WO2022197037A1 - Appareil et procédé de prédiction d'un pronostic de fibrillation auriculaire - Google Patents

Appareil et procédé de prédiction d'un pronostic de fibrillation auriculaire Download PDF

Info

Publication number
WO2022197037A1
WO2022197037A1 PCT/KR2022/003532 KR2022003532W WO2022197037A1 WO 2022197037 A1 WO2022197037 A1 WO 2022197037A1 KR 2022003532 W KR2022003532 W KR 2022003532W WO 2022197037 A1 WO2022197037 A1 WO 2022197037A1
Authority
WO
WIPO (PCT)
Prior art keywords
atrial fibrillation
information
patient
invasive clinical
calculating
Prior art date
Application number
PCT/KR2022/003532
Other languages
English (en)
Korean (ko)
Inventor
박희남
권오석
Original Assignee
연세대학교 산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from KR1020210035138A external-priority patent/KR102559908B1/ko
Priority claimed from KR1020210116405A external-priority patent/KR20220145737A/ko
Application filed by 연세대학교 산학협력단 filed Critical 연세대학교 산학협력단
Publication of WO2022197037A1 publication Critical patent/WO2022197037A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
    • A61B18/04—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating
    • A61B18/12—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating by passing a current through the tissue to be heated, e.g. high-frequency current
    • A61B18/14—Probes or electrodes therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A61B5/346—Analysis of electrocardiograms
    • A61B5/349—Detecting specific parameters of the electrocardiograph cycle
    • A61B5/361—Detecting fibrillation
    • 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
    • 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
    • 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
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Definitions

