obtained through clinical research), the velocity time integral value VT of the aortic valve forward blood flow frequency spectrum is lower than a corresponding threshold value, and the pulmonary ultrasonic image recognizes that the A line and the pleural slip sign disappear, so that the intelligent analysis unit for cardiac arrest judges that the possible cause of the cardiac arrest is tension pneumothorax.
If the epicardium and the pericardium are identified to have obvious pericardial effusion, and the speed time integral value VT of the aortic valve forward blood flow frequency spectrum is lower than a corresponding threshold value, the intelligent analysis unit for cardiac arrest judges that the possible cause of the cardiac arrest is pericardial packing. Wherein, if the vertical maximum distance from the adventitia to the pericardium is more than 1cm or a set threshold value obtained by clinical study, it is judged that there is obvious pericardial effusion.
In the present invention, the carotid blood flow spectrum image is used as a main means and mode for identifying sudden cardiac arrest of a patient, when carotid blood flow spectrum acquisition or identification is difficult, in some embodiments, the cardiac arrest intelligent analysis unit may further determine whether the patient has sudden cardiac arrest according to the ultrasound image transmitted by the heart and lung ultrasound image acquisition module, mainly by the data integration analysis module, according to the corresponding motion condition, blood flow rate and velocity time integral value of the endocardium and the required specific part, to identify whether the heart of the examined person has sudden cardiac arrest. Specifically, the contraction rate of the left ventricle of the patient, the aortic valve opening rate, the velocity time integral value VTI of the aortic valve forward blood flow spectrum and the blood flow rate are taken as main evaluation parameters, the main evaluation parameters are respectively compared with corresponding thresholds for identifying whether the heart is suddenly stopped or not, and if at least one main evaluation parameter is lower than the corresponding threshold, the sudden cardiac stop of the checked person is identified. Wherein the corresponding threshold value can be obtained by clinical studies. The more specific discrimination method is as follows:
When the left endocardial contraction rate cannot be completely identified, the longitudinal contraction rate of the root of the mitral valve annulus is taken as an auxiliary evaluation parameter. When the aortic valve opening is not detected and the aortic valve opening rate cannot be obtained, the mitral valve opening rate is used as an auxiliary evaluation parameter. When the aortic valve opening is not detected and the velocity time integral VT and the blood flow rate of the aortic valve forward blood flow spectrum cannot be obtained, the velocity time integral VT and the blood flow rate of the mitral valve forward blood flow spectrum are taken as auxiliary evaluation parameters.
Comparing the auxiliary evaluation parameter with the main evaluation parameter with a corresponding threshold value for identifying whether the heart is sudden or not; if at least one of the primary evaluation parameters or the plurality of secondary evaluation parameters is below a corresponding threshold, a sudden cardiac arrest of the patient is identified.
When the patient is judged to have sudden cardiac arrest, an alarm is given to remind the patient to start cardiopulmonary resuscitation (CPR) immediately.
Further, in some embodiments, the ultrasound image acquisition module may also be used to assist in assessing cardiopulmonary resuscitation effects, primarily through the data integration analysis module. Specifically, the left endocardial contraction rate, the aortic valve opening rate, the velocity time integral value VT of the aortic valve forward blood flow spectrum and the blood flow rate are used as main evaluation parameters, the main evaluation parameters are respectively compared with corresponding thresholds for evaluating the cardiopulmonary resuscitation effect, and if at least one of the main evaluation parameters is lower than the corresponding threshold, the cardiopulmonary resuscitation effect is judged to be poor.
Further, when the heart-lung resuscitation effect is evaluated, the longitudinal contraction rate of the root of the mitral valve annulus is taken as an auxiliary evaluation parameter when the contraction rate of the left ventricle inner membrane cannot be completely identified. When the aortic valve opening is not detected and the aortic valve opening rate cannot be obtained, the mitral valve opening rate is used as an auxiliary evaluation parameter. When the aortic valve opening is not detected and the velocity time integral VT and the blood flow rate of the aortic valve forward blood flow spectrum cannot be obtained, the velocity time integral VT and the blood flow rate of the mitral valve forward blood flow spectrum are taken as auxiliary evaluation parameters.
And comparing the auxiliary evaluation parameter and the main evaluation parameter with corresponding thresholds for evaluating the cardiopulmonary resuscitation effect. And if at least one main evaluation parameter or a plurality of auxiliary evaluation parameters are lower than the corresponding threshold values, judging that the cardiopulmonary resuscitation effect is poor.
The threshold range of the monitored index pair to the corresponding index of the continuously monitored compression depth and compression effect can be obtained through clinical research.
Example 4
As a preferred embodiment of the present invention, on the basis of the above-described examples, the present examples make further detailed additions and illustrations to the diagnosis and treatment advice unit and the diagnosis and treatment diversion unit, as follows.
