Physiological age prediction method and device, storage medium and computing equipment
By obtaining the user's physical examination information and using multiple predictive sub-models, the problem of inaccurate quantification of physiological age in the prior art is solved, and accurate prediction and health monitoring of the user's physiological age are achieved.
Patent Information
- Application Number
- CN202311492464.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-09
- Publication Date
- 2025-05-09
AI Technical Summary
The prior art cannot accurately quantify the real physiological age of the body, and it is difficult to assist in judging the user's physical health status.
By obtaining the user's physical examination information and/or diagnosis and treatment information, multiple predictive sub-models are used to input the physical examination indicators into the corresponding prediction model to obtain the physiological age and comprehensive age of each organ.
It realizes accurate prediction of users' physiological age, can assist users in health monitoring more comprehensively, and improves the accuracy of health assessment.
Smart Images
Figure CN119964787A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a physiological age prediction method and device, a storage medium, and a computing device. Background Art
[0002] In the field of life and health, it is necessary to predict the user's physiological age to assist in determining the user's physical health status.
[0003] The existing technology mainly has the following implementation methods: using fundus imaging medical equipment to clean image information and predict physiological age.
[0004] However, existing technologies cannot accurately quantify the body's true physiological age. Summary of the invention
[0005] The technical solution of this application can improve the accuracy of physiological age prediction.
[0006] In order to achieve the above objectives, this application provides the following technical solutions:
[0007] In a first aspect, a physiological age prediction method is provided, the physiological age prediction method comprising: obtaining physical examination information and / or diagnosis and treatment information input by a user, the physical examination information and / or diagnosis and treatment information including the actual age and physical examination indicators of the user; inputting the physical examination indicators into a prediction model corresponding to the actual age of the user to obtain a predicted age, the prediction model comprising a plurality of first prediction sub-models and second prediction sub-models, each first prediction sub-model being used to predict the physiological age of an organ of a corresponding type, the second prediction sub-model being used to predict the comprehensive age of the user, the predicted age including the physiological age of each organ and the comprehensive age; and outputting the predicted age.
[0008] Optionally, the physical examination information and / or diagnosis and treatment information also includes gender; and inputting the physical examination indicators into the prediction model corresponding to the actual age of the user includes: inputting the physical examination indicators into the prediction model corresponding to the data combination, and the data combination includes the actual age and gender of the user.
[0009] Optionally, each prediction model corresponds to a gender and a classified age group, and the process of inputting the physical examination indicators into the prediction model corresponding to the data combination includes: determining the first classified age group into which the actual age of the user in the data combination falls; and inputting the physical examination indicators into the prediction model corresponding to the first classified age group and the gender of the user.
[0010] Optionally, the first prediction sub-model is constructed in the following manner: obtaining first physical examination indicators of each first user within the classification age group corresponding to the first prediction sub-model; selecting first indicator data related to the organ of the type corresponding to the first prediction sub-model and the actual age of the first user in the first physical examination indicators as first training data; fitting the first indicator data and the actual age of the first user to obtain the first prediction sub-model.
[0011] Optionally, fitting the first training data includes: using multiple fitting algorithms to fit the first indicator data and the actual age of the first user to obtain multiple fitting functions; selecting the optimal fitting function among the multiple fitting functions that is closest to the first indicator data and the actual age of the first user as the first prediction sub-model.
[0012] Optionally, the selecting of the first indicator data related to the type of organ corresponding to the first prediction sub-model in the first physical examination indicator includes: selecting one or more of the following indicator data related to the type of organ corresponding to the first prediction sub-model in the first physical examination indicator: median, quantile, minimum value, maximum value, standard deviation, as the first indicator data.
[0013] Optionally, the first prediction sub-model is verified and adjusted in the following manner: obtaining second physical examination indicators of the second user in the insurance data and / or medical data; selecting second indicator data related to the organ of the type corresponding to the first prediction sub-model from the second physical examination indicators; and using the second indicator data and the actual age of the second user to verify and adjust the first prediction sub-model.
[0014] Optionally, the second prediction sub-model is constructed in the following manner: obtaining third physical examination indicators of each third user within the classification age group corresponding to the second prediction sub-model as second training data; fitting the second training data with the actual age of the third user to obtain the second prediction sub-model.
[0015] Optionally, the organ is selected from one or more of the following: heart, kidney, immune system, blood vessel, body system, metabolic system and joint.
