RU2718272C1 - Method for screening probability of breast cancer presence - Google Patents

Abstract

FIELD: medicine.

SUBSTANCE: invention refers to medicine, namely oncology, and can be used for screening of probability of presence of breast cancer (BC) in patients of Caucasian race. Level of biomarkers in a biological fluid sample obtained in a subject is measured: CYFRA.21.1, ApoA2, Ddimer, HE4, B2M, ApoA1, sVCAM.1, CA125, CA15.3, TTR, hsCRP, CEA. Set of obtained values of biomarkers is processed using at least one classification model trained to determine a high or low probability of the presence of breast cancer.

EFFECT: method provides higher accuracy of screening detection of cancer in the patients of the Caucasian race by using a classification model trained to determine the high or low probability of the presence of breast cancer.

4 cl, 9 dwg, 4 tbl

Description

FIELD OF THE INVENTION

The invention relates to medicine, namely to Oncology, and can be used for screening to determine the likelihood of breast cancer (breast cancer) or to identify this cancer at an early stage.

State of the art

Malignant tumors are one of the most significant public health problems not only in Russia, but throughout the world.

Oncological diseases are the second most common cause of death in Russia. The average incidence rate of malignant neoplasms in Russia in 2016 was 408.6 people. per 100,000 population. The average mortality rate is 201.6 people. per 100,000 population. Cancer incidence is increasing worldwide. Over the past 10 years, it has increased by more than 20%.

In the case of the development of a malignant disease, the stage at which the oncological process will be detected is one of the determining factors determining the patient's lifespan.

Breast Cancer (BC) is the leading oncological disease in all countries of the world. Annually, more than a million cases of this disease are recorded. Moreover, in the case of detection of the disease at an early stage in the vast majority of cases, a complete cure is possible.

To detect breast cancer, the following instrumental diagnostic methods are known - mammography, ductography, ultrasound (ultrasound), magnetic resonance imaging, positron emission tomography, etc.

The ultrasound method, the most common in women under the age of 35 years, makes it possible to distinguish more dense tumor tissue from surrounding normal tissue. However, in the process of diagnosis, areas of fatty involution may be mistaken for pathological structures. In addition, ultrasound does not visualize microcalcifications often found in malignant neoplasms.

The main method for diagnosing malignant neoplasms of the mammary gland today is mammography, which allows detecting breast neoplasms larger than 10 mm in diameter with a reliability of up to 95%.

However, despite the effectiveness of the X-ray method, in some cases, the resolution of mammography decreases sharply, for example, with severe inflammatory changes, diffuse forms of mastopathy, edema of the gland and background diseases such as fibroadenomatosis.

A common limitation of instrumental diagnostic methods is the ambiguity in interpreting the results, associated with a variety of individual structural features and breast morphology.

As an alternative to instrumental diagnostic methods, diagnostic methods based on the determination of biochemical markers in biological tissues and patient fluids, for example, whole blood, serum, or plasma, can be used. As such markers, various antigens, proteins and metabolites secreted by malignant cells or formed during their death can be used. Currently, there are no recommendations on the use of biomarkers for the diagnosis of breast cancer. Some of the most promising candidates are SBA (cancer embryonic antigen), CYFRA 21-1 (cytokeratin fragment 19) and CA15-3 (cancer antigen 15-3), but their use for the diagnosis of breast cancer is limited due to insufficient sensitivity and specificity (Kazarian et al ., Testing breast cancer serum biomarkers for early detection and prognosis in pre-diagnosis samples. Br J Cancer. 2017 Feb 14; 116 (4): 501-508). The use of multiplex diagnostic methods, implying an assessment of the risk of the presence of a disease based on measurements of several biomarkers, allows us to overcome this problem and achieve more reliable results.

From the international application WO 2013062931, the definition of breast cancer metastases is known by detecting messenger RNAs of specific biomarkers circulating in the peripheral blood serum, bone marrow or lymph nodes - SBA, CA15-3, PIP, hMAM and HER2.