The diagnosis and treatment suggestion unit gives corresponding diagnosis and treatment suggestions according to the risk level sent by the cardiac arrest intelligent identification unit and the possible reasons of the cardiac arrest of the patient output by the cardiac arrest intelligent analysis unit. For example, after the diagnosis and treatment suggestion unit receives the four-level risk early warning, the diagnosis and treatment suggestion of cardiopulmonary resuscitation can be immediately output, and meanwhile, more targeted diagnosis and treatment suggestions are further provided by combining the possible reasons for the cardiac arrest of the patient output by the cardiac arrest intelligent analysis unit. Possible causes of cardiac arrest in patients include myocardial infarction, trauma, acute pulmonary embolism, tension pneumothorax, pericardial tamponade, hypovolemia/blood loss, pericardial effusion, significant increase in right heart, etc.
For example, when a patient has a large amount of pericardial effusion, the diagnosis and treatment suggestion unit can output a prompt that pericardial puncture drainage needs to be carried out on the patient; if the right heart of the patient is diagnosed to be obviously increased, outputting a prompt that the patient possibly suffers from acute pulmonary embolism and needs to have urgent thrombolysis; if the patient has serious capacity deficiency, outputting a prompt to rapidly replenish liquid for the patient; if the patient has tension pneumothorax, outputting a prompt to carry out closed thoracic drainage on the patient; if the patient is myocardial infarction, a prompt is output indicating that PCI needs to be implemented on the patient.
In this embodiment, the quick fluid infusion may be performed by using a venous fluid carried by an ambulance, such as normal saline, sodium lactate ringer's solution, etc., and the quick fluid infusion emergency operation is usually directly performed by a medical staff on site without requiring the environment. Medical staff can comprehensively judge according to diagnosis and treatment advice output by the diagnosis and treatment advice unit and by combining own experience, and finally implement corresponding first-aid measures on patients.
In the invention, the diagnosis and treatment suggestion unit also comprises a corresponding diagnosis and treatment suggestion display module which is used for displaying the diagnosis and treatment suggestion output by the diagnosis and treatment suggestion display module in real time for the emergency personnel to check, and the diagnosis and treatment suggestion unit also sends the diagnosis and treatment suggestion to the diagnosis and treatment diversion unit.
Furthermore, the diagnosis and treatment shunting unit can match medical institutions capable of implementing corresponding medical measures in a database in a system of the diagnosis and treatment shunting unit according to the diagnosis and treatment advice output by the diagnosis and treatment advice unit, and give out shunting advice, so that medical staff can send patients to proper medical institutions for emergency treatment according to the output medical institution list, and the effect of shunting and treatment is achieved. For example, when the patient has cardiac arrest due to myocardial infarction, the patient needs PCI (percutaneous coronary intervention), the diagnosis and treatment shunt unit outputs a medical center capable of executing PCI operation, so that the patient is directly shunted to the medical center with PCI capability for treatment; if cardiopulmonary resuscitation exceeds 10 minutes, if the heart of the patient still does not recover the spontaneous rhythm (whether the heart is effectively beating or not can be seen through the heart ultrasonic probe), the patient is required to perform ECPR, and the diagnosis and treatment shunt unit shunts the patient to a medical center with ECPR capability; if the cause of the sudden cardiac arrest of the patient is an acute pulmonary embolism, the patient is required to perform thrombolysis, and a medical center capable of performing thrombolysis or thrombolysis operation is output, so that the patient is directly shunted to the medical center capable of performing thrombolysis or thrombolysis immediately. Based on the diagnosis and treatment diversion proposal, the invention can realize seamless connection in the pre-hospital, the patient can get on the vehicle to get in the hospital, and the call can be rescuing.
Example 5
As still another preferred embodiment of the present invention, on the basis of the above-described examples, the present example supplements and explains the cardiopulmonary resuscitation effect evaluation unit in further detail, specifically as follows.
The cardiopulmonary resuscitation effect evaluation unit firstly triggers the cardiopulmonary resuscitation effect evaluation unit to work according to the risk level sent by the comprehensive analysis risk classification module, and in the invention, because the fourth-level risk early warning indicates sudden cardiac arrest of a patient, the cardiopulmonary resuscitation of the patient is required, so that the cardiopulmonary resuscitation effect evaluation unit can be set to work after receiving the fourth-level risk early warning, and then further carries out the evaluation of the cardiopulmonary resuscitation effect by combining the blood flow parameters transmitted by the carotid artery blood flow frequency spectrum automatic identification module. In some embodiments, if the patient is provided with a cardiac ultrasound probe at the same time, the cardiopulmonary resuscitation effect can also be evaluated as an aid to the cardiopulmonary resuscitation effect based on the cardiac compression effect detected by the cardiac ultrasound probe, which is described in embodiment 3 and not developed in detail herein. The following explanation and explanation will be made on the specific process of the cardiac arrest intelligent recognition unit participating in the quality evaluation effect of cardiopulmonary resuscitation, specifically as follows.
