Intelligent detection method for premature rupture of fetal membranes

Abstract

The invention relates to the technical field of liquid detection, in particular to an intelligent detection method for premature rupture of fetal membranes, which comprises the following steps of: firstly, analyzing change characteristics of chromatographic data in a detection process according to ion strength deviation and ion strength change conditions of a base peak diagram and a total ion chromatogram in a time sequence; the sample component richness of the secretions of the detection pad is synthesized by combining the ion strength change condition; then further analyzing the chromatographic data of each biomarker, evaluating the chromatographic separation completeness of the biomarkers under the interference of other costs, and amplifying the precision of the biomarkers with higher chromatographic separation completeness in evaluating the pollution characteristics of the sample; finally, the pollution interference degree of the sample is calculated by analyzing the mass spectrum data characteristics of the biomarker and combining the chromatographic separation completeness and the sample component richness, so that the detection accuracy of the biomarker is improved under the condition of considering the pollution interference.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid detection, and particularly relates to an intelligent detection method for premature rupture of fetal membranes. Background Art

[0002] Premature Rupture of Membranes (PROM) refers to the rupture of the fetal membranes before the onset of labor, resulting in the outflow of amniotic fluid. Usually, the detection of premature rupture of fetal membranes is carried out by monitoring biomarkers in the pad secretions. The traditional biomarker detection method is the pH test paper method, which usually detects a single biomarker. When the biomarker is interfered by other body fluids such as vaginal inflammation or blood contamination, the test paper detection result may be affected; in order to ensure the detection accuracy, the existing technology uses mass spectrometry technology to detect various biomarkers in the pad secretions extracted from the pad.

[0003] However, in actual application, the secretion samples on the pad may contain other liquids such as blood and urine, and there are a large number of high-abundance interfering substances such as salts and proteins in samples such as blood and urine, which will cause different ion interference effects, resulting in possible errors in the mass spectrometry measurement results and reducing the detection accuracy of biomarkers; therefore, the method of directly monitoring the biomarkers in the pad secretions by mass spectrometry technology without considering pollution interference in the existing technology has low accuracy. Summary of the Invention

[0004] In order to solve the technical problem that the method of directly monitoring the biomarkers in the pad secretions by mass spectrometry technology without considering interference in the existing technology has low accuracy, the purpose of this application is to provide an intelligent detection method for premature rupture of fetal membranes, and the specific technical solution adopted is as follows: The first aspect of this application provides an intelligent detection method for premature rupture of fetal membranes, including: After separating the components of the physiological characteristics information of each pregnancy test of the pregnant woman and the corresponding pad secretions, obtaining the corresponding mass spectrum, base peak map, total ion current map, and the extracted ion current chromatogram of each biomarker; Determining the richness of the sample components for each test according to the ion intensity deviation and ion intensity change of the physiological characteristics information of the pregnancy and the base peak map and the total ion current map in time series; Determining the chromatographic separation completeness of each biomarker in each test according to the chromatographic peak shape distortion and signal intensity distribution of each biomarker in the extracted ion current chromatogram; Determine the sample contamination interference degree for each detection according to the richness of the sample components, the suppression of the spectral peaks of various biomarkers in the mass spectrum, and the corresponding chromatographic separation completeness; perform premature rupture of membranes detection according to the sample contamination interference degree.

[0005] Further, the process of obtaining the richness of the sample components includes: With the help of a deep learning model, determine the corresponding secretion volume index according to all the physiological characteristics information of the pregnant woman during each detection. Determine the corresponding ion richness according to the ion intensity deviation between the total ion current chromatogram and the base peak chromatogram at each time point. Determine the ion fluctuation degree at each time point according to the relative deviation of the ion intensity change between each time point and the adjacent time point. Determine the adjustment coefficient at each time point according to the product of the ion richness and the ion fluctuation degree; use the ratio of the adjustment coefficient to the corresponding ion intensity in the total ion current chromatogram at the corresponding time point as the weighting coefficient. Determine the richness of the sample components for each detection according to the product of the mean value of the weighting coefficients at all time points and the secretion volume index.

[0006] Further, the process of obtaining the secretion volume index includes: Input all the physiological characteristics information of the pregnant woman during each detection into the trained fully connected neural network model, and output the secretion volume index for each detection.

[0007] Further, the process of obtaining the ion richness includes: Normalize the difference between the corresponding ion intensity in the total ion current chromatogram and the corresponding ion intensity in the base peak chromatogram at each time point to determine the ion richness at each time point.

[0008] Further, the process of obtaining the ion fluctuation degree includes: Take the difference between the derivative value of each time point in the total ion current chromatogram and the derivative value of the previous time point as the first reference difference; take the difference between the derivative value of each time point in the total ion current chromatogram and the derivative value of the next time point as the second reference difference; determine the ion fluctuation degree at each time point according to the mean value between the first reference difference and the second reference difference.

[0009] Further, the process of obtaining the chromatographic separation completeness includes: Determine all the merged chromatographic peaks according to the distribution of the maximum points and inflection points in the extracted ion current chromatogram. Determine the corresponding drift distortion characteristic parameter according to the product between the time length of the interval corresponding to each merged chromatographic peak and the absolute value of skewness; Determine the local separation characteristic value of each merged chromatographic peak according to the ratio between the maximum signal value in each merged chromatographic peak and the drift distortion characteristic parameter; determine the chromatographic separation completeness of each biomarker in each detection according to the mean value of the local separation characteristic values of all merged chromatographic peaks.

