Classifier for early recognition of occurrence risk of high-risk pregnant woman placenta implantable disease and training system thereof

Abstract

The invention discloses a classifier for early recognition of occurrence risks of high-risk pregnant woman placenta implantable diseases and a training system thereof. The system performs normalization and discretization based on pregnant woman plasma free DNA whole genome promoter region coverage rate analysis, identifies the optimal target combination of 23 genes, including ABHD1, ALG1L2, EYS and the like, and has application potential in preparation of diagnostic kits. By applying a machine learning algorithm, the constructed classifier shows high sensitivity and specificity in the aspect of predicting PAS occurrence, the area (AUC) under the operation characteristic curve of a receiver exceeds 0.85, and early risk assessment of a high-risk pregnant woman is effectively realized. The classifier provides a non-invasive prediction tool for clinic, and has remarkable clinical application value and medical significance.

Description

Technical Field

[0001] The present invention belongs to the field of model prediction, and in particular to a classifier for early identification of the risk of placenta accreta disease in high-risk pregnant women and a training system thereof. Background Art

[0002] Placenta accreta spectrum (PAS) is one of the leading causes of severe obstetric emergencies, but its prenatal diagnosis is limited by late detection and frequent missed diagnoses, posing a significant challenge for primary care hospitals. Studies have shown that two-thirds of PAS cases are still missed in clinical practice. Failure to identify PAS prenatally is a risk factor for intrapartum and postpartum hemorrhage, blood transfusions, emergency interventional procedures, and hysterectomy. Therefore, early and accurate prediction of PAS can help high-risk pregnant women choose their fertility preferences, initiate high-risk referrals, and achieve multidisciplinary consultations, thereby reducing risks to both the mother and the perinatal baby.

[0003] Plasma cell-free DNA (cfDNA) is released from apoptotic cells. cfDNA contains nucleosome footprints, which reflect gene expression information from the tissue of origin of the cfDNA. During pregnancy, approximately 10% of circulating cfDNA originates from the placenta. Therefore, early pregnancy plasma cfDNA contains gene expression information from both the placenta and decidua. Genome-wide promoter nucleosome coverage profiles of cfDNA collected during early and mid-pregnancy reflect expression patterns across tissues of origin and have a high predictive value for placental diseases, particularly PAS. Non-invasive prenatal testing (NIPT) is a common prenatal screening procedure in clinical practice. NIPT is performed by hospitals worldwide using low-coverage whole-genome sequencing technologies on various sequencing platforms, such as Illumina, Life Sciences, and BGI. In recent years, cfDNA promoter nucleosome coverage profiles extracted using NIPT have demonstrated significant value in the early prediction of pregnancy complications, such as fetal growth restriction, macrosomia, and preeclampsia, in addition to screening for fetal chromosomal abnormalities. However, effective early prediction models for placental accreta are still lacking. Summary of the Invention

[0004] In response to actual needs and the shortcomings of existing technologies, the present invention provides a classifier and its training system for early identification of the risk of PAS in high-risk pregnant women, in order to solve the problem that there is currently no method to accurately predict the occurrence of PAS in the early and middle stages of pregnancy.

[0005] Technical solution:

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In the first aspect, the present invention provides a classifier for early identification of the risk of PAS in high-risk pregnant women based on plasma cfDNA promoter coverage, wherein the target gene combination includes ABHD1, ALG1L2, EYS, FAM157C, KDSR, KRT5, LANCL2, LINC00390, LINC00964, LOC105371998, LOC107987394, LOC644090, LYZL2, MIR184, MIR4802, MYT1L, NGDN, NSD2, PACRG.AS3, SAP30L.AS1, SLC16A12.AS1, TADA3, and TMEM147.AS1.

[0008] The present invention uses NIPT data to discover the whole-genome promoter coverage characteristic spectrum of cfDNA in the plasma of pregnant women with PAS in the early and middle stages. Through machine learning strategies (see the second aspect), the optimal gene combination and the optimal cutoff value of each gene are obtained, and the optimal classifier is trained. In an independent validation data set, the area under the curve (AUC) of the receiver operating characteristic curve (ROC) of the predicted effect reaches above 0.85, showing good potential as a screening method for pregnant women at high risk of PAS.

[0009] Methods for assessing the risk of placenta accreta in high-risk women include:

[0010] Data collection and preprocessing: Low-coverage whole-genome sequencing data from high-risk pregnant women undergoing NIPT were collected and necessary preprocessing was performed to ensure data quality.

