WO2023216293A1 - 预测痴呆症或轻度认知障碍的系统和方法 - Google Patents

预测痴呆症或轻度认知障碍的系统和方法 Download PDF

Info

Publication number
WO2023216293A1
WO2023216293A1 PCT/CN2022/093822 CN2022093822W WO2023216293A1 WO 2023216293 A1 WO2023216293 A1 WO 2023216293A1 CN 2022093822 W CN2022093822 W CN 2022093822W WO 2023216293 A1 WO2023216293 A1 WO 2023216293A1
Authority
WO
WIPO (PCT)
Prior art keywords
subject
dementia
cognitive impairment
mild cognitive
probability
Prior art date
Application number
PCT/CN2022/093822
Other languages
English (en)
French (fr)
Inventor
韩勇
冯国双
徐慧玉
张洪宪
张丽
Original Assignee
杭州青果医疗科技有限责任公司
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 杭州青果医疗科技有限责任公司 filed Critical 杭州青果医疗科技有限责任公司
Publication of WO2023216293A1 publication Critical patent/WO2023216293A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • 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
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

  • the present invention relates to a system and method for predicting dementia or mild cognitive impairment.
  • Dementia is a major neurocognitive disorder that affects memory, thinking, language, and behavior, all of which interfere with daily life.
  • the World Alzheimer Report 2010 estimates that the aging of the global population will make the economic impact of dementia greater than that of cancer, heart disease and stroke combined. It is estimated that there will be 75 million people globally by 2030 and 135 million by 2050, adding a huge burden to healthcare and public health systems.
  • treatments can only be used to control symptoms and slow the progression of dementia, but there is no known cure.
  • China's birth population decreases year by year China is facing an increasingly severe situation that may be caused by dementia, that is, there are fewer and fewer working-age adults who can provide continuous care for the millions of dementia patients. Therefore, early diagnosis and therapeutic intervention for dementia are important.
  • Diagnosis of dementia is based on history, examination, assessment of cognitive function, brain imaging, and cerebrospinal fluid (CSF) biomarkers.
  • AD Alzheimer's disease
  • VaD vascular dementia
  • DLB dementia with Lewy bodies
  • biomarkers in cerebrospinal fluid are the most reliable indicators for diagnosing AD, including the three core CSF biomarkers amyloid- ⁇ (A ⁇ ), total tau and phosphorylated tau.
  • CSF markers are highly invasive and only useful in the presence of clinical cognitive impairment. Furthermore, although some new imaging-based technologies are gaining traction, they are not cost-effective and not suitable for early screening of Alzheimer's disease. Ultimately, the ideal AD biomarker should be non-invasive, easy to use, cost-effective, and identify early signs of neurodegenerative processes before cognitive abnormalities appear clinically. Currently, there are no existing non-invasive models that can simultaneously screen for the three main types of dementia and mild cognitive impairment (MCI).
  • MCI mild cognitive impairment
  • the purpose of the present invention is to provide an effective system that can be used to predict dementia, including the three most common types of dementia, AD, VaD and DLB, and can also predict MCI.
  • the present invention relates to the following contents:
  • a system for predicting dementia or mild cognitive impairment comprising:
  • a data acquisition module for obtaining data on the subject's miRNA level, the subject's apolipoprotein E4 genotype, the subject's age, and the subject's gender;
  • the module for calculating the probability of suffering from dementia or mild cognitive impairment is used to calculate the data obtained in the data collection module to calculate the probability (p) of the subject suffering from dementia or mild cognitive impairment.
  • the miRNA is selected from one or more of hsa-miR-6761-3p, hsa-miR-3173-5p, hsa-miR-6716-3p, preferably Specifically, the miRNA includes hsa-miR-6761-3p, hsa-miR-3173-5p and hsa-miR-6716-3p.
  • the apolipoprotein E4 genotype of the subject refers to the typing of the apolipoprotein E4 allele.
  • the subject's miRNA level the subject's apolipoprotein E4 genotype, the subject's age, and A formula used to calculate the probability (p) of developing dementia by fitting data on the gender of the subject through logistic regression.
  • p is the probability of suffering from dementia or mild cognitive impairment
  • APOE type is the apolipoprotein E4 genotype of the subject, and i, a, b, c, d, f, and g are unitless parameters;
  • i is any value selected from -22.77226 ⁇ -15.70663, preferably -19.23944;
  • a is any value selected from 0.1653123 to 0.2425499, preferably 0.2039311;
  • d is any value selected from 0.8932064 to 1.7053113, preferably 1.2992589;
  • f is any value selected from -0.722253 ⁇ -0.073824, preferably -0.398038;
  • g is any numerical value selected from 0.0263939 to 0.5324189, and is preferably 0.2794064.
  • b is any value selected from -1.144378 to -0.309418, preferably -0.726898.
  • the value of c is any value from 1.1429478 to 3.7701044, preferably 2.4565261;
  • the value of c is any value from 0.9740697 to 2.038065, preferably 1.5060673.
  • a grouping module in which default dementia or mild cognitive impairment grouping parameters are pre-stored, and based on the grouping parameters, the calculated probability of the subject suffering from dementia or mild cognitive impairment is calculated (p) Grouping subjects at risk of developing dementia or mild cognitive impairment.
  • the grouping basis pre-stored in the grouping module is:
  • a subject's risk of developing dementia or mild cognitive impairment is low risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 10%;
  • the subject's risk of developing dementia or mild cognitive impairment is medium risk when 10% ⁇ the calculated probability (p) of the subject developing dementia or mild cognitive impairment ⁇ 50%;
  • the risk of the subject suffering from dementia or mild cognitive impairment is medium to high risk
  • a subject's risk of developing dementia or mild cognitive impairment is high risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 90%.
  • a method of predicting dementia or mild cognitive impairment comprising:
  • a data collection step that obtains data on the subject's miRNA level, the subject's apolipoprotein E4 genotype, the subject's age, and the subject's gender;
  • the step of calculating the probability of suffering from dementia or mild cognitive impairment calculates the data obtained in the data collection step to calculate the probability (p) that the subject suffers from dementia or mild cognitive impairment.
  • the miRNA is selected from one or more of hsa-miR-6761-3p, hsa-miR-3173-5p, hsa-miR-6716-3p, preferably Specifically, the miRNA includes hsa-miR-6761-3p, hsa-miR-3173-5p and hsa-miR-6716-3p.
  • the apolipoprotein E4 genotype of the subject refers to the typing of the apolipoprotein E4 allele.
  • the subject's miRNA level In the step of calculating the probability of suffering from dementia or mild cognitive impairment, the subject's miRNA level, the subject's apolipoprotein E4 genotype, the subject's age, and A formula used to calculate the probability (p) of developing dementia by fitting data on the gender of the subject through logistic regression.
  • p is the probability of suffering from dementia or mild cognitive impairment
  • APOE type is the apolipoprotein E4 genotype of the subject, and i, a, b, c, d, f, and g are unitless parameters;
  • i is any value selected from -22.77226 ⁇ -15.70663, preferably -19.23944;
  • a is any value selected from 0.1653123 to 0.2425499, preferably 0.2039311;
  • d is any value selected from 0.8932064 to 1.7053113, preferably 1.2992589;
  • f is any value selected from -0.722253 ⁇ -0.073824, preferably -0.398038;
  • g is any numerical value selected from 0.0263939 to 0.5324189, and is preferably 0.2794064.
  • b is any value selected from -1.144378 to -0.309418, preferably -0.726898.
  • the value of c is any value from 1.1429478 to 3.7701044, preferably 2.4565261;
  • the value of c is any value from 0.9740697 to 2.038065, preferably 1.5060673.
  • a grouping step in which default dementia or mild cognitive impairment grouping parameters are pre-stored, and based on the grouping parameters, the calculated probability of the subject suffering from dementia or mild cognitive impairment is calculated (p) Grouping subjects at risk of developing dementia or mild cognitive impairment.
  • the pre-stored grouping basis in the grouping step is:
  • a subject's risk of developing dementia or mild cognitive impairment is low risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 10%;
  • the subject's risk of developing dementia or mild cognitive impairment is medium risk when 10% ⁇ the calculated probability (p) of the subject developing dementia or mild cognitive impairment ⁇ 50%;
  • the risk of the subject suffering from dementia or mild cognitive impairment is medium to high risk
  • a subject's risk of developing dementia or mild cognitive impairment is high risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 90%.
  • This application establishes a method for predicting whether a subject suffers from dementia or mild cognitive impairment based on the subject's miRNA level, the subject's apolipoprotein E4 genotype, the subject's age, and the subject's gender.
  • mathematical model The parameters used in the system established in this application can be detected simply and non-invasively.
  • the system of this application is a non-invasive system that can be used to predict the three main types of dementia and is suitable for predicting MCI.
  • the model has very good generalizability and can be used to universally screen the population. , to identify as many people as possible who are potentially at risk. Among them, it is of great significance for non-predictive MCI.
  • the system of this application can be used as a tool for diagnosing MCI and other dementias.
  • it can be used as a potential drug target for MCI, thereby preventing or slowing down the progression of MCI.
  • Figure 1 shows the prediction results of the prediction model in the training set, test set and validation set of AD.
  • Figure 2 shows the prediction results of the prediction model in the training set, test set and validation set of VAD, DLB and MCI.