[0010] Furthermore, the process of obtaining the merged chromatographic peaks includes: In the extracted ion current chromatogram, take the inflection point closest to each maximum point before and the inflection point closest to it after as the adjacent inflection points of each maximum point; take the local signal segment corresponding to the interval between the two adjacent inflection points corresponding to each maximum point as the initial chromatographic peak; Merge the adjacent initial chromatographic peaks in time sequence to determine all the merged chromatographic peaks.

[0011] Furthermore, the process of obtaining the sample contamination interference degree includes: Determine the corresponding separation weighted interference degree according to the product between the number of maximum values corresponding to each biomarker in the mass-to-charge ratio interval of the mass spectrum and the chromatographic separation completeness; Determine the local change value of each mass-to-charge ratio according to the mean value of the differences between the ion intensity of each mass-to-charge ratio and the ion intensities of the two adjacent mass-to-charge ratios before and after; determine the corresponding interval intensity deviation value according to the mean value of the local change values of all mass-to-charge ratios in the mass-to-charge ratio interval of each biomarker in the mass spectrum; Determine the corresponding ionization suppression effect value according to the product between the spectral peak area corresponding to each biomarker in the mass-to-charge ratio interval of the mass spectrum and the interval intensity deviation value; Determine the reference interference degree of each biomarker according to the ratio between the separation weighted interference degree and the ionization suppression effect value; Perform positive correlation normalization according to the product between the mean value of the reference interference degrees of all biomarkers and the sample component richness to determine the sample contamination interference degree of each detection.

[0012] Furthermore, the process of detecting premature rupture of fetal membranes according to the sample contamination interference degree includes: When the sample contamination interference degree is greater than the preset interference threshold, optimize the mass spectrum detection process of the biomarker, and perform premature rupture of fetal membranes detection according to the mass spectrum of the biomarker obtained by the optimized detection process.

[0013] Furthermore, the process of the optimized detection process includes: During the sample pretreatment process, solid-phase extraction is used to remove high-abundance interfering proteins, and isotope-labeled internal standards are added; hydrophilic interaction chromatography is used in the chromatographic conditions, and a volatile buffer with low ionic strength is selected; dynamic exclusion and multiple reaction monitoring modes are adopted in the adjustment of mass spectrometry parameters; the desolvation gas temperature is increased to 500 °C.

[0014] In a second aspect, the present application provides an intelligent detection system for premature rupture of fetal membranes, and the system includes: A data acquisition and pretreatment module, configured to separate the components of the physiological characteristics information during pregnancy and the corresponding pad secretions for each detection of the parturient to obtain the corresponding mass spectrometry diagram, base peak diagram, total ion current diagram, and extracted ion current chromatogram of each biomarker; A first determination module, configured to determine the richness of the sample components for each detection according to the ion intensity deviation and ion intensity change of the physiological characteristics information during pregnancy, the base peak diagram, and the total ion current diagram in time series; A second determination module, configured to determine the chromatographic separation completeness of each biomarker for each detection according to the chromatographic peak shape distortion and signal intensity distribution of each biomarker in the extracted ion current chromatogram; A premature rupture of fetal membranes detection module, configured to determine the sample contamination interference degree for each detection according to the richness of the sample components, the suppression of the spectral peaks of various biomarkers in the mass spectrometry diagram, and the corresponding chromatographic separation completeness; perform premature rupture of fetal membranes detection according to the sample contamination interference degree.

[0015] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the method as described in the first aspect or any embodiment of the first aspect of the present application.

[0016] In a fourth aspect, the present application provides a computer program product, and the computer program product includes computer program code, which when executed, executes the method as described in the first aspect or any embodiment of the first aspect of the present application.

[0017] In a fifth aspect, the present application provides a computer-readable storage medium, and the computer-readable storage medium stores computer program code, which when executed, executes the method as described in the first aspect or any embodiment of the first aspect of the present application.

[0018] The present application has the following beneficial effects: First, this application analyzes the variation characteristics of chromatographic data during the detection process based on the ion intensity deviation and ion intensity change of the base peak chromatogram and the total ion chromatogram in terms of time sequence, and comprehensively combines the ion intensity change to enrich the sample composition of the detected pad secretion, providing a basis for subsequent analysis of sample contamination characteristics. Then, the chromatographic data of each biomarker is further analyzed to evaluate the chromatographic separation completeness of the biomarker when interfered by other components, which can magnify the accuracy of the biomarker with high chromatographic separation completeness in evaluating sample contamination characteristics and avoid optimizing the detection process only for chromatography or mass spectrometry. Finally, by analyzing the mass spectrometry data characteristics of the biomarker, combining the chromatographic separation completeness and the sample composition richness, the contamination interference degree of the sample is calculated, and the samples with high contamination interference degree are re-detected after optimizing the detection process, so as to improve the detection accuracy of the biomarker considering the contamination interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 Flowchart of an intelligent detection method for premature rupture of fetal membranes provided by an embodiment of the present invention; Figure 2 Structural diagram of an intelligent detection system for premature rupture of fetal membranes provided by an embodiment of the present invention; Figure 3 Structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of an intelligent detection method for premature rupture of fetal membranes proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of these features.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0023] The following specifically describes the specific solution of an intelligent detection method for premature rupture of membranes provided by the present invention in conjunction with the accompanying drawings.

[0024] An embodiment of the present application provides an intelligent detection method for premature rupture of membranes. Please refer to Figure 1 , which shows a flowchart of an intelligent detection method for premature rupture of membranes provided by an embodiment of the present invention. The method includes: Step S101: After separating the components of the physiological characteristics information of the pregnant woman during each detection and the corresponding pad secretions, obtain the corresponding mass spectrum, base peak map, total ion current map, and extracted ion current chromatogram of each biomarker.

