A Down syndrome screening system based on multiple key indicators

Abstract

The present invention relates to the technical field of data analysis, and specifically discloses a Down syndrome screening system based on multiple key indicators. The system comprises: mining the risk distribution pattern of chromosomal abnormality by analyzing historical sample data, including maternal age, weight, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness; standardizing test data using principal component analysis, and grouping maternal characteristics using a clustering algorithm to determine a characteristic shift coefficient; establishing personalized indicator reference intervals based on factors such as fetal structural abnormalities, chromosomal abnormalities, and family genetic disease history; generating a personalized risk probability distribution by fusing individual characteristics with ultrasound measurement data; and calculating risk values ​​and generating a dynamically adjusted risk prediction curve based on real-time test data and the personalized reference intervals, thereby providing an accurate Down syndrome risk assessment basis for clinical decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a Down syndrome screening system based on multiple key indicators. Background Art

[0002] The Down syndrome screening process currently faces a series of interrelated technical challenges. First, individual differences among pregnant women lead to significant variation in screening indicators, necessitating the establishment of personalized reference ranges. Second, serum test data and ultrasound measurement data come from different devices, resulting in data inconsistencies and requiring standardization. Furthermore, factors such as maternal age, weight, and pregnancy history have complex influences on screening indicators, posing a significant challenge in accurately quantifying and correcting for these effects. Furthermore, screening indicators change dynamically with gestational age, posing another challenge in establishing a dynamic risk assessment model. Finally, in practical applications, translating these complex data analysis results into a concise and understandable risk stratification and providing timely high-risk alerts remains a core challenge for the entire screening system. These interconnected challenges together constitute a complex chain of technical challenges in Down syndrome screening. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention provides a Down syndrome screening system based on multiple key indicators, as follows:

[0004] A Down syndrome screening system based on multiple key indicators,

[0005] The first preprocessing module is used to obtain maternal age, weight difference, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness data from the historical sample database. Through statistical analysis, the distribution pattern of chromosomal abnormality risk under the combination of maternal age and ethnic differences is explored to obtain a preliminary risk distribution feature set.

[0006] The second preprocessing module is used to map the serum test data and ultrasound measurement data into a unified feature space to obtain a standardized indicator vector set, and then perform offset correction on the standardized indicator vector set. In combination with fetal structural abnormalities, chromosomal abnormalities, family genetic disease history, and gene mutations, a corrected personalized indicator reference interval set is determined;

[0007] The third preprocessing module is used to extract the distribution characteristics of serum PAPP-A concentration and free β-hCG concentration corresponding to maternal age effect, weight difference and gestational age dependence from the adjusted personalized index reference interval. The individual characteristics are integrated with the ultrasound measurement data through a model fusion method based on conditional probability to obtain a personalized risk probability distribution for chromosomal abnormalities.

[0008] The first screening module is used to obtain the pregnant woman's serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness from the real-time detection device based on the personalized risk probability distribution. If the test value exceeds the personalized reference range, the risk calculation value is calculated by combining the influence of maternal age and family genetic records to obtain the Down syndrome risk assessment curve;

[0009] The second screening module is used to fit the dynamic monitoring data within consecutive gestational weeks using the linear interpolation method based on the changing trend of the risk calculation value in the Down syndrome risk assessment curve, determine the dynamic distribution law of the risk probability under gestational age dependence, and obtain a dynamically adjusted risk prediction curve;

[0010] The third screening module is used to grade the risk probability in the dynamically adjusted risk prediction curve using a grading threshold determined based on clinical research data. If the risk probability is higher than the preset threshold, a high-risk warning signal is generated to determine the output classification of the screening result.

[0011] The first preprocessing module is specifically used for:

[0012] Historical sample data including maternal age, weight difference, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness were obtained to construct the original dataset;

[0013] Statistical analysis methods were used to calculate the correlation strength between maternal age and chromosomal abnormalities in the original data set to obtain the distribution characteristics of the effect of maternal age;

[0014] Performing cluster analysis on the ethnic background and chromosomal abnormalities in the original dataset to determine the distribution pattern of ethnic differences;

[0015] If the distribution characteristics of the maternal age effect exceed a preset threshold, a risk adjustment factor is calculated in combination with the serum PAPP-A concentration and the free β-hCG concentration to obtain an adjusted maternal age risk distribution;

[0016] Determine a comprehensive risk distribution characteristic by fusing the nuchal translucency thickness and the adjusted maternal age risk distribution through regression analysis;

[0017] Obtaining cross-statistical results of the comprehensive risk distribution characteristics and the pregnancy history records to determine the multidimensional distribution pattern of chromosomal abnormalities;

[0018] Generate feature set data according to the multidimensional distribution law and output a preliminary risk distribution feature set.

[0019] The second preprocessing module is specifically used for:

[0020] Acquiring serum test data and ultrasound measurement data, processing the serum test data and ultrasound measurement data using principal component analysis, mapping the serum test data and ultrasound measurement data to a unified feature space, and obtaining a standardized indicator vector set;

[0021] Calculate the variance of PAPP-A concentration and free β-hCG concentration for the serum test data to determine the range of measurement deviation caused by equipment differences;

[0022] If the variance of the PAPP-A concentration or the free β-hCG concentration exceeds a preset threshold, normalizing the serum test data to obtain an adjusted concentration data set;

[0023] Extracting main characteristic components using principal component analysis based on the adjusted concentration data set and the ultrasonic measurement data to obtain a feature matrix after dimensionality reduction;

[0024] Calculating the distribution distance of each sample in the feature space through the feature matrix, judging the measurement consistency between the samples, and obtaining the consistency judgment result;

[0025] According to the consistency judgment result, the samples are grouped using the K-means clustering algorithm to obtain a classified vector set;

[0026] For the classified vector set, the mean of the standardized index of each group is calculated to obtain a standardized index vector set.

[0027] The second preprocessing module is specifically used for:

[0028] Obtaining a standardized indicator vector set, and performing offset correction processing on the standardized indicator vector set using a least squares method to obtain a corrected preliminary indicator set;

[0029] Acquiring fetal structural abnormality data, extracting abnormality feature values ​​from the fetal structural abnormality data, and fusing the abnormality feature values ​​with the preliminary indicator set to obtain a first fused indicator set;

[0030] Acquiring chromosome abnormality data, extracting variation feature values ​​from the chromosome abnormality data, and performing weighted processing on the variation feature values ​​and the first fusion index set to obtain a second fusion index set;

[0031] Acquiring family genetic disease history data, extracting risk factors from the family genetic disease history data, and adjusting the second fusion indicator set using a linear regression method to obtain a third fusion indicator set;

[0032] Obtaining gene mutation data, extracting mutation site information from the gene mutation data, determining whether the mutation site exceeds a preset threshold, and if so, performing weighted calibration on the third fusion indicator set to obtain a fourth fusion indicator set;

[0033] A personalized reference interval set is determined based on the fourth fusion indicator set, and the degree of deviation of abnormal indicators is determined by comparing the fourth fusion indicator set with the personalized reference interval set to obtain a final corrected personalized indicator set.

