Expert rule-based low-molecular-weight heparin precise drug delivery decision-making system and method

Abstract

The invention discloses a low-molecular-weight heparin precise drug delivery decision system and method based on expert rules, and relates to the technical field of medical data intelligent processing, the system comprises a data acquisition module and an expert rule module, the expert rule module comprises a first rule subset, a second rule subset, a third rule subset and a fourth rule subset; the analysis module is used for analyzing the thrombin time data and the platelet counting data according to a second rule subset and a third rule subset in the expert rule module to obtain a bleeding risk assessment result; and the administration dosage determination module is used for calling corresponding dosage parameters from the expert rule module according to the weight grading result of the expert rule module and the bleeding risk assessment result of the analysis module, adjusting the dosage parameters and determining the administration dosage of the low-molecular heparin. According to the method, key physiological data such as the body weight, the thrombin time and the platelet counting of a patient are collected, and an expert rule base is introduced, so that accurate personalized adjustment of the dosage of the low-molecular-weight heparin is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent processing of medical data, and in particular to a system and method for making precise dosing decisions of low molecular weight heparin based on expert rules. Background Art

[0002] In terms of low molecular weight heparin (LMWH) administration, with the increasing incidence of thrombosis-related diseases and the increasing demand for clinical medication, precise and personalized drug administration has become a trend. LMWH is a class of anticoagulants widely used to prevent and treat venous thromboembolic diseases. It is highly respected in clinical practice because of its fewer side effects and relatively long-lasting pharmacological properties. However, the pharmacokinetic properties of LMWH are significantly affected by individual differences, and its effective dose often varies depending on factors such as the patient's weight and coagulation function status, which makes it difficult for traditional dose adjustment methods to meet the needs of individualized treatment. In this context, researchers at home and abroad have gradually explored automated drug delivery systems based on data-driven or rule-based settings, striving to improve the scientificity and safety of clinical drug delivery. At present, there are some precise drug delivery platforms based on rule systems and machine learning algorithms, but the drug delivery decisions of most systems are too dependent on a single variable, fail to fully consider the patient's multiple physiological parameters, and lack accurate assessment of potential bleeding risks, which limits the practicality and promotion value of the system.

[0003] Existing LMWH dosing decision systems generally have some significant deficiencies. First, most systems lack comprehensive consideration of multiple physiological indicators of patients, often use a single variable (such as body weight) for dose calculation, and fail to effectively integrate key indicators such as thrombin time and platelet count, which can easily lead to inaccurate dosing. Secondly, existing systems often ignore the real-time assessment of patients' bleeding risk and lack in-depth consideration of the balance between anticoagulation risk and dosing, thereby increasing the probability of adverse events. Summary of the invention

[0004] In view of the problems existing in the prior art, the present invention proposes a low molecular weight heparin precise dosing decision system and method based on expert rules, which can solve the problems mentioned in the background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a low molecular weight heparin precise dosing decision system based on expert rules, which comprises: A data collection module is used to collect the patient's weight data, thrombin time data and platelet count data, and transmit them to the expert rule module; An expert rule module, the expert rule module comprising a first rule subset, a second rule subset, a third rule subset and a fourth rule subset, for determining a dosage of low molecular weight heparin; An analysis module, configured to analyze the thrombin time data and platelet count data according to the second rule subset and the third rule subset in the expert rule module to obtain a bleeding risk assessment result; The dosage determination module is used to retrieve corresponding dosage parameters from the expert rule module according to the weight classification result of the first rule subset of the expert rule module and the bleeding risk assessment result of the analysis module, and adjust the dosage parameters.

[0006] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, wherein: the first rule subset is used for weight classification; The second rule subset is used for coagulation function assessment; The third rule subset is for platelet assessment; The fourth rule subset adjusts the dosage of low molecular weight heparin based on the first rule subset, the second rule subset and the third rule subset.

