Intelligent VTE prevention and control system

Abstract

The invention discloses an intelligent VTE prevention and control system, and the system comprises a risk assessment module which is used for obtaining a risk index of VTE according to a risk factor; the preventive measure recommendation module is used for recommending preventive measures according to the clinical data; the VTE early warning module is used for acquiring an early warning index of the VTE according to the iconography data, the laboratory examination result and the clinical symptoms; and the treatment scheme optimization module is used for adjusting the treatment scheme according to the individual characteristics, the treatment reaction and the drug interaction, and helping a doctor to provide an auxiliary reference result for the illness state of the patient and subsequent treatment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent prevention and treatment technology, and in particular to an intelligent VTE prevention and treatment system. Background Art

[0002] Venous thromboembolism (VTE) includes deep vein thrombosis (DVT) and pulmonary embolism (PTE), which are two important clinical manifestations of the same disease at different stages and locations. Clinically, patients in many departments are at risk of VTE, which is an important cause of unexpected deaths in hospitals.

[0003] VTE is a preventable disease. Active and effective prevention and treatment can effectively reduce its incidence and mortality. It is estimated that the incidence of DVT can be reduced by up to 70% through drug and physical prevention measures. Thrombosis prevention for hospitalized patients at risk can reduce VTE by 30%-65%. However, the current status of VTE prevention in clinical practice is not optimistic, and the efficiency of VTE prevention relying solely on manual methods is low. Summary of the invention

[0004] To achieve the above-mentioned purpose and other related purposes, the present invention provides an intelligent VTE prevention and treatment system, comprising: Risk assessment module, used to obtain the risk index of VTE based on risk factors; The preventive measures recommendation module is used to recommend preventive measures based on clinical data; VTE early warning module, used to obtain VTE early warning index based on imaging data, laboratory test results and clinical symptoms; Treatment optimization module is used to adjust the treatment plan based on individual characteristics, treatment response and drug interactions.

[0005] Furthermore, the risk index of VTE obtained according to the risk factors includes: VTE risk index = log(Σ(wi×fi))×exp(Δt / τ)+ε(G); Where: wi is the weight of each risk factor, fi is the quantitative value of the risk factor, Δt is the time since admission, τ is the time decay constant, and ε(G) is the genetic risk correction function.

[0006] Furthermore, the preventive measures recommended based on clinical data include: Preventive measures effectiveness index = (Π(1+Ei×Ci))^(1 / n)×(1-exp(-λ×t)); Where: Ei is the effectiveness coefficient of each preventive measure, Ci is the compliance of each preventive measure, n is the number of preventive measures taken, λ is the learning rate, and t is the system operation time.

[0007] Furthermore, the early warning index of VTE obtained based on imaging data, laboratory test results and clinical symptoms includes: VTE warning index = tanh(W1×CNN(I)+W2×RNN(L)+W3×FCN(S))×σ(t) Among them: CNN, RNN, FCN are neural networks for processing imaging experiment data, laboratory test results and clinical symptom data respectively, I, L, S are imaging experiment data, laboratory test results and clinical symptom data respectively, W1, W2, W3 are the weights of each modality, and σ(t) is the time sensitivity function.

[0008] Furthermore, the adjustment of the treatment regimen according to individual characteristics, treatment response and drug interactions includes: Treatment plan optimization index = argmax(Σ(αi×log(Ei+1)-βj×exp(Cj))×Φ(x,y)) Where: Ei is the expected effect of each treatment plan, Cj is the risk and cost of each treatment plan, αi, βj are balance coefficients, and Φ(x, y) is the matching function between the individual characteristics of the patient and the treatment plan.

[0009] Furthermore, the risk factors include: age, BMI, surgery type, surgery complexity and number of previous VTE histories.

[0010] Furthermore, the imaging data include: lower limb venous ultrasound images and CT pulmonary angiography images.

[0011] Furthermore, the laboratory test result data include: D-dimer level, platelet count, and prothrombin time.

[0012] Furthermore, the clinical symptom data include: lower limb swelling degree, dyspnea score, and chest pain score.

