Intelligent early warning and prevention and control system for pediatric infectious diseases

Abstract

The invention discloses an intelligent early warning, prevention and control system for pediatric infectious diseases, and the system comprises a data unit which is used for carrying out the butt joint of hospital information, laboratory information and an electronic medical record system, and obtaining a corresponding physiological feature vector and a physiological feature time sequence; the first infection risk early warning unit is used for calculating the infection probability of the pediatric patient through a logistic regression algorithm based on the physiological feature vector and generating a first early warning signal in time; the second infection risk early warning unit is used for calculating predicted physiological feature data and corresponding residual errors of the pediatric patient through a time sequence analysis algorithm on the basis of the physiological feature time sequence, and generating a second early warning signal in good time; and the propagation risk early warning unit is used for constructing a contact network, a pathogen propagation probability model and a propagation risk dynamic evaluation model. Therefore, the early warning accuracy and timeliness of pediatric infectious diseases can be effectively improved, the misdiagnosis rate can be reduced, the risk of cross infection can be reduced, and medical resource allocation can be optimized.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to an intelligent early warning and prevention and control system for pediatric infectious diseases. Background Art

[0002] In the field of pediatric medicine, traditional management of pediatric infectious diseases mainly relies on doctors' experience and judgment and routine clinical testing methods. For example, doctors will conduct a comprehensive analysis based on the child's symptoms, signs and laboratory test results to assess whether the child has an infectious disease and formulate a corresponding treatment plan.

[0003] In addition, medical institutions usually adopt fixed isolation measures to prevent the spread of pathogens, such as placing children with suspected or confirmed infection in specific isolation wards, restricting their range of activities, and tracking and observing close contacts.

[0004] In recent years, with the popularization of information technology, medical institutions have gradually developed digital platforms such as electronic medical record systems, hospital information systems, and laboratory information systems, which can provide more detailed data support for the diagnosis of pediatric infectious diseases. These systems can record detailed diagnosis and treatment information of children. By integrating the above-mentioned multi-source heterogeneous data, medical staff can have a more comprehensive understanding of the development of the child's disease, thereby making more accurate diagnostic decisions.

[0005] However, under the current technical framework, the early warning mechanism for pediatric infectious diseases still has certain limitations. On the one hand, most existing early warning models are based on static data analysis and fail to fully consider the impact of time series characteristics on human health status. On the other hand, due to the lack of effective dynamic risk assessment tools, it is difficult to predict the possibility of disease outbreaks and their transmission paths in a timely and accurate manner. Therefore, an intelligent early warning and prevention and control system for pediatric infectious diseases is of practical significance. Summary of the Invention

[0006] The present invention aims to solve the technical problems in the above-mentioned technologies at least to some extent.

[0007] To this end, the present invention discloses an intelligent early warning and prevention and control system for pediatric infectious diseases, comprising:

[0008] Data unit, used to connect with hospital information systems, laboratory information systems, and electronic medical record systems to collect physiological characteristics of pediatric patients and generate physiological characteristic vectors and physiological characteristic time series;

[0009] a first infection risk warning unit, configured to receive the physiological characteristic vector, calculate the infection probability of the pediatric patient based on the physiological characteristic vector using a logistic regression algorithm, and generate a first warning signal when the infection probability is greater than or equal to a first preset threshold;

[0010] a second infection risk warning unit, configured to receive the physiological characteristic time series, calculate the predicted physiological characteristic data and the corresponding residual of the pediatric patient based on the physiological characteristic time series using a time series analysis algorithm, and generate a second warning signal when the residual is greater than a second preset threshold;

[0011] A transmission risk warning unit is configured to receive the first warning signal and the second warning signal, and after receiving the first warning signal and the second warning signal, construct a contact network, a pathogen transmission probability model, and a transmission risk dynamic assessment model, wherein:

[0012] When constructing the contact network, the transmission risk warning unit determines the area where the pediatric patient is located and other areas directly adjacent to the area where the pediatric patient is located using a preset area division method to obtain the contact network, specifically, G = (U, V, W), where U is the area where the pediatric patient is located, V = (v1, v2, ..., v n ) are other areas directly adjacent to the area where the pediatric patient is located, W=(ω1,ω2,…,ω n ) is the weight of other areas directly adjacent to the area where the pediatric patient is located;

[0013] When constructing the pathogen transmission probability model, the transmission risk warning unit calculates the transmission probability of each of the other areas directly adjacent to the area where the pediatric patient is located, specifically, Among them, λ is the pathogen transmission ability parameter;

[0014] When constructing the dynamic assessment model of transmission risk, the transmission risk warning unit traverses other areas directly adjacent to the area where the pediatric patient is located to determine whether the transmission probability is greater than or equal to a third preset threshold. If so, an iterative algorithm is used to calculate other areas directly adjacent to the area where the transmission probability is greater than or equal to the third preset threshold, and at the same time, the contact network G = (U, V, W) is updated.

[0015] The intelligent early warning and prevention and control system for pediatric infectious diseases disclosed in the present invention can effectively improve the accuracy and timeliness of early warning of pediatric infectious diseases and reduce the misdiagnosis rate, as well as reduce the risk of cross infection and optimize the allocation of medical resources.

[0016] In addition, the pediatric infectious disease intelligent early warning and prevention and control system disclosed in the present invention may also have the following additional technical features:

[0017] In one embodiment of the present invention, in the data acquisition unit, physiological characteristics of pediatric patients are collected, including but not limited to: body temperature x1, heart rate x2 and respiratory rate x3, the physiological characteristic vector is X = [x1, x2, x3], and the physiological characteristic time series is x1(t), x2(t), x3(t).

[0018] In one embodiment of the present invention, in the first infection risk warning unit, the logistic regression algorithm is Among them, the parameter vector is θ=[θ1,θ2,…,θ n ], when the pediatric patient is infected, Y=1, and when the pediatric patient is not infected, Y=0.

[0019] In one embodiment of the present invention, in the second infection risk warning unit, the time series analysis algorithm is φ p (B)(1-B) d x1(t)=θ q (B)∈(t), where the p-order autoregressive polynomial is φ p (B), the q-order moving average polynomial is θ q (B), the difference order is d, the white noise sequence is ∈(t), the backshift operator is B, and the body temperature residual is e(t)=x1(t)-x'1(t), wherein the actual body temperature of the pediatric patient is x1(t) and the predicted body temperature of the pediatric patient is x'1(t).

[0020] In one embodiment of the present invention, when the body temperature residual e(t) is greater than a second preset threshold, and the actual heart rate x2(t) or respiratory rate x3(t) of the pediatric patient is disordered, a second warning signal is generated.

[0021] In one embodiment of the present invention, in the transmission risk warning unit, the area where the pediatric patient is located is determined by a square area division method or a regular hexagonal area division method.

[0022] In one embodiment of the present invention, in the propagation risk early warning unit, ω i =α1Z i +α2Z', where the population density in the corresponding area is Z i , the transmission rate of pediatric infectious diseases is Z', α1, α2 are weighted coefficients respectively.

[0023] In one embodiment of the present invention, it further comprises:

[0024] Storage unit for storing historical pediatric patient data {(X1, Y1), (X2, Y2), …, (X n ,Y n )}.

[0025] Additional contents and advantages of the present invention will be given in the following description or can be understood through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The technical solutions and beneficial effects of the present invention will become apparent and easily understood from the following contents in conjunction with the accompanying drawings, in which:

[0027] Figure 1 This is a system block diagram of the intelligent early warning and prevention system for pediatric infectious diseases of the present invention;

[0028] Figure 2 This is a workflow diagram of the intelligent early warning and prevention and control system for pediatric infectious diseases of the present invention. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0030] The following will describe the pediatric infectious disease intelligent early warning and prevention and control system disclosed in the present invention with reference to the accompanying drawings.

[0031] like Figure 1 and Figure 2 As shown, a pediatric infectious disease intelligent early warning and prevention and control system 100 includes:

[0032] Data unit 101 is used to connect with the hospital information system, laboratory information system and electronic medical record system to collect physiological characteristics of pediatric patients and generate physiological characteristic vectors and physiological characteristic time series;

[0033] Specifically, in the data collection unit, physiological characteristics of pediatric patients are collected, including but not limited to: body temperature x1, heart rate x2 and respiratory rate x3. The physiological characteristic vector is X = [x1, x2, x3], and the physiological characteristic time series is x1(t), x2(t), x3(t);

[0034] a first infection risk warning unit 102, configured to receive a physiological feature vector, calculate the infection probability of the pediatric patient based on the physiological feature vector using a logistic regression algorithm, and generate a first warning signal when the infection probability is greater than or equal to a first preset threshold;

[0035] Specifically, in the first infection risk warning unit 102, the logistic regression algorithm is Among them, the parameter vector is θ=[θ1,θ2,…,θ n ], Y = 1 when the pediatric patient is infected, and Y = 0 when the pediatric patient is not infected;

[0036] The second infection risk warning unit 103 is configured to receive a physiological characteristic time series, calculate predicted physiological characteristic data of the pediatric patient and a corresponding residual based on the physiological characteristic time series using a time series analysis algorithm, and generate a second warning signal when the residual is greater than a second preset threshold;

[0037] Specifically, in the second infection risk warning unit 103, the time series analysis algorithm is φ p (B)1-B) d x1(t)=θ q (B)∈(t), where the p-order autoregressive polynomial is φ p (B), the q-order moving average polynomial is θ q (B), the difference order is d, the white noise sequence is ∈(t), the backshift operator is B, and the body temperature residual is e(t) = x1(t) - x'1(t), where the actual body temperature of the pediatric patient is x1(t) and the predicted body temperature of the pediatric patient is x'1(t);

[0038] When the body temperature residual e(t) is greater than a second preset threshold, and the actual heart rate x2(t) or respiratory rate x3(t) of the pediatric patient is disordered, a second warning signal is generated;

[0039] The transmission risk warning unit 104 is configured to receive the first warning signal and the second warning signal, and after receiving the first warning signal and the second warning signal, construct a contact network, a pathogen transmission probability model, and a transmission risk dynamic assessment model, wherein:

[0040] When constructing the contact network, the transmission risk warning unit 104 determines the area where the pediatric patient is located and other areas directly adjacent to the area where the pediatric patient is located using a preset area division method to obtain the contact network. Specifically, G = (U, V, W), where U is the area where the pediatric patient is located, and V = (v1, v2, ..., v n ) are other areas directly adjacent to the area where pediatric patients are located, W=(ω1,ω2,…,ω n ) is the weight of other areas directly adjacent to the area where the pediatric patient is located;

[0041] When constructing the pathogen transmission probability model, the transmission risk warning unit 104 calculates the transmission probability of each of the other areas directly adjacent to the area where the pediatric patient is located, specifically, Among them, λ is the pathogen transmission ability parameter;

[0042] When constructing the dynamic assessment model for transmission risk, the transmission risk warning unit 104 checks whether the transmission probability of other areas directly adjacent to the area where the pediatric patient is located is greater than or equal to a third preset threshold. If so, the transmission risk warning unit 104 calculates other areas directly adjacent to the area with a transmission probability greater than or equal to the third preset threshold through an iterative algorithm, and simultaneously updates the contact network G = (U, V, W);

[0043] Specifically, in the transmission risk warning unit 104, the area where the pediatric patient is located is determined by using a square area division method or a regular hexagonal area division method;

[0044] In addition, it should be noted that in the propagation risk warning unit 104, ω i =α1Z i +α2Z', where the population density in the corresponding area is Z i , the transmission rate of pediatric infectious diseases is Z', α1, α2 are weighted coefficients respectively;

[0045] As a possibility, the pediatric infectious disease intelligent early warning and prevention and control system 100 further includes:

[0046] Storage unit 105, used to store historical pediatric patient data {(X1, Y1), (X2, Y2), ..., (X n ,Y n )}.

[0047] In the present invention, when the pediatric infectious disease intelligent early warning and prevention and control system 100 starts running, the data unit 101 continuously obtains the physiological data of the child from the hospital information system, laboratory information system and electronic medical record system, for example, collecting body temperature, heart rate and respiratory rate data every 30 minutes;

[0048] For the first infection risk warning unit 102, it is assumed that the parameter vector θ in the logistic regression model is obtained through analysis and training of a large amount of historical data. For example, when a physiological feature vector X = [38.5, 120, 30] of a child is received, it is substituted into the logistic regression algorithm to calculate the infection probability P(Y = 1|X). If the calculated infection probability is greater than a preset first threshold (assuming it is 0.7), a first warning signal is generated;

[0049] The second infection risk warning unit 103 analyzes the collected physiological characteristic time series. For example, for a child's body temperature time series data, the predicted body temperature x'1(t) is calculated using a time series analysis algorithm, and the body temperature residual e(t) is obtained. If e(t) is greater than a second preset threshold (assuming it is 1.5), and at the same time, the child's heart rate fluctuates greatly (such as the heart rate suddenly increases to 150 times / min and lasts for a period of time) or the respiratory rate is abnormal (such as the respiratory rate increases to 40 times / min and lasts for a period of time), a second warning signal is generated;

[0050] When the transmission risk warning unit 104 receives the first warning signal and the second warning signal, it starts to build a contact network. For example, it uses the square area division method to divide the hospital into multiple areas, determine the area U where the child who issued the warning signal is located and the adjacent area V, and then calculate the contact network based on the regional population density Z. i and disease transmission rate Z' i Calculate the adjacent area weight ω i , and then build a pathogen transmission probability model to calculate the transmission probability p of adjacent areas i If the probability of transmission in a certain adjacent area is found to be greater than the third preset threshold (assuming it is 0.6), the iterative algorithm will further analyze other adjacent areas of the area and update the contact network at the same time so that isolation, prevention and control measures can be taken in a timely manner to prevent the further spread of the disease;

[0051] Throughout the entire process, the storage unit 105 continuously stores historical patient data, which provides a basis for subsequent model optimization and improvement. For example, as new cases increase, the parameter vector θ of the logistic regression model can be regularly retrained to make the early warning model more accurate.

[0052] In summary, the pediatric infectious disease intelligent early warning and prevention and control system 100 disclosed in the present invention can effectively improve the accuracy and timeliness of early warning of pediatric infectious diseases and reduce the misdiagnosis rate, as well as reduce the risk of cross infection and optimize the allocation of medical resources.

[0053] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying 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 orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0054] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0055] In the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connect," "fixed," etc. should be understood broadly. For example, they may refer to fixed connection, detachable connection, or integration; mechanical connection or electrical connection; direct connection or indirect connection through an intermediate medium; internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0056] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0057] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0058] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. An intelligent early warning and prevention system for pediatric infectious diseases, characterized by: include: Data unit, used to connect with hospital information systems, laboratory information systems, and electronic medical record systems to collect physiological characteristics of pediatric patients and generate physiological characteristic vectors and physiological characteristic time series; a first infection risk warning unit, configured to receive the physiological characteristic vector, calculate the infection probability of the pediatric patient based on the physiological characteristic vector using a logistic regression algorithm, and generate a first warning signal when the infection probability is greater than or equal to a first preset threshold; a second infection risk warning unit, configured to receive the physiological characteristic time series, calculate the predicted physiological characteristic data and the corresponding residual of the pediatric patient based on the physiological characteristic time series using a time series analysis algorithm, and generate a second warning signal when the residual is greater than a second preset threshold; A transmission risk warning unit is configured to receive the first warning signal and the second warning signal, and after receiving the first warning signal and the second warning signal, construct a contact network, a pathogen transmission probability model, and a transmission risk dynamic assessment model, wherein: When constructing the contact network, the transmission risk warning unit determines the area where the pediatric patient is located and other areas directly adjacent to the area where the pediatric patient is located using a preset area division method to obtain the contact network, specifically, G = (U, V, W), where U is the area where the pediatric patient is located, V = (v1, v2, ..., v n ) are other areas directly adjacent to the area where the pediatric patient is located, W=(ω1,ω2,…,ω n ) is the weight of other areas directly adjacent to the area where the pediatric patient is located; When constructing the pathogen transmission probability model, the transmission risk warning unit calculates the transmission probability of each of the other areas directly adjacent to the area where the pediatric patient is located, specifically, Among them, λ is the pathogen transmission ability parameter; When constructing the dynamic assessment model of transmission risk, the transmission risk warning unit traverses other areas directly adjacent to the area where the pediatric patient is located to determine whether the transmission probability is greater than or equal to a third preset threshold. If so, an iterative algorithm is used to calculate other areas directly adjacent to the area where the transmission probability is greater than or equal to the third preset threshold, and at the same time, the contact network G = (U, V, W) is updated.

2. The intelligent early warning and prevention and control system for pediatric infectious diseases according to claim 1, characterized in that: In the data acquisition unit, physiological characteristics of pediatric patients are collected, including but not limited to: body temperature x1, heart rate x2 and respiratory rate x3. The physiological characteristic vector is X=[x1, x2, x3], and the physiological characteristic time series is x1(t), x2(t), x3(t).

3. The intelligent early warning and prevention system for pediatric infectious diseases according to claim 2, characterized in that: In the first infection risk warning unit, the logistic regression algorithm is Among them, the parameter vector is θ=[θ1,θ2,…,θ n ], when the pediatric patient is infected, Y=1, and when the pediatric patient is not infected, Y=0.

4. The intelligent early warning and prevention and control system for pediatric infectious diseases according to claim 3, characterized in that: In the second infection risk warning unit, the time series analysis algorithm is φ p (B)(1-B) d x1(t)=θ q (B)∈(t), where the p-order autoregressive polynomial is φ p (B), the q-order moving average polynomial is θ q (B), the difference order is d, the white noise sequence is ∈(t), the backshift operator is B, and the body temperature residual is e(t)=x1(t)-x'1(t), wherein the actual body temperature of the pediatric patient is x1(t) and the predicted body temperature of the pediatric patient is x'1(t).

5. The intelligent early warning and prevention system for pediatric infectious diseases according to claim 4, characterized in that: When the body temperature residual e(t) is greater than a second preset threshold, and the actual heart rate x2(t) or respiratory rate x3(t) of the pediatric patient is disordered, a second warning signal is generated.

6. The intelligent early warning and prevention system for pediatric infectious diseases according to claim 1, characterized in that: In the transmission risk warning unit, the area where the pediatric patient is located is determined by a square area division method or a regular hexagonal area division method.

7. The intelligent early warning and prevention system for pediatric infectious diseases according to claim 1, characterized in that: In the transmission risk early warning unit, ω i =α1Z i +α2Z', where the population density in the corresponding area is Z i , the transmission rate of pediatric infectious diseases is Z', α1, α2 are weighted coefficients respectively.

8. The intelligent early warning and prevention system for pediatric infectious diseases according to claim 3, characterized in that: Also includes: Storage unit for storing historical pediatric patient data {(X1, Y1), (X2, Y2), …, (X n ,Y n )}.

Images