  • the present invention relates to a prognosis prediction apparatus and method for atrial fibrillation. More particularly, it relates to an apparatus and method for predicting the prognosis of atrial fibrillation using non-invasive clinical information and electrocardiogram information that can be easily obtained through a simple examination.
  • the present invention relates to a new and innovative technology that can minimize the physical and economic burden of a patient quickly and with high accuracy in predicting the prognosis of atrial fibrillation by reflecting these conventional problems.
  • a method for predicting atrial fibrillation prognosis includes the steps of: (a) receiving, by an atrial fibrillation prognosis prediction apparatus, any one or more of non-invasive clinical information and electrocardiogram information about a patient , (b) performing, by the atrial fibrillation prognosis predicting device, pre-processing on any one or more of the received non-invasive clinical information and electrocardiogram information for the patient, and (c) the atrial fibrillation prognosis predicting device performing the pre-processing inputting any one or more of non-invasive clinical information and electrocardiogram information about the patient who performed .
  • the predictive model may include: (M-1) receiving one or more selections of information received from non-invasive clinical information and electrocardiogram information from a user, (M-2) using the selected information from the user Selecting a predictor variable for invasive clinical information to be predicted, (M-3) receiving a range of hyperparameters from the user, and (M-4) specifying the range through a grid search manager It can be created by performing a search for the received hyperparameter.
  • step (c) when the information received in step (a) is electrocardiogram information for the patient, step (c) includes, (c-1') electrocardiogram information for the patient who has performed the pre-processing Entering the predictive model and extending it to a third format for a convolution operation, (c-2') Normalizing the ECG information for the patient expanded to the third format based on the number of patients and the number of leads step, (c-3'-1) applying a convolution layer to the normalized electrocardiogram information for the patient, batch normalization, and applying a Leaky ReLU activation function to expand to a fourth form step, (c-3'-2) applying a pooling layer to the electrocardiogram information for the patient expanded in the fourth format to expand to a fifth format, and (c-4') to the fifth format It may include the step of flattening the electrocardiogram information for the expanded patient in the form of a neural network calculation.
  • step (c) when the information received in step (a) is non-invasive clinical information and electrocardiogram information about the patient, step (c) includes: (c-5) of the information input to the predictive model. Determining whether there are a plurality of types and (c-6) If, as a result of the determination in step (d-1), there are a plurality of types of input information, the non-invasive clinical information and the electrocardiogram for the flattened patient are used as the predictive model It may include the step of applying a concatenate layer by inputting into .
  • the computer program stored in the medium according to another embodiment of the present invention for achieving the above technical problem is combined with a computing device, (AA) receiving any one or more of non-invasive clinical information and electrocardiogram information about the patient, (BB) performing pre-processing on any one or more of the received non-invasive clinical information and electrocardiogram information for the patient; is input to the prediction model and outputting any one of the prediction result of the invasive clinical prognosis for the patient and the prediction result of the invasive clinical information for the patient is executed.
  • the predicted value of step (c) is based on a score calculated through a risk model represented by five clinical indices determined using the Youden index and the probability value that electrode catheter ablation is suitable for the patient.
  • the patient group including the patient is divided into a plurality of quantile groups, and when the probability value that electrode catheter ablation is suitable for the patient is calculated using one or more non-invasive clinical indicators of step (a) for the patient, the plurality of Among the groups of quantiles, it may be any one or more of probability values of belonging to a certain group.
  • the first type may be [M ⁇ 15 ⁇ 1]
  • the second type may be [M ⁇ 15 ⁇ 8].
  • the atrial fibrillation prognosis prediction apparatus if the user selects the type of information received and the predictor variables related to the invasive clinical prognosis and invasive clinical information, which are the prognosis of atrial fibrillation to be predicted, the atrial fibrillation prognosis prediction apparatus has very high accuracy. This has the effect of being able to quickly output the prediction results.
  • the user simply selects the Nth atrial fibrillation factor that the user wants to calculate, and the device for calculating the predicted value of the atrial fibrillation factor calculates one or more non-invasive clinical indicators related to the Nth atrial fibrillation factor from a plurality of clinical indicators. and inputting the patient's non-invasive clinical information into the predictive model to automatically calculate and output the predicted value of the Nth atrial fibrillation factor, which provides high accuracy This has the effect of being able to predict quickly and at the same time dramatically improving user convenience.
  • FIG. 2 is a flowchart illustrating representative steps of a method for predicting the prognosis of atrial fibrillation according to a second embodiment of the present invention.
  • FIG. 5 is a diagram exemplarily illustrating a state in which missing values are estimated and written in the non-invasive clinical information shown in FIG. 4 in a table.
  • FIG. 6 is a diagram exemplarily illustrating a state in which missing values entered by table estimation of the non-invasive clinical information shown in FIG. 5 are changed.
  • step S230-5 and step S230-5 of determining whether there are a plurality of types of information input to the prediction model in step S230 if there are a plurality of types of input information, [M ⁇ C FC ] and S230 of step S230-4 by further including the step (S230-6) of applying a concatenate layer by inputting non-invasive clinical information and electrocardiogram for the flattened patient into the predictive model [M ⁇ E FC ] in step -4′ to [M ⁇ (C FC + E FC )]
  • FIG. 17 is a schematic diagram showing the prediction model.
  • the upper left side of the schematic diagram is according to non-invasive clinical information about the patient, and the right side is according to the electrocardiogram for the patient. Since it proceeds to step -7 (or the same S230-7'), if they are connected, explanations will be possible with the flowchart shown in FIG. 14 and the flowchart shown in FIG. 15, respectively.
  • the left atrial wall stress an invasive clinical prognosis, through the non-invasive clinical information of the patient: Type of AF, Hypertension, Disbetes mellitus, Vascular disease, Heart failure, LVEF, E/EM.
  • Prediction results of the left atrial hypotension which is an invasive clinical prognosis through the non-invasive clinical information Age, Sex, type of AF, CHARDsVASc score, LA size, E/Em, Hb, PR interval, and invasive clinical information through electrocardiogram information
  • the prediction result of left atrial voltage and electrocardiogram information show the prediction results of the type, gender, and age of atrial fibrillation, which are invasive clinical information, by way of example. It goes without saying that you can contribute to that.
  • FIG. 1 is a view showing the overall configuration included in the apparatus 100 for calculating a predictive value of atrial fibrillation-related factor according to a fourth embodiment of the present invention.
  • the memory 30 stores various data, commands and/or information, and one or more computer programs 41 from the storage 40 in order to perform the method for calculating the predicted values of the atrial fibrillation-related factors according to the fifth embodiment of the present invention. can be loaded.
  • RAM is illustrated as one of the memories 30 in FIG. 1 , it goes without saying that various storage media can be used as the memory 30 .
  • the storage 40 may non-temporarily store one or more computer programs 41 and a large amount of network data 42 .
  • the storage 40 is a non-volatile memory such as a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, or in the art to which the present invention pertains. It may be any one of widely known computer-readable recording media.
  • the apparatus 100 for calculating a predictive value of atrial fibrillation-related factor may be a physically independent electronic device, but one or more ratios of a patient from a server (not shown) operated by a medical institution such as a hospital. Since invasive clinical information needs to be received, it can be implemented as a function of the server.
  • the server may be a tangible physical server or a virtual cloud server.
  • 19 is a flowchart illustrating representative steps of a method for calculating a predicted value of an atrial fibrillation-related factor according to a fifth embodiment of the present invention.
  • the apparatus 100 for calculating the predicted value of the atrial fibrillation factor calculates one or more non-invasive clinical indicators related to the Nth (N is a natural number) atrial fibrillation factor from among the plurality of clinical indicators (S1210).
  • step S1210 is a flowchart illustrating detailed steps included in step S1210 in the method for calculating the predicted value of the atrial fibrillation factor according to the fifth embodiment of the present invention, and more specifically, the apparatus 100 for calculating the predicted value of the atrial fibrillation factor.
