Application method and system of the whole course management platform based on patient information

Abstract

The present application relates to an application method and system of a full course of disease management platform based on patient information, and belongs to the field of smart medical technology. The method includes: collecting patient information; preprocessing patient information, and extracting the first key feature in the patient information based on the preprocessing result; constructing a full course of disease network architecture based on the first key feature, and extracting the second key feature in the full course of disease network architecture; inputting the target second key feature into the pre-constructed potential risk assessment model to obtain the potential risk assessment result; calculating the stability coefficient between the target risk assessment result and the target first key feature, and determining whether to issue a health reminder based on the stability coefficient. The present application can realize the full course of disease analysis and processing of patient information, thereby performing efficient intelligent tracking, and then giving health reminders in a timely manner, reducing the labor intensity of medical staff, and improving work efficiency and service quality.

Description

Technical Field

[0001] The present application relates to the field of smart medical technology, and in particular to an application method and system for a full-course disease management platform based on patient information. Background Art

[0002] With the continuous development of science and technology, computer technology has been more and more widely used in medical systems. In the existing technology, the medical system can only process a single or several links of the disease course, but cannot process the entire disease course. As a result, in the process of health supervision, there is a lack of timely and effective tracking between doctors and patients, and it is difficult to give corresponding health tips in a timely manner.

[0003] Therefore, there is an urgent need to propose an application method and system for a full-course management platform based on patient information that can effectively analyze patient information. Summary of the invention

[0004] Based on this, it is necessary to provide an application method and system for a full-course management platform based on patient information that can effectively analyze patient information in response to the above-mentioned technical problems.

[0005] On the one hand, a method for applying a full course of disease management platform based on patient information is provided, the method comprising:

[0006] Collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habits information and economic status information;

[0007] Preprocessing the patient information, and extracting a first key feature from the patient information according to a preprocessing result;

[0008] Based on the first key feature, construct a full-course network architecture, and extract a second key feature in the full-course network architecture;

[0009] Inputting the second key characteristic of the target into a pre-built potential risk assessment model to obtain a potential risk assessment result;

[0010] The stability coefficient between the target risk assessment result and the target first key feature is calculated and obtained, and based on the stability coefficient, it is determined whether to issue a health reminder.

[0011] Optionally, the patient information preprocessing method includes:

[0012] Performing data cleaning on the patient information;

[0013] Based on the first preset mapping table, determine the value corresponding to the patient information after data cleaning;

[0014] The value corresponding to the patient information corresponding to the target time node is input into a second preset mapping table, and based on the second preset mapping table, the first key feature in the patient information is extracted.

[0015] Optionally, extracting the first key feature from the patient information according to the preprocessing result includes:

[0016] Calculate the absolute value of the difference between the target patient information in the target time node and the adjacent time nodes;

[0017] In response to detecting that the absolute value of the difference is greater than a first preset value, the patient information corresponding to the target time node is defined as a first key feature.

[0018] Optionally, based on the first key feature, constructing a full-course network architecture includes:

[0019] Obtain target patient information and target time node corresponding to the first key feature;

[0020] The target time node is used as the x-coordinate in the target network architecture, the assigned value corresponding to the patient diagnosis and treatment information in the target patient information is used as the y-coordinate in the target network architecture, and the fitting value of the mean of the assigned values ​​corresponding to other information in the target patient information except the patient diagnosis and treatment information is used as the z-coordinate in the target network architecture. The calculation formula of the fitting value includes:

[0021]

[0022] in, represents the fitted value, represents the mean value of the assigned values ​​corresponding to the patient's living environment information, represents the mean value of the assigned values ​​corresponding to the living habit information, represents the mean value of the assigned value corresponding to the economic status information, , , All represent weight coefficients;

[0023] The target network architecture is defined to include a plurality of three-dimensional coordinates (x, y, z), and the relevant values ​​and time nodes corresponding to the patient information corresponding to the plurality of first key features are mapped into the target network architecture to generate the full course of disease network architecture.

[0024] Optionally, extracting the second key feature in the full course of disease network architecture includes:

[0025] Calculate the slope values ​​of multiple three-dimensional coordinates corresponding to the target time node in the target network architecture and the coordinate origin respectively, and sort them according to the size of the slope value;

[0026] In response to detecting that the difference between the maximum slope value and the minimum slope value is greater than a second preset value, removing the maximum slope value and the minimum slope value, and calculating an average value of the remaining slope values;

[0027] In response to detecting that the difference between the maximum slope value and the minimum slope value is less than or equal to a second preset value, calculating an average value of all slope values;

[0028] In response to detecting that the average value is greater than a third preset value, a patient information-related value corresponding to a target time node corresponding to the average value is determined as the second key feature.