[0016] In a second aspect, the present application also discloses a physiological age prediction device, which includes: an acquisition module, used to obtain physical examination information and / or diagnosis and treatment information input by a user, wherein the physical examination information and / or diagnosis and treatment information include the actual age and physical examination indicators of the user; a prediction module, used to input the physical examination indicators into a prediction model corresponding to the actual age of the user to obtain a predicted age, wherein the prediction model includes multiple first prediction sub-models and second prediction sub-models, each first prediction sub-model is used to predict the physiological age of an organ of a corresponding type, and the second prediction sub-model is used to predict the comprehensive age of the user, and the predicted age includes the physiological age of each organ and the comprehensive age; an output module, used to output the predicted age.
[0017] According to a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. The computer program is executed by a processor to execute any one of the methods provided in the first aspect.
[0018] In a fourth aspect, a computing device is provided, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to execute any one of the methods provided in the first aspect.
[0019] According to a fifth aspect, a computer program product is provided, on which a computer program is stored, and the computer program is executed by a processor to execute any one of the methods provided in the first aspect.
[0020] In a sixth aspect, an embodiment of the present application further provides a chip (or a data transmission device) on which a computer program is stored, and when the computer program is executed by the chip, the steps of the above method are implemented.
[0021] In the seventh aspect, an embodiment of the present application also provides a system chip, which is applied to a terminal, and the chip system includes at least one processor and an interface circuit, the interface circuit and the at least one processor are interconnected through lines, and the at least one processor is used to execute instructions to execute any one of the methods provided in the first aspect.
[0022] Compared with the prior art, the technical solution of this application has the following beneficial effects:
[0023] In the technical solution of the present application, the physical examination information and / or diagnosis and treatment information input by the user is obtained, and the physical examination information and / or diagnosis and treatment information include the actual age and physical examination indicators of the user; the physical examination indicators are input into the prediction model corresponding to the actual age of the user to obtain the predicted age, and the prediction model includes multiple first prediction sub-models and second prediction sub-models, each first prediction sub-model is used to predict the physiological age of the corresponding type of organ, and the second prediction sub-model is used to predict the comprehensive age of the user, and the predicted age includes the physiological age of each organ and the comprehensive age; the predicted age is output. In the technical solution of the present application, the physiological age of users in different age groups is predicted by different prediction models. The prediction model can accurately describe the mapping relationship between the physical examination indicators and each age in the age group, so as to accurately predict the physiological age of the user. In addition, the prediction model includes multiple first prediction sub-models for predicting the physiological age of the corresponding type of organs, so as to realize the prediction of the physiological age of the main organs of the user, so as to more comprehensively predict the actual age of the user and assist the user in health monitoring.
[0024] Furthermore, the present application uses a plurality of fitting algorithms to fit the first training data and the actual age of the first user to obtain a plurality of fitting functions; the optimal fitting function that is closest to the first training data and the actual age of the first user among the plurality of fitting functions is selected as the first prediction sub-model. The present application fits the first training data and the actual age of the first user through a plurality of fitting algorithms, and selects the optimal fitting function as the first prediction sub-model, which can ensure the accuracy of the first prediction sub-model in subsequent physiological age prediction. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 is a flow chart of a physiological age prediction method provided in an embodiment of the present application;
[0026] Figure 2 is a schematic diagram of a prediction model provided in an embodiment of the present application;
[0027] Figure 3 is a flow chart of another physiological age prediction method provided in an embodiment of the present application;
[0028] Figure 4 It is a schematic diagram of the structure of a physiological age prediction device provided in an embodiment of the present application;
[0029] Figure 5 It is a hardware structure diagram of a physiological age prediction device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0030] As described in the background art, existing technologies cannot accurately quantify the true physiological age of an organism.
[0031] In the technical solution of the present application, different prediction models are used to predict the physiological age of users in different age groups. The prediction model can accurately describe the mapping relationship between physical examination indicators and each age in the age group, thereby accurately predicting the physiological age of the user. In addition, the prediction model includes multiple first prediction sub-models for predicting the physiological age of organs of corresponding types, thereby realizing the prediction of the physiological age of the user's main organs, thereby more comprehensively predicting the user's actual age and assisting the user in health monitoring.
[0032] The physical examination indicators referred to in the embodiments of the present application may be physiological indicators of the user's physical health status obtained during a physical examination or diagnosis and treatment, such as diastolic blood pressure, systolic blood pressure, urea nitrogen, etc.