The cardiopulmonary resuscitation effect evaluation unit evaluates the cardiopulmonary resuscitation effect according to six parameters, namely systolic blood flow peak speed, end diastole blood flow speed, blood flow spectrum curve lower area, curve rising slope, curve falling slope and resistance index, which are identified by the carotid artery frequency spectrum automatic identification module, and the specific method comprises the following steps:
Cardiopulmonary resuscitation presses effectively: the heart perfusion device comprises blood flow in both systolic phase and diastolic phase, but the heart output is 30% or less lower than the normal value, the cardiac output is 30% or less lower than the normal value, the curve rising slope and curve falling slope are 30% or less lower than the normal value, and the resistance index is 30% or less higher than the normal value, which indicates that the heart output is present, so that the basic perfusion requirement can be satisfied;
The cardiopulmonary resuscitation presses the effect relatively poor: the heart infusion device comprises blood flow in both systolic phase and diastolic phase, which is 30% -50% lower than normal value, cardiac output is 30% -50% lower than normal value, curve rising slope is 30% -50% lower than normal value, resistance index is 30% -50% higher than normal value, which means cardiac output, but can not meet basic infusion requirement, and compression depth and speed need to be adjusted;
Cardiopulmonary resuscitation presses effectually poor: the heart output is shown to be seriously insufficient, the cardiopulmonary resuscitation pressing effect is poor, and the pressing depth and speed need to be adjusted;
Cardiopulmonary resuscitation compression inefficiency: the heart-lung resuscitation device comprises a heart-lung resuscitation device, a heart-lung resuscitation device and a heart-lung resuscitation device, wherein the heart-lung resuscitation device comprises a heart-lung resuscitation device, a heart-lung resuscitation device and a heart-lung resuscitation device, wherein blood flow does not exist in both systolic phase and diastolic phase, the rising slope of a curve, the falling slope of the curve and a resistance index cannot be measured, the heart-lung resuscitation device is used for indicating that a heart of a patient does not effectively beat out, and the heart-lung resuscitation device is used for indicating that the heart-lung resuscitation is invalid, and a compression depth and the heart-lung resuscitation device are required to be quickly adjusted or a rescue person is replaced.
Thus, in the present invention, for a cardiopulmonary resuscitation evaluation unit, during compressions, whether or not sufficient cardiac output is produced per compression may be evaluated from the above-described measurements of the carotid artery spectrum.
In some embodiments, the cardiopulmonary resuscitation effect evaluation unit may be further connected to an early warning unit, and sends the cardiopulmonary resuscitation quality evaluation effect to the early warning unit, where the early warning unit controls different display lamps to light according to the evaluation result, so that when judging the cardiopulmonary resuscitation effect, the cardiopulmonary resuscitation effect can be directly judged, read and reminded by the reminding lamps of four colors, namely, green, blue, yellow and red. Green represents compression is effective and provides cardiac output that meets basic perfusion requirements; blue represents compression is effective but fails to meet basic perfusion requirements, requiring adjustment of compression depth and speed; yellow represents poor pressing effect, and the pressing depth and speed may need to be adjusted; red indicates that the press is not effective and the press depth, speed or replacement of the rescue personnel should be adjusted quickly.
Example 6
This embodiment is further illustrated on the basis of embodiment 5, as shown in fig. 1, the cardiopulmonary resuscitation integrated first-aid system embeds a pre-cardiopulmonary resuscitation evaluation path and a post-cardiopulmonary resuscitation evaluation path, where the pre-cardiopulmonary resuscitation evaluation path triggers the post-cardiopulmonary resuscitation evaluation path.
The pre-cardiopulmonary resuscitation assessment path includes:
① The carotid blood flow spectrum acquisition unit acquires ultrasonic carotid blood flow spectrum images in the process of suspected cardiac arrest of a patient and sends the ultrasonic carotid blood flow spectrum images to the carotid blood flow spectrum automatic identification module;
① The carotid blood flow spectrum automatic identification module identifies and processes the ultrasonic carotid blood flow spectrum image to obtain relevant blood flow parameters and sends the relevant blood flow parameters to the comprehensive analysis risk classification module;
② The comprehensive analysis risk classification module is used for assisting in judging the carotid artery pulsation condition and the blood flow state according to the related blood flow parameters, classifying the risks of the severity of the heart output condition of a patient, and transmitting the corresponding risk grades to the cardiopulmonary resuscitation effect evaluation unit, the early warning unit and the diagnosis and treatment suggestion unit;
④ The early warning module carries out early warning according to the risk grade sent by the comprehensive analysis risk grading module;
⑤ The diagnosis and treatment suggestion unit generates and outputs diagnosis and treatment suggestions for evaluation before cardiopulmonary resuscitation according to the risk level early warning.