US 6670141 provides a panel of biomarkers for the diagnosis and treatment of breast cancer. At the same time, studies were conducted on the saliva of healthy women, women with benign breast lesions, and women diagnosed with breast cancer. It was found that the levels of c-ErbB-2 (ERB) and CA 15-3 markers in cancer patients are significantly higher than in healthy women and women with benign tumors, and p53 protein levels, in contrast, are higher in the control group of healthy women.

Sets of biomarkers for the diagnosis of breast cancer are also proposed in the applications US 20160282351, US 20150024960, WO 2010017515.

WO 2005113835 identified potential breast cancer biomarkers identified in ductal lavage samples from individual women at high risk of developing breast cancer, among which were identified. Apoliprotein A-I (ApoA-I), Apoliprotein A-II (ApoA-II). It was found that a lower than usual expression level of these markers or combination of markers correlates with breast cancer in a patient.

Patent application WO2005083440 describes a method for diagnosing ovarian cancer, breast cancer and colorectal cancer based on the simultaneous identification of many biomarkers, the production of which in the body increases dramatically in cancer. Among these biomarkers proposed including leptin, prolactin, chymotrypsin enzymes, kallikreins, tumor markers CA125, CA15-3, CA19-9, MUC1, OVX1, CEA, M-CSF, OPN and IGF-II, prostatin, CA54-61, CA72, HMFG2, IL-interleukins 6, IL-10, LSA, M-CSF, NB70K, PLAP, TAG72, factors TNF, TPA, UGTF, VEGF, CLDN3, NOTCH3, E2F, and others. For the diagnosis of breast cancer, biomarkers of leptin, prolactin, OPN and IGF- were isolated I.

From patent RU 2599890 a method is known for detecting and monitoring the treatment of breast cancer and ovarian cancer based on determining the concentrations of tumor-associated antigens: AFP, hCG, CEA, CA125, CA15-3 and CA19-9 in a human serum sample.

From the publication (Kim et al., The multiplex bead array approach to identifying serum biomarkers associated with breast cancer. Breast Cancer Research 2009, 11: R22, doi: 10.1186 / bcr2247) (prototype), a method for assessing the risk of various types of cancer is known, in including Breast cancer, as measured by serum protein biomarkers - AFP, CEA, CA19-9, CA125, PSA, ApoA1, ApoA2, TTR, B2M, IL-6, CRP, PAI-1.

Despite the high discriminatory ability of the model proposed in the prototype, its validation and adaptation is necessary for different populations of the subjects, which is associated with interpopulation differences in the molecular mechanisms of carcinogenesis. Thus, differences were revealed in gene expression, the nature of somatic mutations, and DNA methylation patterns from tumor samples taken from patients of the Caucasian and Black races (Huo et al., Comparison of Breast Cancer Molecular Features and Survival by African and European Ancestry in The Cancer Genome Atlas. JAMA Oncol. 2017 Dec 1; 3 (12): 1654-1662). It was noted in the work that such differences can affect the occurrence of individual subtypes of breast cancer and the prognosis of the disease.

The claimed invention is based on the study of a new complex of markers, which allows to increase the accuracy and reliability of determining the presence of a disease during breast cancer screening in a particular patient of the Caucasian population, the formation on this basis of a particular risk group and the identification of those patients who need an in-depth expensive examination to detect an early stage Breast cancer.

Disclosure of Invention

The technical problem solved by the present invention is the creation of a more accurate method for determining the likelihood of breast cancer in the Caucasoid population.

Achievable technical result is to increase the accuracy of screening for the presence of cancer in patients of the Caucasian population, and already in the early stages of its development, by biostatistical processing of the results of the analysis of the serum and blood plasma fractions with determination of the concentration of the complex group of biomarkers.

