Weight configuration method and device for health assessment indexes, equipment and storage medium

Abstract

The invention provides a weight configuration method and device for health assessment indexes, equipment and a storage medium, and the method comprises the steps: obtaining multiple pieces of target disease information and target indexes, and determining an exclusive index and a shared index; determining a first weight according to the highest monitoring priority based on any sharing index, determining an attenuation coefficient based on the weighting times and the monitoring priority in the remaining second weights, and determining an attenuation weight based on the second weights and the attenuation coefficient; determining the target weight of the exclusive index according to the corresponding initial weight, and determining the sum of the first weight and the attenuation weight as the target weight of the shared index; and configuring a health assessment model based on each target index and the target weight. According to the technical scheme provided by the embodiment of the invention, the exclusive index and the shared index can be automatically distinguished, each second weight is attenuated according to the weighting frequency and the monitoring priority, the numerical expansion of the target weight is inhibited, and the score expansion risk of the health assessment model is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment and storage medium for configuring weights of health assessment indicators. Background Art

[0002] At present, hospitalized patients need to set up different monitoring equipment according to their condition to continuously monitor indicators, such as heart rate, blood pressure and other indicators. They also need to periodically check some indicators according to their actual condition, such as periodic blood tests. Therefore, in the monitoring process of hospitalized patients, multiple indicators need to be tracked and monitored, and the monitoring frequency is high. If doctors or nurses are relied on to manually judge the relevant indicators, it will not only increase the workload of medical staff, but also have a certain lag.

[0003] In related technologies, there are already some health assessment models built based on artificial intelligence technology. After the patient's medical history and indicator values ​​are input into the health assessment model, they are automatically scored to determine health risks, and indicators that exceed the set threshold are warned, which can reduce the workload of medical staff to a certain extent. However, in the existing health assessment model, each indicator is weighted for different diseases. If a patient suffers from multiple diseases, it is easy to have some shared indicators that need to be monitored for various diseases. This causes the shared indicators to perform multiple calculations under multiple initial weights, resulting in a large expansion of the health score, which affects the accuracy of identifying health risks. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a weight configuration method, device, equipment, and storage medium for health assessment indicators, which can perform weight attenuation on shared indicators, reduce score inflation when multiple diseases coexist, and improve the reliability of health scores.

[0005] In a first aspect, an embodiment of the present invention provides a method for configuring weights of health assessment indicators, which is applied to a server, wherein the server is preset with a health assessment model, and the method includes: Acquire multiple target disease information and multiple target indicators of a target patient, and determine an exclusive indicator and a shared indicator from the multiple target indicators, wherein the exclusive indicator is associated with one target disease information, the shared indicator is associated with multiple target disease information, and each target indicator is preset with an initial weight for each associated target disease information; Based on any of the shared indicators, determine the monitoring priority of each of the target disease information, determine the associated target disease information as associated disease information, determine the number of associated disease information as the number of weightings, determine the initial weight of the associated disease information with the highest monitoring priority as the first weight, and determine the remaining initial weights as the second weight; Based on any of the second weights, determine an attenuation coefficient based on the weighted times and the corresponding monitoring priority, and determine an attenuation weight based on the second weight and the attenuation coefficient; The target weight of the exclusive indicator is determined by using the corresponding initial weight, and the sum of the corresponding first weight and the decay weight is determined as the target weight of the shared indicator; A health assessment model for the target patient is configured based on each of the target indicators and the corresponding target weights.

[0006] According to some embodiments of the present invention, the step of obtaining information on multiple target diseases and multiple target indicators of a target patient includes: Acquire target medical record information of the target patient, extract the target disease information from the target medical record information, and determine preset indicators of each of the target disease information, wherein each of the preset indicators is associated with at least one preset descriptive word; The target medical record information is input into a preset NLP model, the condition description words output by the NLP model are obtained, and the target indicator is determined from the plurality of preset indicators based on the condition description words.

[0007] According to some embodiments of the present invention, determining the monitoring priority of each target disease information includes: Obtaining the disease type recorded in the target disease information, determining the target disease information whose disease type represents the main diagnosis as the first disease information, determining the target disease information whose disease type represents the complication as the second disease information, and determining the target disease information whose disease type represents the previous history as the third disease information; constructing a target information group based on each of the first disease information; Based on any of the target information groups, a preset associated diagnostic relationship is obtained from the first disease information, the second disease information and / or the third disease information indicated by the associated diagnostic relationship is saved to the target information group, and the sum of the numbers of the shared indicators in the target information group is determined as an information group reference value, wherein the associated diagnostic relationship is used to indicate the second disease information and / or the third disease information associated with the first disease information; Determine the monitoring priority of each of the first disease information based on the corresponding reference values ​​of the information groups in descending order; Sorting the plurality of second disease information based on the monitoring priority of the first disease information, wherein the second disease information at the first position is arranged after the first disease information at the last position, and the order of the plurality of second disease information corresponding to the same first disease information is determined based on the number of the shared indicators corresponding to each of them; Based on the monitoring priority of the first disease information, the order of the multiple third disease information corresponding to the same first disease information is determined based on the number of the shared indicators corresponding to each of them, wherein the third disease information at the first position is arranged after the second disease information at the last position.

[0008] According to some embodiments of the present invention, the server presets a preset contribution of each target indicator to each target disease information, and after determining the attenuation weight based on the second weight and the attenuation coefficient, the method further includes: When the sharing index is recorded in the target medical record information, the preset contribution degree of each of the related disease information is determined as the related contribution degree; When the second weight corresponds to the first disease information, a preset first ratio is determined as a target ratio, wherein the first ratio is less than 1; When the second weight corresponds to the second disease information or the third disease information, and the corresponding correlation contribution is greater than the preset contribution corresponding to any of the exclusive indicators, a preset second ratio is determined as the target ratio, wherein the second ratio is less than the first ratio; A gain coefficient is determined based on the attenuation coefficient and the target ratio, and the attenuation weight is increased based on the gain coefficient.