The post cardiopulmonary resuscitation evaluation path includes:
1. when the risk level early warning is the highest level, the cardiopulmonary resuscitation effect evaluation unit is triggered to work;
2. medical staff perform cardiopulmonary resuscitation, and simultaneously an ultrasonic carotid blood flow spectrum image in the cardiopulmonary resuscitation process is acquired by a carotid blood flow spectrum acquisition unit and is sent to a carotid blood flow spectrum automatic identification module;
4. the carotid blood flow spectrum automatic identification module identifies and processes the ultrasonic carotid blood flow spectrum image to obtain relevant blood flow parameters and sends the relevant blood flow parameters to the cardiopulmonary resuscitation effect evaluation unit;
5. The cardiopulmonary resuscitation effect evaluation unit evaluates the cardiopulmonary resuscitation quality by utilizing the related blood flow parameters sent by the carotid artery blood flow spectrum automatic identification unit, and sends the cardiopulmonary resuscitation quality evaluation result to the early warning module;
6. the early warning module carries out early warning and warning according to the cardiopulmonary resuscitation quality evaluation result sent by the cardiopulmonary resuscitation quality evaluation module, and sends the corresponding cardiopulmonary resuscitation quality early warning and warning to the diagnosis and treatment suggestion module;
7. The diagnosis and treatment suggestion module generates diagnosis and treatment suggestions after cardiopulmonary resuscitation according to cardiopulmonary resuscitation quality early warning.
Example 7
As a further preferred implementation manner of the present invention, the system in this embodiment may further be externally connected to and incorporated into other monitoring devices and monitoring and inspection indexes, or manually input other relevant vital signs, circulatory hemodynamic and visceral function indexes, for helping comprehensive judgment and assisting decision-making, based on the above embodiments 1-6. And the integrated analysis can be performed by linking other equipment, such as an electrocardiograph monitor, a breathing machine equipment, a blood detector, a POC ultrasonic probe, laboratory examination data (such as blood gas pH value, oxygen partial pressure, carbon dioxide partial pressure, lactic acid and potassium) and the like. The method can be used for single-point or continuous dynamic monitoring, and judging the identification of the sudden cardiac arrest and recovery condition of a patient, the analysis of the cause of the cardiac source factor of the sudden cardiac arrest and the monitoring of the depth and the efficiency of cardiac compression according to the identification result. The system can also be linked with other equipment data export devices to finish the output of the data.
The electrocardiograph monitor can obtain physiological parameters such as heart rate, blood pressure, respiration and blood oxygen saturation of a patient, the physiological parameters can be used as an auxiliary means of the system to realize identification of cardiac arrest of the patient and evaluation of cardiopulmonary resuscitation effect, the system realizes linkage with an external electrocardiograph monitor through a built-in electrocardiograph monitor unit with an electrocardiograph identification function, and the electrocardiograph monitor unit can identify whether the patient is cardiac arrest and evaluation of cardiopulmonary resuscitation effect through real-time analysis of data acquired by the electrocardiograph monitor. For example, the blood flow perfusion index reflects systemic perfusion, normally >1.4, indicating good cardiopulmonary resuscitation compression effect, and if <1.4 indicates insufficient systemic perfusion, poor cardiopulmonary resuscitation compression effect. The evaluation criteria and guidelines for determining cardiac arrest and evaluating the effectiveness of cardiopulmonary resuscitation from data acquired by an electrocardiograph monitor may be referred to in the art and will not be developed in detail herein.
The blood detector can provide electrolyte abnormalities of the patient, such as high potassium, low potassium; internal environmental abnormalities such as acidosis; hemoglobin conditions, such as hemoglobin decline; both of these causes may lead to sudden cardiac arrest in the patient. Therefore, the system can also realize the linkage with an external blood detector through the built-in blood analysis unit with the blood analysis function, and the blood analysis unit can judge the cause of the cardiac arrest of the patient as an auxiliary means of the system through analyzing the data detected by the blood detector. The criteria and criteria for analyzing and discriminating the cause of cardiac arrest from the data detected by the blood detector are referred to in the art and will not be elaborated upon herein.
The POC ultrasonic probe can screen the bleeding part of the non-open wound surface, and can see which part has effusion through ultrasonic, so that bleeding can be prompted at the part. The system can realize linkage with an external POC ultrasonic probe through the built-in POC ultrasonic unit, so that the non-open wound bleeding part of a patient is screened, whether bleeding occurs in the patient body or not is found in time, and quick hemostasis is realized.
