CN114550910A - Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system - Google Patents
Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system Download PDFInfo
- Publication number
- CN114550910A CN114550910A CN202210128146.9A CN202210128146A CN114550910A CN 114550910 A CN114550910 A CN 114550910A CN 202210128146 A CN202210128146 A CN 202210128146A CN 114550910 A CN114550910 A CN 114550910A
- Authority
- CN
- China
- Prior art keywords
- heart failure
- data
- diagnosis
- ejection fraction
- patient
- 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
- G16H50/20—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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0883—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the heart
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Heart & Thoracic Surgery (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Epidemiology (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Cardiology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses an ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence, which comprises an input unit module, a diagnosis unit module, a data matching module and an output unit module, wherein the input unit module is used for inputting heart failure symptoms and physical examination result characteristics of a patient to be diagnosed, the diagnosis unit module is used for training an initial ejection fraction retention type heart failure diagnosis neural network model according to a large amount of heart failure patient historical data to obtain corresponding relations between patient symptom data and heart failure types and ejection fraction retention type heart failure clinical subtypes, the data matching module is used for matching the patient data to be diagnosed into the corresponding relations to generate corresponding matching diagnosis reports, and the output unit module is used for outputting the heart failure types and the ejection fraction retention type heart failure clinical subtypes of the patient to be diagnosed. The ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence can help clinicians to improve diagnosis efficiency and reduce missed diagnosis and misdiagnosis.
Description
Technical Field
The invention belongs to the technical field of medical diagnosis systems, and relates to an ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence.
Background
Heart failure (heart failure) is the severe and terminal stage of all cardiovascular diseases and is an important component in the prevention and treatment of chronic cardiovascular diseases worldwide. With the aging of the population becoming worse, the survival rate of myocardial infarction increasing and the life of heart failure patients (heart failure) being prolonged, about 6000 million people are affected by the heart failure all over the world at present. Clinically, heart failure with reduced ejection fraction (HFrEF), midrange heart failure and heart failure with preserved ejection fraction (HFpEF) are classified according to the high or low left ventricular ejection fraction, with HFpEF accounting for up to 50%, which has become one of the most common types of heart failure.
Because HFpEF has the characteristics of complex clinical phenotype, multiple complications, systemic inflammation and multiple organ injury, the medicines for treating HFrEF cannot effectively improve the clinical prognosis and long-term survival rate of HFpEF patients, and no clear diagnosis method of HFpEF suitable for the patients exists at present. Diagnosis and treatment of HFpEF patients are still difficult in management of chronic diseases, and huge economic and health burden is brought to public health.
According to the definition of the 2016 society for european cardiology, diagnosis of HFpEF can be considered from the following 4 points: (1) the presence of symptoms and/or signs of heart failure (but may not be present in patients in the early phase of heart failure or after diuretic treatment); (2) retained LVEF (greater than or equal to 50%); (3) elevated levels of natriuretic peptide [ BNP >35pg/ml and/or NT-proBNP >125pg/ml ]; (4) there is at least the following 1: related structural heart disease [ left ventricular hypertrophy and/or left atrial enlargement ]; (ii) objective evidence of left ventricular diastolic dysfunction. The last 1 item usually needs to obtain evidence through objective examination such as imaging, particularly echocardiogram and the like, but the steps of the diagnosis method are complicated, the echocardiogram has no specificity to the interpretation index of the diastolic function, and certain operability is lacked for partial specialist doctors and basic doctors, so missed diagnosis and misdiagnosis are easily caused.
Disclosure of Invention
The invention aims to provide an ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence, which has strong operability and can help clinicians to improve diagnosis efficiency and reduce missed diagnosis and misdiagnosis.
It is another object of the invention to provide a computer apparatus.
The invention adopts a first technical scheme that the ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence comprises an input unit module, a diagnosis unit module, a data matching module and an output unit module which are sequentially associated, wherein the input unit module is used for inputting heart failure symptoms and physical examination result characteristics of a patient to be diagnosed, the diagnosis unit module is used for training an initial ejection fraction retention type heart failure diagnosis neural network model according to a large amount of historical data of the heart failure patient to obtain corresponding relations between the heart failure symptoms and the physical examination result characteristics of the patient and the clinical subtypes of the heart failure and the ejection fraction retention type heart failure, the data matching module is used for matching the heart failure symptoms and the physical examination result characteristics of the patient to be diagnosed into the corresponding relations, and generating a corresponding matching diagnosis report, wherein the output unit module is used for outputting the heart failure type of the patient to be diagnosed and the clinical subtype of the ejection fraction retention type heart failure patient.
