Medical care and physical examination data protection method and system

Abstract

The present invention relates to the technical field of medical care informatics, and particularly to a medical care physical examination data protection method and system. Medical care physical examination data having blood glucose curves of several monitored subjects is obtained, and fluctuation analysis is performed on each blood glucose curve to determine several initial key blood glucose values ​​corresponding to each blood glucose curve. The importance of the several initial key blood glucose values ​​corresponding to each blood glucose curve is analyzed to determine the final target key blood glucose value corresponding to each blood glucose curve. The final target key blood glucose value is determined by analyzing the blood glucose curve to determine the key data segment and the non-key data segment. The non-key data segment in each blood glucose curve is encrypted using a second encryption method in a targeted manner, and the key data segment in each blood glucose curve is encrypted using a first encryption method with a higher encryption degree. This method can reduce the cost of computing resources and time and improve efficiency while ensuring the security of medical care physical examination data protection.

Description

Technical Field

[0001] The present invention relates to the technical field of medical care informatics, and in particular to a medical care and physical examination data protection method and system. Background Art

[0002] With the rapid development of information technology and the advent of the digital age, hospital management is gradually transforming towards digitalization. However, while digital management brings convenience to hospitals, it also brings some security issues. Since digital management information in hospitals involves sensitive information such as patients' personal privacy, medical records, and treatment plans, once leaked or tampered with, it can have a serious impact on patients' treatment and recovery. Therefore, ensuring the security of digital management information in hospitals is an urgent issue.

[0003] For example, taking diabetes-related physical examination data as an example, when performing data protection, all data is usually encrypted and stored using a unified encryption algorithm. If shallow encryption is used, there may be a risk of brute force cracking, which has poor security. If deep encryption is used, due to the huge amount of data in the hospital, it will consume a lot of computing resources and time, which is costly and inefficient. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a medical care and physical examination data protection method and system, the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for protecting medical care and physical examination data, comprising:

[0006] Acquiring medical care and physical examination data, wherein the medical care and physical examination data includes blood glucose curves of a plurality of monitored subjects;

[0007] performing fluctuation analysis on the blood glucose curves respectively to determine a number of initial key blood glucose values ​​corresponding to each of the blood glucose curves;

[0008] performing importance analysis on a plurality of initial key blood glucose values ​​corresponding to each of the blood glucose curves to determine a final target key blood glucose value corresponding to each of the blood glucose curves;

[0009] According to the final target critical blood glucose value, the critical data segments and non-critical data segments in each of the blood glucose curves are determined, the critical data segments are first encrypted, and the non-critical data segments are second encrypted; the encryption level of the first encryption is greater than the encryption level of the second encryption.

[0010] In one embodiment, performing fluctuation analysis on the blood glucose curves to determine a number of initial key blood glucose values ​​corresponding to each blood glucose curve includes:

[0011] In each of the blood glucose curves, a plurality of first candidate blood glucose values ​​within a preset neighborhood radius corresponding to each blood glucose value are determined, and an average candidate blood glucose value corresponding to each preset neighborhood radius is determined based on the plurality of first candidate blood glucose values, wherein the first candidate blood glucose values ​​include the blood glucose value;

[0012] determining a fluctuation parameter of each blood glucose value in each of the blood glucose curves according to the candidate blood glucose average value, each of the first candidate blood glucose values, and the number of the first candidate blood glucose values;

[0013] determining the relative importance of each blood glucose value in each blood glucose curve according to the first difference between each blood glucose value in each blood glucose curve and the standard fasting blood glucose value;

[0014] A weighted calculation is performed based on the fluctuation parameters of each blood glucose value in each blood glucose curve, the relative importance of each blood glucose value, and the preset weight to determine the criticality of each blood glucose value in each blood glucose curve, and based on the criticality and the critical threshold, a number of initial critical blood glucose values ​​corresponding to each blood glucose curve are determined.