[0034] The third preprocessing module is specifically used for:

[0035] Obtaining a set of corrected reference intervals, which includes serum PAPP-A concentration and free β-hCG concentration data corresponding to maternal age effects, weight differences, and gestational age dependence;

[0036] Based on the reference interval set, the distribution characteristics of serum PAPP-A and free β-hCG were extracted by statistical analysis, and their correlation parameters with maternal age effect, weight difference and gestational age dependence were determined;

[0037] Obtaining individual characteristics and ultrasound measurement data, integrating the distribution characteristics of the serum PAPP-A and free β-hCG through preprocessing to obtain a standardized feature set;

[0038] A conditional probability model is used to fuse the standardized feature set to calculate the joint probability distribution of individual characteristics and ultrasound measurements with chromosomal abnormalities;

[0039] Updating the conditional probability in the joint probability distribution by using a Bayesian method to obtain a preliminary risk probability distribution for chromosomal abnormalities;

[0040] Determine whether the preliminary risk probability exceeds a preset threshold; if so, adjust the fusion parameters of the conditional probability model based on the distribution characteristics to obtain a final personalized risk probability distribution;

[0041] According to the final personalized risk probability distribution, personalized risk probability distribution characteristics of chromosomal abnormalities are obtained.

[0042] The first screening module is specifically used for:

[0043] Obtain serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness data to obtain the original test values;

[0044] If the original detection value exceeds the preset reference interval, abnormal mark data is obtained;

[0045] Obtaining a maternal age influencing factor, and using a linear regression algorithm to calculate a preliminary risk adjustment value based on the abnormal marker data and the maternal age influencing factor;

[0046] Obtaining family genetic records, and performing secondary correction on the preliminary risk-adjusted value based on the family genetic records to obtain a comprehensive risk value;

[0047] Using a Gaussian distribution model, the comprehensive risk value is processed to generate personalized risk probability distribution data;

[0048] Draw a curve based on the personalized risk probability distribution data to obtain a Down syndrome risk assessment curve;

[0049] If the comprehensive risk value exceeds a preset threshold, the abnormal source of the original detection value is traced back according to the abnormal mark data to determine the key influencing factors.

[0050] The second screening module is specifically used for:

[0051] Obtain initial calculated values ​​for risk assessment within consecutive gestational weeks;

[0052] Using linear interpolation to perform data fitting on the initial calculated value to obtain a smoothed variation trend;

[0053] According to the changing trend, determining the distribution regularity characteristics of the risk probability under gestational age dependence;

[0054] If the distribution regularity characteristic deviates from a preset threshold, dynamically adjusting the risk probability to obtain an adjusted risk probability value;

[0055] Drawing a prediction curve based on the adjusted risk probability value;

[0056] Obtaining time series data of the prediction curve to determine the gestational age-dependent change trend;

[0057] Based on the changing trend, a dynamic monitoring update strategy is generated to obtain an optimized risk assessment result.

[0058] The third screening module is specifically used for:

[0059] Obtain clinical data, use statistical analysis methods to determine the initial parameters of the prediction model, and obtain the basic curve for risk prediction;

[0060] For the basic curve, a time series analysis method is used to perform dynamic adjustments to obtain an adjusted forecast curve and determine the distribution characteristics of the risk probability;

[0061] Extracting the risk probability from the adjusted prediction curve, and if the risk probability is higher than a preset threshold, generating a high-risk flag to determine a potential abnormal state;

[0062] Based on the high-risk identification, a preliminary classification of the screening results is obtained through signal mapping technology;

[0063] After obtaining the preliminary classification, the screening results are optimized using a decision tree algorithm to obtain the final output classification;

[0064] Comparing the output classification with the clinical data to obtain a deviation value of the classification result;

[0065] According to the deviation value, the classification threshold is optimized by adopting an iterative updating method, and the optimized risk prediction curve is obtained through a cyclic processing.

[0066] It also includes: a psychological assessment module, which is used to obtain the patient's physiological signal data and psychological assessment data in real time when the third screening module generates a high-risk prompt signal, generate a multi-dimensional psychological state feature vector based on the risk level, and determine whether to trigger a psychological intervention signal;

[0067] The psychological assessment module is specifically used to:

[0068] Collect patients' real-time physiological signals through wearable devices and extract characteristic parameters related to the autonomic nervous system;

[0069] Synchronously obtain psychological status feedback information submitted by patients and convert it into standardized psychological assessment parameters;

[0070] Comprehensively analyzing the physiological characteristic parameters, psychological assessment parameters and current risk level to generate a psychological stress index;

[0071] When the psychological stress index exceeds a preset range, a psychological intervention signal is triggered and a state vector containing risk-related features is generated.

[0072] It also includes: an intervention decision module, for matching a corresponding intervention plan from a multi-level intervention strategy library according to the state vector;

[0073] The intervention decision module is specifically used to:

[0074] Establish a multi-level intervention strategy that includes immediate consultation, self-directed training, and professional referral;

[0075] Generate matching parameters based on multiple dimensional features of the state vector and dynamically select the type of intervention strategy;

[0076] When a strong correlation is detected between the psychological stress index and the high risk level, real-time interactive intervention by professionals will be initiated first;

[0077] If the psychological stress index is within the adjustable range, customized training content and community support resources will be pushed to the patient terminal;

[0078] When it is monitored that the intervention response does not meet expectations, the family collaborative intervention mechanism is automatically triggered.

[0079] It also includes: an effect feedback module for updating the psychological state assessment model through dynamic monitoring of physiological signals and interactive feedback data;

[0080] The effect feedback module is specifically used for:

[0081] Continuously collect physiological signal change trend data during the intervention implementation cycle;

[0082] Obtain the patient's subjective experience feedback through the interactive interface and extract emotional state characteristics;

[0083] Conduct correlation trend analysis on physiological and psychological data, and automatically increase the intervention intensity level when it detects that the improvement rate is lower than expected;

[0084] The updated feature data are input into the adaptive model to optimize the psychological stress assessment parameters for the next stage.

[0085] The effect feedback module also includes a genetic counseling connection unit, which automatically generates a visual report integrating screening results and psychological assessment when the high-risk prompt signal and psychological intervention effect data meet the preset correlation conditions, and activates the genetic counseling service channel;

[0086] The genetic counseling connection unit is specifically used to:

[0087] Conduct spatiotemporal correlation analysis between the dynamic risk prediction curve and the trend of psychological stress changes;

[0088] When a persistent positive correlation between risk level and psychological stress is detected, a priority consultation channel is triggered;

[0089] The complete assessment record is transmitted to the designated genetic counseling terminal via a secure encryption protocol.

