Auxiliary screening method and system for thalassemia and storage medium
By using a thalassemia prediction model trained with routine blood data, the problems of high false positive rate, high false negative rate and high cost in existing thalassemia screening technologies have been solved, enabling rapid and low-cost prediction of the probability of thalassemia gene mutation carriers.
Patent Information
- Application Number
- CN202511449495.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-11
- Publication Date
- 2026-02-06
AI Technical Summary
Existing technologies for thalassemia screening suffer from high false positive rates, high false negative rates, high testing costs, high technical requirements, and time-consuming processes, making them difficult to widely apply, especially in economically underdeveloped regions.
A machine learning model based on routine blood data was used to predict thalassemia. The model was trained by acquiring routine blood data such as MCV, RBC, Hct, and RDW, and a SHAP influence map was generated for risk assessment.
It enables rapid and low-cost prediction of the probability of carrying thalassemia gene mutations, reduces the false positive rate and the missed diagnosis rate, and simplifies the screening process.
Smart Images
Figure CN121483374A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of medical auxiliary screening, in particular to an auxiliary screening method and system for thalassemia and a storage medium. BACKGROUND
[0002] Thalassemia (referred to as thalassemia) is a group of hereditary hemolytic anemia diseases. Due to genetic defects, the synthesis of one or more globin chains in hemoglobin is deficient or insufficient, resulting in anemia or pathological state. In southern China, especially in coastal areas, the gene mutation carrying rate of the population is high. At present, there is no effective treatment method, and it is difficult to cure. Therefore, it mainly relies on screening in the childbearing population, prenatal diagnosis, prevention of severe thalassemia fetus birth for disease prevention. Specifically, when performing thalassemia screening, the following means are used for routine diagnosis:
[0003] (1) Blood routine examination: can find that the mean corpuscular volume (MCV) and mean corpuscular hemoglobin (MCH) are reduced, which is a commonly used index for thalassemia screening.
[0004] (2) Hemoglobin electrophoresis: can detect abnormal hemoglobin components, which is of great significance for the diagnosis of β-thalassemia and some abnormal hemoglobinopathies.
[0005] (3) Gene detection: is the gold standard for diagnosing thalassemia, which can clearly determine the specific gene defect type.
[0006] The above screening methods have important roles in screening thalassemia, but also have some defects, which are as follows:
[0007] (1) Blood routine examination
[0008] Insufficient specificity: blood routine examination mainly observes indicators such as mean corpuscular volume (MCV) and mean corpuscular hemoglobin (MCH). Many other factors can also cause these indicators to be abnormal, such as iron deficiency anemia, anemia caused by chronic diseases, etc., which can easily cause misdiagnosis or missed diagnosis. According to statistics, only relying on MCV and MCH to screen thalassemia, the false positive rate may be as high as 20%-30%.
[0009] Unable to determine the type and gene defect of thalassemia: blood routine examination can only indicate that thalassemia may exist, but cannot determine whether it is α-thalassemia or β-thalassemia, and cannot determine the specific gene defect site, which has limited significance for subsequent precise diagnosis and genetic counseling.
[0010] (2) Hemoglobin electrophoresis
[0011] Not all abnormal hemoglobins can be detected: Some rare abnormal hemoglobin variants may not be detected by routine hemoglobin electrophoresis, leading to missed diagnoses. For example, some unstable hemoglobins, such as Hb Constant Spring, have electrophoretic migration rates similar to normal hemoglobin and are easily overlooked.
[0012] Interpretation of results is affected by a variety of factors: Hemoglobin electrophoresis results are susceptible to interference from various factors, such as the patient's age, the presence of other blood disorders, and the accuracy of the testing equipment. In the neonatal period, the high level of fetal hemoglobin (HbF) can affect the identification of abnormal hemoglobin; other blood disorders, such as dyshemoglobinopathies, may mask abnormal bands associated with thalassemia, leading to misinterpretation of results.
[0013] (3) Genetic testing
[0014] High testing costs: Gene testing technology is relatively complex and requires specialized equipment and reagents, resulting in high testing costs. This limits its widespread application to some extent, especially in some economically underdeveloped regions.
[0015] High technical requirements: Strict requirements are placed on the technical skills of the testing personnel and the laboratory conditions. Errors in any step of the operation can affect the accuracy of the test results. Furthermore, the interpretation of gene testing results also requires professional knowledge and experience; otherwise, misinterpretation may occur.
[0016] There are cases where some gene mutations cannot be detected: Although gene testing technology is constantly developing, there are still some rare thalassemia gene mutations that have not been fully recognized and detected, which may lead to some patients being missed in diagnosis.
[0017] (4) Blood routine tests, hemoglobin electrophoresis, gene testing and other methods are time-consuming and expensive. Summary of the Invention
[0018] In view of the deficiencies of the prior art mentioned in the background, the purpose of this invention is to provide an auxiliary screening method, system and storage medium for thalassemia.