[0033] The physiological age referred to in the embodiments of the present application refers to the level of physiology and its functions reflected when the user reaches a certain chronological age, that is, the level of physiology and its functions corresponding to a certain chronological age. It is the age measured from the perspective of medicine and biology.
[0034] It should be noted that the various data such as physical examination information and / or diagnosis and treatment information, physical examination indicators, age, gender, indicator data, etc. referred to in the embodiments of the present application are all data authorized by the user.
[0035] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0036] See also Figure 1 The method provided in this application specifically comprises the following steps:
[0037] Step 101: obtaining physical examination information and / or diagnosis and treatment information input by a user, where the physical examination information and / or diagnosis and treatment information includes the actual age and physical examination indicators of the user;
[0038] Step 102: Input the physical examination indicators into the prediction model corresponding to the actual age of the user to obtain the predicted age.
[0039] Step 103: Output the predicted age.
[0040] It should be pointed out that the serial numbers of the steps in this embodiment do not limit the execution order of the steps.
[0041] It is understandable that, in a specific implementation, the physiological age prediction method can be implemented in the form of a software program, which runs in a processor integrated inside a chip or chip module. The method can also be implemented in the form of software combined with hardware, which is not limited in this application.
[0042] In this embodiment, each prediction model corresponds to a classification age group, and the prediction model is used to describe the mapping relationship between the age and the physical examination index within the corresponding classification age group, and is used to predict the age within the classification age group. Taking the classification age groups including 18-19 years old, 20-29 years old, 30-39 years old, 40-49 years old, 50-59 years old, 60-69 years old and over 70 years old as an example, the embodiment of the present application provides seven prediction models for each of the above classification age groups.
[0043] In a specific implementation of step 101, each physical examination index in the physical examination information and / or diagnosis and treatment information can be directly input by the user. For example, an input interface is provided for the user, and the user can enter the physical examination index item by item according to the prompts in the input interface.
[0044] In another specific implementation of step 101, the user may upload a picture including physical examination information and / or diagnosis and treatment information, and obtain the physical examination information and / or diagnosis and treatment information by performing optical character recognition (OCR) on the picture.
[0045] In the specific implementation of step 102, the physical examination indicators will be input into the prediction model corresponding to the actual age of the user. Taking the above seven prediction models as an example, if the user is 35 years old, the physical examination indicators will be input into the prediction model corresponding to the classification age group of 30-39 years old.
[0046] The embodiment of the present application takes into account that the mapping relationship between the physical examination indicators and the age of users in different classified age groups has different rules. By constructing a prediction model by age group, it is possible to more accurately describe the relationship between each physical examination indicator and age, thereby improving the accuracy of physiological age prediction.
[0047] In this embodiment, please refer to Figure 2 , the prediction model 20 includes a plurality of first prediction sub-models 201 and second prediction sub-models 202. Each first prediction sub-model 201 is used to predict the physiological age of the corresponding type of organ, and the second prediction sub-model 202 is used to predict the comprehensive age of the user. Accordingly, the predicted age includes the physiological age of each organ and the comprehensive age.
[0048] Specifically, taking organs including heart, kidney, immune system, blood vessels, body system, metabolic system and joints as an example, the prediction model 20 includes seven first prediction sub-models 201 for the above organs. The first prediction sub-model 201 corresponding to the heart can be used to predict the physiological age of the heart, the first prediction sub-model 201 corresponding to the kidney can be used to predict the physiological age of the kidney, and so on, the first prediction sub-model 201 corresponding to the joint can be used to predict the physiological age of the joint.
[0049] In a specific embodiment, the physical examination index input into the first prediction sub-model 201 corresponding to the heart may be selected from the following: diastolic pressure and systolic pressure.
[0050] In a specific embodiment, the physical examination indexes input into the first prediction sub-model 201 corresponding to the kidney may be selected from the following: urea nitrogen (Bun), urine protein, urine occult blood, and serum creatinine (Cr).
[0051] In a specific embodiment, the physical examination index input into the first prediction sub-model 201 corresponding to the immune system can be selected from the following: lymphocyte percentage, high-density cholesterol, serum alanine aminotransferase (ALT) and serum aspartate aminotransferase (AST).