[0009] According to some embodiments of the present invention, determining a decay coefficient based on the number of weighted assignments and the corresponding monitoring priority, and determining a decay weight based on the second weight and the decay coefficient include: Determine a target ranking of each of the second weights based on the monitoring priority of the associated disease information, wherein a starting value of the target ranking is 2; Acquire a basic value sequence, wherein the basic value sequence includes a plurality of optional attenuation values ​​arranged in order from small to large, and the optional attenuation value is greater than 1 and less than 1.5; Determine the optional attenuation value having an order value in the basic value sequence equal to the weighted number of times as a target attenuation value; Determine the attenuation coefficient by performing a power operation based on the target ranking and the target attenuation value, wherein the target ranking is a base and the target attenuation value is a power exponent; A quotient of the second weight and the attenuation coefficient is determined as the attenuation weight.

[0010] According to some embodiments of the present invention, each target disease information is associated with at least one associated indicator group, each associated indicator group includes a plurality of mutually associated target indicators, and the attenuation coefficient is determined based on the number of weighted times and the corresponding monitoring priority, including: When the shared indicator belongs to the associated indicator group in the associated disease information corresponding to the second weight, and the remaining target indicators of the associated indicator group are all the shared indicators, a preset first threshold is determined as the target threshold; When the shared indicator belongs to the associated indicator group in the associated disease information corresponding to the second weight, and the remaining target indicators of the associated indicator group are all exclusive indicators, a preset second threshold is determined as the target threshold, wherein the second threshold is less than the first threshold; When the shared indicator does not belong to any of the associated indicator groups in the associated disease information corresponding to the second weight, a preset third threshold is determined as the target threshold, wherein the third threshold is less than the second threshold; When the attenuation coefficient is less than the target threshold, the attenuation coefficient is assigned based on the target threshold.

[0011] According to some embodiments of the present invention, after configuring the health assessment model of the target patient based on each of the target indicators and the corresponding target weights, the method further includes: Obtaining target values ​​for each of the target indicators, and inputting the target values ​​into the health assessment model to obtain a first total score; When the first total score is greater than a preset upper limit of the score, based on the target disease information with the highest monitoring priority, the corresponding target indicator and the initial weight are configured into the health assessment model, and the corresponding target value is input into the health assessment model to obtain a second total score; Lowering the target weight of each of the shared indicators based on a preset step value, reconfiguring the health assessment model based on the updated target weight, and obtaining a third total score after inputting the target value; When the third total score is less than or equal to the score upper limit, and the third total score is greater than the second total score, the third total score is determined as the target score of the target patient.

[0012] In a second aspect, an embodiment of the present invention provides a device for configuring weights of health assessment indicators, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the method for configuring weights of health assessment indicators as described in the first aspect above.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a weight configuration device for health assessment indicators as described in the second aspect above.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the weight configuration method of the health assessment indicators as described in the first aspect above.

[0015] The weight configuration method of the health assessment index according to the embodiment of the present invention has at least the following beneficial effects: obtaining multiple target disease information and multiple target indicators of a target patient, determining an exclusive indicator and a shared indicator from the multiple target indicators, wherein the exclusive indicator is associated with one target disease information, the shared indicator is associated with multiple target disease information, and each target indicator is preset with an initial weight for each associated target disease information; based on any of the shared indicators, determining the monitoring priority of each of the target disease information, determining the associated target disease information as the associated disease information, determining the number of associated disease information as the number of weightings, determining the initial weight of the associated disease information with the highest monitoring priority as the first weight, and determining the remaining initial weights as the second weight; based on any of the second weights, determining an attenuation coefficient based on the number of weightings and the corresponding monitoring priority, and determining an attenuation weight based on the second weight and the attenuation coefficient; determining the target weight of the exclusive indicator based on the corresponding initial weight, and determining the sum of the corresponding first weight and the attenuation weight as the target weight of the shared indicator; configuring the health assessment model of the target patient based on each of the target indicators and the corresponding target weights. According to the technical solution of the embodiment of the present invention, it is possible to automatically distinguish between exclusive indicators and shared indicators, retain the first weight with the highest monitoring priority as the weight basis for the shared indicators, and attenuate each second weight according to the number of weightings and the monitoring priority, thereby effectively suppressing the numerical expansion of the target weight, thereby reducing the risk of score inflation in the identification process of the health assessment model, and providing a weight basis for improving the assessment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of a server provided by an embodiment of the present invention; Figure 2 is a flow chart of a method for configuring weights of health assessment indicators provided by another embodiment of the present invention; Figure 3 is a complete flow chart of a weight configuration method for health assessment indicators provided by another embodiment of the present invention; Figure 4 It is a structural diagram of a weight configuration device for health assessment indicators provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0017] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0018] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0019] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0020] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific content of the technical solution.

