A method, device and equipment for multi-cycle analysis of pulmonary function data

Abstract

The application provides a lung function data multi-period analysis method, device and equipment, the method comprising: acquiring a respiratory waveform signal of a target object; acquiring lung function time series data of the target object at a target time point; labeling the lung function time series data according to different dimensional time periods to construct a time period factor variable; inputting the time period factor into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at the target time point; the pre-trained lung function data prediction model is obtained by training based on historical lung function time series data and historical lung function actual measurement values of the target object; and obtaining a lung function analysis result of the target object based on the lung function actual measurement value and the dynamic baseline value of the target object at the target time point.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical data processing, and in particular to a lung function data multi-period analysis method, device and equipment. BACKGROUND

[0002] Existing lung function monitoring mainly relies on single or intermittent detection. However, in fact, lung function time series data is a non-stationary signal, which may change due to factors such as season, temperature, allergens, etc. Therefore, it is difficult to capture complex changes through single or intermittent detection, and it is difficult to distinguish between daily fluctuations and real condition changes. The analysis results obtained are prone to large deviations and poor accuracy. SUMMARY

[0003] Therefore, the present application provides a lung function data multi-period analysis method, device and equipment.

[0004] In a first aspect, the present application provides a lung function data multi-period analysis method, comprising: obtaining lung function time series data of a target object at a target time point; labeling the lung function time series data according to different dimensions of time periods to construct a time period factor variable; inputting the time period factor into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at the target time point; the pre-trained lung function data prediction model is obtained by training based on historical lung function time series data and historical lung function actual measurement values of the target object; and obtaining a lung function analysis result of the target object based on the lung function actual measurement value and the dynamic baseline value of the target object at the target time point.

[0005] In a second aspect, the present application provides a lung function data multi-period analysis device, comprising: a time series data acquisition module configured to obtain lung function time series data of a target object at a target time point; a time period factor variable construction module configured to label the lung function time series data according to different dimensions of time periods to construct a time period factor variable; a dynamic baseline value generation module configured to input the time period factor into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at the target time point; the pre-trained lung function data prediction model is obtained by training based on historical lung function time series data and historical lung function actual measurement values of the target object; and a lung function analysis module configured to obtain a lung function analysis result of the target object based on the lung function actual measurement value and the dynamic baseline value of the target object at the target time point.

[0006] In a third aspect, an embodiment of the present application provides a lung function data multi-period analysis device, comprising: a processor and a memory connected with the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor to enable the processor to perform the lung function data multi-period analysis method of any of the embodiments of the first aspect.

[0007] The lung function data multi-period analysis method, device and equipment provided by the embodiments of the present application generate a "dynamic baseline value" matched with the current physiological state, season, week and daily rhythm of each target object, so that the baseline can be adaptively adjusted according to the individual changes. Moreover, by stripping the normal and predictable multi-period fluctuations, the truly abnormal and possibly abnormal data can be more accurately identified, the false positives caused by physiological fluctuations can be significantly reduced, and accurate and timely lung function analysis can be achieved.

[0008] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the drawings needed in the specific embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0010] Figure 1 is an exemplary system architecture to which the present application can be applied;

[0011] Figure 2 A flowchart of a lung function data multi-period analysis method provided by an embodiment of the present application;

[0012] Figure 3 A flowchart of another lung function data multi-period analysis method provided by an embodiment of the present application;

[0013] Figure 4 A flowchart of still another lung function data multi-period analysis method provided by an embodiment of the present application;

[0014] Figure 5 A function curve diagram corresponding to an annual period provided by an embodiment of the present application;

[0015] Figure 6 A structural block diagram of a lung function data multi-period analysis device provided by an embodiment of the present application;

[0016] Figure 7 A structural schematic diagram of an electronic device suitable for performing the lung function data multi-cycle analysis method according to an embodiment of the present application is provided. DETAILED DESCRIPTION

[0017] The technical solutions of the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0018] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application. In addition, the terms "first", "second", "third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0019] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the communication between two elements inside, it can be wireless connection, or it can be wired connection. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0020] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0021] Figure 1 An exemplary system architecture 100 is shown, which can apply the embodiments of the lung function data multi-cycle analysis method, device and equipment of the present application.