The diagnosis unit module comprises a model training subunit module and is used for training an initial ejection fraction retention type heart failure diagnosis neural network model according to a large amount of heart failure patient historical data to obtain the ejection fraction retention type heart failure diagnosis neural network model, namely a corresponding relation model of patient heart failure symptoms, physical examination result characteristics, heart failure types and ejection fraction retention type heart failure clinical subtypes.
The model training subunit module comprises a data input module, an initial diagnosis module and a diagnosis typing module.
The data input module is used for acquiring a large amount of heart failure patient historical data, setting a data preprocessing rule, and processing data information through the data preprocessing rule to obtain a diagnosis data set, wherein the heart failure patient historical data is heart failure symptom and physical examination result characteristic data, and the physical examination result characteristic data comprises cardiac ultrasound, electrocardiogram, blood pressure, serum cholesterol, liver and kidney function, electrolytes, blood routine, cardiac enzyme, brain sodium titanium, coronary heart disease history and fasting blood sugar.
The data preprocessing rule comprises data type transformation, data filling and data deletion, the data type transformation comprises binary data transformation and multi-valued data transformation, and the data filling is to perform mean filling on null value fields of all items so as to improve the accuracy of model training.
When the data input module acquires heart ultrasonic image type data of an HFpEF patient, intercepting an interested area of a heart ultrasonic image by adopting a fast R-CNN model, highlighting the interested area through image enhancement processing, realizing heart ultrasonic standard section structure detection and identification in the interested area based on a DSSD-inclusion-V3 model, intercepting a structure abnormal area, measuring the sizes of a left ventricle, a right ventricle, a left atrium and a right atrium based on the length-width ratio of a connected component circumscribed rectangle, outputting a measurement result, realizing the judgment of diastolic function insufficiency according to heart structure parameters, functional parameters and corresponding size parameters, finally acquiring historical heart failure basic data information and corresponding heart failure type labeling types according to the heart failure basic data information, and performing type labeling on the heart failure data information according to the historical heart failure basic data information and the corresponding heart failure type labeling types, while correlating with the heart failure data set.
The initial diagnosis module is used for randomly dividing the symptom data set and the heart ultrasonic image data set into a training set, a verification set and a test set, respectively inputting medical case data in the corresponding training set and the corresponding verification set to the initial ejection fraction retention type heart failure diagnosis neural network model for model training, and stopping training when training conditions are met to obtain the trained ejection fraction retention type heart failure diagnosis neural network model.
The neural network model for diagnosing the heart failure with the preserved initial ejection fraction is as follows:
the method comprises the steps of obtaining a semantic attribute prediction layer of ejection fraction retention type heart failure and a semantic attribute prediction vector according to mapping between an image and the semantic attribute, generating mapping from the semantic attribute prediction vector to a word sequence through an LSTM model, and finally outputting the word sequence describing the marked ejection fraction retention type heart failure.
The diagnosis typing module is used for further obtaining the corresponding relation between the patient symptoms and the physical examination result characteristics and the clinical subtype of the heart failure type and ejection fraction retention type by adopting a clustering analysis method according to the symptoms of the heart failure patient and the physical examination result characteristics.
A second technical solution adopted by the present invention is a computer device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the computer program is the above-mentioned ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence.
The invention has the advantages that the ejection fraction retention type heart failure diagnosis and typing system is formed by the input unit module, the diagnosis unit module, the data matching module and the output unit module, the heart failure symptom and the physical examination result characteristic of a patient to be diagnosed are input by the input unit module, the corresponding relation between the heart failure symptom and the physical examination result characteristic of the patient to be diagnosed and the heart failure type and the ejection fraction retention type heart failure clinical subtype is obtained by the diagnosis unit module, the heart failure symptom and the physical examination result characteristic of the patient to be diagnosed are matched into the corresponding relation by the data matching module to generate a corresponding matching diagnosis report, and finally the heart failure type and the ejection fraction retention type heart failure clinical subtype of the patient to be diagnosed are output by the output unit module Misdiagnosis occurs, and operability is strong.