[0021] The embodiment of the present invention provides a weight configuration method, device, equipment, and storage medium for health assessment indicators, wherein the weight configuration method for health assessment indicators includes: obtaining multiple target disease information and multiple target indicators of a target patient, determining an exclusive indicator and a shared indicator from the multiple target indicators, wherein the exclusive indicator is associated with one target disease information, the shared indicator is associated with multiple target disease information, and each target indicator is preset with an initial weight for each associated target disease information; based on any of the shared indicators, determining the monitoring priority of each of the target disease information, determining the associated target disease information as associated disease information, determining the number of associated disease information as the number of weightings, determining the initial weight of the associated disease information with the highest monitoring priority as a first weight, and determining the remaining initial weights as a second weight; based on any of the second weights, determining an attenuation coefficient based on the number of weightings and the corresponding monitoring priority, and determining an attenuation weight based on the second weight and the attenuation coefficient; determining the target weight of the exclusive indicator based on the corresponding initial weight, and determining the sum of the corresponding first weight and the attenuation weight as the target weight of the shared indicator; configuring the health assessment model of the target patient based on each of the target indicators and the corresponding target weights. According to the technical solution of the embodiment of the present invention, it is possible to automatically distinguish between exclusive indicators and shared indicators, retain the first weight with the highest monitoring priority as the weight basis for the shared indicators, and attenuate each second weight according to the number of weightings and the monitoring priority, thereby effectively suppressing the numerical expansion of the target weight, thereby reducing the risk of score inflation in the identification process of the health assessment model, and providing a weight basis for improving the assessment accuracy.

[0022] First, refer to Figure 1 , Figure 1 This is a schematic diagram of a server provided in an embodiment of the present invention. The method of this embodiment is applied to the server, and the server is preset with a health assessment model.

[0023] It should be noted that the application scenario of this embodiment is the inpatient scenario. Since the indicator monitoring of inpatients will continue for a period of time, this embodiment generates a data-independent target container 11 for each inpatient in the server 10, and puts the preset health assessment model into the target container 11 corresponding to each inpatient. After obtaining each target indicator and target weight based on the steps of the subsequent embodiments, the model is configured in the corresponding target container 11, so as to obtain a health assessment model configured for each inpatient according to his own situation. By utilizing the data isolation characteristics of container technology, the data of different inpatients will not interfere with each other, thereby ensuring that the personalized health assessment model can perform accurate health assessments based on the data of the corresponding inpatients.

[0024] The following is based on the Figure 1 The server shown further illustrates the technical solution of the embodiment of the present invention.

[0025] Reference Figure 2 , Figure 2 A flowchart of a method for configuring the weights of health assessment indicators provided by an embodiment of the present invention, the method for configuring the weights of health assessment indicators includes but is not limited to the following steps: S10, obtaining multiple target disease information and multiple target indicators of a target patient, and determining an exclusive indicator and a shared indicator from the multiple target indicators, wherein the exclusive indicator is associated with one target disease information, the shared indicator is associated with multiple target disease information, and each target indicator is preset with an initial weight for each associated target disease information; S20, based on any shared indicator, determining the monitoring priority of each target disease information, determining the associated target disease information as the associated disease information, determining the number of associated disease information as the number of weightings, determining the initial weight of the associated disease information with the highest monitoring priority as the first weight, and determining the remaining initial weights as the second weight; S30, determining an attenuation coefficient based on any second weight, based on the number of weighted assignments and the corresponding monitoring priority, and determining an attenuation weight based on the second weight and the attenuation coefficient; S40, determining the target weight of the exclusive indicator by using the corresponding initial weight, and determining the sum of the corresponding first weight and the decay weight as the target weight of the shared indicator; S50, configuring a health assessment model for the target patient based on each target indicator and the corresponding target weight.

[0026] It should be noted that in this embodiment, various preset disease information and corresponding preset indicators can be pre-set in the server. After constructing the target container corresponding to the target patient, the inpatient usually completes the relevant diagnosis when admitted to the hospital. Therefore, the target medical record information of the target patient can be obtained from the server, and the preset disease information recorded in the target medical record information is determined as the target disease information, and the preset indicator corresponding to the target disease information is determined as the target indicator, thereby realizing the rapid construction of the indicator pool. At the same time, each preset indicator has different weights to be considered in different diseases. In this embodiment, the initial weights in various preset disease information can be configured in advance in the server for each target indicator.

[0027] It is worth noting that the preset disease information and target disease information can be various diseases that have been diagnosed, such as diabetes, hypertension, and respiratory diseases, etc. The preset indicators and target indicators are indicators that need to be monitored in hospitalized scenarios for various diseases, such as blood pressure, blood sugar, various indicators of blood routine tests, medical images, etc. This embodiment does not involve the diagnosis of target disease information, but directly obtains relevant information formed by the diagnosis from the server, such as Figure 1 As shown, the target disease information including disease A, disease B and disease C that have been diagnosed for the target patient can be directly obtained in the server 10 without diagnosing disease A, disease B and disease C through a health assessment model, which will not be repeated later.

[0028] For example, Figure 1 As shown, the preset disease information pre-configured in the server 10 includes disease A, disease B and disease C. The preset indicators configured for disease A include indicator A and indicator B, the preset indicators configured for disease B include indicator A and indicator C, and the preset indicators configured for disease C include indicator A. Indicator A is configured in multiple preset disease information and belongs to the shared indicator of this embodiment. For example, indicator A can be a urine routine indicator, which is relevant in diabetes, kidney disease, and excretory system diseases. This embodiment does not limit the specific indicator type. The initial weight of indicator A corresponding to disease A is A1, and the initial weight corresponding to disease B is A2. The values ​​of A1 and A2 can be equal or unequal, and the remaining initial weights are similar, which will not be repeated here.

[0029] It should be noted that, in this embodiment, target indicators associated with multiple target disease information are determined as shared indicators, for example Figure 1 Indicator A associated with disease A, disease B, and disease C shown in FIG, determines the target indicator associated with only one target disease information as an exclusive indicator, for example Figure 1 Indicator B and indicator C are shown in . Since exclusive indicators do not have the possibility of score inflation due to multiple calculations, this embodiment directly determines the initial weight of the exclusive indicator as the target weight. This embodiment does not adjust the weight of the exclusive indicator, but only performs attenuation adjustment on the initial weight of the shared indicator.

