Biomarkers, models, and uses thereof for predicting risk of postoperative cognitive dysfunction in elderly patients

Abstract

The application discloses a biomarker, a model and application thereof for predicting the risk of postoperative cognitive dysfunction of an elderly patient, and belongs to the technical field of medical diagnosis. The application identifies proteins related to postoperative cognitive dysfunction through Olink proteomics, optimizes a biomarker group composed of GPC5 protein, NEP protein, SPOCK1 protein, LXN protein, IL12 protein, CLM-1 protein, NTRK3 protein and CD200R1 protein, and constructs a POCD risk prediction model according to the biomarker group. Through verification, the POCD risk prediction model has high clinical applicability, and provides a reliable tool for preoperative POCD high-risk population screening of elderly patients.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical diagnosis, and particularly relates to a biomarker for predicting the risk of postoperative cognitive dysfunction of an elderly patient, a model and application thereof. BACKGROUND

[0002] Postoperative cognitive dysfunction (POCD) refers to a complication in which a patient has disorders in memory, executive function and orientation after anesthesia surgery, and is accompanied by a decline in social activity. So far, the exact cause and pathogenesis of POCD have not been clear, and there is a lack of a unified diagnostic standard. The occurrence of POCD will prolong the hospitalization time of patients, reduce the quality of life of patients, increase the postoperative mortality, and cause a serious burden to individuals and society.

[0003] With the aggravation of social aging, the number of surgeries of elderly patients is increasing, and POCD is increasingly concerned. The degenerative changes of the central nervous system of the elderly have their special features, including a decrease in brain mass and neuron quantity, a decrease in blood vessel elasticity causing a decrease in blood flow speed, and an expansion of extracellular space, which will cause a decrease in cognitive function of the elderly.

[0004] Normal aging will cause a change in functional connectivity of the default mode (DMN) main network and some other networks, and affect the reaction time, dual-task performance and executive ability of the elderly. Clinical studies have shown that anesthetic drugs can mainly interfere with high-order brain networks related to cognitive function of patients, thereby causing a change in cognitive function. In summary, the networks related to high-level neuropsychological function (such as DMN, executive control network and salience network) are more sensitive to anesthesia; the DMN of elderly patients is damaged, which will affect cognitive function. When a variety of perioperative factors such as anesthesia and surgery act, cognitive function is further deteriorated to show POCD.

[0005] The incidence of POCD varies greatly among different studies. One international multicenter study of POCD (ISPOCD) showed that the incidence of POCD was 25.8% at 1 week and 9.9% at 3 months after surgery in 1218 patients over 60 years old who underwent non-cardiac surgery. In patients undergoing cardiac surgery, the incidence of POCD was 30%-80% within a few weeks and 10%-60% 3-6 months after surgery. The main reasons for these differences are the use of different behavioral test methods, types of surgery, test time limits, patient age, and other factors in different studies. Although there is no uniform method for neuropsychological testing of POCD, the international academic community generally uses the ISPOCD method and Newman's modified neuropsychological test battery (NP tests) as a template. Domestic research generally uses the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment Scale (MoCA) to detect POCD.

[0006] It is worth noting that current neuropsychological methods mainly focus on the testing of cognitive functions such as learning and memory, and rarely involve changes in patients' emotions such as anxiety and depression. In addition, it is still unclear whether the widespread perioperative pain, reduced sleep quality, drug use, anxiety state, and changes in environmental factors have an impact on the test. Another study reported that the timing of neuropsychological testing (test time window) is crucial for the diagnosis of POCD. Furthermore, how to consider patient loss and exclude patient learning effects are methodological issues worth considering. Neuropsychological testing in clinical practice cannot meet the needs of early diagnosis of POCD. Therefore, identifying potential POCD patients and making early diagnosis has important clinical significance.

[0007] After investigating the incidence of POCD, the current focus of research has shifted to the selection of POCD warning indicators. Most of the current POCD biomarkers are based on their pathophysiological processes and include the following categories: (1) central inflammatory response-related biomarkers such as IL-1, IL-6, TNF-α, etc.; (2) amyloid beta (β-amyloid, Aβ) and tau protein; (3) nerve damage-related markers such as S-100β, neuron-specific enolase, and glial fibrillary acidic protein; (4) neurotransmitters and trophic factors such as acetylcholine and brain-derived nerve growth factor; (5) APOE ε4 gene. However, there is currently a lack of specific and sensitive biological targets for convenient detection in clinical practice.

[0008] Exploring specific POCD molecular markers, developing convenient and efficient and non-invasive prediction and early diagnosis of new technology has become a clinical problem to be solved. However, due to various factors, the relevant researches all have their own limitations and no high-quality and large-sample clinical research. At present, there is still a lack of non-invasive and efficient early prediction and early diagnosis or screening technology for postoperative cognitive dysfunction suitable for Chinese residents developed independently by China. SUMMARY

[0009] Based on the above background, the present application provides a group of neuroprotein-related biomarkers that can be used for the prediction and early screening of the risk of POCD in elderly patients. Further, the present application constructs a POCD risk prediction model according to the biomarkers. Through verification, the POCD risk prediction model has high clinical applicability, can provide a reliable tool for preoperative POCD high-risk population screening in elderly patients, and is expected to become a standardized tool for POCD risk prediction and early diagnosis.

[0010] The present application includes the following technical solutions:

[0011] In a first aspect, the present application provides a group of biomarkers and / or reagents for detecting the biomarkers for use in the preparation and / or screening of products for predicting the risk of postoperative cognitive dysfunction (POCD) in elderly patients, characterized in that the biomarkers are a combination of proteins or encoding genes represented by 1)-8) as follows:

[0012] 1) GPC5 protein or its encoding gene;

[0013] 2) NEP protein or its encoding gene;

[0014] 3) SPOCK1 protein or its encoding gene;

[0015] 4) LXN protein or its encoding gene;

[0016] 5) IL12 protein or its encoding gene;

[0017] 6) CLM-1 protein or its encoding gene;

[0018] 7) NTRK3 protein or its encoding gene;

[0019] 8) CD200R1 protein or its encoding gene.

[0020] The products include but are not limited to models, reagents, kits, chips, test papers, membrane strips or detection platforms.

[0021] The reagent for detecting the biomarker includes any reagent required for detecting the expression level of the protein or the gene encoding the protein shown in 1) to 8) by RT-PCR method, RT-qPCR method, biochip detection method, Southern blotting method, in situ hybridization method, flow cytometry, enzyme-linked immunosorbent assay, immunoblotting method, immunohistochemical method, immunofluorescence method or fluorescent dye method.

[0022] In some embodiments of the present application, the reagent for detecting the biomarker is selected from at least one of the following:

[0023] I) an antibody specifically against the protein shown in 1) to 8);

[0024] II) a primer specifically amplifying the gene encoding the protein shown in 1) to 8);

[0025] III) a probe specifically recognizing the gene or the transcript thereof encoding the protein shown in 1) to 8).

[0026] Preferably, the reagent for detecting the biomarker includes any reagent required for detecting the expression level of the protein shown in 1) to 8) by flow cytometry, enzyme-linked immunosorbent assay, immunoblotting method or immunohistochemical method.

[0027] In some embodiments of the present application, the reagent for detecting the biomarker is selected from an antibody specifically against the protein shown in 1) to 8), which is capable of being coupled with one of acridinium ester, HRP, ALP or FITC.

[0028] Most preferably, the reagent for detecting the biomarker includes any reagent required for detecting the expression level of the protein shown in 1) to 8) by enzyme-linked immunosorbent assay.

[0029] Unless otherwise specified, the prediction in the present application includes predicting the risk of the patient developing cognitive dysfunction before, during and after surgery, the surgery being a conventional surgery for treating diseases known to those skilled in the art, including but not limited to orthopedic surgery, and the anesthetic state during the surgery being selected from general anesthesia or spinal anesthesia.

[0030] Unless otherwise specified, the elderly patient in the present application is selected from a male and / or female with an age of ≥ 60 years, and in specific embodiments of the present application, the elderly patient is selected from a male and / or female with an age of ≥ 65 years.

[0031] In a second aspect, the present application provides a prediction model for predicting the risk of an elderly patient developing postoperative cognitive dysfunction, the model comprising an information acquisition module and a prediction module.

[0032] The information acquisition module is configured to acquire biomarker expression level information of a subject, the biomarker being selected from a combination of GPC5 protein, NEP protein, SPOCK1 protein, LXN protein, IL12 protein, CLM-1 protein, NTRK3 protein and CD200R1 protein.

[0033] The prediction module is configured to predict the risk of cognitive dysfunction of the subject according to the biomarker expression level information.

[0034] Specifically, the model predicts the probability of cognitive dysfunction of the subject after surgery by detecting the expression level of the biomarker protein.

[0035] A person skilled in the art can obtain the expression level information of the above-mentioned biomarker protein in a large number of samples, and model according to a conventional machine learning method to obtain the prediction model of the present application, which includes but is not limited to random forest, kNN or SVM.

[0036] In a third aspect, the present application provides a use of the prediction model of the second aspect of the present application in the preparation of a product for predicting the risk of postoperative cognitive dysfunction of an elderly patient, the use comprising the following steps:

[0037] S1: quantitatively detecting the expression level of biomarkers in a batch of samples, the biomarkers being selected from a combination of GPC5 protein, NEP protein, SPOCK1 protein, LXN protein, IL12 protein, CLM-1 protein, NTRK3 protein and CD200R1 protein;

[0038] S2: data analysis and machine learning algorithm on the biomarker expression level data;

[0039] S3: quantitatively detecting the expression level of biomarkers in a sample of a subject, and predicting the risk of cognitive dysfunction of the subject based on the probability score in the machine learning algorithm.

[0040] The machine learning algorithm of the present application is a conventional technical means in the art, including inputting training set sample data, training the model, evaluating the model, inputting test set sample data for blind test, and evaluating the blind test result of the test set.

[0041] The technical solution provided by the present application has the following technical advantages:

[0042] (1) The present application successfully constructs a biomarker library covering a plurality of POCD significantly related differential proteins, which provides basic data support for in-depth understanding of the pathological mechanism, risk prediction and early diagnosis of POCD, and enhances the ability of research physicians in the field of basic research.

[0043] (2) Based on the screened differential proteins and their functional interaction network, the POCD risk prediction model is successfully constructed, and the prediction performance is evaluated by Logistic regression analysis, and good results are obtained. The verification results show that the model obtained by the application has high clinical applicability, which can provide a reliable tool for preoperative POCD high-risk population screening of elderly patients, and further improve the practical ability of research physicians in model development and clinical application.

[0044] (3) The POCD risk prediction model provided by the application has the advantages of non-invasiveness, convenience and strong operability, and precise risk assessment before operation can be realized through peripheral blood detection, which provides personalized scheme for targeted intervention and perioperative management of elderly patients. With multi-center clinical verification and further optimization of the model, it is expected to become a standardized tool for POCD risk prediction and early diagnosis, and open up a new path for the clinical decision-making and research achievement transformation of physicians in the field of disease prediction and prevention. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The research design and workflow chart involved in the application.

[0046] Figure 2 Differentially expressed proteins in non-POCD and POCD patients before operation (left) and after operation (right).

[0047] Figure 3 ROC curve analysis of the prediction model constructed based on the 4 proteins in the Olink data.

[0048] Figure 4 ROC curve analysis of the prediction model constructed by 8 proteins in the discovery cohort.

[0049] Figure 5 The plasma levels of 8 proteins were determined using ELISA in the validation cohort, *p<0.05, ns: not statistically significant.

[0050] Figure 6 ROC curve analysis of the prediction model constructed by 8 proteins in the validation cohort. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the application will be described below in a clear and complete manner. Obviously, the described embodiments are only some of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the application.

[0052] The terms and abbreviations involved in the application are explained as follows:

[0053] GPC5: Glypican Proteoglycan 5 is a cell surface heparan sulfate proteoglycan, which belongs to the glypican family, and is an important synaptogenesis factor for regulating synaptic maturation and refinement during development.

[0054] SPOCK1: SPARC (Osteonectin), Cwcv And Kazal Like Domains Proteoglycan 1, also known as testisin-1, is currently widely studied in the development of cancer. SPOCK is mainly located in the central nervous system, mainly in the post-synaptic part of hippocampal pyramidal cells, and is involved in the regulation of midbrain dopamine neurons.