[0090] On the other hand, a Down syndrome screening method based on multiple key indicators is provided, including the following technical solution:

[0091] We collected data on maternal age, weight, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness from a historical sample database. Statistical analysis was used to explore the distribution of chromosomal abnormality risk under the influence of maternal age and ethnic differences, resulting in a preliminary risk distribution feature set.

[0092] The serum test data and ultrasound measurement data are mapped to a unified feature space to obtain a standardized indicator vector set. The standardized indicator vector set is then offset-corrected. Combined with fetal structural abnormalities, chromosomal abnormalities, family genetic disease history, and gene mutations, a corrected personalized indicator reference interval set is determined.

[0093] The distribution characteristics of serum PAPP-A and free β-hCG concentrations corresponding to maternal age, weight differences, and gestational age dependence were extracted from the adjusted personalized index reference intervals. Individual characteristics were fused with ultrasound measurement data using a conditional probability model fusion method to obtain a personalized risk probability distribution for chromosomal abnormalities.

[0094] Based on the personalized risk probability distribution, the pregnant woman's serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness are obtained from the real-time detection device. If the test value exceeds the personalized reference range, the risk calculation value is calculated by combining the influence of maternal age and family genetic records to obtain the Down syndrome risk assessment curve;

[0095] Based on the changing trend of the risk calculation value in the Down syndrome risk assessment curve, the linear interpolation method is used to fit the dynamic monitoring data within consecutive gestational weeks to determine the dynamic distribution law of risk probability under gestational age dependence and obtain the dynamically adjusted risk prediction curve.

[0096] The risk probability in the dynamically adjusted risk prediction curve is graded using a grading threshold determined based on clinical research data. If the risk probability is higher than the preset threshold, a high-risk warning signal is generated to determine the output classification of the screening result.

[0097] Compared with the existing technology, the Down syndrome screening system (method) based on multiple key indicators provided by the present invention has the following technical effects:

[0098] The present invention explores the distribution pattern of chromosomal abnormality risk by analyzing historical sample data, including maternal age, weight, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration and nuchal translucency thickness.

[0099] Principal component analysis was used to standardize test data, and clustering algorithms were used to group maternal characteristics and determine characteristic shift coefficients. Personalized reference intervals were established based on factors such as fetal structural abnormalities, chromosomal abnormalities, and family genetic disease history.

[0100] By integrating individual characteristics with ultrasound measurement data, a personalized risk probability distribution is generated. Ultimately, the present invention calculates the risk value and generates a dynamically adjusted risk prediction curve based on real-time test data and personalized reference intervals, providing an accurate Down syndrome risk assessment basis for clinical decision-making.

[0101] By integrating physiological and psychological bimodal data, a psychological assessment is initiated simultaneously when a high-risk screening result appears, preventing anxiety from impacting subsequent diagnosis and treatment decisions and improving clinical compliance with the screening system. A closed-loop correlation between intervention effects and physiological indicators is established, enabling real-time optimization of personalized psychological support plans and ensuring that intervention measures are dynamically aligned with the patient's actual condition.

[0102] Organically combine automated intervention resources with professional personnel services, retain the flexibility of manual intervention while ensuring response speed, and form a multi-dimensional health management chain of screening-psychology-genetics; through the spatiotemporal correlation analysis of psychological stress index and screening risk level, special cases that require special attention can be identified in advance, providing decision support for subsequent genetic counseling. BRIEF DESCRIPTION OF THE DRAWINGS

[0103] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments or the prior art.

[0104] Figure 1 Schematic diagram of the structure of a Down syndrome screening system based on multiple key indicators. DETAILED DESCRIPTION

[0105] The technical solutions in the embodiments of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0106] Example 1

[0107] Figure 1 FIG. 1 shows a schematic structural diagram of an embodiment of a Down syndrome screening system 100 based on multiple key indicators provided by the present invention. Figure 1 As shown, the system 100 includes: a first pre-processing module 110, a second pre-processing module 120, a third pre-processing module 130, a first screening module 140, a second screening module 150 and a third screening module 160;

[0108] The first preprocessing module 110 is configured to obtain maternal age, weight difference, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness data from a historical sample database, and to perform statistical analysis to explore the distribution pattern of chromosomal abnormality risk under the influence of maternal age and ethnic differences, thereby obtaining a preliminary risk distribution feature set;

[0109] The second preprocessing module 120 is used to map the serum test data and the ultrasound measurement data into a unified feature space to obtain a standardized indicator vector set, and perform offset correction processing on the standardized indicator vector set. In combination with fetal structural abnormalities, chromosomal abnormalities, family genetic disease history, and gene mutations, a corrected personalized indicator reference interval set is determined;

[0110] The third preprocessing module 130 is configured to extract the distribution characteristics of serum PAPP-A concentration and free β-hCG concentration corresponding to maternal age effect, weight difference, and gestational age dependence from the corrected personalized index reference interval set, and fuse the individual characteristics with the ultrasound measurement data through a model fusion method based on conditional probability to obtain a personalized risk probability distribution for chromosomal abnormalities;

[0111] The first screening module 140 is configured to obtain the pregnant woman's serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness from a real-time detection device based on the personalized risk probability distribution. If the test values ​​exceed the personalized reference interval, the risk calculation value is calculated by combining the influence of maternal age and family genetic records to obtain a Down syndrome risk assessment curve;

[0112] The second screening module 150 is used to fit the dynamic monitoring data within consecutive gestational weeks using the linear interpolation method based on the changing trend of the risk calculation value in the Down syndrome risk assessment curve, determine the dynamic distribution law of the risk probability under gestational age dependence, and obtain a dynamically adjusted risk prediction curve;

[0113] The third screening module 160 is used to grade the risk probability in the dynamically adjusted risk prediction curve using a grading threshold determined based on clinical research data. If the risk probability is higher than the preset threshold, a high-risk warning signal is generated to determine the output classification of the screening result.

[0114] In an optional manner, the first preprocessing module 110 is specifically configured to:

[0115] Historical sample data including maternal age, weight difference, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness data are obtained to construct an original data set; a statistical analysis method is used to calculate the correlation strength between maternal age and chromosomal abnormalities in the original data set to obtain the distribution characteristics of maternal age effects; a cluster analysis is performed on the ethnic background and chromosomal abnormalities in the original data set to determine the distribution pattern of racial differences; if the distribution characteristics of the maternal age effects exceed a preset threshold, a risk adjustment factor is calculated in combination with the serum PAPP-A concentration and free β-hCG concentration to obtain an adjusted maternal age risk distribution; the nuchal translucency thickness is integrated with the adjusted maternal age risk distribution through regression analysis to determine a comprehensive risk distribution characteristic; cross-statistical results of the comprehensive risk distribution characteristic and the pregnancy history records are obtained to determine the multidimensional distribution law of chromosomal abnormalities; feature set data is generated based on the multidimensional distribution law, and a preliminary risk distribution feature set is output.