[0011] Promoter region identification and coverage extraction: NIPT data were aligned with the human reference genome hg19 using bwa-mem, SAMtools, and BEDtools software and sequence alignment algorithms. The promoter regions pTSS within 1000 bp above and below the transcription start sites (TSS) of 23 genes, including ABHD1, ALG1L2, EYS, FAM157C, KDSR, KRT5, LANCL2, LINC00390, LINC00964, LOC105371998, LOC107987394, LOC644090, LYZL2, MIR184, MIR4802, MYT1L, NGDN, NSD2, PACRG.AS3, SAP30L.AS1, SLC16A12.AS1, TADA3, and TMEM147.AS1, were determined, and the raw read coverage of the pTSS regions of the 23 genes was obtained.

[0012] Characteristic factor normalization processing: The original read coverage of the pTSS region of 23 genes was normalized by the TPM-like method to obtain the TPM-like normalized promoter coverage (TPM-like Normalized pTSSCoverage, NPC-TPM) of 23 genes.

[0013]

[0014] Among them, NPC-TPM i represents the TPM-normalized promoter coverage of the pTSS region of the i-th gene, q i represents the raw read coverage of the pTSS region, l i represents the transcript length (all 2000), ∑ j (q j / l j ) represents the sum of read coverage of each pTSS region after normalization for transcript length.

[0015] Characteristic factor discretization processing: The NPC-TPM values ​​of the 23 genes were compared with the optimal cutoff value of each gene (obtained in the second aspect). When the characteristic factor NPC-TPM was greater than the corresponding optimal cutoff value, it was set to 1; otherwise, it was set to 0.

[0016] Risk assessment: The discretized NPC-TPM values ​​of the pregnant woman's 23 genes were input into the classifier to calculate the risk of PAS.

[0017] This method is suitable for singleton pregnant women with at least one of the following high-risk factors for PAS: ① History of previous uterine surgery, such as cesarean section, myomectomy, and hysterectomy; ② History of previous uterine cavity manipulation, such as hysteroscopic surgery and uterine curettage; ③ In vitro fertilization-embryo transfer (IVF-ET).

[0018] This process, based on pTSS coverage extraction from NIPT data, provides a non-invasive assessment method. This suggests that the specific combination and expression pattern of the 23 genes mentioned above have great potential in the development of diagnostic kits. In the development of diagnostic kits, the detection of these gene expression using precise molecular diagnostic techniques can be designed into highly sensitive and specific assays, enabling accurate early prediction of pregnancies at high risk for PAS. This is expected to become a routine clinical test, serving a wider patient population.

[0019] In a second aspect, the present invention provides a classifier training system for the risk of PAS in high-risk pregnant women based on early and mid-pregnancy plasma cfDNA promoter sequencing;

[0020] The classifier training method for PAS risk in high-risk pregnant women based on early and mid-pregnancy plasma cfDNA promoter sequencing includes:

[0021] Dataset division module: Extract medical data of PAS high-risk pregnant women who underwent NIPT on different sequencing platforms in advance, match PAS pregnant women with those without PAS according to age, gestational age at NIPT, fetal sex, and distribution of high-risk factors, randomly divide samples from the main platform into a training dataset and an internal validation dataset, and use samples from other platforms as independent external validation datasets.

[0022] Influencing factor extraction module: The pre-collected NIPT data of PAS high-risk pregnant women are used to annotate the cfDNA promoter nucleosome coverage spectrum and extract features.

[0023] NIPT involves low-depth, high-throughput sequencing of cell-free DNA from maternal peripheral blood. Using precise sequence alignment algorithms, bwa-mem, SAMtools, and BEDtools software are used to align NIPT data with the human reference genome hg19. PCR duplicates are removed, and the promoter region (pTSS) is identified within 1000 bp above and below the transcription start site (TSS). Raw read coverage of the pTSS region is then calculated.

[0024] The TPM-like Normalized pTSS Coverage (NPC-TPM) of each gene was obtained by TPM-like calculation to reduce the impact of sequencing depth on data extraction and analysis.

[0025]

[0026] Among them, NPC-TPM i represents the TPM-normalized promoter coverage of the pTSS region of the i-th gene, q i represents the raw read coverage of the pTSS region, l i represents the transcript length (all 2000), ∑ j (q j / l j ) represents the sum of the read coverage of the pTSS regions of all genes in a sample after normalization of transcript length.