[0052] In a specific embodiment, the physical examination index input into the first prediction sub-model 201 corresponding to the blood vessel can be selected from the following: high-density lipoprotein cholesterol, triglycerides, diastolic blood pressure, systolic blood pressure and low-density lipoprotein cholesterol.
[0053] In a specific embodiment, the physical examination index input into the first prediction sub-model 201 corresponding to the body system can be selected from the following: total cholesterol and body mass index (Body Mass Index, BMI).
[0054] In a specific embodiment, the physical examination index input into the first prediction sub-model 201 corresponding to the metabolic system can be selected from the following: high-density cholesterol, blood sugar test value, diastolic blood pressure, systolic blood pressure, triglyceride and BMI.
[0055] In a specific embodiment, the physical examination index input into the first prediction sub-model 201 corresponding to the joint includes BMI.
[0056] In the embodiment of the present application, different prediction models are used to predict the physiological age of users in different age groups. The prediction model can accurately describe the mapping relationship between physical examination indicators and each age in the age group, thereby accurately predicting the physiological age of the user. In addition, the prediction model includes multiple first prediction sub-models for predicting the physiological age of organs of corresponding types, thereby realizing the prediction of the physiological age of the user's main organs, thereby more comprehensively predicting the user's actual age and assisting the user in health monitoring.
[0057] In a non-limiting embodiment, the physical examination information and / or the diagnosis and treatment information also includes gender. Then, in the specific implementation of step 102, the physical examination index can be input into the prediction model corresponding to the data combination, and the data combination includes the actual age and gender of the user.
[0058] Taking the classified age groups including 18-19 years old, 20-29 years old, 30-39 years old, 40-49 years old, 50-59 years old, 60-69 years old and over 70 years old, and the gender including male and female as an example, the embodiment of the present application provides 14 prediction models for each of the above classified age groups and gender combinations.
[0059] For example, if the user is 45 years old and female, the user's physical examination indicators will be input into the prediction model corresponding to the 40-49 age group and females. The prediction model can be used to predict the comprehensive age of females in the 40-49 age group and the physiological age of each organ.
[0060] Continue to refer to Figure 1 In step 103, the predicted age output by the prediction model can be displayed to the user through a display terminal. Specifically, the physiological age and the comprehensive age of each organ can be displayed to the user on the display interface.
[0061] For example, the display interface shows that the user's heart age is 38.3 years old, kidney age is 37 years old, immune age is 36 years old, vascular age is 35.2 years old, body age is 34.6 years old, metabolic age is 34.4 years old, joint age is 32.8 years old and comprehensive age is 34.8 years old.
[0062] Furthermore, the comprehensive age and the physiological age of each organ can be analyzed, and the analysis results can be displayed to the user. Specifically, the difference between the comprehensive age, the physiological age of each organ and the actual age of the user can be compared, and the difference can be displayed to the user in a visual form.
[0063] For example, the difference between the comprehensive age and the actual age is -2.2 years, ranking 43% in the same age. The difference between the heart age and the actual age is +1.3 years, the difference between the kidney age and the actual age is 0 years, the difference between the immune age and the actual age is -1 year, the difference between the vascular age and the actual age is -1.8 years, the difference between the body age and the actual age is -2.4 years, the difference between the metabolic age and the actual age is -2.6 years, and the difference between the joint age and the actual age is -4.2 years.
[0064] Furthermore, the user's comprehensive age and the ranking of the physiological age of each organ among all users can be counted and displayed to the user in a visual form.
[0065] It should be noted that any feasible statistical analysis can be performed on the predicted age according to actual application requirements, and this application does not impose any restrictions on this.
[0066] In a non-limiting example, see Figure 3 , the first prediction sub-model is constructed in the following manner:
[0067] In step 301, a first physical examination indicator of each first user in a classified age group corresponding to a first prediction sub-model is obtained;
[0068] In step 302, first indicator data related to the organ of the type corresponding to the first prediction sub-model in the first physical examination indicator and the actual age of the first user are selected as first training data;
[0069] In step 303, the first training data is fitted with the actual age of the first user to obtain a first prediction sub-model.
[0070] In the embodiment of the present application, the first physical examination indicator of the first user is data authorized by the first user, and the number of first users is large (for example, greater than 200) to improve the accuracy of the first prediction model.
