A plateau newborn genetic metabolic disease screening system, a computer readable storage medium and an application thereof

Abstract

The present application belongs to the technical field of medical software development, and particularly relates to a highland newborn genetic metabolic disease screening system, a computer readable storage medium and an application thereof. The screening system establishes an altitude stratified multi-level reference value database based on a local healthy newborn cohort, solves the problem of high false positive rate of screening models in plain areas in highland areas by fitting altitude metabolic marker reference median and standard deviation curves. By designing a three-level control data processing flow of "biochemical primary screening-risk score-targeted sequencing automatic triggering", only when the biochemistry is high risk, the population-specific pathogenic mutation library guided targeted sequencing is started, unnecessary whole genome sequencing is avoided, and the screening cost is significantly reduced. The system can also continuously iterate the reference curve and risk threshold according to the confirmed data, realize the closed loop dynamic optimization from sample collection to report generation. The present application has highland adaptability, population specificity and controllable cost, and has good clinical application prospect.

Description

Technical Field

[0001] This invention belongs to the field of medical software development technology, specifically relating to a screening system for genetic metabolic diseases in newborns in high-altitude areas, a computer-readable storage medium, and their applications. Background Technology

[0002] Neonatal inherited metabolic disorders are numerous and most are highly dangerous, with high mortality and disability rates. Early screening is a crucial step in identifying high-risk infants. Currently, neonatal inherited metabolic disorder screening involves collecting heel prick blood using special filter paper 48-72 hours after birth to detect disease-specific metabolites and identify certain inherited metabolic disorders. With the development of testing technology, screening techniques have evolved from the initial bacterial inhibition method to fluorescence immunoassay and tandem mass spectrometry.

[0003] However, directly transplanting this model to high-altitude areas (≥2500 meters) faces the following prominent problems:

[0004] 1. Metabolic baseline drift: Low-pressure, low-oxygen environments cause the baseline levels of some metabolic markers (such as 17-hydroxyprogesterone, thyroid-stimulating hormone, and lactate) in healthy newborns to be significantly higher than the baseline reference values. According to literature reports, directly applying the baseline cutoff value can lead to a false positive rate of over 40%, causing unnecessary family anxiety and wasting medical resources.

[0005] 2. Genetic heterogeneity in the population: People who live in high-altitude areas for a long time have developed a unique spectrum of pathogenic mutations during the process of adapting to the plateau. The general gene database does not cover the specific variations in this region, resulting in a low gene diagnosis rate.

[0006] 3. The contradiction between screening cost and efficiency: Whole genome / whole exome sequencing is costly and time-consuming, making it difficult to promote in large-scale screening in high-altitude areas at present; while relying solely on biochemical screening is prone to missing some diseases with inconspicuous metabolites.

[0007] While some existing studies have attempted altitude-corrected metabolites, they mostly employ simple linear regression without incorporating local healthy newborn cohort data. Furthermore, there is a lack of intelligent screening decision-making systems that integrate biochemical risk, altitude, and genetic background. Therefore, there is an urgent need for a genetic metabolic disease screening system specifically designed for high-altitude areas, driven by data, with two-tiered linkage, and continuously self-optimizing capabilities. Summary of the Invention

[0008] To address the aforementioned problems in the existing technology, this invention provides a high-altitude newborn genetic metabolic disease screening system and storage medium.

[0009] A screening system for inherited metabolic diseases in newborns at high altitudes, the screening system comprising:

[0010] The data acquisition module is configured to acquire the detection values ​​of metabolic markers in newborn blood samples and the altitude of the blood collection point;

[0011] A multi-level reference database is configured to pre-store the reference median and reference standard deviation of metabolic markers based on healthy newborn populations at different altitudes.

[0012] The population-specific pathogenic mutation library is configured to pre-store information on pathogenic or potentially pathogenic mutation sites in newborns with genetic metabolic diseases in high-altitude areas.

[0013] The intelligent decision-making engine includes: an altitude correction unit, a risk calculation unit, and a gene detection triggering unit, wherein:

[0014] The altitude correction unit is configured to retrieve the corresponding reference median and reference standard deviation from the multi-level reference value database based on the altitude of the blood collection point, and calculate the altitude correction Z-score of the metabolic biomarker detection value.