[0022] As shown in Figure 1 The system architecture 100 can include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a communication link medium between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0023] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 and the server 105 can be installed with various applications for realizing information communication between the two, such as instant messaging applications, etc.

[0024] The terminal devices 101, 102, 103 and the server 105 can be hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, etc.; when the terminal devices 101, 102, 103 are software, they can be installed in the above-mentioned electronic devices, and can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or as a single server; when the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here.

[0025] The server 105 can provide various services through various built-in applications. It should be noted that the data or information required to provide various services can be obtained from the terminal devices 101, 102, 103 through the network 104, or can be pre-stored locally in the server 105 in various ways. Therefore, when the server 105 detects that the local has already stored these data, it can choose to obtain these data directly from the local, in which case the exemplary system architecture 100 can also not include the terminal devices 101, 102, 103 and the network 104.

[0026] Since providing various services may require significant computing resources and power, the multi-cycle lung function data analysis method provided in the subsequent embodiments of this invention is generally executed by a server 105 with strong computing power and abundant computing resources. Correspondingly, the multi-cycle lung function data analysis device is also generally located within the server 105. However, it should also be noted that when terminal devices 101, 102, and 103 also possess sufficient computing power and resources, they can also perform the aforementioned calculations performed by the server 105 through their installed applications, thereby outputting the same results as the server 105. Especially when multiple terminal devices with different computing capabilities exist simultaneously, but the relevant application determines that the terminal device has strong computing power and abundant remaining computing resources, the terminal device can perform the aforementioned calculations, thereby appropriately reducing the computing pressure on the server 105. Accordingly, the multi-cycle lung function data analysis device can also be located within terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may also exclude the server 105 and the network 104.

[0027] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0028] Please refer to Figure 2 , Figure 2 A flowchart of a multi-cycle analysis method for lung function data provided in an embodiment of the present invention is included, wherein process 200 includes the following steps:

[0029] Step 201: Obtain the lung function time series data of the target object at the target time point.

[0030] This step aims to be performed by the entity carrying out the multi-cycle analysis method of lung function data (e.g., Figure 1 The server 105 shown obtains the lung function time series data of the target subject at the target time point. In this embodiment, the target subject mainly refers to the person as the subject. The target time point can be a fixed time, such as 10:00 AM every day, which can be set and adjusted according to actual needs. The lung function time series data refers to the time series data of core lung function indicators, which may include respiratory rate, expiratory time, inspiratory time, inspiratory-expiratory ratio, etc. The time series data can be formed by forming an independent time series based on these indicators. For example, a respiratory rate curve per minute throughout the day, or the changing trend of expiratory time and inspiratory time each night, can be plotted.

[0031] Step 202: labeling the lung function time series data according to different dimensions of time periods to construct time period factor variables.

[0032] This step aims to label the lung function time series data according to different dimensions of time periods (for example, one day as a period, one week as a period, one month as a period, etc.) based on the corresponding time information in the lung function time series data to construct time period factor variables. In this embodiment, the label of different dimensions of time periods is labeled for each data in the lung function time series data where h(t) represents a certain time period in a day, d(t) represents the day of the week, and s(t) represents a certain day of the year, thereby constructing the time period factor variables.

[0033] Step 203: inputting the time period factor into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at a target time point.

[0034] This step aims to input the time period factor into a pre-trained lung function data prediction model by the above-mentioned execution subject. The output of the pre-trained lung function data prediction model is the predicted value of the lung function of the target object at the target time point, that is, the dynamic baseline value of the target object at the target time point. The pre-trained lung function data prediction model is trained based on the historical lung function time series data and the historical lung function actual measurement value of the target object. The specific training process of the model will be further described below.

[0035] Step 204: obtaining a lung function analysis result of the target object based on the actual measurement value and the dynamic baseline value of the target object at the target time point.