  • step S1210 is a flowchart of a specific method for calculating one or more non-invasive clinical indicators related to the Nth atrial fibrillation factor.
  • one or more non-invasive clinical indicators are selected from among a plurality of clinical indicators, one or more non-invasive clinical indicators selected by the apparatus 100 for calculating a predictive value of atrial fibrillation-related factors are used as independent variables, Nth atrial fibrillation related One or more noninvasive clinical indicators with a P-Value of less than 0.05 by defining factors as dependent variables and applying linear regression analysis to one or more noninvasive clinical indicators related to the Nth atrial fibrillation factor It is calculated as an index (S1210-2).
  • Linear regression analysis is a representative technique of supervised learning. It is a statistical technique that can infer the effect of one or more variables on another variable.
  • the influencing variable is called an independent variable or explanatory variable.
  • Variables affected by are called dependent variables or response variables, and there are simple linear regression models, multiple regression models, polynomial regression models, and nonlinear regression models.
  • one or more non-invasive clinical indicators are the independent variable, Nth atrial fibrillation.
  • a related factor is defined as a dependent variable, and when the P-Value is less than 0.05, it can act as a standard that can be considered statistically significant, but it may be increased or decreased in part according to the user's setting.
  • the user's doctor wants to widely calculate one or more non-invasive clinical indicators related to the Nth atrial fibrillation factor, it may be set based on a number greater than 0.05, and the user's doctor may set the Nth If you want to strictly calculate one or more non-invasive clinical indicators related to atrial fibrillation factors, you can give freedom by setting a number smaller than 0.05 as a standard.
  • one or more non-invasive clinical indicators related to suitability for catheter ablation calculated according to step S1210 are age (Age), Sex, Type of atrial fibrillation, Body mass index, Congestive heart failure, Hypertension, Diabetes mellitus, Stroke or transient ischemia Stroke or TIA, vascular disease, left atrium size (LA dimension), left ventricular ejection fraction (LV ejection fraction), and mitral valve maximal blood flow velocity versus mitral valve inner ring peak blood flow velocity in cardiac Doppler histology images.
  • the patient corresponding to the one or more non-invasive clinical indicators calculated by the atrial fibrillation factor predictive value calculating device 100 .
  • Pre-processing is performed on one or more non-invasive clinical information of (S1220).
  • the pre-processing corresponds to a process for conforming to a format or standard that can be input to the predictive model in step S1230 to be described later, and will be described with reference to FIG. 22 .
  • the non-invasive clinical information received for a specific patient is shown in a table format in FIG. 4 , and it can be confirmed that the “systolic blood pressure” item among various non-invasive clinical information for the patient “Hong Gil-dong” is empty.
  • the absence of a value for a specific item included in the non-invasive clinical information is called a missing value, and a plurality of missing values may exist for the non-invasive clinical information for a specific patient. Treatment for all patients This is because the results and the type of test performed may be different.
  • step S1220-1 if there is a missing value, the apparatus 100 for calculating the predicted value of the atrial fibrillation-related factor estimates and writes the missing value based on the learning data (S1220-2).
  • step S1220-3 step S1220-3 is not performed, and the apparatus 100 for calculating a predicted value of atrial fibrillation-related factor estimates a missing value and performs normalization on the written non-invasive clinical information (S1220) -4) and the step (S1220-5) of encoding non-invasive clinical information subjected to normalization may be performed, which corresponds to a known technique commonly performed in the pre-processing process for information, detailed description is omitted, and through this, non-invasive clinical information about the patient is converted into a machine-readable state.
  • step S1220-4 may be directly performed without going through steps S1220-2 and S1220-3. In this case, step S1220-4 is missing value estimation. and simply performing normalization regardless of writing.
  • the atrial fibrillation-related factor prediction value calculating device 100 predicts one or more non-invasive clinical information of the patient who has performed the pre-processing
  • the predicted value of the N-th atrial fibrillation factor for the patient is calculated and output by input to the model (S1230).
  • a convolution layer is applied to one or more non-invasive clinical information of a patient normalized by the apparatus 100 for calculating a predictive value of atrial fibrillation-related factors (2D Convolution), batch normalization (Batch Normalization), and Leaky ReLU activation
  • 2D Convolution a predictive value of atrial fibrillation-related factors
  • Batch Normalization batch normalization
  • Leaky ReLU activation The function is applied and extended to the second form (S1230-3).
  • the atrial fibrillation-related factor prediction value calculation apparatus 100 flattens one or more non-invasive clinical information of the patient expanded in the second format for neural network calculation (S1230-4).
  • a Fully Connected Layer is applied to one or more non-invasive clinical information of the patient flattened by the apparatus 100 for calculating the predictive value of the atrial fibrillation factor, batch normalization, and the ReLU activation function is applied. and a dropout layer is applied (S1230-5).
  • the output layer can finally output [M ⁇ Y] as the predicted value of the Nth atrial fibrillation factor for the patient through the [M ⁇ FC N N ] ⁇ [FC N N ⁇ Y] neural network operation, and the predictor variable Y
  • the first case is [M ⁇ 4] ⁇ [4 ⁇ 3] in the output layer, finally [M ⁇ 3] through the neural network operation.
  • M ⁇ 4 the predicted value for the individual left atrial wall stress of the patient through the sigmoid function (or the Softmax function is also possible).
  • Steps S1230-1 and S1230-6 described above are steps made inside the predictive model, and when viewed from the outside, they will be treated as black box-processed, but a conceptual description has been made for the understanding of the invention.
  • the appearance of the predictive model in the case is shown as an example of the predictive model in the second case in Fig. 25, and since the predictive model described above is a deep learning-based model, learning data is accumulated by continuous use As the use is repeated through this, the accuracy and speed of the prediction value calculation may be improved.
  • the predicted value calculated and output in step S1230 may be in the form of a probability value, for example, Nth atrial fibrillation related factor.
  • the step of verifying the calculated and output predicted value of the atrial fibrillation factor related to the Nth may be further performed. Bar, this is an additional step that can be applied to the first case.
  • All of the above five clinical indicators are independently related to the progression of atrial fibrillation, and the STAAR score model can calculate a risk score for each patient through Cox regression analysis for the five clinical indicators.
  • the B coefficient and P-value are values obtained through Cox regression analysis, and the following Cox proportional hazards model can be obtained by performing multiple Cox regression analysis using five clinical indicators.
  • 27 is a result of evaluating the validity and performance of the STAAR score model, and more specifically, performing performance evaluation on 1,214 patients through five clinical indicators included in the STAAR score model.
  • FIG. 28 is a diagram exemplarily showing performance evaluation of the method for calculating the predicted value of atrial fibrillation-related factor according to the fifth embodiment of the present invention, and more specifically, the performance evaluation data in the first case.
  • the apparatus 100 for calculating the predicted value of the atrial fibrillation-related factor according to the fourth embodiment of the present invention and the predicted value of the atrial fibrillation-related factor according to the fifth embodiment of the present invention may be implemented as a computer program stored in the medium according to the sixth embodiment of the present invention including the same technical features.
  • the computer program stored in the medium is combined with a computing device, (AA) calculating one or more non-invasive clinical indicators related to the Nth (N is a natural number) atrial fibrillation factor among a plurality of clinical indicators, ( BB) performing pre-processing on one or more non-invasive clinical information of the patient corresponding to the calculated one or more non-invasive clinical indicators, and (C) inputting one or more non-invasive clinical information of the patient who performed the pre-processing into the predictive model
  • the step of calculating and outputting the predicted value of the Nth atrial fibrillation factor for the patient may be executed.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Surgery (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Physics & Mathematics (AREA)
  • Cardiology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Biophysics (AREA)
  • Robotics (AREA)
  • Plasma & Fusion (AREA)
  • Otolaryngology (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