[0029] Optionally, the second key feature of the target is input into a pre-built potential risk assessment model to obtain potential risk assessment results including:

[0030] Acquire a second key feature of the target, where the second key feature of the target includes a second key feature corresponding to a current time node and a second key feature corresponding to an adjacent time node;

[0031] The current second key feature and the adjacent second key feature are input into a pre-built potential risk assessment model, wherein the pre-built potential risk assessment model includes:

[0032]

[0033] in, Indicated in The state value corresponding to the time node, represents the correction function, Indicated in The state value corresponding to the time node, , is the coupling coefficient, respectively. Time nodes and The strength of the coupling relationship between time nodes in the whole disease course network architecture, express The number of three-dimensional coordinate nodes corresponding to the time node, It means the medication is effective. Indicates the drug injury factor, represents the sum of the weighted patient information parameter variables, express The patient information parameter variable value corresponding to the time node, represents a constant;

[0034] based on The state value corresponding to the time node and the third preset mapping table determine the potential risk assessment result.

[0035] Optionally, calculating and obtaining a stability coefficient between the target risk assessment result and the target first key feature includes:

[0036] In response to detecting that the potential risk assessment result is greater than a fourth preset value, a stability coefficient between the target risk assessment result and the target first key feature is calculated based on an objective function, wherein the objective function includes:

[0037]

[0038] in, represents the stability coefficient, Represents the average value of the patient information corresponding to the first key feature of the target, Represents the sum of the probabilities of the patient information corresponding to the first key feature of the target stimulating risk, represents the risk factor, Indicates the time dimension assignment, Indicates potential risk assessment results.

[0039] Optionally, determining whether to issue a health reminder according to the stability coefficient includes:

[0040] In response to detecting that the stability coefficient is less than a fifth preset value, a health prompt is issued to the terminal.

[0041] On the other hand, an application system of a full course of disease management platform based on patient information is provided, the system comprising:

[0042] An information collection module is used to collect patient information, wherein the patient information includes at least: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information;

[0043] A preprocessing module, used for preprocessing the patient information and extracting a first key feature from the patient information according to the preprocessing result;

[0044] A feature extraction module, used to construct a full-course network architecture based on the first key feature, and extract a second key feature in the full-course network architecture;

[0045] A risk assessment module, used to input the second key feature of the target into a pre-built potential risk assessment model to obtain a potential risk assessment result;

[0046] The health prompt module is used to calculate the stability coefficient between the target risk assessment result and the first key feature of the target, and determine whether to issue a health prompt based on the stability coefficient.

[0047] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0048] Collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habits information and economic status information;

[0049] Preprocessing the patient information, and extracting a first key feature from the patient information according to a preprocessing result;

[0050] Based on the first key feature, construct a full-course network architecture, and extract a second key feature in the full-course network architecture;

[0051] Inputting the second key characteristic of the target into a pre-built potential risk assessment model to obtain a potential risk assessment result;

[0052] The stability coefficient between the target risk assessment result and the target first key feature is calculated and obtained, and based on the stability coefficient, it is determined whether to issue a health reminder.

[0053] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0054] Collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habits information and economic status information;

[0055] Preprocessing the patient information, and extracting a first key feature from the patient information according to a preprocessing result;

[0056] Based on the first key feature, construct a full-course network architecture, and extract a second key feature in the full-course network architecture;

[0057] Inputting the second key characteristic of the target into a pre-built potential risk assessment model to obtain a potential risk assessment result;

[0058] The stability coefficient between the target risk assessment result and the target first key feature is calculated and obtained, and based on the stability coefficient, it is determined whether to issue a health reminder.

[0059] The above-mentioned application method and system of the full-course management platform based on patient information, the method includes: collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information; preprocessing the patient information, and extracting the first key feature in the patient information based on the preprocessing result; based on the first key feature, constructing a full-course network architecture, and extracting the second key feature in the full-course network architecture; inputting the target second key feature into the pre-constructed potential risk assessment model to obtain a potential risk assessment result; calculating the stability coefficient between the target risk assessment result and the target first key feature, and determining whether to issue a health prompt based on the stability coefficient. The present application can realize the full-course analysis and processing of patient information, thereby performing efficient intelligent tracking, and then giving health prompts in a timely manner, reducing the labor intensity of medical staff, and improving work efficiency and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is an application environment diagram of an application method of a full-course management platform based on patient information in one embodiment;

[0061] Figure 2 It is a flowchart of an application method of a full course of disease management platform based on patient information in one embodiment;

[0062] Figure 3 It is a structural block diagram of an application system of a full course of disease management platform based on patient information in one embodiment;

[0063] Figure 4 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] It should be understood that in the description of the present application, unless the context clearly requires otherwise, words such as "include", "comprises", and the like throughout the specification should be interpreted as including rather than being exclusive or exhaustive; that is, as including but not limited to.

[0066] It should also be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of this application, unless otherwise specified, "plurality" means two or more.

