WO2021256784A1 - Procédé et dispositif de prédiction de la démence à l'aide d'un facteur de risque de démence en fonction du sexe d'un patient - Google Patents

Procédé et dispositif de prédiction de la démence à l'aide d'un facteur de risque de démence en fonction du sexe d'un patient Download PDF

Info

Publication number
WO2021256784A1
WO2021256784A1 PCT/KR2021/007346 KR2021007346W WO2021256784A1 WO 2021256784 A1 WO2021256784 A1 WO 2021256784A1 KR 2021007346 W KR2021007346 W KR 2021007346W WO 2021256784 A1 WO2021256784 A1 WO 2021256784A1
Authority
WO
WIPO (PCT)
Prior art keywords
dementia
risk factors
gender
patient
prediction model
Prior art date
Application number
PCT/KR2021/007346
Other languages
English (en)
Korean (ko)
Inventor
전홍우
최재규
권이남
Original Assignee
한국과학기술정보연구원
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
Application filed by 한국과학기술정보연구원 filed Critical 한국과학기술정보연구원
Publication of WO2021256784A1 publication Critical patent/WO2021256784A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/40—Detecting, measuring or recording for evaluating the nervous system
    • A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
    • A61B5/4088—Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
    • 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
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
    • 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
    • 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
    • G06N3/042—Knowledge-based neural networks; Logical representations of neural 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
    • G06N3/08—Learning methods
    • 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
    • G16H50/50—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 method and apparatus for predicting dementia using dementia risk factors according to the gender of a patient. More specifically, it relates to a dementia prediction method and apparatus capable of more accurately predicting dementia through different dementia risk factors according to the gender of a patient.
  • dementia Although research for the treatment of dementia has been conducted worldwide for over 20 years, it is a symptom for which there is still no complete cure. Since dementia cannot be cured according to the current medical level, the only solution is to predict dementia early and use drugs to slow the rate of dementia.
  • Various drugs can be used as a treatment method for dementia, but these drugs only have the effect of slowing the progression, not the fundamental treatment of dementia. However, it has a relatively high effect when prescribed and treated in the early stages of dementia.
  • early prediction and early diagnosis of dementia can play a decisive role in alleviating dementia symptoms. If symptoms are alleviated through early prediction of dementia, unnecessary social and economic costs can be reduced. In order to solve the rapid increase in the number of dementia patients and high social costs, early prediction of dementia disease is a very urgent problem.
  • risk factors/biomarkers of dementia requires a long time and cost. Therefore, if not only dementia risk factors but also new dementia risk factor candidates are identified, it may be possible to save time and money by building a model for discovering new biomarkers.
  • the technical problem to be solved by the present invention is dementia prediction using dementia risk factors according to the gender of the patient, which can not only analyze the difference between the risk factors for dementia in men and women, but also find new biomarker candidates that have not been previously identified. To provide a method and apparatus.
  • the method for predicting dementia according to the gender of a patient includes the steps of obtaining data corresponding to dementia risk factors according to the sex from the test subject and according to the sex of the test subject Predicting dementia of the test subject by inputting data corresponding to dementia risk factors into a dementia prediction model, wherein the dementia prediction model is a male dementia risk factor from cohort data collected from a normal group and a dementia patient group It can be a model that learns dementia risk factors according to gender by feature extraction of dementia risk factors of women and men.
  • Dementia prediction apparatus for solving the above technical problem is a processor, a network interface, a memory that is executed by the processor to load a computer program, and the computer program Including a storage to store, the computer program, instructions for obtaining data corresponding to the dementia risk factors according to the sex from the test subject, and the data corresponding to the dementia risk factors according to the sex of the test subject dementia prediction model Including instructions for predicting dementia of the test subject by inputting to, the dementia prediction model is characterized by extracting male dementia risk factors and female dementia risk factors from cohort data collected from a normal group and a dementia patient group. It may be a model that learned dementia risk factors according to gender.
  • FIG. 1 is an exemplary diagram of a dementia prediction system according to the gender of a patient according to some embodiments of the present invention.