[0071] Specifically, taking the construction of the first prediction sub-model corresponding to the 40-49 years old classification age group and the female heart as an example, the first indicator data: diastolic pressure and systolic pressure are selected from the first physical examination indicators of each female user in the 40-49 years old classification age group. The relationship between the diastolic pressure, the systolic pressure and the actual age of each of the above female users is fitted to obtain the first prediction sub-model.
[0072] Furthermore, the first indicator data may be all indicator data related to the type of organ corresponding to the first prediction sub-model, or may be one or more of the following among all indicator data: median, quantile, minimum value, maximum value, and standard deviation.
[0073] In a specific embodiment, one or more of the following fitting algorithms may be used for fitting: general linear regression, logistic regression, polynomial regression, stepwise regression, lasso regression, decision tree, naive Bayes algorithm, etc.
[0074] In a specific embodiment, multiple fitting algorithms are used to fit the first indicator data in the first training data and the actual age of the first user to obtain multiple fitting functions; the optimal fitting function that is closest to the first indicator data and the actual age of the first user among the multiple fitting functions is selected as the first prediction sub-model.
[0075] The embodiment of the present application obtains a fitting function according to different fitting algorithms, and finds the optimal fitting function that is closest to the mapping relationship between the first indicator data and the actual age of the first user as the first prediction sub-model.
[0076] The above method can avoid the limitations brought by a single fitting method, and enable the first prediction sub-model to more accurately describe the relationship between physical examination indicators and actual age, thereby laying the foundation for more accurate age prediction in the future.
[0077] In a non-limiting embodiment, after the first prediction sub-model is obtained by fitting, the first prediction sub-model may be verified and its parameters may be adjusted.
[0078] Specifically, obtain the second physical examination indicators of the second user in the insurance data and / or medical data; select the second indicator data related to the organ type corresponding to the first prediction sub-model in the second physical examination indicators; and use the second indicator data and the actual age of the second user to verify and adjust the parameters of the first prediction sub-model.
[0079] In the embodiment of the present application, the insurance data and medical treatment data of the second user are different from the first physical examination index authorized by the first user, and data can be provided from multiple dimensions to ensure the comprehensiveness of the data. Specifically, the second index data can also be obtained from literature data.
[0080] The embodiment of the present application verifies and adjusts the first prediction sub-model through a second physical examination indicator that is different from the source of the first physical examination indicator. By obtaining more comprehensive physical examination indicators through multiple channels, it can ensure that the first prediction sub-model covers a wider range of users, improve the scope of application of the first prediction sub-model, and at the same time improve the accuracy of the first prediction sub-model.
[0081] Specifically, adjusting the parameters of the first prediction sub-model may be adjusting hyperparameters such as bias and variance in the first prediction sub-model.
[0082] Accordingly, the embodiment of the present application can construct a second prediction sub-model in the following manner: obtain the third physical examination indicators of each third user within the classification age group corresponding to the second prediction sub-model as the second training data; fit the second training data with the actual age of the third user to obtain the second prediction sub-model.
[0083] Different from the first physical examination index in the aforementioned embodiment, the third physical examination index in the embodiment of the present application includes indexes for various organs and can cover more types of data. For example, the third physical examination index may include all indexes related to the heart, kidneys, immune system, blood vessels, body systems, metabolic system and joints.
[0084] Furthermore, the second prediction sub-model may be verified and adjusted in accordance with the aforementioned method of verifying and adjusting the first prediction sub-model.
[0085] Specifically, obtain the fourth physical examination indicator of the fourth user in the insurance data and / or medical treatment data; and use the fourth indicator data and the actual age of the fourth user to verify and adjust the parameters of the second prediction sub-model.
[0086] Specifically, adjusting the parameters of the second prediction sub-model may be adjusting hyperparameters such as bias and variance in the second prediction sub-model.
[0087] It should be noted that the method of adjusting the parameters of the first prediction sub-model and the second prediction sub-model can adopt any feasible algorithm, such as grid / random search and Bayesian optimization, and this application does not impose any restrictions on this.
[0088] For more specific implementation methods of the embodiments of the present application, please refer to the aforementioned embodiments, which will not be repeated here.