[0015] The risk calculation unit is configured to calculate a comprehensive risk index based on the altitude-corrected Z-score and a preset disease-specific normalization weight.

[0016] The gene detection triggering unit is configured to generate a sequencing instruction containing a list of genes to be tested and sequencing depth requirements and push it to the gene detection terminal when the comprehensive risk index is greater than or equal to a preset disease-specific threshold.

[0017] The report generation module is configured to receive gene variation data returned by the gene testing terminal, compare the gene variation data with the population-specific pathogenic mutation library, and generate a structured screening risk assessment report according to the comparison results and the comprehensive risk index, based on preset positive / negative determination rules.

[0018] Preferably, the reference median and reference standard deviation in the multi-level reference value database are constructed in the following manner:

[0019] Blood samples were collected from healthy full-term newborns at different altitudes to detect the concentration of target metabolic markers or enzyme activities. The median and standard deviation were calculated by grouping the samples into intervals of 500 meters each. Local weighted regression was used to fit and establish continuous altitude-reference median and altitude-reference standard deviation curves.

[0020] Preferably, in the population-specific pathogenic mutation library, the mutation sites include one or more of the following sites: c.293-13A / C>G and p.Ile172Asn of the CYP21A2 gene; p.Arg243Gln and p.Tyr204His of the PAH gene; and c.95A>G and c.871G>A of the G6PD gene.

[0021] Preferably, the disease-specific normalization weights and disease-specific thresholds are determined by training with a logistic regression algorithm using case-control data, and all weights satisfy the normalization condition.

[0022] Preferably, the inherited metabolic disease includes at least one of congenital adrenal hyperplasia, phenylketonuria, glucose-6-phosphate dehydrogenase deficiency, and fatty acid oxidation disorder; the metabolic markers include at least one of 17-hydroxyprogesterone concentration, phenylalanine concentration, glucose-6-phosphate dehydrogenase activity, and 3-hydroxyisovalerylcarnitine concentration.

[0023] Preferably, the altitude-corrected Z-score of the metabolic biomarker detection value is calculated according to the following formula:

[0024]

[0025] in, X To measure the values ​​of metabolic markers, M ( h ( ) represents the reference median for metabolic biomarkers. SD ( h () represents the reference standard deviation of metabolic markers.

[0026] Preferably, the comprehensive risk index is calculated according to the following formula:

[0027]

[0028] in, CRI Z is a comprehensive risk index. i w is the altitude-corrected Z-score for the i-th metabolic biomarker. i Let s be the disease-specific normalized weight of the i-th metabolic biomarker. i The risk direction sign for the i-th metabolic biomarker is represented by a value of +1 (indicating a higher risk for a larger Z-score) or -1 (indicating a higher risk for a smaller Z-score). When Z... i When s is negative i = -1, Z i It is mapped as a positive value to participate in risk accumulation.

[0029] Preferably, it also includes a feedback optimization module, configured to receive clinical diagnosis result data, periodically refit the reference median and reference standard deviation of metabolic markers, optimize disease-specific normalization weights and disease-specific thresholds, and update the multi-level reference value database and the population-specific pathogenic mutation library.

[0030] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the functions of the above-mentioned plateau newborn genetic metabolic disease screening system.

[0031] The present invention also provides the application of a high-altitude newborn genetic metabolic disease screening system, which is deployed in medical institutions in high-altitude areas and is used to interact with hospital information systems, laboratory information management systems or regional health information platforms.

[0032] The present invention has achieved the following beneficial effects:

[0033] 1. Scientific approach to high-altitude acclimatization correction: This invention abandons empirical formulas and uses real-world cohort data to construct an altitude-metabolic biomarker reference curve, which can improve the accuracy of screening results.

[0034] 2. Population-specific and precise detection: It has the first large-scale gene mutation database for neonatal genetic metabolic diseases in high-altitude areas, and the gene diagnosis rate is higher than that of general databases.

[0035] 3. Resource-saving screening process: By using CRI to intelligently screen high-risk individuals for targeted sequencing, the proportion of gene testing can be reduced, significantly reducing the total screening cost.

[0036] 4. Closed-loop self-optimization capability: The feedback optimization module enables the system's reference thresholds and weights to continuously iterate as confirmed data accumulates, without the need for frequent manual adjustments.