[0027] The NPC-TPM values ​​corresponding to all genes were input into the system as influencing factors.

[0028] Feature Screening Module: Using the propensity score, high-risk pregnant women with and without PAS were matched 1:1 in the training dataset and included in the differential analysis. Each influencing factor was analyzed using DESeq2, limma-voom, and rank sum tests. Factors with p-values ​​< 0.05 for all three differential analysis methods or p-values ​​< 0.05 for at least two methods were selected as feature factors.

[0029] Feature factor discrete module: To enhance the universality and clinical applicability of the classifier on different sequencing platforms, a discretization strategy is adopted:

[0030] The optimal cutoff value for each eigenfactor was set to the NPC-TPM value that maximized the sum of sensitivity and specificity in the training dataset. When the eigenfactor NPC-TPM was greater than the corresponding optimal cutoff value, it was set to 1; otherwise, it was set to 0.

[0031] Model acquisition module: The screened feature factors are input into machine learning feature selection processes such as recursive feature elimination (RFE), and a PAS disease prediction classifier is gradually constructed using multiple machine learning methods such as support vector machine (SVM)-linear kernel (Linear kernel) and SVM-Gaussian kernel function (Radial Basis Function, RBF).

[0032] The PAS pregnant women were set to 1 and the non-PAS high-risk pregnant women were set to 0 and input into the system for classifier training. To improve the sensitivity of the classifier, the parameter value of class_weight was set to {0:0.1,1:0.3}.

[0033] The disease risk assessment results of the target to be predicted were obtained, and k-fold cross validation (k=10) was applied to increase the robustness of the assessment.

[0034] Extract the best feature factor combination and output the optimal classifier and its evaluation results.

[0035] Beneficial effects of the present invention

[0036] PAS is a general term for a group of conditions in which the placenta abnormally adheres to or invades the myometrium. In patients with PAS, the placenta fails to detach normally after fetal delivery, resulting in profuse bleeding from the detachment site. This condition is a leading cause of emergency hysterectomy, multiple organ failure, disseminated intravascular coagulation, shock, and other obstetric emergencies, including perinatal death. In recent years, with the increase in cesarean sections and advances in intrauterine manipulation and assisted reproductive technology, the incidence of PAS has steadily increased. According to statistics, it occurs in 1 in every 300 to 400 pregnancies. Although PAS cases diagnosed prenatally using current clinical methods often have more severe myometrial invasion, the emergency cesarean section rate, blood loss, and transfusion requirements are lower than in undiagnosed PAS cases. Therefore, prenatal identification and perinatal management of PAS are crucial.

[0037] This study developed a classifier based on 23 gene NPCs, using non-invasive blood tests during early and mid-term pregnancy. This classifier can effectively predict the risk of PAS in high-risk pregnant women and has important clinical application value. This innovative method is expected to be directly applicable in clinical practice, providing scientific evidence and practical guidance for the early diagnosis and treatment of PAS. It has important clinical significance for early prediction of clinical outcomes in pregnant women with placenta accreta, referral of high-risk pregnant women, multidisciplinary consultation, and reducing risks to both the mother and the perinatal period. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is the Venn diagram for differential gene screening in Example 1

[0039] Figure 2 This is the Venn diagram for differential gene screening in Example 2

[0040] Figure 3 Schematic diagram of the performance of the 25-gene LR classifier obtained by inputting the NPC-TPM values ​​of 702 genes in Example 2

[0041] Figure 4 Schematic diagram of the performance of the 23-gene SVM-RBF kernel classifier obtained by inputting the NPC-TPM values ​​of 702 genes in Example 2 DETAILED DESCRIPTION

[0042] The present invention will be further described below with reference to the embodiments, but the scope of protection of the present invention is not limited thereto:

[0043] Example 1

[0044] Methods: A high-risk PAS cohort was established at the Maternal and Child Health Hospital of City A (BGI sequencing platform) and the Maternal and Child Health Hospital of City B (Illumina sequencing platform). NIPT data and clinical information of pregnant women who underwent non-invasive DNA screening and had PAS high-risk factors (at least one of the following: previous cesarean section, uterine surgery such as uterine fibroids, hysteroscopy or intrauterine operation, assisted reproductive technology) were prospectively collected. The patients were followed up until 28 days after delivery.

[0045] Exclusion criteria included: ① stillbirth, neonatal death, or other non-viable pregnancy outcomes; ② fetal chromosomal abnormalities or structural developmental abnormalities; and ③ multiple pregnancies. Pregnant women with PAS and those without PAS were matched based on age, gestational age at NIPT, fetal sex, and distribution of high-risk factors.