[0025] First, collect the physiological characteristics information of the pregnant woman during each detection through a medical database; in a specific implementation manner of the embodiment of the present invention, the physiological characteristics information of pregnancy includes estrogen and progesterone levels, vaginal secretion pH value, blood glucose, and gestational diabetes screening results, which can be adjusted according to the types of data collected by the pregnant woman during physical examination or inspection in the specific implementation environment, and all the physiological characteristics information of pregnancy collected is data authorized by the pregnant woman, which will not be further elaborated here.

[0026] Furthermore, considering that pad secretions are easily interfered by cross-contamination caused by other liquids such as urine and blood secretions, which affects the accuracy of detecting a single biomarker by test strip detection methods; therefore, in order to more accurately detect biomarkers, the present application first uses chromatography-mass spectrometry coupling technology to perform high-precision detection and processing on the secretions extracted from the pad; in a specific implementation manner of the embodiment of the present invention, first use a pad containing a multi-layer absorbent core to collect the pad secretions of the pregnant woman during each detection, extract the pad secretions on the pad into a special container through a straw or test strip sampling tool, and dissolve the secretions in a buffer solution, that is, 0.9% normal saline, and filter the sample to remove large particle impurities such as pad fibers; then remove impurities by centrifugation at 3000 rpm for 5 minutes, and extract the supernatant; then remove impurities by liquid-liquid extraction, and separate the biomarkers in the amniotic fluid; then perform enzymatic hydrolysis on the sample to optimize the detection sensitivity, and the implementer can also use derivatization treatment to replace the enzymatic hydrolysis process; in a specific implementation manner of the embodiment of the present invention, the biomarkers include: fetal fibronectin, placental alpha-microglobulin-1, insulin-like growth factor binding protein-1, and soluble intercellular adhesion molecule-1, which can be adjusted according to the specific implementation environment.

[0027] Further separate the processed samples through a liquid chromatography system, using a reverse-phase chromatographic column (such as Phenomenex Gemini C18, 100 mm×2.1 mm, 3 μm), with the column temperature at 40 °C to improve the separation efficiency and reduce the injection pressure; the mobile phase is configured as follows: Phase A: 0.1% formic acid + 4 mmol / L ammonium acetate aqueous solution (pH 3.0) to enhance the ionization efficiency; Phase B: acetonitrile (containing 0.1% formic acid); adopt a gradient elution method, with a flow rate of 0.4 mL / min to separate each component in the secretion; then ionize the split samples by electrospray ionization method, and use the full scan mode to enable the mass spectrometry system to obtain the corresponding mass spectrum (MS), base peak chromatogram (BPC), total ion current chromatogram (TIC), and extracted ion current chromatogram (EIC diagram of each biomarker); where the abscissa of the MS diagram is the mass-to-charge ratio of the ions, and the ordinate is the ion intensity; the ordinate of the BPC diagram is the ion intensity of the strongest ion peak; the ordinate of the TIC diagram is the total intensity of all ion signals; the ordinate of the EIC diagram is the ion intensity corresponding to the corresponding biomarker; the abscissa of the BPC diagram, TIC diagram, and EIC diagram is the retention time of the ions in the chromatography; it should be noted that the specific acquisition processes of the MS diagram, BPC diagram, TIC diagram, and EIC diagram, the reverse-phase chromatographic column, the gradient elution method, and the electrospray ionization method are all well-known technical means to those skilled in the art and will not be further limited and elaborated here.

[0028] Step S102: Determine the richness of the sample components for each detection according to the physiological characteristic information during pregnancy, as well as the ion intensity deviation and ion intensity change of the base peak chromatogram and the total ion current chromatogram in time series.

[0029] To analyze the interference of other body fluid components in the mass spectrometry detection data of the pad secretions, it is usually necessary to evaluate the physiological factors of the parturient herself, that is, to analyze according to the physiological characteristic information during pregnancy. In addition, during the sampling process of the parturient's pad samples, the extracted samples may be obtained by mixing various secretions or body fluids. These body fluids contain high-abundance proteins (such as albumin, mucoprotein) and metabolites (urea, creatinine, etc.). These matrices (matrices refer to the components other than the analytes in the samples) may significantly interfere with the analysis process of the analytes and affect the accuracy of the analysis results. To analyze the matrix effect interference suffered by the mass spectrometry data this time, it is first necessary to analyze the richness of the sample components in the sample. The greater the richness of the sample components, the more abundant the ion species that can be ionized are usually, and the more serious the corresponding pollution interference is. And the ion intensity deviation between the base peak chromatogram and the total ion current chromatogram can usually reflect the abundance of ion species to a certain extent. Therefore, this application determines the richness of the sample components for each detection according to the physiological characteristic information during pregnancy, as well as the ion intensity deviation and ion intensity change situation of the base peak chromatogram and the total ion current chromatogram in time series.

[0030] Preferably, in a specific implementation manner of the embodiment of the present invention, the process of obtaining the richness of the sample components includes: With the help of a deep learning model, according to all the physiological characteristic information of the parturient during each detection, determine the corresponding secretion volume index. The process of obtaining the secretion volume index includes: inputting all the physiological characteristic information of the parturient during each detection into the trained fully connected neural network model, and outputting the secretion volume index for each detection. Since the data affecting other body fluid components are usually multi-modal data, it is difficult to comprehensively evaluate the physiological condition of the parturient through a single analysis method. Therefore, the physiological condition of the parturient is evaluated by means of a neural network.