[0013] By adopting the above-mentioned technical solution, patient data can be input in real time, the system will perform calculations and analyses instantly, and intuitively display risk assessment results, prevention suggestions, early warning information and treatment plan recommendations on the interface. It can comprehensively and accurately manage VTE risks and help doctors provide auxiliary reference results for patients' conditions and subsequent treatments. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0015] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] Reference Figure 1 , an intelligent VTE prevention and treatment system according to an embodiment of the present invention is characterized by comprising: The risk assessment module is used to obtain the risk index of VTE based on risk factors.

[0018] The risk index of VTE obtained according to the risk factors includes: VTE risk index = log(Σ(wi×fi))×exp(Δt / τ)+ε(G); Among them, wi is the weight of each risk factor, which can be dynamically adjusted according to historical data through machine learning algorithms. fi is the quantitative value of the risk factor. Δt is the time since the patient was admitted to the hospital (in days), and τ is the time decay constant, which is used to reflect the change of risk over time. ε(G) is the genetic risk correction function, which can be personalized according to the patient's genetic test results.

[0019] Among them, the various risk factors include: Age: Enter the actual age value, and the system will quantify it according to the preset age risk curve. BMI: Automatically calculated based on height and weight, and compared with the WHO standard BMI classification. Type of surgery: Use the preset surgical risk level (level 1-5), such as level 1 for low-risk outpatient surgery and level 5 for high-risk major surgery. Complexity of surgery: Enter after evaluation by the surgeon (1-10 points), taking into account factors such as operation time and amount of bleeding. Number of previous VTE histories: Enter the number directly, and the system will assign different weights based on the number of times.

[0020] The preventive measures recommendation module is used to recommend preventive measures based on clinical data.

[0021] The preventive measures recommended based on clinical data include: Preventive measures effectiveness index = (Π(1+Ei×Ci))^(1 / n)×(1-exp(-λ×t)); Where: Ei is the effect coefficient of each preventive measure, Ci is the compliance of each preventive measure, n is the number of preventive measures taken, λ is the learning rate, which reflects the system optimization speed and is usually set to 0.01, and t is the system running time Specifically, the system has built-in a series of preventive measures, including: mechanical prevention: intermittent pneumatic compression device (IPC), gradient compression stockings (GCS), drug prevention: low molecular weight heparin (LMWH), direct oral anticoagulants (DOAC), lifestyle intervention: early activity, appropriate water intake.

[0022] The VTE early warning module is used to obtain the early warning index of VTE based on imaging data, laboratory test results and clinical symptoms.

[0023] The early warning index for VTE based on imaging data, laboratory test results and clinical symptoms includes: VTE warning index = tanh(W1×CNN(I)+W2×RNN(L)+W3×FCN(S))×σ(t) Among them: CNN, RNN, FCN are neural networks for processing imaging experimental data, laboratory test results and clinical symptom data, respectively; I, L, S are imaging experimental data, laboratory test results and clinical symptom data, respectively; W1, W2, W3 are weights of each modality, with initial values ​​set to 0.4, 0.3, 0.3, and then automatically adjusted through the back propagation algorithm; σ(t) is the time sensitivity function, defined as: σ(t)=1 / (1+exp(-0.1×(t-10))).

[0024] Specifically, imaging data processing: The pre-trained ResNet50 convolutional neural network was used to process lower limb venous ultrasound images and CT pulmonary angiography images after transfer learning.

[0025] The network output is an anomaly probability score (between 0 and 1).

[0026] Analysis of laboratory test results: Long short-term memory network (LSTM) was used to analyze the dynamic changes of D-dimer level, platelet count, prothrombin time and other indicators.

[0027] The network output is the abnormality score of each indicator (between 0 and 1).

[0028] Clinical symptom assessment: The data such as lower limb swelling degree, dyspnea score, and chest pain score were processed by multi-layer perceptron (MLP).

[0029] The output of the network is a symptom severity score (between 0 and 1).

[0030] Specifically, the imaging data include: lower limb venous ultrasound images, CT pulmonary angiography images, laboratory test results include: D-dimer level, platelet count, prothrombin time, clinical symptom data include: lower limb swelling degree, dyspnea score, chest pain score.

[0031] Treatment optimization module is used to adjust the treatment plan based on individual characteristics, treatment response and drug interactions.