The technical result is achieved by implementing a screening method for determining the likelihood of breast cancer in patients of the Caucasian population, including measuring the level of biomarkers in a sample of biological fluid (for example, plasma or whole blood, urine, sputum) obtained from a subject: HE4, ApoA2, CYFRA.21.1, Ddimer , ApoA1, TTR, B2M, CA125, hsCRP, CEA, sVCAM.1, CA15.3, followed by processing the set of obtained biomarker values using at least one classification model trained to determine high or low weight the presence of breast cancer.

As classification models, the random forest method and / or linear discriminant analysis and / or the support vector method are used.

A trained classification model is obtained by implementing the following steps:

- form a training and test sample of records of subjects with measured biomarkers (HE4, ApoA2, CYFRA.21.1, Ddimer, ApoA1, TTR, B2M, CA125, hsCRP, CEA, sVCAM.1, CA15.3), including records of patients of different ages ;

- teach the classification model to identify a given pathology using the records of the training and test samples;

- retain the relationships and weights of the trained classification model, for the subsequent determination of the likelihood of breast cancer according to the results of processing the measured biomarker data of the subject.

When forming a training and test sample, they include records of subjects with a revealed pathology - the presence and absence of breast cancer.

The technical result is achieved through the implementation of a screening system for determining the likelihood of breast cancer, including

- module for entering the measured biomarker values of the subject HE4, ApoA2, CYFRA.21.1, Ddimer, ApoA1, TTR, B2M, CA125, hsCRP, CEA, sVCAM.1, CA15.3;

- a data storage module configured to store the training and test samples of the classification model, the relationships and weights of the trained classification model, records of subjects with measured values of the HE4, ApoA2, CYFRA.21.1, Ddimer, ApoA1, TTR, B2M, CA125, hsCRP, CEA biomarkers , sVCAM.1, CA15.3, including records of patients of different ages;

- module trained classification model, made with the possibility of building and training at least one classification model to determine the presence of a given pathology for the said markers taken from the data storage module;

- a diagnostic module configured to process the entered biomarker values of the subject using at least one trained classification model;

- a data output module, configured to obtain data on a high or low probability of breast cancer.

The accuracy of the proposed multiplex method for the diagnosis of breast cancer is ensured through the use of a complex of 12 biomarkers, as well as through the use of several classification models with the subsequent averaging of model results.

Brief Description of the Drawings

The invention is illustrated by drawings, where:

In FIG. Figure 1 shows a scatter plot of the patient's age — concentration of biomarkers. Points are individual measurements, lines are predictions of a linear regression model. The graphs show the values of correlation coefficients calculated by the Pearson method and P-values calculated by the Student test;

In FIG. 2 - ROC-curves for assessing the predictive ability of individual biomarkers (line type corresponds to the biomarker);

In FIG. 3. - Examples of decision trees obtained as a result of training the multivariate classification algorithm random forest on experimental data for 12 biomarkers;

In FIG. 4 - Visualization of the results of the separation of patients into 2 classes (healthy donors and patients with breast cancer) using a linear discriminant analysis of 12 biomarkers;

In FIG. 5 - Examples of 3-dimensional projections of the division of the combined patient population into 2 classes (healthy donors and patients with breast cancer) using the support vector method for 12 biomarkers;

In FIG. 6 - The proportion of classifiers stratified by AUROC depending on the number of biomarkers included in them. The training was conducted using A. Method of support vectors B. Linear discriminant analysis.

In FIG. 7 - ROC curves for evaluating the predictive ability of various classification algorithms. A. The entire data set was used both for model training and for its validation; B. 80% of the data was used to train the model, 20% - for validation.

In FIG. 8 is a block diagram of a system designed to assess the likelihood of breast cancer based on patient data.

In FIG. 9 - Algorithm for assessing the likelihood of breast cancer based on patient data.

The implementation of the invention

The initial group of biomarkers used in the diagnostic test to determine the likelihood of breast cancer was obtained using a multivariate classification model. Such methods make it possible to find combinations of biomarkers with the greatest diagnostic potential. The mathematical model is trained on experimental measurements of a given set of biomarkers obtained on a mixed sample of healthy volunteers and patients with breast cancer. The trained model can be used to assess the risk of a patient having a disease based on indicators of her biomarkers.