[0015] In one embodiment, determining the fluctuation parameter of each blood glucose value in each blood glucose curve based on the candidate average blood glucose value, each of the first candidate blood glucose values, and the number of the first candidate blood glucose values ​​includes:

[0016] determining a first absolute value of a second difference between each of the first candidate blood glucose values ​​and the corresponding candidate blood glucose average value in each blood glucose curve;

[0017] The fluctuation parameter of each blood glucose value in each blood glucose curve is determined by summing and averaging the first absolute value and the number of the first candidate blood glucose values.

[0018] In one embodiment, performing importance analysis on the initial key blood glucose values ​​corresponding to each blood glucose curve to determine the final target key blood glucose value corresponding to each blood glucose curve includes:

[0019] Classifying the blood glucose curves to determine at least one blood glucose curve for a regular diet and at least one blood glucose curve for an irregular diet;

[0020] Clustering the blood glucose curves of each of the dietary patterns to determine a plurality of clusters corresponding to each of the blood glucose curves of the dietary patterns, and determining at least one key cluster from the plurality of clusters corresponding to each of the blood glucose curves of the dietary patterns based on characteristic analysis of meal times;

[0021] Analyzing the key clusters respectively to determine the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster and the blood glucose recovery capacity coefficient of each key cluster;

[0022] Determining a first importance level for each initial key blood glucose value in each key cluster based on the degree of abnormal blood glucose change and the blood glucose recovery ability coefficient, and determining a first target key blood glucose value in each blood glucose curve of the dietary pattern based on the first importance level and the importance level threshold;

[0023] Analyzing each of the irregular eating blood glucose curves to determine a second importance level of each initial key blood glucose value in each of the irregular eating blood glucose curves, and determining a second target key blood glucose value in each of the irregular eating blood glucose curves based on the second importance level and an importance level threshold;

[0024] The final target critical blood glucose value includes the first target critical blood glucose value and the second target critical blood glucose value.

[0025] In one embodiment, classifying the blood glucose curves to determine the blood glucose curves of patients with regular diet and the blood glucose curves of patients with irregular diet includes:

[0026] Determining a first curve from all the blood glucose curves, and determining each second curve except the first curve, and respectively determining the Spearman correlation coefficient between the first curve and each second curve and the degree of fluctuation of the first curve;

[0027] Summing and averaging the Spearman correlation coefficient and the number of the second curves to determine an average Spearman correlation coefficient value, and determining a calculation result based on the inverse of the average Spearman correlation coefficient value and a natural exponential function;

[0028] Determining the blood glucose curve rhythm disorder index of the first curve based on the first product of the calculation result and the fluctuation degree and a normalization function, and returning to the step of determining the first curve from all the blood glucose curves until the blood glucose curve rhythm disorder index of each of the blood glucose curves is obtained;

[0029] The blood glucose curve with a rhythm disorder index greater than or equal to the disorder threshold is regarded as a blood glucose curve with irregular diet, and the blood glucose curve with a rhythm disorder index less than the disorder threshold is regarded as a blood glucose curve with regular diet.

[0030] In one embodiment, analyzing the key clusters separately to determine the degree of abnormal blood glucose change for each initial key blood glucose value in each key cluster includes:

[0031] Determining, in each of the key clusters, a time interval between the lowest initial key blood glucose value and the highest initial key blood glucose value, and a plurality of second candidate blood glucose values ​​within a preset neighborhood radius corresponding to each initial key blood glucose value, where the second candidate blood glucose values ​​include the initial key blood glucose value;

[0032] Determining a second absolute value of a first-order backward difference value of each second candidate blood glucose value, and summing and averaging the second absolute value and the number of the second candidate blood glucose values ​​to determine a blood glucose change degree of each initial key blood glucose value in each key cluster;

[0033] Determining a third difference between the highest initial key blood glucose value in each key cluster and each initial key blood glucose value in the key cluster, and determining a second product of the highest initial key blood glucose value, the degree of blood glucose change corresponding to each initial key blood glucose value in the key cluster, and the time interval;

[0034] The degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster is determined according to the ratio of the second product to the third difference.