  • Figure 3 shows the grouping results of the predicted probability and actual incidence rate of the prediction model in AD data.
  • variable types In statistics, variable types can be divided into two types: quantitative variables and qualitative variables (also called categorical variables).
  • Quantitative variables are variables used to describe the quantity and number of things, and can be divided into continuous and discrete types.
  • a continuous variable refers to a variable that can take any value within a certain range. Its value is continuous and can have decimal points.
  • blood pressure, blood sugar, and anthropometric height, weight, chest circumference, etc. are continuous variables, and their values can only be obtained by measurement or measurement methods.
  • Discrete variables are variables whose values can only be natural numbers or integer units. For example, the pain score, the number of transferred lesions, the number of retrieved eggs, etc. can only be positive numbers and cannot take decimal points. The values of such variables are generally obtained by counting methods.
  • Variable types are not static and can be converted between various types of variables according to the needs of the research purpose.
  • the amount of hemoglobin (g/L) is originally a numerical variable. If it is divided into two categories according to normal and low hemoglobin, it can be analyzed according to two classification data; if it is divided into two categories: severe anemia, moderate anemia, mild anemia, normal, hemoglobin When the height increase is divided into five levels, the data can be analyzed according to the levels. Sometimes categorical data can also be quantified. For example, if the patient's nausea reaction can be expressed as 0, 1, 2, or 3, it can be analyzed as numerical variable data (quantitative data).
  • Logistics regression is a generalized linear regression analysis model that is commonly used in data mining, automatic disease diagnosis, economic forecasting and other fields. For example, explore the risk factors that cause disease and predict the probability of disease occurrence based on risk factors.
  • gastric cancer conditions two groups of people are selected, one is the gastric cancer group and the other is the non-gastric cancer group.
  • the two groups of people must have different physical signs and lifestyles. Therefore, the dependent variable is whether there is gastric cancer, and the value is "yes" or "no".
  • the independent variables can include many, such as age, gender, eating habits, Helicobacter pylori infection, etc.
  • the independent variables can be either continuous or categorical.
  • the dependent variable of logistic regression can be binary or multi-category.
  • the model used in this article to fit the data through logistic regression is a logistic regression model that penalizes the absolute size of the coefficients of the regression model based on the value of ⁇ . The larger the penalty, the estimate of the weaker factor approaches zero, so only the strongest predictors remain in the model.
  • MicroRNA is an endogenous non-coding RNA of approximately 22 nucleotides that regulates gene expression at the post-transcriptional level. Due to its small molecular weight, it can break away from cell membranes and travel through the blood circulation. Therefore, miRNA can serve as a powerful tool for non-invasive screening of diseases. Increasing evidence suggests that microRNAs play key roles in different pathological processes throughout AD progression. In this application, the inventor attempts to use miRNA and other basic clinical information to establish a non-invasive model for early identification of dementia, thereby contributing to early intervention of dementia-related symptoms.
  • serum miRNAs mainly come from microvesicle-mediated active secretion. They exhibit remarkable long-term stability in the extracellular environment, mainly due to their interactions with Argonaute2-miRNA complexes or lipoprotein complexes or vesicles. Therefore, miRNAs, as key regulators of gene expression, are increasingly recognized as promising new non-invasive, cheap and sensitive diagnostic biomarker candidates.
  • Differently expressed serum miRNAs such as miR-31, -93, -143, -146a, -135a, -193b, and -384, were previously found in AD patients using relatively the same sample size. The applicant of this application has made significant advances in the data sources studied, using large prospective cohort data to build a single model to predict different dementia subtypes and mild cognitive impairment.
  • the data source team of this application used serum miRNA expression data from 1,601 Japanese people and established three different models using AD, VaD and DLB and normal control population data respectively.
  • the AUCs in the AD, VaD and DLB models were respectively 0.874, 0.867 and 0.870, the number of miRNAs discovered by the three prediction models are 78 miRNAs, 86 miRNAs and 110 miRNAs respectively.
  • the authors of the data source team of this application have established three different models for three different types of dementia data, and the models have many independent variables. This aspect generally means less practical significance in terms of statistics and practical experience.
  • different models use different predictor variables, and no common rules for different dementias are found, which also suggests that the model has low application value.
  • AD dementia the most common type of dementia
  • MCI the model of the model of this application may discover different dementia types and mild cognitive impairment. It may be used in the diagnosis and screening of dementia and mild cognitive impairment in the future, and may even be used as a target for drug development. It has potentially great social and economic significance.
  • APOE epsilon4 apolipoprotein E4, APOE4
  • Estrogen is the primary female sex hormone and plays important roles in both the reproductive and non-reproductive systems, including neuroprotection. Estrogen treatment initiated in early menopause has beneficial effects on neuroprotection when neurons are in a healthy state. Patterns of APOE epsilon4 allele status were also found to be associated with estrogen treatment. In addition, subjects with the APOE epsilon4 genotype had a 15-fold increased risk compared with the normal genotype. APOE epsilon4 also contributes to the progression of atherosclerosis and neurodegenerative diseases.
  • this application relates to a system for predicting dementia or mild cognitive impairment, which includes: a data acquisition module for obtaining the subject's miRNA level, the subject's lipid content Data on the protein E4 genotype, the age of the subject, and the gender of the subject; and a module for calculating the probability of suffering from dementia or mild cognitive impairment, which is used to calculate the data obtained in the data acquisition module, The probability (p) of the subject suffering from dementia or mild cognitive impairment is thus calculated.
  • the data collection module there are no restrictions on the data collection module, as long as it can be used to obtain the subject's miRNA level, the subject's apolipoprotein E4 (APOE4) genotype, the subject's age, and the subject's gender.
  • the data there are no restrictions on the data collection module, as long as it can be used to obtain the subject's miRNA level, the subject's apolipoprotein E4 (APOE4) genotype, the subject's age, and the subject's gender.
  • the subject's miRNA level obtained by the data acquisition module refers to the abundance of miRNA in the serum, which can be detected using existing sequencing, PCR, or miRNA chip methods.
  • the data acquisition module obtains the expression level of each miRNA respectively.
  • the subject's miRNA levels can be obtained through existing chip detection.
  • the miRNA is selected from one or more of hsa-miR-6761-3p, hsa-miR-3173-5p, hsa-miR-6716-3p.
  • the miRNA includes hsa-miR-6761-3p, hsa-miR-3173-5p, hsa-miR-6716-3p.
  • the data acquisition module needs to obtain the levels of hsa-miR-6761-3p, hsa-miR-3173-5p, and hsa-miR-6716-3p respectively in the subject.
  • the three main types of dementia are AD, VaD dementia, and DLB dementia.
  • Mild cognitive impairment refers to a disease state between normal aging and dementia. Compared with normal elderly people matched by age and education level, the patient had mild cognitive decline, but his daily abilities were not significantly affected.
  • the core symptom of mild cognitive impairment is a decline in cognitive function. Depending on the cause or location of brain damage, it can affect one or more of memory, executive function, language, use, visuospatial structural skills, etc., leading to corresponding clinical symptoms. .
  • the module for calculating the probability of suffering from dementia or mild cognitive impairment calculates the above-mentioned data obtained in the data collection module, thereby calculating the probability that the subject suffers from dementia or mild cognitive impairment ( p).
  • p the probability that the subject suffers from dementia or mild cognitive impairment
  • the existing database refers to a database composed of subjects that can be obtained.
  • the sample size of the database There is no agreement on the sample size of the database.
  • the larger the sample size of the database the better.
  • it can be 100 subjects, 200 subjects, etc.
  • the number of subjects is 300 subjects, preferably 400 subjects or more, and more preferably 500 subjects or more.
  • this pre-stored formula is calculated by using the data of the subject's miRNA level, the subject's apolipoprotein E4 genotype, the subject's age, and the subject's gender collected by the data acquisition module.
  • a formula for calculating the probability that a subject will develop dementia is calculated by using the data of the subject's miRNA level, the subject's apolipoprotein E4 genotype, the subject's age, and the subject's gender collected by the data acquisition module.
  • the gender of the subject is a two-category variable
  • the apolipoprotein E4 allele status of the subject is a three-category variable.