[0037] 5. Clear and explicit reporting rules: This invention specifies in detail the content structure of the screening risk assessment report and the rules for determining positive / negative results, ensuring the consistency and interpretability of the system output.

[0038] In summary, this invention constructs a complete screening system and process for inherited metabolic diseases in newborns at high altitudes, optimized for the genetic background of high-altitude populations to improve screening accuracy. Simultaneously, it introduces a screening step for high-risk individuals, effectively reducing the proportion of gene testing, thus better aligning with the objective environment of high-altitude regions. Therefore, this invention combines high-altitude adaptability, population specificity, and cost controllability, demonstrating promising clinical application prospects.

[0039] Obviously, based on the above description of the present invention, and according to common technical knowledge and conventional methods in the field, various other modifications, substitutions or alterations can be made without departing from the basic technical concept of the present invention.

[0040] The following detailed embodiments further illustrate the above-described content of the present invention. However, this should not be construed as limiting the scope of the present invention to the following examples. All technologies implemented based on the above-described content of the present invention fall within the scope of the present invention. Attached Figure Description

[0041] Figure 1 This is a schematic diagram of the process of the plateau newborn genetic metabolic disease screening system in Example 1. Detailed Implementation

[0042] It should be noted that the algorithms for data acquisition, transmission, storage and processing steps not specifically described in the embodiments, as well as the hardware structures and circuit connections not specifically described, can all be implemented using content already disclosed in the prior art.

[0043] Example 1: High-altitude newborn genetic metabolic disease screening system

[0044] The system in this embodiment is as follows: Figure 1 As shown, it includes:

[0045] The data acquisition module is configured to acquire the detection values ​​of metabolic biomarkers in newborn blood samples and the altitude of the blood collection point. In a preferred embodiment, the data acquisition module also records the unique identifier of the blood sample, the blood collection institution, the blood collection time, the newborn's birth weight, gestational age, and the latitude and longitude of the blood collection point. The system automatically parses the altitude of the blood collection point through GIS reverse geocoding and binds the above information with the metabolic biomarker detection results, uploading it to the cloud.

[0046] A multi-level reference database is configured to pre-store reference medians and reference standard deviations of metabolic markers based on healthy newborn populations at different altitudes.

[0047] The population-specific pathogenic mutation library is configured to pre-store information on pathogenic or potentially pathogenic mutation sites in newborns with genetic metabolic diseases in high-altitude areas.

[0048] The intelligent decision-making engine includes: an altitude correction unit, a risk calculation unit, and a gene detection triggering unit, wherein:

[0049] The altitude correction unit is configured to retrieve the corresponding reference median and reference standard deviation from the multi-level reference value database based on the altitude of the blood collection point, and calculate the altitude correction Z-score of the metabolic biomarker detection value.

[0050] The risk calculation unit is configured to calculate a comprehensive risk index based on the altitude-corrected Z-score and a preset disease-specific normalization weight.

[0051] The gene detection trigger unit is configured such that when the comprehensive risk index is greater than or equal to a preset disease-specific threshold, the system determines it as "high biochemical risk," generates sequencing instructions (including sample identifier, list of genes to be tested, and sequencing depth requirements), and pushes them to the gene detection terminal. If the comprehensive risk index is less than the preset disease-specific threshold, the system determines it as "low biochemical risk," directly generates a negative report, and pushes it to the newborn's family.

[0052] The report generation module is configured to receive gene variation data returned by the gene testing terminal, compare the gene variation data with the population-specific pathogenic mutation library, filter benign variations and low-frequency polymorphic sites, perform ACMG grading annotation on pathogenic or potentially pathogenic variations, and generate a screening risk assessment report (positive / negative / suspected) based on the comprehensive risk index. The report is pushed to parents and attending physicians via SMS and mobile application; clinical diagnosis results are fed back to the feedback optimization module.

[0053] The feedback optimization module is configured to receive clinical diagnosis data, periodically refit the reference median and reference standard deviation of metabolic markers, optimize disease-specific normalization weights and disease-specific thresholds, and update the multi-level reference value database and the population-specific pathogenic mutation library.