[0116] Specifically, data on maternal age, weight variation, ethnicity, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness were extracted from a historical sample database. The data were first cleaned to remove missing and outliers. For example, ① the maternal age data contained records of women younger than 15 years or older than 50 years, which were considered outliers and removed. Next, the data were normalized using a standardization method, converting serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness to Z scores to ensure comparability of data across different dimensions. ② The mean of serum PAPP-A concentration was 8 MoM with a standard deviation of 2. After Z-score conversion, the values ​​ranged from -3 to 3. Subsequently, a multivariate regression model was used with maternal age and ethnicity as independent variables and the risk of chromosomal abnormality as the dependent variable for statistical analysis. ③ The model results showed that the risk of chromosomal abnormalities was significantly increased in women aged 35 years and older, with a hazard ratio (OR) of 5, while the OR for Asian women was 8. Furthermore, using cluster analysis, pregnant women were grouped by age and ethnic background to obtain risk distribution characteristics under different combinations. ④ Asian pregnant women over 35 years old had the highest risk of chromosomal abnormalities, with a risk value of 2, while African pregnant women under 30 years old had the lowest risk value of 7. Finally, a decision tree algorithm was used to further explore the risk distribution feature set and identify high-risk groups. ⑤ The decision tree model showed that pregnant women with serum PAPP-A concentrations below 5MoM and nuchal translucency thickness greater than 5 mm had a significantly increased risk of chromosomal abnormalities, with a risk value of 5. Through the above statistical analysis, the distribution pattern of chromosomal abnormality risk under the combination of maternal age and racial differences was preliminarily obtained, providing data support for subsequent clinical decision-making.

[0117] In an optional manner, the second preprocessing module 120 is specifically configured to:

[0118] Acquire serum test data and ultrasound measurement data, process the serum test data and ultrasound measurement data using principal component analysis, map the serum test data and ultrasound measurement data to a unified feature space, and obtain a standardized indicator vector set; for the serum test data, calculate the variance of PAPP-A concentration and free β-hCG concentration, and determine the measurement deviation range caused by equipment differences; if the variance of the PAPP-A concentration or free β-hCG concentration exceeds a preset threshold, normalize the serum test data to obtain an adjusted concentration data set; extract the main feature components based on the adjusted concentration data set and the ultrasound measurement data using principal component analysis to obtain a feature matrix after dimensionality reduction; calculate the distribution distance of each sample in the feature space using the feature matrix, judge the measurement consistency between samples, and obtain a consistency judgment result; based on the consistency judgment result, group the samples using a K-means clustering algorithm to obtain a classified vector set; for the classified vector set, calculate the mean of the standardized index of each group to obtain a standardized indicator vector set; obtain a standardized indicator vector The method comprises the following steps: obtaining fetal structural abnormality data, extracting abnormal characteristic values ​​from the fetal structural abnormality data, and fusing the abnormal characteristic values ​​with the preliminary indicator set to obtain a first fusion indicator set; obtaining chromosomal abnormality data, extracting variation characteristic values ​​from the chromosomal abnormality data, and weighting the variation characteristic values ​​with the first fusion indicator set to obtain a second fusion indicator set; obtaining family genetic disease history data, extracting risk factors from the family genetic disease history data, and adjusting the second fusion indicator set using a linear regression method to obtain a third fusion indicator set; obtaining gene mutation data, extracting mutation site information from the gene mutation data, and determining whether the mutation site exceeds a preset threshold. If so, weighting and calibrating the third fusion indicator set to obtain a fourth fusion indicator set; determining a personalized reference interval set based on the fourth fusion indicator set, and determining the degree of deviation of the abnormal indicators by comparing the fourth fusion indicator set with the personalized reference interval set to obtain a final corrected personalized indicator set.

[0119] Specifically, during the measurement of serum PAPP-A and free β-hCG concentrations, data inconsistencies may occur due to differences in testing methods or equipment. Therefore, principal component analysis (PCA) is first used to reduce the dimensionality of the serum and ultrasound data. Consider a set of 100 serum test data samples, each containing two features: PAPP-A and free β-hCG concentrations, and 50 ultrasound measurement data samples, each containing two features: fetal head circumference and abdominal circumference. First, these data are merged into a 150×4 matrix and then normalized so that each feature has a mean of 0 and a standard deviation of 1. Next, the covariance matrix is ​​calculated and eigenvalue decomposition is performed to obtain eigenvalues ​​and eigenvectors. Assuming that the cumulative contribution of the first two principal components reaches 90%, these two principal components are selected as the new feature space. The original data are projected onto these two principal components to obtain a 150×2 set of normalized indicator vectors.

[0120] For example, the projection value of the first sample on the first principal component is 85, and the projection value on the second principal component is -45. In this way, the serum test data and ultrasound measurement data are mapped to a unified feature space, which solves the problem of inconsistent measurements and provides a unified standardized indicator for subsequent risk assessment.

[0121] Specifically, the standardized indicator vector set is first offset-corrected, and the least squares method is used to fit the data. Suppose there is a set of fetal structural abnormality indicator vectors, including head circumference, abdominal circumference, and femur length, which are standardized to [8, 2, 9], respectively. Least squares fitting yields correction coefficients of [95, 05, 98], and the corrected indicator vector is [76, 26, 88]. Next, considering chromosomal abnormality data, such as the probability of chromosomal abnormality in trisomy 21 being 0.1, the corrected probability is calculated using Bayesian theorem to be 0.15. Furthermore, considering family genetic history, such as a family history of congenital heart disease, the genetic risk coefficient is 3. Using the weighted average method, the corrected indicator vector is adjusted to [76*3, 26*3, 88*3], resulting in [988, 638, 144]. Finally, combined with gene mutation data, for example, if the risk factor for a gene mutation is 2, the corrected indicator vector is further adjusted to [988*2,638*2,144*2] using a multiplicative model, resulting in [186,966,373]. Ultimately, the corrected personalized indicator reference interval set is determined to be [186,966,373] for subsequent fetal health assessment and diagnosis.

[0122] It should be noted that the second preprocessing module 120 is also used to: group the individual characteristics of pregnant women through a clustering algorithm based on the correlation between the influence of maternal age, weight differences and pregnancy history records and screening indicators in the standardized indicator vector set, determine the distribution offset of each group of nuchal translucency thickness and serum test data, and obtain the grouped feature offset coefficient set. Obtain an indicator vector set, which includes the correlation coefficients between maternal age influence, weight difference and pregnancy history records and screening indicators; standardize the indicator vector set to obtain an initial correlation data set; based on the initial correlation data set, use the K-means clustering algorithm to group the pregnant women's data according to individual characteristics to obtain a clustering grouping result set; for the clustering grouping result set, calculate the data distribution offset of the nuchal translucency in each group to obtain a nuchal translucency offset set; for the clustering grouping result set, calculate the distribution offset of the serum test data in each group to obtain a serum test offset set; based on the nuchal translucency offset set and the serum test offset set, judge the characteristic change trend of the distribution offset to obtain a characteristic offset coefficient set; obtain the characteristic offset coefficient set, and if the characteristic offset coefficient exceeds a preset threshold, adjust the clustering grouping parameters, recalculate the distribution offset, and obtain an optimized characteristic offset coefficient set; based on the optimized characteristic offset coefficient set, determine the association pattern between the individual characteristics of each group of pregnant women and the screening indicators to obtain a final grouping feature set.