  • the subject's miRNA level and the subject's age are continuous variables.
  • the specific formula is the following formula 1:
  • p is the probability of suffering from dementia or early cognitive impairment
  • APOE4 genotype is the apolipoprotein E4 allele status of the subject, i, a, b, c, d, f and g are unitless parameters;
  • i is any value selected from -22.77226 ⁇ -15.70663, preferably -19.23944;
  • a is any value selected from 0.1653123 to 0.2425499, preferably 0.2039311;
  • d is any value selected from 0.8932064 to 1.7053113, preferably 1.2992589;
  • f is any value selected from -0.722253 ⁇ -0.073824, preferably -0.398038;
  • g is any numerical value selected from 0.0263939 to 0.5324189, and is preferably 0.2794064.
  • the gender of the subject is a binary variable.
  • the value of b is 0; when the subject is a male, b is selected from -1.144378 to -0.309418. any value, preferably -0.726898.
  • the subject's apolipoprotein E allele status is a three-category variable.
  • the value of c is 0; when the subject is APOE4 pure
  • the value of c is any value from 0.9740697 to 2.038065, preferably 1.5060673.
  • system of the present application may also include a grouping module, in which default dementia or mild cognitive impairment grouping parameters are pre-stored, and based on the grouping parameters, the calculated subjects suffering from The risk of developing dementia or mild cognitive impairment is grouped by the probability (p) of dementia or mild cognitive impairment.
  • a grouping module in which default dementia or mild cognitive impairment grouping parameters are pre-stored, and based on the grouping parameters, the calculated subjects suffering from The risk of developing dementia or mild cognitive impairment is grouped by the probability (p) of dementia or mild cognitive impairment.
  • the grouping basis pre-stored in the grouping module is:
  • a subject's risk of developing dementia or mild cognitive impairment is low risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 10%;
  • the subject's risk of developing dementia or mild cognitive impairment is medium risk when 10% ⁇ the calculated probability (p) of the subject developing dementia or mild cognitive impairment ⁇ 50%;
  • the risk of the subject suffering from dementia or mild cognitive impairment is medium to high risk
  • a subject's risk of developing dementia or mild cognitive impairment is high risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 90%.
  • the present application also relates to a method for predicting dementia or mild cognitive impairment, which includes: a data collection step, which obtains the subject's miRNA level, the subject's apolipoprotein E4 allele status, the subject's Data on the age and sex of the subject; and
  • the step of calculating the probability of suffering from dementia or early cognitive impairment is to calculate the data obtained in the data collection step to calculate the probability (p) of the subject suffering from dementia or early cognitive impairment.
  • the method of predicting dementia or early cognitive impairment of the present application involves specific contents in the data collection steps and the steps of calculating the probability of suffering from dementia or early cognitive impairment, such as using the subject's miRNA level. , the subject's apolipoprotein E4 genotype, the subject's age, and the subject's gender are obtained, and the probability (p) of the subject suffering from dementia or early cognitive impairment can be calculated with reference to the above-mentioned Description of each module of the system involved in this application.
  • the model building data included 1,309 samples from 1,021 AD patients and 288 healthy controls. 91 VaD cases, 169 DLB cases, and 32 MCI cases were further used to evaluate the performance of the AD prediction model in other types of dementia and mild cognitive impairment.
  • the serum miRNA chip data of the above subjects and the corresponding age, gender, and APOE allele genotype were downloaded from GEO (Gene Expression Omnibus), and the storage number is GSE120584.
  • GSE120584 and related articles (Shigemizu D, Akiyama S, Asanomi Y, Boroevich KA, Sharma A, Tsunoda T, Matsukuma K, Ichikawa M, Sudo H, Takizawa S et al: Risk prediction models for dementia constructed by supervised principal component analysis using As described in miRNA expression data. Commun Biol 2019, 2:77.), all 1601 subjects were >60 years old, had APOE4 genotype detected and underwent Mini-Mental State Examination (MMSE) assessment. .
  • MMSE Mini-Mental State Examination
  • Diagnosis of all patients and healthy controls was based on medical history, physiological examination, diagnostic testing, neurological examination, neuropsychological testing, and brain imaging with magnetic resonance imaging (MRI) or computed tomography (CT).
  • Neuropsychological tests included the MMSE, Alzheimer's Disease Evaluation Scale Cognitive Component Japanese version, Wechsler Memory Scale-Revised Logical Memory I and II, Frontal Appraisal Battery, Raven's Colored Progressive Matrices, and Geriatric Depression Scale. If necessary, to diagnose DLB, dopamine transporter imaging and meta-iodobenzylguanidine myocardial scintigraphy are used. Cerebrospinal fluid biomarkers and pathological examination are not used for the diagnosis of dementia.
  • AD and MCI are based on the criteria of the National Alzheimer's Association Task Force (McKhann GM, Knopman DS, Chertkow H, Hyman BT, Jack CR, Jr., Kawas CH, Klunk WE, Koroshetz WJ, Manly JJ, Mayeux R et al: The diagnosis of dementia due to Alzheimer's disease: recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease.
  • VaD and DLB subjects were analyzed according to the NINDS-AIREN International Workshop (Roman GC, Tatemichi TK, Erkinjuntti T, Cummings JL, Masdeu JC, Garcia JH, Amaducci L, Orgogozo JM, Brun A, Hofman A et al: Vascular dementia: diagnostic criteria for research studies.Report of the NINDS-AIREN International Workshop.Neurology 1993,43(2):250-260.) and the fourth report of the DLB Alliance (McKeith IG, Boeve BF, Dickson DW, Halliday G, Taylor JP, Weintraub D, Aarsland D, Galvin J, Attems J, Ballard CG et al: Diagnosis and management of dementia with Lewy bodies: Fourth consensus report of the DLB Consortium. Neurology 2017,89(1):88-100.) diagnosis. All healthy controls had MMSE scores >23.
  • Serum miRNA extraction and expression profiling are described in Shigemizu D, Akiyama S, Asanomi Y, Boroevich KA, Sharma A, Tsunoda T, Matsukuma K, Ichikawa M, Sudo H, Takizawa S et al: Risk prediction models for dementia constructed by supervised principal component analysis using miRNA expression data.Commun Biol 2019,2:77. Briefly, serum samples were isolated and transferred to a ⁇ 80°C refrigerator for storage. Total RNA was then extracted and comprehensive miRNA expression analysis was performed using the Human miRNA Oligo Chip, which is designed to detect 2562 miRNA sequences. Normalization of miRNA expression was then performed.
  • the expression abundance of miRNA probes was sorted from high to low, and the top 1000 miRNA probes were selected.
  • the Limma package in R software was used. According to the standards of P ⁇ 0.05 and fold change>1.3, 22 miRNAs were finally obtained.
  • Table 1 shows that APOE4 allele status and female gender are the main risk factors for mild cognitive impairment and dementia, accounting for 53.4%, 11.1% and 3.5%, respectively. Only 3 of the 11 miRNAs contributed the most, namely hsa-miR-6761-3p, hsa-miR-3173-5p, and hsa-miR-6716-3p. Therefore, the other 8 small contributions were deleted and remodeled, and the modeling results are shown in Figure 1.
  • p is the probability of suffering from dementia or early cognitive impairment
  • i -19.23944, a is 0.2039311, d is 1.2992589, f is -0.398038, and g is 0.2794064;
  • the value of c is 0; when the subject's APOE4 is homozygous, the value of c is 2.4565261; when the subject's APOE4 is heterozygous, the value of c is is 1.5060673.
  • the model established by this application using AD data only includes the levels of three miRNAs (miR-6761-3p, miR-3173-5p and miR-6716-3p) of the subject, and the subject's apolipoprotein E4 (APOE4) gene.
  • Type, age of the subject, and gender of the subject are non-invasive parameters. It performs well not only in predicting AD, but also in predicting VaD dementia, DLB dementia, and MCI, with an AUC of 0.874 (0.834, 0.914) in AD validation data and an AUC of 0.835 (0.798, 0.872) in VaD dementia, 0.856 (0.824, 0.888 in DLB dementia) and 0.808 (0.765, 0.851) in MCI respectively.
  • a subject's risk of developing dementia or mild cognitive impairment is low risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 10%, as shown in Figure 3 when When the calculated p value is 0-0.1, the actual incidence of AD is about 5%, which means that the risk of AD is at a low level;
  • the calculated probability (p) of the subject suffering from dementia or mild cognitive impairment ⁇ 50% the risk of the subject suffering from dementia or mild cognitive impairment is medium risk, as shown in Figure 3 It shows that when the calculated p value is 0.1-0.2, the actual incidence of AD does not exceed 10%. When the calculated p value is 0.2-0.3, the actual incidence of AD is about 20%. When the calculated p value At 0.3-0.5, the actual incidence of AD is less than 30-40%, which means that the subject has a certain risk of AD;
  • a subject's risk of developing dementia or mild cognitive impairment is high risk when the calculated probability (p) of the subject developing dementia or mild cognitive impairment is ⁇ 90%, as shown in Figure 3 when When the calculated p value is 0.9-1, the actual occurrence of AD should exceed 95%, which means that the risk of such subjects is extremely high.
  • Figure 3 shows the group verification based on AD patients.
  • AD has the largest sample size and is therefore the most representative. Therefore, the calculation results based on the above Figure 3 basically confirm the grouping basis of the prediction model of this application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Primary Health Care (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioethics (AREA)
  • Biotechnology (AREA)
  • Evolutionary Biology (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)