[0054] in,

[0055] In a multi-level reference database, the reference median and reference standard deviation are constructed as follows:

[0056] Within an altitude range of 2500-5000 meters, the study was divided into intervals of 500 meters, with at least 100 healthy full-term newborns recruited for each interval. Heel prick blood samples were collected to detect the concentration of target metabolic markers or enzyme activities. Medians and standard deviations were calculated for each altitude interval, and continuous altitude-reference median and altitude-reference standard deviation curves were established using LOESS fitting. The fitting parameters were set as follows: span=0.5 (controlling the weight range of local data points), degree=1 (local linear fitting).

[0057] In the population-specific pathogenic mutation library, the variant sites include one or more of the following sites: c.293-13A / C>G and p.Ile172Asn of the CYP21A2 gene; p.Arg243Gln and p.Tyr204His of the PAH gene; and c.95A>G and c.871G>A of the G6PD gene.

[0058] The disease-specific normalized weights and disease-specific thresholds were determined by collecting metabolic biomarker data and altitude information from previously confirmed cases and healthy controls. The model was trained using a logistic regression algorithm, with the diagnosis result (positive = 1, negative = 0) as the dependent variable and the altitude-corrected Z-score of the metabolic biomarker as the independent variable. 10-fold cross-validation was used to prevent overfitting during model training. The regression coefficients obtained after training were normalized and used as the disease-specific normalized weights; all weights satisfied the normalization conditions. The optimal threshold was determined by maximizing the Youden Index, and this threshold was used as a disease-specific threshold.

[0059] The genetic metabolic disorders include at least one of congenital adrenal hyperplasia, phenylketonuria, glucose-6-phosphate dehydrogenase deficiency, and fatty acid oxidation disorder; the metabolic markers include at least one of 17-hydroxyprogesterone concentration, phenylalanine concentration, glucose-6-phosphate dehydrogenase activity, and 3-hydroxyisovalerylcarnitine concentration.

[0060] The altitude-corrected Z-score of the metabolic biomarker detection values ​​is calculated according to the following formula:

[0061]

[0062] in, X To measure the values ​​of metabolic markers, M ( h ( ) represents the reference median for metabolic biomarkers. SD ( h () represents the reference standard deviation of metabolic markers.

[0063] The comprehensive risk index is calculated according to the following formula:

[0064]

[0065] CRI stands for Comprehensive Risk Index. Let Z be the altitude-corrected Z-score for the i-th metabolic biomarker. Let be the disease-specific normalized weight of the i-th metabolic biomarker. The risk direction sign for the i-th metabolic biomarker is represented by a value of +1 (indicating a higher risk for a larger Z-score) or -1 (indicating a higher risk for a smaller Z-score). When Z... i When s is negative i = -1, Z i It is mapped as a positive value to participate in risk accumulation.

[0066] The system incorporates a disease-gene mapping table and minimum sequencing depth requirements (e.g., CYP21A2 ≥ 100×, G6PD ≥ 50×). The list of genes to be tested is determined according to the preset disease-gene mapping table. In a preferred embodiment, it includes at least one of CYP21A2, PAH, G6PD, and ACADM, along with corresponding minimum sequencing depth requirements.

[0067] As a preferred approach, the screening risk assessment report includes the following:

[0068] Basic information of newborns: including sample number, blood collection date, report generation date, age, sex, and altitude of the blood collection site;

[0069] Metabolic marker test results: including metabolite name, test value, altitude-corrected reference range, Z score, and abnormal markers;

[0070] Comprehensive Risk Index: Includes CRI value, disease-specific threshold, and risk level (low / high).

[0071] Gene testing results (if triggered): include a list of genes tested, testing methods, detected variant sites, comparison results with a population-specific pathogenic mutation library (whether it is included, pathogenicity classification), and ACMG classification annotation;

[0072] Final conclusion: including positive / negative result, disease name (if applicable), and diagnostic recommendation.

[0073] As a preferred approach, positive / negative results can be determined in the following way:

[0074]

[0075] For scenario 3, the report conclusion is marked as "suspicious" and suggests that clinical confirmation is required.

[0076] The following two examples illustrate the operation of the system in this embodiment.