[0046] Among high-risk pregnant women undergoing NIPT using the BGI sequencing platform, 54 PAS and 157 non-PAS high-risk women were included in the training dataset, 26 PAS and 71 non-PAS high-risk women were included in the internal validation dataset, and 25 PAS and 77 non-PAS high-risk women were included in the time validation dataset for differential analysis and model training. In addition, 54 PAS and 162 non-PAS high-risk women undergoing NIPT using the Illumina sequencing platform were included in an independent external validation dataset.

[0047] The NIPT data of the enrolled pregnant women were annotated with cfDNA promoter nucleosome coverage profiles, and sequence alignment was performed with the human reference genome hg19. PCR duplicates were removed, and the raw read coverage of the pTSS region was calculated. The raw read coverage was normalized using two methods to obtain the NPC-RPKM value and NPC-TPM value of each gene, respectively.

[0048]

[0049] Among them, NPC-RPKM i represents the RPKM-normalized promoter coverage of the pTSS region of the i-th gene, NPC-TPM i represents the TPM-normalized promoter coverage of the pTSS region of the i-th gene, q i represents the raw read coverage of the pTSS region, l i represents the transcript length (all 2000), tmr represents the total length of all genes, ∑ j (q j / l j ) represents the sum of the read coverage of the pTSS regions of all genes in a sample after normalization of transcript length.

[0050] In the training data set, PAS pregnant women were matched 1:1 with non-PAS high-risk pregnant women. Each group had 54 samples. DESeq2, limma-voom and rank sum test were used for analysis. Genes with p-values ​​< 0.05 and log2FC > 0.5 calculated by at least two of the three differential analysis methods were screened, and 226 differential pTSS coverage genes were obtained. Figure 1 Shown is a Venn diagram for differential gene screening.

[0051] To validate the effectiveness of the models after standardization using different methods, the optimal cutoff values ​​for the 226 eigenfactors were set to the NPC-RPKM and NPC-TPM values ​​that maximized the sum of sensitivity and specificity in the training dataset. When the NPC eigenfactor (NPC-RPKM or NPC-TPM) was greater than the corresponding optimal cutoff value, it was set to 1; otherwise, it was set to 0.

[0052] The selected feature factors were input into the RFE process, and a PAS disease prediction classifier was gradually constructed using various machine learning methods. The classifiers were trained using the SVM-Linear kernel, SVM-RBF kernel, and LR. Pregnant women with PAS were assigned a value of 1, while those without PAS were assigned a value of 0. To improve the sensitivity of the classifier, the class_weight parameter was set to {0:0.1, 1:0.3}. The disease risk assessment results for the target disease were obtained, and k-fold cross-validation (k=10) was applied to increase the robustness of the assessment. The optimal feature factor combinations under different modeling methods were extracted, and the optimal classifier and its evaluation results were output.

[0053] For the NPC-RPKM value, the output result is a 23-gene SVM-Linear classifier, which has poor performance (AUC < 0.5) in the external validation set of different platforms, as shown in Table 1.

[0054] Table 1

[0055]

[0056] For the NPC-TPM value, the output result is a 31-gene SVM-Linear kernel classifier. The verification performance of this classifier in both the time validation set and the external validation set has increased significantly. It can be seen that the NPC-TPM value is more suitable for data from different platforms. See Table 2 for details.

[0057] Table 2

[0058]

[0059]

[0060] For the NPC-TPM values, the output results were a 38-gene LR classifier and a 38-gene SVM-RBF kernel classifier, as detailed in Tables 3 and 4. Both classifiers showed significant improvements in validation performance on the external validation set (AUC > 0.7), with the SVM-RBF kernel classifier performing best. This indicates that the discrete data of the NPC-TPM applied to different platforms better conforms to the nonlinear model of the SVM-RBF kernel, making the SVM-RBF kernel more suitable for constructing classifiers on different platforms.

[0061] Table 3

[0062]

[0063] Table 4

[0064]

[0065] Example 2

[0066] On the basis of Example 1, the PAS high-risk cohort of the Maternal and Child Health Hospital of City C (Life sequencing platform) was added, and the inclusion criteria and prospective sample data collection method were the same as in Example 1.

[0067] Among high-risk pregnant women undergoing NIPT using the BGI sequencing platform, 70 PAS and 210 non-PAS high-risk women were included in the training dataset, and 35 PAS and 95 non-PAS high-risk women were included in the internal validation dataset for differential analysis and model training. Furthermore, 51 PAS and 163 non-PAS high-risk women who underwent NIPT PLUS (higher sequencing depth) testing on the BGI sequencing platform at City A Maternal and Child Health Hospital, 54 PAS and 162 non-PAS high-risk women enrolled at City B Maternal and Child Health Hospital, and 55 PAS and 165 non-PAS high-risk women enrolled at City C Maternal and Child Health Hospital were included in three independent external validation datasets (NIPT PLUS dataset, Illumina validation set, and Life validation set).

[0068] The NIPT data of the enrolled pregnant women were annotated with cfDNA promoter nucleosome coverage profiles using the same method as in Example 1, and the NPC-TPM values ​​were input into the classifier training system.

[0069] In the training data set, PAS-recombinant pregnant women were matched 1:1 with non-PAS high-risk pregnant women, with 35 samples in each group. DESeq2, limma-voom and rank sum test were used for analysis, and genes with p values ​​< 0.05 calculated by the three differential analysis methods were screened, resulting in 702 differential pTSS coverage genes. Figure 2 Shown is a Venn diagram for differential gene screening.

[0070] The optimal cutoff value for each of the 702 eigenfactors was set to the NPC-TPM value that maximized the sum of sensitivity and specificity in the training dataset. When the NPC eigenfactor (i.e., NPC-TPM) was greater than the corresponding optimal cutoff value, it was set to 1; otherwise, it was set to 0.

[0071] The selected feature factors were input into the RFE process, and a PAS disease prediction classifier was gradually constructed using various machine learning methods. The SVM-RBF kernel and LR method were selected for classifier training.

[0072] The PAS pregnant women were set to 1 and the non-PAS high-risk pregnant women were set to 0 and input into the system for classifier training. To improve the sensitivity of the classifier, the parameter value of class_weight was set to {0:0.1,1:0.3}.

[0073] The disease risk assessment results of the target to be predicted were obtained, and k-fold cross validation (k=10) was applied to increase the robustness of the assessment.

[0074] Extract the best feature factor combination under different modeling methods, and output the optimal classifier and its evaluation results.

[0075] The LR training method was used to output a 25-gene LR classifier. The AUC, accuracy, sensitivity, and specificity of the classifier were calculated in the training dataset, internal validation dataset, and external validation dataset. See Table 5. Figure 3 .

[0076] Table 5

[0077]

[0078]

[0079] The SVM-RBF kernel training method was used, and the output result was an SVM-RBF kernel classifier for 23 genes. The discretization thresholds for each gene are shown in Table 6.

[0080] Table 6

[0081]

[0082] The AUC, accuracy, sensitivity, and specificity of the classifier were calculated in the training data set, internal validation data set, and external validation data set, as shown in Table 7. Figure 4The SVM classifier uses fewer genes and performs better than the LR classifier. The 702-characteristic factor set, obtained by 1:1 matching 35 PAS-rearranged pregnant women with 35 high-risk non-PAS pregnant women, was superior to the 226-characteristic factor set obtained by 54 PAS-rearranged pregnant women with 54 high-risk non-PAS pregnant women. The results suggest that integrating the expression levels of 23 genes, including ABHD1, ALG1L2, EYS, FAM157C, KDSR, KRT5, LANCL2, LINC00390, LINC00964, LOC105371998, LOC107987394, LOC644090, LYZL2, MIR184, MIR4802, MYT1L, NGDN, NSD2, PACRG.AS3, SAP30L.AS1, SLC16A12.AS1, TADA3, and TMEM147.AS1, can accurately predict PAS at an early stage and design highly sensitive and specific detection methods, which is expected to be used in clinical diagnosis kits to promote the development of personalized medicine and precision treatment.

[0083] Table 7

[0084]

[0085] The specific embodiments described herein are merely illustrative of the spirit of the present invention. Persons skilled in the art may make various modifications, additions, or substitutions to the described specific embodiments without departing from the spirit of the present invention or exceeding the scope of the appended claims.