[0036] This step aims to obtain the lung function actual measurement value of the target object at the target time point by the above-mentioned execution subject, and obtain the lung function analysis result of the target object based on the lung function actual measurement value and the dynamic baseline value. The dynamic baseline value is obtained by the lung function data prediction model at the target time point, so that the lung function actual measurement value of the target object is compared with the dynamic baseline value, and the lung function analysis result of the target object can be obtained.

[0037] The lung function data multi-period analysis method provided by the embodiment of the present application generates a "dynamic baseline value" matched with the current physiological state, season, week, and daily rhythm of each target object, so that the baseline can be adaptively adjusted according to the individual changes. Moreover, by stripping the normal and predictable multi-period fluctuations, the truly abnormal and possibly abnormal data can be more accurately identified, the false positives caused by physiological fluctuations can be significantly reduced, and accurate and timely lung function analysis can be realized.

[0038] Please refer to Figure 3 , Figure 3 A flowchart of a multi-cycle analysis method for lung function data provided in this disclosure embodiment, namely for... Figure 2 Step 202 in process 200 provided a specific implementation. Other steps in process 200 are not adjusted; a new complete embodiment is obtained by replacing step 202 with the specific implementation provided in this embodiment. Process 300 includes the following steps:

[0039] Step 301: Label the lung function time series data according to daily, weekly, and annual cycles, and determine the correlation between the lung function time series data in different cycle dimensions.

[0040] In this embodiment, lung function time series data are labeled according to three dimensions: daily cycle, weekly cycle, and yearly cycle. Where h(t) represents a certain time period within a day, d(t) represents a day of the week within a week, and s(t) represents a certain day of the year, to characterize the data of each lung function characteristic indicator in a certain time period of a certain day of a certain year.

[0041] Step 302: Extract features from the labeled lung function time series data to obtain the time period factor variable.

[0042] In this embodiment, after labeling the lung function time series data, feature extraction is performed to obtain data that can be directly called by the model.

[0043] In some optional implementations of this embodiment, such as Figure 4 As shown, the training process of the pre-trained lung function data prediction model mainly includes:

[0044] Step 401: Obtain historical lung function time series data and historical actual lung function measurements of the target object within a preset time period.

[0045] In this embodiment, the data required to train the model consists of historical lung function time-series data for the target object over a preset time period (e.g., the past week, month, or year), and the corresponding historical actual lung function measurements as sample data. For example, for the t-th sample: h(t) can represent an integer from 1 to 24, representing the hour; d(t) can represent an integer from 1 to 7, representing the day of the week; and s(t) can represent an integer from 1 to 365, representing the day of the year.

[0046] Step 402: Calculate the global average lung function of the target subject based on historical lung function time series data.

[0047] In this embodiment, the lung function data prediction model is trained based on a generalized additive model (GAM), for which smooth functions, global average values, residual terms, etc. need to be determined. In this step, the lung function global average value of the target object is calculated based on historical lung function time series data.

[0048] Step 403: Label the historical lung function time series data according to different dimensions of time period, and construct historical time period factor variables.

[0049] In this embodiment, the historical lung function time series data is labeled according to three dimensions of daily period, weekly period, and annual period where h(t) represents a certain time period in a day, d(t) represents the day of the week, and s(t) represents a certain day of the year, to represent the data of each lung function characteristic index on the day of the week in a certain year at a certain time period.

[0050] Step 404: Input the historical time period factor and the historical lung function actual measurement value into the initial generalized additive model, and train to obtain the lung function data prediction model.

[0051] In this embodiment, the historical time period factor and the historical lung function actual measurement value are input into the initial generalized additive model, and the initial generalized additive model is trained to obtain the lung function data prediction model. Exemplarily, the training process can mainly include:

[0052] Step 1: Specify the smooth base function and the penalty term.

[0053] First, select the base function. For each smooth term in the initial generalized additive model, select a set of base functions.

[0054] Then, define the penalty term. To prevent overfitting, the "degree of curvature" of the base function is penalized. The square integral of the second derivative of the function (which measures the concave-convex change of the curve) can be used as the penalty term. The more curved it is, the greater the penalty. In this way, the model will seek a balance between "fitting degree" and "smoothness".

[0055] Step 2: Fit / learn model parameters.