[0035] In one embodiment, analyzing the key clusters separately to determine the blood glucose recovery ability coefficient of each key cluster includes:

[0036] Calculating a blood glucose plateau value using the blood glucose values ​​other than the initial key blood glucose value in each of the blood glucose curves, and determining a recovery time for the highest initial key blood glucose value in each of the key clusters to recover to the corresponding blood glucose plateau value;

[0037] Determine the difference between two adjacent blood glucose values ​​in each blood glucose curve within the recovery time, and sum and average the difference values ​​and the number of the difference values ​​to obtain a difference average value;

[0038] The third product of the recovery time and half of the recovery time is determined in each of the key clusters, and the blood glucose recovery ability coefficient of each key cluster is determined based on the ratio of the difference average value to the third product.

[0039] In one embodiment, determining the first importance of each initial key blood glucose value in each key cluster according to the abnormal blood glucose change degree and the blood glucose recovery ability coefficient includes:

[0040] respectively determining the fourth product of the inverse of the blood glucose recovery capacity coefficient of each key cluster and the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster;

[0041] The first importance of each initial key blood glucose value in each key cluster is determined according to the fourth product and the normalization function.

[0042] In one embodiment, analyzing each of the irregular eating blood glucose curves to determine the second importance of each initial key blood glucose value in each of the irregular eating blood glucose curves includes:

[0043] Determining the variance of the blood glucose values ​​in each of the irregular diet blood glucose curves, determining the first-order backward difference value of each of the initial key blood glucose values ​​in each of the irregular diet blood glucose curves, and determining the average blood glucose value corresponding to all the regular diet blood glucose curves;

[0044] Determining a fourth difference between each of the initial key blood glucose values ​​and the average blood glucose value in each of the blood glucose curves for the irregular diet, and determining a function adjustment value based on a natural exponential function and the fourth difference;

[0045] The fifth product of the function adjustment value and the corresponding variance is determined respectively, and the second importance of each initial key blood glucose value in each of the irregular diet blood glucose curves is obtained based on the ratio of the fifth product to the first-order backward difference value of the corresponding initial key blood glucose value.

[0046] In a second aspect, an embodiment of the present application provides a medical care and physical examination data protection system, including:

[0047] An acquisition module, used to obtain blood glucose curves of several monitored subjects;

[0048] a first determining module, configured to perform fluctuation analysis on each of the blood glucose curves to determine a plurality of initial key blood glucose values ​​corresponding to each of the blood glucose curves;

[0049] a second determining module, configured to analyze the importance of a plurality of initial key blood glucose values ​​corresponding to each of the blood glucose curves, and determine a final target key blood glucose value corresponding to each of the blood glucose curves;

[0050] An encryption module is used to determine the key data segments and non-key data segments in each of the blood glucose curves based on the final target critical blood glucose value, perform a first encryption on the key data segments, and perform a second encryption on the non-key data segments; the encryption level of the first encryption is greater than the encryption level of the second encryption.

[0051] The present invention has the following beneficial effects:

[0052] By obtaining medical care physical examination data with blood glucose curves of several monitoring objects, fluctuation analysis is performed on the blood glucose curves respectively, and several initial key blood glucose values ​​corresponding to each blood glucose curve are determined, and the importance of the several initial key blood glucose values ​​corresponding to each blood glucose curve is analyzed to determine the final target key blood glucose value corresponding to each blood glucose curve. By analyzing the blood glucose curve to determine the final target key blood glucose value, key data segments and non-key data segments are determined, and the second encryption method is used to encrypt the non-key data segments in each blood glucose curve in a targeted manner, and the key data segments in each blood glucose curve are encrypted using the first encryption method with a higher degree of encryption. This can reduce the cost of computing resources and time and improve efficiency while ensuring the security of medical care physical examination data protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A schematic flow chart of the steps of a method for protecting medical care and physical examination data provided by one embodiment of the present invention;

[0055] Figure 2 A schematic diagram of a blood glucose curve of a monitored subject during a partial time period provided by one embodiment of the present invention;

[0056] Figure 3 This is a structural block diagram of a medical care and physical examination data protection system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0057] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method and system for protecting medical care and physical examination data according to the present invention, including its specific implementation, structure, features, and effectiveness. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0058] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0059] It should be noted that the term “exemplary” in the embodiments of the present application refers to examples listed for the convenience of explanation, and other embodiments are not limited to the examples listed.