[0030] It should be noted that the monitoring priority of this embodiment can be pre-set according to the actual situation of the target patient, and multiple target disease information can be sorted according to the monitoring priority. The monitoring priority can be the common high, medium, and low, or one target disease information is set as a major diagnosis disease, and the other target disease information is a complication or a previous history. The monitoring priority of the major diagnosis disease is higher than that of the complication and the previous history. This embodiment does not limit the specific form of the monitoring priority.

[0031] It should be noted that after the shared indicators are determined, this embodiment independently performs weight calculation for each shared indicator, and the principle is described below using one shared indicator.

[0032] It should be noted that after determining the monitoring priority, this embodiment further determines the target disease information corresponding to the shared indicator as the associated disease information, and determines the number of associated disease information as the number of weightings. In a scenario where multiple diseases coexist, each associated disease information will carry a shared indicator, and the health assessment model will perform an assessment calculation based on the shared indicator, so the number of weightings can represent the number of times the shared indicator is calculated.

[0033] It should be noted that the shared indicator corresponds to multiple diseases. This embodiment uses coefficients to perform proportional attenuation when performing weight attenuation. If the value of the initial weight is large, the value will decrease more during proportional attenuation. If the initial weight corresponding to the associated disease information with the highest monitoring priority is large, and all initial weights are attenuated, it is very likely that the target weight obtained by subsequent summation will be smaller than the initial weight with the highest monitoring priority. Therefore, this embodiment uses the initial weight of the associated disease information with the highest monitoring priority as the first weight, does not attenuate the first weight, but retains the original value to ensure that the target weight is at least greater than the first weight with the highest monitoring priority, so as to avoid excessive weight attenuation of the shared indicator during model calculation and cause distortion of the score.

[0034] For example, Figure 1 As shown, Figure 1 Taking indicator A in as an example, indicator A is associated with disease A, disease B and disease C, so it is determined as a shared indicator. The main diagnosis, complications and past history are used as representations of monitoring priority. Disease A as the main diagnosis has the highest monitoring priority, and the corresponding initial weight A1 is the first weight. Disease B corresponds to A2 of indicator A as the second weight, and disease C corresponds to A3 of indicator A as the second weight. The monitoring priority of A2 is higher than that of A3, and the number of weightings is 3.

[0035] It should be noted that, for the second weight, this embodiment gives the number of weightings and the monitoring priority to determine the attenuation coefficient, so that multiple attenuation coefficients are shared based on the number of weightings, and gradually decrease in the order of monitoring priority. The attenuation weight is determined by the product of the attenuation coefficient and the second weight, so that the shared indicator is changed from multiple initial weights to a first weight and multiple progressively attenuated second weights. The target weight is obtained by summing the first weight and the multiple attenuation weights. The target weight must be less than the sum of all initial weights. Therefore, the shared indicators reused for multiple diseases can be weighted attenuated, effectively suppressing score inflation.

[0036] Exemplarily, continuing to refer to the examples of the above-mentioned indicators A1, A2 and A3, A1 retains its original value unchanged, and the second weights A2 and A3 determine the attenuation coefficient according to the number of weightings and the monitoring priority, respectively. The number of weightings corresponding to A2 and A3 are the same, and the monitoring priority of A2 is higher than that of A3. Therefore, the attenuation coefficient W1 corresponding to A2 is smaller than the attenuation coefficient W2 corresponding to A3, that is, the attenuation amplitude of A2 is smaller than that of A3. The final calculated target weight of indicator A is A0=A1+(A2xW1)+(A3xW2).

[0037] It should be noted that this embodiment does not involve improvements to the health assessment model and can adopt an artificial intelligence model in the prior art. This embodiment only involves the weight configuration of different indicators in the health assessment model. After completing the configuration of the target indicators and the corresponding target weights, after inputting various indicator data obtained by monitoring or detecting the target patient, the health assessment model can predict the health score through machine learning. The specific model principles will not be elaborated here.

[0038] In addition, in one embodiment, referring to Figure 3 In step S10, multiple target disease information and multiple target indicators of the target patient are obtained, which specifically includes but is not limited to the following steps: S11, obtaining target medical record information of a target patient, extracting target disease information from the target medical record information, and determining preset indicators of each target disease information, wherein each preset indicator is associated with at least one preset descriptive word; S12, inputting the target medical record information into a preset NLP model, obtaining the condition description words output by the NLP model, and determining the target indicator from a plurality of preset indicators based on the condition description words.

[0039] It should be noted that the medical records of hospitalized patients usually record the preliminary diagnosis results before admission. In this embodiment, the medical record information uploaded to the server when admitted to the hospital is determined as the target medical record information. The target medical record information is usually described in professional terms, so the target disease information can be extracted through simple text recognition.

[0040] It should be noted that although the present embodiment configures preset indicators for each preset disease information on the server, the condition of each patient is different, and it is not necessarily necessary to monitor all predictive indicators. In order to improve the accuracy of health assessment, the present embodiment associates at least one preset descriptor with each preset indicator, describes the preset indicator in the context of the preset disease information through the preset descriptor, uses the NLP model to identify the condition descriptor recorded in the target medical record information, and uses the pairing of the condition descriptor and the preset descriptor to accurately identify the target indicator, thereby reducing unnecessary indicator calculations.

[0041] For example, the preset descriptor recorded in indicator A corresponding to disease A is "symptom A exists", the preset descriptor recorded in indicator B is "symptom B lasts for a period of time", and the target medical record information records "the patient suffers from symptoms A and C, but not B". The condition descriptors output by the NLP model can be "symptom A exists" and "symptom C exists", thereby determining indicator A as the target indicator. This embodiment does not involve the improvement of the NLP model, and it is sufficient to achieve relevant semantic recognition.

