CN111128381A - Active 120 system based on artificial intelligence - Google Patents
Active 120 system based on artificial intelligence Download PDFInfo
- Publication number
- CN111128381A CN111128381A CN201911359440.5A CN201911359440A CN111128381A CN 111128381 A CN111128381 A CN 111128381A CN 201911359440 A CN201911359440 A CN 201911359440A CN 111128381 A CN111128381 A CN 111128381A
- Authority
- CN
- China
- Prior art keywords
- layer
- data
- diagnosis
- series
- artificial intelligence
- 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.)
- Pending
Links
Images
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses an active 120 system based on artificial intelligence, which comprises: the system comprises a user health data acquisition module, a diagnosis and treatment module and a health management module, wherein the user health data acquisition module is used for acquiring daily health data of a user through intelligent health wearable equipment and associating physical examination data of the user with medical data in the diagnosis and treatment process; the artificial intelligence auxiliary diagnosis module is used for analyzing and screening abnormal data of the user data; and the active 120 docking module is used for performing 120 calling active intervention according to the diagnosis result of the artificial intelligence auxiliary diagnosis module. The invention provides an artificial intelligence auxiliary analysis model, which pushes abnormal data to a doctor for diagnosis or intervention, so that the workload of the doctor is greatly reduced, and meanwhile, abnormal patients can be quickly found, early warning is timely carried out, and medical intervention is timely prompted.
Description
Technical Field
The invention relates to a medical health service informatization technology, in particular to an active 120 system based on artificial intelligence.
Background
According to the related reports, the cardiovascular disease patients in China reach 2.9 hundred million, and the morbidity and mortality of chronic diseases such as hypertension, tumors, cerebral apoplexy, cardiovascular diseases and the like are on the trend of increasing year by year. The main reasons for this are that the early awareness of the disease and the intervention rate are not high, and most medical institutions are still in a passive service mode for disease diagnosis and treatment. How to shorten the time from the onset of symptoms of a patient to the acceptance of effective medical treatment and treatment has important significance for reducing the death rate of patients with myocardial infarction.
Based on the combination of an artificial intelligence technology and wearable equipment, by utilizing information technologies such as the Internet of things, the mobile internet and big data, an active 120-degree health monitoring system for cardiovascular diseases is researched and developed, the compliance of patients with chronic diseases and the control rate of the chronic diseases are improved, the time from symptom attack to medical treatment implementation of the patients with chronic diseases is shortened, a passive medical service mode is changed, and a novel medical health service mode of 'prevention before illness, treatment before slow diseases, treatment before serious diseases and treatment quickly after acute diseases' is realized has important significance.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an active 120 system based on artificial intelligence, aiming at the defects in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: an artificial intelligence based active 120 system, comprising:
the system comprises a user health data acquisition module, a diagnosis and treatment module and a health management module, wherein the user health data acquisition module is used for acquiring daily health data of a user through intelligent health wearable equipment and associating physical examination data of the user with medical data in the diagnosis and treatment process; uploading the user data to a cloud;
the artificial intelligence auxiliary diagnosis module is used for analyzing and screening abnormal data of the user data, and an electrocardio artificial intelligence analysis model is adopted for analyzing and screening;
the active 120 docking module is used for performing 120-call active intervention according to the diagnosis result of the artificial intelligence auxiliary diagnosis module, and specifically comprises the following steps:
if the diagnosis result is evaluated to be normal, the diagnosis result is sent to the user;
if the diagnosis result is evaluated to be slightly abnormal, the diagnosis result is sent to the user and the doctor, and whether the call center is triggered 120 is determined according to the secondary confirmation and interpretation result of the doctor;
if the diagnosis is assessed as critical, the diagnosis is sent to the user and the call center is triggered 120.
According to the scheme, the intelligent health wearable equipment in the user health data acquisition module comprises single-lead or twelve-lead electrocardio wearable equipment.