[0060] The following describes in detail a specific scheme of a medical care and physical examination data protection method and system provided by the present invention in conjunction with the accompanying drawings.

[0061] See also Figure 1 , which shows a flow chart of a medical care and physical examination data protection method provided by an embodiment of the present invention. The medical care and physical examination data protection method may include at least steps S100-S400:

[0062] S100: Obtain medical care and physical examination data.

[0063] In the embodiment of the present application, the medical care and physical examination data include blood glucose curves of several monitored subjects.

[0064] S200 , performing fluctuation analysis on each blood glucose curve to determine a number of initial key blood glucose values ​​corresponding to each blood glucose curve.

[0065] S300: Analyze the importance of several initial key blood glucose values ​​corresponding to each blood glucose curve to determine the final target key blood glucose value corresponding to each blood glucose curve.

[0066] S400. Determine the key data segments and non-key data segments in each blood glucose curve based on the final target key blood glucose value, perform a first encryption on the key data segments, and perform a second encryption on the non-key data segments; the encryption level of the first encryption is greater than the encryption level of the second encryption.

[0067] The technical solution of the embodiment of the present application obtains medical care physical examination data with blood glucose curves of several monitored objects, performs fluctuation analysis on the blood glucose curves respectively, determines several initial key blood glucose values ​​corresponding to each blood glucose curve, performs importance analysis on the several initial key blood glucose values ​​corresponding to each blood glucose curve, determines the final target key blood glucose value corresponding to each blood glucose curve, determines the key data segment and the non-key data segment by analyzing the blood glucose curve to determine the final target key blood glucose value, uses the second encryption method to encrypt the non-key data segment in each blood glucose curve in a targeted manner, and encrypts the key data segment in each blood glucose curve using the first encryption method with a higher degree of encryption. This can reduce the cost of computing resources and time and improve efficiency while ensuring the security of medical care physical examination data protection.

[0068] In one embodiment, in step S100, a continuous glucose monitoring device (CGM, such as Dexcom G6) can be used to obtain the daily blood glucose curve of the monitored subject. The acquisition frequency can be set to record blood glucose once every 1 minute, covering 24 hours a day. The specific frequency can be adjusted according to actual needs. In this way, the blood glucose curves of several monitored subjects can be obtained, such as Figure 2 As shown in the figure, it is a schematic diagram of the blood glucose curve of a monitored subject, and the horizontal axis is the corresponding time. For example, it can be seen that on November 20, the blood glucose value corresponding to 10:46 is 14.3mmol / L, and the blood glucose value corresponding to 12:49 is 3mmol / L. Therefore, the blood glucose curve can reflect the changes in blood glucose of the monitored subject during fasting, after meals, sleep and other periods.

[0069] It should be noted that, considering that the monitored subjects may have irregular diet during the monitoring period, an in-depth analysis is conducted on the effects of dietary patterns on the blood glucose curve to obtain key blood glucose information values ​​and non-critical blood glucose information in the blood glucose curve of the monitored subjects under different dietary patterns, and encryption protection is performed using encryption methods with different strategies to improve the security and efficiency of medical care and physical examination data protection.

[0070] In addition, under normal circumstances, the blood sugar curve of the monitored subject fluctuates slightly, and the blood sugar value is not much different from the standard fasting blood sugar value. If the blood sugar curve fluctuates greatly and the difference between the blood sugar value and the standard fasting blood sugar value is greater, it means that the blood sugar value may be more critical.