[0042] In addition, in one embodiment, referring to Figure 3 In step S20, the monitoring priority of each target disease information is determined, which specifically includes but is not limited to the following steps: S21, obtaining the disease type recorded in the target disease information, determining the target disease information whose disease type represents the main diagnosis as the first disease information, determining the target disease information whose disease type represents the complication as the second disease information, and determining the target disease information whose disease type represents the past history as the third disease information; S22, constructing a target information group based on each first disease information; S23, based on any target information group, obtaining a preset associated diagnosis relationship from the first disease information, saving the second disease information and / or the third disease information indicated by the associated diagnosis relationship to the target information group, and determining the sum of the number of shared indicators in the target information group as the information group reference value, wherein the associated diagnosis relationship is used to indicate the second disease information and / or the third disease information associated with the first disease information; S24, determining the monitoring priority of each first disease information based on the corresponding information group reference value in descending order; S25, sorting the plurality of second disease information based on the monitoring priority of the first disease information, wherein the second disease information at the first position is sorted after the first disease information at the last position, and the order of the plurality of second disease information corresponding to the same first disease information is determined based on the number of shared indicators corresponding to each of them; S26, based on the monitoring priority of the first disease information, multiple third disease information are monitored, wherein the third disease information at the first position is arranged after the second disease information at the last position, and the order of the multiple third disease information corresponding to the same first disease information is determined based on the number of shared indicators corresponding to each of them.

[0043] It should be noted that in the inpatient monitoring scenario, the diseases that need to be monitored based on indicators include not only the main diagnosed diseases this time, but also the complications that may be caused by the diagnosed diseases. The target patient's medical history also needs to be considered. Therefore, this embodiment records the disease type in the target disease information. There are three preset disease types, namely main diagnosis, complications and past history. The disease type can be determined based on the target medical record information. Each type of disease has many complications. The target disease information of the main diagnosis this time can be recorded in the target medical record information, and the complications that need to be prevented and the past history of the target patient can be recorded by associating the diagnosis information. The disease type in this embodiment can be extracted from the target medical record information without the need for further diagnosis. This embodiment does not involve the diagnosis of disease types, but only the extraction of information.

[0044] It should be noted that after determining the disease type, it is divided into first disease information, second disease information and third disease information based on different disease types. The first disease information is the target disease information with the highest monitoring priority, and each first disease information should occupy a larger weight in health assessment. This embodiment constructs a target information group based on each first disease information, and saves the second disease information and the third disease information associated with the first disease information into the same target information group. The target information group is used to associate and group coexisting multiple diseases, thereby providing an information basis for determining monitoring priorities.

[0045] Exemplarily, the first disease information of the target patient includes diabetes and influenza, the second disease information includes hypertension and pneumonia, and the third disease information includes kidney stones. The first information group is constructed based on diabetes, and the second information group is constructed based on influenza. Hypertension is recorded as a complication of diabetes in the associated diagnostic information, and the target patient has suffered from kidney stones caused by diabetes. Therefore, hypertension in the second disease information and kidney stones in the third disease information are placed in the first information group, and similarly, pneumonia is placed in the second information group.

[0046] It should be noted that the monitoring priority of this embodiment is used to determine the first weight of the shared indicator. The shared indicator can be associated with multiple first disease information. Therefore, it is necessary to ensure that the monitoring priority of the first disease information used to determine the first weight is the highest. When there are multiple first disease information, this embodiment uses the sum of the number of shared indicators of each target information group as the information group reference value. The higher the information group reference value, the more shared indicators correspond to the first disease information in the group, and the higher the monitoring priority of the first disease information. This embodiment sorts the first disease information based on the information group reference value from high to low.

[0047] It should be noted that, when determining the monitoring priority, this embodiment first sorts the first disease information, then sorts the second disease information, and finally sorts the third disease information. When determining the monitoring priority of multiple second disease information, since the second disease information is a complication of the first disease information, the higher the monitoring priority of the first disease information, the higher the corresponding monitoring priority of the second disease information. This embodiment uses the monitoring priority of the first disease information as the basis for sorting the second disease information. If multiple second disease information corresponds to the same first disease information, they can be sorted according to the number of corresponding shared indicators. The same is true for the third disease information, which will not be elaborated here.

[0048] Exemplarily, continuing to refer to the above-mentioned examples of the first information group and the second information group, taking the example that the information group reference value of the first information group is greater than that of the second information group, the monitoring priority of diabetes is 1, and the monitoring priority of influenza is 2. When determining the order of the second disease information, due to the higher monitoring priority of diabetes, it can be determined that the monitoring priority of hypertension is 3, and the monitoring priority of pneumonia is 4. Similarly, the monitoring priority of kidney stones is 5.

[0049] In addition, in one embodiment, the server presets a preset contribution degree of each target indicator to each target disease information, referring to Figure 3 In step S30, after the attenuation weight is determined based on the second weight and the attenuation coefficient, the following steps are also included but not limited to: S311, when the sharing index is recorded in the target medical record information, the preset contribution degree of each associated disease information is determined as the associated contribution degree; S312, when the second weight corresponds to the first disease information, determining a preset first ratio as a target ratio, wherein the first ratio is less than 1; S313, when the second weight corresponds to the second disease information or the third disease information, and the corresponding correlation contribution is greater than the preset contribution corresponding to any exclusive indicator, determining the preset second ratio as the target ratio, wherein the second ratio is less than the first ratio; S314, determining a gain coefficient based on the attenuation coefficient and the target ratio, and increasing the attenuation weight based on the gain coefficient.