[0056] In this embodiment, the process can be implemented using the "penalized iteratively reweighted least squares method". The loss function can use the square loss function, and the objective function is equal to the loss function + penalty term.

[0057] In the fitting process, first, initial values are set for all coefficients (including the aforementioned global average and coefficients of each basis function). Then, the predicted value and the residual are calculated according to the current coefficients. All coefficients and smoothing parameters are solved simultaneously by a mathematical optimization algorithm to minimize the above objective function, and in this optimization process, the above coefficients are updated. Finally, a set of optimal coefficients is obtained, thereby determining the coefficients of each smoothing function, etc., and thus obtaining the lung function data prediction model.

[0058] In some optional embodiments of the present embodiment, in the process of analyzing the lung function of the target object using the above lung function data prediction model, the lung function data prediction model can be updated based on the actual data accumulated over a period of time, so that the lung function data prediction model can adapt to the long-term changes of the lung function of the target object. Specifically, the updating process mainly includes:

[0059] Step one: obtain lung function time series data, corresponding dynamic baseline values and lung function measured values within a preset time length after a target time point.

[0060] In the present embodiment, lung function time series data within a period of time (for example, one week, one month or one year, etc.) and its corresponding dynamic baseline values and lung function measured values are obtained.

[0061] Step two: based on the lung function analysis result, screen the first lung function measured value within the normal range and its corresponding first dynamic baseline value, first lung function time series data.

[0062] In the present embodiment, it is hoped that the output result (i.e. dynamic baseline value) of the lung function data prediction model can be more in line with the standard value of the normal lung function of the target object, and can be dynamically adjusted. Therefore, in this process, the first lung function measured value within the normal range and its corresponding first dynamic baseline value, first lung function time series data need to be screened out, so as to eliminate the lung function measured value and its corresponding dynamic baseline value, lung function time series data when the analysis result is abnormal.

[0063] Step three: based on the first lung function measured value and its corresponding first dynamic baseline value, first lung function time series data, the lung function data prediction model is trained to update the lung function data prediction model.

[0064] In the present embodiment, after determining the data used for updating, these data (first lung function measured value and its corresponding first dynamic baseline value, first lung function time series data) can be input into the lung function data prediction model to update it.

[0065] Through the above process, the lung function prediction model can be dynamically updated in real time, so as to adapt to the long-term changes of the lung function of the target object, more match the actual physical condition of the target object, and make the output prediction result more accurate and effective.

[0066] In some optional embodiments of the present embodiment, the process of obtaining the lung function analysis result of the target object based on the actual measurement value and the dynamic baseline value of the target object at the target time point in step 204 mainly includes:

[0067] Step one: calculate the deviation value between the actual measurement value and the dynamic baseline value of the lung function.

[0068] In the present embodiment, the deviation value is obtained by subtracting the dynamic baseline value from the actual measurement value of the lung function. Specifically, the deviation is determined by the following formula: ,

[0069] Among them, represents the actual measurement value of the lung function of the target object, represents the dynamic baseline value.

[0070] Correspondingly, the lung function data prediction model is represented by the following formula:

[0071] ,

[0072] Among them, represents the global average value; represents the t-th time period in the day cycle; represents the t-th day in the week cycle; represents the t-th day in the year cycle; represents three periodic components respectively; represents the interaction between periods; represents the residual error.

[0073] Dynamic baseline value ,

[0074] Among them, represents the dynamic baseline value of the lung function at time t, is the mathematical expectation operator.

[0075] Step two: determine the lung function analysis result based on the preset threshold multiple factor, the standard deviation of the prediction error of the lung function data prediction model and the deviation value.

[0076] In the present embodiment, the lung function analysis result is determined by the following formula:

[0077] ,

[0078] wherein k represents a threshold multiplier, denotes a standard deviation of the prediction error, the standard deviation being represented by: .

[0079] In practical applications, the number corresponding to the threshold multiplier represents the allowed deviation range of the deviation value. For example, k = 2, that is, the allowed deviation range is 2 standard deviations. If the actual measurement value of a certain time is significantly lower than the dynamic baseline value, that is, the deviation is greater than 2 standard deviations, the corresponding lung function analysis result is determined to be abnormal.