  • FIG. 2 is a flowchart of a method for predicting dementia according to a patient's gender according to some embodiments of the present invention.
  • 3 is a diagram for explaining the details of the Senior Cohort DB.
  • 4 is a diagram for explaining detailed items of PIE-DB, MT-DB, and GHE-DB among Senior Cohort DBs.
  • 5 is a diagram for explaining the sampling rate of the data of the elderly with dementia and the normal elderly from the Senior Cohort DB.
  • FIG. 6 is a diagram for explaining the configuration of a neural network of a dementia prediction model according to some embodiments of the present invention.
  • FIG. 9 is a list of factors excluding some of the dementia risk factors that develop dementia in men of FIG. 8 .
  • 10 is a list of dementia risk factors that develop dementia in women.
  • FIG. 11 is a list of factors excluding some of the dementia risk factors that develop dementia in the woman of FIG. 10 .
  • FIG. 12 is a hardware configuration diagram of an apparatus for predicting dementia according to a patient's gender according to another embodiment of the present invention.
  • FIG. 1 is an exemplary diagram of a dementia prediction system according to the gender of a patient according to some embodiments of the present invention.
  • the dementia prediction device 100 obtains data corresponding to the dementia risk factors according to the gender from the test subject, and inputs the dementia risk factors into the dementia prediction model to be tested of dementia can be predicted.
  • Dementia risk factors according to gender are biomarkers that can express dementia due to differences in gender between men and women in the course of performing the dementia prediction model.
  • the dementia prediction model can predict dementia more efficiently by intensively analyzing dementia risk factors according to gender, which are biomarkers that express dementia.
  • Dementia prediction model can machine learning dementia prediction by collecting datasets from Cohort DB that includes male and female medical records.
  • the dementia prediction model can be learned in a way that continuously reduces the error generated by comparing the results of the dementia prediction model with whether the patients stored in the Cohort DB are actual dementia patients or normal groups.
  • the dementia prediction model can learn intensively by selecting as a feature a dementia risk factor according to gender, which was found to have a significant effect on dementia in the process of repeating this learning.
  • Dementia risk factors according to gender were found to be 7 in males and 11 in females.
  • the dementia prediction system according to the gender of the patient can more accurately predict the dementia of the test subject by intensively analyzing the dementia risk factors according to the gender.
  • Risk factors for dementia in men include: Diseases of the thymus, Other disorders of adrenal gland, Other disorders of male genital organs, Hemiplegia, lethargy/ Somnolence, stupor and coma (Somnolence, stupor and coma), Urethral stricture and Symptoms and signs involving appearance and behavior.
  • risk factors for dementia in women include Inflammatory disease of uterus, except cervix, Unspecified urinary incontinence, Other disorders of adrenal gland, lymph nodes Enlarged lymph nodes, Polyps of female genital tract, Symptoms and signs involving appearance and behavior, Other symptoms related to general sensation and perception and signs involving general sensations and perceptions, Hypofunction and other disorders of pituitary gland, Systemic Inflammatory Response Syndrome, Diseases of thymus, and Urethral stricture ) may include at least one of
  • dementia prediction system predicts dementia using the dementia risk factors according to the gender found above, as shown in the experimental results to be described later, the effect of increasing the accuracy and reliability compared to the model is there was.
  • the dementia prediction system may generate new dementia risk factor candidates that have not been previously identified.
  • the dementia prediction apparatus 100 may obtain data corresponding to dementia risk factors according to gender from the test subject, and input the dementia risk factors into the dementia prediction model to predict dementia of the test subject.
  • the dementia prediction model intensively analyzes the dementia risk factors according to gender, which is a biomarker that can cause dementia, and outputs the results of whether the test subject is likely to develop dementia or is normal without the possibility of dementia. can
  • FIG. 2 is a flowchart of a method for predicting dementia according to a patient's gender according to some embodiments of the present invention.
  • step S100 of FIG. 2 data corresponding to dementia risk factors according to gender may be obtained from the test subject.
  • Data corresponding to dementia risk factors previously detected by the dementia prediction model may be collected from the test subject. In this case, only data corresponding to dementia risk factors may be collected, or data including overall medical information of the test subject may be collected.
  • step S200 data corresponding to the dementia risk factors according to the sex of the test subject may be input into the dementia prediction model to predict dementia of the test subject.