Un procédé de prédiction d'un pronostic de fibrillation auriculaire selon un mode de réalisation de la présente invention comprend les étapes dans lesquelles : (a) un appareil de prédiction d'un pronostic de fibrillation auriculaire reçoit des informations cliniques et/ou des informations d'électrocardiogramme non invasives d'un patient ; (b) l'appareil de prédiction d'un pronostic de fibrillation auriculaire prétraite les informations cliniques et/ou les informations d'électrocardiogramme non invasives reçues du patient ; et (c) l'appareil de prédiction d'un pronostic de fibrillation auriculaire saisit les informations cliniques et/ou les informations d'électrocardiogramme non invasives prétraitées du patient dans un modèle de prédiction, pour émettre un résultat de prédiction d'un pronostic clinique invasif et/ou un résultat de prédiction d'informations cliniques invasives du patient.
PCT/KR2022/003532 2021-03-18 2022-03-14 Appareil et procédé de prédiction d'un pronostic de fibrillation auriculaire WO2022197037A1 (fr)

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
KR1020210035138A KR102559908B1 (ko) 2021-03-18 2021-03-18 심방세동의 예후 예측 장치 및 예측 방법
KR10-2021-0035138 2021-03-18
KR10-2021-0052459 2021-04-22
KR20210052459 2021-04-22
KR10-2021-0116405 2021-09-01
KR1020210116405A KR20220145737A (ko) 2021-04-22 2021-09-01 심방세동 유관 인자의 예측값 산출 장치 및 산출 방법