As part of the work carried out at the stage of developing a diagnostically significant set of indicators, we used the measurement data of 16 biomarkers (AFP, CEA, CA 19-9, CA 125, HE4, tPSA, CA 15-3, B2M, hsCRP, Ddimer, CYFRA 21-1, ApoA1, ApoA2, Apo B, TTR, sVCAM-1) obtained from a sample of healthy volunteers of the Caucasian population (104 women, average age 50 years) and patients with breast cancer (86 women, average age 63 years).

Statistical processing of experimental data and the development of classification models was carried out in R {RDevelopmentCoreTeam (2007). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0}.

The first step was statistical analysis and data visualization. For healthy volunteers, the effect of age on biomarker indices was evaluated (Fig. 1). Based on the results of the study at this stage, it was concluded that there was no significant correlation between the age of patients and the performance of most biomarkers (with the exception of CYFRA.21.1 and HE4).

At the next stage, the significance of differences in the levels of individual biomarkers between healthy volunteers and patients with breast cancer was assessed using the Student criterion after normalization of experimental data by log transformation (Table 1).

¹ - comparison by student's test after normalization of experimental data; * - P-values <0.05, ** - P-values <0.01, *** - P-values <0.001.

Based on the analysis, it was concluded that there were no significant differences in the concentrations of AFP, CA19.9 and ApoB between healthy volunteers and patients with breast cancer. Also in the framework of this study, there was a significant difference in the concentrations of CA15.3 and Ddimer, not included in the prototype.

To assess the diagnostic value of individual biomarkers, the logistic regression method was used. In these statistical models, the relationship between the concentration of the biomarker and the probability of the presence of the disease was considered (equation 1):

where P (Y) is the probability of the presence of the disease, b ₀ and b ₁ are the coefficients determined by the experimental data, X is the predictor (biomarker concentration).

The predictive ability of logistic models was evaluated using ROC analysis, which involves the determination of the sensitivity, specificity and accuracy of a method relative to a test or general data set. For this, the value of the threshold probability determining the presence of the disease varied from 0 to 1 with a given step; for each step, the share of correctly diagnosed cases of the disease (sensitivity) (S _e ), correctly identified cases of absence of the disease (specificity) (S _p ) , as well as the total proportion of correctly diagnosed cases, both the presence and absence of the disease (accuracy) (Acc), (equations 2-4):

where TP is a correctly classified positive result (a correctly diagnosed disease), FP is a false positive result (a misdiagnosed disease), TN is a correctly classified negative result (a correctly diagnosed absence of disease), FN is a false negative result (a misdiagnosed absence of disease).

The resulting set of sensitivity and specificity values was used to construct the ROC curve. The area under the ROC curve (AUROC) was used as an integral indicator of the quality of models: predictors with the maximum predictive ability show the highest AUROC values. The results of the ROC analysis are shown in FIG. 2 and in table 2.

Based on the results of statistical analysis of the data and assessment of the predictive ability of one-factor logistic models, biomarkers were selected, which were subsequently included in multifactor classification models. The inclusion criteria for biomarkers were pval <0.005 (Table 1) and AUROC≥0.6 (Table 2). Thus, to construct classification models, experimental measurements of 12 biomarkers were selected (CYFRA.21.1, ApoA2, Ddimer, HE4, B2M, ApoA1, sVCAM.1, CA125, CA15.3, TTR, hsCRP, CEA).

The development of multifactor classification models was the final stage of the study. Various machine learning methods (random forest, linear discriminant analysis, support vector method) were used as part of the current task. The estimation of model parameters (training) was carried out on the combined data obtained from healthy volunteers and patients with breast cancer, and was aimed at minimizing the predictive errors of the algorithm. A detailed description of the methods used is given in the book (Bishop CM, Pattern recognition and machine learning. Springer. 2006).