[0031] In a specific implementation of an embodiment of the present invention, the neural network training process is as follows: select the physiological characteristics of pregnancy that affect the accuracy of secretions collected by maternal pads, that is, the estrogen and progesterone levels, vaginal secretion pH value, blood sugar and gestational diabetes screening results in the embodiment of the present invention, collect a large number of physiological characteristics of pregnancy information sets, and use manual scoring to score each physiological characteristic data of pregnancy in combination with the above characteristics. The scoring values are: 0.1, 0.2, 0.3, ... 1, a total of 10 score types, corresponding to 10 physiological condition levels, and the scoring result is the secretion volume index. The higher the secretion volume index, the better the maternal pad. The more types and amounts of secretions that the pad may extract; the classification network structure is a 5-layer fully connected neural network, and other embodiments may be set to neural networks of other structures. This embodiment does not specifically limit it, and the loss function is a cross entropy function; the labeled data set is divided into a training set and a validation set in a ratio of 7:3, and the training set data is input into the classification network for training, and the gradient descent method is used for training until the loss function converges and the classification network training is completed; according to the physiological characteristics of pregnancy in the most recent prenatal examination report and other physical examination results of the parturient, the physiological characteristics of pregnancy are input into the trained neural network, and the secretion volume index of the current parturient is output. The secretion volume index of the parturient can reflect the types and amounts of secretions that may be contained in the way of pad sampling under her own physiological condition. The larger the value, the more it is necessary to improve the ion separation degree in the pre-treatment process of mass spectrometry detection.

[0032] Further, the corresponding ion richness is determined based on the ion intensity deviation between the total ion flow diagram and the base peak diagram at each time point; in a specific implementation method of an embodiment of the present invention, the process of obtaining the ion richness includes: normalizing the difference between the corresponding ion intensity in the total ion flow diagram at each time point and the corresponding ion intensity in the base peak diagram to determine the ion richness at each time point.

[0033] Chromatographic data can separate different compounds and use signal intensity to reflect the relative abundance of compounds. The BPC diagram can reflect the maximum ion intensity data at different times of the separation process. When the sample is interfered by body fluids such as urine or blood, a large number of small molecule metabolites (urea, creatinine) will be introduced, causing the biomarker signal to be masked by noise, which in turn causes the overall low ion intensity at each time point in the BPC diagram. TIC records the total intensity of all ion signals entering the mass spectrometer at each time point during the chromatographic separation process and their retention time in the chromatogram. During the separation process, the greater the relative intensity of all ion signals generated at the same time point and the lower the intensity of the single ion with the highest signal intensity, the less the single ion that conducts is present in the currently ionized ions. This indicates that the ion species ionized at the current moment are rich. Therefore, the greater the overall ion richness at each time point, the greater the richness of the sample components.

[0034] Considering that there are high-abundance non-target compounds in the sample, the elution of these substances may cause a sudden increase or decrease in the signal, that is, frequent numerical fluctuations occur in certain regions of the TIC diagram; such situations usually occur when there are multiple high-abundance components in the sample, and these components may be eluted successively during the chromatographic process and produce significant signal changes. Therefore, it is also necessary to evaluate the component richness of the sample by combining the data fluctuation characteristics in the TIC diagram. Therefore, further, according to the relative deviation of the ion intensity change between each time point and the adjacent time point, the ion fluctuation degree at each time point is determined.

[0035] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the ion richness includes: the process of obtaining the ion fluctuation degree includes: taking the difference between the derivative value of each time point in the total ion current diagram and the derivative value of the previous time point as the first reference difference; taking the difference between the derivative value of each time point in the total ion current diagram and the derivative value of the next time point as the second reference difference; determining the ion fluctuation degree at each time point according to the mean value between the first reference difference and the second reference difference; the greater the overall ion fluctuation degree at each time point, the more significant the signal change reflected, and the greater the corresponding sample component richness.

[0036] Further, the ion richness and the ion fluctuation degree are combined, and according to the product between the ion richness and the ion fluctuation degree, the adjustment coefficient at each time point is determined; so that the adjustment coefficient is positively correlated with the sample component richness; taking the ratio of the adjustment coefficient to the corresponding ion intensity in the total ion current diagram at the corresponding time point as the weighting coefficient; because when the single ion intensity with the highest signal intensity at each time point in the TIC diagram is lower, the corresponding ion species ionized are rich, so on the basis of the adjustment coefficient, a ratio process is combined with the corresponding ion intensity in the total ion current diagram at the corresponding time point, so that the obtained weighting coefficient can more accurately represent the sample components at each time point; The secretion amount index reflects the types and amounts of secretions that may be contained by sampling with a sanitary pad under its own physiological conditions. Therefore, on the basis of the overall size of the weighting coefficients at all time points, the secretion amount index is combined to comprehensively represent the sample component richness characterizing the number of types of secretion components. The embodiment of the present invention determines the sample component richness of each detection according to the product between the mean value of the weighting coefficients at all time points and the secretion amount index.

[0037] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the sample component richness is expressed by the formula: ; where is the sample component richness of the th detection; is the Index of the amount of secretion detected in the second test; is the Number of time points commonly corresponding in the total ion chromatogram and the base peak chromatogram of the is the ion intensity corresponding in the total ion chromatogram at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the is the ion intensity corresponding in the base peak chromatogram at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the is a linear normalization function, and the normalization processing method can be adjusted according to the specific implementation environment, such as the sigmoid function; is the degree of ion fluctuation at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the is the abundance of ions at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the is the adjustment coefficient at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the is the weighting coefficient at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the

[0038] In a specific implementation manner of the embodiment of the present invention, the acquisition process of the degree of ion fluctuation is expressed by the formula: ; where is the first reference difference at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the is the second reference difference at the th common corresponding time point in the total ion chromatogram and the base peak chromatogram of the test; it should be noted that when the corresponding time point is the first time point, the corresponding second reference difference is used as the degree of ion fluctuation; when the corresponding time point is the last time point, the corresponding first reference difference is used as the degree of ion fluctuation.