[0123] Specifically, within the standardized indicator vector set, correlation analysis was first performed for maternal age, weight difference, and pregnancy history. Pearson correlation coefficients were used to calculate the correlation between each indicator and the screening indicator. For example, the correlation coefficient between maternal age and serum test data was 45, the correlation coefficient between weight difference and nuchal translucency thickness was 32, and the correlation coefficient between pregnancy history and screening indicators was 28. Next, the K-means clustering algorithm was used to group individual maternal characteristics, setting the number of clusters to 3. The similarity between samples was calculated using the Euclidean distance. After 100 iterations, three cluster centers were obtained: [5, 6, 7], [3, 4, 5], and [8, 9, 0]. Then, the distribution shift of nuchal translucency thickness and serum test data within each cluster was calculated. Using the Kolmogorov-Smirnov test, the shift was 12 for the first cluster, 0.8 for the second, and 15 for the third. Finally, a set of characteristic shift coefficients was calculated based on the shifts: 2 for the first cluster, 9 for the second, and 5 for the third. These coefficients were used to formulate personalized screening strategies.

[0124] In an optional manner, the third preprocessing module 130 is specifically configured to:

[0125] Obtain a corrected reference interval set, the reference interval set including serum PAPP-A concentration and free β-hCG concentration data corresponding to maternal age effect, weight difference, and gestational age dependence; extract the distribution characteristics of serum PAPP-A and free β-hCG through statistical analysis based on the reference interval set, and determine their correlation parameters with maternal age effect, weight difference, and gestational age dependence; obtain individual characteristics and ultrasound measurement data, integrate the distribution characteristics of serum PAPP-A and free β-hCG through preprocessing, and obtain a standardized feature set; use a conditional probability model to fuse the standardized feature set, and calculate the joint probability distribution of individual characteristics, ultrasound measurement, and chromosomal abnormalities; update the conditional probability in the joint probability distribution through a Bayesian method to obtain a preliminary risk probability distribution for chromosomal abnormalities; determine whether the preliminary risk probability exceeds a preset threshold, and if so, adjust the fusion parameters of the conditional probability model based on the distribution characteristics to obtain a final personalized risk probability distribution; and obtain personalized risk probability distribution characteristics for chromosomal abnormalities based on the final personalized risk probability distribution.

[0126] Specifically, from the adjusted personalized index reference interval set, the distribution characteristics of serum PAPP-A and free β-hCG concentrations corresponding to maternal age, weight differences, and gestational age are first extracted. For example, for a pregnant woman aged 30 years, the reference interval for serum PAPP-A concentration is 5-5 MoM, and for free β-hCG concentration is 8-2 MoM. For a pregnant woman weighing 70 kg, the PAPP-A concentration is adjusted to 6-4 MoM, and for free β-hCG concentration is 7-1 MoM. For a pregnant woman at 12 weeks of gestation, the PAPP-A concentration is further adjusted to 7-3 MoM, and for free β-hCG concentration is 9-3 MoM. These adjustments are based on statistical analysis of extensive clinical data to ensure the accuracy of the reference intervals. Next, individual characteristics are fused with ultrasound measurement data using a model fusion method based on conditional probability. For example, for a 35-year-old woman weighing 65 kg at 11 weeks' gestation, ultrasound measurements include a fetal nuchal translucency thickness of 5 mm. Combined with serum PAPP-A concentrations of 8 MoM and free β-hCG concentrations of 5 MoM, the Bayesian theorem is used to calculate the risk probability of a chromosomal abnormality. The algorithm is: P(chromosomal abnormality|data) = P(data|chromosomal abnormality) * P(chromosomal abnormality) / P(data), where P(data|chromosomal abnormality) is estimated using historical case data, P(chromosomal abnormality) is the population baseline probability, and P(data) is the sum of the data distributions under normal and abnormal conditions. Ultimately, a personalized risk probability distribution is obtained for each woman, such as a 1:250 risk for trisomy 21 and a 1:1000 risk for trisomy 18, providing a precise basis for clinical decision-making.

[0127] It should be noted that the third preprocessing module 130 is further configured to: extract the distribution characteristics of serum PAPP-A and free β-hCG through statistical analysis based on the serum PAPP-A concentration and free β-hCG concentration data corresponding to maternal age-related weight differences and gestational age-dependent weight differences; use a conditional probability model to fuse individual characteristics and ultrasound measurement data to determine whether the preliminary risk probability exceeds a threshold; and adjust the fusion parameters of the conditional probability model based on the distribution characteristics to obtain a final personalized risk probability distribution for chromosomal abnormalities. Serum PAPP-A and free β-hCG concentration data corresponding to maternal age, weight and gestational age are obtained, and their distribution characteristics are extracted through statistical methods to obtain a standardized distribution parameter set; a conditional probability model is used to fuse individual characteristics and ultrasound measurement data, and combined with the standardized distribution parameter set, a joint probability distribution is calculated to obtain a preliminary probability estimate; a Bayesian method is used to update the conditional probability in the joint probability distribution, and a preliminary risk probability value is determined in combination with the distribution characteristics; it is determined whether the preliminary risk probability value exceeds a preset threshold, and if so, the fusion parameters are adjusted to obtain optimized conditional probability model parameters; based on the optimized conditional probability model parameters, the individual characteristics and ultrasound measurement data are re-fused, and the adjusted joint probability distribution is calculated to obtain a final risk probability distribution; based on the final risk probability distribution, the probability distribution characteristics of chromosomal abnormalities are extracted to determine a personalized risk feature set; by analyzing the personalized risk feature set, the distribution law related to chromosomal abnormalities is obtained to obtain final business output data.