Abstract

一种预测痴呆症或轻度认知障碍的系统，其包括：数据采集模块，其用于获取受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据；以及计算罹患痴呆症或轻度认知障碍(MCI)的概率的模块，其用于将数据采集模块中获取的数据进行计算，从而计算出受试者罹患痴呆或MCI的概率(p)。所述系统一方面可以作为诊断MCI和其他痴呆的工具，另一方面可以作为MCI的潜在药物靶点，从而预防或延缓MCI的进展。

Description

预测痴呆症或轻度认知障碍的系统和方法 技术领域
本发明涉及一种预测痴呆症或轻度认知障碍的系统和方法。
背景技术
痴呆症是一种主要的神经认知障碍，会影响记忆、思维、语言和行为，所有这些都会干扰日常生活。《2010年世界阿尔茨海默病报告》估计，全球人口老龄化将使痴呆症的经济影响大于癌症、心脏病和中风的总和。据估计，到2030年，全球将达到7500万，到2050年将达到1.35亿，这增加了医疗保健和公共卫生系统的巨大负担。目前，治疗只能用于控制症状和延缓痴呆症的进展，但没有已知的治愈方法。同时，随着中国出生人口逐年减少，中国正面临着可能由痴呆症带来的日益严峻的形势，即能够为数百万痴呆症患者提供持续护理的适龄工作成年人越来越少。因此，对痴呆症的早期诊断和治疗干预非常重要。
痴呆(主要神经认知障碍)和轻度认知障碍(轻度神经认知障碍/MCI)的诊断基于病史、检查、认知功能评估、脑成像和脑脊液(CSF)生物标志物。阿尔茨海默病(AD)是最常见的痴呆类型，其次是血管性痴呆(VaD)和路易体痴呆(DLB)。虽然目前痴呆症患者无法治愈，但如果能及早发现，是可以治疗的。为了识别这些患者，认知评估是目前最方便、最常用的方法。目前，脑脊液中的生物标志物是诊断AD最可靠的指标，包括淀粉样蛋白-β(Aβ)、总tau和磷酸化tau三个核心CSF生物标志物。然而，脑脊液标记物具有高度侵入性，仅在出现临床认知障碍时才有用。此外，尽管一些新的基于成像的技术越来越受到关注，但它们并不具有成本效益，不适用于阿尔茨海默病的早期筛查。最终，理想的AD生物标志物应该是非侵入性的、易于使用的、具有成本效益的，并在认知异常临床出现之前识别神经退行过程的早期迹象。目前，没有现有的非侵入性模型可以同时筛查痴呆症的主要三种类型和 轻度认知障碍(MCI)。
发明内容
本发明的目的在于提供一种有效的系统，其可以用于预测痴呆症，包括AD、VaD和DLB最常见的三种痴呆类型，还可以预测MCI。
综上，本发明涉及如下内容：
1.一种预测痴呆症或轻度认知障碍的系统，其包括：
数据采集模块，其用于获取受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据；以及
计算罹患痴呆症或轻度认知障碍的概率的模块，其用于将数据采集模块中获取的数据进行计算，从而计算出受试者罹患痴呆症或轻度认知障碍的概率(p)。
2.根据项1所述的系统，其中，所述miRNA选自hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p中的一种或两种以上，优选地，所述miRNA包括hsa-miR-6761-3p、hsa-miR-3173-5p以及hsa-miR-6716-3p。
3.根据项1所述的系统，其中，
所述受试者的载脂蛋白E4基因型是指是载脂蛋白E4等位基因的分型。
4.根据项1所述的系统，其中，
在计算罹患痴呆症或轻度认知障碍的概率的模块中，预先存储有基于现有数据库中受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据通过逻辑回归拟合而成的用于计算罹患痴呆症的概率(p)的公式。
5.根据项4所述的系统，其中，
所述公式为如下公式一：
p＝1/[1+e-(i+a*Age+b*性别+c*APOE分型+d*hsa-miR-6761-3p+f*hsa-miR-3173-5p+g*hsa-miR-6716-3p)](公式一)
其中，p为罹患痴呆症或轻度认知障碍的概率；APOE分型为受试者的载脂蛋白E4基因型，i、a、b、c、d、f、g为无单位参数；
在计算罹患痴呆症的概率的模块中，基于受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别来获取a、b、c、d、f、g的取值并带入公式一进行计算。
6.根据项5所述的系统，其中，
i为选自-22.77226～-15.70663中的任意数值，优选为-19.23944；
a为选自0.1653123～0.2425499中的任意数值，优选为0.2039311；
d为选自0.8932064～1.7053113中的任意数值，优选为1.2992589；
f为选自-0.722253～-0.073824中的任意数值，优选为-0.398038；
g为选自0.0263939～0.5324189中的任意数值，优选为0.2794064。
7.根据项5所述的系统，其中，
当受试者为女性时，b取值为0；
当受试者为男性时，b为选自-1.144378～-0.309418中的任意数值，优选为-0.726898。
8.根据项5所述的系统，其中，
当受试者不表达APOE4基因型时，c取值为0；
当受试者的APOE4基因型为纯合时，c取值为1.1429478～3.7701044中的任意数值，优选为2.4565261；
当受试者的APOE4基因型为杂合时，c取值为0.9740697～2.038065中的任意数值，优选为1.5060673。
9.根据项1所述的系统，其还包括：
分组模块，在所述分组模块中预存有默认的痴呆症或轻度认知障碍分组参数，并且依据该分组参数，对所述计算得到的受试者罹患痴呆症或轻度认知障碍的概率(p)进行分组，从而对受试者罹患痴呆症或轻度认知障碍的风险进行分组。
10.根据项9所述的系统，其中，
在所述分组模块中预存的分组依据为：
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<10％时，受试者罹患痴呆症或轻度认知障碍的风险是低危；
当10％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<50％时，受试者罹患痴呆症或轻度认知障碍的风险是中风险；
当50％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<90％时，受试者罹患痴呆症或轻度认知障碍的风险是中高风险；
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)≥90％时，受试者罹患痴呆症或轻度认知障碍的风险是高风险。
11.一种预测痴呆症或轻度认知障碍的方法，其包括：
数据采集步骤，其获取受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据；以及
计算罹患痴呆症或轻度认知障碍的概率的步骤，其将数据采集步骤中获取的数据进行计算，从而计算出受试者罹患痴呆症或轻度认知障碍的概率(p)。
12.根据项11所述的方法，其中，所述miRNA选自hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p中的一种或两种以上，优选地，所述miRNA包括hsa-miR-6761-3p、hsa-miR-3173-5p以及hsa-miR-6716-3p。
13.根据项11所述的方法，其中，
所述受试者的载脂蛋白E4基因型是指是载脂蛋白E4等位基因的分型。
14.根据项11所述的方法，其中，
在计算罹患痴呆症或轻度认知障碍的概率的步骤中，预先存储有基于现有数据库中受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据通过逻辑回归拟合而成的用于计算罹患痴呆症的概率(p)的公式。
15.根据项14所述的方法，其中，
所述公式为如下公式一：
p＝1/[1+e -(i+a*Age+b*性别+c*APOE分型+d*hsa-miR-6761-3p+f*hsa-miR-3173-5p+g*hsa-miR-6716-3p)](公式一)
其中，p为罹患痴呆症或轻度认知障碍的概率；APOE分型为受试者的载脂蛋白E4基因型，i、a、b、c、d、f、g为无单位参数；
在计算罹患痴呆症的概率的步骤中，基于受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别来获取a、b、c、d、f、g的取值并带入公式一进行计算。
16.根据项15所述的方法，其中，
i为选自-22.77226～-15.70663中的任意数值，优选为-19.23944；
a为选自0.1653123～0.2425499中的任意数值，优选为0.2039311；
d为选自0.8932064～1.7053113中的任意数值，优选为1.2992589；
f为选自-0.722253～-0.073824中的任意数值，优选为-0.398038；
g为选自0.0263939～0.5324189中的任意数值，优选为0.2794064。
17.根据项15所述的方法，其中，
当受试者为女性时，b取值为0；
当受试者为男性时，b为选自-1.144378～-0.309418中的任意数值，优选为-0.726898。
18.根据项15所述的方法，其中，
当受试者不表达APOE4基因型时，c取值为0；
当受试者的APOE4基因型为纯合时，c取值为1.1429478～3.7701044中的任意数值，优选为2.4565261；
当受试者的APOE4基因型为杂合时，c取值为0.9740697～2.038065中的任意数值，优选为1.5060673。
19.根据项11所述的方法，其还包括：
分组步骤，在所述分组步骤中预存有默认的痴呆症或轻度认知障碍分组参数，并且依据该分组参数，对所述计算得到的受试者罹患痴呆症或轻度认知障碍的概率(p)进行分组，从而对受试者罹患痴呆症或轻度认知障碍的风险进行分组。
20.根据项19所述的方法，其中，
在所述分组步骤中预存的分组依据为：
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<10％时，受试者罹患痴呆症或轻度认知障碍的风险是低危；
当10％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<50％时，受试者罹患痴呆症或轻度认知障碍的风险是中风险；
当50％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<90％时，受试者罹患痴呆症或轻度认知障碍的风险是中高风险；
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)≥90％时，受试者罹患痴呆症或轻度认知障碍的风险是高风险。
发明的效果
本申请建立了基于试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别来预测受试者是否罹患痴呆症或轻度认知障碍的数学模型。本申请建立的系统所采用的参数均可简单、无创检测。本申请的系统是一种非侵入性系统，可以用于痴呆症三种主要类型的预测，并 适用于预测MCI，该模型的普适性非常好，能够利用这样的模型对人群进行普遍筛查，以尽可能多的确认存在潜在风险的人群。其中，对非预测MCI具有重要意义，本申请的系统一方面可以作为诊断MCI和其他痴呆的工具，另一方面可以作为MCI的潜在药物靶点，从而预防或减缓MCI的进展。
附图说明
通过阅读下文优选的具体实施方式中的详细描述，本申请各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。说明书附图仅用于示出优选实施方式的目的，而并不认为是对本申请的限制。显而易见地，下面描述的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。而且在整个附图中，用相同的附图标记表示相同的部件。