According to the scheme, the method for establishing the artificial intelligence analysis model of the electrocardio comprises the following steps:
1) establishing a data set, wherein the data set is an original value of massive electrocardiosignal data;
2) data processing: performing data preprocessing on the acquired data, wherein the data preprocessing comprises the following steps: data desensitization, data cleaning, noise reduction, standardization and normalization;
3) labeling the abnormal physiological signal data by using a medical data labeling tool, wherein the labeling types are 18 classifications of clinical diagnosis statistics;
4) dividing data into a training set and a verification set, training a deep neural network model based on the training set, wherein the neural network model is a convolutional neural network model for physiological electric signal analysis, adopting a four-classification method for single-lead electrocardiogram data, adopting a two-classification method for twelve-lead electrocardiogram data, and performing transfer learning on the model on the basis of 18 cardiovascular disease classifications;
according to the scheme, the data preprocessing in the step 2) is specifically as follows:
data desensitization: removing patient-related sensitive information from the data set;
data cleaning: judging whether the acquired data is normally acquired data or not according to the diagnosis information of the doctor, and removing the abnormally acquired data;
noise reduction: filtering information which causes interference to the training result through band-pass filtering;
and (3) standardization: converting the data according to a specified standard, and storing the data according to a uniform format;
normalization: and limiting the value of the data in a certain range and meeting the specified distribution condition, so as to accelerate the training of the model and improve the precision of the model.
According to the scheme, the data preprocessing in the step 2) further comprises data slicing, and the data slicing comprises directly dividing the data according to the type of the data and time or dividing the data according to the clinical significance of the data.
The invention has the following beneficial effects:
1. in the face of the fact that a large amount of collected electrocardio monitoring data cannot be diagnosed one by one, the invention provides an artificial intelligent auxiliary analysis model, abnormal data are pushed to a doctor for diagnosis or intervention, the workload of the doctor is greatly reduced, meanwhile, abnormal patients can be found quickly, early warning is carried out in time, and medical intervention is prompted in time;
2. through the combination of artificial intelligence assistance and the initiative 120, the doctor can timely know abnormal health data of the patient and give scientific and accurate diagnosis, and can timely trigger 120 a call center for critically ill patients, and meanwhile, basic data information of the patient and diagnosis conditions of the doctor also provide basis for pre-hospital first aid, so that full-flow closed-loop application service of linkage of the patient, the hospital and the first aid 120 is established, and the transition from passive rescue to active intervention medical service mode is realized.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a schematic structural diagram of an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, an artificial intelligence based cardiovascular disease initiative 120 system, comprising:
the system comprises a user health data acquisition module, a diagnosis and treatment module and a health management module, wherein the user health data acquisition module is used for acquiring daily health data of a user through intelligent health wearable equipment and associating physical examination data of the user with medical data in the diagnosis and treatment process; uploading the user data to a cloud;
data acquisition mainly accomplishes the collection to the medical data of public user's daily electrocardio data, physical examination data, outpatient service, the process of diagnosing such as being in hospital through intelligent wearing equipment and medical grade collection equipment, gathers effective data according to the requirement after, the patient finishes gathering, and data automatic upload reaches the high in the clouds.
The artificial intelligence auxiliary diagnosis module is used for analyzing and screening abnormal data of the user data, and an electrocardio artificial intelligence analysis model is adopted for analyzing and screening;
to the effective data who uploads to the high in the clouds, carry out the analysis screening of abnormal data through the supplementary diagnostic module of artificial intelligence to carry out the early warning and in time propelling movement to user's cell-phone APP and management backstage to abnormal data, the doctor carries out the secondary through the management backstage and confirms the interpretation, artificial intelligence's interpretation in advance has not only greatly alleviateed doctor's work load, also can discover unusual patient fast simultaneously, and timely early warning in time prompts medical intervention.
Effective data are prejudged through an artificial intelligence auxiliary diagnosis system, and the judged patient can check an evaluation result through a monitoring record of the mobile phone APP. If the AI evaluation result is abnormal, the patient can apply for the diagnosis of the doctor, the monitoring record is transmitted to the management background, and the doctor carries out secondary interpretation according to the monitoring data information; the AI prejudgment result is high-risk abnormal, the AI intelligent calls an automatic online management doctor, and a call center is triggered 120.
The artificial intelligence assistant decision-making related model adopts an electrocardio artificial intelligence analysis model, and the model is matched with a million-magnitude labeled database to carry out deep neural network modeling on a life signal, realize the automatic assistant diagnosis of related diseases with higher accuracy and be matched with the diagnosis and treatment specifications of clinical related diseases. The method comprises the following specific steps:
1) data acquisition:
and collecting mass medical data and acquiring the original value of the physiological signal. The physiological signals comprise single-lead electrocardiogram data, twelve-lead electrocardiogram data and other relevant clinical medical data;
the current data source is based on the clinical medical data accumulated in the heart function room of the hospital.