[0128] Specifically, when analyzing the effects of maternal age, weight, and gestational age on serum PAPP-A and free β-hCG concentrations, we first extracted distributional characteristics through big data analysis. For example, for a 28-year-old woman, the mean of the serum PAPP-A concentration distribution was 8 MoM with a standard deviation of 2; the mean of the free β-hCG concentration was 1 MoM with a standard deviation of 3. For a 60-kg woman, the mean of the PAPP-A concentration distribution was adjusted to 9 MoM with a standard deviation of 15; the mean of the free β-hCG concentration was adjusted to 0 MoM with a standard deviation of 25. For a 10-week gestational age woman, the mean of the PAPP-A concentration distribution was further adjusted to 0 MoM with a standard deviation of 1; the mean of the free β-hCG concentration was adjusted to 2 MoM with a standard deviation of 2. These distributional characteristics were fitted using a Gaussian distribution model to ensure data accuracy and reliability. Next, a conditional probability model was used to integrate individual characteristics with the ultrasound measurement data. For example, for a 32-year-old woman weighing 58 kg at 9 weeks' gestation, ultrasound data revealed fetal nasal bone absence. Combined with a serum PAPP-A concentration of 7 MoM and a free β-hCG concentration of 3 MoM, the conditional probability formula P(chromosomal abnormality|data) = P(data|chromosomal abnormality) * P(chromosomal abnormality) / P(data) was used to calculate the probability. Here, P(data|chromosomal abnormality) is estimated to be 0.5 based on historical case data, P(chromosomal abnormality) is the population baseline probability of 0.1, and P(data) is the sum of the data distribution under normal and abnormal conditions, 0.6. Preliminary calculations indicate a chromosomal abnormality risk probability of 0.083, exceeding the pre-set threshold of 0.05. Based on the distribution characteristics, the fusion parameters of the conditional probability model were adjusted, correcting P(data|chromosomal abnormality) to 0.6. After recalculation, the final risk probability was 0.1, providing a more accurate basis for clinical decision-making.

[0129] In an optional manner, the first screening module 140 is specifically configured to:

[0130] Serum PAPP-A concentration, free β-hCG concentration and nuchal translucency thickness data are obtained to obtain the original test value; if the original test value exceeds the preset reference interval, abnormal marker data is obtained; the maternal age influencing factor is obtained, and a linear regression algorithm is used to calculate the preliminary risk adjustment value based on the abnormal marker data and the maternal age influencing factor; family genetic records are obtained, and the preliminary risk adjustment value is secondary corrected based on the family genetic records to obtain a comprehensive risk value; the comprehensive risk value is processed using a Gaussian distribution model to generate personalized risk probability distribution data; a curve is drawn based on the personalized risk probability distribution data to obtain a Down syndrome risk assessment curve; if the comprehensive risk value exceeds the preset threshold, the abnormal source of the original test value is traced based on the abnormal marker data, and the key influencing factors are determined.

[0131] Specifically, the real-time testing device first acquires biomarker data such as the pregnant woman's serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness. For example, a pregnant woman's serum PAPP-A concentration is 8 MoM (multiple of the median), free β-hCG concentration is 2 MoM, and nuchal translucency thickness is 5 mm. The system then compares these values ​​with personalized reference intervals. If the values ​​exceed these ranges, the system further calculates the risk based on maternal age and family genetic history. For example, if the pregnant woman is 35 years old and has a family history of Down syndrome, the system uses a Bayesian algorithm to adjust the risk probability based on these factors. The specific calculation process is: the baseline risk based on maternal age is 1 / 250, the family genetic history increases the risk factor by 5 times, abnormal serum PAPP-A and free β-hCG concentrations contribute risk factors of 2 and 3, respectively, and abnormal nuchal translucency thickness contributes a risk factor of 4. Using a multiplicative model, the final risk value is 1 / 250 × 5 × 2 × 3 × 4 = 1 / 96. The system plots this risk value onto the Down syndrome risk assessment curve to form a personalized risk assessment report, providing a basis for clinical decision-making.

[0132] In an optional manner, the second screening module is specifically configured to:

[0133] Obtain initial calculated values ​​for risk assessment within consecutive gestational weeks; perform data fitting on the initial calculated values ​​using linear interpolation to obtain a smoothed trend of change; determine the distribution regularity characteristics of the risk probability under gestational age dependence based on the trend of change; if the distribution regularity characteristics deviate from a preset threshold, dynamically adjust the risk probability to obtain an adjusted risk probability value; draw a prediction curve based on the adjusted risk probability value; obtain time series data of the prediction curve to determine the trend of change under gestational age dependence; generate a dynamic monitoring update strategy based on the trend of change to obtain an optimized risk assessment result.

[0134] Specifically, Down syndrome risk assessment first requires dynamic monitoring data for pregnant women at different gestational ages. For example, the calculated risk at 12 weeks of gestation is 1:500, and at 16 weeks of gestation it is 1:300. These data points can be fitted using linear interpolation. For example, at 14 weeks of gestation, the calculated risk is 1:400. This is calculated using the linear interpolation formula (y = y1 + (x - x1) * (y2 - y1) / (x2 - x1)), where x1 = 12, y1 = 500, x2 = 16, y2 = 300, and x = 14. Substituting this into the formula yields y = 400. Next, the dynamic distribution of risk probability as it depends on gestational age is analyzed. For example, between 12 and 16 weeks of gestation, the risk probability shows a linear downward trend, decreasing by approximately 50% with each additional week. Based on this pattern, the risk prediction curve can be dynamically adjusted. For example, at 18 weeks of gestation, the calculated risk is estimated to be 1:200. This is achieved by continuing to apply linear interpolation, combining known data points and trend predictions. Ultimately, through information technology processing, a smooth risk prediction curve can be generated, providing a scientific basis for clinical decision-making.

[0135] In an optional manner, the third screening module 160 is specifically configured to:

[0136] Acquire clinical data, use statistical analysis methods to determine the initial parameters of the prediction model, and obtain a basic curve for risk prediction; use time series analysis methods to dynamically adjust the basic curve to obtain an adjusted prediction curve, and determine the distribution characteristics of the risk probability; extract the risk probability from the adjusted prediction curve, and if the risk probability is higher than a preset threshold, generate a high-risk mark to determine the potential abnormal state; based on the high-risk mark, obtain a preliminary classification of the screening results through signal mapping technology; after obtaining the preliminary classification, use a decision tree algorithm to optimize the screening results to obtain the final output classification; compare the output classification with the clinical data to obtain the deviation value of the classification result; based on the deviation value, use an iterative update method to optimize the grading threshold, and obtain the optimized risk prediction curve through loop processing.

[0137] Specifically, based on clinical research data, a logistic regression model is first used to dynamically adjust a patient's risk probability. The model inputs include multiple characteristic variables such as age, gender, blood pressure, and blood glucose. Model parameters are fitted using maximum likelihood estimation. For example, the regression coefficient for age is 15, and the regression coefficient for systolic blood pressure is 0.8. The final output risk probability ranges from 0 to 1. Next, grading thresholds are set according to clinical guidelines, such as 2 for low risk, 5 for medium risk, and 8 for high risk. The adjusted risk prediction curve is then graded. If a patient's risk probability is 85, exceeding the preset high-risk threshold, the system automatically generates a high-risk alert signal. A decision tree algorithm is then used to categorize the screening results. For example, if the risk probability is greater than 8 and the age is over 65, the output is classified as "High-risk population, immediate intervention recommended." Throughout this process, a machine learning model and preset thresholds are used to automatically grade risk probabilities and intelligently classify screening results, ensuring the accuracy and operability of the analysis results.