Furthermore, after recognizing that the heart of the patient is suddenly stopped, the system can also link the cardiopulmonary resuscitation machine, trigger the work based on the risk level sent by the cardiac sudden stop intelligent recognition unit, timely start the chest cardiac compression, and similarly, the triggering mechanism of the cardiopulmonary resuscitation machine can also be triggered to work by setting when the patient is at the four-level risk level. When the linked cardiopulmonary resuscitation machine is started, the system can pop the window to prompt the medical staff whether to immediately execute cardiopulmonary resuscitation, and after confirmation by the medical staff, the cardiopulmonary resuscitation machine starts to work. The cardiopulmonary resuscitator is a portable cardiopulmonary resuscitator, and can be a portable product produced by Suzhou Shang-collar medical science and technology Co., ltd, weier, and other companies.
The foregoing description is only a preferred embodiment of the present invention and is not intended to limit the invention in any way, but any simple modification, equivalent variation, etc. of the above embodiment according to the technical substance of the present invention falls within the scope of the present invention.
Claims (20)
1. An off-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest, comprising:
the carotid blood flow spectrum acquisition unit is used for acquiring a carotid blood flow spectrum image of a patient;
The heart and lung ultrasonic image acquisition unit is used for acquiring heart ultrasonic images and lung ultrasonic images of patients;
The heart sudden stop intelligent identification unit is connected with the carotid artery blood flow spectrum acquisition unit, obtains current blood flow parameters of a patient based on the carotid artery blood flow spectrum image of the patient acquired by the carotid artery blood flow spectrum acquisition unit, judges the output condition of the heart of the patient, carries out severity risk classification according to the output condition of the heart of the patient, and identifies whether the heart sudden stop occurs or not; the corresponding risk level is sent to a diagnosis and treatment suggestion unit and a cardiopulmonary resuscitation effect evaluation unit, and meanwhile, the current blood flow parameters of the patient are also sent to the cardiopulmonary resuscitation effect evaluation unit;
The heart sudden stop intelligent analysis unit is connected with the heart and lung ultrasonic image acquisition unit, and based on the patient heart ultrasonic image and the lung ultrasonic image acquired by the heart and lung ultrasonic image acquisition unit, corresponding motion conditions, blood flow rate, speed time integral values and basic pathological feature results of the lung of the patient heart inner membrane and required specific parts are obtained, and possible reasons for the heart sudden stop of the patient are analyzed and output to the diagnosis and treatment suggestion unit;
The diagnosis and treatment suggestion unit is connected with the intelligent cardiac arrest identification unit and the intelligent cardiac arrest analysis unit, and generates and outputs diagnosis and treatment suggestions based on the risk level sent by the intelligent cardiac arrest identification unit and the possible cause of cardiac arrest output by the intelligent cardiac arrest analysis unit;
The cardiopulmonary resuscitation effect evaluation unit is connected with the cardiac arrest intelligent recognition unit, and is used for evaluating the cardiopulmonary resuscitation effect based on the risk level and the current blood flow parameter of the patient sent by the cardiac arrest intelligent recognition unit and outputting an evaluation result;
The diagnosis and treatment shunting unit is connected with the diagnosis and treatment suggestion unit and shunts patients to different medical institutions for treatment based on the diagnosis and treatment suggestions transmitted by the diagnosis and treatment suggestion unit.
2. The system of claim 1, wherein the blood flow parameters include systolic peak blood flow velocity, end diastole blood flow velocity, area under the blood flow spectrum curve, curve rising slope, curve falling slope, and resistance index.
3. The extra-hospital emergency system for automatic identification and intelligent decision-making assistance of cardiac arrest according to claim 2, wherein the systolic peak blood flow velocity is the fastest of carotid arteries in systole;
The end diastole blood flow velocity refers to the velocity of the carotid artery at end diastole;
the area under the blood flow spectrum curve is the time integral VTI of the blood flow velocity of the carotid artery is measured from the arterial spectrum corresponding to a plurality of continuous cardiac cycles of the carotid artery in a set time period according to the time integral of the velocity of the boundary trace of the carotid artery spectrum, and the forward blood flow VTI of the peripheral artery is calculated by combining the cross-sectional area CSA of the carotid artery;
the curve rising slope refers to the ratio of the speed difference to the time difference in the blood flow speed rising process;
The curve descending slope refers to the ratio of the speed difference to the time difference in the blood flow speed descending process;
The resistance index refers to a parameter representing vascular resistance calculated from carotid blood flow velocity.
4. The automated cardiac arrest identification and intelligent decision-assist system as recited in claim 1 wherein said severity risk classification comprises, in order from light to heavy, a first level risk, a second level risk, a third level risk, and a fourth level risk, said fourth level risk being indicative of a cardiac arrest in a patient.