[0080] To deepen the understanding, the present application also gives a specific implementation scheme in combination with a specific application scenario.

[0081] Suppose that the lung function of the target object is measured 24 times per day (h(t)), 7 times per week (d(t)), and 365 times per year (s(t)). And thus the lung function data prediction model is obtained: wherein:

[0082] is the intercept term in the generalized additive model (GAM), representing the average level of lung function, for example = 0.6.

[0083] is the period of influence:

[0084] ,

[0085] It can be seen from the above formula that the lung function of the target object is high in the morning period, and the lung function is poor in the evening period (late afternoon and night).

[0086] is the influence of the week:

[0087] ,

[0088] It can be seen from the above formula that the body state (lung function) of the target object is best on the weekend, and the lung function is worst on Monday.

[0089] is the annual cycle (smoothing function fitting):

[0090] ,

[0091] wherein, represents the basic annual cycle trend (high in summer and low in winter), represents a short-term decrease in spring allergy (mid-March), represents a short-term decrease in autumn allergy (mid-September), Representing the additional drop in winter (first 60 days, last 35 days). The function curve is as shown in Figure 5

[0092] The hour x weekday interaction function is:

[0093]

[0094] From the above equation, we can see that for this target object, the lung function is less affected in the early morning on weekends, more affected in the early morning on weekdays, most affected in the evening peak on weekdays, less affected in the evening on weekends, and not affected at other times.

[0095] The weekday x in-year period interaction function is:

[0096]

[0097] From the above equation, we can see that for this target object, the lung function is more affected in spring + Monday, less affected in spring + weekend, more affected in autumn + Monday, less affected in autumn + weekend, and not affected at other times.

[0098] On this basis, the effects of all functions are added to obtain the expected normal lung function value (dynamic baseline value) of the target object at the specific time point of "Wednesday morning 9 o'clock, spring 100th day (April 10th)":

[0099]

[0100] = 0.60 + 0.60 + (-0.30) + (-0.50) + (-0.20) + 0

[0101] = 0.20.

[0102] If the actual measured value of the lung function of the target object is At this time, the deviation value is calculated as: =0.15-0.20=-0.05.

[0103] Assuming the historical prediction error standard deviation of the model σ = 0.02, and setting the threshold k = 2.

[0104] Abnormal threshold: -k * σ = -2 * 0.02 = -0.04; comparison: residual (-0.05) < threshold (-0.04). Therefore, the actual measured value is significantly lower than the dynamic baseline predicted value (more than 2 standard deviations), thus triggering the "indicator drop" warning.

[0105] Further reference​​​Figure 6 As an implementation of the method shown in the above figures, the present application provides an embodiment of a lung function data multi-period analysis device, which corresponds to the method embodiment shown in Figure 2 The device can be applied in various electronic devices.

[0106] As shown in Figure 6 , the lung function data multi-period analysis device 600 of the embodiment can include a time series data acquisition module 601, a time period factor variable construction module 602, a dynamic baseline value generation module 603, and a lung function analysis module 604. The time series data acquisition module 601 is configured to acquire lung function time series data of a target object at a target time point. The time period factor variable construction module 302 is configured to label the lung function time series data according to different dimensions of time periods, and construct time period factor variables. The dynamic baseline value generation module 603 is configured to input the time period factor into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at the target time point. The pre-trained lung function data prediction model is obtained by training based on historical lung function time series data and historical lung function actual measurement values of the target object. The lung function analysis module 604 is configured to obtain a lung function analysis result of the target object based on the lung function actual measurement value and the dynamic baseline value of the target object at the target time point.

[0107] In the embodiment, the specific processing of the time series data acquisition module 601, the time period factor variable construction module 602, the dynamic baseline value generation module 603, and the lung function analysis module 604 in the lung function data multi-period analysis device 600 and the technical effects brought by the specific processing can be respectively referred to the related descriptions of steps 201-204 in the corresponding embodiment, which will not be repeated here. Figure 2

[0108] In some optional implementations of the embodiment, the time period factor variable construction module 602 is specifically configured to label the lung function time series data according to daily periods, weekly periods, and annual periods, and determine the correlation between the lung function time series data in different period dimensions. The labeled lung function time series data is subjected to feature extraction to obtain the time period factor variables.