Publications (1)

Publication Number Publication Date
WO2022197037A1 true WO2022197037A1 (fr) 2022-09-22

Family

ID=83320778

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/003532 WO2022197037A1 (fr) 2021-03-18 2022-03-14 Appareil et procédé de prédiction d'un pronostic de fibrillation auriculaire

Country Status (1)

Country Link
WO (1) WO2022197037A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130204149A1 (en) * 2012-02-08 2013-08-08 Samsung Electronics Co., Ltd. Apparatus and method for generating atrial fibrillation prediction model, and apparatus and method for predicting atrial fibrillation
KR20170021099A (ko) * 2015-08-17 2017-02-27 연세대학교 산학협력단 심장 세동 질환 예측 방법 및 그 장치
WO2017174764A1 (fr) * 2016-04-07 2017-10-12 Ruprecht-Karls-Universität Heidelberg Modèle et score mathématiques permettant de prédire la présence d'une fibrillation auriculaire paroxystique
KR20180052943A (ko) * 2016-11-11 2018-05-21 충북도립대학산학협력단 신경망을 이용한 심방세동 판별장치 및 심방세동 판별방법
WO2020086865A1 (fr) * 2018-10-26 2020-04-30 Mayo Foundation For Medical Education And Research Réseaux neuronaux pour le dépistage de la fibrillation auriculaire
KR20200084561A (ko) * 2019-01-03 2020-07-13 인하대학교 산학협력단 딥러닝을 이용한 정상동율동 심전도 상태에서의 발작성 심방세동 예측방법