[0007] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, wherein: the weight classification standard includes light weight, standard weight and heavy weight; The weight classification standard is stored in the expert rule module in the form of weight grade-weight coefficient; The weight data of the patient is compared with the weight classification standard. If the weight of the patient is in the first preset interval, the patient is classified as light weight and a first weight coefficient is assigned; if the weight of the patient is in the second preset interval, the patient is classified as standard weight and a second weight coefficient is assigned; if the weight of the patient is in the third preset interval, the patient is classified as heavy weight and a third weight coefficient is assigned; If the patient's weight data is at the critical value position of the adjacent level, the weight coefficients of the adjacent levels are recorded at the same time, and the arithmetic mean thereof is taken as the final weight coefficient.

[0008] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, obtaining the bleeding risk assessment result includes: Extracting a coagulation index reference threshold from the expert rule module as a benchmark calibration value; Based on the patient's thrombin time data, a fitting model for thrombin time was established to obtain a thrombin time score. ; Based on the platelet count data of the patient, a dynamic response function of platelet count is established to obtain a platelet score ; Based on the thrombin time score , the platelet score The bleeding risk is assessed by comparing the coagulation index reference threshold to obtain a preliminary bleeding risk score. ; The initial bleeding risk score Performing time series correction and fuzzy judgment to obtain the bleeding risk assessment result; The bleeding risk assessment results include low risk, medium risk and high risk.

[0009] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, wherein: the thrombin time score The calculation of is as follows: ; in, is the measured thrombin time value, The standard reference value is 20s. , , is the fitting coefficient; is the time correction factor; The platelet score The calculation is as follows: ; in, To measure the platelet count, is the standard reference value, is the platelet baseline coefficient, is the logarithmic adjustment coefficient, is the period correction factor.

[0010] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, the calculation of the preliminary bleeding risk score is shown in the following formula: ; in, is the thrombin time weight coefficient, is the platelet count weight coefficient, Calibrate the function for the rule base, is the interaction coefficient; Wherein, the thrombin time weight coefficient and the platelet count weight coefficient are determined by the following formula: ; ; The rule base calibration function is shown in the following formula: ; in, is the rule weight, is the deviation measure between the current value and each threshold of the rule base, is the number of rules involved in the calculation, is the second rule subset, It is the third rule subset.

[0011] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, determining the dosage of low molecular weight heparin includes: Determine the range of the initial basal dose based on the weight classification results; Calibrate the initial basal dose based on the bleeding risk assessment results; Expert rule-constrained validation of weight- and risk-adjusted dose values; Determine whether the patient has used low molecular weight heparin. If so, fine-tune the verified dosage value according to the medication record. If not, determine the dosage of low molecular weight heparin.

[0012] As a preferred solution of the expert rule-based low molecular weight heparin precise dosing decision system of the present invention, the range of determining the initial basic dose includes: For patients with mild weight classification, the corresponding light weight dose reference interval is retrieved from the expert rule module, which is usually 20% lower than the standard dose; for patients with standard weight classification, the standard dose reference interval is retrieved; for patients with severe weight classification, the aggravated dose reference interval is retrieved, which is 20% higher than the standard dose; The expert rule constraint verification includes: Check whether the dose meets the safety threshold requirements set in the expert rule base, including the maximum dose limit and the minimum effective dose limit for a single dose; if the adjusted dose exceeds the safety threshold range, it will be automatically calibrated to the nearest safety threshold.

[0013] In a second aspect, the present invention provides a method for making precise dosing decisions for low molecular weight heparin based on expert rules, which comprises: Collecting the patient's weight data, thrombin time data, and platelet count data, and transmitting them to the expert rule module; According to the weight classification standard preset in the expert rule module, the weight data is classified to obtain a weight classification result; Based on the coagulation index threshold in the expert rule module, analyzing the thrombin time data and the platelet count data to obtain a bleeding risk assessment result; According to the weight classification result and the bleeding risk assessment result, the corresponding low molecular weight heparin basic dose parameter is retrieved from the expert rule module and adjusted; A recommended dosage value is generated according to the adjusted low molecular weight heparin basic dosage parameter, and the recommended dosage value is output to the medical terminal.