2) Data processing:
performing preprocessing operations on the acquired data, wherein the preprocessing operations comprise:
desensitization: sensitive information relating to the patient is removed from the acquired data.
Cleaning: according to the diagnosis information of the doctor, whether the acquired data are normally acquired (the conditions of equipment falling, interference and the like are possible) is judged, and the abnormally acquired data are removed.
Noise reduction: information that may interfere with the training results is filtered out by bandpass filtering.
Normalization: normalization is a statistical concept, is a part of data preprocessing like noise reduction, and can accelerate the training of the model and improve the precision of the model by limiting the value of data in a certain range and meeting certain specified distribution conditions through normalization.
Through the series of processing, the data meet the requirements of deep neural network modeling. Because the deep neural network model needs input data with a fixed length, data slicing is carried out, including data direct division according to time and data division according to clinical significance of the data, for example, electrocardiogram data can be divided according to a cardiac cycle, and subsequent training can select one of two scales for model training according to characteristics of corresponding diseases and characteristics of data sources.
3) Data labeling and classifying:
the content of the data label is counted to be 18 existing classifications according to the types covering more than 90% of the clinical diagnosis. And labeling the abnormal signals by using a medical data labeling tool based on a cloud platform. Because the tool provides an open interface, the tool can be compatible with data forms in various formats and can be conveniently integrated into a system;
4) model training:
the data are divided into a training set and a verification set, deep neural network model training is carried out based on the training set, and a reasonable network architecture is selected for different electrocardiogram data. For twelve-lead electrocardiogram data, an 88-layer deep convolutional neural network is adopted, and a two-classification method is adopted to finely tune and migrate a model on the basis of 18 classifications. Raw data is input and a score for each classification is output. The technique consists of two parts. The first part is a feature identifier, which automatically learns the features in the input data. The second part is a fully connected multi-layer perceptron. Further, the feature identifier component includes a convolutional layer and a pooling layer. In the convolutional layer, the feature map from the previous layer is convolved using a convolution kernel, which will be biased and input to the activation function to generate the feature map for the next layer. The pooling layer enables the reduction of the activation graph and strengthens invariance to input distortion, the convolution and pooling layer realizes high-level feature extraction, and global pooling and Dense layer classifiers are used for realizing classification of the electrocardiosignals at the output part of the convolutional neural network. The 88-layer deep neural network sequentially comprises an input layer, a (1 st) one-dimensional convolutional layer, a (2 nd) one-dimensional convolutional layer, a (1 st) maximum pooling layer, a (3 rd) one-dimensional convolutional layer, a (1 st) series layer, a (4 th) one-dimensional convolutional layer, a (2 nd) series layer, a (5 th) one-dimensional convolutional layer, a (3 rd) series layer, a (6 th) one-dimensional convolutional layer, a (2 nd) maximum pooling layer, a (1 st) average pooling layer, a (4 th) series layer, a (7 th) one-dimensional convolutional layer, a (5 th) series layer, a (8 th) one-dimensional convolutional layer, a (6 th) series layer, a (9 th) one-dimensional convolutional layer, a (7 th) series layer, a (10 th) one-dimensional convolutional layer, a (3 rd) maximum pooling layer, a (2 nd) average pooling layer, a (8 th) series layer, a (11 th) one-dimensional convolutional layer, (12 th) one-dimensional convolution layer, (9 th) series layer, (13 th) one-dimensional convolution layer, (10 th) series layer, (14 th) one-dimensional convolution layer, (11 th) series layer, (15 th) one-dimensional convolution layer, (4 th) maximum convolution layer, (3 rd) average convolution layer, (12 th) series layer, (16 th) one-dimensional convolution layer, (13 th) series layer, (17 th) one-dimensional convolution layer, (14 th) series layer, (18 th) one-dimensional convolution layer, (15 th) series layer, (19 th) one-dimensional convolution layer, (5 th) maximum convolution layer, (4 th) average convolution layer, (16 th) series layer, (20 th) one-dimensional convolution layer, (21 th) one-dimensional convolution layer, (17 th) series layer, (22 th) one-dimensional convolution layer, (18 th) series layer, (23 rd) one-dimensional convolution layer, (19 th) series layer, (24 th) one-dimensional convolution layer, (6 th) maximum convolution layer, (5 th) average convolution layer, (20 th) series layer, (25 th) one-dimensional convolution layer, (21 st) series layer, (26 th) one-dimensional convolution layer, (22 nd) series layer, (27 th) one-dimensional convolution layer, (23 th) series layer, (28 th) one-dimensional convolution layer, (7 th) maximum convolution layer, (6 th) average convolution layer, (24 th) series layer, (29 th) one-dimensional convolution layer, (30 th) one-dimensional convolution layer, (25 th) series layer, (31 th) one-dimensional convolution layer, (26 th) series layer, (32 th) one-dimensional convolution layer, (8 th) maximum convolution layer, (7 th) average convolution layer, (27 th) series layer, The (33 th) one-dimensional convolution layer, the (28 th) series layer, the (34 th) one-dimensional convolution layer, the (29 th) series layer, the (35 th) one-dimensional convolution layer, the (9 th) maximum pooling layer, the (8 th) average pooling layer, the (30 th) series layer, the (36 th) one-dimensional convolution layer, the (1 st) global average pooling layer, the (1 st) fully-connected dense layer, the (2 nd) fully-connected dense layer and the output layer.