[0109] In some optional implementations of the embodiment, the lung function analysis module 604 is specifically configured to calculate a deviation value between the lung function actual measurement value and the dynamic baseline value, and determine the lung function analysis result based on a preset threshold multiple factor, a standard deviation of a prediction error of the lung function data prediction model, and the deviation value.

[0110] ​In some optional implementations of the present embodiment, the lung function data multi-period analysis apparatus 600 further comprises a historical data acquisition module configured to acquire historical lung function time series data and historical lung function actual measurement values of the target object within a preset time; a global average value calculation module configured to calculate a global average value of lung function of the target object based on the historical lung function time series data; a historical time period factor variable construction module configured to label the historical lung function time series data according to different dimensions of time periods, and construct historical time period factor variables; and a lung function data prediction model generation module configured to input the historical time period factors and the historical lung function actual measurement values into an initial generalized additive model, and train to obtain a lung function data prediction model.

[0111] In some optional implementations of the present embodiment, the lung function data multi-period analysis apparatus 600 further comprises a model updating module, specifically configured to perform the following process: acquiring lung function time series data, corresponding dynamic baseline values and lung function actual measurement values within a preset time length after a target time point; filtering first lung function actual measurement values and corresponding first dynamic baseline values and first lung function time series data within a normal range based on lung function analysis results; and training the lung function data prediction model based on the first lung function actual measurement values and corresponding first dynamic baseline values and first lung function time series data, to update the lung function data prediction model.

[0112] The present embodiment, as a device embodiment corresponding to the above-mentioned method embodiment, provides a lung function data multi-period analysis apparatus that generates a "dynamic baseline value" matched with the current physiological state, season, week and daily rhythm of each target object, so that the baseline can be adaptively adjusted according to individual changes. Moreover, by stripping the normal and predictable multi-period fluctuations, the truly abnormal and possibly abnormal data can be more accurately identified, the false positives caused by physiological fluctuations can be significantly reduced, and accurate and timely lung function analysis can be achieved.

[0113] According to the embodiments of the present application, the present application further provides an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the lung function data multi-period analysis method described in any of the above embodiments when executed.

[0114] According to the embodiments of the present application, the present application further provides a readable storage medium storing computer instructions for enabling a computer to implement the lung function data multi-period analysis method described in any of the above embodiments when executed.

[0115] According to an embodiment of the present application, the present application also provides a computer program product, which, when executed by a processor, can implement the lung function data multi-cycle analysis method described in any of the above embodiments.

[0116] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0117] As shown in Figure 7 The device 700 includes a computing unit 701 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0118] Various components in the device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; the storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0119] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs various methods and processes described above, such as the lung function data multi-cycle analysis method. For example, in some embodiments, the lung function data multi-cycle analysis method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the lung function data multi-cycle analysis method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the lung function data multi-cycle analysis method by any other suitable means, such as by means of firmware.

[0120] Those skilled in the art will appreciate that embodiments of the present application can be supplied as a method, a system, or a computer program product. Thus, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage media, etc.) having computer usable program code embodied in the medium.

[0121] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagrams, and a combination of flows and / or blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processing machine, or other programmable data processing apparatus to produce a machine, so that the instructions, which are executed via the processor of the computer or other programmable data processing apparatus, create a means for implementing the functions specified in the flowchart and / or block diagrams block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flowchart and / or block diagrams block or blocks.

[0122] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow or flows and / or blocks Figure 1 The function specified in the flow or flows and / or block or blocks.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 The flow or flows and / or blocks Figure 1 Figure 1 The function specified in the flow or flows and / or block or blocks.

[0124] Obviously, the above-described embodiments are only examples and are not intended to limit the present application. Other variations and modifications can be made based on the above description and illustrations, and such variations and modifications are also within the scope of the present application. It is not necessary to recite all the embodiments of the present application. The obvious variations and modifications that are derived from the present application are also within the scope of the present application.