[0071] In one embodiment, step S200 includes steps S201-S204:

[0072] S201. In each blood glucose curve, determine a plurality of first candidate blood glucose values ​​within a preset neighborhood radius corresponding to each blood glucose value, and determine an average candidate blood glucose value corresponding to each preset neighborhood radius based on the plurality of first candidate blood glucose values, where the first candidate blood glucose values ​​include the blood glucose value.

[0073] Optionally, the preset neighborhood radius range can be set based on actual conditions. For example, taking a neighborhood radius of 5 as an example, it is equivalent to a range of 5 minutes. Therefore, with each blood glucose value as the center, a radius range of 5 is determined. At this time, it is equivalent to determining a total of 10 first candidate blood glucose values ​​before and after, and a total of 11 first candidate blood glucose values ​​including this blood glucose value. It should be noted that in other methods, the blood glucose value can also be used as the starting point to determine several first candidate blood glucose values ​​forward or backward based on the preset neighborhood radius, without specific limitation.

[0074] In the embodiment of the present application, several first candidate blood glucose values ​​within a preset neighborhood radius corresponding to each blood glucose value are determined respectively. back( That is The first blood glucose value within the preset neighborhood radius first candidate blood glucose values), respectively according to several first candidate blood glucose values , determine the candidate blood glucose average value corresponding to each preset neighborhood radius (i.e. The candidate blood glucose average values ​​corresponding to the preset neighborhood radius range of the blood glucose values ​​are respectively based on several first candidate blood glucose values ​​within each preset neighborhood radius. Calculate the average value).

[0075] S202: Determine fluctuation parameters of each blood glucose value in each blood glucose curve according to the candidate average blood glucose value, each first candidate blood glucose value, and the number of first candidate blood glucose values.

[0076] First, determine the first candidate blood glucose value in each blood glucose curve. The corresponding candidate blood glucose average The first absolute value of the second difference .

[0077] Secondly, according to the first absolute value and the number of first candidate blood glucose values The sum and average are performed to determine the fluctuation parameters of each blood glucose value in each blood glucose curve. The calculation formula is:

[0078]

[0079] Where, is the number of first candidate blood glucose values, The blood glucose curve of (any one) monitoring subject The fluctuation parameter of blood glucose value is expressed by the fluctuation of a blood glucose value in a certain neighborhood local area, which reduces the impact of analyzing the change of a single blood glucose value.

[0080] S203: Determine the relative importance of each blood glucose value in each blood glucose curve according to the first difference between each blood glucose value in each blood glucose curve and the standard fasting blood glucose value.

[0081] Optionally, according to each blood glucose value in each blood glucose curve (No. blood glucose value) and standard fasting blood glucose value (The first difference is the blood sugar value at 7 o'clock in the morning in the blood sugar curve as the standard fasting blood sugar value) , determine the relative importance of each blood glucose value in each blood glucose curve ,in For the The relative importance of each blood sugar value.

[0082] S204, respectively according to the fluctuation parameters of each blood glucose value in each blood glucose curve , the relative importance of each blood sugar value And perform weighted calculation with preset weights to determine the criticality of each blood glucose value in each blood glucose curve, and determine several initial critical blood glucose values ​​corresponding to each blood glucose curve based on the criticality and the critical threshold.

[0083] Optionally, the calculation formula is:

[0084]

[0085] Where, and are respectively the first weight and the second weight in the preset weights, exemplarily , , For each blood glucose curve The key of blood sugar value; when the blood sugar curve of the monitored object is The more a blood sugar value is greater than the standard fasting blood sugar value, the more important it is.

[0086] Then, the criticality is normalized to determine the normalized criticality, which is compared with a critical threshold (e.g., 0.8), and the blood glucose value with a normalized criticality greater than 0.8 is used as the corresponding initial critical blood glucose value in the blood glucose curve. Thus, several initial critical blood glucose values ​​corresponding to each blood glucose curve can be determined.

[0087] In one embodiment, step S300 includes steps S301-S305:

[0088] S301 , classifying each blood glucose curve to determine at least one blood glucose curve for a regular diet and at least one blood glucose curve for an irregular diet.