  • the information of the test subject collected from the test subject may include various data in addition to data corresponding to dementia risk factors.
  • the dementia risk factors of the test subject among various data may be intensively analyzed.
  • model performance results could be derived through the experimental process of DB analysis, feature selection, and dementia prediction.
  • FIGS. 3 to 11 a process in which dementia risk factors according to gender are discovered and an experimental result in which a dementia prediction model performs dementia prediction using this will be described.
  • FIG. 3 is a diagram for explaining detailed contents of the Senior Cohort DB
  • FIG. 5 is a diagram for explaining detailed items of PIE-DB, MT-DB, and GHE-DB among Senior Cohort DBs.
  • the Cohort DB (1) of FIG. 3 may be collected from the elderly cohort data distribution institution and service, the National Health Insurance Corporation (KNHIS) and the National Health Insurance Sharing Service (NHISS).
  • the National Health Insurance Corporation (NHIS) is an institution that operates health insurance and long-term care insurance for the elderly
  • the National Health Insurance Sharing Service (NHISS) is a national medical information database.
  • the data of 2.1 trillion won, the data held by the National Health Insurance contains information of 50 million citizens accumulated during the course of the corporation's business, including health insurance, long-term care insurance, and four major insurance collection tasks.
  • the 313.2 billion national health information DB was established to produce information necessary for disease prevention and health promotion, health and medical policy establishment, and improvement of medical quality.
  • the elderly cohort can be used.
  • PIE-DB is demographic, socio-economic level and other data
  • MT-DB is treatment item and treatment disease data
  • GHE-DB is medical examination history from physical measurements to past medical records
  • MCI-DB is medical institution It is data such as type, area and installation period, number of beds in medical institutions, number of doctors, and availability of equipment. .
  • a table (2) of detailed items of PIE-DB, GHE-DB, and MT-DB is shown, from which a feature can be selected.
  • Feature selection was selected based on the items presented in the elderly cohort data.
  • the elderly cohort DBs only PIE-DB, GHE-DB, and MT-DB performed feature selection because the remaining MCI-DB and LCI-DB are limited to the elderly related to long-term care, and the number of experimental subjects is insufficient. Therefore, a rich data set for learning could be secured using PIE-DB, GHE-DB, and MT-DB with a large number of test subjects.
  • Each feature can be divided and classified by year from 2002 to 2013 to identify time series patterns.
  • PIE-DB, MT-DB, and GHE-DB can be feature grouped in several ways.
  • gender is grouped into male and female
  • age is grouped into 7 levels
  • income quintile is grouped into 3 levels
  • disease information in MT-DB is used by mapping with the international standard ICD code (International Classification of Diseases). became The structure of the original ICD code consists of 7 digits. In this study, the data sparseness problem could be avoided by grouping the top 3 digits.
  • the height was classified into 10 cm units and the body weight was classified into 11 levels by 5 kg units. Waist, body mass index, blood test, and urine test were classified as normal and abnormal according to the criteria of the health examination standard (Health and Welfare Notice No. 2016-11).
  • 5 is a diagram for explaining the sampling rate of the data of the elderly with dementia and the normal elderly from the Senior Cohort DB.
  • the dementia prediction model can be learned using cohort data collected from the normal group and the dementia patient group within the last 3 years.
  • FIG. 6 is a diagram for explaining the configuration of a neural network of a dementia prediction model according to some embodiments of the present invention.
  • the neural network 3 of the dementia prediction model may be composed of a multi-layer perceptron composed of a plurality of hidden layers.
  • the dementia prediction model may calculate an error value by comparing the dementia prediction result of the test subject predicted using the dementia risk factors determined by the dementia prediction model with the actual dementia of the test subject.
  • the dementia prediction model may be learned by back-propagating the calculated error value.
  • vectorized Top 100 diseases can be input by onehot encoding method.
  • the nodes of the hidden layer of the dementia prediction model can calculate the weight value as an operator.
  • the resulting value is classified by probability as the final value.
  • the dementia prediction model can output Dementia when the probability of developing dementia is high, and Normal when the probability of expressing dementia is low.
  • the dementia prediction model may use the Leaky-ReLu function as an activation function that converts the sum of input signals entering individual neurons of the neural network into an output signal. Accordingly, as the dementia prediction model uses Leaky-ReLu, it is possible to more activate learning in the hidden layer by overcoming the disadvantage that the gradient is unconditionally 0 when x is negative in ReLu.
  • the dementia prediction model may optimize the weight parameters of the neural network using an Adam optimizer.
  • the dementia prediction model can use the L2 loss function instead of the L1 loss function. Since the square of the error is intuitively added, the L1 Loss function is more robust to the Outlier than the L2 Loss function, and the L2 Loss function is more robust to the Outlier. can be greatly affected.
  • the dementia prediction model can avoid overfitting by using cross validation divided into 10 folds.
  • FIG. 9 a list of dementia risk factors (6) in which low weight-related diseases were excluded from among the top 50 dementia risk factors for men was used.
  • the dementia prediction model through the process of learning the characteristics of the other risk factors for dementia except for diseases related to low body weight, it was confirmed that seven major factors had a very large effect on the expression of dementia in men.
  • the major risk factors for dementia in men are: Diseases of the thymus, Other disorders of adrenal gland, Other disorders of male genital organs, Hemiplegia, lethargy Somnolence, stupor and coma (Somnolence, stupor and coma), Urethral stricture and Symptoms and signs involving appearance and behavior were found.
  • 9 and 10 are lists of dementia risk factors that develop dementia in women.
  • the top 50 dementia risk factors (7) for women in FIG. 10 may be composed of factors different from the top 50 dementia risk factors (5) for men in FIG. 8 .
  • FIG. 11 a list of dementia risk factors (8) was used in which obesity, hypertension and diabetes type 2 were excluded for women.
  • the major risk factors for dementia in men are Inflammatory disease of uterus, except cervix, Unspecified urinary incontinence, Other disorders of adrenal gland, and enlarged lymph nodes ( Enlarged lymph nodes), Polyp of female genital tract, Symptoms and signs involving appearance and behavior, Other symptoms and signs related to general sensation and perception of general sensations and perceptions, hypofunction and other disorders of pituitary gland, Systemic Inflammatory Response Syndrome, Diseases of thymus, and Urethral stricture was found
  • FIG. 12 is an exemplary hardware configuration diagram illustrating the computing device 500 .
  • the computing device 500 loads one or more processors 510 , a bus 550 , a communication interface 570 , and a computer program 591 executed by the processor 510 . It may include a memory 530 and a storage 590 for storing the computer program (591). However, only the components related to the embodiment of the present invention are illustrated in FIG. 12 . Accordingly, one of ordinary skill in the art to which the present invention pertains can know that other general-purpose components other than the components shown in FIG. 12 may be further included.
  • the processor 510 controls the overall operation of each component of the computing device 500 .
  • the processor 510 includes at least one of a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art. may be included.
  • the processor 510 may perform an operation on at least one application or program for executing the method/operation according to various embodiments of the present disclosure.
  • Computing device 500 may include one or more processors.
  • the memory 530 stores various data, commands, and/or information.
  • the memory 530 may load one or more programs 591 from the storage 590 to execute methods/operations according to various embodiments of the present disclosure.
  • logic or a module
  • FIG. 4 may be implemented on the memory 530 .
  • An example of the memory 530 may be a RAM, but is not limited thereto.
  • the bus 550 provides a communication function between components of the computing device 500 .
  • the bus 550 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.
  • the communication interface 570 supports wired/wireless Internet communication of the computing device 500 .
  • the communication interface 570 may support various communication methods other than Internet communication.
  • the communication interface 570 may be configured to include a communication module well-known in the art.
  • the storage 590 may non-temporarily store one or more computer programs 591 .
  • the storage 590 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 well in the art to which the present invention pertains. It may be configured to include any known computer-readable recording medium.
  • the computer program 591 may include one or more instructions in which methods/operations according to various embodiments of the present invention are implemented.
  • the processor 510 may execute the one or more instructions to perform methods/operations according to various embodiments of the present disclosure.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Neurology (AREA)
  • Psychiatry (AREA)
  • Physiology (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Developmental Disabilities (AREA)
  • Neurosurgery (AREA)
  • Psychology (AREA)
  • Hospice & Palliative Care (AREA)
  • Child & Adolescent Psychology (AREA)
  • Fuzzy Systems (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

L'invention concerne un procédé et un dispositif de prédiction de la démence en fonction du sexe des patients. Le procédé de prédiction de la démence en fonction du sexe des patients dans un mode de réalisation de la présente invention comprend les étapes consistant à : acquérir des données correspondant à des facteurs de risque de démence en fonction du sexe des sujets soumis à un test ; et à entrer les données correspondant à des facteurs de risque de démence selon le sexe des sujets d'essai à un modèle de prédiction de démence pour prédire la démence des sujets soumis à un test, le modèle de prédiction de démence pouvant être un modèle qui a appris des facteurs de risque de démence selon le sexe par extraction, en tant qu'éléments des facteurs de risque de démence mâle et des facteurs de risque de démence femelle, de données de cohorte collectées de groupes de patients normaux et de patients atteints de démence.
PCT/KR2021/007346 2020-06-19 2021-06-11 Procédé et dispositif de prédiction de la démence à l'aide d'un facteur de risque de démence en fonction du sexe d'un patient WO2021256784A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2020-0074861 2020-06-19
KR1020200074861A KR102380312B1 (ko) 2020-06-19 2020-06-19 환자의 성별에 따른 치매 위험 인자를 이용한 치매 예측 방법 및 장치

Publications (1)

Publication Number Publication Date
WO2021256784A1 true WO2021256784A1 (fr) 2021-12-23

Family

ID=79178085

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/007346 WO2021256784A1 (fr) 2020-06-19 2021-06-11 Procédé et dispositif de prédiction de la démence à l'aide d'un facteur de risque de démence en fonction du sexe d'un patient

Country Status (2)

Country Link
KR (1) KR102380312B1 (fr)
WO (1) WO2021256784A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101881731B1 (ko) * 2018-02-27 2018-07-25 한국과학기술정보연구원 기계 학습을 통한 치매 예측용 데이터 처리 장치 및 그 방법, 이를 수록한 기록 매체
KR20190048926A (ko) * 2017-10-31 2019-05-09 연세대학교 산학협력단 딥러닝을 이용한 rna-가이드 뉴클레아제의 활성 예측 시스템
KR102009840B1 (ko) * 2018-03-19 2019-08-12 한림대학교 산학협력단 인공신경망(ann)을 이용하여 지속적 혈류역학적 이상(phd)를 예측하는 방법 및 장치
KR20200061713A (ko) * 2018-11-26 2020-06-03 연세대학교 산학협력단 섬망 발병 위험도의 예측 방법 및 이를 이용한 디바이스

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102046515B1 (ko) * 2017-03-06 2019-11-20 주식회사 아이메디신 넥밴드 타입 헬스케어 서비스 시스템 및 방법

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190048926A (ko) * 2017-10-31 2019-05-09 연세대학교 산학협력단 딥러닝을 이용한 rna-가이드 뉴클레아제의 활성 예측 시스템
KR101881731B1 (ko) * 2018-02-27 2018-07-25 한국과학기술정보연구원 기계 학습을 통한 치매 예측용 데이터 처리 장치 및 그 방법, 이를 수록한 기록 매체
KR102009840B1 (ko) * 2018-03-19 2019-08-12 한림대학교 산학협력단 인공신경망(ann)을 이용하여 지속적 혈류역학적 이상(phd)를 예측하는 방법 및 장치
KR20200061713A (ko) * 2018-11-26 2020-06-03 연세대학교 산학협력단 섬망 발병 위험도의 예측 방법 및 이를 이용한 디바이스

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
GO, SEUNG-AH ET AL.: "Gender Differences in Risk Factor Prevalence and Cognitive Functions in Alzheimer’s Disease; Experience of Ewha Dementia Clinic", DEMENTIA AND NEUROCOGNITIVE DISORDERS, vol. 6, no. 2, 1 January 2007 (2007-01-01), Seoul, pages 34 - 37, XP009533162, ISSN: 2384-0757 *

Also Published As

Publication number Publication date
KR102380312B1 (ko) 2022-03-30
KR20210157048A (ko) 2021-12-28

Similar Documents

Publication Publication Date Title
Wang et al. Development of deep learning algorithm for detection of colorectal cancer in EHR data
Li et al. Progress in biological age research
Roy et al. Early prediction of COVID-19 using ensemble of transfer learning
Ni et al. Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis
CN112270988A (zh) 一种罕见病辅助诊断的方法及系统
Alkaragole et al. Comparison of data mining techniques for predicting diabetes or prediabetes by risk factors
Mandava MDensNet201-IDRSRNet: Efficient cardiovascular disease prediction system using hybrid deep learning
CN111816303A (zh) 一种基于机器学习的难治性精神分裂症风险的预测方法
Piñeros-Fernández Artificial intelligence applications in the diagnosis of neuromuscular diseases: a narrative review
Khan et al. Detection and spread prediction of COVID-19 from chest X-ray images using convolutional neural network-Gaussian mixture model
Murugan et al. Impact of Internet of Health Things (IoHT) on COVID-19 disease detection and its treatment using single hidden layer feed forward neural networks (SIFN)
CN114242259A (zh) 高龄流感病情预测系统、程序产品及其建立与使用方法
WO2021256784A1 (fr) Procédé et dispositif de prédiction de la démence à l'aide d'un facteur de risque de démence en fonction du sexe d'un patient
Wang et al. Integration of the Extreme Gradient Boosting model with electronic health records to enable the early diagnosis of multiple sclerosis
Kashyap et al. Prediction of suicidal risk using machine learning models
JP7333549B2 (ja) 疾病リスク評価方法、疾病リスク評価システム、及び健康情報処理装置
Basha et al. Deep learning neural network (DLNN)-based classification and optimization algorithm for organ inflammation disease diagnosis
Komalavalli et al. An Effective Heart Disease Prediction Using Machine Learning
Ganasegeran et al. Artificial intelligence for risk prediction of Alzheimer's disease: a new promise for community health screening in the older aged
Patel et al. Accu-Help: A Machine-Learning-Based Smart Healthcare Framework for Accurate Detection of Obsessive Compulsive Disorder
CN109492690B (zh) 一种基于卷积神经网络检测ct图像的方法
Zhu et al. Design and development of a readmission risk assessment system for patients with cardiovascular disease
Lakshmi et al. A Review And Analysis Of The Role Of Machine Learning Techniques To Predict Health Risks Among Women During Menopause
CN111986801A (zh) 基于深度学习的康复评定方法、装置及介质
Abenga et al. Identifying Biomarkers for Diabetic Kidney Disease Using GraphSAGE Neural Network

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: 21824968

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: 21824968

Country of ref document: EP

Kind code of ref document: A1