Claims

1. A method for multi-period analysis of lung function data, characterized in that, The method comprises the following steps: obtaining lung function time series data of a target object at a target time point; labeling the lung function time series data according to different dimensions of time periods to construct time period factor variables; inputting the time period factors into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at the target time point; the pre-trained lung function data prediction model is obtained based on historical lung function time series data and historical lung function actual measurement values of the target object; obtaining a lung function analysis result of the target object based on a lung function actual measurement value of the target object at the target time point and the dynamic baseline value; wherein the labeling of the lung function time series data according to different dimensions of time periods to construct time period factor variables comprises: labeling the lung function time series data according to daily, weekly and annual periods, and determining the correlation between the lung function time series data in different period dimensions; extracting features from the labeled lung function time series data to obtain the time period factor variables.

2. The method of claim 1, wherein, The method further comprises the following steps: obtaining the historical lung function time series data and the historical lung function actual measurement values of the target object within a preset time period; calculating a global average value of the lung function of the target object based on the historical lung function time series data; labeling the historical lung function time series data according to different dimensions of time periods to construct historical time period factor variables; inputting the global average value of the lung function, the historical time period factors and the historical lung function actual measurement values into an initial generalized additive model to train the lung function data prediction model.

3. The method of claim 2, wherein, The method further comprises the following steps: obtaining lung function time series data, corresponding dynamic baseline values and lung function actual measurement values within a preset time period after the target time point; based on the lung function analysis result, filtering first lung function actual measurement values and corresponding first dynamic baseline values and first lung function time series data within a normal range; training the lung function data prediction model based on the first lung function actual measurement values and corresponding first dynamic baseline values and first lung function time series data to update the lung function data prediction model.

4. The method of claim 1, wherein, The method of obtaining a lung function analysis result of the target object based on a lung function actual measurement value of the target object at the target time point and the dynamic baseline value comprises the following steps: calculating a deviation value between the lung function actual measurement value and the dynamic baseline value; determining the lung function analysis result based on a preset threshold factor, a standard deviation of a prediction error of the lung function data prediction model and the deviation value.

5. The method of claim 4, wherein, The lung function data prediction model is represented by the following formula: ， wherein, denotes the global average; denotes the t-th time period in the day cycle; denotes the t-th day in the week cycle; denotes the t-th day in the year cycle; denotes the three periodic components, respectively; denotes the interaction between the periods; denotes the residual.

6. The method of claim 5, wherein, The prediction value output by the lung function data prediction model is represented by the following formula: ， wherein denotes a dynamic baseline value of the lung function at time t, is the mathematical expectation operator.

7. The method of claim 5, wherein, The lung function analysis result is determined by the following formula: ， wherein k denotes the threshold factor, denotes the standard deviation of the prediction error, the standard deviation is represented by: .

8. A multi-cycle analysis device for pulmonary function data, characterized by The method comprises the following steps: a time series data acquisition module configured to obtain lung function time series data of a target object at a target time point; a time period factor variable construction module configured to label the lung function time series data according to different dimensions of time periods to construct time period factor variables; The dynamic baseline value generation module is configured to input the time period factor into a pre-trained lung function data prediction model to obtain a dynamic baseline value of the target object at the target time point; the pre-trained lung function data prediction model is obtained by training based on historical lung function time series data and historical lung function actual measurement values of the target object; The lung function analysis module is configured to obtain a lung function analysis result of the target object based on the lung function actual measurement value and the dynamic baseline value of the target object at the target time point; The time period factor variable is constructed by marking the lung function time series data according to different dimensions of time periods, including: The lung function time series data is marked according to day periods, week periods and year periods, and the association between the lung function time series data in different period dimensions is determined; The time period factor variable is obtained by performing feature extraction on the marked lung function time series data.

9. A lung function data multi-cycle analysis device, characterized by The method comprises: A processor and a memory connected to the processor; wherein the memory stores instructions executable by the processor, and the instructions are executed by the processor to enable the processor to perform the lung function data multi-period analysis method according to any one of claims 1-7.

Images