[0039] It should be noted that in the embodiments of the present invention, the time interval between two adjacent time points is set to 1 minute, which can be adjusted according to the specific implementation environment. And to ensure the meaningfulness of the calculation results, when performing fractional operations in the embodiments of the present invention, in the case of a denominator of 0, a tuning factor greater than 0 needs to be added to the denominator to prevent the denominator from being 0. The value of the tuning factor is set by the implementer according to the actual situation, and this application does not make special restrictions.

[0040] Step S103: Determine the chromatographic separation completeness of each biomarker in each detection according to the chromatographic peak shape distortion situation and signal intensity distribution situation of each biomarker in the extracted ion current chromatogram.

[0041] In addition to analyzing the richness of the sample components, it is also necessary to analyze the influence of other interfering components such as other body fluids on the ionization of biomarkers during the actual ionization process. Therefore, it is necessary to analyze various biomarkers for interfering components by combining chromatographic data characteristics; among the interfering components that may be contained in the feminine care pad, urine contains a large amount of small molecule organic acids and inorganic salts, which may affect the stability of the stationary phase of the chromatographic column (for example, high-concentration sodium ions (about 130 - 260 mmol / L in urine) compete with ion-pair reagents). In the chromatographic data, this feature is reflected as abnormal chromatographic peak shapes of biomarkers in the EIC diagram, such as peak broadening or peak height reduction, and the characteristic of target peak retention time drift. Among them, the EIC diagram is the chromatogram of the parent ion with a specific mass-to-charge ratio, that is, the extracted ion current chromatogram corresponding to each biomarker.

[0042] In addition, in addition to the salt interference in urine, phospholipids in blood may also interfere with the ionization process of biomarkers: when lecithin co-elutes with biomarkers, it may cause peak shape distortion characteristics such as shoulder peaks (such as the PAMG-1 peak splitting into double peaks) in the chromatographic peaks of biomarkers. Therefore, the chromatographic separation effect of biomarkers can be further evaluated through the chromatographic peak characteristics of biomarkers.

[0043] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining chromatographic separation completeness includes: Determine all merged chromatographic peaks according to the distribution of maximum points and inflection points in the extracted ion current chromatogram; the process of obtaining merged chromatographic peaks includes: in the extracted ion current chromatogram, take the nearest inflection point before and the nearest inflection point after each maximum point as the adjacent inflection points of each maximum point; take the local signal segment corresponding to the interval between the two adjacent inflection points corresponding to each maximum point as the initial chromatographic peak; merge the adjacent initial chromatographic peaks in time sequence to determine all merged chromatographic peaks. By merging chromatographic peaks, it is avoided that shoulder peaks are divided into two peaks when selecting chromatographic peaks, which affects the interference analysis of phospholipids in blood on the ionization process; Determine the corresponding drift distortion characteristic parameter according to the product of the time length and the absolute value of skewness of each merged chromatographic peak corresponding interval; determine the local separation eigenvalue of each merged chromatographic peak according to the ratio between the signal maximum value in each merged chromatographic peak and the drift distortion characteristic parameter; determine the chromatographic separation completeness of each biomarker in each detection according to the mean value of the local separation eigenvalues of all merged chromatographic peaks. The time length of the interval corresponding to the merged chromatographic peak here is the peak width, which can reflect the retention time drift characteristic of the chromatographic peak of the biomarker. The larger the corresponding peak width is, the more obvious the retention time drift characteristic is.

[0044] In addition, the absolute value of skewness represents the peak shape distortion characteristic of the merged chromatographic peak of the corresponding biomarker. The larger the corresponding absolute value of skewness is, the more obvious the peak shape distortion characteristic of the corresponding merged chromatographic peak is; therefore, when the drift distortion characteristic parameter obtained by the product of the time length of the interval corresponding to each merged chromatographic peak and the absolute value of skewness is larger, the corresponding interference is greater, and the chromatographic separation completeness is lower; and the signal maximum value in the merged chromatographic peak of the biomarker can reflect the ionization efficiency of the corresponding biomarker. Too low peak height is usually caused by matrix suppression. Therefore, the larger the overall signal maximum value in each merged chromatographic peak is, the more complete the corresponding chromatographic separation is, and the higher the corresponding chromatographic separation completeness is; in addition, when multiple peaks appear in the EIC map of the biomarker, it indicates that the target compound and matrix interferents (such as metabolites, salts) co-elute due to similar retention times, or peak splitting is caused by differences in adsorption-desorption kinetics on the chromatographic column. Therefore, further adjust the calculation result of the weighted mean value to make the characterization of chromatographic separation completeness more accurate.

[0045] In a specific implementation manner of the embodiment of the present invention, the acquisition process of chromatographic separation completeness is expressed by the formula: ; where is the chromatographic separation completeness of the th biomarker in the th detection; is the number of merged chromatographic peaks in the extracted ion chromatogram of the th biomarker in the th detection; is the signal maximum value of the th merged chromatographic peak in the extracted ion chromatogram of the th biomarker in the th detection; is the time length of the th merged chromatographic peak in the extracted ion chromatogram of the th biomarker in the th detection; is the The absolute skewness value of the th biomarker in the extracted ion current chromatogram of the th merged chromatographic peak; it should be noted that the calculation of skewness is a well-known technical means for those skilled in the art and will not be further defined and elaborated herein; The th biomarker in the extracted ion current chromatogram of the th merged chromatographic peak; The drift distortion characteristic parameter of the th biomarker in the extracted ion current chromatogram of the th merged chromatographic peak; The th biomarker in the extracted ion current chromatogram of the

[0046] Step S104: Determine the sample contamination interference degree for each detection according to the sample component richness, the suppression situation of the spectral peaks of various biomarkers in the mass spectrum, and the corresponding chromatographic separation completeness; perform premature rupture of membranes detection according to the sample contamination interference degree.