[0089] It should be noted that although it is normal for blood sugar to rise after a meal, the diet of the monitored subject may be irregular. For example, the subject may only eat two or one meal out of three meals a day. If the diet of the monitored subject is irregular, the subsequent importance model will make inaccurate judgments on key information in determining the blood sugar curve, which will ultimately reduce the effectiveness and efficiency of deep encryption protection. In the embodiment of the present application, by analyzing the volatility of the blood sugar curve and the degree of rhythmic disorder of the blood sugar level, the regularity of the change of the blood sugar curve with the meal is obtained, and then according to the regularity of the change, the blood sugar curve of regular diet and the blood sugar curve of irregular diet are classified. Specifically:

[0090] First, determine the first curve (e.g., the first a blood glucose curve of each monitored subject), and determining each second curve other than the first curve (e.g., The Spearman correlation coefficient between the first curve and each second curve is determined and the degree of fluctuation of the first curve (No. The fluctuation degree of the blood glucose curve of each monitored object). It should be noted that The coefficient of variation (CV) of the blood glucose value in the blood glucose curve of each monitored subject is used as the fluctuation degree of the blood glucose curve of the monitored subject. The calculation methods of Spearman correlation coefficient and CV are existing methods and will not be described in detail.

[0091] Secondly, the average value of the Spearman correlation coefficient is determined by summing and averaging the Spearman correlation coefficient and the number of second curves. , and according to the inverse of the mean of the Spearman correlation coefficient and the natural exponential function , determine the calculation results ,in is the number of monitored objects, -1 corresponds to the number of the second curve.

[0092] Furthermore, according to the first product of the calculated result and the volatility and the normalization function , determine the blood glucose curve rhythm disorder index of the first curve, return to the step of determining the first curve from all blood glucose curves, until the blood glucose curve rhythm disorder index of each blood glucose curve is obtained, the specific formula is:

[0093]

[0094] Where, For the The blood glucose curve rhythm disorder index of the monitored subjects is When different values ​​are taken, it refers to each blood glucose curve, so the blood glucose curve rhythm disorder index of each blood glucose curve can be determined by the above formula. It reflects the The fluctuation of the blood sugar curve of each monitored object. Under the condition of three regular meals for normal people, the blood sugar rise after each meal is basically the same. If the monitored object has an irregular diet, it will destroy the fluctuation of the blood sugar curve under normal diet conditions, and the greater the fluctuation of the blood sugar curve; at the same time, if the first The monitoring object and The Spearman correlation coefficient between the blood glucose curves of the monitored subjects is small, indicating that monitoring objects and The blood glucose curves of the monitored subjects vary greatly. Under normal circumstances, most of the monitored subjects will have a normal diet. The larger the blood glucose curve rhythm disorder index is, the greater the blood glucose curve is affected by irregular diet and the more irregular the diet is.

[0095] Then, the blood glucose curve with a blood glucose curve rhythm disorder index greater than or equal to a disorder threshold (eg, 0.8) is regarded as a blood glucose curve of irregular diet, and the blood glucose curve with a blood glucose curve rhythm disorder index less than the disorder threshold is regarded as a blood glucose curve of regular diet.

[0096] It should be noted that for blood sugar curves of individuals with regular meals, since the initial critical blood sugar values ​​obtained above are only possible critical values, to provide more effective protection, it is necessary to determine these initial critical blood sugar values ​​to reduce irrelevant critical values. Subjects experience elevated blood sugar levels after meals. This is generally normal, but it can also be associated with diabetic hyperglycemia. However, there are significant physiological differences between normal postprandial blood sugar elevation and that seen in diabetic subjects, primarily in the magnitude, duration, and speed of recovery. Specifically, blood sugar levels in healthy individuals typically rise, but over a period of time, insulin is rapidly secreted to facilitate glucose entry into cells, gradually returning blood sugar to normal levels. Blood sugar levels peak after a period of time and then return to normal values ​​over time. This increase is short-lived, with blood sugar levels returning to the normal range within a short period of time after a meal. However, due to insufficient insulin secretion or inadequate insulin action, the postprandial blood sugar elevation in diabetic subjects is typically greater, with the peak value reaching a higher level. This peak value often occurs longer after a meal, and the magnitude and duration of the blood sugar elevation are much greater than in healthy individuals, necessitating separate, targeted analyses.