[0138] The technical solution of this embodiment mines the distribution pattern of chromosomal abnormality risk by analyzing historical sample data, including maternal age, weight, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness. The test data are standardized using principal component analysis, and the characteristics of the pregnant women are grouped using a clustering algorithm to determine the characteristic deviation coefficient. Personalized indicator reference intervals are established by combining factors such as fetal structural abnormalities, chromosomal abnormalities, and family genetic disease history. A personalized risk probability distribution is generated by fusing individual characteristics with ultrasound measurement data. Ultimately, the technical solution of this embodiment calculates the risk value and generates a dynamically adjusted risk prediction curve based on real-time test data and personalized reference intervals, providing an accurate basis for Down syndrome risk assessment for clinical decision-making.

[0139] Example 2

[0140] Based on Example 1, the present invention provides an embodiment of a Down syndrome screening method based on multiple key indicators, the method comprising the following steps:

[0141] S1. Obtain maternal age, weight, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness data from a historical sample database. Statistical analysis is then performed to explore the distribution patterns of chromosomal abnormality risk under the influence of maternal age and ethnic differences, yielding a preliminary risk distribution feature set.

[0142] S2. Map the serum test data and ultrasound measurement data to a unified feature space to obtain a standardized indicator vector set, and perform offset correction on the standardized indicator vector set. Combined with fetal structural abnormalities, chromosomal abnormalities, family genetic disease history, and gene mutations, determine a corrected personalized indicator reference interval set;

[0143] S3. Extract the distribution characteristics of serum PAPP-A concentration and free β-hCG concentration corresponding to maternal age, weight difference, and gestational age dependence from the adjusted personalized index reference interval. Use a conditional probability-based model fusion method to fuse individual characteristics with ultrasound measurement data to obtain a personalized risk probability distribution for chromosomal abnormalities.

[0144] S4. Based on the personalized risk probability distribution, the pregnant woman's serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness are obtained from the real-time detection device. If the test value exceeds the personalized reference range, the risk calculation value is calculated by combining the influence of maternal age and family genetic records to obtain the Down syndrome risk assessment curve;

[0145] S5. Based on the changing trend of the risk calculation value in the Down syndrome risk assessment curve, the linear interpolation method is used to fit the dynamic monitoring data within consecutive gestational weeks to determine the dynamic distribution law of the risk probability under gestational age dependence, and obtain the dynamically adjusted risk prediction curve;

[0146] S6. Use the grading threshold determined based on clinical research data to grade the risk probability in the dynamically adjusted risk prediction curve. If the risk probability is higher than the preset threshold, a high-risk warning signal is generated to determine the output classification of the screening result.

[0147] It should be noted that the beneficial effects of the Down syndrome screening method based on multiple key indicators provided in the above embodiment are the same as the beneficial effects of the above-mentioned Down syndrome screening system 100 based on multiple key indicators, and will not be repeated here.

[0148] Example 3

[0149] Based on Example 1, the present invention further includes a psychological assessment module, an intervention decision module, and an effect feedback module.

[0150] The psychological assessment module collects real-time physiological data, such as electrocardiogram (ECG) signals, from wearable devices (such as smart wristbands). Combined with questionnaire responses submitted via mobile devices, it extracts comprehensive characteristics reflecting psychological status. The system's built-in assessment algorithm integrates physiological signal characteristics (such as heart rate variability patterns) with standardized psychological scores to generate a dynamic psychological stress index. When the index exceeds a set threshold, a graded intervention mechanism is triggered.

[0151] The intervention decision-making module selects intervention measures of appropriate intensity from a strategy library based on a combination of risk level and psychological stress characteristics. For high-risk cases, the system automatically connects with online experts for video counseling. For patients experiencing moderate stress, the system provides meditation training courses and access to a community of patients. If the system detects that a patient has not completed an intervention task on time, a reminder notification is sent to a pre-determined family contact.

[0152] The effectiveness feedback module continuously tracks physiological signal changes and patients' daily mood logs to assess the effectiveness of interventions. If improvement trends fall short of expectations, the system automatically upgrades the intervention intensity, for example, switching from self-training to manual intervention. The genetic counseling connection unit generates interactive reports with medical explanations when screening reveals both risk and psychological stress levels are exceeded, and schedules a remote consultation with a professional genetic counselor.

[0153] The above description is only an illustration of the preferred embodiments of the present invention and the technical principles used. The above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A Down syndrome screening system based on multiple key indicators, characterized in that: include: The first preprocessing module is used to obtain maternal age, weight difference, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness data from the historical sample database. Through statistical analysis, the distribution pattern of chromosomal abnormality risk under the combination of maternal age and ethnic differences is explored to obtain a preliminary risk distribution feature set. The second preprocessing module is used to map the serum test data and ultrasound measurement data into a unified feature space to obtain a standardized indicator vector set, and then perform offset correction on the standardized indicator vector set. In combination with fetal structural abnormalities, chromosomal abnormalities, family genetic disease history, and gene mutations, a corrected personalized indicator reference interval set is determined; The third preprocessing module is specifically used to: Obtaining a set of corrected reference intervals, which includes serum PAPP-A concentration and free β-hCG concentration data corresponding to maternal age effects, weight differences, and gestational age dependence; Based on the reference interval set, the distribution characteristics of serum PAPP-A and free β-hCG were extracted by statistical analysis, and their correlation parameters with maternal age effect, weight difference and gestational age dependence were determined; Obtaining individual characteristics and ultrasound measurement data, integrating the distribution characteristics of the serum PAPP-A and free β-hCG through preprocessing to obtain a standardized feature set; A conditional probability model is used to fuse the standardized feature set to calculate the joint probability distribution of individual characteristics and ultrasound measurements with chromosomal abnormalities; Updating the conditional probability in the joint probability distribution by using a Bayesian method to obtain a preliminary risk probability distribution for chromosomal abnormalities; Determine whether the preliminary risk probability exceeds a preset threshold; if so, adjust the fusion parameters of the conditional probability model based on the distribution characteristics to obtain a final personalized risk probability distribution; Obtaining personalized risk probability distribution characteristics of chromosomal abnormalities according to the final personalized risk probability distribution; The first screening module is used to obtain the pregnant woman's serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness from the real-time detection device based on the personalized risk probability distribution. If the test value exceeds the personalized reference range, the risk calculation value is calculated by combining the influence of maternal age and family genetic records to obtain the Down syndrome risk assessment curve; The second screening module is used to fit the dynamic monitoring data within consecutive gestational weeks using the linear interpolation method based on the changing trend of the risk calculation value in the Down syndrome risk assessment curve, determine the dynamic distribution law of the risk probability under gestational age dependence, and obtain a dynamically adjusted risk prediction curve; The third screening module is used to grade the risk probability in the dynamically adjusted risk prediction curve using a grading threshold determined based on clinical research data. If the risk probability is higher than the preset threshold, a high-risk warning signal is generated to determine the output classification of the screening result.