[0055] CLM-1: MRF35-like molecule-1, also known as CD300 molecule-like family member, is an inhibitory receptor that regulates immune response.

[0056] EZR: Ezrin is one of the specific proteins that connect the cytoskeleton and the cell membrane, which helps intracellular endocytosis, cell exocytosis and transmembrane signal transmission pathways.

[0057] IL12: Interleukin 12 is a pro-inflammatory cytokine that promotes Th1 cell differentiation.

[0058] LXN: Latexin is a metal carboxypeptidase inhibitor, expressed in a subset of glutamatergic projection neurons in the mammalian lateral neocortex, and LXN plays an important role in the development of specific networks in the brain.

[0059] NEP: Neprilysin is a type II membrane metal endopeptidase, and NEP is currently found to be one of the most critical metalloproteinases involved in the degradation and clearance of beta amyloid protein, which is an important pathological mechanism for the progression of Alzheimer's disease.

[0060] NTRK3: n Neurotrophic tyrosine receptor kinase 3 is a membrane-bound receptor that phosphorylates NTRK3 protein and MAPK signaling pathway by binding with neurotrophins. Studies have found that NTRK3 gene mutations are associated with mood anxiety disorders.

[0061] The CD200-CD200Ra pairing system inhibits the activation of central nervous system microglia under physiological conditions. CD200 is a transmembrane protein also known as OX-2 protein, which is widely distributed on the surface of various cells such as glial cells, neurons, and epithelial cells, and is an important immunomodulatory protein. CD200R1 is a subtype of CD200 receptor.

[0062] Olink: A newly developed technology that plays an important role in precision proteomics research and provides new options for multi-omics research. Olink technology can detect low concentrations of biomarkers in small volumes, and can efficiently and accurately detect multiple important biomarkers. Olink has been applied to cancer, cardiovascular disease, aging, multiple sclerosis, psoriasis and hidradenitis suppurativa, primary biliary cholangitis, Alzheimer's disease, diabetes, diabetic nephropathy, and clonal hematopoiesis of serum samples. In this study, Olink target 96 neuro exploratory panel (Olink Proteomics AB, Uppsala, Sweden) was used to analyze the readouts expressed as standardized protein expression values. Details of the analytical validation information, such as the limit of detection, intra- and inter-assay precision data, can be found at the link www.olink.com.

[0063] The research scheme and research results involved in the present application are as follows:

[0064] 1. Inclusion of research subjects

[0065] This study is a prospective multicenter predictive study. A total of 285 patients over 65 years old undergoing orthopedic surgery were included. The inclusion criteria include a minimum of 9 years of compulsory education, research compliance, no history of serious acute infection or malignant disease, and a baseline MMSE score higher than or equal to 27 points.

[0066] The research scheme was approved by the Ethics Committee of Zhongshan Hospital, Fudan University (B2022-476R). All analyses comply with the local and international ethical regulations for human subject research, written informed consent is provided, and the research complies with the principles of the "Helsinki Declaration".

[0067] The sample size was calculated using G*Power software. 88 patients (non-POCD: POCD = 58:30) were included in the discovery cohort, and 40 patients (non-POCD: POCD = 20:20) were included in the validation cohort.

[0068] 2. Research methods

[0069] In this study, the cognitive function of patients was assessed using the Mini-Mental State Examination (MMSE). Nurses conducted MMSE examinations on patients preoperatively (baseline), 1 day postoperatively (day 1), and 3 days postoperatively (day 3). Patients with a baseline MMSE examination score of 27 points or higher were included in this study. Patients with a postoperative MMSE score of less than 26 points were diagnosed with POCD. Patient plasma samples were collected, aliquoted, and frozen at -80°C for research. The design and process of this study are shown in Figure 1 .

[0070] Prediction model construction: Based on Olink proteomics data, logistic regression model was constructed using stat R package. ROC curve was drawn using pROC R package, and area under curve (AUC) was calculated.

[0071] 3. Data analysis

[0072] The baseline characteristics and biochemical indicators of POCD patients were expressed as the mean ± standard deviation of normally distributed measurement data and the median (25% and 75%) of non-normally distributed measurement data. Count data was described using proportions. Normally distributed measurement data was analyzed using independent sample t-test, and non-normally distributed measurement data was analyzed using non-parametric test. Chi-square test or Fisher's exact test was used for count data analysis. Statistical analysis was performed using IBM SPSS Statistics 25 and R software (version 4.3.1). It was statistically significant when p-value < 0.05.

[0073] 4. Research results

[0074] A total of 285 patients were included in this study, and preoperative MMSE examination was used to evaluate the cognitive function of patients (28.53 ± 1.02). On the first day after surgery, 50 patients had MMSE scores below 27, and 16.78% of patients had postoperative cognitive dysfunction. To explore the potential risks of these patients, they were divided into non-POCD and POCD groups according to MMSE scores. In this study, there were more female patients (male: female = 118:167, p < 0.03), but the incidence of POCD was lower in female patients (male: female = 28 / 118:22 / 167, p < 0.04). The baseline and intraoperative characteristics of patients in the two groups, including age, height, weight, BMI, morbidity, fasting blood glucose level, resting blood pressure, and anesthesia status, are shown in Table 1.

[0075] Table 1 Clinical characteristics of patients

[0076]

[0077]

[0078] A total of 285 patients were included in this study, and preoperative MMSE examination was used to evaluate the cognitive function of patients (28.53 ± 1.02). On the first day after surgery, 50 patients had MMSE scores below 27, and 16.78% of patients had postoperative cognitive dysfunction. To explore the potential risks of these patients, they were divided into non-POCD and POCD groups according to MMSE scores. In this study, there were more female patients (male: female = 118:167, p < 0.03), but the incidence of POCD was lower in female patients (male: female = 28 / 118:22 / 167, p < 0.04). The baseline and intraoperative characteristics of patients in the two groups, including age, height, weight, BMI, morbidity, fasting blood glucose level, resting blood pressure, and anesthesia status, are shown in Table 1.

[0079] Table 2 Clinical characteristics of patients in the discovery cohort

[0080]

[0081]

[0082] In the discovery cohort, patient blood samples were tested using Olink neuroproteomics panel to detect potential biomarkers in POCD patients, as shown in Figure 2 Compared with the non-POCD group, the POCD patients had lower plasma levels of GPC5, LXN, NEP, Sparc, Cwcv, and SPOCK1 in the preoperative baseline state. Importantly, the GPC5 protein was further reduced in POCD and non-POCD patients after surgery, and the LXN and NEP proteins were reduced in non-POCD patients upon surgical challenge, while SPOCK1 was unresponsive to surgery. The POCD patients had lower postoperative GPC5 protein levels and higher postoperative EZR and IL12 protein levels than the non-POCD patients, with both groups of patients having decreased IL12 and increased EZR after surgery.

[0083] Binary logistic regression was used to predict potential biomarkers for POCD patients, and four significantly reduced proteins in POCD patients were selected as biomarkers, namely the combination of GPC5, LXN, NEP, and SPOCK1. Using this biomarker as a variable, a prediction model was built, and the receiver operating characteristic (ROC) curve was plotted, with an area under the curve (AUC) value of 0.74 (95% CI: 0.62-0.86), as shown in Figure 3 .

[0084] Further, other proteins with differential expression trends (p < 0.10) were included, and the AUC value of each protein was calculated. Eight proteins with the highest AUC values were selected for prediction, namely the combination of GPC5, NEP, SPOCK1, LXN, IL12, CLM-1, NTRK3, and CD200R1. Using these eight proteins as variables, a prediction model was built, and the receiver operating characteristic (ROC) curve was plotted, with an AUC value under the ROC curve of 0.84 (95% CI: 0.74-0.93), as shown in Figure 4 .

[0085] There were 20 non-POCD patients and 20 POCD patients in the validation cohort. Patient baseline and intraoperative characteristics included age, gender, height, weight, BMI, morbidity, fasting blood glucose level, resting blood pressure, and anesthesia status, as shown in Table 3.

[0086] Table 3 Clinical characteristics of patients in the validation cohort

[0087]

[0088]

[0089] To verify the circulating changes of POCD patients and their neurobiomarkers, the plasma samples of the verification cohort were detected by ELISA method. Specifically, the ELISA kits of CD200R1 (ab272196, Abeam), CLM-1 (CSB-EL004921HU, Cusabio), GPC5 (ab313967, Abeam), IL12 (KE00240, Proteintech), LXN (ab313989, Abeam), NEP (RDRNEP Hu, Reddot Biotech), NTRK3 (KA5476, Abnova), and Spock1 (KA5960, Abnova) were used, and the specific operation method can be found in the kit instruction.

[0090] Consistent with the Olink results, as shown in Table 6, the plasma levels of GPC5, NEP and SPOCK1 in the POCD group were significantly lower than those in the non-POCD group, and the changes of NTRK3, CD200R1, CLM-1, IL12 and LXN proteins in the POCD plasma were similar to the Olink detection results, but without statistical significance. Figure 5 Further verification showed that the AUC value of the ROC curve of the 8 proteins was 0.92 (95% CI: 0.84-0.92), as shown in Table 7. Figure 6

[0091] The present application found that 16.78% of the elderly orthopedic surgery patients had cognitive dysfunction, therefore, it is particularly important to obtain biomarkers with high specificity for early prediction of the risk of POCD in elderly patients. The present application identified a series of neural cell biomarkers through Olink proteomics, and obtained 8 proteins combined as biomarkers for predicting POCD through further optimization, and successfully constructed a POCD risk prediction model, and obtained good results through Logistic regression analysis to evaluate its prediction performance, which provides a new idea for future surgical risk assessment.

[0092] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.​

Claims

1. Use of a reagent for detecting a biomarker in the preparation of a product for predicting the risk of postoperative cognitive dysfunction in elderly patients, characterized in that: The postoperative condition refers to orthopedic surgery, and the biomarkers are the protein combinations shown in 1)-8): 1) GPC5 protein; 2) NEP protein; 3) SPOCK1 protein; 4) LXN protein; 5) IL12 protein; 6) CLM-1 protein; 7) NTRK3 protein; 8) CD200R1 protein.

2. The use according to claim 1, characterized in that The products include models, reagents, kits, chips, test strips, membrane strips or detection platforms.

3. The use according to claim 1, characterized in that The reagents for detecting biomarkers include any reagents required for detecting the expression levels of the proteins shown in 1) to 8) by flow cytometry, enzyme-linked immunosorbent assay, immunoblotting, immunohistochemistry, immunofluorescence or fluorescent dye method.

4. The use according to claim 3, characterized in that The reagent for detecting biomarkers is selected from antibodies specifically against the proteins shown in 1)-8).

5. The use according to claim 1, characterized in that The elderly patients are selected from males and / or females aged ≥60 years.

6. A prediction model for predicting the risk of postoperative cognitive dysfunction in elderly patients after orthopedic surgery, the model comprising an information acquisition module and a prediction module; The information acquisition module is configured to execute the step of acquiring biomarker expression level information of the subject, wherein the biomarker is selected from a combination of GPC5 protein, NEP protein, SPOCK1 protein, LXN protein, IL12 protein, CLM-1 protein, NTRK3 protein, and CD200R1 protein; The prediction module is used to execute the step of predicting the risk of cognitive dysfunction in the subject based on the biomarker expression level information.

7. The prediction model according to claim 6, characterized in that The prediction model is constructed by the following method: obtaining the biomarker protein expression level information in a large number of samples and modeling according to conventional machine learning methods, and the prediction model includes random forest, kNN or SVM.

8. Use of the prediction model according to claim 6 or 7 in the preparation of a product for predicting the risk of postoperative cognitive dysfunction in elderly patients, wherein the postoperative period is orthopedic surgery, the use comprising the following steps: S1: Quantitatively detecting the expression level of biomarkers in batch samples, wherein the biomarkers are selected from a combination of GPC5 protein, NEP protein, SPOCK1 protein, LXN protein, IL12 protein, CLM-1 protein, NTRK3 protein and CD200R1 protein; S2: Perform data analysis and machine learning algorithms on biomarker expression level data; S3: Quantitatively detect the expression levels of biomarkers in the subject's sample, and predict the risk of cognitive dysfunction in the subject based on the probability score in the machine learning algorithm.

Images