Drawings
FIG. 1 is a schematic structural diagram of an ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence;
fig. 2 is a schematic view of the working flow of the diagnosis unit module in the system for diagnosing and typing heart failure based on artificial intelligence and preserved ejection fraction.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention relates to an ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence, which comprises an input unit module, a diagnosis unit module, a data matching module and an output unit module which are sequentially associated, wherein the input unit module is used for inputting heart failure symptoms and physical examination result characteristics of a patient to be diagnosed, the diagnosis unit module is used for training an initial ejection fraction retention type heart failure diagnosis neural network model according to a large amount of historical data of the heart failure patient to obtain the corresponding relation between the heart failure symptoms and the physical examination result characteristics of the patient and the types of the heart failure and the clinical subtypes of the ejection fraction retention type heart failure, the data matching module is used for matching the heart failure symptoms and the physical examination result characteristics of the patient to be diagnosed into the corresponding relation, and generating a corresponding matching diagnosis report, wherein the output unit module is used for outputting the heart failure type of the patient to be diagnosed and the clinical subtype of the ejection fraction retention type heart failure patient.
Referring to fig. 2, the diagnosis unit module includes a model training subunit module, configured to train an initial ejection fraction retention type heart failure diagnosis neural network model according to a large amount of heart failure patient history data, and obtain an ejection fraction retention type heart failure diagnosis neural network model, that is, a corresponding relationship model between patient heart failure symptoms, physical examination result characteristics, and heart failure types and ejection fraction retention type heart failure clinical subtypes.
The model training subunit module comprises a data input module, an initial diagnosis module and a diagnosis typing module. The data input module is used for acquiring a large amount of heart failure patient historical data, setting a data preprocessing rule, and processing data information through the data preprocessing rule to obtain a diagnosis data set, wherein the heart failure patient historical data is heart failure symptom and physical examination result characteristic data, and the physical examination result characteristic data comprises cardiac ultrasound, electrocardiogram, blood pressure, serum cholesterol, liver and kidney function, electrolytes, blood routine, cardiac enzyme, brain sodium titanium, coronary heart disease history and fasting blood sugar.
The data preprocessing rules comprise data type conversion, data filling and data deletion, wherein the data type conversion comprises binary data conversion (for example, a sex field is male or female, namely, the sex field can respectively represent '0' or '1') and multi-value data conversion (for example, symptoms of chest distress, 'shortness of breath', 'hypodynamia' and 'no symptoms', namely, '1', '2', '3' and '4'), and the data filling is used for carrying out mean filling on null value fields of various items (such as patient ID, identity card number, age, sex, blood pressure, serum cholesterol, liver and kidney functions, electrolytes, blood routine, cardiac enzyme, brain natrium titanium, diabetes history, coronary heart disease history, fasting blood sugar, smoking, drinking and the like) so as to improve the accuracy of model training.
When the data input module acquires heart ultrasonic image type data of an HFpEF patient, intercepting an interested area of a heart ultrasonic image by adopting a fast R-CNN model, highlighting the interested area through image enhancement processing, realizing heart ultrasonic standard section structure detection and identification in the interested area based on a DSSD-inclusion-V3 model, intercepting a structure abnormal area, measuring the sizes of a left ventricle, a right ventricle, a left atrium and a right atrium based on the length-width ratio of a connected component circumscribed rectangle, outputting a measurement result, realizing the judgment of diastolic function insufficiency according to heart structure parameters, functional parameters and corresponding size parameters, finally acquiring historical heart failure basic data information and corresponding heart failure type labeling types according to the heart failure basic data information, and performing type labeling on the heart failure data information according to the historical heart failure basic data information and the corresponding heart failure type labeling types, while correlating with the heart failure data set.
The initial diagnosis module is used for randomly dividing the symptom data set and the heart ultrasonic image data set into a training set, a verification set and a test set, respectively inputting medical case data in the corresponding training set and the corresponding verification set to the initial ejection fraction retention type heart failure diagnosis neural network model for model training, and stopping training when training conditions are met to obtain the trained ejection fraction retention type heart failure diagnosis neural network model.