[0019] To achieve the above objectives, in a first aspect, embodiments of the present invention provide an auxiliary screening method for thalassemia, comprising:
[0020] Obtain complete blood count data of patients to be screened for thalassemia, and extract model input data from the patient's complete blood count data; wherein, the model input data includes mean erythrocyte volume (MCV), red blood cell count (RBC), hematocrit (Hct), and red blood cell distribution width (RDW);
[0021] The input data of the model is input into a pre-trained thalassemia prediction model for prediction, and the probability of thalassemia gene mutation carrier is output.
[0022] As a preferred implementation of this application, before obtaining the blood routine data of the patient to be screened for thalassemia, the method further includes:
[0023] Acquire sample data and divide the sample data into training set and test set;
[0024] The model is trained based on the training set and the test set, and the optimal model is selected as the thalassemia prediction model.
[0025] As a preferred implementation of this application, after outputting the probability of thalassemia gene mutation carrier occurrence, the method further includes:
[0026] Based on the predicted probabilities output by the thalassemia prediction model, a SHAP influence map is generated;
[0027] Risk assessment is conducted based on the predicted probability and prediction results.
[0028] Secondly, embodiments of the present invention also provide an auxiliary screening system for thalassemia, comprising:
[0029] The acquisition unit is used to acquire complete blood count data of patients undergoing thalassemia screening.
[0030] Extraction unit, used to extract model input data from the patient's blood routine data;
[0031] The prediction unit is used to input the model input data into a pre-trained thalassemia prediction model for prediction and output the probability of thalassemia gene mutation carrier.
[0032] As a preferred implementation of this application, the auxiliary screening system further includes a model training unit, used for:
[0033] Acquire sample data and divide the sample data into training set and test set;
[0034] The model is trained based on the training set and the test set, and the optimal model is selected as the thalassemia prediction model.
[0035] As a preferred implementation of this application, the auxiliary screening system further includes:
[0036] The chart generation unit is used to generate a SHAP influence map based on the predicted probabilities output by the thalassemia prediction model.
[0037] The risk assessment unit is used to conduct risk assessments based on predicted probabilities and prediction results.
[0038] Thirdly, embodiments of the present invention also provide another auxiliary screening system for thalassemia, including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method described in the first aspect.
[0039] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, cause the processor to perform the method described in the first aspect.
[0040] The assisted screening scheme for thalassemia provided in this embodiment of the invention uses a model for screening. This model only requires input of four red blood cell values from the routine blood test results to predict the probability of thalassemia gene mutation carriers. Compared with existing screening methods, this invention is faster and less expensive. Attached Figure Description
[0041] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below.
[0042] Figure 1 This is a flowchart of the auxiliary screening method for thalassemia provided in an embodiment of the present invention;
[0043] Figure 2 This is a structural diagram of the auxiliary screening system for thalassemia provided in an embodiment of the present invention;
[0044] Figure 3 yes Figure 2 Another structural diagram of the system shown. Detailed Implementation
[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0046] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0047] Please refer to Figure 1 This is an auxiliary screening method for thalassemia provided in an embodiment of the present invention, comprising the following steps:
[0048] S1. Obtain sample data and train a thalassemia prediction model based on the sample data.
[0049] Specifically, the sample data is first divided into training and test sets. Then, cross-validation is used to train the model on the training set, and the optimal model is trained as the final model. The threshold at this point is recorded as the final threshold. Finally, the performance of the model on the test set is observed. By continuously adjusting the model's parameters, the model's generalization ability is improved, so that the model's performance on the training, validation, and test sets reaches relative optimality.
[0050] S2, Obtain complete blood count data of patients to be screened for thalassemia.
[0051] S3 extracts model input data from patient blood routine data.
[0052] Specifically, four values were extracted from the patient's blood routine data:
[0053] MCV: Mean corpuscular volume, measured in fl, e.g., 78.3
[0054] RBC: Red blood cell count per liter. Enter the value before multiplying by 10^12, such as 4.55.
[0055] Hct: Hematocrit, such as 0.335
[0056] RDW: Red blood cell distribution width. Enter a value in fl, such as 33.2.
[0057] S4 inputs the model input data into the pre-trained thalassemia prediction model for prediction and outputs the probability of thalassemia gene mutation carrier.
[0058] Specifically, by inputting the four red blood cell values from the routine blood test into the thalassemia model, the probability of carrying the thalassemia gene mutation can be predicted. According to the results, a probability higher than 0.5 indicates a high chance of carrying the thalassemia gene mutation, while a probability lower than 0.5 indicates a low chance of carrying the thalassemia gene mutation.
[0059] S5. Generate the SHAP influence map based on the predicted probabilities output by the thalassemia prediction model.
[0060] S6, conduct risk assessment based on predicted probabilities and prediction results.