[0089] Please refer to Figure 4 , Figure 4 A physiological age prediction device 40 is shown, and the physiological age prediction device 40 may include:
[0090] The acquisition module 401 is used to acquire the physical examination information and / or diagnosis and treatment information input by the user, where the physical examination information and / or diagnosis and treatment information includes the actual age and physical examination index of the user;
[0091] Prediction module 402, used to input the physical examination index into the prediction model corresponding to the actual age of the user to obtain the predicted age, the prediction model includes multiple first prediction sub-models and second prediction sub-models, each first prediction sub-model is used to predict the physiological age of the corresponding type of organ, and the second prediction sub-model is used to predict the comprehensive age of the user, and the predicted age includes the physiological age of each organ and the comprehensive age;
[0092] The output module 403 is used to output the predicted age.
[0093] In a specific implementation, the above-mentioned physiological age prediction device 40 can correspond to a chip with a physiological age prediction function in a terminal device, such as a system-on-a-chip (SOC), a baseband chip, etc.; or correspond to a chip module with a physiological age prediction function in a terminal device; or correspond to a chip module with a data processing function chip, or correspond to a terminal device.
[0094] In a specific embodiment, the prediction module 402 inputs the physical examination index into a prediction model corresponding to a data combination, where the data combination includes the actual age and gender of the user.
[0095] Specifically, the prediction module 402 determines the first classification age group into which the actual age of the user in the data combination falls; and inputs the physical examination indicators into a prediction model corresponding to the first classification age group and the gender of the user.
[0096] For other related descriptions about the physiological age prediction device 40 , reference may be made to the related descriptions in the aforementioned embodiments, which will not be repeated here.
[0097] Regarding the various modules / units included in the various devices and products described in the above embodiments, they can be software modules / units, or hardware modules / units, or they can be partially software modules / units and partially hardware modules / units. For example, for various devices and products applied to or integrated in a chip, the various modules / units included therein can all be implemented in the form of hardware such as circuits, or at least some of the modules / units can be implemented in the form of software programs, which run on a processor integrated inside the chip, and the remaining (if any) modules / units can be implemented in the form of hardware such as circuits; for various devices and products applied to or integrated in a chip module, the various modules / units included therein can all be implemented in the form of hardware such as circuits, and different modules / units can be located in the same component of the chip module (such as a chip, circuit module, etc.) or in different components, or at least some of the modules / units can be implemented in the form of software programs. It is implemented in the form of a software program, which runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal equipment, or, at least some modules / units can be implemented in the form of a software program, which runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.
[0098] The embodiment of the present application also discloses a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is run, the steps of the method shown in the above embodiment can be executed. The storage medium may include a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. The storage medium may also include a non-volatile memory (non-volatile) or a non-transitory memory, etc.
[0099] Please refer to Figure 5 The embodiment of the present application also provides a hardware structure diagram of a communication device. The device includes a processor 501, a memory 502 and a transceiver 503.
[0100] Processor 501 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. Processor 501 may also include multiple CPUs, and processor 501 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, or processing cores for processing data (such as computer program instructions).
[0101] The memory 502 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, and the embodiments of the present application do not impose any restrictions on this. The memory 502 may exist independently (in this case, the memory 502 may be located outside the device or inside the device), or it may be integrated with the processor 501. Among them, the memory 502 may contain a computer program code. The processor 501 is used to execute the computer program code stored in the memory 502, thereby realizing the method provided in the embodiments of the present application.
[0102] The processor 501, the memory 502 and the transceiver 503 are connected via a bus. The transceiver 503 is used to communicate with other devices or a communication network. Optionally, the transceiver 503 may include a transmitter and a receiver. The device used to implement the receiving function in the transceiver 503 can be regarded as a receiver, and the receiver is used to perform the receiving step in the embodiment of the present application. The device used to implement the sending function in the transceiver 503 can be regarded as a transmitter, and the transmitter is used to perform the sending step in the embodiment of the present application.
[0103] when Figure 5 The schematic diagram of the structure shown is used to illustrate the structure of the terminal device involved in the above embodiment. The processor 501 is used to control and manage the actions of the terminal device. For example, the processor 501 is used to support the terminal device to execute Figure 1 Step 101, step 102 and step 103 in , or Figure 3 The processor 501 may communicate with other network entities via the transceiver 503. The memory 502 is used to store program codes and data of the terminal device.
[0104] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship.
[0105] The "plurality" appearing in the embodiments of the present application refers to two or more.
[0106] The first, second, etc. descriptions appearing in the embodiments of the present application are only used for illustration and distinction of the description objects. There is no order, nor do they indicate any special limitation on the number of devices in the embodiments of the present application, and cannot constitute any limitation on the embodiments of the present application.