[0067] It should be noted that the terms "S1", "S2", etc. are only used for the purpose of describing the steps, and do not specifically refer to the order or sequence, nor are they used to limit the present application. They are only for the convenience of describing the method of the present application, and cannot be understood as indicating the order of the steps. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0068] The application method of the full course of disease management platform based on patient information provided in this application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the data processing platform set on the server 104 through the network, wherein the terminal 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0069] In one embodiment, Figure 2 As shown, an application method of a full course of disease management platform based on patient information is provided. Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0070] S1: Collecting patient information, which includes at least: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information.

[0071] It should be noted that patient diagnosis and treatment information may include basic information about the patient (such as age, gender, etc.), symptom information (such as a certain high value in the blood, abnormal data in the CT image, etc.), past medical history and treatment methods, etc.; patient living environment information may include direct environmental factors that cause the above symptoms (such as environmental pollution values, etc.); lifestyle information may include direct lifestyle factors that cause the above symptoms (such as staying up late, irregular diet, etc.); economic status information may include medical insurance payment information, etc., and the economic value that patients can afford for the treatment of the above diseases, and determine the type of commonly used drugs based on the economic value to further determine the effectiveness of the drugs and other information.

[0072] S2: Preprocess the patient information, and extract the first key feature in the patient information according to the preprocessing result.

[0073] It should be noted that, in some specific implementations, the patient information preprocessing method includes:

[0074] Performing data cleaning on the patient information, wherein data cleaning is generally used to check data consistency, process invalid values ​​and missing values, and correct errors in the data. The cleaning methods generally include duplicate data cleaning, incomplete data cleaning, data format cleaning, etc. Data cleaning is performed on the patient information to ensure that the data for subsequent risk assessment is more accurate and to improve the accuracy of health reminder information;

[0075] Based on the first preset mapping table, determining the value corresponding to the patient information after data cleaning, wherein the first preset mapping table includes at least one mapping relationship between patient information and its value, and the value data is a numerical value obtained through multiple tests combined with expert scoring;

[0076] The assignment corresponding to the patient information corresponding to the target time node is input into a second preset mapping table, and based on the second preset mapping table, the first key feature in the patient information is extracted, wherein the second preset mapping table includes at least a mapping relationship between a time node and the assignment corresponding to the patient information, and there can be multiple assignments of patient information corresponding to a time node.

[0077] In some specific embodiments, extracting the first key feature from the patient information according to the preprocessing result includes:

[0078] Calculate the absolute value of the difference between the values ​​assigned to the target patient information at the target time node and the adjacent time node, wherein the calculation of the absolute value of the difference between the target patient information can be the absolute value of the difference between two separate values, such as the absolute value of the difference between two values ​​corresponding to a certain high value in the blood in the symptom information, or the absolute value of the difference between the average values ​​of multiple values ​​corresponding to two time nodes. The corresponding data calculation basis can be determined according to the actual situation;

[0079] In response to detecting that the absolute value of the difference is greater than the first preset value, the patient information corresponding to the target time node is defined as the first key feature, that is, the target time node is determined by calculating the absolute value of the difference. After the target time node is determined, according to the second preset mapping table, the assignment of all patient information corresponding to the target time node is used as the first key feature for subsequent construction of the full disease course network structure, wherein the first preset value can be set according to actual conditions.

[0080] S3: Based on the first key feature, construct a full-course network architecture, and extract the second key feature in the full-course network architecture.

[0081] It should be noted that this step specifically includes:

[0082] Obtain target patient information and target time node corresponding to the first key feature;

[0083] The target time node is used as the x-coordinate in the target network architecture, the assigned value corresponding to the patient diagnosis and treatment information in the target patient information is used as the y-coordinate in the target network architecture, and the fitting value of the mean of the assigned values ​​corresponding to other information in the target patient information except the patient diagnosis and treatment information is used as the z-coordinate in the target network architecture. The calculation formula of the fitting value includes:

[0084]

[0085] in, represents the fitted value, represents the mean value of the assigned values ​​corresponding to the patient's living environment information, represents the mean value of the assigned values ​​corresponding to the living habit information, represents the mean value of the assigned value corresponding to the economic status information, , , All represent weight coefficients;

[0086] The target network architecture is defined to include multiple three-dimensional coordinates (x, y, z), and the relevant values ​​and time nodes corresponding to the patient information corresponding to the multiple first key features are mapped into the target network architecture to generate the full disease course network architecture, wherein a time node generally includes a z value and at least one y value, that is, if there is only one patient information assignment at the target time node, the assignment corresponding to the patient information is defined as the y value; if there are multiple patient information assignments, multiple three-dimensional coordinates are generated based on the y value corresponding to each patient information assignment and mapped into the target network architecture to generate the full disease course network architecture.