(5) And (3) comparison and verification:
and for the convolutional neural network model obtained by training, performing comparison and verification based on clinical data, and performing iterative training according to a verification result.
The active 120 docking module is used for performing 120-call active intervention according to the diagnosis result of the artificial intelligence auxiliary diagnosis module, and specifically comprises the following steps:
if the diagnosis result is evaluated to be normal, the diagnosis result is sent to the user;
if the diagnosis result is evaluated to be slightly abnormal, the diagnosis result is sent to the user and the doctor, and whether the call center is triggered 120 is determined according to the secondary confirmation and interpretation result of the doctor;
if the diagnosis is assessed as critical, the diagnosis is sent to the user and the call center is triggered 120.
The invention establishes an active medical artificial intelligence service platform, further realizes an active 120 novel medical service mode, promotes the existing medical service to change to comprehension, intellectualization, precision and initiative, and is mainly embodied as follows:
(1) data sharing and medical collaboration:
based on data acquired by wearable equipment and evaluated by an artificial intelligence model, the data are simultaneously docked with data of systems such as HIS/LIS/PACS of a hospital, and a set of comprehensive, uniform and standardized resident major health database is established. Health monitoring, disease early warning, postoperative follow-up and health consultation of users with chronic diseases are realized. The artificial intelligence is used as a router of massive clinical medical data, and intelligent sharing of high-quality medical resources is achieved. The resident health big database is used as a link to connect patients, primary hospitals or community hospitals and large-scale third hospitals, and a hospital integrated cooperation platform is established. The system not only accords with the policy of national classification diagnosis and treatment, but also optimizes medical resources, is convenient for the primary difficult and serious patients to be quickly transferred to the third hospital, and leads the patients to enjoy more excellent diagnosis and treatment service of the third hospital. In addition, remote consultation, operation teaching and the like among medical conjuncted hospitals are beneficial to the improvement of diagnosis and treatment level, the improvement of working efficiency and the reduction of diagnosis and treatment risks of primary medical institutions.
(2) Passive rescue to active intervention:
through the acquisition and real-time monitoring of resident health data, utilize artificial intelligence to assist the aassessment simultaneously, carry out health early warning and early disease screening, realize "the prevention first before illness, have the disease and treat earlier". In addition, cooperation and data interconnection and intercommunication among the hospital bodies not only provide convenience for patient referral, but also can respond in time among the hospital bodies to compete for the 'gold time' for rescue. Meanwhile, through the combination of artificial intelligence assistance and initiative 120, doctors can timely know abnormal health data of patients and give scientific and accurate diagnosis. For critically ill patients, the doctor can trigger 120 the call center in time, and meanwhile, the basic data information of the patients and the diagnosis condition of the doctor also provide basis for pre-hospital first aid. Therefore, a full-flow closed-loop application service of linkage of the patient, the hospital and the first aid 120 is established, and the transition from a passive rescue to an active intervention medical service mode is realized.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (7)
1. An artificial intelligence based active 120 system, comprising:
the system comprises a user vital sign health data acquisition module, a diagnosis and treatment module and a health management module, wherein the user vital sign health data acquisition module is used for acquiring daily health data of a user through intelligent health wearing equipment and associating physical examination data of the user with medical data in the diagnosis and treatment process; uploading the user data to a cloud;
the artificial intelligence auxiliary diagnosis module is used for analyzing and screening the user health data, and an artificial intelligence analysis model is adopted for analysis and screening;
the active 120 docking module is used for performing 120-call active intervention according to the diagnosis result of the artificial intelligence auxiliary diagnosis module, and specifically comprises the following steps:
if the diagnosis result is evaluated to be normal, the diagnosis result is sent to the user;
if the diagnosis result is evaluated to be slightly abnormal, the diagnosis result is sent to the user and the doctor, and whether the call center is triggered 120 is determined according to the secondary confirmation and interpretation result of the doctor;
if the diagnosis is assessed as critical, the diagnosis is sent to the user and the call center is triggered 120.