2. The Down syndrome screening system based on multiple key indicators according to claim 1, characterized in that: The first preprocessing module is specifically used for: Historical sample data including maternal age, weight difference, ethnic background, pregnancy history, serum PAPP-A concentration, free β-hCG concentration, and nuchal translucency thickness were obtained to construct the original dataset; Statistical analysis methods were used to calculate the correlation strength between maternal age and chromosomal abnormalities in the original data set to obtain the distribution characteristics of the effect of maternal age; Performing cluster analysis on the ethnic background and chromosomal abnormalities in the original dataset to determine the distribution pattern of ethnic differences; If the distribution characteristics of the maternal age effect exceed a preset threshold, a risk adjustment factor is calculated in combination with the serum PAPP-A concentration and the free β-hCG concentration to obtain an adjusted maternal age risk distribution; Determine a comprehensive risk distribution characteristic by fusing the nuchal translucency thickness and the adjusted maternal age risk distribution through regression analysis; Obtaining cross-statistical results of the comprehensive risk distribution characteristics and the pregnancy history records to determine the multidimensional distribution pattern of chromosomal abnormalities; Generate feature set data according to the multidimensional distribution law and output a preliminary risk distribution feature set.

3. The Down syndrome screening system based on multiple key indicators according to claim 1, characterized in that: The second preprocessing module is specifically used for: Acquiring serum test data and ultrasound measurement data, processing the serum test data and ultrasound measurement data using principal component analysis, mapping the serum test data and ultrasound measurement data to a unified feature space, and obtaining a standardized indicator vector set; Calculate the variance of PAPP-A concentration and free β-hCG concentration for the serum test data to determine the range of measurement deviation caused by equipment differences; If the variance of the PAPP-A concentration or the free β-hCG concentration exceeds a preset threshold, normalizing the serum test data to obtain an adjusted concentration data set; Extracting main characteristic components using principal component analysis based on the adjusted concentration data set and the ultrasonic measurement data to obtain a feature matrix after dimensionality reduction; Calculating the distribution distance of each sample in the feature space through the feature matrix, judging the measurement consistency between the samples, and obtaining the consistency judgment result; According to the consistency judgment result, the samples are grouped using the K-means clustering algorithm to obtain a classified vector set; For the classified vector set, the mean of the standardized index of each group is calculated to obtain a standardized index vector set.

4. The Down syndrome screening system based on multiple key indicators according to claim 1, characterized in that: The second preprocessing module is specifically used for: Obtaining a standardized indicator vector set, and performing offset correction processing on the standardized indicator vector set using a least squares method to obtain a corrected preliminary indicator set; Acquiring fetal structural abnormality data, extracting abnormality feature values ​​from the fetal structural abnormality data, and fusing the abnormality feature values ​​with the preliminary indicator set to obtain a first fused indicator set; Acquiring chromosome abnormality data, extracting variation feature values ​​from the chromosome abnormality data, and performing weighted processing on the variation feature values ​​and the first fusion index set to obtain a second fusion index set; Acquiring family genetic disease history data, extracting risk factors from the family genetic disease history data, and adjusting the second fusion indicator set using a linear regression method to obtain a third fusion indicator set; Obtaining gene mutation data, extracting mutation site information from the gene mutation data, determining whether the mutation site exceeds a preset threshold, and if so, performing weighted calibration on the third fusion indicator set to obtain a fourth fusion indicator set; A personalized reference interval set is determined based on the fourth fusion indicator set, and the degree of deviation of abnormal indicators is determined by comparing the fourth fusion indicator set with the personalized reference interval set to obtain a final corrected personalized indicator set.

5. The Down syndrome screening system based on multiple key indicators according to claim 1, characterized in that: The second screening module is specifically used for: Obtain initial calculated values ​​for risk assessment within consecutive gestational weeks; Using linear interpolation to perform data fitting on the initial calculated value to obtain a smoothed variation trend; According to the changing trend, determining the distribution regularity characteristics of the risk probability under gestational age dependence; If the distribution regularity characteristic deviates from a preset threshold, dynamically adjusting the risk probability to obtain an adjusted risk probability value; Drawing a prediction curve based on the adjusted risk probability value; Obtaining time series data of the prediction curve to determine the gestational age-dependent change trend; Based on the changing trend, a dynamic monitoring update strategy is generated to obtain an optimized risk assessment result.

6. The Down syndrome screening system based on multiple key indicators according to claim 1, characterized in that: Also includes: The psychological assessment module is used to obtain the patient's physiological signal data and psychological assessment data in real time when the third screening module generates a high-risk prompt signal, generate a multi-dimensional psychological state feature vector based on the risk level, and determine whether to trigger a psychological intervention signal; The psychological assessment module is specifically used to: Collect patients' real-time physiological signals through wearable devices and extract characteristic parameters related to the autonomic nervous system; Synchronously obtain psychological status feedback information submitted by patients and convert it into standardized psychological assessment parameters; Comprehensively analyzing the physiological characteristic parameters, psychological assessment parameters and current risk level to generate a psychological stress index; When the psychological stress index exceeds a preset range, a psychological intervention signal is triggered and a state vector containing risk-related features is generated.

7. The Down syndrome screening system based on multiple key indicators according to claim 6, characterized in that: Also includes: An intervention decision module, configured to match a corresponding intervention plan from a multi-level intervention strategy library according to the state vector; The intervention decision module is specifically used to: Establish a multi-level intervention strategy that includes immediate consultation, self-directed training, and professional referral; Generate matching parameters based on multiple dimensional features of the state vector and dynamically select the type of intervention strategy; When a strong correlation is detected between the psychological stress index and the high risk level, real-time interactive intervention by professionals will be initiated first; If the psychological stress index is within the adjustable range, customized training content and community support resources will be pushed to the patient terminal; When it is monitored that the intervention response does not meet expectations, the family collaborative intervention mechanism is automatically triggered.

8. The Down syndrome screening system based on multiple key indicators according to claim 1, characterized in that: Also includes: The effect feedback module is used to update the psychological state assessment model through dynamic monitoring of physiological signals and interactive feedback data; The effect feedback module is specifically used for: Continuously collect physiological signal change trend data during the intervention implementation cycle; Obtain the patient's subjective experience feedback through the interactive interface and extract emotional state characteristics; Conduct correlation trend analysis on physiological and psychological data, and automatically increase the intervention intensity level when it detects that the improvement rate is lower than expected; The updated feature data are input into the adaptive model to optimize the psychological stress assessment parameters for the next stage.

9. The Down syndrome screening system based on multiple key indicators according to claim 8, characterized in that: The effect feedback module also includes a genetic counseling connection unit, which automatically generates a visual report integrating screening results and psychological assessment when the high-risk prompt signal and psychological intervention effect data meet the preset correlation conditions, and activates the genetic counseling service channel; The genetic counseling connection unit is specifically used to: Conduct spatiotemporal correlation analysis between the dynamic risk prediction curve and the trend of psychological stress changes; When a persistent positive correlation between risk level and psychological stress is detected, a priority consultation channel is triggered; The complete assessment record is transmitted to the designated genetic counseling terminal via a secure encryption protocol.

Images