[0087] In some specific embodiments, extracting the second key feature in the full course of disease network architecture includes:

[0088] Calculate the slope values ​​of multiple three-dimensional coordinates corresponding to the target time node in the target network architecture and the coordinate origin respectively, and sort them according to the size of the slope values, wherein the slope value is calculated by taking the plane generated by the x and y axes in the coordinate system as the two-dimensional rectangular coordinate system, obtaining the x and y values ​​of the multiple three-dimensional coordinates corresponding to the target time node, and calculating the slope value between the multiple (x, y) coordinates and the coordinate origin, that is, the slope value between the above multiple three-dimensional coordinates and the coordinate origin;

[0089] In response to detecting that the difference between the maximum slope value and the minimum slope value is greater than a second preset value, the maximum slope value and the minimum slope value are removed, and an average value of the remaining slope values ​​is calculated, wherein the second preset value can be set according to actual needs;

[0090] In response to detecting that the difference between the maximum slope value and the minimum slope value is less than or equal to a second preset value, calculating an average value of all slope values;

[0091] In response to detecting that the average value is greater than a third preset value, determining the patient information related value corresponding to the target time node corresponding to the average value as the second key feature, wherein the third preset value can be set according to actual needs.

[0092] S4: Input the second key feature of the target into the pre-built potential risk assessment model to obtain the potential risk assessment result.

[0093] It should be noted that this step specifically includes:

[0094] Obtain the second key feature of the target, wherein the second key feature of the target includes the second key feature corresponding to the current time node and the second key feature corresponding to the adjacent time node, wherein the current time node is time node, the adjacent time nodes are Time nodes;

[0095] The current second key feature and the adjacent second key feature are input into a pre-built potential risk assessment model, wherein the pre-built potential risk assessment model includes:

[0096]

[0097] in, Indicated in The state value corresponding to the time node, represents the correction function, Indicated in The state value corresponding to the time node, , is the coupling coefficient, respectively. Time nodes and The strength of the coupling relationship between time nodes in the whole disease course network architecture, express The number of three-dimensional coordinate nodes corresponding to the time node, It means the medication is effective. Indicates the drug injury factor, represents the sum of the weighted patient information parameter variables, express The patient information parameter variable value corresponding to the time node, represents a constant;

[0098] based on The state value corresponding to the time node and the third preset mapping table determine the potential risk assessment result, wherein the third preset mapping table includes a mapping relationship between at least one state value and the potential risk assessment result, and the potential risk assessment result is a value obtained through multiple tests and combined with expert scores.

[0099] S5: Calculate and obtain the stability coefficient between the target risk assessment result and the first key feature of the target, and determine whether to issue a health reminder based on the stability coefficient.

[0100] It should be noted that this step specifically includes:

[0101] In response to detecting that the potential risk assessment result is greater than a fourth preset value, wherein the fourth preset value can be set according to actual needs, a stability coefficient between the target risk assessment result and the target first key feature is calculated based on an objective function, and the objective function includes:

[0102]

[0103] in, represents the stability coefficient, Represents the average value of the patient information corresponding to the first key feature of the target, Represents the sum of the probabilities of the patient information corresponding to the first key feature of the target stimulating risk, represents the risk factor, Indicates the time dimension assignment, Indicates potential risk assessment results.

[0104] In some specific implementations, determining whether to issue a health reminder based on the stability coefficient includes:

[0105] In response to detecting that the stability coefficient is less than a fifth preset value, a health reminder is issued to the terminal, wherein the fifth preset value can be set according to actual needs, and the health reminder can be issued to the terminal in the form of text message, phone call, or a reminder mark on a specific app.

[0106] In the above-mentioned application method of the full-course management platform based on patient information, the method includes: collecting patient information, and the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information; preprocessing the patient information, and extracting the first key feature in the patient information based on the preprocessing result; based on the first key feature, constructing a full-course network architecture, and extracting the second key feature in the full-course network architecture; inputting the target second key feature into the pre-constructed potential risk assessment model to obtain a potential risk assessment result; calculating the stability coefficient between the target risk assessment result and the target first key feature, and determining whether to issue a health prompt based on the stability coefficient. The present application can realize the full-course analysis and processing of patient information, thereby performing efficient intelligent tracking, and then giving health prompts in a timely manner, reducing the labor intensity of medical staff, and improving work efficiency and service quality.

[0107] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0108] In one embodiment, Figure 2 As shown, an application system of a full-course management platform based on patient information is provided, including: an information collection module, a preprocessing module, a feature extraction module, a risk assessment module and a health reminder module, wherein:

[0109] An information collection module is used to collect patient information, wherein the patient information includes at least: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information;

[0110] A preprocessing module, used for preprocessing the patient information and extracting a first key feature from the patient information according to the preprocessing result;

[0111] A feature extraction module, used to construct a full-course network architecture based on the first key feature, and extract a second key feature in the full-course network architecture;

[0112] A risk assessment module, used to input the second key feature of the target into a pre-built potential risk assessment model to obtain a potential risk assessment result;

[0113] A health reminder module is used to calculate the stability coefficient between the target risk assessment result and the first key feature of the target, and determine whether to issue a health reminder based on the stability coefficient.