2. The artificial intelligence based active 120 system of claim 1, wherein the intelligent health-wearing devices in the user cardiovascular health data collection module comprise single-lead or multi-lead electrocardiograph wearing devices.
3. The artificial intelligence based cardiovascular disease initiative 120 system of claim 1 wherein the artificial intelligence assisted diagnosis module is established by:
1) constructing a data set, wherein the data set is massive single-lead or twelve-lead electrocardiogram data;
2) data processing: carrying out data preprocessing on the acquired data, wherein the data preprocessing process comprises the following steps: data desensitization, data cleaning, noise reduction, standardization and normalization;
3) labeling data: labeling the abnormal physiological signal data by using a medical data labeling tool, wherein the labeling types are 18 classifications of clinical diagnosis statistics;
4) constructing a model: the data are divided into a training set and a verification set, a deep neural network model is trained on the basis of the training set, the deep neural network model is a convolutional neural network model for electrocardiosignal analysis, a four-classification method is adopted for single-lead electrocardio data to mainly diagnose atrial fibrillation, and an eighteen-classification method is adopted for twelve-lead electrocardio data to mainly diagnose normal and other 17 cardiovascular diseases of clinical statistics.
4. The artificial intelligence based initiative 120 system of claim 1 wherein the data processing in step 2) is specifically as follows:
data desensitization: removing patient-related sensitive information from the data set;
data cleaning: judging whether the acquired data is normally acquired data or not according to the diagnosis information of the doctor, and removing the abnormally acquired data;
noise reduction: filtering information which causes interference to the training result through band-pass filtering;
and (3) standardization: converting the data according to a specified standard, and storing the data according to a uniform format;
normalization: and limiting the value of the data in a certain range and meeting the specified distribution condition, so as to accelerate the training of the model and improve the precision of the model.
5. The artificial intelligence based initiative 120 system of claim 4 wherein the data processing in step 2) further comprises data slicing, the data slicing comprising either directly slicing the data by time according to the type of data or slicing the data according to the clinical significance of the data.
6. The artificial intelligence based active 120 system of claim 3, wherein the model building in step 4) comprises four classification model building, specifically, 88 layers of deep neural network model are adopted, sequentially comprising an input layer, a one-dimensional convolutional layer, a maximum pooling layer, a one-dimensional convolutional layer, a series layer, a one-dimensional convolutional layer, a maximum pooling layer, an average pooling layer, a series layer, a one-dimensional convolutional layer, an average pooling layer, a series layer, a one, A series layer, a one-dimensional convolutional layer, a maximum pooling layer, an average pooling layer, a series layer, a one-dimensional convolutional layer, a maximum pooling layer, an average pooling layer, a series layer, a one-dimensional convolutional layer, a maximum pooling layer, a series layer, a one-dimensional convolutional layer, a series layer, a one-dimensional convolutional layer, a maximum pooling layer, an average pooling layer, a series layer, a one-dimensional convolutional layer, a global average pooling layer, a one-dimensional convolutional layer, a series layer, the all-connected dense layer, the all-connected dense layer and the output layer.
7. The artificial intelligence based active 120 system of claim 3, wherein the modeling in step 4) comprises eighteen classification models, specifically, two true and false classifications are performed on each of eighteen classes, the two classification models are migration learning on the eighteen classes to obtain a final eighteen classification model, the two classification models are 88-layer deep neural network models, and are sequentially an input layer, a one-dimensional convolutional layer, a maximum pooling layer, a one-dimensional convolutional layer, a series layer, a one-dimensional convolutional layer, a maximum pooling layer, a one-dimensional convolutional layer, a series layer, a one-dimensional convolutional layer, a maximum pooling layer, an average pooling layer, a series layer, a one-dimensional convolutional layer, a series layer, a one-dimensional convolutional layer, a, One-dimensional convolutional layer, series layer, one-dimensional convolutional layer, maximum pooling layer, average pooling layer, series layer, one-dimensional convolutional layer, series layer, one-dimensional convolutional layer, maximum pooling layer, average pooling layer, etc, The device comprises a series layer, a one-dimensional convolution layer, a maximum pooling layer, an average pooling layer, a series layer, a one-dimensional convolution layer, a global average pooling layer, a fully connected dense layer and an output layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911359440.5A CN111128381A (en) | 2019-12-25 | 2019-12-25 | Active 120 system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911359440.5A CN111128381A (en) | 2019-12-25 | 2019-12-25 | Active 120 system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111128381A true CN111128381A (en) | 2020-05-08 |
Family
ID=70502445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911359440.5A Pending CN111128381A (en) | 2019-12-25 | 2019-12-25 | Active 120 system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111128381A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106790317A (en) * | 2015-11-18 | 2017-05-31 | 浪潮乐金数字移动通信有限公司 | A kind of wearable necklace equipment of intelligence and its application system |
| CN107529645A (en) * | 2017-06-29 | 2018-01-02 | 重庆邮电大学 | A kind of heart sound intelligent diagnosis system and method based on deep learning |
| CN109935319A (en) * | 2019-03-15 | 2019-06-25 | 南京邮电大学 | Chronic disease systematic management system |
-
2019
- 2019-12-25 CN CN201911359440.5A patent/CN111128381A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106790317A (en) * | 2015-11-18 | 2017-05-31 | 浪潮乐金数字移动通信有限公司 | A kind of wearable necklace equipment of intelligence and its application system |
| CN107529645A (en) * | 2017-06-29 | 2018-01-02 | 重庆邮电大学 | A kind of heart sound intelligent diagnosis system and method based on deep learning |
| CN109935319A (en) * | 2019-03-15 | 2019-06-25 | 南京邮电大学 | Chronic disease systematic management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107680676B (en) | Gestational diabetes prediction method based on electronic medical record data drive | |
| Smys et al. | Internet of things and big data analytics for health care with cloud computing | |
| CN112289437B (en) | Diabetes adjuvant therapy cloud platform system based on edge computing framework | |
| CN105162880A (en) | ACS (Acute Coronary Syndrome) regional synergistic treatment network system and assistant decision-making method thereof | |
| CN109009102B (en) | Electroencephalogram deep learning-based auxiliary diagnosis method and system | |
| CN111613335A (en) | Health early warning system and method | |
| CN109846474B (en) | Processing method and device of electrocardiogram and remote processing method and system of electrocardiogram | |
| CN107145715B (en) | Clinical medicine intelligence discriminating gear based on electing algorithm | |
| CN107887010A (en) | A kind of angiocardiopathy data acquisition examines platform with dividing | |
| CN113241196A (en) | Remote medical treatment and grading monitoring system based on cloud-terminal cooperation | |
| CN114048343A (en) | Classification platform covering medical image information of patients in whole disease course | |
| Yin et al. | Influence of optimization design based on artificial intelligence and internet of things on the electrocardiogram monitoring system | |
| CN111986812A (en) | Internet-based gynecological disease medical diagnosis and treatment control system | |
| Jameil et al. | Efficient cnn architecture on fpga using high level module for healthcare devices | |
| CN117476217B (en) | Chronic heart disease state of illness trend prediction system | |
| CN111403025A (en) | Intelligent diagnosis and treatment system based on internet medical service | |
| CN114242259A (en) | Advanced influenza condition prediction system, program product and establishing and using method thereof | |
| CN112735579A (en) | Rapid registration treatment system for emergency patients | |
| CN117292829A (en) | Graded diagnosis and treatment information system for coronary heart disease | |
| CN111128381A (en) | Active 120 system based on artificial intelligence | |
| CN116978510A (en) | Nursing grading evaluation system for home cerebral apoplexy patient | |
| KR20180002229A (en) | An agent apparatus for constructing database for dementia information and the operating method by using the same | |
| CN110223743A (en) | A kind of structuring processing method and system for pulmonary cancer diagnosis record | |
| CN115331837A (en) | Man-machine interaction intelligent inquiry system | |
| CN109659040A (en) | A kind of tele-medicine computer information system |
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 |