[0014] The beneficial effect of the present invention is that by collecting key physiological data such as patient weight, thrombin time and platelet count, and introducing an expert rule base, accurate and personalized adjustment of low molecular weight heparin dosage is achieved. Multiple rule subsets in the expert rule base can be dynamically graded according to patient weight, coagulation function and platelet level, and on this basis, bleeding risk assessment is performed, thereby effectively determining the initial dose range and adjustment coefficient, ensuring the scientificity and safety of the dosage. Furthermore, the system combines the patient's historical medication records and real-time monitoring data to intelligently adjust the dosage to adapt to the patient's physiological changes, ensure the effectiveness and safety of anticoagulant therapy, and reduce the risk of adverse events. This decision-making system based on multi-dimensional data analysis and dynamic adjustment has significant advantages in individualized precision medication, and helps to improve the rationality of clinical medication and patient prognosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 This is a structural diagram of the expert rule-based low molecular weight heparin precision dosing decision system.

[0016] Figure 2 Flow chart of the expert rule-based decision-making method for precision dosing of low molecular weight heparin. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0019] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0020] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0021] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0022] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0023] Example 1: Reference Figure 1 , which is the first embodiment of the present invention, provides a low molecular weight heparin precise dosing decision system based on expert rules, including: a data acquisition module, an expert rule module, an analysis module and a dosing dosage determination module.

[0024] The patient's weight data, thrombin time data and platelet count data are collected through the data acquisition module of the medical terminal, wherein the weight data is obtained by measuring with a medical electronic scale, the thrombin time data is obtained by detecting with a fully automatic coagulation analyzer, and the platelet count data is obtained by detecting with a fully automatic blood cell analyzer.

[0025] The weight data, thrombin time data and platelet count data are input into a preset expert rule database through the data transmission interface of the medical terminal, and the expert rule database is set in the internal server of the hospital; wherein, the expert rule database includes the following rules: the first rule subset is the weight classification rule, which defines a weight of 30-50 kg as a light weight class, 51-80 kg as a standard weight class, and 81-150 kg as a heavy weight class; the second rule subset is the coagulation function evaluation rule, which defines a thrombin time of 10-20s as a normal level, 21-40s as a mild abnormal level, and 41-60s as a severe abnormal level; the third rule subset is the platelet count evaluation rule, which defines a platelet count of (50-100)×10 9 / L is defined as a severely reduced level, (101-150)×10 9 / L is defined as a mildly decreased level, (151-450)×10 9 / L is defined as the normal level; the fourth rule subset is the dose adjustment rule library, which includes a low molecular weight heparin dosage parameter table based on the combination of the above three subset rules.

[0026] Furthermore, the weight data is numerically compared with a preset weight classification standard, in which 30-50 kg is classified as a light weight class and assigned a weight coefficient of 0.8, 51-80 kg is classified as a standard weight class and assigned a weight coefficient of 1.0, and 81-150 kg is classified as a heavy weight class and assigned a weight coefficient of 1.2; secondly, based on the specific value of the weight data, it is classified into a corresponding weight class category, and the weight coefficient corresponding to the class is recorded to obtain a weight classification result, which is stored in the expert rule database in the form of "weight class-weight coefficient"; if the weight data is at the critical value position of the adjacent class, the weight coefficients of the adjacent classes are recorded at the same time, and the arithmetic mean thereof is taken as the final weight coefficient; the weight classification result will be used as the basic parameter for the subsequent adjustment of the low molecular weight heparin dosage parameters.