[0114] As a preferred implementation, in the embodiment of the present invention, the preprocessing module is specifically used for:

[0115] Performing data cleaning on the patient information;

[0116] Based on the first preset mapping table, determine the value corresponding to the patient information after data cleaning;

[0117] The value corresponding to the patient information corresponding to the target time node is input into a second preset mapping table, and based on the second preset mapping table, the first key feature in the patient information is extracted.

[0118] As a preferred implementation, in the embodiment of the present invention, the preprocessing module is further used for:

[0119] Calculate the absolute value of the difference between the target patient information in the target time node and the adjacent time nodes;

[0120] In response to detecting that the absolute value of the difference is greater than a first preset value, the patient information corresponding to the target time node is defined as a first key feature.

[0121] As a preferred implementation, in the embodiment of the present invention, the feature extraction module is specifically used for:

[0122] Obtain target patient information and target time node corresponding to the first key feature;

[0123] The target time node is used as the x-coordinate in the target network architecture, the assigned value corresponding to the patient diagnosis and treatment information in the target patient information is used as the y-coordinate in the target network architecture, and the fitting value of the mean of the assigned values ​​corresponding to other information in the target patient information except the patient diagnosis and treatment information is used as the z-coordinate in the target network architecture. The calculation formula of the fitting value includes:

[0124]

[0125] in, represents the fitted value, represents the mean value of the assigned values ​​corresponding to the patient's living environment information, represents the mean value of the assigned values ​​corresponding to the living habit information, represents the mean value of the assigned value corresponding to the economic status information, , , All represent weight coefficients;

[0126] The target network architecture is defined to include a plurality of three-dimensional coordinates (x, y, z), and the relevant values ​​and time nodes corresponding to the patient information corresponding to the plurality of first key features are mapped into the target network architecture to generate the full course of disease network architecture.

[0127] As a preferred implementation, in the embodiment of the present invention, the feature extraction module is further used for:

[0128] Calculate the slope values ​​of multiple three-dimensional coordinates corresponding to the target time node in the target network architecture and the coordinate origin respectively, and sort them according to the size of the slope value;

[0129] In response to detecting that the difference between the maximum slope value and the minimum slope value is greater than a second preset value, removing the maximum slope value and the minimum slope value, and calculating an average value of the remaining slope values;

[0130] In response to detecting that the difference between the maximum slope value and the minimum slope value is less than or equal to a second preset value, calculating an average value of all slope values;

[0131] In response to detecting that the average value is greater than a third preset value, a patient information-related value corresponding to a target time node corresponding to the average value is determined as the second key feature.

[0132] As a preferred implementation, in the embodiment of the present invention, the risk assessment module is specifically used for:

[0133] Acquire a second key feature of the target, where the second key feature of the target includes a second key feature corresponding to a current time node and a second key feature corresponding to an adjacent time node;

[0134] The current second key feature and the adjacent second key feature are input into a pre-built potential risk assessment model, wherein the pre-built potential risk assessment model includes:

[0135]

[0136] in, Indicated in The state value corresponding to the time node, represents the correction function, Indicated in The state value corresponding to the time node, , is the coupling coefficient, respectively. Time nodes and The strength of the coupling relationship between time nodes in the whole disease course network architecture, express The number of three-dimensional coordinate nodes corresponding to the time node, It means the medication is effective. Indicates the drug injury factor, represents the sum of the weighted patient information parameter variables, express The patient information parameter variable value corresponding to the time node, represents a constant;

[0137] based on The state value corresponding to the time node and the third preset mapping table determine the potential risk assessment result.

[0138] As a preferred implementation, in the embodiment of the present invention, the health reminder module is specifically used for:

[0139] In response to detecting that the potential risk assessment result is greater than a fourth preset value, a stability coefficient between the target risk assessment result and the target first key feature is calculated based on an objective function, wherein the objective function includes:

[0140]

[0141] in, represents the stability coefficient, Represents the average value of the patient information corresponding to the first key feature of the target, Represents the sum of the probabilities of the patient information corresponding to the first key feature of the target stimulating risk, represents the risk factor, Indicates the time dimension assignment, Indicates potential risk assessment results.

[0142] As a preferred implementation, in the embodiment of the present invention, the health reminder module is further used for:

[0143] In response to detecting that the stability coefficient is less than a fifth preset value, a health prompt is issued to the terminal.

[0144] For the specific definition of the application system of the full course of disease management platform based on patient information, please refer to the definition of the application method of the full course of disease management platform based on patient information above, which will not be repeated here. Each module in the above-mentioned application system of the full course of disease management platform based on patient information can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0145] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, 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 network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an application method of a full course of disease management platform based on patient information is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0146] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0147] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0148] S1: Collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information;

[0149] S2: preprocessing the patient information, and extracting a first key feature from the patient information according to the preprocessing result;

[0150] S3: Based on the first key feature, construct a full-course network architecture, and extract a second key feature in the full-course network architecture;

[0151] S4: inputting the second key feature of the target into the pre-built potential risk assessment model to obtain a potential risk assessment result;

[0152] S5: Calculate and obtain the stability coefficient between the target risk assessment result and the first key feature of the target, and determine whether to issue a health reminder based on the stability coefficient.

[0153] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0154] Performing data cleaning on the patient information;

[0155] Based on the first preset mapping table, determine the value corresponding to the patient information after data cleaning;

[0156] The value corresponding to the patient information corresponding to the target time node is input into a second preset mapping table, and based on the second preset mapping table, the first key feature in the patient information is extracted.

[0157] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0158] Calculate the absolute value of the difference between the target patient information in the target time node and the adjacent time nodes;

[0159] In response to detecting that the absolute value of the difference is greater than a first preset value, the patient information corresponding to the target time node is defined as a first key feature.

[0160] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0161] Obtain target patient information and target time node corresponding to the first key feature;

[0162] The target time node is used as the x-coordinate in the target network architecture, the assigned value corresponding to the patient diagnosis and treatment information in the target patient information is used as the y-coordinate in the target network architecture, and the fitting value of the mean of the assigned values ​​corresponding to other information in the target patient information except the patient diagnosis and treatment information is used as the z-coordinate in the target network architecture. The calculation formula of the fitting value includes:

[0163]

[0164] in, represents the fitted value, represents the mean value of the assigned values ​​corresponding to the patient's living environment information, represents the mean value of the assigned values ​​corresponding to the living habit information, represents the mean value of the assigned value corresponding to the economic status information, , , All represent weight coefficients;

[0165] The target network architecture is defined to include a plurality of three-dimensional coordinates (x, y, z), and the relevant values ​​and time nodes corresponding to the patient information corresponding to the plurality of first key features are mapped into the target network architecture to generate the full course of disease network architecture.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] Calculate the slope values ​​of multiple three-dimensional coordinates corresponding to the target time node in the target network architecture and the coordinate origin respectively, and sort them according to the size of the slope value;

[0168] In response to detecting that the difference between the maximum slope value and the minimum slope value is greater than a second preset value, removing the maximum slope value and the minimum slope value, and calculating an average value of the remaining slope values;

[0169] In response to detecting that the difference between the maximum slope value and the minimum slope value is less than or equal to a second preset value, calculating an average value of all slope values;

[0170] In response to detecting that the average value is greater than a third preset value, a patient information-related value corresponding to a target time node corresponding to the average value is determined as the second key feature.

[0171] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0172] Acquire a second key feature of the target, where the second key feature of the target includes a second key feature corresponding to a current time node and a second key feature corresponding to an adjacent time node;

[0173] The current second key feature and the adjacent second key feature are input into a pre-built potential risk assessment model, wherein the pre-built potential risk assessment model includes:

[0174]

[0175] in, Indicated in The state value corresponding to the time node, represents the correction function, Indicated in The state value corresponding to the time node, , is the coupling coefficient, respectively. Time nodes and The strength of the coupling relationship between time nodes in the whole disease course network architecture, express The number of three-dimensional coordinate nodes corresponding to the time node, It means the medication is effective. Indicates the drug injury factor, represents the sum of the weighted patient information parameter variables, express The patient information parameter variable value corresponding to the time node, represents a constant;

[0176] based on The state value corresponding to the time node and the third preset mapping table determine the potential risk assessment result.

[0177] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0178] In response to detecting that the potential risk assessment result is greater than a fourth preset value, a stability coefficient between the target risk assessment result and the target first key feature is calculated based on an objective function, wherein the objective function includes:

[0179]

[0180] in, represents the stability coefficient, Represents the average value of the patient information corresponding to the first key feature of the target, Represents the sum of the probabilities of the patient information corresponding to the first key feature of the target stimulating risk, represents the risk factor, Indicates the time dimension assignment, Indicates potential risk assessment results.

[0181] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0182] In response to detecting that the stability coefficient is less than a fifth preset value, a health prompt is issued to the terminal.

[0183] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0184] S1: Collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information;

[0185] S2: preprocessing the patient information, and extracting a first key feature from the patient information according to the preprocessing result;

[0186] S3: Based on the first key feature, construct a full-course network architecture, and extract a second key feature in the full-course network architecture;

[0187] S4: inputting the second key feature of the target into the pre-built potential risk assessment model to obtain a potential risk assessment result;

[0188] S5: Calculate and obtain the stability coefficient between the target risk assessment result and the first key feature of the target, and determine whether to issue a health reminder based on the stability coefficient.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0190] Performing data cleaning on the patient information;

[0191] Based on the first preset mapping table, determine the value corresponding to the patient information after data cleaning;

[0192] The value corresponding to the patient information corresponding to the target time node is input into a second preset mapping table, and based on the second preset mapping table, the first key feature in the patient information is extracted.

[0193] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0194] Calculate the absolute value of the difference between the target patient information in the target time node and the adjacent time nodes;

[0195] In response to detecting that the absolute value of the difference is greater than a first preset value, the patient information corresponding to the target time node is defined as a first key feature.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0197] Obtain target patient information and target time node corresponding to the first key feature;

[0198] The target time node is used as the x-coordinate in the target network architecture, the assigned value corresponding to the patient diagnosis and treatment information in the target patient information is used as the y-coordinate in the target network architecture, and the fitting value of the mean of the assigned values ​​corresponding to other information in the target patient information except the patient diagnosis and treatment information is used as the z-coordinate in the target network architecture. The calculation formula of the fitting value includes:

[0199]

[0200] in, represents the fitted value, represents the mean value of the assigned values ​​corresponding to the patient's living environment information, represents the mean value of the assigned values ​​corresponding to the living habit information, represents the mean value of the assigned value corresponding to the economic status information, , , All represent weight coefficients;

[0201] The target network architecture is defined to include a plurality of three-dimensional coordinates (x, y, z), and the relevant values ​​and time nodes corresponding to the patient information corresponding to the plurality of first key features are mapped into the target network architecture to generate the full course of disease network architecture.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0203] Calculate the slope values ​​of multiple three-dimensional coordinates corresponding to the target time node in the target network architecture and the coordinate origin respectively, and sort them according to the size of the slope value;

[0204] In response to detecting that the difference between the maximum slope value and the minimum slope value is greater than a second preset value, removing the maximum slope value and the minimum slope value, and calculating an average value of the remaining slope values;

[0205] In response to detecting that the difference between the maximum slope value and the minimum slope value is less than or equal to a second preset value, calculating an average value of all slope values;

[0206] In response to detecting that the average value is greater than a third preset value, a patient information-related value corresponding to a target time node corresponding to the average value is determined as the second key feature.

[0207] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0208] Acquire a second key feature of the target, where the second key feature of the target includes a second key feature corresponding to a current time node and a second key feature corresponding to an adjacent time node;

[0209] The current second key feature and the adjacent second key feature are input into a pre-built potential risk assessment model, wherein the pre-built potential risk assessment model includes:

[0210]

[0211] in, Indicated in The state value corresponding to the time node, represents the correction function, Indicated in The state value corresponding to the time node, , is the coupling coefficient, respectively. Time nodes and The strength of the coupling relationship between time nodes in the whole disease course network architecture, express The number of three-dimensional coordinate nodes corresponding to the time node, It means the medication is effective. Indicates the drug injury factor, represents the sum of the weighted patient information parameter variables, express The patient information parameter variable value corresponding to the time node, represents a constant;

[0212] based on The state value corresponding to the time node and the third preset mapping table determine the potential risk assessment result.

[0213] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0214] In response to detecting that the potential risk assessment result is greater than a fourth preset value, a stability coefficient between the target risk assessment result and the target first key feature is calculated based on an objective function, wherein the objective function includes:

[0215]

[0216] in, represents the stability coefficient, Represents the average value of the patient information corresponding to the first key feature of the target, Represents the sum of the probabilities of the patient information corresponding to the first key feature of the target stimulating risk, represents the risk factor, Indicates the time dimension assignment, Indicates potential risk assessment results.

[0217] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0218] In response to detecting that the stability coefficient is less than a fifth preset value, a health prompt is issued to the terminal.