[0047] Premature rupture of membranes has multiple biomarkers. In addition to reflecting the separation characteristics of biomarkers in chromatographic data, it is also necessary to analyze the information of biomarkers in mass spectrometry data and evaluate the contamination interference degree in the current monitoring process. For different biomarkers, the stronger the chromatographic separation completeness, the more consistent the performance in mass spectrometry data should be with the actual performance of the sample. However, even if the chromatographic separation of biomarkers is complete, high-concentration components in the matrix (such as urea and creatinine in urine, phospholipids in blood) may still inhibit or enhance the ionization efficiency of biomarkers by competing for charges or changing the surface tension of droplets. For example, in electrospray ionization, phospholipids or high-concentration salts cover the surface of the ion source, reducing the ionization efficiency of biomarkers and resulting in signal attenuation. In mass spectrometry data, this situation is reflected in a significant reduction in the peak area corresponding to the biomarker and a weak main peak signal. Moreover, in samples with higher component richness, the inhibitory effect on the ionization efficiency of biomarkers may also be higher. Therefore, when the overall chromatographic separation completeness of various biomarkers is greater, the greater the sample component richness and the more significant the suppression of spectral peaks in the mass spectrum, the stronger the interference to the sample in this detection process and the greater the corresponding contamination interference degree.

[0048] Preferably, in some possible implementation manners of the embodiments of the present invention, the process of obtaining the sample contamination interference degree includes: The separation weighted interference degree is determined according to the product of the number of maxima corresponding to each biomarker in the mass-to-charge ratio range of the mass spectrum and the chromatographic separation completeness. First, the chromatographic separation completeness can characterize the credibility of the mass spectrometry data, so it acts as a weight. Specifically, when the chromatographic separation is complete, if contamination interference is still detected, such as ion suppression or overlapping peaks, it indicates that the contamination interference is more concealed and has a more serious impact. At this time, the influence of the interference is amplified by the chromatographic separation completeness. The number of mass spectrometry peak maxima can reflect the peak splitting or overlapping interference of biomarkers in the mass spectrum. The larger the corresponding mass spectrometry peak maximum, the more interference peaks of other interfering substances there are in the mass-to-charge ratio range corresponding to the biomarker in the mass spectrum, and the more significant the contamination interference. Therefore, after weighting by the chromatographic separation completeness, the separation weighted interference degree can more accurately characterize the contamination interference suffered by each biomarker.

[0049] The local change value of each mass-to-charge ratio is determined according to the mean value of the differences between the ion intensities of each mass-to-charge ratio and the ion intensities of the two adjacent mass-to-charge ratios before and after. The interval intensity deviation value corresponding to each biomarker is determined according to the mean value of the local change values of all mass-to-charge ratios in the mass-to-charge ratio range of the mass spectrum. The ionization suppression effect value corresponding to each biomarker is determined according to the product of the spectral peak area corresponding to each biomarker in the mass-to-charge ratio range of the mass spectrum and the interval intensity deviation value. The interval intensity deviation value measures the fluctuation of the ion intensity within the mass spectrometry peak. The smaller the overall local change value in the mass-to-charge ratio range of the corresponding biomarker, the smoother the peak shape, indicating that the signal of the biomarker may be uniformly suppressed or covered due to matrix interference. That is, when the interval intensity deviation value is smaller, the corresponding contamination interference is more serious. The spectral peak area reflects the degree of suppression of the ionization efficiency of the biomarker. The smaller the corresponding spectral peak area, the higher the degree of suppression of the ionization efficiency, and the more serious the contamination interference. Therefore, the smaller the ionization suppression effect value obtained by combining the spectral peak area and the interval intensity deviation value through multiplication, the more serious the corresponding contamination interference.

[0050] Combined with the corresponding correlation relationship, the reference interference degree of each biomarker is determined according to the ratio between the separation weighted interference degree and the ionization suppression effect value. The greater the reference interference degree, the more serious the interference suffered by the corresponding biomarker. Considering that the sample component richness characterizes the degree of interference from the dimension of the number of sample components, finally, positive correlation normalization is performed according to the product of the mean value of the reference interference degrees of all biomarkers and the sample component richness to determine the more accurate sample contamination interference degree for each detection.

[0051] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the sample contamination interference degree is expressed by the formula: ; where is the sample contamination interference degree of the th detection; is the sample composition richness of the th detection; is the chromatographic separation completeness of the th biomarker in the th detection; is the number of maximum values corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the th detection; is the separation weighted interference degree of the th biomarker in the th detection; is the peak area corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the th detection; is the interval intensity deviation value corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the th detection; is the ionization inhibition effect value of the th biomarker in the th detection; is the reference interference degree of the th biomarker in the th detection; is the hyperbolic tangent function, and the normalization method can be adjusted according to the specific implementation environment, such as linear normalization.