图1为预测模型在AD的训练集、测试集和验证集中的预测结果。
图2为预测模型在VAD、DLB、MCI的训练集、测试集和验证集中的预测结果。
图3为预测模型在AD数据中的预测概率与实际发生率的分组结果。
具体实施方式
下面将参照附图更详细地描述本发明的具体实施例。虽然附图中显示了本发明的具体实施例，然而应当理解，可以以各种形式实现本发明而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本发明，并且能够将本发明的范围完整的传达给本领域的技术人员。
需要说明的是，在说明书及权利要求当中使用了某些词汇来指称特定组件。本领域技术人员应可以理解，技术人员可能会用不同名词来称呼同一个组件。本说明书及权利要求并不以名词的差异来作为区分组件的方式，而是以组件在功能上的差异来作为区分的准则。如在通篇说明书及权利要求当中所提及的“包含”或“包括”为一开放式用语，故应解释成“包含但不限定于”。说明书后续描述为实施本发明的较佳实施方式，然所述描述乃以说明书的一般原则为目的，并非用以限定本发明的范围。本发明的保护范围当视所附权利要求所界定者为准。
变量类型：在统计学中，变量类型可分为定量变量与定性变量(也称分 类变量)两种。
定量变量是用于描述事物数量和个数的变量，又可分为连续型和离散型。连续型变量是指在一定区间内可以任意取值的变量，其数值是连续不断的，可以有小数点。例如，血压值、血糖值，人体测量的身高、体重、胸围等为连续变量，其数值只能用测量或计量的方法取得。离散型变量是指其取值只能是自然数或整数单位的变量。例如，疼痛分值，病灶转移个数，获卵数等，只能是正数，不能取小数点，这种变量的数值一般用计数方法取得。
变量类型不是一成不变的，根据研究目的的需要，各类变量之间可以进行转化。例如血红蛋白量(g/L)原属数值变量，若按血红蛋白正常与偏低分为两类时，可按二项分类资料分析；若按重度贫血、中度贫血、轻度贫血、正常、血红蛋白增高分为五个等级时，可按等级资料分析。有时亦可将分类资料数量化，如可将病人的恶心反应以0、1、2、3表示，则可按数值变量资料(定量资料)分析。
逻辑回归(logistics regression)，是一种广义的线性回归分析模型，常用于数据挖掘，疾病自动诊断，经济预测等领域。例如，探讨引发疾病的危险因素，并根据危险因素预测疾病发生的概率等。以胃癌病情分析为例，选择两组人群，一组是胃癌组，一组是非胃癌组，两组人群必定具有不同的体征与生活方式等。因此因变量就为是否胃癌，值为“是”或“否”，自变量就可以包括很多了，如年龄、性别、饮食习惯、幽门螺杆菌感染等。自变量既可以是连续的，也可以是分类的。然后通过逻辑回归分析，可以得到自变量的权重，从而可以大致了解到底哪些因素是胃癌的危险因素。同时根据该权值可以根据危险因素预测一个人患癌症的可能性。逻辑回归的因变量可以是二分类的，也可以是多分类的。
在本文中使用的数据通过逻辑回归拟合模型是一个逻辑回归模型，它基于λ的值对回归模型的系数的绝对大小进行惩罚。惩罚越大，对较弱因素的估计就趋近于零，因此只有最强的预测变量保留在模型中。
MicroRNA(miRNA)是内源性约22个核苷酸的非编码RNA，可在转录后水平调节基因表达。由于其分子量小，它可以脱离细胞膜并在血液循环中穿行。因此，miRNA可以作为一种强大的工具用于疾病的非侵入性筛查。越来越多的证据表明，microRNA在整个AD进展的不同病理过程中发挥着关键作用。在本申请中发明人尝试利用miRNA以及其他基础临床信息建立 一个非侵入性模型，用于早期识别痴呆症，从而有助于早期干预痴呆症相关症状。
在本文中，血清miRNA主要来自微泡介导的主动分泌。它们在细胞外环境中长期表现出显著的稳定性，主要是由于它们与Argonaute2-miRNA复合物或脂蛋白复合物或囊泡的相互作用。因此，作为基因表达的关键调节剂的miRNA，越来越被认为是有前途的新型非侵入性、廉价和敏感的诊断生物标志物候选者。以前在AD患者中发现了使用相对相同的样本量不同表达的血清miRNA，例如miR-31、-93、-143、-146a、-135a、-193b和-384。本申请的申请人研究的数据源取得了重大进展，利用大样本的前瞻性队列数据建立了单一的模型来预测不同的痴呆亚型和轻度认知障碍。
本申请的数据源团队使用来自1,601名日本人的血清miRNA表达数据，分别利用AD、VaD和DLB以及正常对照人群数据分别建立了三个不同的模型，AD、VaD和DLB模型中的AUC分别为0.874、0.867和0.870，三个预测模型发现的miRNA个数分别是78个miRNA、86个miRNA和110个miRNA。本申请的数据源团队的作者分别三种不同痴呆数据建立了三个不同的模型，且模型的自变量非常多，这一方面在统计学和实际经验上一般都意味着更小的实际意义，另一方面不同模型使用不同的预测变量，没有发现不同痴呆的共同规律，也提示了模型较低的应用价值。本申请用痴呆中最常见的类型AD痴呆建模，找到了三个关键的miRNA，并对该模型进行了内部和外部数据验证，提示模型的更好的稳定性。另外，建立的模型不只在AD痴呆中效果好，在不同的痴呆类型及MCI中均有良好的预测效果，提示本申请的模型发现的三种miRNA可能发现了不同痴呆类型和轻度认知障碍的共同规律，因此具有更为重要的意义，可能未来一方面用于诊断和筛查痴呆和轻度认知障碍，另一方面甚至有可能作为药物研发的靶点。具有潜在重大的社会意义和经济意义。
神经退行性疾病的最大风险因素是高龄。随着年龄的增长，APOE epsilon4(载脂蛋白E4，APOE4)基因型和女性性别是AD的两个众所周知的危险因素。据推测，绝经以及卵巢雌激素缺乏是导致65岁以上女性AD发病率升高的原因。雌激素是主要的女性性激素，在生殖系统和非生殖系统中都发挥着重要作用，包括神经保护作用。在神经元处于健康状态时，在绝经早期开始的雌激素治疗对神经保护具有有益作用。APOE epsilon4等位基因 状态的模式也被发现与雌激素治疗有关。此外，与正常基因型相比，APOE epsilon4基因型受试者的风险增加至15倍。APOE epsilon4也有助于动脉粥样硬化和神经退行性疾病的进展。
为了解决现有技术存在的问题，本申请涉及一种预测痴呆症或轻度认知障碍的系统，其包括：数据采集模块，其用于获取受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据；以及计算罹患痴呆症或轻度认知障碍的概率的模块，其用于将数据采集模块中获取的数据进行计算，从而计算出受试者罹患痴呆症或轻度认知障碍的概率(p)。
在本文中，对于数据采集模块没有任何限定，只要可以用于获取受试者的miRNA水平、受试者的载脂蛋白E4(APOE4)基因型、受试者的年龄、以及受试者的性别的数据。
其中，具体来说，数据采集模块获取的受试者的miRNA水平是指血清中miRNA的丰度，可以采用现有的测序、PCR或者miRNA芯片等方法进行检测。
当miRNA包括多个时，数据采集模块分别获得各个miRNA的表达水平。受试者的miRNA水平可以通过现有的芯片检测获得。
在一个具体的实施方式中，所述miRNA选自hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p中的一种或两种以上。
在一个具体的实施方式中，所述miRNA包括hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p。此时，数据采集模块需要分别获取受试者的hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p这3个miRNA的水平。
在本申请中初步筛查了大量的miRNA，但是经过申请人的深入研究显示当选用hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p这三种miRNA中的一种或两种或三种时，可以获得最为显著的效果，并且可以使本申请的方法和系统能够用于预测痴呆症的主要三种类型和轻度认知障碍(MCI)。现有技术中虽然已经有研究利用不同的miRNA来进行预测，但是本领域中还没有建立一种普适性的系统和方法能够用来初步筛查老年痴呆，本申请从miRNA芯片中的2562个miRNA中经过大量的实验最终选取了3个miRNA，并构建了本申请的方法和系统。痴呆症的主要三种类型是指AD、 VaD痴呆、DLB痴呆。轻度认知障碍是指介于正常衰老和痴呆之间的一种疾病状态。与年龄和教育程度匹配的正常老人相比，患者存在轻度认知功能减退，但日常能力没有受到明显影响。轻度认知障碍的核心症状是认知功能的减退，根据病因或大脑损害部位的不同，可以累及记忆、执行功能、语言、运用、视空间结构技能等一项或以上，导致相应的临床症状。现有技术中一直缺乏针对老年痴呆主要三种类型和轻度认知障碍进行广泛普遍筛查的方法和系统，而本申请的方法和系统则填补了这样的空白。
在本申请中，计算罹患痴呆症或轻度认知障碍的概率的模块对数据采集模块中的获取的上述数据进行计算，从而计算出受试者罹患痴呆症或轻度认知障碍的概率(p)。首先，应当理解，在该模块中预先存储有基于现有数据库中受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据通过逻辑回归拟合而成的用于计算罹患痴呆症的概率(p)的公式。利用这样预存好的公式，可以针对任意受试者进行计算。
在本发明中，现有数据库是指能够获取的受试者组成的数据库，对于数据库的样本量没有任何约定，当然数据库的样本量越大越好，例如可以是利用100个受试者，200个受试者，300个受试者，优选为400个受试者以上，更优选为500个受试者以上。
在计算时，这个预存的公式是利用所述数据采集模块采集的受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据来计算受试者罹患痴呆症的概率的公式。
其中，受试者的性别为二分类变量，受试者的载脂蛋白E4等位基因状态为三分类变量。受试者的miRNA水平、受试者的年龄为连续变量。
进一步，本申请的发明人构建了用于预测受试者罹患痴呆症的概率(p)的具体的公式，具体的公式为如下公式一：
p＝1/[1+e -(i+a*Age+b*性别+c*APOE分型+d*hsa-miR-6761-3p+f*hsa-miR-3173-5p+g*hsa-miR-6716-3p)](公式一)；
进一步地，在所述公式一中，p为罹患痴呆症或早期认知障碍的概率；APOE4基因型为受试者的载脂蛋白E4等位基因状态，i、a、b、c、d、f、g为无单位参数；
在计算罹患痴呆症的概率的模块中，基于受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别来获取a、b、 c、d、f、g的取值并带入公式一进行计算。
在一个具体的实施方式中，
i为选自-22.77226～-15.70663中的任意数值，优选为-19.23944；
a为选自0.1653123～0.2425499中的任意数值，优选为0.2039311；
d为选自0.8932064～1.7053113中的任意数值，优选为1.2992589；
f为选自-0.722253～-0.073824中的任意数值，优选为-0.398038；
g为选自0.0263939～0.5324189中的任意数值，优选为0.2794064。
在一个具体的实施方式中，受试者的性别为二分类变量，当受试者为女性时，b取值为0；当受试者为男性时，b为选自-1.144378～-0.309418中的任意数值，优选为-0.726898。
在一个具体的实施方式中，受试者的载脂蛋白E等位基因状态为三分类变量，当受试者的不表达APOE4基因型时，c取值为0；当受试者为APOE4纯合型时，c取值为1.1429478～3.7701044中的任意数值，优选为2.4565261；当受试者为APOE4杂合型时，c取值为0.9740697～2.038065中的任意数值，优选为1.5060673。
进一步地，本申请的系统还可以包括分组模块，在所述分组模块中预存有默认的痴呆症或轻度认知障碍分组参数，并且依据该分组参数，对所述计算得到的受试者罹患痴呆症或轻度认知障碍的概率(p)进行分组，从而对受试者罹患痴呆症或轻度认知障碍的风险进行分组。