[0027] Furthermore, the reference thresholds of coagulation indexes are extracted from the expert rule base as the benchmark calibration values, where: Rule set R1 (thrombin time): 10-20s is defined as normal level, 21-40s is defined as mildly abnormal level, and 41-60s is defined as severely abnormal level; Rule set R2 (platelet count): (50-100) x 10 9 / L is defined as a severely reduced level, (101-150)×10 9 / L is defined as a mildly decreased level, (151-450)×10 9 / L is defined as normal level; Establish a polynomial fitting model for the thrombin time and calculate the corrected thrombin time score : ; wherein, is the measured thrombin time value, is the standard reference value of 20 s, , , are fitting coefficients; is the time correction coefficient, which is determined by the following conditions: When T ≤ 20 s, α = 1.0; When 20 s < T ≤ 40 s, α = 1.2 + 0.01×(T - 20); When T > 40 s, α = 1.5 + 0.02×(T - 40); , , are fitting coefficients, which are determined by the threshold intervals in the rule base R1 in the following manner: = -0.2×(Tmax - Tmin) / (T0×10) = 0.5×(Tmid - T0) / T0 = 0.8×(Tmax / Tmin) wherein, Tmax, Tmin, and Tmid are the maximum, minimum, and middle thresholds in the rule base R1, respectively; Secondly, construct a dynamic response function for the platelet count and calculate the platelet score : ; wherein, is the measured platelet count value, is the standard reference value of 150×10 9 / L, is the platelet baseline coefficient, is the logarithmic adjustment coefficient, is the cycle correction coefficient: When P ≥ 150×10 9 / L, β = 1.0, γ = 0.2, δ = 0.1; When 100×10 9 / L ≤ P < 150×10 9 / L, β = 1.3, γ = 0.3, δ = 0.15; When P < 100×10 9 / L, β=1.6, γ=0.4, δ=0.2; in, , , The value of is dynamically adjusted according to the threshold interval in the rule base R2: = 1.0 + 0.3×(Pmax-P) / (Pmax-Pmin) = 0.2 + 0.1×(Pmid-P) / (Pmax-Pmin) = 0.1 + 0.05×(P-Pmin) / (Pmax-Pmin) Where Pmax, Pmin, and Pmid are the maximum, minimum, and middle thresholds in the rule base R2, respectively; Then, a comprehensive risk score dynamic model CR is established: ; in, is the interaction coefficient, is the thrombin time weight coefficient, is the platelet count weight coefficient: ; ; in, Calibrate the function for the rule base, ; in, is the rule weight, is the deviation measure between the current value and each threshold of the rule base, is the number of rules involved in the calculation, is the second rule subset, It is the third rule subset.

[0028] Furthermore, the results of the comprehensive risk score dynamic model are corrected in time series to calculate the final risk score FR: ; in, is the time interval between two tests (hours), is the characteristic time constant of 24 hours, The time decay coefficient is 0.1.

[0029] Finally, based on fuzzy mathematics theory, a risk level determination model is established: When 1.0≤ When <1.8, the low risk RL is calculated as follows: ; When 1.8≤ When <2.5, the medium risk RM is calculated as follows: ; when When ≥2.5, high-risk RH is calculated as follows: ; The final risk factor , or As a dynamic adjustment coefficient for low molecular weight heparin dosage.

[0030] Furthermore, the initial basic dose range is determined based on the weight classification results. For patients with mild weight classification, the corresponding light weight dose reference interval is retrieved from the expert rule library, which is usually 20% lower than the standard dose; for patients with standard weight classification, the standard dose reference interval is retrieved; for severe patients, the system retrieves the aggravated dose reference interval, which is usually 20% higher than the standard dose. During the retrieval process, the system will also consider the relative position of the patient's specific weight value within the classification range and make fine adjustments to the basic dose.

[0031] Secondly, the initial basal dose is calibrated based on the bleeding risk assessment results. For low-risk patients, the initial basal dose remains unchanged; for moderate-risk patients, the system extracts the risk calibration factor from the expert rule base and adjusts the initial basal dose downward according to the factor, usually by 25%; for high-risk patients, a larger reduction ratio is used, usually by 50%.

[0032] Furthermore, the dose value after double adjustment for weight and risk is verified by expert rule constraints. First, check whether the dose meets the safety threshold requirements set in the expert rule library, including the maximum dose limit and the minimum effective dose limit for a single dose. If the adjusted dose exceeds the safety threshold range, the system will automatically calibrate it to the nearest safety threshold. At the same time, verify whether the dose complies with the dosing rules in a specific clinical scenario.

[0033] If the patient has previously used low molecular weight heparin, the system will retrieve historical medication records and analyze the safety and effectiveness of previous doses. If the previous dose is within the safety range and the efficacy is satisfactory, the system will refer to the historical data to fine-tune the currently calculated dose to ensure the continuity and stability of treatment. If there have been safety issues or poor efficacy with previous doses, the system will adjust the dose calculation parameters accordingly to avoid similar problems from happening again.

[0034] After determining the basic dose, the system will continuously monitor the changes in the patient's coagulation indicators and evaluate the appropriateness of the dose in combination with the monitoring rules in the expert rule base. If the monitoring indicators indicate that the dose needs to be adjusted, the system will start the dose adjustment process and recalculate and verify the above steps.

[0035] A dosage recommendation value is generated according to the low molecular weight heparin basic dosage parameter, and the dosage recommendation value is output to the medical terminal.

[0036] Furthermore, this embodiment also provides a method for making a precise dosing decision for low molecular weight heparin based on expert rules, including: Collecting the patient's weight data, thrombin time data, and platelet count data, and transmitting them to the expert rule module; According to the weight classification standard preset in the expert rule module, the weight data is classified to obtain a weight classification result; Based on the coagulation index threshold in the expert rule module, analyzing the thrombin time data and the platelet count data to obtain a bleeding risk assessment result; According to the weight classification result and the bleeding risk assessment result, the corresponding low molecular weight heparin basic dose parameter is retrieved from the expert rule module and adjusted; A recommended dosage value is generated according to the adjusted low molecular weight heparin basic dosage parameter, and the recommended dosage value is output to the medical terminal.

[0037] This embodiment also provides a computer device, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to implement the expert rule-based low molecular weight heparin precise dosing decision method proposed in the above embodiment when executing the computer executable instructions.

[0038] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0039] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for implementing the expert rule-based precise dosing decision method for low molecular weight heparin proposed in the above embodiment is implemented.

[0040] Example 2: This is the second example of the present invention. This example provides a low molecular weight heparin precise dosing decision system based on expert rules. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0041] A three-month clinical validation trial was conducted in the cardiology department of a tertiary hospital. 120 patients who needed low molecular weight heparin anticoagulation therapy were selected as research subjects, including patients with different indications such as acute coronary syndrome, deep vein thrombosis, and pulmonary embolism. Through the data acquisition module of the medical terminal, the OMRON HN-289 medical electronic scale was used to measure the patient's weight, the Sysmex CS-5100 fully automatic coagulation analyzer was used to detect the thrombin time, and the Sysmex XN-3000 fully automatic blood cell analyzer was used to detect the platelet count. All testing equipment has been metrologically certified to ensure the accuracy and reliability of the data.

[0042] The test process strictly follows the standard operating procedures (SOP). First, the first comprehensive test is carried out when the patient is admitted to the hospital, and the test data is transmitted in real time to the expert rule database server deployed in the hospital through the data transmission interface of the medical terminal. The server uses Dell PowerEdge R750 dual-core server, equipped with Intel Xeon Gold 6348 processor, 256GB memory, and Red Hat Enterprise Linux 8.4 operating system to ensure the efficiency and stability of data processing.

[0043] After data collection is completed, the system automatically starts the analysis process. First, a weight classification assessment is performed. For patients at critical weight values ​​(such as 50±0.5kg, 80±0.5kg, 150±0.5kg), the system uses an interpolation algorithm to calculate the weight coefficient to ensure the continuity and smoothness of the dose adjustment. At the same time, the system fine-tunes the weight coefficient based on basic information such as the patient's age and gender, making the dose calculation more individualized.

[0044] In the risk assessment stage, the system uses an improved polynomial fitting model to process thrombin time data and analyzes the trend of platelet count changes through a dynamic response function. To improve the accuracy of the assessment, the system introduces a time weighting factor to perform a weighted average of multiple test data in a short period of time to reduce the impact of random fluctuations. In addition, the system has established a data quality control mechanism to mark obviously abnormal test values ​​and require retesting to ensure the reliability of the assessment results.

[0045] In the dose calculation phase, the system uses a multi-layer neural network model to comprehensively analyze the patient's weight classification results and risk assessment results. The model establishes a more accurate dose prediction model through deep learning of historical medication data. At the same time, the system also takes into account factors such as the patient's complications and concomitant medications to make personalized adjustments to the calculation results.

[0046] The following is a partial statistical table of the test data and dose adjustment results of 120 patients.