[0050] It should be noted that when a shared indicator is recorded in the target medical record information, it can be determined that the shared indicator is more important in the health assessment. This embodiment reduces the expansion of the score through weight attenuation, but for indicators that need to be focused on, the degree of attenuation also needs to be reduced to ensure that the shared indicator can still contribute more scores in the health assessment model.

[0051] It should be noted that the server may record the preset contribution of each target indicator to the target disease information. For example, the preset contribution of blood pressure indicators to heart disease is greater than the preset contribution of blood routine. The specific preset contribution can be set according to actual needs. The higher the preset contribution, the higher the weight of the corresponding target indicator in the evaluation process of the corresponding target disease information. Of course, if the shared indicator corresponds to multiple target disease information, a preset contribution can be set for each target disease information.

[0052] It should be noted that when the shared indicator is weighted attenuated, if it is recorded in the target medical record information, the preset contribution of each associated disease information is first determined as the associated contribution. According to the description of the above embodiment, the first disease information is the main diagnosed disease, so the weight ratio should be relatively high, and the second disease information and the third disease information are associated diseases, and a certain degree of weight suppression should be maintained. Therefore, if the second weight corresponds to the first disease information, the first ratio with a larger value is directly used as the target ratio. If the second weight corresponds to the second disease information or the third disease information, and the associated contribution is greater than any exclusive indicator, it can be determined that the shared indicator has a higher contribution in the second disease information corresponding to the second weight, thereby triggering an increase in the attenuation weight, but it is necessary to ensure that the increase is less than the second weight corresponding to the first disease information, so the second ratio is used as the target ratio, and ensure that the second ratio is less than the first ratio.

[0053] It should be noted that after determining the target ratio, the product of the attenuation coefficient and the target ratio is determined as the gain coefficient, and then the attenuation weight is adjusted upward. For example, if the attenuation coefficient is 0.5, the target ratio is the first ratio, and the value is 0.1, then the gain coefficient is 0.05, and the attenuation weight is adjusted upward to 1.05 times the original.

[0054] In addition, in one embodiment, referring to Figure 3 In step S30, the attenuation coefficient is determined based on the number of weighted times and the corresponding monitoring priority, and the attenuation weight is determined based on the second weight and the attenuation coefficient, specifically including but not limited to the following steps: S321, determining the target ranking of each second weight based on the monitoring priority of the associated disease information, wherein the starting value of the target ranking is 2; S322, obtaining a basic value sequence, wherein the basic value sequence includes a plurality of optional attenuation values ​​arranged in ascending order, and the optional attenuation value is greater than 1 and less than 1.5; S323, determining the optional attenuation value whose order value in the basic value sequence is equal to the number of weighting times as the target attenuation value; S324, performing a power operation based on the target ranking and the target attenuation value to determine the attenuation coefficient, wherein the target ranking is the base and the target attenuation value is the power exponent; S325: Determine the quotient of the second weight and the attenuation coefficient as the attenuation weight.

[0055] It should be noted that when determining the attenuation weight, the second weight is the weight of the shared indicator in a target disease information. The number of weightings corresponding to multiple second weights of the same shared indicator is the same. The only difference parameter of the multiple second weights is the monitoring priority, and the number of weightings corresponding to different shared indicators is different. Therefore, this embodiment constructs a basic value sequence, determines the target attenuation value in the basic value sequence by the number of weightings, and applies the target attenuation value to multiple second weights of the same shared indicator as the calculation base of the attenuation coefficient. For example, the basic value sequence takes {1.2, 1.25, 1.3, 1.35} as an example. When the number of weightings is 3, the third optional attenuation value 1.3 is selected from the basic value sequence as the target attenuation value.

[0056] It should be noted that in the same shared indicator, the first weight must be ranked first. Therefore, when sorting multiple second weights, the target ranking of the second weight ranked first is 2. The target ranking is used as the difference parameter of the attenuation coefficient of the same shared indicator, so that different attenuation coefficients are calculated under the same target attenuation value, and the later the ranking, the larger the attenuation coefficient.

[0057] It is worth noting that the larger the attenuation coefficient, the greater the attenuation degree of the second weight, and the smaller the obtained attenuation weight, that is, the attenuation coefficient is inversely proportional to the attenuation weight, and the attenuation weight is proportional to the second weight. The calculation formula of this embodiment is as follows: ,in, is the decay weight, represents the i-th attenuation weight, is the second weight, represents the i-th second weight, n is the number of weightings, and β is the target attenuation value.

[0058] In addition, in one embodiment, referring to Figure 3 Each target disease information is associated with at least one associated indicator group, and each associated indicator group includes a plurality of interrelated target indicators. In step S30, the attenuation coefficient is determined based on the number of weighted times and the corresponding monitoring priority, including but not limited to the following steps: S331, when the shared indicator belongs to the associated indicator group in the associated disease information corresponding to the second weight, and the remaining target indicators of the associated indicator group are all shared indicators, the preset first threshold is determined as the target threshold; S332, when the shared indicator belongs to the associated indicator group in the associated disease information corresponding to the second weight, and the remaining target indicators of the associated indicator group are all exclusive indicators, a preset second threshold is determined as the target threshold, wherein the second threshold is less than the first threshold; S333, when the shared indicator does not belong to any associated indicator group in the associated disease information corresponding to the second weight, determining a preset third threshold as a target threshold, wherein the third threshold is less than the second threshold; S334: When the attenuation coefficient is less than the target threshold, the attenuation coefficient is assigned based on the target threshold.

[0059] It should be noted that in this embodiment, multiple target indicators that are related to each other are recorded through associated indicator groups. For example, there are multiple blood indicators in a routine blood test, and these blood indicators have a strong correlation. Each target indicator corresponding to the routine blood test can be set to an associated indicator group. For example, there is a certain correlation between liver indicators and kidney indicators, and they can also be set in the same associated indicator group.

[0060] It should be noted that if the associated disease information corresponding to the second weight belongs to the associated indicator group, and the target indicators of the entire associated indicator group are shared indicators, it can be determined that the target indicators in the associated indicator group are more important, and due to the existence of correlation, the weight of one shared indicator cannot be attenuated more, and the weight of another shared indicator cannot be attenuated less. This will cause multiple target indicators with correlation to lose correlation due to large weight deviations during model calculation. Even if the shared indicator does not belong to the associated indicator group, if there is a lot of associated target disease information, it may also cause the attenuation weights ranked later to be excessively attenuated. Therefore, this embodiment sets a lower limit value for the attenuation weight by setting the first threshold, the second threshold, and the third threshold whose values ​​are arranged from large to small, to ensure that the attenuation weight obtained after attenuation can still contribute to the score for the corresponding shared indicator in the health assessment model, thereby ensuring that the score will not be excessively suppressed while suppressing score inflation.

[0061] It should be noted that if the associated indicator group in which the shared indicator is located is all shared indicators, the first threshold with the largest value is used as the target threshold, so that the attenuation weight stops at the larger first threshold, ensuring that the second weights of multiple shared indicators with strong correlation can converge, thereby enhancing the correlation in the evaluation calculation.

[0062] It should be noted that if the remaining target indicators in the associated indicator group are exclusive indicators, the other target indicators in the associated indicator group will not experience weight decay, so the second weight can be decayed to a certain extent, and the second threshold whose value is less than the first threshold is used as the target threshold.

[0063] It should be noted that if the shared indicator does not correspond to any associated indicator group, the shared indicator is a target indicator that is judged independently, and can be attenuated to a greater extent to avoid score inflation. The third threshold with the smallest value can be used as the target threshold.

[0064] In addition, in one embodiment, referring to Figure 3 After executing step S50, the following steps are also included but not limited to: S51, obtaining target values ​​of each target indicator, and inputting the target values ​​into a health assessment model to obtain a first total score; S52, when the first total score is greater than the preset upper limit of the score, based on the target disease information with the highest monitoring priority, the corresponding target indicator and the initial weight are configured into a health assessment model, and the corresponding target value is input into the health assessment model to obtain a second total score; S53, lowering the target weight of each shared indicator based on a preset step value, reconfiguring the health assessment model based on the updated target weight, and obtaining a third total score after inputting the target value; S54: When the third total score is less than or equal to the score upper limit and the third total score is greater than the second total score, the third total score is determined as the target score of the target patient.

[0065] It should be noted that after determining the target weights of each target indicator and configuring the health assessment model, although the score expansion can be suppressed to a certain extent by weight attenuation, the number of shared indicators of different target patients is different, and the effect of weight suppression is also different. In this embodiment, the first total score output by the health assessment model is first obtained. If the first total score exceeds the upper limit of the score, the effect of weight suppression is insufficient. Of course, if the scores of some target indicators are negative after calculation, the first total score may be too low if the weight is too large, but when the first total score is low, an early warning is usually issued, and manual judgment is made through the intervention of medical staff to ensure the reliability of the health assessment. Therefore, this embodiment does not need to set a lower limit for the score, only an upper limit for the score is set. When the first total score exceeds the upper limit of the score, it is determined that the weight suppression is insufficient and further adjustment is required.

[0066] It should be noted that in step S52, this embodiment configures the health assessment model with the target indicators and initial weights of the target disease information with the highest monitoring priority, and calculates the second total score. The second total score obtained by the single disease information with the highest priority can be used as the reference score before weighting. After incorporating the shared indicators, the calculated score must be greater than the second total score.

[0067] It should be noted that, in this embodiment, the target weights of each shared indicator are numerically lowered with the same step value, and the third total score is calculated using the updated health assessment model. If the third total score is between the upper limit value of the score and the second total score, the third total score is preliminarily determined to be the available score obtained after successfully suppressing expansion, and it can be determined as the target score.

[0068] like Figure 4 As shown, Figure 4The present invention also provides a device for configuring the weight of health assessment indicators, including: The processor 401 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other applications. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the weight configuration method of the health assessment index of the embodiment of this application; Input / output interface 403, used to implement information input and output; Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.); A bus 405 that transmits information between various components of the device (e.g., processor 401, memory 402, input / output interface 403, and communication interface 404); The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0069] An embodiment of the present application also provides an electronic device, including the weight configuration device for the health assessment index as described above.

[0070] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by a processor, the weight configuration method of the above-mentioned health assessment indicators is implemented.

[0071] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are implemented to be located in one place, or may also be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0072] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0073] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions under the shared conditions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for weighting health assessment indicators, characterized in that: Applied to a server, the server being preset with a health assessment model, the method comprising: Acquire multiple target disease information and multiple target indicators of a target patient, and determine an exclusive indicator and a shared indicator from the multiple target indicators, wherein the exclusive indicator is associated with one target disease information, the shared indicator is associated with multiple target disease information, and each target indicator is preset with an initial weight for each associated target disease information; Based on any of the shared indicators, determine the monitoring priority of each of the target disease information, determine the associated target disease information as associated disease information, determine the number of associated disease information as the number of weightings, determine the initial weight of the associated disease information with the highest monitoring priority as the first weight, and determine the remaining initial weights as the second weight; Based on any of the second weights, determine an attenuation coefficient based on the weighted times and the corresponding monitoring priority, and determine an attenuation weight based on the second weight and the attenuation coefficient; The target weight of the exclusive indicator is determined by using the corresponding initial weight, and the sum of the corresponding first weight and the decay weight is determined as the target weight of the shared indicator; A health assessment model for the target patient is configured based on each of the target indicators and the corresponding target weights.