在所述分组模块中预存的分组依据为：
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<10％时，受试者罹患痴呆症或轻度认知障碍的风险是低危；
当10％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<50％时，受试者罹患痴呆症或轻度认知障碍的风险是中风险；
当50％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<90％时，受试者罹患痴呆症或轻度认知障碍的风险是中高风险；
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)≥90％时，受试者罹患痴呆症或轻度认知障碍的风险是高风险。
本申请还涉及一种预测痴呆症或轻度认知障碍的方法，其包括：数据采集步骤，其获取受试者的miRNA水平、受试者的载脂蛋白E4等位基因状态、受试者的年龄、以及受试者的性别的数据；以及
计算罹患痴呆症或早期认知障碍的概率的步骤，其将数据采集步骤中获取的数据进行计算，从而计算出受试者罹患痴呆症或早期认知障碍的概率(p)。
如上所述，本申请的预测痴呆症或早期认知障碍的方法所涉及的数据采集步骤和计算罹患痴呆症或早期认知障碍的概率的步骤中的具体内容，如用受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据的获取，计算受试者罹患痴呆症或早期认知障碍的概率(p)可以参照上述针对本申请涉及的系统各模块的描述。
实施例
用于构建模型的数据
模型构建数据包括1,021名AD患者和288名健康对照的1,309个样本。91例VaD病例、169例DLB病例和32例MCI病例进一步用于评估AD预测模型在其他类型痴呆和轻度认知障碍中的表现。
上述受试者的血清miRNA芯片数据及对应的年龄、性别、APOE等位基因基因型从GEO(Gene Expression Omnibus)下载，存储号为GSE120584。
根据GSE120584及相关文章(Shigemizu D,Akiyama S,Asanomi Y,Boroevich KA,Sharma A,Tsunoda T,Matsukuma K,Ichikawa M,Sudo H,Takizawa S et al:Risk prediction models for dementia constructed by supervised principal component analysis using miRNA expression data.Commun Biol 2019,2:77.)的描述，所有1601名受试者均>60岁，检测到APOE4基因型并进行了简易智力状况检查法(Mini-Mental State Exam，MMSE)评估。
所有患者和健康对照者的诊断均基于病史、生理检查、诊断测试、神经系统检查、神经心理学测试以及磁共振成像(MRI)或计算机断层扫描(CT)的脑成像。神经心理学测试包括MMSE、阿尔茨海默病评估量表认知成分日本版、韦氏记忆量表修订版的逻辑记忆I和II、正面评估组、瑞文彩色渐进矩阵和老年抑郁量表。如有必要，为了诊断DLB，使用多巴胺转运蛋白成像和间碘苄基胍心肌闪烁显像。脑脊液生物标志物和病理检查未用于痴呆的诊断。
本研究中的AD病例为可能的AD。AD和MCI的诊断依据是美国国家老年痴呆症协会工作组的标准(McKhann GM,Knopman DS,Chertkow H,Hyman BT,Jack CR,Jr.,Kawas CH,Klunk WE,Koroshetz WJ,Manly JJ,Mayeux R et al:The diagnosis of dementia due to Alzheimer's disease:recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease.Alzheimers Dement 2011,7(3):263-269；Albert MS,DeKosky ST,Dickson D,Dubois B,Feldman HH,Fox NC,Gamst A,Holtzman DM,Jagust WJ,Petersen RC et al:The diagnosis of mild cognitive impairment due to Alzheimer's disease:recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease.Alzheimers Dement 2011,7(3):270-279.)。VaD和DLB受试者分别根据NINDS-AIREN国际研讨会(Roman GC,Tatemichi TK,Erkinjuntti T,Cummings JL,Masdeu JC,Garcia JH,Amaducci L,Orgogozo JM,Brun A,Hofman A et al:Vascular dementia:diagnostic criteria for research studies.Report of the NINDS-AIREN International Workshop.Neurology 1993,43(2):250-260.)和DLB联盟的第四次报告(McKeith IG,Boeve BF,Dickson DW,Halliday G,Taylor JP,Weintraub D,Aarsland D,Galvin J,Attems J,Ballard CG et al:Diagnosis and management of dementia with Lewy bodies:Fourth consensus report of the DLB Consortium.Neurology 2017,89(1):88-100.)进行诊断。所有健康对照的MMSE评分均>23。
本研究中的所有数据均来自公开可用的资源。
检测miRNA表达丰度
血清miRNA提取和表达谱分析描述于Shigemizu D,Akiyama S,Asanomi Y,Boroevich KA,Sharma A,Tsunoda T,Matsukuma K,Ichikawa M,Sudo H,Takizawa S et al:Risk prediction models for dementia constructed by supervised principal component analysis using miRNA expression data.Commun Biol 2019,2:77。简而言之，分离血清样品并转移到-80℃冰箱中储存。随后提取总RNA，然后使用人类miRNA Oligo芯片进行全面的miRNA表达分析， 该芯片旨在检测2562个miRNA序列。然后进行miRNA表达的标准化。
筛选不同表达的miRNA
首先，将miRNA探针表达丰度从高到低排序，选出前1000个miRNA探针。为了进一步识别差异表达的miRNA，使用了R软件中的Limma程序包。根据P<0.05和倍数变化>1.3的标准，最终获得22个miRNA。
系统模型的构建
使用lasso逻辑回归结合5折交叉验证在训练集数据中建模，在验证集数据中进行验证，通过缩放负对数似然(-Log L(β))以确定最优模型，验证集中缩放的-Log L(β)值越小，模型拟合越好。最终11个miRNA，受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别作为自变量被纳入最终模型，见表1。表1为模型构建过程中各变量的估计参数值、P值、及贡献。
表1 预测模型的参数估计结果
Figure PCTCN2022093822-appb-000001
表1显示APOE4等位基因状态和女性性别是轻度认知障碍和痴呆的主要危险因素，分别占53.4％、11.1％和3.5％。11个miRNA中只有3个贡献最大，即hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p。因此删除了其他8个贡献小的重新建模，建模结果图1所示。
基于上述方法，在本实施例中确认了如下公式一作为预测模型：
p＝1/[1+e -(i+a*Age+b*性别+c*APOE分型+d*hsa-miR-6761-3p+f*hsa-miR-3173-5p+g*hsa-miR-6716-3p)](公式一)
其中，p为罹患痴呆症或早期认知障碍的概率；
i为-19.23944，a为0.2039311，d为1.2992589，f为-0.398038，g为0.2794064；
当受试者为女性时，b取值为0；当受试者为男性时，b为-0.726898；
当受试者不表达APOE4基因型时，c取值为0；当受试者的APOE4为纯合型时，c取值为2.4565261；当受试者的APOE4为杂合型时，c取值为1.5060673。
利用上述方法构建的模型在其他痴呆类型和MCI的预测效果如图2所示。
本申请使用AD数据建立的模型仅包含受试者三个miRNA(miR-6761-3p、miR-3173-5p和miR-6716-3p)的水平、受试者的载脂蛋白E4(APOE4)基因型、受试者的年龄、以及受试者的性别这些无创参数。它不仅在预测AD方面表现良好，而且在预测VaD痴呆、DLB痴呆和MCI方面表现良好，AD验证数据中的AUC为0.874(0.834,0.914)，VaD痴呆中的AUC为0.835(0.798,0.872)，0.856(0.824,在DLB痴呆中为0.888)，在MCI中分别为0.808(0.765,0.851)。
使用构建的模型在AD的验证集中的分组结果如图3所示，其中AD表示实际罹患AD的患者，NC表示阴性对照。由图3的结果可以获得以下的预测痴呆症或轻度认知障碍的模型的分组依据：
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<10％时，受试者罹患痴呆症或轻度认知障碍的风险是低危，如图3中显示当计算的p值在0-0.1时，实际罹患AD的情况在5％左右，这表示罹患AD的风险处于较低的水平；
当10％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<50％时，受试者罹患痴呆症或轻度认知障碍的风险是中风险，如图3中显示当计算的p值在0.1-0.2时，实际罹患AD的情况均不超过10％，当计算的p值在0.2-0.3时，实际罹患AD的情况在20％左右，当计算的p值在0.3-0.5时，实际罹患AD的情况不到在30-40％左右，这表示受试者存在一定的罹患AD的风险；
当50％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<90％时，受试者罹患痴呆症或轻度认知障碍的风险是中高风险，如图3中显示当计算的p值在0.5-0.9时，实际罹患AD的情况均高于50％，甚至有的情况下会高达87％，这表示罹患的风险已经相当高；
当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)≥90％时，受试者罹患痴呆症或轻度认知障碍的风险是高风险，如图3中显示当计算的p值在0.9-1时，实际罹患AD的情况应超过了95％，这表示这类受试者的风险极高。
图3显示的是基于AD患者进行分组验证，在实际情况中由于AD样本量最大，因此最为有代表性，因此基于上述图3的计算结果基本确认了本申请的预测模型的分组依据。
尽管以上结合附图对本发明的实施方案进行了描述，但本发明并不局限于上述的具体实施方案和应用领域，上述的具体实施方案仅仅是示意性的、指导性的，而不是限制性的。本领域的普通技术人员在本说明书的启示下和在不脱离本发明权利要求所保护的范围的情况下，还可以做出很多种的形式，这些均属于本发明保护之列。

Claims (20)

  1. 一种预测痴呆症或轻度认知障碍的系统，其包括：
    数据采集模块，其用于获取受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据；以及
    计算罹患痴呆症或轻度认知障碍的概率的模块，其用于将数据采集模块中获取的数据进行计算，从而计算出受试者罹患痴呆症或轻度认知障碍的概率(p)。
  2. 根据权利要求1所述的系统，其中，所述miRNA选自hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p中的一种或两种以上，优选地，所述miRNA包括hsa-miR-6761-3p、hsa-miR-3173-5p以及hsa-miR-6716-3p。
  3. 根据权利要求1所述的系统，其中，
    所述受试者的载脂蛋白E4基因型是指是载脂蛋白E4等位基因的分型。
  4. 根据权利要求1所述的系统，其中，
    在计算罹患痴呆症或轻度认知障碍的概率的模块中，预先存储有基于现有数据库中受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据通过逻辑回归拟合而成的用于计算罹患痴呆症的概率(p)的公式。
  5. 根据权利要求4所述的系统，其中，
    所述公式为如下公式一：
    p＝1/[1+e -(i+a*Age+b*性别+c*APOE分型+d*hsa-miR-6761-3p+f*hsa-miR-3173-5p+g*hsa-miR-6716-3p)](公式一)
    其中，p为罹患痴呆症或轻度认知障碍的概率；APOE分型为受试者的载脂蛋白E4基因型，i、a、b、c、d、f、g为无单位参数；
    在计算罹患痴呆症的概率的模块中，基于受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别来获取a、b、c、d、f、g的取值并带入公式一进行计算。
  6. 根据权利要求5所述的系统，其中，
    i为选自-22.77226～-15.70663中的任意数值，优选为-19.23944；
    a为选自0.1653123～0.2425499中的任意数值，优选为0.2039311；
    d为选自0.8932064～1.7053113中的任意数值，优选为1.2992589；
    f为选自-0.722253～-0.073824中的任意数值，优选为-0.398038；
    g为选自0.0263939～0.5324189中的任意数值，优选为0.2794064。
  7. 根据权利要求5所述的系统，其中，
    当受试者为女性时，b取值为0；
    当受试者为男性时，b为选自-1.144378～-0.309418中的任意数值，优选为-0.726898。
  8. 根据权利要求5所述的系统，其中，
    当受试者不表达APOE4基因型时，c取值为0；
    当受试者的APOE4基因型为纯合时，c取值为1.1429478～3.7701044中的任意数值，优选为2.4565261；
    当受试者的APOE4基因型为杂合时，c取值为0.9740697～2.038065中的任意数值，优选为1.5060673。
  9. 根据权利要求1所述的系统，其还包括：
    分组模块，在所述分组模块中预存有默认的痴呆症或轻度认知障碍分组参数，并且依据该分组参数，对所述计算得到的受试者罹患痴呆症或轻度认知障碍的概率(p)进行分组，从而对受试者罹患痴呆症或轻度认知障碍的风险进行分组。
  10. 根据权利要求9所述的系统，其中，
    在所述分组模块中预存的分组依据为：
    当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<10％时，受试者罹患痴呆症或轻度认知障碍的风险是低危；
    当10％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<50％时，受试者罹患痴呆症或轻度认知障碍的风险是中风险；
    当50％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<90％时，受试者罹患痴呆症或轻度认知障碍的风险是中高风险；
    当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)≥90％时，受试者罹患痴呆症或轻度认知障碍的风险是高风险。
  11. 一种预测痴呆症或轻度认知障碍的方法，其包括：
    数据采集步骤，其获取受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据；以及
    计算罹患痴呆症或轻度认知障碍的概率的步骤，其将数据采集步骤中获取的数据进行计算，从而计算出受试者罹患痴呆症或轻度认知障碍的概率(p)。
  12. 根据权利要求11所述的方法，其中，所述miRNA选自hsa-miR-6761-3p、hsa-miR-3173-5p、hsa-miR-6716-3p中的一种或两种以上，优选地，所述miRNA包括hsa-miR-6761-3p、hsa-miR-3173-5p以及hsa-miR-6716-3p。
  13. 根据权利要求11所述的方法，其中，
    所述受试者的载脂蛋白E4基因型是指是载脂蛋白E4等位基因的分型。
  14. 根据权利要求11所述的方法，其中，
    在计算罹患痴呆症或轻度认知障碍的概率的步骤中，预先存储有基于现有数据库中受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别的数据通过逻辑回归拟合而成的用于计算罹患痴呆症的概率(p)的公式。
  15. 根据权利要求14所述的方法，其中，
    所述公式为如下公式一：
    p＝1/[1+e -(i+a*Age+b*性别+c*APOE分型+d*hsa-miR-6761-3p+f*hsa-miR-3173-5p+g*hsa-miR-6716-3p)](公式一)
    其中，p为罹患痴呆症或轻度认知障碍的概率；APOE分型为受试者的载脂蛋白E4基因型，i、a、b、c、d、f、g为无单位参数；
    在计算罹患痴呆症的概率的步骤中，基于受试者的miRNA水平、受试者的载脂蛋白E4基因型、受试者的年龄、以及受试者的性别来获取a、b、c、d、f、g的取值并带入公式一进行计算。
  16. 根据权利要求15所述的方法，其中，
    i为选自-22.77226～-15.70663中的任意数值，优选为-19.23944；
    a为选自0.1653123～0.2425499中的任意数值，优选为0.2039311；
    d为选自0.8932064～1.7053113中的任意数值，优选为1.2992589；
    f为选自-0.722253～-0.073824中的任意数值，优选为-0.398038；
    g为选自0.0263939～0.5324189中的任意数值，优选为0.2794064。
  17. 根据权利要求15所述的方法，其中，
    当受试者为女性时，b取值为0；
    当受试者为男性时，b为选自-1.144378～-0.309418中的任意数值，优选为-0.726898。
  18. 根据权利要求15所述的方法，其中，
    当受试者不表达APOE4基因型时，c取值为0；
    当受试者的APOE4基因型为纯合时，c取值为1.1429478～3.7701044中的任意数值，优选为2.4565261；
    当受试者的APOE4基因型为杂合时，c取值为0.9740697～2.038065中的任意数值，优选为1.5060673。
  19. 根据权利要求11所述的方法，其还包括：
    分组步骤，在所述分组步骤中预存有默认的痴呆症或轻度认知障碍分组参数，并且依据该分组参数，对所述计算得到的受试者罹患痴呆症或轻度认知障碍的概率(p)进行分组，从而对受试者罹患痴呆症或轻度认知障碍的风险进行分组。
  20. 根据权利要求19所述的方法，其中，
    在所述分组步骤中预存的分组依据为：
    当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<10％时，受试者罹患痴呆症或轻度认知障碍的风险是低危；
    当10％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<50％时，受试者罹患痴呆症或轻度认知障碍的风险是中风险；
    当50％≤计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)<90％时，受试者罹患痴呆症或轻度认知障碍的风险是中高风险；
    当计算出的受试者罹患痴呆症或轻度认知障碍的概率(p)≥90％时，受试者罹患痴呆症或轻度认知障碍的风险是高风险。
PCT/CN2022/093822 2022-05-11 2022-05-19 预测痴呆症或轻度认知障碍的系统和方法 WO2023216293A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210510090.3 2022-05-11
CN202210510090.3A CN114822850A (zh) 2022-05-11 2022-05-11 预测痴呆症或轻度认知障碍的系统