[0047] Table 1 Data table of personalized dosage of low molecular weight heparin Patient number Weight(kg) Thrombin time (s) Platelet count (×10^9 / L) Risk Scoring Dosage recommendations (IU / kg) Clinical effect score EG001 45.5 18.5 165 1.25 75 92 EG002 62.8 25.3 142 1.85 65 88 EG003 85.2 42.1 95 2.62 45 85 EG004 55.6 19.8 175 1.15 80 94 EG005 73.4 35.6 115 2.15 55 87 EG006 48.2 22.4 158 1.45 70 90 CG001 46.8 19.2 162 1.28 85 82 CG002 63.5 26.1 138 1.92 75 78 CG003 84.7 41.8 98 2.58 60 75 CG004 54.9 20.2 172 1.18 90 85 CG005 72.8 34.9 118 2.08 70 80 CG006 47.5 21.8 155 1.42 80 83 In the above Table 1, EG001- CG006 belong to the experimental group patients, and CG001- CG006 belong to the control group patients.

[0048] Through statistical analysis of the test data, the following conclusions can be drawn: The average clinical effect score of the experimental group was 89.3 points, while that of the control group was 80.5 points, and the difference between the two groups was statistically significant (P<0.01). This shows that the intelligent adjustment system of the present invention can more accurately determine the dosage and improve the treatment effect. In particular, when dealing with patients with special weights (such as EG001 and EG003), the system achieves a more personalized dosing regimen through dynamic weight adjustment.

[0049] By comparing the relationship between risk score and dosage, it can be found that the dosage of the experimental group for high-risk patients (risk score ≥ 2.5) is generally 15-25% lower than that of the control group, but the clinical effect score is 8-12 points higher. This shows that this system can effectively reduce the risk of bleeding complications while ensuring the treatment effect.

[0050] From the data of patient EG005, it can be seen that when the thrombin time is moderately abnormal (35.6s) and the platelet count is low (115×10 9 / L), the system can comprehensively consider the interactive effects of multiple indicators and give more reasonable dosage adjustment suggestions. In contrast, the dosage of CG005 in the control group was higher under similar circumstances, which increased the risk of bleeding.

[0051] For patients whose weight is at a critical value (such as EG006, 48.2kg), the system calculates the weight coefficient through a smooth transition algorithm, avoiding the "cliff effect" in traditional methods, and the dosing regimen is more in line with physiological characteristics. Data show that the clinical effect scores of such patients in the experimental group are generally 7-10 points higher than those in the control group.

[0052] In summary, the low molecular weight heparin dosage intelligent adjustment system proposed in the present invention has obvious innovation and practical value. Its core advantages are: comprehensive evaluation of multi-dimensional parameters; dynamic weight adaptive adjustment; accurate risk stratification management; and personalized dosing regimen formulation. These features enable the system to minimize medication risks while ensuring the therapeutic effect, providing a more scientific and reliable decision support tool for clinical anticoagulant therapy.

[0053] These data fully demonstrate the innovation and practical value of the present invention in the formulation of individualized low molecular weight heparin dosing regimens, which not only improves the accuracy and safety of dosing, but also greatly improves clinical work efficiency. The promotion and application of this method will provide strong technical support for the standardization and individualization of anticoagulant therapy.

[0054] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The expert rule-based low molecular weight heparin precise dosing decision system is characterized by: include: A data collection module is used to collect the patient's weight data, thrombin time data and platelet count data, and transmit them to the expert rule module; An expert rule module, the expert rule module comprising a first rule subset, a second rule subset, a third rule subset and a fourth rule subset, for determining a dosage of low molecular weight heparin; An analysis module, configured to analyze the thrombin time data and platelet count data according to the second rule subset and the third rule subset in the expert rule module to obtain a bleeding risk assessment result; The dosage determination module is used to retrieve corresponding dosage parameters from the expert rule module according to the weight classification result of the first rule subset of the expert rule module and the bleeding risk assessment result of the analysis module, and adjust the dosage parameters.

2. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 1, characterized in that: The first rule subset is used for weight classification; The second rule subset is used for coagulation function assessment; The third rule subset is for platelet assessment; The fourth rule subset adjusts the dosage of low molecular weight heparin based on the first rule subset, the second rule subset and the third rule subset.

3. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 2, characterized in that: The weight classification standards include light weight, standard weight and heavy weight; The weight classification standard is stored in the expert rule module in the form of weight grade-weight coefficient; The weight data of the patient is compared with the weight classification standard. If the weight of the patient is in the first preset interval, the patient is classified as light weight and a first weight coefficient is assigned; if the weight of the patient is in the second preset interval, the patient is classified as standard weight and a second weight coefficient is assigned; if the weight of the patient is in the third preset interval, the patient is classified as heavy weight and a third weight coefficient is assigned; If the patient's weight data is at the critical value position of the adjacent level, the weight coefficients of the adjacent levels are recorded at the same time, and the arithmetic mean thereof is taken as the final weight coefficient.

4. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 3, characterized in that: Obtaining the bleeding risk assessment result includes: Extracting a coagulation index reference threshold from the expert rule module as a benchmark calibration value; Based on the patient's thrombin time data, a fitting model for thrombin time was established to obtain a thrombin time score. ; Based on the platelet count data of the patient, a dynamic response function of platelet count is established to obtain a platelet score ; Based on the thrombin time score , the platelet score The bleeding risk is assessed by comparing the coagulation index reference threshold to obtain a preliminary bleeding risk score. ; The initial bleeding risk score Performing time series correction and fuzzy judgment to obtain the bleeding risk assessment result; The bleeding risk assessment results include low risk, medium risk and high risk.

5. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 4, characterized in that: The thrombin time score The calculation of is as follows: ； in, is the measured thrombin time value, The standard reference value is 20s. , , is the fitting coefficient; is the time correction factor; The platelet score The calculation is as follows: ； in, To measure the platelet count, is the standard reference value, is the platelet baseline coefficient, is the logarithmic adjustment coefficient, is the period correction factor.

6. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 5, characterized in that: The calculation of the preliminary bleeding risk score is shown below: ； in, is the thrombin time weight coefficient, is the platelet count weight coefficient, Calibrate the function for the rule base, is the interaction coefficient; Wherein, the thrombin time weight coefficient and the platelet count weight coefficient are determined by the following formula: ； ； The rule base calibration function is shown in the following formula: ； in, is the rule weight, is the deviation measure between the current value and each threshold of the rule base, is the number of rules involved in the calculation, is the second rule subset, It is the third rule subset.

7. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 6, characterized in that: Determining the dosage of the low molecular weight heparin includes: Determine the range of the initial basal dose based on the weight classification results; Calibrate the initial basal dose based on the bleeding risk assessment results; Expert rule-constrained validation of weight- and risk-adjusted dose values; Determine whether the patient has used low molecular weight heparin. If so, fine-tune the verified dosage value according to the medication record. If not, determine the dosage of low molecular weight heparin.

8. The expert rule-based low molecular weight heparin precise dosing decision system according to claim 7, characterized in that: The range for determining the initial basal dose includes: For patients with mild weight classification, the corresponding light weight dose reference interval is retrieved from the expert rule module, which is usually 20% lower than the standard dose; for patients with standard weight classification, the standard dose reference interval is retrieved; for patients with severe weight classification, the aggravated dose reference interval is retrieved, which is 20% higher than the standard dose; The expert rule constraint verification includes: Check whether the dose meets the safety threshold requirements set in the expert rule base, including the maximum dose limit and the minimum effective dose limit for a single dose; if the adjusted dose exceeds the safety threshold range, automatically calibrate it to the nearest safety threshold.

9. A method for precise dosing decision of low molecular weight heparin based on expert rules, based on the precise dosing decision system of low molecular weight heparin based on expert rules according to any one of claims 1 to 8, characterized in that: include: Collecting the patient's weight data, thrombin time data, and platelet count data, and transmitting them to the expert rule module; According to the weight classification standard preset in the expert rule module, the weight data is classified to obtain a weight classification result; Based on the coagulation index threshold in the expert rule module, analyzing the thrombin time data and the platelet count data to obtain a bleeding risk assessment result; According to the weight classification result and the bleeding risk assessment result, the corresponding low molecular weight heparin basic dose parameter is retrieved from the expert rule module and adjusted; A recommended dosage value is generated according to the adjusted low molecular weight heparin basic dosage parameter, and the recommended dosage value is output to the medical terminal.

Images