The random forest (RF) method involves the creation of a set of cross-validated decision trees. Each of these trees is trained on a subsample of data, which includes information only on the part of biomarkers and observations, and is validated on a subsample not used to construct it (bagging). Based on the predictions of each of the constructed decision trees, the patient is assigned to one of the groups (healthy donors or patients with breast cancer), the final prediction of the classifier is determined by the majority of votes of the constructed trees (see Fig. 3A, B).

The use of linear discriminant analysis (LDA) involves the search for a linear combination of biomarkers - discriminants, which ensures the best separation of the entire population of subjects into healthy volunteers and patients with breast cancer. The linear discriminant can be calculated: z (x) = β ₁ x ₁ + ... + β _n x _n , where x _i are the concentrations of the ith biomarker, β ₁ are the model coefficients. This problem is solved by finding the axis, the projection onto which provides the maximum ratio of the total variance of the linear combination of biomarkers of the sample to the sum of the variances of the linear combination of biomarkers within the classes (see Fig. 4).

Table 3. The values of linear coefficients in discriminant (LDAcomponent 1)

Using the support vector method (SVM) involves finding an (n-1) -dimensional hyperplane dividing the n-dimensional space of biomarker values into two classes. Let there be a training sample (x ₁ , y ₁ ), ... (x _n , y _n ), x _i ∈ R ⁿ , y _i ∈ {-1,1}, where x _i is the vector of biomarker values, ay _i determines the membership patient to class. The classifying function can be defined as F (x) = sign (〈w, x〉 + b), where w is the normal vector to the dividing hyperplane, b is an auxiliary parameter, and the function can take the values 1 or -1 depending on the class of the object . Learning an algorithm involves finding a hyperplane that provides the smallest empirical classification error and maximizes the distance between the biomarkers of patients belonging to different classes (see Fig. 5):

At the first stage of building multivariate models, the diagnostic value of various combinations of biomarkers from the above group was studied. For this, all possible combinations, including from 2 to 12 biomarkers, were used to build classification models (4,803 options). For training, we used the combined data obtained from healthy volunteers and patients with breast cancer, and the methods of linear discriminant analysis and reference vectors. The developed models were ranked in accordance with their predictive potential, estimated by the AUROC indicator (Fig. 7, table 4).

As can be seen from FIG. 6, complex tests, including 11-12 biomarkers, have the highest predictive ability, while for a relatively small proportion of classifiers, including combinations of 2-3 biomarkers, the AUROC indicator is more than 80%.

The final phase of constructing classifiers was their validation.

The pooled data obtained from healthy volunteers and patients with breast cancer were randomly divided into training and test samples. The estimation of model parameters (training) was carried out on a training set and was aimed at minimizing the predictive errors of the algorithm. The validation of trained models was to evaluate their predictive ability on a test sample. The predictive ability of multifactor classification models was evaluated using ROC analysis as was done previously for individual biomarkers (Fig. 7, Table 4).

Final classification models are trained algorithms that predict the likelihood of breast cancer based on experimental measurements of patient biomarkers.

The final solution is determining the probability of breast cancer, calculated as the median of the probability of breast cancer, calculated in 3 classification models (RF, LDA SVM), trained on the entire sample of patients (see, for example, Kittler J, Hatef M, Duin RPW et al. On Combining Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, VOL. 20, NO. 3, MARCH 1998 226-39.)

To implement the proposed method, software was developed (PO), which allows calculating the probability of having breast cancer based on the data of a particular patient (biomarker measurement results). A block diagram of an embodiment of the invention is shown in FIG. eight.