[0061] The assisted screening method for thalassemia provided in this embodiment of the invention uses a model for screening. This model only requires input of four red blood cell values from the routine blood test results to predict the probability of thalassemia gene mutation carriers. Compared with existing screening methods, this invention is faster and less expensive.
[0062] Based on the same inventive concept, embodiments of the present invention also provide an auxiliary screening system for thalassemia, such as... Figure 2 As shown, it includes:
[0063] The model training unit is used to acquire sample data, divide the sample data into training set and test set, train the model based on the training set and test set, and select the optimal model as the thalassemia prediction model.
[0064] The acquisition unit is used to acquire complete blood count data of patients undergoing thalassemia screening.
[0065] Extraction unit, used to extract model input data from the patient's blood routine data;
[0066] The prediction unit is used to input the model input data into a pre-trained thalassemia prediction model for prediction and output the probability of thalassemia gene mutation carrier.
[0067] Furthermore, the auxiliary screening system also includes:
[0068] The chart generation unit is used to generate a SHAP influence map based on the predicted probabilities output by the thalassemia prediction model.
[0069] The risk assessment unit is used to conduct risk assessments based on predicted probabilities and prediction results.
[0070] It should be noted that the specific workflow of this embodiment is described in the foregoing method embodiment section, and will not be repeated here.
[0071] Furthermore, another embodiment of the present invention also provides an auxiliary screening system for thalassemia. For example... Figure 3As shown, the thalassemia screening system may include one or more processors 101, one or more input devices 102, one or more output devices 103, and a memory 104. The processors 101, input devices 102, output devices 103, and memory 104 are interconnected via a bus 105. The memory 104 stores a computer program, which includes program instructions. The processor 101 is configured to invoke the program instructions to execute the methods described in the above-described method embodiment.
[0072] It should be understood that, in this embodiment of the invention, the processor 101 may be a central processing unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0073] Input device 102 may include a keyboard, etc., and output device 103 may include a display (LCD, etc.), a speaker, etc.
[0074] The memory 104 may include read-only memory and random access memory, and provides instructions and data to the processor 101. A portion of the memory 104 may also include non-volatile random access memory. For example, the memory 104 may also store device type information.
[0075] In specific implementations, the processor 101, input device 102, and output device 103 described in the embodiments of the present invention can execute the implementation methods described in the embodiments of the auxiliary screening method for thalassemia provided in the present invention, which will not be repeated here.
[0076] Accordingly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor, implement the above-described auxiliary screening method for thalassemia.
[0077] The computer-readable storage medium can be an internal storage unit of the system described in any of the foregoing embodiments, such as the system's hard disk or memory. The computer-readable storage medium can also be an external storage device of the system, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the system. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.
[0078] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0079] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, or may be electrical, mechanical or other forms of connection.
[0080] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.
[0081] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0082] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0083] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. An auxiliary screening method for thalassemia, characterized in that, include: Obtain complete blood count data of patients to be screened for thalassemia, and extract model input data from the complete blood count data of the patients; The input data of the model is input into a pre-trained thalassemia prediction model for prediction, and the probability of thalassemia gene mutation carrier is output.
2. The auxiliary screening method for thalassemia as described in claim 1, characterized in that, The model input data includes mean erythrocyte volume (MCV), red blood cell count (RBC), hematocrit (Hct), and red blood cell distribution width (RDW).
3. The auxiliary screening method for thalassemia as described in claim 1, characterized in that, Before obtaining complete blood count data from patients undergoing thalassemia screening, the method further includes: Acquire sample data and divide the sample data into training set and test set; The model is trained based on the training set and the test set, and the optimal model is selected as the thalassemia prediction model.
4. The auxiliary screening method for thalassemia as described in claim 1, characterized in that, After outputting the probability of thalassemia gene mutation carrier occurrence, the method further includes: Based on the predicted probabilities output by the thalassemia prediction model, a SHAP influence map is generated; Risk assessment is conducted based on the predicted probability and prediction results.
5. An auxiliary screening system for thalassemia, characterized in that, include: The acquisition unit is used to acquire complete blood count data of patients undergoing thalassemia screening. Extraction unit, used to extract model input data from the patient's blood routine data; The prediction unit is used to input the model input data into a pre-trained thalassemia prediction model for prediction and output the probability of thalassemia gene mutation carrier.
6. The assisted screening system for thalassemia as described in claim 5, characterized in that, The auxiliary screening system also includes a model training unit for: Acquire sample data and divide the sample data into training set and test set; The model is trained based on the training set and the test set, and the optimal model is selected as the thalassemia prediction model.
7. The assisted screening system for thalassemia as described in claim 5 or 6, characterized in that, The auxiliary screening system also includes: The chart generation unit is used to generate a SHAP influence map based on the predicted probabilities output by the thalassemia prediction model. The risk assessment unit is used to conduct risk assessments based on predicted probabilities and prediction results.
8. An auxiliary screening system for thalassemia, characterized in that, The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the method as described in claim 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-4.