5. The system for automatically identifying cardiac arrest and intelligently assisting decision-making outside-hospital emergency treatment according to claim 1, wherein the cardiac arrest intelligent identification unit processes the patient carotid blood flow spectrum image acquired by the carotid blood flow spectrum acquisition unit in a machine learning manner to obtain current blood flow parameters of the patient and judge cardiac output conditions of the patient, and the system specifically comprises:
The carotid blood flow spectrum acquisition unit acquires ultrasonic carotid blood flow spectrum information of a patient and sends the ultrasonic carotid blood flow spectrum information to the cardiac arrest intelligent identification unit, and a qualified doctor marks the acquired carotid blood flow spectrum boundary and calculates systolic blood flow peak speed, end diastole blood flow speed, area under a blood flow spectrum curve, curve rising slope, curve falling slope and resistance index;
The heart sudden stop intelligent recognition unit performs machine learning by comparing the manually marked frequency spectrum picture with the original picture, automatically recognizes the carotid blood flow frequency spectrum, and automatically calculates the systolic blood flow peak speed, the end diastole blood flow speed, the area under the blood flow frequency spectrum curve, the curve rising slope, the curve falling slope and the resistance index; judging the heart output condition of the patient according to the data obtained by calculation, and grading the severity of the heart abnormal condition;
Expert auditing is carried out on the effect of machine learning, and the machine learning is corrected by adopting a correction algorithm, so that the intelligent heart sudden stop recognition unit with automatic carotid artery blood flow spectrum recognition and automatic severity grading is formed.
6. The system according to claim 1, wherein the cardiac arrest intelligent recognition unit processes the patient carotid blood flow spectrum image acquired by the carotid blood flow spectrum acquisition unit by means of machine learning, the machine learning comprises normal carotid blood flow spectrum learning, and the normal carotid blood flow spectrum learning comprises:
Collecting carotid artery blood flow spectrum of healthy volunteers for machine learning, training a machine to identify normal blood flow spectrum, and automatically generating systolic blood flow peak velocity, end diastole blood flow velocity, area under a blood flow spectrum curve, curve rising slope, curve falling slope and resistance index parameters; and checking the accuracy of the normal carotid blood flow learning parameters through expert examination.
7. The system according to claim 1, wherein the cardiac arrest intelligent recognition unit processes the patient carotid blood flow spectrum image acquired by the carotid blood flow spectrum acquisition unit by means of machine learning, the machine learning comprises abnormal carotid blood flow spectrum learning, and the abnormal carotid blood flow spectrum learning comprises:
The clinical abnormal carotid blood flow spectrum is collected for machine learning, the machine is trained to identify the abnormal carotid blood flow spectrum, the heartbeat state of a patient is automatically identified according to abnormal conditions of systolic blood flow peak speed, end diastole blood flow speed, blood flow spectrum curve lower area, curve rising slope, curve falling slope and resistance index parameters, classification according to the spectrum severity is automatically identified and carried out, comparison is carried out with expert identification results and severity classification, and the accuracy of identification and severity classification of abnormal carotid blood flow is checked.
8. The system according to claim 1, wherein the analysis of possible causes of abnormal cardiac function of the patient based on the patient's heart ultrasound image and the lung ultrasound image obtained by the heart and lung ultrasound image acquisition unit, and the results of the corresponding motion condition, blood flow rate, velocity time integral value and basic pathological features of the lung of the patient's endocardium and the required specific part are obtained, and the analysis of possible causes of abnormal cardiac function of the patient is output to the diagnosis and treatment advice unit, comprises:
the heart and lung ultrasonic image acquisition unit acquires heart ultrasonic images, blood flow Doppler images of aortic valves and mitral valves and lung ultrasonic images of different sections of the examined person;
Identifying the endocardium, the required specific part and the corresponding movement condition of the specific part in real time according to the acquired heart ultrasonic image; detecting a regular frequency spectrum and measuring a blood flow velocity value and a velocity time integral value according to the acquired blood flow Doppler images of the aortic valve and the mitral valve; identifying basic pathological feature results of the lung according to the lung ultrasonic image;
and analyzing possible reasons for the sudden cardiac arrest of the patient according to the corresponding motion conditions, blood flow rate, velocity time integral values and basic pathological feature results of the lung of the endocardium and the required specific part, and finally outputting the possible reasons for the sudden cardiac arrest of the patient to a diagnosis and treatment suggestion unit.
9. The automated cardiac arrest identification and intelligent decision-assist system according to claim 8, wherein said endocardial and desired specific locations include the endocardial border of the four-chamber endocardial left ventricle, the endocardial border of the right ventricle, the epicardium and pericardium, the root of the mitral valve free wall annulus, the aortic outflow tract, the mitral valve and the aortic valve.
10. The extra-hospital emergency system for automatic identification and intelligent decision-making assistance of cardiac arrest according to claim 9, wherein the respective motion of the endocardium and the required features comprises: the intimal contraction rate, the annular root longitudinal contraction rate, the mitral valve opening rate, and the aortic valve opening rate.