[0097] S302. Cluster the blood glucose curves of each dietary pattern to determine a number of clusters corresponding to the blood glucose curve of each dietary pattern. Based on characteristic analysis of meal times, determine at least one key cluster from the several clusters corresponding to the blood glucose curve of each dietary pattern.

[0098] Optionally, DBSCAN density clustering is performed on the initial key blood glucose values ​​in the blood glucose curve of each dietary pattern to obtain several clusters corresponding to the blood glucose curve of each dietary pattern. Then, based on the characteristic analysis of the meal time, at least one key cluster is determined from the several clusters corresponding to the blood glucose curve of each dietary pattern. Specifically, the average time of each key blood glucose value in each cluster and the average key blood glucose value of all initial key blood glucose values ​​in the blood glucose curve of each dietary pattern are determined respectively, and then the initial key blood glucose values ​​greater than the average key blood glucose value are recorded as candidate key blood glucose values. Finally, the time period corresponding to the candidate key blood glucose values ​​in the blood glucose curve of each dietary pattern is determined, and then the three time periods with the most concentrated time (i.e., the three time periods with the largest number of candidate key blood glucose values) are regarded as normal meal times, and the cluster with the average time closest to the normal meal time is regarded as the key cluster, thereby determining at least one key cluster.

[0099] S303 , analyzing the key clusters respectively to determine the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster and the blood glucose recovery capacity coefficient of each key cluster.

[0100] Optionally, in S303, each key cluster is analyzed to determine the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster, specifically including:

[0101] First, determine the lowest initial critical blood sugar value to the highest initial critical blood sugar value in each key cluster. (i.e., the time interval between peak blood sugar levels) , a plurality of second candidate blood glucose values ​​within a preset neighborhood radius corresponding to each initial key blood glucose value, where the second candidate blood glucose values ​​include the initial key blood glucose value. Refer to the principle description of step S201 and no further details will be given.

[0102] Secondly, determine the first-order backward difference value of each second candidate blood glucose value The second absolute value of , For the The first key blood glucose value within the preset neighborhood radius The first-order backward difference value of the second candidate blood glucose value is calculated using the existing method; then, according to the second absolute value and the number of the second candidate blood glucose values, Sum and average to determine the degree of blood sugar change of each initial key blood sugar value in each key cluster , that is, in the key cluster, The degree of blood glucose change of the initial key blood glucose value is calculated based on the same principle for each key cluster. The specific formula is:

[0103]

[0104] Among them, if The greater the change between the second candidate blood glucose values ​​within the preset neighborhood radius of the first key blood glucose value, the greater the increase in local blood glucose than that of normal people, and the greater the degree of blood glucose change; considering that the first-order backward difference value may be negative, but the greater the local increase, the subsequent blood glucose level will be maintained at a higher level, and the overall blood glucose change will also be greater, so the absolute value is taken to reflect the first candidate blood glucose value in the key cluster. The degree of blood sugar change at each key blood sugar value.

[0105] Furthermore, the highest initial key blood glucose value in each key cluster is determined and the initial key blood glucose values ​​in this key cluster (i.e. The third difference of the key blood sugar value , and determine the highest initial critical blood glucose value , the degree of blood sugar change corresponding to each initial key blood sugar value in the key cluster and time intervals The second product of .

[0106] Then, the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster is determined based on the ratio of the second product to the third difference. The specific formula is:

[0107]

[0108] Where, is a hyperparameter used to prevent the denominator from being zero. Among them, compared with normal people, the subjects of diabetes monitoring usually have a larger increase in blood sugar after a meal due to insufficient insulin secretion or insufficient insulin action, that is, they lack some insulin action restrictions. Therefore, the larger the highest initial key blood sugar value in the key cluster, the longer it takes to reach the highest initial key blood sugar value. At the same time, The closer the key blood sugar values ​​are to the highest initial key blood sugar value, and the greater the degree of blood sugar change The larger the value is, the more The more abnormal the change in a key blood sugar value, the greater the degree of abnormal blood sugar change.