[0052] In a specific implementation manner of the embodiment of the present invention, the process of obtaining the interval intensity deviation value includes: ; where is the interval intensity deviation value corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the th detection; is the number of mass-to-charge ratios corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the th detection; is the absolute value of the difference between the ion intensity of the th mass-to-charge ratio and the ion intensity of the previous mass-to-charge ratio corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the th detection; is the absolute value of the difference between the ion intensity of the th mass-to-charge ratio and the ion intensity of the previous mass-to-charge ratio corresponding to the th biomarker in the mass-to-charge ratio interval of the mass spectrum in the The absolute value of the difference between the ion intensity of one mass-to-charge ratio and the ion intensity of the next mass-to-charge ratio; is the th local change value of the th mass-to-charge ratio in the mass-to-charge ratio range of the mass spectrum of the th biomarker; when there is no previous mass-to-charge ratio, use the corresponding as the local change value; when there is no subsequent mass-to-charge ratio, use the corresponding

[0053] Finally, calculate the pollution interference degree for each detection, and finally perform premature rupture of membranes detection based on the pollution interference degree; Preferably, in some possible implementation manners of the embodiments of the present invention, the process of performing premature rupture of membranes detection according to the sample pollution interference degree includes: When the sample pollution interference degree is greater than the preset interference threshold, optimize the mass spectrum detection process of the biomarker, and perform premature rupture of membranes detection based on the mass spectrum of the biomarker obtained from the optimized detection process; wherein, the process of the optimized detection process includes: during the sample pretreatment process, use solid-phase extraction to remove high-abundance interfering proteins, and add isotope-labeled internal standards to correct the extreme value effect; use hydrophilic interaction chromatography in the chromatographic conditions, or extend the gradient elution time to improve the separation degree of polar metabolites, and select a volatile buffer with a low ion intensity to reduce salt interference; adopt dynamic exclusion and multiple reaction monitoring modes in the mass spectrometry parameter adjustment to reduce non-target ion interference; increase the desolvation gas temperature to 500 °C to enhance the dissociation specificity of the target substance. In a specific implementation manner of the embodiments of the present invention, the preset interference threshold is set to 0.75, and it can be adjusted according to the specific implementation environment. The greater the sample pollution interference degree, the more serious the pollution of the sample, so the more necessary it is to optimize the mass spectrum detection process; after obtaining the mass spectrum of the biomarker obtained from the optimized detection process, analyze the premature rupture of membranes situation of the parturient through the biomarker in the corresponding mass spectrometry data. It should be noted that the process of analyzing the premature rupture of membranes situation of the parturient through the biomarker in the corresponding mass spectrometry data is a well-known technical means in the art and will not be further described herein.

[0054] In summary, an intelligent detection method for premature rupture of fetal membranes first analyzes the chromatographic data change characteristics during the detection process based on the ion intensity deviation and ion intensity change of the base peak chromatogram and total ion current chromatogram in time series, and combines the ion intensity change to comprehensively evaluate the sample component richness of the pad secretion in this detection, providing a basis for subsequent sample contamination characteristic analysis; then further analyzes the chromatographic data of each biomarker to evaluate the chromatographic separation completeness of the biomarker when interfered by other components, which can amplify the accuracy of the biomarker with higher chromatographic separation completeness in evaluating sample contamination characteristics and avoid the optimization of the detection process only targeting chromatography or mass spectrometry; finally, by analyzing the mass spectrometry data characteristics of the biomarker, combining the chromatographic separation completeness and sample component richness, calculates the sample contamination interference degree, and re-detects the sample with a higher contamination interference degree after optimizing the detection process, so as to improve the detection accuracy of the biomarker considering contamination interference.

[0055] The present application also provides an intelligent detection system for premature rupture of fetal membranes. Please refer to Figure 2 , which shows the structural diagram of an intelligent detection system for premature rupture of fetal membranes provided by an embodiment of the present invention. The system includes: a data acquisition and preprocessing module 201, a first determination module 202, a second determination module 203, and a premature rupture of fetal membranes detection module 204.

[0056] The data acquisition and preprocessing module 201 is used to separate the components of the physiological characteristics information during pregnancy and the corresponding pad secretion for each detection of the parturient to obtain the corresponding mass spectrogram, base peak chromatogram, total ion current chromatogram, and extracted ion current chromatogram of each biomarker. The first determination module 202 is used to determine the sample component richness for each detection according to the physiological characteristics information during pregnancy and the ion intensity deviation and ion intensity change of the base peak chromatogram and total ion current chromatogram in time series. The second determination module 203 is used to determine the chromatographic separation completeness of each biomarker in each detection according to the chromatographic peak shape distortion and signal intensity distribution of each biomarker in the extracted ion current chromatogram. The premature rupture of fetal membranes detection module 204 is used to determine the sample contamination interference degree for each detection according to the sample component richness, the suppression of spectral peaks of various biomarkers in the mass spectrogram, and the corresponding chromatographic separation completeness; perform premature rupture of fetal membranes detection according to the sample contamination interference degree.

[0057] It should be noted that for the system provided in the above embodiments, only the division of the above functional modules is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, an intelligent premature rupture of membranes detection system and an intelligent premature rupture of membranes detection method provided in the above embodiments belong to the same concept. For the specific implementation process, please refer to the method embodiments and will not be elaborated here.

[0058] An embodiment of the present application further provides a computer device. Please refer to Figure 3 , which shows a schematic structural diagram of a computer device provided in an embodiment of the present invention. The computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302. When the processor 302 executes the computer program 303, the computer device can execute any one of the intelligent premature rupture of membranes detection methods introduced above.

[0059] An embodiment of the present application further provides a computer program product. When the computer program product runs on a computer device, the computer device can execute any one of the intelligent premature rupture of membranes detection methods introduced above.

[0060] An embodiment of the present application further provides a computer-readable storage medium. Computer program code is stored in the computer-readable storage medium. When the computer program code runs on a computer device, the computer device can execute any one of the intelligent premature rupture of membranes detection methods introduced above.

[0061] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product, and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be elaborated here.