11. The system for automatic identification and intelligent decision-aid of cardiac arrest according to claim 10, wherein the identification of the corresponding movement of the endocardium and the required features is:
according to the endocardial edge and the endocardial edge of the left ventricle of the four-chamber heart of the apex of the heart, calculate left and right endocardial areas and left ventricular endocardial shrinkage, calculate the area of the right ventricle at the end diastole: ratio of left ventricular area;
calculating the longitudinal contraction rate of the root part of the mitral valve annulus according to the root part of the mitral valve free wall annulus;
calculating the mitral valve opening rate according to the mitral valve opening condition;
The aortic valve opening rate is calculated according to the aortic valve opening condition.
12. The system for automatic cardiac arrest identification and intelligent decision-assist in an off-hospital emergency according to claim 11, wherein said detection of a regular spectrum and measurement of a blood flow rate, a velocity time integral value are performed based on acquired blood flow doppler images of aortic and mitral valves: detecting to obtain an aortic valve forward blood flow spectrum and a mitral valve forward blood flow spectrum, and calculating blood flow velocity and velocity time integral values of the aortic valve forward blood flow spectrum and the mitral valve forward blood flow spectrum respectively.
13. The extra-hospital emergency system for automatic identification and intelligent decision-assist of cardiac arrest according to claim 8, wherein said identification of basic pathological feature results of the lungs comprises: line a, line B, signs of pleural sliding disappeared and signs of pulmonary metaplasia.
14. The system for automatic cardiac arrest identification and intelligent decision-assist in an off-hospital emergency according to claim 8, wherein the method for analyzing the possible cause of cardiac arrest is specifically as follows:
If one or more indexes in the velocity time integral value of the left ventricular endocardial contraction rate and the aortic valve forward blood flow frequency spectrum are lower than corresponding thresholds and the left ventricular endocardial contraction movement mode is a segment obstacle, the intelligent cardiac arrest analysis unit judges that the possible cause of prompting cardiac arrest is myocardial infarction;
if the left ventricular intima contraction rate and the velocity time integral value of the aortic valve forward blood flow frequency spectrum are lower than the corresponding threshold values, and the left ventricular intima contraction movement mode is a non-segmental obstacle, the cardiac arrest intelligent analysis unit judges that the possible cause of prompting cardiac arrest is wound-related cardiac arrest;
if the areas of the left endocardium and the right endocardium are smaller than the corresponding threshold values, the intelligent analysis unit for cardiac arrest judges that the possible cause of the cardiac arrest is low volume/blood loss;
Right ventricular area: the proportion of the left ventricle area is obviously increased, the velocity time integral value of the aortic valve forward blood flow spectrum is lower than a corresponding threshold value, and the pulmonary ultrasonic image identifies that the A line or the B line or the pleural slip sign exists, so that the intelligent cardiac arrest analysis unit judges that the possible cause of the cardiac arrest is acute pulmonary embolism;
Right ventricular area: the proportion of the left ventricle area is increased, the velocity time integral value of the aortic valve forward blood flow spectrum is lower than a corresponding threshold value, and the pulmonary ultrasonic image recognizes that the A line and the pleural slip sign disappear, so that the intelligent analysis unit for cardiac arrest prompts that the possible cause of the cardiac arrest is tension pneumothorax;
If the epicardium and the pericardium are identified to have obvious pericardial effusion, and the velocity time integral value of the aortic valve forward blood flow frequency spectrum is lower than the corresponding threshold value, the intelligent analysis unit for cardiac arrest judges that the possible cause of the cardiac arrest is pericardial packing.
15. The automated cardiac arrest identification and intelligent decision-assist extra-hospital emergency system according to claim 1, wherein the cardiopulmonary resuscitation quality assessment results include cardiopulmonary resuscitation compression effective, cardiopulmonary resuscitation compression poor, and cardiopulmonary resuscitation compression ineffective; when the output cardiopulmonary resuscitation compression effect is poor, bad or invalid, the cardiopulmonary resuscitation effect evaluation unit outputs a prompt that the compression depth and speed need to be adjusted.
16. The extra-hospital emergency system for automatic identification and intelligent decision-making assistance of cardiac arrest according to claim 1, wherein said carotid blood flow spectrum acquisition unit comprises a stick-on vascular ultrasound probe.
17. The system for automatic identification and intelligent decision-aid of cardiac arrest according to claim 1, wherein the heart and lung ultrasound image acquisition unit comprises a heart ultrasound image acquisition module and a lung ultrasound image acquisition module; the heart ultrasonic image acquisition module is a paste type transthoracic heart ultrasonic probe or a transesophageal ultrasonic probe; the lung ultrasonic image acquisition module comprises a paste type lung ultrasonic probe.