A computer-implemented system consists of (1) an interface including a patient data input device (results of biomarker measurements) and output of calculation results (probability of breast cancer); (2) a memory block containing trained classifier models and software products needed to work with them (R portable, Google Chrome Portable); and (3) a software module that implements the program code needed to exchange data between the interface and the memory block . The shiny package was used to create the GUI (Winston Chang, Joe Cheng, JJ Allaire, Yihui Xie and Jonathan McPherson (2017). Shiny: Web Application Framework for RR package version 1.0.5. Https: //CRAN.R-project. org / package = shiny) created on the basis of the R {RDevelopmentCoreTeam (2007) environment. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0}. To work with this package, you must have the R portable and Google Chrome portable software products stored in the memory block. To work with the proposed models, the following packages are required: (1) RandomForest (A. Liaw and M. Wiener (2002). Classification and Regression by randomForest. R News 2 (3), 18-22); (2) MASS (Venables, W.N. & Ripley, B.D. (2002) Modern Applied Statistics with S. Fourth Edition. Springer, New York. ISBN 0-387-95457-0); (3) e1071 (David Meyer, Evgenia Dimitriadou, Kurt Hornik, Andreas Weingessel and Friedrich Leisch (2017). E1071: Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien. R package version 1.6- 8. https://CRAN.R-project.org/package=e1071).

An algorithm for assessing the likelihood of breast cancer based on patient data is presented in FIG. 9.

Patient data is entered via the interface and served as input variables in the developed models, in each of which the probability of breast cancer is calculated. Further, according to the results of model predictions, the average value is calculated, which is displayed in the output window.

The diagnostic multiplex panel for breast cancer risk assessment includes biomarkers that showed the maximum predictive potential in the framework of the study (Fig. 2, table 2): CYFRA.21.1, ApoA2, Ddimer, HE4, B2M, ApoA1. In addition, the claimed complex includes additional biomarkers with less predictive potential, but significantly different between healthy volunteers and patients with breast cancer (Table 1): sVCAM.1, CA125, CA15.3, TTR, hsCRP, CEA in the studied population.

The following are clinical examples of the application of the method.

Example 1. Patient I., 63 years old.

The patient was invited to participate in the Oncopoisk program.

The patient (724) was examined as part of the program. The following results were obtained:

AFP 2.7 IU / ml, CEA 50.4 ng / ml, CA 19-9 77.8 IU / ml, CA15.3 824.4 IU / ml, CA125 820.9 IU / ml, B2M 3261 ng / ml , hsCRP 2 ng / ml, HE4 138.8 pmol / L, Ddimer 473.0 ng / ml, CYFRA.21.1 19.92 ng / ml, Apo A1 1.01 g / L, Aro A2 0.16 g / L , Apo B 0.9 g / l, TTR (prealb) 15.0 mg / dl, sVCAM. 998 ng / ml, Rantes 33263 pg / ml, VEGFR1 151 pg / ml, LRG-1 136201 ng / ml, Apo A4 37.8 μg / ml.

When processing the results by the claimed method, the probability of breast cancer was found that significantly exceeded the threshold value of 50% (Table 4): model RF - 99.8%, model LDA - 99.1%, model SVM - 94.5%, average total probability of the presence of breast cancer over three models amounted to 97.8%.

The patient is invited for examination.

On examination:

Peripheral lymph nodes are not enlarged. The mammary glands are symmetrical. Nipples and areoles are not changed. In both mammary glands, nodular formations are not determined, the tissue of the mammary glands of increased density. There are no skin symptoms.

The patient is directed to mammography with tomosynthesis.

On mammography, mammary glands of increased mammographic density (4). In the tissue of both mammary glands, residual effects of fibrocystic mastopathy with a pronounced fibrous component. In the upper-outer quadrant of the right mammary gland, a site with an accumulation of microcalcifications, an area of up to 2 cm, is determined.

Under the supervision of an ultrasound, a puncture of a cancerous area of the right breast was performed.

Cytological conclusion: cancer cells.

The patient underwent surgical treatment in the amount of radical resection of the right breast. Histological conclusion: In the tissue of the mammary gland sector, the tumor node is 0.8 cm in diameter. Has the structure of infiltrative ductal cancer of the II degree of malignancy, with the presence of ductal cancer structures in situ.

