WO2023191538A1 - System for diagnosing alzheimer's disease by using biomarkers in cerebrospinal fluid and blood - Google Patents

System for diagnosing alzheimer's disease by using biomarkers in cerebrospinal fluid and blood Download PDF

Info

Publication number
WO2023191538A1
WO2023191538A1 PCT/KR2023/004262 KR2023004262W WO2023191538A1 WO 2023191538 A1 WO2023191538 A1 WO 2023191538A1 KR 2023004262 W KR2023004262 W KR 2023004262W WO 2023191538 A1 WO2023191538 A1 WO 2023191538A1
Authority
WO
WIPO (PCT)
Prior art keywords
disease
alzheimer
biomarkers
probability
amyloid
Prior art date
Application number
PCT/KR2023/004262
Other languages
French (fr)
Korean (ko)
Inventor
고성호
이은혜
권혁성
Original Assignee
한양대학교 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
Application filed by 한양대학교 산학협력단 filed Critical 한양대학교 산학협력단
Publication of WO2023191538A1 publication Critical patent/WO2023191538A1/en

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
    • 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
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
    • C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
    • C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
    • 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
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • 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
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q2600/00—Oligonucleotides characterized by their use
    • C12Q2600/156—Polymorphic or mutational markers

Definitions

  • the present invention relates to an Alzheimer's disease diagnosis program and system using biomarkers in cerebrospinal fluid and blood.
  • Alzheimer's disease is a type of dementia and is also known as senile dementia due to a decline in functions such as memory, language ability, and judgment.
  • AD Alzheimer's disease
  • the drugs that exist are limited to slowing the progression of the disease.
  • it is very important to diagnose the disease early because early diagnosis can significantly slow the progression of the disease.
  • expensive diagnostic methods eg, Amyloid PET, Tau PET, MRI, etc.
  • a method is needed to predict Alzheimer's disease using a blood test that is simple and inexpensive.
  • the technical problem to be achieved by the present invention is to overcome the problem of low accessibility to patients by requiring expensive diagnostic methods to diagnose Alzheimer's disease, and to develop cerebrospinal fluid that can predict Alzheimer's disease through a blood test that is simple and inexpensive.
  • the goal is to provide an Alzheimer's disease diagnosis system using biomarkers in the blood.
  • the Alzheimer's disease diagnosis program using biomarkers in cerebrospinal fluid and blood proposed in the present invention includes the steps of acquiring gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from a subject through a data collection unit, and amyloid A step of calculating a probability for diagnosing Alzheimer's disease using gene expression data of a biomarker related to the prognosis of Alzheimer's disease in order to determine whether amyloid is positive from the data through a positivity probability calculator.
  • the step of calculating the probability for diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis in order to determine the positivity of amyloid from the data through the amyloid positive probability calculator is Phospho-tau 181, Phospho- Biomarkers related to Alzheimer's disease prognosis, including tau 199, Total-tau, ApoE, A ⁇ (Amyloid beta) 42, A ⁇ 40, Neurogranin, Telomere length, ApoE presence, gender, age, sTREM2, and NfL (Neurofilament Light Chain)
  • the probability of diagnosing Alzheimer's disease is calculated using a combination of these.
  • k represents the number of biomarkers used to calculate the probability for diagnosing Alzheimer's disease, is a constant to correct the error
  • x is the type of biomarker used to calculate the probability (P) for diagnosing Alzheimer's disease
  • P probability for diagnosing Alzheimer's disease
  • the probability for diagnosing Alzheimer's disease is used to express it as AUC (Area Under the ROC Curve), and the pathological aspect of Alzheimer's disease is predicted using the AUC.
  • the gene expression data of the biomarkers and the Alzheimer's disease diagnosis information are updated in the database, more biomarkers related to the prognosis of the Alzheimer's disease are added or the expression of Alzheimer's disease for each of the biomarkers is updated. Contribution is adjusted.
  • the Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood proposed in the present invention includes a data collection unit that acquires gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from the subject, and In order to determine whether amyloid is positive from the data, it includes an amyloid positive probability calculation unit that calculates the probability for Alzheimer's disease diagnosis using gene expression data of biomarkers related to Alzheimer's disease prognosis.
  • the Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood is a system that can facilitate the diagnosis of Alzheimer's disease, compared to existing high-cost and low-access diagnostic methods such as Amyloid PET and MRI. Not only can results be obtained quickly and easily, but diagnosis is also easily accessible, making early diagnosis of Alzheimer's disease possible. In addition, it has superior technological development value as it has greater discernment than conventional technologies.
  • Figure 1 is a flowchart illustrating the operation method of an Alzheimer's disease diagnostic program using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
  • Figure 2 is a diagram showing the configuration of an Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
  • Figure 3 is a graph showing the AUC value of one biomarker according to the prior art for amyloid positivity.
  • Figure 4 is a graph showing the AUC value of a combination of multiple biomarkers for amyloid positivity according to an embodiment of the present invention.
  • Figure 1 is a flowchart illustrating an Alzheimer's disease diagnosis program using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
  • the proposed Alzheimer's disease diagnosis program using biomarkers in cerebrospinal fluid and blood is a step of acquiring gene expression data of multiple biomarkers from blood or cerebrospinal fluid extracted from the subject through a data collection unit (110) and an amyloid positive probability calculation unit.
  • a step 120 of calculating the probability of diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis is included.
  • step 110 gene expression data of a plurality of biomarkers may be obtained from blood or cerebrospinal fluid extracted from the subject through the data collection unit.
  • Blood or cerebrospinal fluid extracted from the subject is obtained through a diagnostic kit of the Alzheimer's disease diagnostic system according to an embodiment of the present invention, and the data collection unit acquires gene expression data of a plurality of biomarkers from the blood or cerebrospinal fluid obtained in this way.
  • step 120 the probability of diagnosing Alzheimer's disease is calculated using the gene expression data of a biomarker related to the prognosis of Alzheimer's disease in order to determine the positivity of amyloid from the data through the amyloid positivity probability calculation unit.
  • the dependent variable is a dichotomous variable of presence or absence of amyloid positivity
  • binary logistic regression analysis is used.
  • the following logistic regression model can be estimated using the maximum likelihood method:
  • x1, x2 are variables for creating the model
  • P represents the probability of amyloid positivity for diagnosing Alzheimer's disease.
  • Biomarkers related to the prognosis of Alzheimer's disease include Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, A ⁇ (Amyloid beta) 42, A ⁇ 40, Neurogranin, Telomere length, presence of ApoE, It may include gender, age, sTREM2, and Neurofilament Light Chain (NfL).
  • the probability for diagnosing Alzheimer's disease is calculated using a combination of biomarkers related to the prognosis of Alzheimer's disease.
  • the probability (P) for diagnosing Alzheimer's disease is calculated using equation (2) using the contribution to the expression of Alzheimer's disease of each of the biomarkers related to Alzheimer's disease prognosis according to an embodiment of the present invention:
  • k represents the number of biomarkers used to calculate the probability for diagnosing Alzheimer's disease, is a constant to correct the error
  • x is the type of biomarker used to calculate the probability (P) for diagnosing Alzheimer's disease
  • P probability for diagnosing Alzheimer's disease
  • the probability (P) for diagnosing Alzheimer's disease can be calculated by applying APOE (x1) and pTau-181 (x2) among the plurality of biomarkers to Equation (1). At this time, the probability (P) for diagnosing Alzheimer's disease can be expressed as equation (3):
  • Equation (1) Age (x1), sex (x2), APOE (x3), pTau-181 (x4), and NFL (x5) are applied to Equation (1) to diagnose Alzheimer's disease.
  • the probability (P) for can be calculated.
  • the probability (P) for diagnosing Alzheimer's disease can be expressed as equation (4):
  • Age (x1), sex (x2), APOE (x3), pTau-181 (x4), NFL (x5), and telomere length (x6) among the plurality of biomarkers are expressed in Equation (1)
  • the probability (P) for diagnosing Alzheimer's disease can be calculated.
  • the probability (P) for diagnosing Alzheimer's disease can be expressed as equation (5):
  • AUC Average Under the ROC Curve
  • gene expression data of the biomarker and Alzheimer's disease diagnosis information can be continuously updated in the database. As these data are updated in the database, more biomarkers related to Alzheimer's disease prognosis may be added, or the contribution of each biomarker to the expression of Alzheimer's disease may be adjusted.
  • Figure 2 is a diagram showing the configuration of an Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
  • the Alzheimer's disease diagnosis system 200 may include a processor 210, a bus 220, a network interface 230, a memory 240, and a database 250.
  • the memory 240 may include an operating system 241 and an Alzheimer's disease diagnosis routine 242 using biomarkers in cerebrospinal fluid and blood.
  • the processor 210 may include a data collection unit 211 and an amyloid positive probability calculation unit 212.
  • the Alzheimer's disease diagnostic system 200 may include more components than those of FIG. 2 . However, there is no need to clearly show most prior art components.
  • the Alzheimer's disease diagnosis system 200 may include other components such as a display, transceiver, diagnostic kit, smart terminal, etc.
  • the memory 240 is a computer-readable recording medium and may include a non-permanent mass storage device such as random access memory (RAM), read only memory (ROM), and a disk drive. Additionally, the memory 240 may store an operating system 241 and program code for an Alzheimer's disease diagnosis routine 242 using biomarkers in cerebrospinal fluid and blood. These software components may be loaded from a computer-readable recording medium separate from the memory 240 using a drive mechanism (not shown). Such separate computer-readable recording media may include computer-readable recording media (not shown) such as floppy drives, disks, tapes, DVD/CD-ROM drives, and memory cards. In another embodiment, software components may be loaded into the memory 240 through the network interface 230 rather than a computer-readable recording medium.
  • Bus 220 may enable communication and data transfer between components of Alzheimer's disease diagnosis system 200.
  • Bus 220 may be configured using a high-speed serial bus, parallel bus, storage area network (SAN), and/or other suitable communication technology.
  • SAN storage area network
  • Network interface 230 may be a computer hardware component for connecting Alzheimer's disease diagnosis system 200 to a computer network.
  • the network interface 230 may connect the Alzheimer's disease diagnosis system 200 to a computer network through a wireless or wired connection.
  • the database 250 may serve to store and maintain all information necessary for diagnosing Alzheimer's disease using biomarkers in cerebrospinal fluid and blood.
  • the database 250 is built and included inside the Alzheimer's disease diagnosis system 200, but it is not limited to this and may be omitted depending on the system implementation method or environment, or all or part of the database may be included. It is also possible to exist as an external database built on a separate system.
  • the processor 210 may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations of the Alzheimer's disease diagnosis system 200. Commands may be provided to processor 210 by memory 240 or network interface 230 and via bus 220.
  • the processor 210 may be configured to execute program code for the data collection unit 211 and the amyloid positive probability calculation unit 212. These program codes may be stored in a recording device such as memory 240.
  • the data collection unit 211 and the amyloid positive probability calculation unit 212 may be configured to perform steps 110 to 120 of FIG. 1.
  • the Alzheimer's disease diagnosis system 200 may include a data collection unit 211 and an amyloid positive probability calculation unit 212.
  • the data collection unit 211 acquires gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from a subject.
  • the Alzheimer's disease diagnosis system 200 acquires blood or cerebrospinal fluid extracted from a subject through a diagnostic kit, and the data collection unit 211 collects a plurality of biomarkers from the blood or cerebrospinal fluid obtained in this way. Acquire gene expression data.
  • the amyloid positivity probability calculation unit 212 calculates the probability for diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis in order to determine the positivity of amyloid from the acquired data. do.
  • the amyloid positive probability calculator 212 includes Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, A ⁇ (Amyloid beta) 42, A ⁇ 40, Neurogranin, Telomere length, ApoE presence, and gender.
  • the probability of diagnosing Alzheimer's disease is calculated using a combination of biomarkers related to Alzheimer's disease prognosis, including age, sTREM2, and NfL (Neurofilament Light Chain).
  • the amyloid positive probability calculator 212 uses the contribution to the expression of Alzheimer's disease of each biomarker related to the prognosis of Alzheimer's disease and uses the equation (2) to determine the probability of diagnosing Alzheimer's disease ( Calculate P).
  • AUC Average Under the ROC Curve
  • the Alzheimer's disease diagnosis system 200 may further include a diagnostic kit and a smart terminal.
  • the diagnostic kit according to an embodiment of the present invention can obtain blood or cerebrospinal fluid extracted from a subject to obtain gene expression data of multiple biomarkers.
  • a smart terminal according to an embodiment of the present invention can be equipped with an application for diagnosing Alzheimer's disease.
  • Alzheimer's disease diagnosis information using the smart terminal can be managed through the database 250.
  • gene expression data of the biomarker and Alzheimer's disease diagnosis information may be continuously updated in the database 250.
  • the amyloid positive probability calculator 212 adds more biomarkers related to the prognosis of Alzheimer's disease or determines the expression of Alzheimer's disease for each of the biomarkers. You can also adjust your contribution.
  • Figure 3 is a graph showing the AUC value of one biomarker according to the prior art for amyloid positivity.
  • Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, A ⁇ (Amyloid beta) 42, A ⁇ 40, Neurogranin, Telomere length, ApoE presence, gender, age, sTREM2, and NfL (Neurofilament Light Chain) were measured.
  • Figure 4 is a graph showing the AUC value of a combination of multiple biomarkers for amyloid positivity according to an embodiment of the present invention.
  • Figure 4(a) shows the AUC of the plasma biomarker and Figure 4(b) shows the AUC of the CSF biomarker.
  • the pathological aspect of Alzheimer's disease is shown to have an AUC value in the mid to high 0.8 range, which is stronger than the single biomarker in Figure 3.
  • a system suitable for predicting can be operated.
  • a formula for calculating the probability of diagnosing Alzheimer's disease was proposed by finding a combination of biomarkers that can detect Alzheimer's disease with the highest probability. By entering the values of each biomarker obtained from the subject in the proposed formula, it is possible to diagnose and predict whether the subject is positive for amyloid.
  • gene expression data of the biomarker and Alzheimer's disease diagnosis information can be continuously updated in the database. As these data are updated in the database, more biomarkers related to Alzheimer's disease prognosis may be added, or the contribution of each biomarker to the expression of Alzheimer's disease may be adjusted.
  • the probability of diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis to determine whether amyloid is positive can be summarized as follows.
  • Equation (3) An example of calculating the probability of predicting amyloid positivity in an actual subject using Equation (3) above is described below.
  • the probability that the subject was positive for amyloid was calculated to be 92.4%.
  • the probability of the subject being amyloid positive was calculated to be 31.7%.
  • the prediction probability can be increased, and when a 50-year-old male subject does not have APOE e4, p-tau181 is confirmed to be 15 pg/ml, and NFL is confirmed to be 12 pg/ml. , the probability that the subject was positive for amyloid was calculated to be 99.99%.
  • the present invention is a system that can facilitate the diagnosis of Alzheimer's, and results can be obtained more easily and quickly than existing high-cost and low-access diagnostic methods such as amyloid PET and MRI.
  • it is a system that can enable early diagnosis of Alzheimer's disease due to its excellent accessibility to diagnosis, and has excellent technological development value as it has better discrimination ability than conventional technologies.
  • the system proposed in the present invention can be expected to reduce the medical budget due to the diagnosis of Alzheimer's disease and reduce personal and socioeconomic costs due to early diagnosis.
  • devices and components described in embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general-purpose or special-purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions.
  • a processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software.
  • OS operating system
  • a processing device may access, store, manipulate, process, and generate data in response to the execution of software.
  • a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include.
  • a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.
  • Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device.
  • Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. It can be embodied in .
  • Software may be distributed over networked computer systems and stored or executed in a distributed manner.
  • Software and data may be stored on one or more computer-readable recording media.
  • the method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium.
  • the computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination.
  • Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software.
  • Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks.
  • Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

Abstract

A program and a system for diagnosing Alzheimer's disease by using biomarkers in the cerebrospinal fluid and blood are provided. The program for diagnosing Alzheimer's disease by using biomarkers in the cerebrospinal fluid and blood, presented in the present invention, comprises the steps of: obtaining gene expression data of a plurality of biomarkers from the blood or cerebrospinal fluid extracted from a subject through a data collection unit; and calculating the probability of an Alzheimer's disease diagnosis by using gene expression data of biomarkers associated with Alzheimer's disease prognosis in order to determine amyloid positivity from the data through an amyloid positivity probability calculation unit.

Description

뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 시스템Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood
본 발명은 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 프로그램 및 시스템에 관한 것이다.The present invention relates to an Alzheimer's disease diagnosis program and system using biomarkers in cerebrospinal fluid and blood.
알츠하이머병(Alzheimer's Disease; AD)은 치매의 한 종류로서 기억력, 언어 능력, 판단력 등의 기능 저하로 노인성 치매로도 알려져 있다. 한국의 고령화에 따라 알츠하이머병의 발병률 및 이로 인한 사회적인 비용 및 개인과 가족의 피해는 해를 거듭해 가면서 더 심해지고 있다. 하지만 현재로서는 알츠하이머병에 대한 근본적인 치료책이 없고 그나마 존재하는 약제들은 병의 진행을 늦추는 정도에 머물고 있다. 알츠하이머병의 경우 조기진단이 병증의 진행 정도를 현저히 늦출 수 있기 때문에 병을 조기에 진단하는 것이 매우 중요하다. 이에 반해, 알츠하이머병을 진단하기 위해서는 고액의 진단 방법(예를 들어, Amyloid PET, Tau PET, MRI 등)이 사용되어 환자들의 접근성이 낮다는 문제점이 있다. 이러한 문제점을 극복하기 위해 검사도 간편하며 비용도 저렴한 혈액 검사로 알츠하이머병을 예측할 수 있는 방안을 필요로 한다. Alzheimer's disease (AD) is a type of dementia and is also known as senile dementia due to a decline in functions such as memory, language ability, and judgment. As Korea ages, the incidence of Alzheimer's disease and the resulting social costs and damage to individuals and families are worsening over the years. However, there is currently no fundamental cure for Alzheimer's disease, and the drugs that exist are limited to slowing the progression of the disease. In the case of Alzheimer's disease, it is very important to diagnose the disease early because early diagnosis can significantly slow the progression of the disease. On the other hand, to diagnose Alzheimer's disease, expensive diagnostic methods (eg, Amyloid PET, Tau PET, MRI, etc.) are used, which has the problem of low accessibility for patients. To overcome these problems, a method is needed to predict Alzheimer's disease using a blood test that is simple and inexpensive.
종래기술 Shorena Janelidze et al., "Detecting amyloid positivity in early Alzheimer's disease using combinations of plasma Aβ42/Aβ40 and p-tau", Alzheimer's Dement, 2021.05.07. 에서는 초기 알츠하이머병(Alzheimer's Disease; AD)의 여러 단계에서 비정상적인 뇌 아밀로이드 베타(Amyloid beta; Aβ) 침착을 감지하기 위해 혈액 아밀로이드 베타(Aβ) 42, Aβ40, 인산화 타우(phosphorylated tau; p-tau)217 및 미세신경섬유 경쇄(Neurofilament Light Chain; NfL)을 결합하는 것의 유용성을 개시하고 있다. Prior art Shorena Janelidze et al., "Detecting amyloid positivity in early Alzheimer's disease using combinations of plasma Aβ42/Aβ40 and p-tau", Alzheimer's Dement, 2021.05.07. In order to detect abnormal brain amyloid beta (Aβ) deposition in various stages of early Alzheimer's disease (AD), blood amyloid beta (Aβ) 42, Aβ40, and phosphorylated tau (p-tau) 217 and Neurofilament Light Chain (NfL).
또 다른 종래기술 Sebastian Palmqvist et al., "Prediction of future Alzheimer's disease dementia using plasma phospho-tau combined with other accessible measures", Nature Medicine, Nature Medicine, Vol 27, JUNE 2021. 에서는 혈장 인산화-타우(P-tau)와 기타 접근 가능한 바이오마커의 조합을 이용한 알츠하이머병(AD) 치매 발병 위험에 대한 정확한 예측 방법을 개시하고 있다. 여기서, BioFINDER(n= 340) 및 알츠하이머병 신경 영상 이니셔티브(Alzheimer's Disease Neuroimaging Initiative; ADNI)(n= 543) 연구에서 주관적 인지 감퇴와 경도 인지 장애가 있는 참가자를 대상으로 조사했다. 혈장 p-tau, 혈장 Aβ 42, Aβ40, 혈장 신경섬유 광, APOE 유전자형, 간단한 인지 검사 및 AD-특이 자기 공명 영상 측정을 결과로서 AD로의 진행을 사용하여 조사하였다. 혈장 p-tau217은 4년 이내에 BioFINDER에서 AD를 정확하게 예측했다. 혈장 p-tau217, 기억, 집행 기능 및 APOE를 결합하여 더 높은 정확도를 생성했다(AUC = 0.91, P< 0.001). ADNI에서 이 모델은 p-tau217 대신 혈장 p-tau181을 사용하여 유사한 AUC(0.90)를 보였다. 이 모델은 개인이 알츠하이머병으로 진행될 확률을 예측하기 위해 온라인으로 구현되었다. 2년과 6년 이내에 유사한 모델의 AUC는 두 집단 모두에서 0.90-0.91이었다. 혈장 바이오마커 대신 뇌척수액 p-tau, Aβ42, Aβ40 및 신경섬유 광을 사용해도 정확도가 크게 향상되지 않았다. 기억 클리닉 의사의 임상 예측은 정확도가 상당히 낮았다(4year AUC = 0.71). 요약하면, 혈장 p-tau는 간단한 인지 테스트 및 APOE 유전자형과 함께 AD의 진단 예측을 크게 향상시키고 AD 시험 모집을 용이하게 할 수 있다. In another prior art Sebastian Palmqvist et al., "Prediction of future Alzheimer's disease dementia using plasma phospho-tau combined with other accessible measures", Nature Medicine, Nature Medicine, Vol 27, JUNE 2021. In plasma phospho-tau (P-tau) ) and other accessible biomarkers are being used to accurately predict the risk of developing Alzheimer's disease (AD) dementia. Here, we examined participants with subjective cognitive decline and mild cognitive impairment from the BioFINDER (n = 340) and Alzheimer's Disease Neuroimaging Initiative (ADNI) (n = 543) studies. Plasma p-tau, plasma Aβ 42, Aβ40, plasma neurofilament, APOE genotype, brief cognitive test and AD-specific magnetic resonance imaging measurements were investigated with progression to AD as the outcome. Plasma p-tau217 accurately predicted AD in BioFINDER within 4 years. Combining plasma p-tau217, memory, executive function and APOE produced higher accuracy (AUC = 0.91, P < 0.001). In ADNI, this model showed a similar AUC (0.90) using plasma p-tau181 instead of p-tau217. This model was implemented online to predict the probability that an individual will develop Alzheimer's disease. The AUC of similar models within 2 and 6 years was 0.90-0.91 in both groups. The use of cerebrospinal fluid p-tau, Aβ42, Aβ40, and neurofibrillary acid instead of plasma biomarkers did not significantly improve accuracy. The memory clinician's clinical predictions were significantly less accurate (4year AUC = 0.71). In summary, plasma p-tau, in combination with brief cognitive tests and APOE genotyping, can significantly improve diagnostic prediction of AD and facilitate AD trial recruitment.
또 다른 종래기술 Sung Hoon Kang et al., "Machine Learning for the Prediction of Amyloid Positivity in Amnestic Mild Cognitive Impairment", Journal of Alzheimer's Disease, 2021, 01,23. 에서는 aMCI(Amnestic mild cognitive impairment) 환자에서 A 양성을 예측하기 위한 ML 접근법을 개시한다. 여기서, 로지스틱 회귀 및 기계 학습 방법과 같은 기존 예측 모델의 성능을 비교하고, 뇌 영상 정보를 추가하면 예측 성능이 향상되는지 여부를 평가한다. 가장 성능이 좋은 모델을 선택하여 해석 가능한 ML 모델에 대해 가능한 많은 변수를 삽입하여 어떤 변수가 중요한지 확인한다. aMCI의 다양한 임상적, 신경심리학적, 신경영상적 특징이 A 양성과 관련이 있을 것이며 이러한 특징의 조합이 A 양성을 정확하게 예측하는 것을 가능하게 할 수 있다. Another prior art Sung Hoon Kang et al., "Machine Learning for the Prediction of Amyloid Positivity in Amnestic Mild Cognitive Impairment", Journal of Alzheimer's Disease, 2021, 01,23. discloses an ML approach to predict A positivity in patients with amnestic mild cognitive impairment (aMCI). Here, we compare the performance of existing prediction models such as logistic regression and machine learning methods, and evaluate whether adding brain imaging information improves prediction performance. Select the best-performing model and insert as many variables as possible into an interpretable ML model to determine which variables are important. A variety of clinical, neuropsychological, and neuroimaging features of aMCI will be associated with A positivity, and a combination of these features may make it possible to accurately predict A positivity.
본 발명이 이루고자 하는 기술적 과제는 알츠하이머병을 진단하기 위해서는 고액의 진단 방법을 필요로하여 환자들의 접근성이 낮다는 문제점을 극복하기 위해 검사도 간편하며 비용도 저렴한 혈액 검사로 알츠하이머병을 예측할 수 있는 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 시스템을 제공하는데 있다. The technical problem to be achieved by the present invention is to overcome the problem of low accessibility to patients by requiring expensive diagnostic methods to diagnose Alzheimer's disease, and to develop cerebrospinal fluid that can predict Alzheimer's disease through a blood test that is simple and inexpensive. The goal is to provide an Alzheimer's disease diagnosis system using biomarkers in the blood.
일 측면에 있어서, 본 발명에서 제안하는 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 프로그램은 데이터 수집부를 통해 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득하는 단계 및 아밀로이드 양성 확률 계산부를 통해 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 단계를 포함한다. In one aspect, the Alzheimer's disease diagnosis program using biomarkers in cerebrospinal fluid and blood proposed in the present invention includes the steps of acquiring gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from a subject through a data collection unit, and amyloid A step of calculating a probability for diagnosing Alzheimer's disease using gene expression data of a biomarker related to the prognosis of Alzheimer's disease in order to determine whether amyloid is positive from the data through a positivity probability calculator.
상기 아밀로이드 양성 확률 계산부를 통해 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 단계는 Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ(Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE유무, 성별, 나이, sTREM2, 및 NfL(Neurofilament Light Chain) 을 포함하는 알츠하이머병 예후와 관련 있는 바이오마커들의 조합을 이용하여 알츠하이머병 진단을 위한 확률을 계산한다. The step of calculating the probability for diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis in order to determine the positivity of amyloid from the data through the amyloid positive probability calculator is Phospho-tau 181, Phospho- Biomarkers related to Alzheimer's disease prognosis, including tau 199, Total-tau, ApoE, Aβ (Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE presence, gender, age, sTREM2, and NfL (Neurofilament Light Chain) The probability of diagnosing Alzheimer's disease is calculated using a combination of these.
상기 알츠하이머병 예후와 관련 있는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 이용하여 하기 식을 통해 알츠하이머병 진단을 위한 확률(P)을 계산하고, Calculate the probability (P) for diagnosing Alzheimer's disease using the following equation using the contribution of each of the biomarkers related to the prognosis of Alzheimer's disease to the expression of Alzheimer's disease,
Figure PCTKR2023004262-appb-img-000001
Figure PCTKR2023004262-appb-img-000001
여기서, k는 알츠하이머병 진단을 위한 확률 계산에 이용된 바이오마커의 수를 나타내고,
Figure PCTKR2023004262-appb-img-000002
는 오차를 보정하기 위한 상수이고, x는 알츠하이머병 진단을 위한 확률(P) 계산에 이용된 바이오마커의 유형,
Figure PCTKR2023004262-appb-img-000003
는 해당 바이오마커의 알츠하이머병 발현에 대한 기여도를 나타내는 회귀계수(상수)이다. Here, k represents the number of biomarkers used to calculate the probability for diagnosing Alzheimer's disease,
Figure PCTKR2023004262-appb-img-000002
is a constant to correct the error, x is the type of biomarker used to calculate the probability (P) for diagnosing Alzheimer's disease,
Figure PCTKR2023004262-appb-img-000003
is a regression coefficient (constant) that represents the contribution of the corresponding biomarker to the expression of Alzheimer's disease.
상기 알츠하이머병 진단을 위한 확률을 이용하여 AUC(Area Under the ROC Curve)로 나타내고, 상기 AUC를 이용하여 알츠하이머병의 병리학적 양상을 예측한다. The probability for diagnosing Alzheimer's disease is used to express it as AUC (Area Under the ROC Curve), and the pathological aspect of Alzheimer's disease is predicted using the AUC.
상기 혈액 또는 뇌척수액의 분석 결과, 상기 바이오마커의 유전자 발현 데이터 및 알츠하이머병 진단 정보가 데이터베이스에 업데이트됨에 따라 상기 알츠하이머병 예후와 관련 있는 바이오마커들이 더 추가되거나 또는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도가 조정된다. As a result of the analysis of the blood or cerebrospinal fluid, the gene expression data of the biomarkers and the Alzheimer's disease diagnosis information are updated in the database, more biomarkers related to the prognosis of the Alzheimer's disease are added or the expression of Alzheimer's disease for each of the biomarkers is updated. Contribution is adjusted.
또 다른 일 측면에 있어서, 본 발명에서 제안하는 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 시스템은 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득하는 데이터 수집부 및 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 아밀로이드 양성 확률 계산부를 포함한다.In another aspect, the Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood proposed in the present invention includes a data collection unit that acquires gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from the subject, and In order to determine whether amyloid is positive from the data, it includes an amyloid positive probability calculation unit that calculates the probability for Alzheimer's disease diagnosis using gene expression data of biomarkers related to Alzheimer's disease prognosis.
본 발명의 실시예들에 따른 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 시스템은 알츠하이머의 진단을 용이하게 해 줄 수 있는 시스템으로서 기존에 고비용 저접근성을 가진 Amyloid PET, MRI와 같은 진단법에 비해 쉽고 빠르게 결과를 얻을 수 있을 뿐만 아니라 진단에 대한 접근성이 용이하여 알츠하이머병의 조기진단을 가능하게 해 줄 수 있다. 뿐만 아니라, 종래기술보다 더욱 뛰어난 분별력을 가지고 있어 기술적 개발 가치가 뛰어나다.The Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood according to embodiments of the present invention is a system that can facilitate the diagnosis of Alzheimer's disease, compared to existing high-cost and low-access diagnostic methods such as Amyloid PET and MRI. Not only can results be obtained quickly and easily, but diagnosis is also easily accessible, making early diagnosis of Alzheimer's disease possible. In addition, it has superior technological development value as it has greater discernment than conventional technologies.
도 1은 본 발명의 일 실시예에 따른 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 프로그램의 동작 방법을 설명하기 위한 흐름도이다. Figure 1 is a flowchart illustrating the operation method of an Alzheimer's disease diagnostic program using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
도 2는 본 발명의 일 실시예에 따른 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 시스템의 구성을 나타내는 도면이다. Figure 2 is a diagram showing the configuration of an Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
도 3은 종래기술에 따른 하나의 바이오마커가 아밀로이드 양성에 대해 가지는 AUC 값을 나타내는 그래프이다.Figure 3 is a graph showing the AUC value of one biomarker according to the prior art for amyloid positivity.
도 4는 본 발명의 일 실시예에 따른 복수의 바이오마커들의 조합이 아밀로이드 양성에 대해 가지는 AUC 값을 나타내는 그래프이다. Figure 4 is a graph showing the AUC value of a combination of multiple biomarkers for amyloid positivity according to an embodiment of the present invention.
이하, 본 발명의 실시 예를 첨부된 도면을 참조하여 상세하게 설명한다.Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.
도 1은 본 발명의 일 실시예에 따른 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 프로그램을 설명하기 위한 흐름도이다. Figure 1 is a flowchart illustrating an Alzheimer's disease diagnosis program using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
제안하는 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 프로그램은 데이터 수집부를 통해 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득하는 단계(110) 및 아밀로이드 양성 확률 계산부를 통해 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 단계(120)를 포함한다. The proposed Alzheimer's disease diagnosis program using biomarkers in cerebrospinal fluid and blood is a step of acquiring gene expression data of multiple biomarkers from blood or cerebrospinal fluid extracted from the subject through a data collection unit (110) and an amyloid positive probability calculation unit. In order to determine whether amyloid is positive from the data, a step 120 of calculating the probability of diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis is included.
단계(110)에서, 데이터 수집부를 통해 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득할 수 있다. In step 110, gene expression data of a plurality of biomarkers may be obtained from blood or cerebrospinal fluid extracted from the subject through the data collection unit.
본 발명의 실시예에 따른 알츠하이머병 진단 시스템의 진단 키트를 통해 대상자로부터 추출된 혈액 또는 뇌척수액을 획득하고, 데이터 수집부는 이와 같이 획득된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득한다. Blood or cerebrospinal fluid extracted from the subject is obtained through a diagnostic kit of the Alzheimer's disease diagnostic system according to an embodiment of the present invention, and the data collection unit acquires gene expression data of a plurality of biomarkers from the blood or cerebrospinal fluid obtained in this way.
단계(120)에서, 아밀로이드 양성 확률 계산부를 통해 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산한다. In step 120, the probability of diagnosing Alzheimer's disease is calculated using the gene expression data of a biomarker related to the prognosis of Alzheimer's disease in order to determine the positivity of amyloid from the data through the amyloid positivity probability calculation unit.
본 발명의 실시예에 따르면, 종속 변수가 아밀로이드 양성 유무인 이분형 변수이기 때문에, 이분형 로지스틱 회귀분석을 사용한다. 최대 우도법(maximum likelihood method)을 통하여 다음과 같은 로지스틱 회귀모형을 추정할 수 있다: According to an embodiment of the present invention, since the dependent variable is a dichotomous variable of presence or absence of amyloid positivity, binary logistic regression analysis is used. The following logistic regression model can be estimated using the maximum likelihood method:
Figure PCTKR2023004262-appb-img-000004
식(1)
Figure PCTKR2023004262-appb-img-000004
Equation (1)
Figure PCTKR2023004262-appb-img-000005
는 상수 값이며, x1, x2는 모델을 만들기 위한 변수이고, P는 알츠하이머병 진단을 위한 아밀로이드 양성 확률을 나타낸다.
Figure PCTKR2023004262-appb-img-000005
is a constant value, x1, x2 are variables for creating the model, and P represents the probability of amyloid positivity for diagnosing Alzheimer's disease.
본 발명의 실시예에 따른 알츠하이머병 예후와 관련 있는 바이오마커로는 Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ(Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE유무, 성별, 나이, sTREM2, 및 NfL(Neurofilament Light Chain) 등을 포함할 수 있다. 본 발명에서는 이러한 알츠하이머병 예후와 관련 있는 바이오마커들의 조합을 이용하여 알츠하이머병 진단을 위한 확률을 계산한다. Biomarkers related to the prognosis of Alzheimer's disease according to an embodiment of the present invention include Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ (Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, presence of ApoE, It may include gender, age, sTREM2, and Neurofilament Light Chain (NfL). In the present invention, the probability for diagnosing Alzheimer's disease is calculated using a combination of biomarkers related to the prognosis of Alzheimer's disease.
본 발명의 실시예에 따른 알츠하이머병 예후와 관련 있는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 이용하여 식(2)을 통해 알츠하이머병 진단을 위한 확률(P)을 계산한다: The probability (P) for diagnosing Alzheimer's disease is calculated using equation (2) using the contribution to the expression of Alzheimer's disease of each of the biomarkers related to Alzheimer's disease prognosis according to an embodiment of the present invention:
Figure PCTKR2023004262-appb-img-000006
식(2)
Figure PCTKR2023004262-appb-img-000006
Equation (2)
여기서, k는 알츠하이머병 진단을 위한 확률 계산에 이용된 바이오마커의 수를 나타내고,
Figure PCTKR2023004262-appb-img-000007
는 오차를 보정하기 위한 상수이고, x는 알츠하이머병 진단을 위한 확률(P) 계산에 이용된 바이오마커의 유형,
Figure PCTKR2023004262-appb-img-000008
는 해당 바이오마커의 알츠하이머병 발현에 대한 기여도를 나타내는 회귀계수(상수)이다. Here, k represents the number of biomarkers used to calculate the probability for diagnosing Alzheimer's disease,
Figure PCTKR2023004262-appb-img-000007
is a constant to correct the error, x is the type of biomarker used to calculate the probability (P) for diagnosing Alzheimer's disease,
Figure PCTKR2023004262-appb-img-000008
is a regression coefficient (constant) that represents the contribution of the corresponding biomarker to the expression of Alzheimer's disease.
일 실시예에 따르면, 복수의 바이오마커들 중 APOE (x1), pTau-181 (x2)를 식(1)에 적용하여 알츠하이머병 진단을 위한 확률(P)을 계산할 수 있다. 이때 알츠하이머병 진단을 위한 확률(P)은 식(3)과 같이 나타낼 수 있다: According to one embodiment, the probability (P) for diagnosing Alzheimer's disease can be calculated by applying APOE (x1) and pTau-181 (x2) among the plurality of biomarkers to Equation (1). At this time, the probability (P) for diagnosing Alzheimer's disease can be expressed as equation (3):
Figure PCTKR2023004262-appb-img-000009
식(3)
Figure PCTKR2023004262-appb-img-000009
Equation (3)
또 다른 실시예에 따르면, 복수의 바이오마커들 중 Age (x1), sex (x2), APOE (x3), pTau-181 (x4), NFL (x5)를 식(1)에 적용하여 알츠하이머병 진단을 위한 확률(P)을 계산할 수 있다. 이때 알츠하이머병 진단을 위한 확률(P)은 식(4)과 같이 나타낼 수 있다:According to another embodiment, among the plurality of biomarkers, Age (x1), sex (x2), APOE (x3), pTau-181 (x4), and NFL (x5) are applied to Equation (1) to diagnose Alzheimer's disease. The probability (P) for can be calculated. At this time, the probability (P) for diagnosing Alzheimer's disease can be expressed as equation (4):
Figure PCTKR2023004262-appb-img-000010
식(4)
Figure PCTKR2023004262-appb-img-000010
Equation (4)
또 다른 실시예에 따르면, 복수의 바이오마커들 중 Age (x1), sex (x2), APOE (x3), pTau-181 (x4), NFL (x5), telomere length (x6)를 식(1)에 적용하여 알츠하이머병 진단을 위한 확률(P)을 계산할 수 있다. 이때 알츠하이머병 진단을 위한 확률(P)은 식(5)과 같이 나타낼 수 있다:According to another embodiment, Age (x1), sex (x2), APOE (x3), pTau-181 (x4), NFL (x5), and telomere length (x6) among the plurality of biomarkers are expressed in Equation (1) By applying this, the probability (P) for diagnosing Alzheimer's disease can be calculated. At this time, the probability (P) for diagnosing Alzheimer's disease can be expressed as equation (5):
Figure PCTKR2023004262-appb-img-000011
식(5)
Figure PCTKR2023004262-appb-img-000011
Equation (5)
이와 같이 계산된 알츠하이머병 진단을 위한 확률을 이용하여 AUC(Area Under the ROC Curve)로 나타내고, 상기 AUC를 이용하여 알츠하이머병의 병리학적 양상을 예측할 수 있다. The probability for diagnosing Alzheimer's disease calculated in this way is expressed as AUC (Area Under the ROC Curve), and the pathological aspects of Alzheimer's disease can be predicted using the AUC.
본 발명의 실시예에 따라 대상자로부터 추출된 혈액 또는 뇌척수액의 분석 결과, 상기 바이오마커의 유전자 발현 데이터 및 알츠하이머병 진단 정보는 지속적으로 데이터베이스에 업데이트될 수 있다. 이러한 데이터가 데이터베이스에 업데이트됨에 따라 알츠하이머병 예후와 관련 있는 바이오마커들이 더 추가되거나 또는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도가 조정될 수도 있다. According to an embodiment of the present invention, as a result of analysis of blood or cerebrospinal fluid extracted from a subject, gene expression data of the biomarker and Alzheimer's disease diagnosis information can be continuously updated in the database. As these data are updated in the database, more biomarkers related to Alzheimer's disease prognosis may be added, or the contribution of each biomarker to the expression of Alzheimer's disease may be adjusted.
도 2는 본 발명의 일 실시예에 따른 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 시스템의 구성을 나타내는 도면이다. Figure 2 is a diagram showing the configuration of an Alzheimer's disease diagnosis system using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention.
본 실시예에 따른 알츠하이머병 진단 시스템(200)은 프로세서(210), 버스(220), 네트워크 인터페이스(230), 메모리(240) 및 데이터베이스(250)를 포함할 수 있다. 메모리(240)는 운영체제(241) 및 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 루틴(242)을 포함할 수 있다. 프로세서(210)는 데이터 수집부(211) 및 아밀로이드 양성 확률 계산부(212)를 포함할 수 있다. 다른 실시예들에서 알츠하이머병 진단 시스템(200)은 도 2의 구성요소들보다 더 많은 구성요소들을 포함할 수도 있다. 그러나, 대부분의 종래기술적 구성요소들을 명확하게 도시할 필요성은 없다. 예를 들어, 알츠하이머병 진단 시스템(200)은 디스플레이, 트랜시버(transceiver), 진단 키트, 스마트 단말 등과 같은 다른 구성요소들을 포함할 수도 있다. The Alzheimer's disease diagnosis system 200 according to this embodiment may include a processor 210, a bus 220, a network interface 230, a memory 240, and a database 250. The memory 240 may include an operating system 241 and an Alzheimer's disease diagnosis routine 242 using biomarkers in cerebrospinal fluid and blood. The processor 210 may include a data collection unit 211 and an amyloid positive probability calculation unit 212. In other embodiments, the Alzheimer's disease diagnostic system 200 may include more components than those of FIG. 2 . However, there is no need to clearly show most prior art components. For example, the Alzheimer's disease diagnosis system 200 may include other components such as a display, transceiver, diagnostic kit, smart terminal, etc.
메모리(240)는 컴퓨터에서 판독 가능한 기록 매체로서, RAM(random access memory), ROM(read only memory) 및 디스크 드라이브와 같은 비소멸성 대용량 기록장치(permanent mass storage device)를 포함할 수 있다. 또한, 메모리(240)에는 운영체제(241)와 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단 루틴(242)을 위한 프로그램 코드가 저장될 수 있다. 이러한 소프트웨어 구성요소들은 드라이브 메커니즘(drive mechanism, 미도시)을 이용하여 메모리(240)와는 별도의 컴퓨터에서 판독 가능한 기록 매체로부터 로딩될 수 있다. 이러한 별도의 컴퓨터에서 판독 가능한 기록 매체는 플로피 드라이브, 디스크, 테이프, DVD/CD-ROM 드라이브, 메모리 카드 등의 컴퓨터에서 판독 가능한 기록 매체(미도시)를 포함할 수 있다. 다른 실시예에서 소프트웨어 구성요소들은 컴퓨터에서 판독 가능한 기록 매체가 아닌 네트워크 인터페이스(230)를 통해 메모리(240)에 로딩될 수도 있다. The memory 240 is a computer-readable recording medium and may include a non-permanent mass storage device such as random access memory (RAM), read only memory (ROM), and a disk drive. Additionally, the memory 240 may store an operating system 241 and program code for an Alzheimer's disease diagnosis routine 242 using biomarkers in cerebrospinal fluid and blood. These software components may be loaded from a computer-readable recording medium separate from the memory 240 using a drive mechanism (not shown). Such separate computer-readable recording media may include computer-readable recording media (not shown) such as floppy drives, disks, tapes, DVD/CD-ROM drives, and memory cards. In another embodiment, software components may be loaded into the memory 240 through the network interface 230 rather than a computer-readable recording medium.
버스(220)는 알츠하이머병 진단 시스템(200)의 구성요소들간의 통신 및 데이터 전송을 가능하게 할 수 있다. 버스(220)는 고속 시리얼 버스(high-speed serial bus), 병렬 버스(parallel bus), SAN(Storage Area Network) 및/또는 다른 적절한 통신 기술을 이용하여 구성될 수 있다. Bus 220 may enable communication and data transfer between components of Alzheimer's disease diagnosis system 200. Bus 220 may be configured using a high-speed serial bus, parallel bus, storage area network (SAN), and/or other suitable communication technology.
네트워크 인터페이스(230)는 알츠하이머병 진단 시스템(200)을 컴퓨터 네트워크에 연결하기 위한 컴퓨터 하드웨어 구성요소일 수 있다. 네트워크 인터페이스(230)는 알츠하이머병 진단 시스템(200)을 무선 또는 유선 커넥션을 통해 컴퓨터 네트워크에 연결시킬 수 있다. Network interface 230 may be a computer hardware component for connecting Alzheimer's disease diagnosis system 200 to a computer network. The network interface 230 may connect the Alzheimer's disease diagnosis system 200 to a computer network through a wireless or wired connection.
데이터베이스(250)는 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단을 위해 필요한 모든 정보를 저장 및 유지하는 역할을 할 수 있다. 도 2에서는 알츠하이머병 진단 시스템(200)의 내부에 데이터베이스(250)를 구축하여 포함하는 것으로 도시하고 있으나, 이에 한정되는 것은 아니며 시스템 구현 방식이나 환경 등에 따라 생략될 수 있고 혹은 전체 또는 일부의 데이터베이스가 별개의 다른 시스템 상에 구축된 외부 데이터베이스로서 존재하는 것 또한 가능하다.The database 250 may serve to store and maintain all information necessary for diagnosing Alzheimer's disease using biomarkers in cerebrospinal fluid and blood. In Figure 2, it is shown that the database 250 is built and included inside the Alzheimer's disease diagnosis system 200, but it is not limited to this and may be omitted depending on the system implementation method or environment, or all or part of the database may be included. It is also possible to exist as an external database built on a separate system.
프로세서(210)는 기본적인 산술, 로직 및 알츠하이머병 진단 시스템(200)의 입출력 연산을 수행함으로써, 컴퓨터 프로그램의 명령을 처리하도록 구성될 수 있다. 명령은 메모리(240) 또는 네트워크 인터페이스(230)에 의해, 그리고 버스(220)를 통해 프로세서(210)로 제공될 수 있다. 프로세서(210)는 데이터 수집부(211) 및 아밀로이드 양성 확률 계산부(212)를 위한 프로그램 코드를 실행하도록 구성될 수 있다. 이러한 프로그램 코드는 메모리(240)와 같은 기록 장치에 저장될 수 있다.The processor 210 may be configured to process commands of a computer program by performing basic arithmetic, logic, and input/output operations of the Alzheimer's disease diagnosis system 200. Commands may be provided to processor 210 by memory 240 or network interface 230 and via bus 220. The processor 210 may be configured to execute program code for the data collection unit 211 and the amyloid positive probability calculation unit 212. These program codes may be stored in a recording device such as memory 240.
데이터 수집부(211) 및 아밀로이드 양성 확률 계산부(212)는 도 1의 단계들(110~120)을 수행하기 위해 구성될 수 있다.The data collection unit 211 and the amyloid positive probability calculation unit 212 may be configured to perform steps 110 to 120 of FIG. 1.
알츠하이머병 진단 시스템(200)은 데이터 수집부(211) 및 아밀로이드 양성 확률 계산부(212)를 포함할 수 있다.The Alzheimer's disease diagnosis system 200 may include a data collection unit 211 and an amyloid positive probability calculation unit 212.
본 발명의 실시예에 따른 데이터 수집부(211)는 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득한다. The data collection unit 211 according to an embodiment of the present invention acquires gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from a subject.
본 발명의 실시예에 따른 알츠하이머병 진단 시스템(200)은 진단 키트를 통해 대상자로부터 추출된 혈액 또는 뇌척수액을 획득하고, 데이터 수집부(211)는 이와 같이 획득된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득한다. The Alzheimer's disease diagnosis system 200 according to an embodiment of the present invention acquires blood or cerebrospinal fluid extracted from a subject through a diagnostic kit, and the data collection unit 211 collects a plurality of biomarkers from the blood or cerebrospinal fluid obtained in this way. Acquire gene expression data.
본 발명의 실시예에 따른 아밀로이드 양성 확률 계산부(212)는 획득된 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산한다. The amyloid positivity probability calculation unit 212 according to an embodiment of the present invention calculates the probability for diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis in order to determine the positivity of amyloid from the acquired data. do.
본 발명의 실시예에 따른 아밀로이드 양성 확률 계산부(212)는 Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ(Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE유무, 성별, 나이, sTREM2, 및 NfL(Neurofilament Light Chain) 등을 을 포함하는 알츠하이머병 예후와 관련 있는 바이오마커들의 조합을 이용하여 알츠하이머병 진단을 위한 확률을 계산한다.The amyloid positive probability calculator 212 according to an embodiment of the present invention includes Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ (Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE presence, and gender. The probability of diagnosing Alzheimer's disease is calculated using a combination of biomarkers related to Alzheimer's disease prognosis, including age, sTREM2, and NfL (Neurofilament Light Chain).
본 발명의 실시예에 따른 아밀로이드 양성 확률 계산부(212)는 알츠하이머병 예후와 관련 있는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 이용하여 상기 식(2)을 통해 알츠하이머병 진단을 위한 확률(P)을 계산한다. The amyloid positive probability calculator 212 according to an embodiment of the present invention uses the contribution to the expression of Alzheimer's disease of each biomarker related to the prognosis of Alzheimer's disease and uses the equation (2) to determine the probability of diagnosing Alzheimer's disease ( Calculate P).
이와 같이 계산된 알츠하이머병 진단을 위한 확률을 이용하여 AUC(Area Under the ROC Curve)로 나타내고, 상기 AUC를 이용하여 알츠하이머병의 병리학적 양상을 예측할 수 있다. The probability for diagnosing Alzheimer's disease calculated in this way is expressed as AUC (Area Under the ROC Curve), and the pathological aspects of Alzheimer's disease can be predicted using the AUC.
본 발명의 실시예에 따른 알츠하이머병 진단 시스템(200)은 진단 키트 및 스마트 단말을 더 포함할 수 있다. The Alzheimer's disease diagnosis system 200 according to an embodiment of the present invention may further include a diagnostic kit and a smart terminal.
본 발명의 실시예에 따른 진단 키트는 복수의 바이오마커의 유전자 발현 데이터를 획득하기 위해 대상자로부터 추출된 혈액 또는 뇌척수액을 획득할 수 있다. The diagnostic kit according to an embodiment of the present invention can obtain blood or cerebrospinal fluid extracted from a subject to obtain gene expression data of multiple biomarkers.
본 발명의 실시예에 따른 스마트 단말은 알츠하이머병 진단을 위한 어플리케이션을 탑재할 수 있다. A smart terminal according to an embodiment of the present invention can be equipped with an application for diagnosing Alzheimer's disease.
상기 스마트 단말을 이용한 알츠하이머병 진단 정보는 데이터베이스(250)를 통해 관리될 수 있다. Alzheimer's disease diagnosis information using the smart terminal can be managed through the database 250.
본 발명의 실시예에 따라 대상자로부터 추출된 혈액 또는 뇌척수액의 분석 결과, 상기 바이오마커의 유전자 발현 데이터 및 알츠하이머병 진단 정보는 지속적으로 데이터베이스(250)에 업데이트될 수 있다. 본 발명의 실시예에 따른 아밀로이드 양성 확률 계산부(212)는 이러한 데이터가 데이터베이스(250)에 업데이트됨에 따라 알츠하이머병 예후와 관련 있는 바이오마커들이 더 추가되거나 또는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 조정할 수도 있다.According to an embodiment of the present invention, as a result of analysis of blood or cerebrospinal fluid extracted from a subject, gene expression data of the biomarker and Alzheimer's disease diagnosis information may be continuously updated in the database 250. As these data are updated in the database 250, the amyloid positive probability calculator 212 according to an embodiment of the present invention adds more biomarkers related to the prognosis of Alzheimer's disease or determines the expression of Alzheimer's disease for each of the biomarkers. You can also adjust your contribution.
도 3은 종래기술에 따른 하나의 바이오마커가 아밀로이드 양성에 대해 가지는 AUC 값을 나타내는 그래프이다. Figure 3 is a graph showing the AUC value of one biomarker according to the prior art for amyloid positivity.
본 발명의 실시예에 따른 뇌척수액과 혈액 내 바이오마커들을 활용한 알츠하이머병 진단을 위해 대상자 101 명으로부터 Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ(Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE유무, 성별, 나이, sTREM2, 및 NfL(Neurofilament Light Chain) 등을 측정하였다. For the diagnosis of Alzheimer's disease using biomarkers in cerebrospinal fluid and blood according to an embodiment of the present invention, Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ (Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE presence, gender, age, sTREM2, and NfL (Neurofilament Light Chain) were measured.
도 3과 같이, 측정한 하나의 바이오마커만으로도 이미 AUC(Area Under the ROC Curve) 값 0.7-0.8대로 충분히 아밀로이드 PET 양성기준을 분별하고 있다.As shown in Figure 3, just one measured biomarker is already sufficient to distinguish amyloid PET positive criteria with an AUC (Area Under the ROC Curve) value of 0.7-0.8.
도 4는 본 발명의 일 실시예에 따른 복수의 바이오마커들의 조합이 아밀로이드 양성에 대해 가지는 AUC 값을 나타내는 그래프이다.Figure 4 is a graph showing the AUC value of a combination of multiple biomarkers for amyloid positivity according to an embodiment of the present invention.
도 4(a)는 플라즈마 바이오마커, 도 4(b)는 CSF 바이오마커의 AUC를 각각 나타낸다. Figure 4(a) shows the AUC of the plasma biomarker and Figure 4(b) shows the AUC of the CSF biomarker.
도 4와 같이 본 발명의 실시예에 따른 복수의 바이오마커들의 조합을 이용하여 알츠하이머병 진단을 위한 확률을 계산함으로써, 도 3의 하나의 바이오마커보다 강력한 AUC 값 0.8 중후반대로 알츠하이머병의 병리학적 양상을 예측하는데 적합한 시스템을 가동할 수 있다.As shown in Figure 4, by calculating the probability for diagnosing Alzheimer's disease using a combination of multiple biomarkers according to an embodiment of the present invention, the pathological aspect of Alzheimer's disease is shown to have an AUC value in the mid to high 0.8 range, which is stronger than the single biomarker in Figure 3. A system suitable for predicting can be operated.
본 발명의 실시예에 따라 알츠하이머병을 가장 높은 확률로 감지할 수 있는 바이오마커의 조합을 찾아 알츠하이머병 진단을 위한 확률을 계산하기 위한 수식을 제안하였다. 제안하는 수식에 대상에게서 얻은 각 바이오마커의 수치를 기입하면 대상자의 아밀로이드 양성 유무를 진단 예측할 수 있다. According to an embodiment of the present invention, a formula for calculating the probability of diagnosing Alzheimer's disease was proposed by finding a combination of biomarkers that can detect Alzheimer's disease with the highest probability. By entering the values of each biomarker obtained from the subject in the proposed formula, it is possible to diagnose and predict whether the subject is positive for amyloid.
본 발명의 실시예에 따른 실험을 통해 뇌척수액과 혈액에서 나이, 성별, Phospho-tau 181, NfL, ApoE4 유무의 조합이 아밀로이드 PET 결과와 비교하여 양성 진단을 예측할 수 있는 최고의 조합임을 발견하였다. 이를 토대로 본 발명에서 제안하는 수식에 환자의 각각의 바이오마커들 값을 입력하면 알츠하이머병의 진단을 예측할 수 있는 확률을 구할 수 있다. 이러한 바이오마커들의 조합은 일 실시예일뿐 더 많은 또는 더욱 다양한 바이오마커들의 조합을 이용하여 알츠하이머병의 진단을 예측할 수도 있다. Through an experiment according to an embodiment of the present invention, it was found that the combination of age, gender, presence or absence of Phospho-tau 181, NfL, and ApoE4 in cerebrospinal fluid and blood was the best combination for predicting a benign diagnosis compared to amyloid PET results. Based on this, by entering the values of each patient's biomarkers into the formula proposed in the present invention, the probability of predicting a diagnosis of Alzheimer's disease can be obtained. This combination of biomarkers is only an example, and the diagnosis of Alzheimer's disease can be predicted using a combination of more or more diverse biomarkers.
본 발명의 실시예에 따라 대상자로부터 추출된 혈액 또는 뇌척수액의 분석 결과, 상기 바이오마커의 유전자 발현 데이터 및 알츠하이머병 진단 정보는 지속적으로 데이터베이스에 업데이트될 수 있다. 이러한 데이터가 데이터베이스에 업데이트됨에 따라 알츠하이머병 예후와 관련 있는 바이오마커들이 더 추가되거나 또는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도가 조정될 수도 있다. According to an embodiment of the present invention, as a result of analysis of blood or cerebrospinal fluid extracted from a subject, gene expression data of the biomarker and Alzheimer's disease diagnosis information can be continuously updated in the database. As these data are updated in the database, more biomarkers related to Alzheimer's disease prognosis may be added, or the contribution of each biomarker to the expression of Alzheimer's disease may be adjusted.
본 발명의 실시예에 따라 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률은 다음과 같이 정리할 수 있다.According to an embodiment of the present invention, the probability of diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis to determine whether amyloid is positive can be summarized as follows.
조합 변수combination variable 아밀로이드 양성 예측 확률Amyloid positive predicted probability
P-tau181 + APOE(e4 carrier) P-tau181 + APOE (e4 carrier) 87.1%87.1%
Age + sex + P-tau181 + APOE + NFLAge+sex+P-tau181+APOE+NFL 88.9%88.9%
Age + sex + P-tau181 + APOE + NFL + telomere lengthAge + sex + P-tau181 + APOE + NFL + telomere length 89.1%89.1%
상기 식(3)을 통해, 실제 대상자에서 아밀로이드 양성을 예측할 확률을 계산한 예시를 아래에서 설명한다. An example of calculating the probability of predicting amyloid positivity in an actual subject using Equation (3) above is described below.
제1 예시에서, 혈액 내 P-tau181 값이 4.87 pg/ml, APOE e4 유전자를 가지고 있다는 것 이외 대상자의 다른 정보가 전혀 없다면, 해당 대상자가 아밀로이드 양성일 확률은 92.4% 로 계산되었다. In the first example, if there was no other information about the subject other than that the blood P-tau181 value was 4.87 pg/ml and that the subject had the APOE e4 gene, the probability that the subject was positive for amyloid was calculated to be 92.4%.
제2 예시에서, APOE e4유전자를 가지고 있지 않으면서 P-tau181 값이 3.0 pg/ml 이며 대상자에 대한 다른 정보가 없다면 해당 대상자가 아밀로이드 양성일 확률은 31.7% 로 계산되었다. In the second example, if the subject does not have the APOE e4 gene, the P-tau181 value is 3.0 pg/ml, and there is no other information about the subject, the probability of the subject being amyloid positive was calculated to be 31.7%.
제3 예시에서, 대상자에 대한 정보가 많으면, 예측 확률을 높일 수 있으며, 50세 남자 대상자가 APOE e4를 가지고 있지 않고, p-tau181 이 15 pg/ml, NFL이 12 pg/ml로 확인된 경우, 해당 대상자가 아밀로이드 양성일 확률은 99.99% 로 계산되었다. In the third example, if there is more information about the subject, the prediction probability can be increased, and when a 50-year-old male subject does not have APOE e4, p-tau181 is confirmed to be 15 pg/ml, and NFL is confirmed to be 12 pg/ml. , the probability that the subject was positive for amyloid was calculated to be 99.99%.
제4 예시에서, 만약 80세 여자 대상자가 APOE e4를 가지고 있지 않으며, p-tau181 이 1 pg/ml, NFL이 2 pg/ml로 확인되면, 해당 대상자가 아밀로이드 양성일 확률은 13.1% 로 계산되었다. In the fourth example, if an 80-year-old female subject did not have APOE e4, p-tau181 was confirmed to be 1 pg/ml, and NFL was 2 pg/ml, the probability that the subject was positive for amyloid was calculated to be 13.1%.
알츠하이머병의 치료를 위해 수많은 연구들이 계속 되어 왔지만 결과적으로 모두 실패하였고, 이로 인해 바이오마커의 변화만을 가지고도 효과가 있는 약물은 FDA 승인을 해 주는 방향으로 연구의 흐름이 진행되고 있다. 하지만 이 또한 개발 초기에 해당하여 바이오마커의 선정과 이를 이용한 진단법은 아직 더욱 개발되어야 하는 실정이다. 본 발명은 알츠하이머의 진단을 용이하게 해 줄 수 있는 시스템으로 기존의 고비용 저접근성을 가진 아밀로이드 PET, MRI와 같은 진단법보다 쉽고 빠르게 결과를 얻을 수 있다. 뿐만 아니라 진단에 대한 접근성이 우수하여 알츠하이머병의 조기진단을 가능하게 해 줄 수 있는 시스템으로 종래기술보다 더욱 뛰어난 분별력을 가지고 있어 기술적 개발 가치가 뛰어나다. Numerous studies have been conducted to treat Alzheimer's disease, but all have ultimately failed, and as a result, research is progressing toward FDA approval of drugs that are effective only through changes in biomarkers. However, this is also in the early stages of development, and the selection of biomarkers and diagnostic methods using them still need to be further developed. The present invention is a system that can facilitate the diagnosis of Alzheimer's, and results can be obtained more easily and quickly than existing high-cost and low-access diagnostic methods such as amyloid PET and MRI. In addition, it is a system that can enable early diagnosis of Alzheimer's disease due to its excellent accessibility to diagnosis, and has excellent technological development value as it has better discrimination ability than conventional technologies.
고령화 사회로 가는 우리나라의 경우 2040년 치매 환자의 수는 196만명에 이르고 이로 인한 사회적 비용은 34조 2000억에 이를 것으로 예상된다. 빠르게 진행하는 고령화 사회에 알츠하이머병 환자 수의 증가도 불가피하며 이로 인한 사회경제적 부담도 함께 증가할 것으로 예상된다. In Korea, which is moving towards an aging society, the number of dementia patients in 2040 is expected to reach 1.96 million, and the resulting social cost is expected to reach 34.2 trillion won. In a rapidly aging society, the number of Alzheimer's disease patients will inevitably increase, and the resulting socioeconomic burden is expected to increase as well.
이에 따라 본 발명에서 제안하는 시스템을 통해 알츠하이머병 진단으로 인한 의료비 예산의 감축 및 조기 진단 가능으로 인한 개인 및 사회 경제적 비용의 감소를 예상해 볼 수 있다. Accordingly, the system proposed in the present invention can be expected to reduce the medical budget due to the diagnosis of Alzheimer's disease and reduce personal and socioeconomic costs due to early diagnosis.
이상에서 설명된 장치는 하드웨어 구성요소, 소프트웨어 구성요소, 및/또는 하드웨어 구성요소 및 소프트웨어 구성요소의 조합으로 구현될 수 있다. 예를 들어, 실시예들에서 설명된 장치 및 구성요소는, 예를 들어, 프로세서, 콘트롤러, ALU(arithmetic logic unit), 디지털 신호 프로세서(digital signal processor), 마이크로컴퓨터, FPA(field programmable array), PLU(programmable logic unit), 마이크로프로세서, 또는 명령(instruction)을 실행하고 응답할 수 있는 다른 어떠한 장치와 같이, 하나 이상의 범용 컴퓨터 또는 특수 목적 컴퓨터를 이용하여 구현될 수 있다. 처리 장치는 운영 체제(OS) 및 상기 운영 체제 상에서 수행되는 하나 이상의 소프트웨어 애플리케이션을 수행할 수 있다.　 또한, 처리 장치는 소프트웨어의 실행에 응답하여, 데이터를 접근, 저장, 조작, 처리 및 생성할 수도 있다.　 이해의 편의를 위하여, 처리 장치는 하나가 사용되는 것으로 설명된 경우도 있지만, 해당 기술분야에서 통상의 지식을 가진 자는, 처리 장치가 복수 개의 처리 요소(processing element) 및/또는 복수 유형의 처리 요소를 포함할 수 있음을 알 수 있다.　 예를 들어, 처리 장치는 복수 개의 프로세서 또는 하나의 프로세서 및 하나의 콘트롤러를 포함할 수 있다.　 또한, 병렬 프로세서(parallel processor)와 같은, 다른 처리 구성(processing configuration)도 가능하다.The device described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, devices and components described in embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general-purpose or special-purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. A processing device may execute an operating system (OS) and one or more software applications that run on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.
소프트웨어는 컴퓨터 프로그램(computer program), 코드(code), 명령(instruction), 또는 이들 중 하나 이상의 조합을 포함할 수 있으며, 원하는 대로 동작하도록 처리 장치를 구성하거나 독립적으로 또는 결합적으로(collectively) 처리 장치를 명령할 수 있다.　 소프트웨어 및/또는 데이터는, 처리 장치에 의하여 해석되거나 처리 장치에 명령 또는 데이터를 제공하기 위하여, 어떤 유형의 기계, 구성요소(component), 물리적 장치, 가상 장치(virtual equipment), 컴퓨터 저장 매체 또는 장치에 구체화(embody)될 수 있다.　 소프트웨어는 네트워크로 연결된 컴퓨터 시스템 상에 분산되어서, 분산된 방법으로 저장되거나 실행될 수도 있다. 소프트웨어 및 데이터는 하나 이상의 컴퓨터 판독 가능 기록 매체에 저장될 수 있다.Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. It can be embodied in . Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.
실시예에 따른 방법은 다양한 컴퓨터 수단을 통하여 수행될 수 있는 프로그램 명령 형태로 구현되어 컴퓨터 판독 가능 매체에 기록될 수 있다.　 상기 컴퓨터 판독 가능 매체는 프로그램 명령, 데이터 파일, 데이터 구조 등을 단독으로 또는 조합하여 포함할 수 있다.　 상기 매체에 기록되는 프로그램 명령은 실시예를 위하여 특별히 설계되고 구성된 것들이거나 컴퓨터 소프트웨어 당업자에게 공지되어 사용 가능한 것일 수도 있다.　 컴퓨터 판독 가능 기록 매체의 예에는 하드 디스크, 플로피 디스크 및 자기 테이프와 같은 자기 매체(magnetic media), CD-ROM, DVD와 같은 광기록 매체(optical media), 플롭티컬 디스크(floptical disk)와 같은 자기-광 매체(magneto-optical media), 및 롬(ROM), 램(RAM), 플래시 메모리 등과 같은 프로그램 명령을 저장하고 수행하도록 특별히 구성된 하드웨어 장치가 포함된다.　 프로그램 명령의 예에는 컴파일러에 의해 만들어지는 것과 같은 기계어 코드뿐만 아니라 인터프리터 등을 사용해서 컴퓨터에 의해서 실행될 수 있는 고급 언어 코드를 포함한다.　 The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -Includes optical media (magneto-optical media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.
이상과 같이 실시예들이 비록 한정된 실시예와 도면에 의해 설명되었으나, 해당 기술분야에서 통상의 지식을 가진 자라면 상기의 기재로부터 다양한 수정 및 변형이 가능하다.　 예를 들어, 설명된 기술들이 설명된 방법과 다른 순서로 수행되거나, 및/또는 설명된 시스템, 구조, 장치, 회로 등의 구성요소들이 설명된 방법과 다른 형태로 결합 또는 조합되거나, 다른 구성요소 또는 균등물에 의하여 대치되거나 치환되더라도 적절한 결과가 달성될 수 있다.As described above, although the embodiments have been described with limited examples and drawings, various modifications and variations can be made by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.
그러므로, 다른 구현들, 다른 실시예들 및 특허청구범위와 균등한 것들도 후술하는 특허청구범위의 범위에 속한다.Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (10)