18. The extra-hospital emergency system for automatic identification and intelligent decision-making assistance of cardiac arrest according to claim 1, further comprising a portable extra-thoracic compression cardiopulmonary resuscitator connected to the intelligent cardiac arrest identification unit.
19. The system according to claim 1, further comprising an early warning unit connected to the cardiac arrest intelligent recognition unit and the cardiopulmonary resuscitation effect evaluation unit, wherein the early warning unit carries out early warning prompt based on the severity risk classification output by the cardiac arrest intelligent recognition unit and the cardiopulmonary resuscitation quality evaluation result output by the cardiopulmonary resuscitation effect evaluation unit.
20. The system according to claim 19, wherein the early warning module comprises four color indicator lights of green, blue, yellow and red, respectively corresponding to the risk level output by the cardiac arrest intelligent recognition unit and the cardiopulmonary resuscitation quality evaluation result output by the cardiopulmonary resuscitation effect evaluation unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311545097.XA CN117577301B (en) | 2023-11-20 | 2023-11-20 | Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311545097.XA CN117577301B (en) | 2023-11-20 | 2023-11-20 | Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117577301A CN117577301A (en) | 2024-02-20 |
| CN117577301B true CN117577301B (en) | 2024-05-10 |
Family
ID=89883826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311545097.XA Active CN117577301B (en) | 2023-11-20 | 2023-11-20 | Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117577301B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459328A (en) * | 2019-07-05 | 2019-11-15 | 梁俊 | A kind of Clinical Decision Support Systems for assessing sudden cardiac arrest |
| CN111180075A (en) * | 2020-03-02 | 2020-05-19 | 浙江大学 | Dynamic model established based on heart murmur and computer simulation method |
| CN114171203A (en) * | 2021-11-29 | 2022-03-11 | 浙江大学 | Behavior feature based deep learning cardiac arrest animal model prediction method and system |
-
2023
- 2023-11-20 CN CN202311545097.XA patent/CN117577301B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110459328A (en) * | 2019-07-05 | 2019-11-15 | 梁俊 | A kind of Clinical Decision Support Systems for assessing sudden cardiac arrest |
| CN111180075A (en) * | 2020-03-02 | 2020-05-19 | 浙江大学 | Dynamic model established based on heart murmur and computer simulation method |
| CN114171203A (en) * | 2021-11-29 | 2022-03-11 | 浙江大学 | Behavior feature based deep learning cardiac arrest animal model prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117577301A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7771364B2 (en) | Method and system for cardiovascular system diagnosis | |
| US9451921B2 (en) | System and method for indicating coronary artery disease risk based on low and high frequency bands | |
| US5957866A (en) | Apparatus and methods for analyzing body sounds | |
| CN111685992B (en) | Cardio-pulmonary resuscitation feedback system | |
| JP2020536629A (en) | ECG-based ejection fraction screening | |
| EP2117645B1 (en) | Monitoring mechanical heart properties | |
| WO2005069740A2 (en) | Method and system for cardiovascular system diagnosis | |
| CN105473065A (en) | Determining return of spontaneous circulation during CPR | |
| CN109640805A (en) | With the multi-functional measuring device for determining Blood pressure of carotid artery | |
| CN117635552B (en) | Auxiliary decision making system for rapid identification and reason analysis of sudden cardiac arrest | |
| CN110200619A (en) | It is a kind of to establish major cardiovascular disease risks Early-warning Model method and device | |
| CN117243634B (en) | Cardiac arrest identification analysis judgment system based on ultrasonic carotid artery blood flow | |
| JPH05176932A (en) | Diagnostic method for cerebral infarction | |
| CN114898882B (en) | Method and system for ultrasound-based assessment of right heart function | |
| CN115294030A (en) | Method and device for acquiring coronary artery functional indexes | |
| CN117577301B (en) | Outside-hospital emergency system for automatic identification and intelligent auxiliary decision-making of cardiac arrest | |
| Shokouhmand et al. | Detection of left ventricular ejection fraction abnormality using fusion of acoustic and biopotential characteristics of precordium | |
| A‐Mohannadi et al. | Conventional Clinical Methods for Predicting Heart Disease | |
| WO2018223269A1 (en) | Apparatus to test for orthostatic hypotension | |
| Lin et al. | Korotkoff sounds dynamically reflect changes in cardiac function based on deep learning methods | |
| Guedes et al. | Heart sound analysis for blood pressure estimation | |
| US20220125367A1 (en) | Screening cardiac conditions using cardiac vibrational energy spectral heat maps | |
| TWI695705B (en) | Irregular heartbeat detecting device combining exercise intensity analysis and the detecting method thereof | |
| WO2023149058A1 (en) | Heart sound analysis device, heart sound analysis program, and recording medium | |
| EP4029437A1 (en) | Blood pressure estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |