Asthma patient information management system

Abstract

The invention relates to the technical field of asthma analysis, and provides an asthma patient information management system, and the system comprises an obtaining module which is used for obtaining the values of all influence factors of a plurality of different types of asthma patients; the construction module is used for constructing a linear regression model between all the influence factors under the type and the hospitalization duration and a re-admission risk model of the asthma patients under the type according to the values of all the influence factors of all the asthma patients under the type; the analysis module is used for performing analysis according to the linear regression model and the re-admission risk model to obtain a prediction state of the asthma patient, and obtaining a total hospitalization duration and an average hospitalization frequency according to the prediction state; and the treatment recommendation module is used for outputting treatment recommendation information for the target asthma patient based on the total hospitalization duration and the average hospitalization frequency of all types. According to the system, the reasonability of the treatment recommendation information of the asthma patient can be improved.

Description

Technical Field

[0001] This application relates to the technical field of asthma analysis, and particularly to an information management system for asthma patients. Background Art

[0002] In current asthma management, there is insufficient control over readmission and the use of medical resources. On the one hand, there is a lack of accurate analysis tools, making it difficult to accurately identify the key factors affecting asthma patients' readmission and the use of medical resources, resulting in the inability to formulate targeted intervention measures. On the other hand, when simulating the treatment process and resource consumption of patients, existing technologies cannot comprehensively consider various complex factors, causing a large deviation between the prediction results and the actual situation and being unable to provide an effective basis for formulating treatment plans.

[0003] Existing solutions: Some studies use simple statistical analysis to understand the readmission situation of asthma patients, such as calculating the average readmission rate, but cannot deeply analyze the complex factors behind it. In terms of the use of medical resources, only a simple linear model is established to analyze the relationship between a single factor (such as the severity of the disease) and resource consumption, ignoring many other influencing factors.

[0004] Disadvantages of existing solutions: Simple statistical analysis and linear models cannot comprehensively consider various factors such as patient individual differences, disease characteristics, treatment methods, medical policies, and living habits. These factors are intertwined and jointly affect the readmission situation of asthma patients. The one-sidedness of existing solutions leads to inaccurate analysis results, unable to provide a reliable reference for medical decision-making, and resulting in unreasonable treatment recommendation plans for asthma patients. Summary of the Invention

[0005] This application provides an information management system for asthma patients, which can solve the problem of unreasonable treatment recommendation plans for asthma patients.

[0006] An embodiment of this application provides an information management system for asthma patients, which includes:

[0007] An acquisition module, configured to acquire the values of all influencing factors of multiple asthma patients of different types; the influencing factors are the factors affecting the readmission of asthma patients, and each type corresponds to at least one asthma patient;

[0008] A construction module, configured to respectively for each type, according to the values of all influencing factors of all asthma patients of the type, construct a linear regression model between all influencing factors and the length of hospital stay under the type, and a readmission risk model of asthma patients under the type;

[0009] An analysis module, configured to analyze, according to the linear regression model and readmission risk model corresponding to each asthma patient, to obtain the predicted status of each asthma patient, and to obtain the total length of hospital stay and average number of hospitalizations for each type according to all the predicted statuses;

[0010] A treatment recommendation module, configured to output treatment recommendation information for a target asthma patient based on the total length of hospital stay and average number of hospitalizations for all types.

[0011] Optionally, the linear regression model is:

[0012]

[0013] Wherein, for the asthma patients of the i-th type, Y i represents the length of hospital stay, represents the intercept, L represents the set of values of all influencing factors, represents the influence coefficient of the influencing factor l on the length of hospital stay, and X l represents the value of the influencing factor l, i = 1, 2,..., I, and I represents the number of patient types.

[0014] Optionally, the readmission risk model is:

[0015]

[0016] Wherein, for the asthma patients of the i-th type, h(t|X) i represents the readmission risk value, represents the baseline risk function, represents the influence coefficient of the influencing factor l on the readmission intensity, and exp represents the exponential function.

[0017] Optionally, according to the linear regression model and readmission risk model corresponding to each asthma patient, the predicted status of each asthma patient is analyzed, including:

[0018] For each asthma patient, the following steps are respectively performed:

[0019] Taking the values of all influencing factors of the asthma patient and the type of the asthma patient as the current status;

[0020] Constructing a state transition function according to the current status, and calculating the next state of the asthma patient and the time interval of the state transition according to the state transition function and the readmission risk model, and taking the patient status described by the next state as the predicted patient status of the asthma patient; the patient status is death or readmission, and the state transition function is used to calculate the probability of the asthma patient transferring to the next state and the probability of the time interval of the state transition according to the values of all influencing factors of the asthma patient and the type of the asthma patient;

[0021] Determine whether the time interval is greater than the remaining observation duration, or predict whether the patient's status is death;

[0022] If the time interval is greater than the remaining observation duration, or the predicted patient status is death, then count the number of times the predicted patient status is readmission, calculate the length of stay for each readmission according to the corresponding linear regression model, and use the number of readmissions and the total length of stay as the predicted status of the predicted patient status;

[0023] If the time interval is less than or equal to the remaining observation duration and the predicted patient status is not death, then take the next status as the current status, take the difference between the remaining observation duration and the time interval as the remaining observation duration, return the step of constructing the state transition function according to the current status, and calculate the predicted patient status of the asthma patient according to the state transition function.

[0024] Optionally, the state transition function is:

[0025]

[0026] where p(s'|s,t) represents the probability that an asthma patient transfers from the current state s to state s' with a time interval of t, and ω Death (s) represents whether the asthma patient in the current state s is dead, with the value 0 indicating not dead and the value 1 indicating dead, and ω Death (s') represents whether the asthma patient in state s' is dead, L represents the set of values of all influencing factors, and ω l (s) represents the value of the influencing factor l in the current state s, and ω l (s') represents the value of the influencing factor l in state s', and ω Type (s) represents the type of the asthma patient in the current state s, and ω Type (s') represents the type of the asthma patient in state s', and ω Admission (s) represents the number of readmissions of the asthma patient in the current state s, and ω Admission (s') represents the number of readmissions of the asthma patient in state s', d and μ(s) represent the distribution parameters of the current state s, d is the distribution parameter of whether the asthma patient is dead, and μ(s) is the distribution parameter of the number of readmissions of the asthma patient, is the probability of readmission of the asthma patient, is the probability of death of the asthma patient, and F(s'|s,t) represents the probability that an asthma patient transfers from s to s' when the asthma patient does not die:

[0027]

[0028] where, Denote the baseline readmission intensity of asthma patients of type ω Type (s), Denote the readmission transfer intensity parameter of patients of type ω Type on influencing factor l, Denote the change rate parameter of influencing factor l of patients of type ω Type (s), where f(s'|s,l,t) represents the probability that the current state s is consistent with state s' on feature l, and e represents the natural logarithm.

[0029] Optionally, calculate the next state of the asthma patient and the time interval of state transition according to the state transition function and the readmission risk model, including:

[0030] Initialize multiple states and multiple time intervals according to the readmission risk model;

[0031] For each state respectively, calculate the probability that the current state transitions to this state and the time interval is t i ; t i = 1, 2,..., T, where T represents the number of initialized time intervals;

[0032] Determine the next state of the asthma patient and the time interval of state transition from all states and time intervals according to all probabilities.

[0033] Optionally, obtain the total hospitalization duration and average hospitalization times of each type according to all predicted states, including:

[0034] For each type respectively, perform the following steps:

[0035] Sum up the total admission durations in the predicted states of all asthma patients corresponding to the type to obtain the total hospitalization duration of the type;

[0036] Average the number of readmissions in the predicted states of all asthma patients corresponding to the type to obtain the average hospitalization times of the type.

[0037] The above solution of this application has the following beneficial effects:

[0038] In some embodiments of the present application, by obtaining the values of all influencing factors of multiple asthma patients of different types, and then for each type respectively, according to the values of all influencing factors of all asthma patients of the type, a linear regression model between all influencing factors and the length of hospital stay under the type, as well as a readmission risk model of asthma patients under the type are constructed. Then, according to the linear regression model and the readmission risk model corresponding to each asthma patient, the predicted status of each asthma patient is analyzed, and based on all the predicted statuses, the total length of hospital stay and the average number of hospitalizations of each type are obtained. Finally, based on the total length of hospital stay and the average number of hospitalizations of all types, treatment recommendation information is output for the target asthma patient. Among them, comprehensively considering multiple influencing factors can improve the rationality and practicality of analyzing asthma patients. Predicting the status of readmission and the length of hospital stay of asthma patients can provide intuitive and reliable data on the number of hospitalizations and the length of hospital stay of patients, providing accurate data basis for the admission treatment management of asthma patients, and further improving the rationality of the treatment recommendation information for asthma patients.

[0039] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0041] Figure 1 It is a schematic structural diagram of an asthma patient information management system provided by an embodiment of the present application;

[0042] Figure 2 It is a schematic flowchart of the process of using an asthma patient information management system provided by an embodiment of the present application;

[0043] Figure 3 It is a simulation flowchart of a single patient provided by an embodiment of the present application;

[0044] Figure 4 It is a simulation flowchart of a population provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obscuring the description of the present application.

[0046] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0047] It should also be understood that the term "and / or" as used in the specification and the appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0048] As used in the specification and the appended claims of the present application, the term "if" can be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0049] In addition, in the description of the specification and the appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0050] The reference to "one embodiment" or "some embodiments" or the like described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0051] In view of the problem that the existing treatment management plan for asthma patients is unreasonable, the embodiment of the present application provides an asthma patient information management system. The management system obtains the values of all influencing factors of multiple asthma patients of different types, and then for each type, according to the values of all influencing factors of all asthma patients of the type, constructs a linear regression model between all influencing factors and the length of hospitalization under the type, and a readmission risk model of asthma patients under the type. Then, according to the linear regression model and readmission risk model corresponding to each asthma patient, the predicted status of each asthma patient is analyzed, and the total length of hospitalization and average number of hospitalizations of each type are obtained according to all predicted statuses. Finally, based on the total length of hospitalization and average number of hospitalizations of all types, treatment recommendation information is output for the target asthma patient. Among them, considering multiple influencing factors comprehensively can improve the rationality and practicality of analyzing asthma patients, predict the status of readmission and length of hospitalization of asthma patients, can provide intuitive and reliable data on the number of hospitalizations and length of hospitalization of patients, provide accurate data basis for the admission treatment management of asthma patients, and further improve the rationality of treatment recommendation information for asthma patients.

[0052] As Figure 1 shown in the figure, the asthma patient information management system 100 provided by the present application includes:

[0053] An acquisition module 101, configured to acquire the values of all influencing factors of multiple asthma patients of different types; the influencing factors are factors that affect the readmission of asthma patients, and each type corresponds to at least one asthma patient;

[0054] A construction module 102, configured to, for each type, according to the values of all influencing factors of all asthma patients of the type, construct a linear regression model between all influencing factors and the length of hospitalization under the type, and a readmission risk model of asthma patients under the type;

[0055] An analysis module 103, configured to analyze the predicted status of each asthma patient according to the linear regression model and readmission risk model corresponding to each asthma patient, and obtain the total length of hospitalization and average number of hospitalizations of each type according to all predicted statuses;

[0056] A treatment recommendation module 104, configured to output treatment recommendation information for the target asthma patient based on the total length of hospitalization and average number of hospitalizations of all types.

[0057] As Figure 2 shown in the figure, the following steps are included in the process of using the asthma patient information management system provided by the present application:

[0058] Step 21, acquire the values of all influencing factors of multiple asthma patients of different types.

[0059] The above influencing factors are the factors affecting the readmission of asthma patients (such as the number of times the patient has been admitted to the hospital, survival status, medium - acting hormone medication status, long - acting technology medication status, antibiotic medication status, β2 - receptor agonist medication status, leukotriene receptor antagonist medication status, etc.), and each type corresponds to at least one asthma patient. The types are divided according to the gender, medical insurance type, main diagnosis, etc. of the asthma patients, such as mild asthma, moderate asthma, severe asthma, etc.

[0060] In some embodiments of the present application, the values of the influencing factors of asthma patients can be obtained by accessing the hospital's medical treatment system, etc.

[0061] It should be noted that for influencing factors whose data are text - based, the corresponding values can be obtained by encoding them. For example, for the survival status, encoding 1 represents death and encoding 0 represents not dead; for the antibiotic medication status, encoding 1 represents being on medication and encoding 0 represents not on medication.

[0062] Step 22: For each type, according to the values of all influencing factors of all asthma patients of the type, construct a linear regression model between all influencing factors and the length of hospitalization under the type, and a readmission risk model for asthma patients under the type.

[0063] Specifically, the linear regression model is:

[0064]

[0065] Among them, for the asthma patients of the i - th type, Y i represents the length of hospitalization, represents the intercept, L represents the set of values of all influencing factors, represents the influence coefficient of the influencing factor l on the length of hospitalization, X l represents the value of the influencing factor l, i = 1, 2,..., I, and I represents the number of patient types.

[0066] The readmission risk model is:

[0067]

[0068] Among them, for the asthma patients of the i - th type, h(t|X) i represents the readmission risk value, represents the baseline risk function, represents the influence coefficient of the influencing factor l on the readmission intensity, and exp represents the exponential function.

[0069] It should be noted that the influence coefficient of the above influencing factors on the length of hospitalization and the influence coefficient of the influencing factors on the readmission intensity can be obtained by collecting the values of all influencing factors and the length of hospitalization of multiple asthma patients as samples, and performing a regression analysis on the values of the influencing factors and the length of hospitalization. For the influence coefficient of the influencing factors on the length of hospitalization, taking the length of hospitalization as the dependent variable and the values of the influencing factors of asthma patients as the independent variables, a linear regression analysis is performed to obtain the influence coefficient of the influencing factors on the length of hospitalization; for the influence coefficient of the influencing factors on the readmission intensity, taking the readmission risk value as the dependent variable and the values of the influencing factors of asthma patients as the independent variables, a proportional hazards regression analysis is performed to obtain the influence coefficient of the influencing factors on the readmission intensity; the above baseline hazard function is the readmission risk model when all independent variables (i.e., the values of all influencing factors) are 0, and it is estimated by the proportional hazards method considering only the relationship between time and the readmission risk value.

[0070] Step 23: According to the linear regression model and the readmission risk model corresponding to each asthma patient, analyze to obtain the predicted status of each asthma patient, and obtain the total length of hospitalization and the average number of hospitalizations for each type based on all the predicted statuses.

[0071] In some embodiments of the present application, the step of analyzing to obtain the predicted status of each asthma patient according to the linear regression model and the readmission risk model corresponding to each asthma patient includes:

[0072] For each asthma patient, the following steps are respectively performed:

[0073] First step: Take the values of all influencing factors of the asthma patient and the type of the asthma patient as the current status.

[0074] Second step: Construct a state transition function according to the current status, and calculate the next status of the asthma patient and the time interval of the state transition according to the state transition function and the readmission risk model, and take the patient status described by the next status as the predicted patient status of the asthma patient.

[0075] The above patient status is death or readmission. The state transition function is used to calculate the probability of the asthma patient transferring to the next status and the probability of the time interval of the state transition according to the values of all influencing factors of the asthma patient and the type of the asthma patient. The current status refers to the status of the asthma patient at the current moment, and the next status is the status of the asthma patient at the next moment of the current moment.

[0076] Specifically, the state transition function is:

[0077]

[0078] Among them, p(s'|s,t) represents the probability that an asthma patient transfers from the current state s to state s' with a time interval of t, ω Death ω(s) represents whether an asthma patient in the current state s has died. A value of 0 indicates not dead, and a value of 1 indicates dead, ω Death ω(s') represents whether an asthma patient in state s' has died. L represents the set of values of all influencing factors, ω l ω(s) represents the value of the influencing factor l in the current state s, ω l ω(s') represents the value of the influencing factor l in state s', ω Type ω(s) represents the type of an asthma patient in the current state s, ω Type ω(s') represents the type of an asthma patient in state s', ω Admission ω(s) represents the number of readmissions of an asthma patient in the current state s, ω Admission ω(s') represents the number of readmissions of an asthma patient in state s'. d and μ(s) represent the distribution parameters of the current state s. d is the distribution parameter for whether an asthma patient has died, and μ(s) is the distribution parameter for the number of readmissions of an asthma patient, is the probability of an asthma patient being readmitted, is the probability of an asthma patient dying. F(s'|s,t) represents the probability that an asthma patient transfers from s to s' without dying:

[0079]

[0080] Among them, represents the basic readmission intensity of an asthma patient of type ω Type (s), represents the readmission transfer intensity parameter of type ω Type (s) patients on the influencing factor l, represents the change rate parameter of the influencing factor l of type ω Type (s) patients, that is, the change coefficient (intensity) of the influencing factor l over time. f(s'|s,l,t) represents the probability that the current state s and state s' are consistent in the characteristic l. e represents the natural logarithm, and t represents the time step for the state transition in this step.

[0081] It should be noted that the above state transition function assumes that the state transition processes of each characteristic are independent, which is in line with the actual situation and is convenient for calculation. In this algorithm, the readmission intensity μ(s) is independent of time and only related to the current state of the patient; μ(s) is a special case of h(t|X). Among them, corresponds to is a constant that is only related to the patient type and independent of time; is related to corresponds to; I(ω Death (s)=0) is used to characterize that the readmission intensity is 0 if the patient has died.

[0082] The steps of calculating the next state of the asthma patient and the time interval of state transition according to the state transition function and the readmission risk model are specifically as follows:

[0083] First, initialize multiple states and multiple time intervals according to the readmission risk model.

[0084] Specifically, the readmission risk model reflects the risk of readmission of asthma patients and to a certain extent reflects the probability of readmission of asthma patients. Substitute the current state of the asthma patient into the readmission risk model, calculate the readmission risk value, and generate multiple states and multiple time intervals according to the readmission risk value. For example, the readmission risk value can be used to screen multiple randomly generated states. If the readmission risk value is 0.5, it is considered that there is a 50% probability of readmission, and half of the states generated should correspond to the patient state of readmission. Multiple time intervals can be randomly generated. Each state includes the values of all random influencing factors and the patient state (dead or readmitted).

[0085] Then, for each state respectively, calculate the probability that the current state transitions to this state and the time interval is t i ; t i =1, 2,..., T, where T represents the number of initialized time intervals.

[0086] Specifically, substitute each state and time interval into the state transition function to calculate the corresponding probability. That is, each state corresponds to T probabilities.

[0087] Finally, determine the next state of the asthma patient and the time interval of state transition from all states and time intervals according to all probabilities. For example, in the current state A, the probability of transitioning to the next state B1 and the time interval being C1 is 0.2, the probability of transitioning to the next state B2 and the time interval being C2 is 0.5, and the probability of transitioning to the next state B3 and the time interval being C3 is 0.3. That is, there is a 0.2 probability of transitioning to state B1 and the time interval being C1, a 0.5 probability of transitioning to state B2 and the time interval being C2, and a 0.3 probability of transitioning to state B3 and the time interval being C3.

[0088] Third step, determine whether the time interval is greater than the remaining observation duration, or whether the predicted patient state is dead.

[0089] The above remaining observation duration is the remaining observation duration of the asthma patient. The initial value of the observation duration is a preset value, which is set according to the actual disease duration of the asthma patient.

[0090] If the time interval is greater than the remaining observation duration, or the predicted patient status is death, then count the number of times the predicted patient status is readmission, calculate the length of stay for each readmission according to the corresponding linear regression model, and use the number of readmissions and the total length of stay as the predicted status of the predicted patient status.

[0091] If the time interval is less than or equal to the remaining observation duration and the predicted patient status is not death, then take the next status as the current status, take the difference between the remaining observation duration and the time interval as the remaining observation duration, return the step of constructing the state transition function according to the current status, and calculate the predicted patient status of the asthma patient according to the state transition function.

[0092] Specifically, substitute the values of all influencing factors in the status at each readmission into the linear regression model to obtain the length of stay for readmission.

[0093] Fourth step, obtain the total length of stay and the average number of hospitalizations for each type according to all predicted statuses.

[0094] Specifically, for each type, perform the following steps:

[0095] Sum up the total length of stay in the predicted statuses of all asthma patients corresponding to the type to obtain the total length of stay of the type.

[0096] Average the number of readmissions in the predicted statuses of all asthma patients corresponding to the type to obtain the average number of hospitalizations of the type.

[0097] It should be noted that the process of this step can also introduce the medical resources consumed by the asthma patient each time they are admitted to the hospital for calculation, add the medical resource consumption data of the asthma patient to the current status, and introduce the medical resource consumption data when initializing the status. Through the above calculation process, the medical resource consumption status of the asthma patients of each type can finally be obtained, such as the average value of the medical resources consumed by the patients of this type each time they are admitted to the hospital, the total medical resource consumption of the patients of this type, etc.

[0098] The following uses a specific example to give an exemplary description of this step.

[0099] Such as Figure 3As shown, the process of processing a single asthma patient in this step is implemented using simulation software. After the patient enters the simulation system, the duration of the first hospitalization is recorded, and the next event (used to describe whether the patient dies or is readmitted, equivalent to the state in the above text) and the time interval T are generated. Then, it is judged whether T is greater than the remaining observation period (i.e., the remaining observation duration in the above text). If so, the total hospitalization duration and the number of hospitalizations during the observation period are calculated. Otherwise, the event type is judged. If it is death, the total hospitalization duration and the number of hospitalizations during the observation period are calculated. If it is readmission, the remaining observation period is updated = the original remaining period - T, and the duration of this hospitalization is recorded, and the step of generating the next event and the event interval T is returned.

[0100] The simulation process for all asthma patients is as Figure 4 shown. After starting, the patient type and the death intensity parameter are determined, and then the set of patients of this type is initialized. It is judged whether there are still unprocessed patients. If so, the next patient is taken out and the Figure 3 simulation for a single asthma patient shown is executed. The total hospitalization duration and the number of hospitalizations of this patient are recorded, and the step of judging whether there are still unprocessed patients is returned. If there are no unprocessed patients, the data of all patients are aggregated, and the total hospitalization duration and the average number of hospitalizations of each type of group are calculated, and the process ends.

[0101] Step 24: Based on the total hospitalization duration and the average number of hospitalizations of all types, output treatment recommendation information for the target asthma patient.

[0102] The above target asthma patient is an asthma patient who needs treatment.

[0103] Exemplarily, for the convenience of analysis, the total hospitalization duration and the average number of hospitalizations of each type can be converted into values commonly used in statistical analysis, such as mean, standard deviation, etc. According to the type of the target asthma patient, based on the corresponding values of this type, it is judged whether the target asthma patient needs to prepare for readmission treatment, or treatment recommendation information such as the hospitalization duration during readmission. For example, if the type of the target asthma patient is mild asthma and the average number of hospitalizations of this type is 4 times, and the target asthma patient has only been hospitalized once, it can be considered that the probability of the target asthma patient being readmitted later is high, and the treatment recommendation information that the target asthma patient is ready for readmission treatment at any time is obtained.

[0104] It should be noted that medical staff can also specify a reasonable medical resource allocation plan, personalized treatment plan, etc. for the target patient according to the total hospitalization duration, average number of hospitalizations, and medical resource consumption status of all types, so as to improve the rationality and reliability of patient treatment management.

[0105] In the above embodiments, the descriptions of the respective embodiments each have their own emphasis. For parts not described or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0106] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0107] The above is the preferred implementation manner of this application. It should be noted that for those of ordinary skill in the technical field, without departing from the principle described in this application, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this application.

Claims

1. An information management system for asthma patients, characterized in that, Comprising: An acquisition module, configured to acquire values of all influencing factors of multiple asthma patients of different types; The influencing factors are factors affecting readmission of asthma patients, and each type corresponds to at least one asthma patient; A construction module, configured to respectively construct, for each of the types, a linear regression model between all influencing factors and the length of hospital stay under the type, and a readmission risk model of asthma patients under the type, according to the values of all influencing factors of all asthma patients of the type; An analysis module, configured to analyze and obtain the predicted status of each asthma patient according to the linear regression model and the readmission risk model corresponding to each asthma patient, and obtain the total length of hospital stay and the average number of hospitalizations of each type according to all the predicted statuses; A treatment recommendation module, configured to output treatment recommendation information for a target asthma patient based on the total length of hospital stay and the average number of hospitalizations of all types; Wherein, the analysis module is specifically configured to implement: For each asthma patient, respectively perform the following steps: Taking the values of all influencing factors of the asthma patient and the type of the asthma patient as the current status; Constructing a state transition function according to the current status, and calculating the next status of the asthma patient and the time interval of state transition according to the state transition function and the readmission risk model, and taking the patient status described by the next status as the predicted patient status of the asthma patient; the patient status is death or readmission, and the state transition function is used to calculate the probability of the asthma patient transferring to the next status and the probability of the time interval of state transition according to the values of all influencing factors of the asthma patient and the type of the asthma patient; Judging whether the time interval is greater than the remaining observation duration, or whether the predicted patient status is death; If the time interval is greater than the remaining observation duration, or the predicted patient status is death, then counting the number of times the predicted patient status is readmission, calculating the length of hospital stay for each readmission according to the corresponding linear regression model, and taking the number of readmissions and the total length of hospital stay as the predicted status of the predicted patient status; If the time interval is less than or equal to the remaining observation duration and the predicted patient status is not death, then taking the next status as the current status, taking the difference between the remaining observation duration and the time interval as the remaining observation duration, and returning to the step of constructing a state transition function according to the current status and calculating the predicted patient status of the asthma patient according to the state transition function.

2. The asthma patient information management system according to claim 1, wherein The linear regression model is: Among them, for the i-th type of asthma patients, Y i represents the length of hospitalization, represents the intercept, L represents the set of values of all influencing factors, represents the influence coefficient of the influencing factor l on the length of hospitalization, X l represents the value of the influencing factor l, i = 1, 2,..., I, and I represents the number of patient types.

3. The asthma patient information management system according to claim 2, characterized in that, The readmission risk model is: Among them, for the \(i\)-th type of asthma patients, \(h(t|X)\) i represents the readmission risk value, represents the baseline risk function, represents the influence coefficient of the influencing factor \(l\) on the readmission intensity, and exp represents the exponential function.

4. The asthma patient information management system according to claim 1, wherein, The state transition function is: Among them, p(s'|s,t) represents the probability that an asthma patient transfers from the current state s to state s' with a time interval of t, ω Death (s) represents whether an asthma patient in the current state s has died. The value 0 indicates not dead, and the value 1 indicates dead, ω Death (s') represents whether an asthma patient in state s' has died. L represents the set of values of all influencing factors, ω l (s) represents the value of the influencing factor l in the current state s, ω l (s') represents the value of the influencing factor l in state s', ω Type (s) represents the type of asthma patient in the current state s, ω Type (s') represents the type of asthma patient in state s', ω Admission (s) represents the number of readmissions of an asthma patient in the current state s, ω Admission (s') represents the number of readmissions of an asthma patient in state s'. d and μ(s) represent the distribution parameters of the current state s. d is the distribution parameter of whether an asthma patient has died, and μ(s) is the distribution parameter of the number of readmissions of an asthma patient, is the probability of an asthma patient being readmitted, is the probability of an asthma patient dying. F(s'|s,t) represents the probability that an asthma patient transfers from s to s' without dying: Among them, represents the baseline readmission intensity of asthma patients of type ω Type (s), represents the readmission transfer intensity parameter of patients of type ω Type (s) on influencing factor l, represents the change rate parameter of influencing factor l of patients of type ω Type (s), f(s'|s, l, t) represents the probability that the current state s is consistent with state s' on feature l, and e represents the natural logarithm.

5. The asthma patient information management system according to claim 4, wherein The calculating the next status of the asthma patient and the time interval of state transition according to the state transition function and the readmission risk model includes: Initializing multiple statuses and multiple time intervals according to the readmission risk model; For each of the said states, calculate the probability that the current state transfers to the said state according to the state transition function, with a time interval of t i ; t i = 1, 2, ..., T, where T represents the number of initialized time intervals; Determining the next status of the asthma patient and the time interval of state transition from all the statuses and time intervals according to all the probabilities.

6. The asthma patient information management system according to claim 1, wherein The obtaining the total length of hospital stay and the average number of hospitalizations of each type according to all the predicted statuses includes: For each of the said types, the following steps are carried out: Sum up the total length of hospital stay in the predicted status of all asthma patients corresponding to the said type to obtain the total length of hospital stay for the said type; Average the number of readmissions in the predicted status of all asthma patients corresponding to the said type to obtain the average number of hospitalizations for the said type.

Images