The neural network model for diagnosing the heart failure with the preserved initial ejection fraction is as follows:
the method comprises the steps of obtaining a semantic attribute prediction layer of ejection fraction retention type heart failure and a semantic attribute prediction vector according to mapping between an image and the semantic attribute, generating mapping from the semantic attribute prediction vector to a word sequence through an LSTM model, and finally outputting the word sequence describing the marked ejection fraction retention type heart failure.
The diagnosis typing module is used for further obtaining the corresponding relation between the patient symptoms and the physical examination result characteristics and the clinical subtype of the heart failure type and ejection fraction retention type by adopting a clustering analysis method according to the symptoms of the heart failure patient and the physical examination result characteristics.
The invention provides computer equipment, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the computer program is the ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence.
Claims (10)
1. An ejection fraction retention type heart failure diagnosis and typing system based on artificial intelligence is characterized by comprising an input unit module, a diagnosis unit module, a data matching module and an output unit module which are sequentially associated, wherein the input unit module is used for inputting heart failure symptoms and physical examination result characteristics of a patient to be diagnosed, the diagnosis unit module is used for training an initial ejection fraction retention type heart failure diagnosis neural network model according to a large amount of historical data of the heart failure patient to obtain corresponding relations among the heart failure symptoms and the physical examination result characteristics of the patient, the heart failure types and the ejection fraction retention type heart failure clinical subtypes, the data matching module is used for matching the heart failure symptoms and the physical examination result characteristics of the patient to be diagnosed into the corresponding relations, and generating a corresponding matching diagnosis report, wherein the output unit module is used for outputting the heart failure type of the patient to be diagnosed and the clinical subtype of the ejection fraction retention type heart failure patient.
2. The system of claim 1, wherein the diagnosis unit module comprises a model training subunit module for training an initial ejection fraction-preserved heart failure diagnosis neural network model according to a plurality of heart failure patient history data to obtain an ejection fraction-preserved heart failure diagnosis neural network model, i.e. a corresponding relationship model between patient heart failure symptoms, physical examination result characteristics and heart failure types and ejection fraction-preserved heart failure clinical subtypes.
3. The system of claim 2, wherein the model training subunit module comprises a data input module, an initial diagnosis module and a diagnosis typing module.
4. The system of claim 3, wherein the data input module is configured to obtain a large amount of heart failure patient history data, set data preprocessing rules, and process data information according to the data preprocessing rules to obtain a diagnosis data set, wherein the heart failure patient history data is heart failure symptoms and physical examination result characteristic data, and the physical examination result characteristic data includes cardiac ultrasound, electrocardiogram, blood pressure, serum cholesterol, liver and kidney function, electrolytes, blood routine, cardiac myozyme, brain natrium titanium, coronary heart disease history, and fasting plasma glucose.
5. The system of claim 4, wherein the data preprocessing rules comprise data type transformation, data filling and data deletion, the data type transformation comprises binary data transformation and multi-valued data transformation, and the data filling is to perform mean filling on null value fields of each item so as to improve the accuracy of model training.
6. The system of claim 5, wherein when the data input module obtains the heart ultrasound image data of the HFpEF patient, the data input module intercepts the region of interest of the heart ultrasound image based on the Faster R-CNN model, and highlights the region of interest through image enhancement, and implements the detection and identification of the standard tangent plane structure of the heart ultrasound in the region of interest based on the DSSD _ Inception _ V3 model, and intercepts the abnormal structure region, and implements the measurement of the sizes of the left ventricle, the right ventricle, the left atrium and the right atrium based on the length-width ratio of the rectangle circumscribed by the connected component, outputs the measurement result, implements the judgment of diastolic dysfunction according to the structural parameters, the functional parameters and the corresponding size parameters of the heart, and finally obtains the historical heart failure basic data information and the corresponding heart failure type labeling categories according to the heart failure basic data information, and performing type marking on the heart failure data information according to the historical heart failure basic data information and the corresponding heart failure type marking category, and associating with the heart failure data set.
7. The system of claim 3, wherein the initial diagnosis module is configured to randomly divide the symptom data set and the cardiac ultrasound image data set into a training set, a verification set, and a test set, and then input medical record data in the training set and the verification set to the initial ejection fraction-preserving heart failure diagnosis neural network model for model training, and stop training when a training condition is met, so as to obtain the trained ejection fraction-preserving heart failure diagnosis neural network model.