[0219] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0220] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0221] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An application method of a full course of disease management platform based on patient information, characterized in that: The method comprises: Collecting patient information, the patient information at least includes: patient diagnosis and treatment information, patient living environment information, living habits information and economic status information; Preprocessing the patient information, and extracting a first key feature from the patient information according to the preprocessing result, wherein the preprocessing method of the patient information includes: Performing data cleaning on the patient information; Based on the first preset mapping table, determining the value corresponding to the patient information after data cleaning, wherein the first preset mapping table includes at least one mapping relationship between patient information and its value, and the value data is a numerical value obtained through multiple tests combined with expert scoring; Inputting the value corresponding to the patient information corresponding to the target time node into a second preset mapping table, and extracting the first key feature in the patient information based on the second preset mapping table, wherein the second preset mapping table includes at least a mapping relationship between a time node and the value corresponding to the patient information, and there are multiple values ​​for the patient information corresponding to one time node; Based on the first key feature, the whole course network architecture is constructed including: Obtain target patient information and target time node corresponding to the first key feature; The target time node is used as the x-coordinate in the target network architecture, the assigned value corresponding to the patient diagnosis and treatment information in the target patient information is used as the y-coordinate in the target network architecture, and the fitting value of the mean of the assigned values ​​corresponding to other information in the target patient information except the patient diagnosis and treatment information is used as the z-coordinate in the target network architecture. The calculation formula of the fitting value includes: in, represents the fitted value, represents the mean value of the assigned values ​​corresponding to the patient's living environment information, represents the mean value of the assigned values ​​corresponding to the living habit information, represents the mean value of the assigned value corresponding to the economic status information, , , All represent weight coefficients; Defining a target network architecture including a plurality of three-dimensional coordinates (x, y, z), mapping relevant values ​​and time nodes corresponding to the patient information corresponding to the plurality of first key features into the target network architecture, and generating the full course of disease network architecture; The second key feature extracted from the full course network architecture includes: Calculate the slope values ​​of multiple three-dimensional coordinates corresponding to the target time node in the target network architecture and the coordinate origin respectively, and sort them according to the size of the slope value; In response to detecting that the difference between the maximum slope value and the minimum slope value is greater than a second preset value, removing the maximum slope value and the minimum slope value, and calculating an average value of the remaining slope values; In response to detecting that the difference between the maximum slope value and the minimum slope value is less than or equal to a second preset value, calculating an average value of all slope values; In response to detecting that the average value is greater than a third preset value, determining that the patient information-related value corresponding to the target time node corresponding to the average value is the second key feature; Input the second key feature of the target into the pre-built potential risk assessment model, and obtain the potential risk assessment results including: Acquire a second key feature of the target, where the second key feature of the target includes a second key feature corresponding to a current time node and a second key feature corresponding to an adjacent time node; The current second key feature and the adjacent second key feature are input into a pre-built potential risk assessment model, wherein the pre-built potential risk assessment model includes: in, Indicated in The state value corresponding to the time node, represents the correction function, Indicated in The state value corresponding to the time node, , is the coupling coefficient, respectively. Time nodes and The strength of the coupling relationship between time nodes in the whole disease course network architecture, express The number of three-dimensional coordinate nodes corresponding to the time node, It means the medication is effective. Indicates the drug injury factor, represents the sum of the weighted patient information parameter variables, express The patient information parameter variable value corresponding to the time node, represents a constant; based on The state value corresponding to the time node and the third preset mapping table are used to determine the potential risk assessment result; The stability coefficient between the target risk assessment result and the target first key feature is calculated as follows: In response to detecting that the potential risk assessment result is greater than a fourth preset value, a stability coefficient between the target risk assessment result and the target first key feature is calculated based on an objective function, wherein the objective function includes: in, represents the stability coefficient, Represents the average value of the patient information corresponding to the first key feature of the target, Represents the sum of the probabilities of the patient information corresponding to the first key feature of the target stimulating risk, represents the risk factor, Indicates the time dimension assignment, Indicates potential risk assessment results; Determining whether to issue a health reminder based on the stability coefficient includes: In response to detecting that the stability coefficient is less than a fifth preset value, issuing a health prompt to the terminal; According to the preprocessing result, extracting the first key feature in the patient information includes: Calculate the absolute value of the difference between the values ​​assigned to the target patient information at the target time node and the adjacent time nodes, wherein the calculation of the absolute value of the difference between the target patient information is the absolute value of the difference between two individual values ​​or the absolute value of the difference between the average values ​​of multiple assigned values ​​corresponding to the two time nodes; In response to detecting that the absolute value of the difference is greater than a first preset value, the patient information corresponding to the target time node is defined as the first key feature, that is, the target time node is determined by calculating the absolute value of the difference. After the target time node is determined, all patient information corresponding to the target time node is assigned as the first key feature according to the second preset mapping table, so as to be used for the subsequent construction of the full disease course network structure.

2. An application system of a full course of disease management platform based on patient information using the application method of the full course of disease management platform based on patient information as claimed in claim 1, characterized in that: The system comprises: An information collection module is used to collect patient information, wherein the patient information includes at least: patient diagnosis and treatment information, patient living environment information, living habit information and economic status information; A preprocessing module, used for preprocessing the patient information and extracting a first key feature from the patient information according to the preprocessing result; A feature extraction module, used to construct a full-course network architecture based on the first key feature, and extract a second key feature in the full-course network architecture; A risk assessment module, used to input the second key feature of the target into a pre-built potential risk assessment model to obtain a potential risk assessment result; The health prompt module is used to calculate the stability coefficient between the target risk assessment result and the first key feature of the target, and determine whether to issue a health prompt based on the stability coefficient.

Images