Claims

1. A classifier training system for early identification of the risk of placenta accreta disease in high-risk pregnant women, characterized in that It includes: Dataset division module: extract the pre-collected medical data of pregnant women at high risk of placenta accreta disease (PAS), and divide it into discovery data set, training data set, internal validation data set, and external validation data set; Influencing factor extraction module: The non-invasive prenatal DNA test NIPT data of PAS high-risk pregnant women collected in advance are used to annotate the promoter nucleosome coverage spectrum of free DNA whole genome and extract features, calculate the original read coverage of the pTSS region, perform TPM-like standardization on the original read coverage of the pTSS region to obtain the TPM-like standardized promoter coverage NPC-TPM, and the NPC-TPM corresponding to all genes is used as the influencing factor; Feature screening module: Screen the influencing factors of high-risk pregnant women with and without PAS in the discovery data set to determine the characteristic factors; Characteristic factor discretization module: determine the optimal cutoff value for each characteristic factor and discretize the characteristic factor based on the optimal cutoff value; Model acquisition module: Input the screened feature factors into the feature recursive elimination (RFE) process, and use a variety of machine learning algorithms to gradually build a PAS disease prediction classifier; obtain the disease risk assessment results of the target to be predicted, and apply k-fold cross validation to increase the robustness of the assessment; extract the best feature factor combination, and output the optimal classifier and its evaluation results.

2. The system according to claim 1, characterized in that In the data set division module, pregnant women with PAS and those without PAS were matched according to age, gestational age at NIPT, fetal sex, and distribution of high-risk factors. The samples from the main center were randomly divided into a training data set and an internal validation data set, and the samples from each branch center were used as independent external validation data sets. The discovery data set was obtained by performing a 1:1 matching of the training data set with the gestational age at NIPT and the fetal sex.

3. The system according to claim 1, characterized in that In the impact factor extraction module, the NIPT data were aligned with the human reference genome hg19 using a sequence alignment algorithm, PCR duplicates were removed, the region 1000 bp above and below the transcription start site TSS was determined as the promoter region pTSS, and the raw read coverage of the pTSS region was calculated.

4. The system according to claim 3, characterized in that In the impact factor extraction module, the raw read coverage of the pTSS region is normalized to a TPM-like standard, and NPC-TPM is obtained by the following formula: Among them, NPC-TPM i represents the TPM-normalized promoter coverage of the pTSS region of the ith gene, q i represents the raw read coverage of the pTSS region, l i represents the transcript length, ∑ j (q j / l j ) represents the sum of the read coverage of the pTSS regions of all genes in a sample after normalization of transcript length.

5. The system according to claim 1, characterized in that the feature screening In this module, the influencing factors of high-risk pregnant women with and without PAS in the discovery data set were analyzed by DESeq2, limma-voom and rank sum test, and the influencing factors with p values ​​of <0.05 calculated by the three difference analysis methods were selected as characteristic factors.

6. The system according to claim 1, characterized in that the characteristic factor In the discrete module, in order to enhance the universality and clinical practicality of the classifier for different sequencing platforms, the optimal cutoff value of each feature factor was set to the NPC-TPM value with the maximum sum of sensitivity and specificity in the training data set; When the characteristic factor NPC-TPM is greater than the corresponding optimal cutoff value, it is set to 1; otherwise, it is set to 0.

7. The system according to claim 1, characterized in that In the model acquisition module, a variety of machine learning algorithms are used to gradually build a PAS disease prediction classifier, and logistic regression LR, support vector machine SVM linear kernel and RBF kernel function are selected for classifier training.

8. The system according to claim 1, characterized in that In the model acquisition module: The best characteristic factor combination is the target gene: ABHD1, ALG1L2, EYS, FAM157C, KDSR, KRT5, LANCL2, LINC00390, LINC00964, LOC105371998, LOC107987394, LOC644090, LYZL2, MIR184, MIR4802, MYT1L, NGDN, NSD2, PACRG.AS3, SAP30L.AS1, SLC16A12.AS1, TADA3, TMEM147.AS1; The optimal classifier uses the support vector machine SVM-RBF kernel.

9. A classifier for early identification of the risk of placenta accreta disease in high-risk pregnant women, characterized in that It is obtained by the training system described in any one of claims 1-8.

10. Reagents for detecting the expression of ABHD1, ALG1L2, EYS, FAM157C, KDSR, KRT5, LANCL2, LINC00390, LINC00964, LOC105371998, LOC107987394, LOC644090, LYZL2, MIR184, MIR4802, MYT1L, NGDN, NSD2, PACRG.AS3, SAP30L.AS1, SLC16A12.AS1, TADA3, and TMEM147.AS1 genes are used in the preparation of diagnostic kits for early identification of the risk of placental accreta disease in high-risk pregnant women.

Images