In 18 examined lymph nodes, cancer metastases were not detected.

Immunohistochemical study: ER (estrogen receptors) 105 N-points, PR (progesterone receptors) - 50 N-points. Her2neu 1+.

When examining data for distant metastases was not detected.

Diagnosis: Cancer of the right breast T1N0M0.

Example 2. Patient K., 72 years old.

The patient was invited to participate in the Oncopoisk program.

The patient (659) was examined as part of the program. The following results were obtained:

AFP 4.14 IU / ml, CEA 1.68 ng / ml, CA 19-9 14.92 IU / ml, CA15.3 57.29 IU / ml, CA125 15.11 IU / ml, B2M 3527 ng / ml, hsCRP 32 ng / ml, HE4 143.3 pmol / l, Ddimer 466.0 ng / ml, CYFRA.21.1 4.79 ng / ml, Apo A1 1.65 g / l, Apo A2 0.344 g / l, Apo B 2 , 04 g / l, TTR (prealb) 26.0 mg / dl, sVCAM.1 1278 ng / ml, Rantes 59201 pg / ml, VEGFR1 91 pg / ml, LRG-1 98732 ng / ml, Aro A4 32.5 mcg / ml.

When processing the results obtained by the claimed method revealed a high probability of breast cancer.

When processing the results by the claimed method, the probability of breast cancer was significantly higher than the threshold value of 50% (Table 4): model RF - 96.6%, model LDA - 81.1%, model SVM - 94.8%, the average total value of the likelihood of breast cancer in three models was 90.8%.

The patient is invited for examination.

On examination, the peripheral l / nodes are not enlarged. No tumor is detected in the tissue of both mammary glands.

Earlier last year, the patient was examined, a mammogram was performed. According to the conclusion: involutive changes in the tissue of the mammary glands.

A mammogram with tomosynthesis was performed. In the upper outer quadrant of the right mammary gland, an accumulation of microcalcinates is determined on an area of 2 cm. A Cor biopsy of this area of breast tissue was performed under the control of targeted mammography.

Histological conclusion: a picture of an invasive, without signs of specificity, breast cancer G2, a trabecular solid structure. Immunohistochemical study: estrogen receptors 8 points, progesterone receptors 8 points, Ki 67 4%, Her2neu - 0.

The diagnosis of breast cancer T1N0M0, luminal A.

Surgical treatment in the amount of radical resection of the right breast.

The diagnosis is histologically confirmed. A tumor measuring 15 mm, without signs of vascular and perineural invasion. In 17 examined lymph nodes with no signs of metastasis.

Claims (7)

1. A method for screening the probability of breast cancer (breast cancer) in a Caucasian patient, including measuring the level of biomarkers in a sample of body fluid obtained from a subject: CYFRA.21.1, ApoA2, Ddimer, HE4, B2M, ApoA1, sVCAM.1, CA125 , CA15.3, TTR, hsCRP, CEA, followed by processing the totality of the obtained biomarker values using at least one classification model trained to determine whether breast cancer is high or low. 2. The method according to p. 1, characterized in that as the classification models use the method of "random forest" (random forest), and / or linear discriminant analysis, and / or the method of support vectors. 3. The method according to p. 1, characterized in that the trained classification model is obtained by implementing the following steps: - form training and test samples of records of subjects with measured biomarkers CYFRA.21.1, ApoA2, Ddimer, HE4, B2M, ApoA1, sVCAM.1, CA125, CA15.3, TTR, hsCRP, CEA, including records of patients of different ages; - teach the classification model to identify a given pathology using the records of the training and test samples; - retain the relationships and weights of the trained classification model for the subsequent determination of the likelihood of breast cancer following the processing of the measured data of the subject's biomarkers. 4. The method according to p. 3, characterized in that during the formation of the training and test samples include records of subjects with identified pathology - the presence and absence of breast cancer.

Images