[0077] Case 1: Newborn screening for congenital adrenal hyperplasia (CAH) in high-altitude areas

[0078] 1. Data Preparation Stage

[0079] Two hundred healthy full-term newborns were recruited at altitudes of 3200 meters, 3700 meters, 4200 meters, and 4700 meters. Heel blood was collected and the 17-OHP concentration was tested.

[0080] 2. System Configuration

[0081] CAH uses only 17-OHP as a single biomarker, therefore the disease-specific normalization weight is set to 1, and the disease-specific threshold for CAH is... .

[0082] 3. Screening Examples

[0083] The 17-OHP value of a newborn (male, 3 days old, altitude 3650 meters) in heel prick blood was 45 nmol / L.

[0084] The system retrieves the reference median (M = 25) nmol / L and standard deviation (SD = 8) nmol / L corresponding to an altitude of 3650 meters.

[0085] calculate .

[0086] CRI = 1.0 × 2.5 = 2.5, which equals the preset threshold. .

[0087] The system determined it to be "high risk" and automatically sent a sequencing command (sample ID, CYP21A2 gene, sequencing depth ≥100×) to the hospital's gene laboratory.

[0088] The gene lab received instructions, simultaneously transferred samples, and used multiplex PCR to amplify all exons and promoter regions of CYP21A2 for targeted sequencing, discovering the c.293-13A / C>G heterozygous mutation (the pathogenic site is included in the population-specific pathogenic mutation library).

[0089] The report generation module determines a "positive" result based on a CRI of 2.5 or higher and the detection of pathogenic sites from the mutation library, and generates a report accordingly.

[0090] Metabolic marker results: 17-OHP 45 nmol / L (Z=2.5).

[0091] Overall Risk Index: CRI=2.5, Risk Level: High.

[0092] Genetic testing results: CYP21A2 c.293-13A / C>G heterozygous mutation (compared with the population-specific pathogenic mutation library: included, pathogenicity grade: pathogenic).

[0093] Final conclusion: Positive, highly suspected CAH.

[0094] The entire process, from blood collection to report generation, took 47 hours.

[0095] Case 2: Screening for Glucose-6-phosphate dehydrogenase deficiency (G6PD) in newborns at high altitudes

[0096] 1. Data Preparation

[0097] Heel blood was collected from healthy full-term newborns (male and female separately) at different altitudes to detect G6PD enzyme activity, and altitude-reference median and standard deviation curves were constructed for males and females respectively.

[0098] 2. System Configuration

[0099] The relevant metabolic markers for G6PD are enzyme activity values. The disease-specific normalization weight is set to 1.0. When the Z-score is negative, the absolute value of CRI is mapped to a positive risk value.

[0100] Initial threshold: (Z<-2.0) and the reference curve corresponding to gender, trigger G6PD gene sequencing (G6PD gene whole exon, sequencing depth ≥50×).

[0101] 3. Screening Examples

[0102] Female infant, at an altitude of 3800 meters, G6PD enzyme activity detected value = 4.5 U / gHb.

[0103] Reference median for women at corresponding altitude U / gHb, U / gHb.

[0104] .

[0105] (Through risk mapping) If the value exceeds the threshold of 2.0, sequencing is triggered.

[0106] Sequencing revealed a c.95A>G hemizygous mutation in the G6PD gene (a potentially pathogenic site is included in the population-specific pathogenic mutation library).

[0107] The report generation module determines a "positive" result based on a CRI of 2.06 or higher and the detection of mutation sites included in the mutation library, and generates a report accordingly.

[0108] Metabolic marker results: G6PD enzyme activity 4.5 U / gHb (Z=-2.06).

[0109] Overall Risk Index: CRI=2.06, Risk Level: High.

[0110] Genetic testing results: G6PD c.95A>G hemizygous mutation (compared with the population-specific pathogenic mutation library: included, pathogenicity grade: possibly pathogenic).

[0111] Final conclusion: Positive, high risk of G6PD deficiency. In summary, this invention constructs a high-altitude adaptive newborn genetic metabolic disease screening system, which can efficiently and accurately screen newborns for genetic metabolic diseases and has outstanding application value at high altitudes.