[0032] Specifically, the adjustment of the treatment regimen according to individual characteristics, treatment response and drug interactions includes: Treatment plan optimization index = argmax(Σ(αi×log(Ei+1)-βj×exp(Cj))×Φ(x,y)) Where: Ei is the expected effect of each treatment plan, Cj is the risk and cost of each treatment plan, αi, βj are balance coefficients, and Φ(x, y) is the matching function between the individual characteristics of the patient and the treatment plan.

[0033] Assuming α=1, β=0.5, Φ(x,y) are 0.9, 0.8, and 0.6 respectively, the optimization index is calculated as follows: Solution 1: (1log(0.8+1)-0.5exp(0.3))×0.9=0.38 Solution 2: (1log(0.85+1)-0.5exp(0.4))×0.8=0.33 Solution 3: (1log(0.9+1)-0.5exp(0.7))×0.6=0.13 The system will recommend Plan 1 to the doctor to assist the doctor in making a selection.

[0034] This embodiment provides an intelligent VTE prevention and treatment system. Medical staff can input patient data in real time. The system will perform calculations and analyses immediately and intuitively display risk assessment results, prevention suggestions, early warning information and treatment plan recommendations on the interface. It can comprehensively and accurately manage VTE risks and help doctors provide auxiliary reference results for patients' conditions and subsequent treatments.

[0035] For the convenience of description, the above devices are described in terms of functions and are divided into various units and modules. Of course, when implementing the present application, the functions of each unit and module can be implemented in the same or multiple software and / or hardware.

[0036] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined.

[0037] For the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0038] It can be known from the description of the above implementation modes that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute the methods described in the various implementation modes of the present application or certain parts of the implementation modes.

[0039] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent VTE prevention and treatment system, characterized in that: include: Risk assessment module, used to obtain the risk index of VTE based on risk factors; The preventive measures recommendation module is used to recommend preventive measures based on clinical data; VTE early warning module, used to obtain VTE early warning index based on imaging data, laboratory test results and clinical symptoms; Treatment optimization module is used to adjust the treatment plan based on individual characteristics, treatment response and drug interactions.

2. The system according to claim 1, characterized in that The risk index of VTE obtained according to the risk factors includes: VTE risk index = log(Σ(wi×fi))×exp(Δt / τ)+ε(G); Where: wi is the weight of each risk factor, fi is the quantitative value of the risk factor, Δt is the time since admission, τ is the time decay constant, and ε(G) is the genetic risk correction function.

3. The system according to claim 1, characterized in that The preventive measures recommended based on clinical data include: Preventive measures effectiveness index = (Π(1+Ei×Ci))^(1 / n)×(1-exp(-λ×t)); Where: Ei is the effectiveness coefficient of each preventive measure, Ci is the compliance of each preventive measure, n is the number of preventive measures taken, λ is the learning rate, and t is the system operation time.

4. The system according to claim 1, characterized in that The early warning index for VTE based on imaging data, laboratory test results and clinical symptoms includes: VTE warning index = tanh(W1×CNN(I)+W2×RNN(L)+W3×FCN(S))×σ(t); Among them: CNN, RNN, FCN are neural networks for processing imaging experiment data, laboratory test results and clinical symptom data respectively, I, L, S are imaging experiment data, laboratory test results and clinical symptom data respectively, W1, W2, W3 are the weights of each modality, and σ(t) is the time sensitivity function.

5. The system according to claim 1, characterized in that Adjustments to treatment regimens based on individual characteristics, treatment response, and drug interactions include: Treatment optimization index = argmax(Σ(αi×log(Ei+1)-βj×exp(Cj))×Φ(x,y)); Where: Ei is the expected effect of each treatment plan, Cj is the risk and cost of each treatment plan, αi, βj are balance coefficients, and Φ(x, y) is the matching function between the patient's individual characteristics and the treatment plan.

6. The system according to claim 3, characterized in that The risk factors included age, BMI, type of surgery, complexity of surgery, and number of previous VTEs.

7. The system according to claim 4, characterized in that The imaging data include: lower limb venous ultrasound images and CT pulmonary angiography images.

8. The system according to claim 4, characterized in that The laboratory test result data include: D-dimer level, platelet count, and prothrombin time.

9. The system according to claim 4, characterized in that The clinical symptom data include: lower limb swelling degree, dyspnea score, and chest pain score.

Images