  1. 데이터 수집부를 통해 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득하는 단계; 및 Obtaining gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from the subject through a data collection unit; and
    아밀로이드 양성 확률 계산부를 통해 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 단계Calculating the probability for diagnosing Alzheimer's disease using gene expression data of biomarkers related to Alzheimer's disease prognosis in order to determine the positivity of amyloid from the data through the amyloid positive probability calculator.
    를 포함하는 컴퓨터 판독 가능한 저장 매체에 저장된 프로그램. A program stored on a computer-readable storage medium containing a.
  2. 제1항에 있어서,According to paragraph 1,
    상기 아밀로이드 양성 확률 계산부를 통해 상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 단계는, The step of calculating the probability for diagnosing Alzheimer's disease using the gene expression data of a biomarker related to the prognosis of Alzheimer's disease in order to determine the positivity of amyloid from the data through the amyloid positivity probability calculation unit,
    Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ(Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE유무, 성별, 나이, sTREM2, 및 NfL(Neurofilament Light Chain) 을 포함하는 알츠하이머병 예후와 관련 있는 바이오마커들의 조합을 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 Alzheimer's including Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ (Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE presence, gender, age, sTREM2, and NfL (Neurofilament Light Chain) Calculate the probability of diagnosing Alzheimer's disease using a combination of biomarkers related to disease prognosis.
    컴퓨터 판독 가능한 저장 매체에 저장된 프로그램. A program stored on a computer-readable storage medium.
  3. 제2항에 있어서,According to paragraph 2,
    상기 알츠하이머병 예후와 관련 있는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 이용하여 하기 식을 통해 알츠하이머병 진단을 위한 확률(P)을 계산하고, Calculate the probability (P) for diagnosing Alzheimer's disease using the following equation using the contribution of each of the biomarkers related to the prognosis of Alzheimer's disease to the expression of Alzheimer's disease,
    Figure PCTKR2023004262-appb-img-000012
    Figure PCTKR2023004262-appb-img-000012
    여기서, k는 알츠하이머병 진단을 위한 확률 계산에 이용된 바이오마커의 수를 나타내고,
    Figure PCTKR2023004262-appb-img-000013
    는 오차를 보정하기 위한 상수이고, x는 알츠하이머병 진단을 위한 확률(P) 계산에 이용된 바이오마커의 유형,
    Figure PCTKR2023004262-appb-img-000014
    는 해당 바이오마커의 알츠하이머병 발현에 대한 기여도를 나타내는 회귀계수(상수)인     Here, k represents the number of biomarkers used to calculate the probability for diagnosing Alzheimer's disease,
    Figure PCTKR2023004262-appb-img-000013
    is a constant to correct the error, x is the type of biomarker used to calculate the probability (P) for diagnosing Alzheimer's disease,
    Figure PCTKR2023004262-appb-img-000014
    is a regression coefficient (constant) indicating the contribution of the corresponding biomarker to the expression of Alzheimer's disease.
    컴퓨터 판독 가능한 저장 매체에 저장된 프로그램. A program stored on a computer-readable storage medium.
  4. 제3항에 있어서,According to paragraph 3,
    상기 알츠하이머병 진단을 위한 확률을 이용하여 AUC(Area Under the ROC Curve)로 나타내고, 상기 AUC를 이용하여 알츠하이머병의 병리학적 양상을 예측하는 The probability for diagnosing Alzheimer's disease is used to express AUC (Area Under the ROC Curve), and the AUC is used to predict the pathological aspect of Alzheimer's disease.
    컴퓨터 판독 가능한 저장 매체에 저장된 프로그램. A program stored on a computer-readable storage medium.
  5. 제3항에 있어서,According to paragraph 3,
    상기 혈액 또는 뇌척수액의 분석 결과, 상기 바이오마커의 유전자 발현 데이터 및 알츠하이머병 진단 정보가 데이터베이스에 업데이트됨에 따라 상기 알츠하이머병 예후와 관련 있는 바이오마커들이 더 추가되거나 또는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도가 조정되는 As a result of the analysis of the blood or cerebrospinal fluid, the gene expression data of the biomarkers and the Alzheimer's disease diagnosis information are updated in the database, more biomarkers related to the prognosis of the Alzheimer's disease are added or the expression of Alzheimer's disease for each of the biomarkers is updated. contribution is adjusted
    컴퓨터 판독 가능한 저장 매체에 저장된 프로그램. A program stored on a computer-readable storage medium.
  6. 대상자로부터 추출된 혈액 또는 뇌척수액으로부터 복수의 바이오마커의 유전자 발현 데이터를 획득하는 데이터 수집부; 및 a data collection unit that acquires gene expression data of a plurality of biomarkers from blood or cerebrospinal fluid extracted from the subject; and
    상기 데이터로부터 아밀로이드의 양성을 판단하기 위해 알츠하이머병 예후와 관련 있는 바이오마커의 유전자 발현 데이터를 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 아밀로이드 양성 확률 계산부 An amyloid positivity probability calculation unit that calculates the probability for diagnosing Alzheimer's disease using gene expression data of biomarkers related to the prognosis of Alzheimer's disease in order to determine the positivity of amyloid from the above data.
    를 포함하는 알츠하이머병 진단 시스템. Alzheimer's disease diagnosis system including.
  7. 제6항에 있어서,According to clause 6,
    상기 아밀로이드 양성 확률 계산부는, The amyloid positive probability calculator,
    Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ(Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE유무, 성별, 나이, sTREM2, 및 NfL(Neurofilament Light Chain) 을 포함하는 알츠하이머병 예후와 관련 있는 바이오마커들의 조합을 이용하여 알츠하이머병 진단을 위한 확률을 계산하는 Alzheimer's disease including Phospho-tau 181, Phospho-tau 199, Total-tau, ApoE, Aβ (Amyloid beta) 42, Aβ40, Neurogranin, Telomere length, ApoE presence, gender, age, sTREM2, and NfL (Neurofilament Light Chain) Calculate the probability of diagnosing Alzheimer's disease using a combination of biomarkers related to disease prognosis.
    알츠하이머병 진단 시스템. Alzheimer's disease diagnosis system.
  8. 제7항에 있어서,In clause 7,
    상기 아밀로이드 양성 확률 계산부는, The amyloid positive probability calculator,
    상기 알츠하이머병 예후와 관련 있는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 이용하여 하기 식을 통해 알츠하이머병 진단을 위한 확률(P)을 계산하고, Calculate the probability (P) for diagnosing Alzheimer's disease using the following equation using the contribution of each of the biomarkers related to the prognosis of Alzheimer's disease to the expression of Alzheimer's disease,
    Figure PCTKR2023004262-appb-img-000015
    Figure PCTKR2023004262-appb-img-000015
    여기서, k는 알츠하이머병 진단을 위한 확률 계산에 이용된 바이오마커의 수를 나타내고,
    Figure PCTKR2023004262-appb-img-000016
    는 오차를 보정하기 위한 상수이고, x는 알츠하이머병 진단을 위한 확률(P) 계산에 이용된 바이오마커의 유형,
    Figure PCTKR2023004262-appb-img-000017
    는 해당 바이오마커의 알츠하이머병 발현에 대한 기여도를 나타내는 회귀계수(상수)인    Here, k represents the number of biomarkers used to calculate the probability for diagnosing Alzheimer's disease,
    Figure PCTKR2023004262-appb-img-000016
    is a constant to correct the error, x is the type of biomarker used to calculate the probability (P) for diagnosing Alzheimer's disease,
    Figure PCTKR2023004262-appb-img-000017
    is a regression coefficient (constant) indicating the contribution of the corresponding biomarker to the expression of Alzheimer's disease.
    알츠하이머병 진단 시스템. Alzheimer's disease diagnosis system.
  9. 제8항에 있어서,According to clause 8,
    상기 아밀로이드 양성 확률 계산부는,The amyloid positive probability calculator,
    상기 알츠하이머병 진단을 위한 확률을 이용하여 AUC(Area Under the ROC Curve)로 나타내고, 상기 AUC를 이용하여 알츠하이머병의 병리학적 양상을 예측하는 The probability for diagnosing Alzheimer's disease is used to express AUC (Area Under the ROC Curve), and the AUC is used to predict the pathological aspect of Alzheimer's disease.
    알츠하이머병 진단 시스템. Alzheimer's disease diagnosis system.
  10. 제8항에 있어서,According to clause 8,
    복수의 바이오마커의 유전자 발현 데이터를 획득하기 위해 대상자로부터 추출된 혈액 또는 뇌척수액을 분석하기 위한 진단 키트; A diagnostic kit for analyzing blood or cerebrospinal fluid extracted from a subject to obtain gene expression data of multiple biomarkers;
    알츠하이머병 진단을 위한 어플리케이션을 탑재한 스마트 단말; 및 Smart terminal equipped with an application for diagnosing Alzheimer's disease; and
    상기 스마트 단말을 이용한 알츠하이머병 진단 정보를 관리하는 데이터베이스Database that manages Alzheimer's disease diagnosis information using the smart terminal
    를 더 포함하고, It further includes,
    상기 아밀로이드 양성 확률 계산부는, The amyloid positive probability calculator,
    상기 혈액 또는 뇌척수액의 분석 결과, 상기 바이오마커의 유전자 발현 데이터 및 알츠하이머병 진단 정보가 상기 데이터베이스에 업데이트됨에 따라 상기 알츠하이머병 예후와 관련 있는 바이오마커들이 더 추가되거나 또는 바이오마커들 각각의 알츠하이머병 발현에 대한 기여도를 조정하는 As a result of the analysis of the blood or cerebrospinal fluid, the gene expression data of the biomarkers and the Alzheimer's disease diagnosis information are updated in the database, more biomarkers related to the prognosis of the Alzheimer's disease are added or the expression of Alzheimer's disease for each of the biomarkers is updated. adjusting the contribution to
    알츠하이머병 진단 시스템.Alzheimer's disease diagnosis system.
PCT/KR2023/004262 2022-04-01 2023-03-30 System for diagnosing alzheimer's disease by using biomarkers in cerebrospinal fluid and blood WO2023191538A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2022-0041098 2022-04-01
KR1020220041098A KR20230142182A (en) 2022-04-01 2022-04-01 Alzheimer's Disease Diagnosis System using Biomarkers in Cerebrospinal Fluid and Blood