Claims

1. A screening system for inherited metabolic diseases in newborns at high altitudes, characterized in that, The screening system includes: The data acquisition module is configured to acquire the detection values ​​of metabolic markers in newborn blood samples and the altitude of the blood collection point; A multi-level reference database is configured to pre-store the reference median and reference standard deviation of metabolic markers based on healthy newborn populations at different altitudes. The population-specific pathogenic mutation library is configured to pre-store information on pathogenic or potentially pathogenic mutation sites in newborns with genetic metabolic diseases in high-altitude areas. The intelligent decision-making engine includes: an altitude correction unit, a risk calculation unit, and a gene detection triggering unit, wherein: The altitude correction unit is configured to retrieve the corresponding reference median and reference standard deviation from the multi-level reference value database based on the altitude of the blood collection point, and calculate the altitude correction Z-score of the metabolic biomarker detection value. The risk calculation unit is configured to calculate a comprehensive risk index based on the altitude-corrected Z-score and a preset disease-specific normalization weight. The gene detection triggering unit is configured to generate a sequencing instruction containing a list of genes to be tested and sequencing depth requirements and push it to the gene detection terminal when the comprehensive risk index is greater than or equal to a preset disease-specific threshold. The report generation module is configured to receive gene variation data returned by the gene testing terminal, compare the gene variation data with the population-specific pathogenic mutation library, and generate a structured screening risk assessment report according to the comparison results and the comprehensive risk index, based on preset positive / negative determination rules. The reference median and reference standard deviation in the multi-level reference value database are constructed in the following manner: Blood samples were collected from healthy full-term newborns at different altitudes to detect the concentration of target metabolic markers or enzyme activities. The median and standard deviation were calculated by grouping the samples into intervals of 500 meters each. Local weighted regression was used to fit and establish continuous altitude-reference median and altitude-reference standard deviation curves. The altitude-corrected Z-score of the metabolic biomarker detection values ​​is calculated according to the following formula: in, X To measure the values ​​of metabolic markers, M ( h ( ) represents the reference median for metabolic biomarkers. SD ( h () represents the reference standard deviation of metabolic markers; The comprehensive risk index is calculated according to the following formula: in, CRI Z is a comprehensive risk index. i w is the altitude-corrected Z-score for the i-th metabolic biomarker. i Let s be the disease-specific normalized weight of the i-th metabolic biomarker. i The risk direction sign for the i-th metabolic biomarker is represented by a value of +1 or -1, where Z is the risk direction sign for the i-th metabolic biomarker. i When s is negative i = -1, Z i It is mapped as a positive value to participate in risk accumulation.

2. The high-altitude newborn genetic metabolic disease screening system according to claim 1, characterized in that, In the population-specific pathogenic mutation library, the mutation sites include one or more of the following sites: c.293-13A / C>G and p.Ile172Asn of the CYP21A2 gene; p.Arg243Gln and p.Tyr204His of the PAH gene; and c.95A>G and c.871G>A of the G6PD gene.

3. The high-altitude newborn genetic metabolic disease screening system according to claim 1, characterized in that, The disease-specific normalization weights and disease-specific thresholds are determined by training the case-control data using a logistic regression algorithm, and all weights satisfy the normalization conditions.

4. The high-altitude newborn genetic metabolic disease screening system according to claim 1, characterized in that, The genetic metabolic disorders include at least one of congenital adrenal hyperplasia, phenylketonuria, glucose-6-phosphate dehydrogenase deficiency, and fatty acid oxidation disorder; the metabolic markers include at least one of 17-hydroxyprogesterone concentration, phenylalanine concentration, glucose-6-phosphate dehydrogenase activity, and 3-hydroxyisovalerylcarnitine concentration.

5. The high-altitude newborn genetic metabolic disease screening system according to claim 1, characterized in that, It also includes a feedback optimization module, which is configured to receive clinical diagnosis data, periodically refit the reference median and reference standard deviation of metabolic markers, optimize disease-specific normalization weights and disease-specific thresholds, and update the multi-level reference value database and the population-specific pathogenic mutation library.

6. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, performs the function of the plateau newborn genetic metabolic disease screening system according to any one of claims 1 to 5.

7. The application of the plateau newborn genetic metabolic disease screening system according to any one of claims 1 to 5, characterized in that, The plateau newborn genetic metabolic disease screening system is deployed in medical institutions in plateau areas and is used to interact with hospital information systems, laboratory information management systems or regional health information platforms.

Images