Publications (1)

Publication Number Publication Date
WO2023216293A1 true WO2023216293A1 (zh) 2023-11-16

Family

ID=82512557

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/093822 WO2023216293A1 (zh) 2022-05-11 2022-05-19 预测痴呆症或轻度认知障碍的系统和方法

Country Status (2)

Country Link
CN (1) CN114822850A (zh)
WO (1) WO2023216293A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117373668A (zh) * 2023-10-25 2024-01-09 六合熙诚(北京)信息科技有限公司 一种老年期痴呆发病风险预测模型建立方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015179909A1 (en) * 2014-05-26 2015-12-03 The University Of Melbourne Mirna biomarkers of alzheimer's disease
CN108597615A (zh) * 2018-04-19 2018-09-28 南京脑科医院 一种轻度认知障碍患者痴呆转化的筛选参考方法
CN110268269A (zh) * 2016-12-18 2019-09-20 赛隆特拉有限公司 使用apoe4基序介导的基因以用于诊断和治疗阿尔茨海默氏病
CN113383090A (zh) * 2018-12-04 2021-09-10 拉筹伯大学 诊断疾病状态的方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015179909A1 (en) * 2014-05-26 2015-12-03 The University Of Melbourne Mirna biomarkers of alzheimer's disease
CN110268269A (zh) * 2016-12-18 2019-09-20 赛隆特拉有限公司 使用apoe4基序介导的基因以用于诊断和治疗阿尔茨海默氏病
CN108597615A (zh) * 2018-04-19 2018-09-28 南京脑科医院 一种轻度认知障碍患者痴呆转化的筛选参考方法
CN113383090A (zh) * 2018-12-04 2021-09-10 拉筹伯大学 诊断疾病状态的方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CHENG L; DOECKE J D; SHARPLES R A; VILLEMAGNE V L; FOWLER C J; REMBACH A; MARTINS R N; ROWE C C; MACAULAY S L; MASTERS C L; HILL A: "Prognostic serum miRNA biomarkers associated with Alzheimer’s disease shows concordance with neuropsychological and neuroimaging assessment", MOLECULAR PSYCHIATRY, NATURE PUBLISHING GROUP UK, LONDON, vol. 20, no. 10, 28 October 2014 (2014-10-28), London, pages 1188 - 1196, XP036972601, ISSN: 1359-4184, DOI: 10.1038/mp.2014.127 *
廖峥娈 等 (LIAO, ZHENGLUAN ET AL.): "基于血清小分子核糖核酸的阿尔茨海默病诊断模型构建与验证 (Construction and Validation of Diagnostic Models for Alzheimer′s Disease based on Serum MicroRNAs)", 中华精神科杂志 (CHINESE JOURNAL OF PSYCHIATRY), vol. 54, no. 5, 31 October 2021 (2021-10-31), XP009550270 *

Also Published As

Publication number Publication date
CN114822850A (zh) 2022-07-29

Similar Documents

Publication Publication Date Title
Ning et al. Classifying Alzheimer's disease with brain imaging and genetic data using a neural network framework
Morra et al. Automated 3D mapping of hippocampal atrophy and its clinical correlates in 400 subjects with Alzheimer's disease, mild cognitive impairment, and elderly controls
Mielke et al. Fornix integrity and hippocampal volume predict memory decline and progression to Alzheimer’s disease
Mori et al. Accelerated hippocampal atrophy in Alzheimer's disease with apolipoprotein E ε4 allele
Illán-Gala et al. Challenges associated with biomarker-based classification systems for Alzheimer's disease
Andrawis et al. Effects of ApoE4 and maternal history of dementia on hippocampal atrophy
Escudero et al. Early detection and characterization of Alzheimer's disease in clinical scenarios using Bioprofile concepts and K-means
Negash et al. Cognitive and functional resilience despite molecular evidence of Alzheimer’s disease pathology
US11412977B2 (en) Systems and methods for quantitatively characterizing Alzheimer&#39;s disease risk events based on multimodal biomarker data
Chen et al. Staging Alzheimer’s disease risk by sequencing brain function and structure, cerebrospinal fluid, and cognition biomarkers
Nao et al. Adverse effects of the apolipoprotein E ε4 allele on episodic memory, task switching and gray matter volume in healthy young adults
Gifford et al. Associations between verbal learning slope and neuroimaging markers across the cognitive aging spectrum
Holbrook et al. Anterolateral entorhinal cortex thickness as a new biomarker for early detection of Alzheimer's disease
Ge et al. A kernel machine method for detecting effects of interaction between multidimensional variable sets: An imaging genetics application
Zhan et al. Boosting brain connectome classification accuracy in Alzheimer's disease using higher-order singular value decomposition
Morrison et al. Regional brain atrophy and cognitive decline depend on definition of subjective cognitive decline
Martínez-Torteya et al. Improved diagnostic multimodal biomarkers for Alzheimer’s disease and mild cognitive impairment
Shook et al. Racing against the clock: recognizing, differentiating, diagnosing, and referring the amyotrophic lateral sclerosis patient
Qiu et al. Predicting diagnosis 4 years prior to Alzheimer’s disease incident
WO2023216293A1 (zh) 预测痴呆症或轻度认知障碍的系统和方法
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
Senthilkumar et al. Primitive detection of Alzheimer’s disease using neuroimaging: A progression model for Alzheimer’s disease: Their applications, benefits, and drawbacks
Kim et al. Examining the diagnostic value of the mnemonic discrimination task for classification of cognitive status and amyloid-beta burden
Li et al. Applications and challenges of machine learning methods in Alzheimer's disease multi-source data analysis
De Francesco et al. Norms for automatic estimation of hippocampal atrophy and a step forward for applicability to the Italian population

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: 22941242

Country of ref document: EP

Kind code of ref document: A1