8. The system of claim 7, wherein the neural network model for diagnosing and typing heart failure with preserved ejection fraction based on artificial intelligence is:
the method comprises the steps of obtaining a semantic attribute prediction layer of ejection fraction retention type heart failure and a semantic attribute prediction vector according to mapping between an image and the semantic attribute, generating mapping from the semantic attribute prediction vector to a word sequence through an LSTM model, and finally outputting the word sequence describing the marked ejection fraction retention type heart failure.
9. The system of claim 8, wherein the diagnosis and typing module is further configured to use a cluster analysis method to obtain the correspondence between the patient symptoms and the physical examination result characteristics and the clinical subtypes of heart failure and ejection fraction-preserved heart failure according to the patient symptoms and the physical examination result characteristics.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being the artificial intelligence based ejection fraction preserving heart failure diagnosis and typing system of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210128146.9A CN114550910A (en) | 2022-02-10 | 2022-02-10 | Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210128146.9A CN114550910A (en) | 2022-02-10 | 2022-02-10 | Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114550910A true CN114550910A (en) | 2022-05-27 |
Family
ID=81674365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210128146.9A Pending CN114550910A (en) | 2022-02-10 | 2022-02-10 | Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114550910A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114831643A (en) * | 2022-07-04 | 2022-08-02 | 南京大学 | Electrocardiosignal monitoring devices and wearable equipment |
-
2022
- 2022-02-10 CN CN202210128146.9A patent/CN114550910A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114831643A (en) * | 2022-07-04 | 2022-08-02 | 南京大学 | Electrocardiosignal monitoring devices and wearable equipment |
| CN114831643B (en) * | 2022-07-04 | 2022-10-04 | 南京大学 | Electrocardiosignal monitoring devices and wearable equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11864944B2 (en) | Systems and methods for a deep neural network to enhance prediction of patient endpoints using videos of the heart | |
| Acharya et al. | Deep convolutional neural network for the automated diagnosis of congestive heart failure using ECG signals | |
| Amal et al. | Use of multi-modal data and machine learning to improve cardiovascular disease care | |
| WO2021120936A1 (en) | Chronic disease prediction system based on multi-task learning model | |
| EP4042445A1 (en) | Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems | |
| Zhang et al. | Semi-supervised learning for automatic atrial fibrillation detection in 24-hour Holter monitoring | |
| Akerman et al. | Automated echocardiographic detection of heart failure with preserved ejection fraction using artificial intelligence | |
| CN109907751B (en) | Laboratory chest pain data inspection auxiliary identification method based on artificial intelligence supervised learning | |
| CN110010250B (en) | Cardiovascular disease patient weakness grading method based on data mining technology | |
| Luo et al. | Multi-Task Learning Using Attention-Based Convolutional Encoder-Decoder for Dilated Cardiomyopathy CMR Segmentation and Classification. | |
| Sujatha et al. | Heart Failure Patient Survival Analysis with Multi Kernel Support Vector Machine. | |
| Sanders Jr et al. | Machine learning: at the heart of failure diagnosis | |
| Negi et al. | Machine Learning-Based Analysis of Echocardiography Images for Cardiac Disease Diagnosis | |
| RU2704913C1 (en) | Neural network analysis method of cardiac condition | |
| CN114550910A (en) | Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system | |
| Andry et al. | Electronic health record to predict a heart attack used data mining with Naïve Bayes method | |
| CN113128654A (en) | Improved random forest model for coronary heart disease pre-diagnosis and pre-diagnosis system thereof | |
| CN116230224A (en) | Method and system for predicting adverse events of heart failure based on time sequence model | |
| CN113449757A (en) | Construction method and construction system of heart failure diagnosis model and heart failure diagnosis device | |
| Plati et al. | Machine learning techniques for predicting and managing heart failure | |
| Brohet et al. | Computer interpretation of pediatric orthogonal electrocardiograms: statistical and deterministic classification methods. | |
| Ulloa et al. | A deep neural network to enhance prediction of 1-year mortality using echocardiographic videos of the heart | |
| González et al. | Multi-modal heart failure risk estimation based on short ECG and sampled long-term HRV | |
| Luo et al. | Artificial intelligence-enabled 8-lead ECG detection of atrial septal defect among adults: A novel diagnostic tool | |
| Botros et al. | Detection of Heart Failure Using a Convolutional Neural Network via ECG Signals |
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 |