Publications (1)

Publication Number Publication Date
WO2023191538A1 true WO2023191538A1 (en) 2023-10-05

Family

ID=88202820

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2023/004262 WO2023191538A1 (en) 2022-04-01 2023-03-30 System for diagnosing alzheimer's disease by using biomarkers in cerebrospinal fluid and blood

Country Status (2)

Country Link
KR (1) KR20230142182A (en)
WO (1) WO2023191538A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160146650A (en) * 2014-01-28 2016-12-21 프레뎀테크 게엠바하 Biomarker and methods for early diagnosis of alzheimer's disease
KR20190063275A (en) * 2017-11-29 2019-06-07 서울대학교산학협력단 Predictive model for the accumulation of brain amyloid and predictive method using thereof
KR102044094B1 (en) * 2018-05-03 2019-11-12 한동대학교 산학협력단 Method for classifying cancer or normal by deep neural network using gene expression data
KR20190137012A (en) * 2018-05-31 2019-12-10 한국과학기술원 Method for predicting disease risk based on analysis of complex genetic information

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160146650A (en) * 2014-01-28 2016-12-21 프레뎀테크 게엠바하 Biomarker and methods for early diagnosis of alzheimer's disease
KR20190063275A (en) * 2017-11-29 2019-06-07 서울대학교산학협력단 Predictive model for the accumulation of brain amyloid and predictive method using thereof
KR102044094B1 (en) * 2018-05-03 2019-11-12 한동대학교 산학협력단 Method for classifying cancer or normal by deep neural network using gene expression data
KR20190137012A (en) * 2018-05-31 2019-12-10 한국과학기술원 Method for predicting disease risk based on analysis of complex genetic information

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
EVIN GENEVIÈVE: "Platelets and Alzheimer’s disease: Potential of APP as a biomarker", WORLD JOURNAL OF PSYCHIATRY, vol. 2, no. 6, 1 January 2012 (2012-01-01), pages 102 - 113, XP093097110, ISSN: 2220-3206, DOI: 10.5498/wjp.v2.i6.102 *

Also Published As

Publication number Publication date
KR20230142182A (en) 2023-10-11

Similar Documents

Publication Publication Date Title
Miller et al. A 26-hour system of highly sensitive whole genome sequencing for emergency management of genetic diseases
Oh et al. Predicting autism spectrum disorder using blood-based gene expression signatures and machine learning
Chong et al. GWAS and ExWAS of blood mitochondrial DNA copy number identifies 71 loci and highlights a potential causal role in dementia
Wigdor et al. The female protective effect against autism spectrum disorder
US20060099624A1 (en) System and method for providing personalized healthcare for alzheimer&#39;s disease
Ballard et al. Pathway analysis comparison using Crohn's disease genome wide association studies
Shi et al. Episodic memory–related imaging features as valuable biomarkers for the diagnosis of Alzheimer’s disease: A multicenter study based on machine learning
WO2023191538A1 (en) System for diagnosing alzheimer&#39;s disease by using biomarkers in cerebrospinal fluid and blood
Al Hashmi et al. Characteristics and outcomes of patients with cerebral venous sinus thrombosis
Tandon et al. Machine learning selection of most predictive brain proteins suggests role of sugar metabolism in Alzheimer’s disease
He et al. Integrative computational approach identifies immune‐relevant biomarkers in ulcerative colitis
Shigemizu et al. Classification and deep-learning–based prediction of Alzheimer disease subtypes by using genomic data
Zhao et al. Eye-brain connections revealed by multimodal retinal and brain imaging genetics in the UK Biobank
Vukadinovic et al. Deep learning-enabled analysis of medical images identifies cardiac sphericity as an early marker of cardiomyopathy and related outcomes
Nomura et al. Predicting serious bacterial infection in febrile young infants utilizing body temperature
Kim et al. Identifying novel genetic variants for brain amyloid deposition: a genome-wide association study in the Korean population
Carreiro et al. Integrative biomarker discovery in neurodegenerative diseases
Li et al. Study on the correlation and clinical significance of T-lymphocyte Subsets, IL-6 and PCT in the severity of patients with sepsis
Celestino-Soper et al. Validation and utilization of a clinical next-generation sequencing panel for selected cardiovascular disorders
WO2021091288A1 (en) Method and system for predicting hepatocellular carcinoma using machine-learning model
CN116230245A (en) Disease course prediction method, device, electronic equipment and storage medium
Green et al. Investigating associations between blood metabolites, later life brain imaging measures, and genetic risk for Alzheimer’s disease
Chiu et al. Predicting neurodegenerative diseases using a novel blood biomarkers-based model by machine learning
Bhuvaneshwar et al. Bioinformatics in Mental Health: Deriving Knowledge from Molecular and Cellular Data
Dong et al. Precision medicine via the integration of phenotype-genotype information in neonatal genome project

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: 23781390

Country of ref document: EP

Kind code of ref document: A1