2. The weight configuration method of health assessment indicators according to claim 1, characterized in that: The step of obtaining information on multiple target diseases and multiple target indicators of a target patient includes: Acquire target medical record information of the target patient, extract the target disease information from the target medical record information, and determine preset indicators of each of the target disease information, wherein each of the preset indicators is associated with at least one preset descriptive word; The target medical record information is input into a preset NLP model, the condition description words output by the NLP model are obtained, and the target indicator is determined from the plurality of preset indicators based on the condition description words.

3. The weight configuration method of health assessment indicators according to claim 2, characterized in that: Determine the monitoring priorities for each target disease information, including: Obtaining the disease type recorded in the target disease information, determining the target disease information whose disease type represents the main diagnosis as the first disease information, determining the target disease information whose disease type represents the complication as the second disease information, and determining the target disease information whose disease type represents the previous history as the third disease information; constructing a target information group based on each of the first disease information; Based on any of the target information groups, a preset associated diagnostic relationship is obtained from the first disease information, the second disease information and / or the third disease information indicated by the associated diagnostic relationship is saved to the target information group, and the sum of the numbers of the shared indicators in the target information group is determined as an information group reference value, wherein the associated diagnostic relationship is used to indicate the second disease information and / or the third disease information associated with the first disease information; Determine the monitoring priority of each of the first disease information based on the corresponding reference values ​​of the information groups in descending order; Sorting the plurality of second disease information based on the monitoring priority of the first disease information, wherein the second disease information at the first position is arranged after the first disease information at the last position, and the order of the plurality of second disease information corresponding to the same first disease information is determined based on the number of the shared indicators corresponding to each of them; Based on the monitoring priority of the first disease information, the order of the multiple third disease information corresponding to the same first disease information is determined based on the number of the shared indicators corresponding to each of them, wherein the third disease information at the first position is arranged after the second disease information at the last position.

4. The weight configuration method of health assessment indicators according to claim 3 is characterized in that: The server is preset with a preset contribution of each target indicator to each target disease information. After determining the attenuation weight based on the second weight and the attenuation coefficient, the method further includes: When the sharing index is recorded in the target medical record information, the preset contribution degree of each of the related disease information is determined as the related contribution degree; When the second weight corresponds to the first disease information, a preset first ratio is determined as a target ratio, wherein the first ratio is less than 1; When the second weight corresponds to the second disease information or the third disease information, and the corresponding associated contribution is greater than the preset contribution corresponding to any of the exclusive indicators, a preset second ratio is determined as the target ratio, wherein the second ratio is less than the first ratio; A gain coefficient is determined based on the attenuation coefficient and the target ratio, and the attenuation weight is increased based on the gain coefficient.

5. The weight configuration method of health assessment indicators according to claim 1, characterized in that: Determining a decay coefficient based on the number of weighted assignments and the corresponding monitoring priority, and determining a decay weight based on the second weight and the decay coefficient, includes: Determine a target ranking of each of the second weights based on the monitoring priority of the associated disease information, wherein a starting value of the target ranking is 2; Acquire a basic value sequence, wherein the basic value sequence includes a plurality of optional attenuation values ​​arranged in order from small to large, and the optional attenuation value is greater than 1 and less than 1.5; Determine the optional attenuation value having an order value in the basic value sequence equal to the weighted number of times as a target attenuation value; Determine the attenuation coefficient by performing a power operation based on the target ranking and the target attenuation value, wherein the target ranking is a base and the target attenuation value is a power exponent; A quotient of the second weight and the attenuation coefficient is determined as the attenuation weight.

6. The weight configuration method of health assessment indicators according to claim 5, characterized in that: Each target disease information is associated with at least one associated indicator group, each associated indicator group includes a plurality of mutually associated target indicators, and an attenuation coefficient is determined based on the number of weighted times and the corresponding monitoring priority, including: When the shared indicator belongs to the associated indicator group in the associated disease information corresponding to the second weight, and the remaining target indicators of the associated indicator group are all the shared indicators, a preset first threshold is determined as the target threshold; When the shared indicator belongs to the associated indicator group in the associated disease information corresponding to the second weight, and the remaining target indicators of the associated indicator group are all exclusive indicators, a preset second threshold is determined as the target threshold, wherein the second threshold is less than the first threshold; When the shared indicator does not belong to any of the associated indicator groups in the associated disease information corresponding to the second weight, a preset third threshold is determined as the target threshold, wherein the third threshold is less than the second threshold; When the attenuation coefficient is less than the target threshold, the attenuation coefficient is assigned based on the target threshold.

7. The weight configuration method of health assessment indicators according to claim 1, characterized in that: After configuring the health assessment model of the target patient based on each of the target indicators and the corresponding target weights, the method further includes: Obtaining target values ​​for each of the target indicators, and inputting the target values ​​into the health assessment model to obtain a first total score; When the first total score is greater than a preset upper limit of the score, based on the target disease information with the highest monitoring priority, the corresponding target indicator and the initial weight are configured into the health assessment model, and the corresponding target value is input into the health assessment model to obtain a second total score; Lowering the target weight of each of the shared indicators based on a preset step value, reconfiguring the health assessment model based on the updated target weight, and obtaining a third total score after inputting the target value; When the third total score is less than or equal to the score upper limit, and the third total score is greater than the second total score, the third total score is determined as the target score of the target patient.

8. A device for configuring weights of health assessment indicators, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the weight configuration method of the health assessment indicator as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: A weight configuration device comprising the health assessment index as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the weight configuration method for health assessment indicators as described in any one of claims 1 to 7.

Images