[0062] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. An intelligent detection method for premature rupture of fetal membranes, characterized in that, The method includes: After separating the components of the physiological characteristics information during pregnancy for each detection of the pregnant woman and the corresponding pad secretions, obtaining the corresponding mass spectrometry diagram, base peak diagram, total ion current diagram, and extracted ion current chromatogram of each biomarker; Determining the richness of the sample components for each detection according to the ion intensity deviation and ion intensity change of the physiological characteristics information during pregnancy, the base peak diagram, and the total ion current diagram in terms of time sequence; Determining the chromatographic separation completeness of each biomarker for each detection according to the chromatographic peak shape distortion and signal intensity distribution of each biomarker in the extracted ion current chromatogram; Determining the sample contamination interference degree for each detection according to the richness of the sample components, the suppression situation of the spectral peaks of various biomarkers in the mass spectrometry diagram, and the corresponding chromatographic separation completeness; performing premature rupture of membranes detection according to the sample contamination interference degree; The process of obtaining the richness of the sample components includes: With the help of a deep learning model, determining the corresponding secretion volume index according to all the physiological characteristics information during pregnancy of the pregnant woman for each detection; Determining the corresponding ion richness according to the ion intensity deviation between the total ion current diagram and the base peak diagram at each time point; Determining the ion fluctuation degree at each time point according to the relative deviation of the ion intensity change between each time point and the adjacent time point; Determining the adjustment coefficient for each time point according to the product of the ion richness and the ion fluctuation degree; taking the ratio between the adjustment coefficient and the corresponding ion intensity in the total ion current diagram at the corresponding time point as the weighting coefficient; Determining the richness of the sample components for each detection according to the product of the mean value of the weighting coefficients at all time points and the secretion volume index.

2. The intelligent detection method for premature rupture of fetal membranes according to claim 1, characterized in that, The process of obtaining the secretion volume index includes: Inputting all the physiological characteristics information during pregnancy of the pregnant woman for each detection into the trained fully connected neural network model, and outputting the secretion volume index for each detection.

3. The intelligent detection method for premature rupture of fetal membranes according to claim 1, characterized in that, The process of obtaining the ion richness includes: Normalizing the difference between the corresponding ion intensity in the total ion current diagram and the corresponding ion intensity in the base peak diagram at each time point to determine the ion richness at each time point.

4. The intelligent detection method for premature rupture of fetal membranes according to claim 1, characterized in that, The process of obtaining the ion fluctuation degree includes: Taking the difference between the derivative value of each time point in the total ion current diagram and the derivative value of the previous time point as the first reference difference; taking the difference between the derivative value of each time point in the total ion current diagram and the derivative value of the next time point as the second reference difference; determining the ion fluctuation degree at each time point according to the mean value between the first reference difference and the second reference difference.

5. The intelligent detection method for premature rupture of fetal membranes according to claim 1, wherein The process of obtaining the chromatographic separation completeness includes: Determining all the merged chromatographic peaks according to the distribution of the maximum points and inflection points in the extracted ion current chromatogram; Determining the corresponding drift distortion characteristic parameter according to the product of the time length and the absolute value of skewness of the corresponding interval of each merged chromatographic peak; Determine the local separation eigenvalue of each merged chromatographic peak according to the ratio between the signal maximum value in each merged chromatographic peak and the drift distortion characteristic parameter; determine the chromatographic separation completeness of each biomarker in each detection according to the mean value of the local separation eigenvalues of all merged chromatographic peaks.

6. The intelligent detection method for premature rupture of fetal membranes according to claim 5, wherein The process of obtaining the merged chromatographic peaks includes: In the extracted ion chromatogram, take the inflection point closest to each maximum point before and the inflection point closest to it after as the adjacent inflection points of each maximum point; take the local signal segment corresponding to the interval between the two adjacent inflection points corresponding to each maximum point as the initial chromatographic peak. Merge the adjacent initial chromatographic peaks in time sequence to determine all the merged chromatographic peaks.

7. The intelligent detection method for premature rupture of fetal membranes according to claim 1, wherein, The process of obtaining the sample contamination interference degree includes: Determine the corresponding separation weighted interference degree according to the product of the number of maximum values corresponding to each biomarker in the mass-to-charge ratio interval of the mass spectrum and the chromatographic separation completeness. Determine the local change value of each mass-to-charge ratio according to the mean value of the differences between the ion intensity of each mass-to-charge ratio and the ion intensities of the two adjacent mass-to-charge ratios before and after; determine the corresponding interval intensity deviation value according to the mean value of the local change values of all mass-to-charge ratios in the mass-to-charge ratio interval of the mass spectrum for each biomarker. Determine the corresponding ionization suppression effect value according to the product of the spectral peak area corresponding to each biomarker in the mass-to-charge ratio interval of the mass spectrum and the interval intensity deviation value. Determine the reference interference degree of each biomarker according to the ratio between the separation weighted interference degree and the ionization suppression effect value. Perform positive correlation normalization according to the product of the mean value of the reference interference degrees of all biomarkers and the sample component richness to determine the sample contamination interference degree of each detection.

8. The intelligent detection method for premature rupture of fetal membranes according to claim 1, characterized in that, The process of detecting premature rupture of membranes according to the sample contamination interference degree includes: When the sample contamination interference degree is greater than the preset interference threshold, optimize the mass spectrometry detection process of the biomarker, and perform premature rupture of membranes detection according to the mass spectrum of the biomarker obtained by the optimized detection process.

9. The intelligent detection method for premature rupture of fetal membranes according to claim 8, wherein The process of the optimized detection process includes: During sample pretreatment, use solid-phase extraction to remove high-abundance interfering proteins and add isotope-labeled internal standards; use hydrophilic interaction chromatography in chromatographic conditions and select a volatile buffer with low ionic strength; adopt dynamic exclusion and multiple reaction monitoring modes in mass spectrometry parameter adjustment; increase the desolvation gas temperature to 500 °C.

Images