[0107] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means.
[0108] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0109] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device embodiments described above are merely schematic; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0112] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the method described in each embodiment of the present application.
[0113] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application, so the protection scope of the present application shall be subject to the scope defined by the claims.
Claims
1. A method for predicting physiological age, characterized in that: include: Acquire physical examination information and / or diagnosis and treatment information input by a user, wherein the physical examination information and / or diagnosis and treatment information includes the actual age and physical examination indicators of the user; Inputting the physical examination index into a prediction model corresponding to the actual age of the user to obtain a predicted age, wherein the prediction model includes a plurality of first prediction sub-models and second prediction sub-models, each first prediction sub-model is used to predict the physiological age of an organ of a corresponding type, and the second prediction sub-model is used to predict the comprehensive age of the user, wherein the predicted age includes the physiological age of each organ and the comprehensive age; The predicted age is output.
2. The physiological age prediction method according to claim 1, characterized in that: The physical examination information and / or diagnosis and treatment information also includes gender; the inputting of the physical examination index into the prediction model corresponding to the actual age of the user includes: The physical examination indicators are input into a prediction model corresponding to a data combination, where the data combination includes the actual age and gender of the user.
3. The physiological age prediction method according to claim 2, characterized in that: Each prediction model corresponds to a gender and a classified age group, and the prediction model corresponding to the combination of the physical examination index input data includes: Determine the first classification age group into which the actual age of the user in the data combination falls; The physical examination index is input into a prediction model corresponding to the first classification age group and the gender of the user.
4. The physiological age prediction method according to claim 1, characterized in that: The first prediction sub-model is constructed in the following manner: Obtaining a first physical examination indicator of each first user within the classified age group corresponding to the first prediction sub-model; Selecting first indicator data related to the type of organ corresponding to the first prediction sub-model and the actual age of the first user in the first physical examination indicator as first training data; The first indicator data is fitted with the actual age of the first user to obtain the first prediction sub-model.
5. The physiological age prediction method according to claim 4, characterized in that: The fitting of the first training data comprises: Using multiple fitting algorithms to fit the first indicator data and the actual age of the first user to obtain multiple fitting functions; An optimal fitting function among the multiple fitting functions that is closest to the first indicator data and the actual age of the first user is selected as the first prediction sub-model.
6. The physiological age prediction method according to claim 4, characterized in that: The selecting of the first indicator data related to the organ of the type corresponding to the first prediction sub-model from the first physical examination indicator includes: Select one or more of the following indicator data related to the type of organ corresponding to the first prediction sub-model in the first physical examination indicator: median, quantile, minimum value, maximum value, standard deviation, as the first indicator data.
7. The physiological age prediction method according to claim 4, characterized in that: The first prediction sub-model is verified and adjusted in the following manner: Acquiring a second physical examination indicator of the second user in the insurance data and / or the diagnosis and treatment data; Selecting second indicator data related to the type of organ corresponding to the first prediction sub-model from the second physical examination indicator; The first prediction sub-model is verified and adjusted using the second indicator data and the actual age of the second user.
8. The physiological age prediction method according to claim 1, characterized in that: The second prediction sub-model is constructed in the following manner: Acquire a third physical examination indicator of each third user in the classified age group corresponding to the second prediction sub-model as second training data; The second training data is fitted with the actual age of the third user to obtain the second prediction sub-model.
9. The physiological age prediction method according to claim 1, characterized in that: The organ is selected from one or more of the following: heart, kidney, immune system, blood vessel, body system, metabolic system and joint.
10. A physiological age prediction device, characterized in that: include: An acquisition module, used to acquire physical examination information and / or diagnosis and treatment information input by a user, wherein the physical examination information and / or diagnosis and treatment information includes the actual age and physical examination indicators of the user; A prediction module, used for inputting the physical examination index into a prediction model corresponding to the actual age of the user to obtain a predicted age, wherein the prediction model includes a plurality of first prediction sub-models and second prediction sub-models, each of which is used to predict the physiological age of an organ of a corresponding type, and the second prediction sub-model is used to predict the comprehensive age of the user, wherein the predicted age includes the physiological age of each organ and the comprehensive age; An output module is used to output the predicted age.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the physiological age prediction method according to any one of claims 1 to 9 are performed.
12. A computing device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor runs the computer program, the processor performs the steps of the physiological age prediction method according to any one of claims 1 to 9.