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130204149A1 (en) * 2012-02-08 2013-08-08 Samsung Electronics Co., Ltd. Apparatus and method for generating atrial fibrillation prediction model, and apparatus and method for predicting atrial fibrillation
KR20170021099A (ko) * 2015-08-17 2017-02-27 연세대학교 산학협력단 심장 세동 질환 예측 방법 및 그 장치
WO2017174764A1 (fr) * 2016-04-07 2017-10-12 Ruprecht-Karls-Universität Heidelberg Modèle et score mathématiques permettant de prédire la présence d'une fibrillation auriculaire paroxystique
KR20180052943A (ko) * 2016-11-11 2018-05-21 충북도립대학산학협력단 신경망을 이용한 심방세동 판별장치 및 심방세동 판별방법
WO2020086865A1 (fr) * 2018-10-26 2020-04-30 Mayo Foundation For Medical Education And Research Réseaux neuronaux pour le dépistage de la fibrillation auriculaire
KR20200084561A (ko) * 2019-01-03 2020-07-13 인하대학교 산학협력단 딥러닝을 이용한 정상동율동 심전도 상태에서의 발작성 심방세동 예측방법

Similar Documents

Publication Publication Date Title
WO2020235966A1 (fr) Dispositif et procédé de traitement d'une image médicale à l'aide de métadonnées prédites
Gupta et al. Blood pressure detection using CNN-LSTM model
WO2020242239A1 (fr) Système de prise en charge de diagnostic basé sur l'intelligence artificielle utilisant un algorithme d'apprentissage d'ensemble
WO2022220649A1 (fr) Système et procédé d'évaluation de patient basée sur une image d'électrocardiogramme
WO2018124831A1 (fr) Dispositif et procédé de prédiction du risque de maladie lié à la maladie du trouble métabolique
WO2022031038A1 (fr) Dispositif informatique pour prédire un état de sommeil sur la base de données mesurées dans un environnement de sommeil d'un utilisateur
WO2017142183A1 (fr) Appareil de traitement d'image, procédé de traitement d'image et support d'enregistrement enregistrant celle-ci
WO2021107310A1 (fr) Système et procédé d'aide au diagnostic de patient en fonction d'une analyse d'électroencéphalogramme
WO2019125026A1 (fr) Procédé et appareil pour aider au diagnostic d'une maladie cardiovasculaire
WO2017191858A1 (fr) Dispositif et serveur pour mesurer des composants corporels, pour fournir des informations personnalisées
WO2022197037A1 (fr) Appareil et procédé de prédiction d'un pronostic de fibrillation auriculaire
WO2021006522A1 (fr) Appareil de diagnostic d'image utilisant un modèle d'apprentissage profond et son procédé
WO2017217599A1 (fr) Amélioration de la performance des mesures biologiques en présence de bruit
Shin Deep convolutional neural network-based signal quality assessment for photoplethysmogram
Wu et al. Deep learning networks accurately detect ST-segment elevation myocardial infarction and culprit vessel
Rajendran et al. Heart disease prediction system using ensemble of machine learning algorithms
Burel et al. Mozart+: Masking outputs with zeros for improved architectural robustness and testing of dnn accelerators
WO2021107471A1 (fr) Procédé de récupération de données médicales
WO2023239151A1 (fr) Procédé et dispositif de conversion de données de radiologie thoracique en vecteur numérique, et procédé et dispositif d'analyse de maladie les utilisant
WO2023177150A1 (fr) Procédé de distribution d'images de lame entière pour l'entraînement distribué d'un modèle d'apprentissage profond, et système informatique le mettant en œuvre
WO2021040315A1 (fr) Système d'aide au diagnostic du kératocône et procédé d'utilisation de celui-ci.
WO2023048546A1 (fr) Procédé pour fournir des informations sur un trouble dépressif majeur et dispositif pour fournir des informations sur un trouble dépressif majeur utilisant celui-ci
Park et al. Feasibility of Artificial Intelligence–Based Electrocardiography Analysis for the Prediction of Obstructive Coronary Artery Disease in Patients With Stable Angina: Validation Study
WO2020036446A1 (fr) Procédé d'obtention d'informations au moyen d'un son cardio-pulmonaire
WO2017217598A1 (fr) Détection du stress sur la base de l'équilibre sympathovagal

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22771703

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22771703

Country of ref document: EP

Kind code of ref document: A1