[0109] It should be noted that normal people have a very rapid insulin response, and their blood sugar levels usually return to normal levels in a relatively short period of time. Usually, within a few hours, blood sugar levels will fall back to normal. However, due to insufficient insulin secretion or insufficient action, the blood sugar levels of diabetic subjects may remain high for a long time after a meal. Even a few hours after a meal, blood sugar levels can still remain high, indicating that insulin cannot quickly lower blood sugar levels. The recovery rate of diabetic subjects is usually slow, and it may take longer to return to the normal range. The blood sugar levels of some subjects may even remain high for a long time. Therefore, the changes in the recovery rate of blood sugar values ​​in key clusters can be analyzed to obtain the blood sugar recovery ability coefficients of key clusters.

[0110] Optionally, in S303, the key clusters are analyzed separately to determine the blood glucose recovery ability coefficient of each key cluster, specifically including:

[0111] First, the blood glucose plateau value is calculated using the blood glucose values ​​other than the initial key blood glucose value in each blood glucose curve, and the recovery time for the highest initial key blood glucose value in each key cluster to return to the corresponding blood glucose plateau value is determined. .

[0112] Secondly, determine the recovery time of each blood glucose curve The difference between two adjacent blood glucose values , that is, The blood sugar value and The difference between the blood sugar values, and the difference value and the number of difference values Sum and average to get the difference average ,in Recovery time The amount of blood sugar levels.

[0113] Then, determine the recovery time for each key cluster separately. and half of the recovery time (denoted as , which is the third product of the half-life from the highest initial critical blood sugar value to the blood sugar plateau value. A shorter half-life usually means a faster blood sugar recovery rate and a stronger regulatory mechanism. , and determine the blood sugar recovery coefficient of each key cluster based on the ratio of the difference mean to the third product The calculation principle of each key cluster is the same, and the blood sugar recovery ability coefficient of each key cluster can be determined eventually. :

[0114]

[0115] in, The smaller the value, the stronger the blood sugar regulation ability of the monitored object corresponding to the blood sugar curve. The larger the value, the more it reflects the blood sugar recovery ability of the monitored object from the overall aspect. However, different monitored objects have different individual recovery levels due to different severity of illness. Therefore, , combined with the local half-life recovery rate analysis, The larger it is, the slower the local recovery rate is, the less sensitive the monitored subject is to insulin, the blood sugar remains at a relatively high level after a meal, the worse the recovery ability is, and the smaller the blood sugar recovery ability coefficient is.

[0116] S304. Determine the first importance of each initial key blood glucose value in each key cluster based on the degree of abnormal blood glucose change and the blood glucose recovery capacity coefficient, and determine the first target key blood glucose value in the blood glucose curve of each dietary pattern based on the first importance and the importance threshold.

[0117] First, determine the inverse of the blood glucose recovery coefficient of each key cluster The degree of abnormal blood glucose change compared to each initial key blood glucose value in each key cluster The fourth product

[0118] Secondly, according to the fourth product And the normalization function is used to determine the first importance of each initial key blood glucose value in each key cluster. The final calculation formula is:

[0119]

[0120] Where, For the key cluster The first importance of each initial key blood glucose value can be determined by this formula. is a normalized function. Among them, when the monitored subject's post-meal blood sugar recovery ability is poor, that is, the sugar recovery ability coefficient The smaller the blood sugar level, the greater the degree of abnormal changes The larger the value, the more important the blood sugar value contains, and it can reflect the blood sugar health level of the monitored object to a certain extent. The bigger.

[0121] In the embodiment of the present application, for example, the importance threshold is 0.78, which is not limited in other implementations. Each first importance is compared with the importance threshold of 0.78. When the first importance of an initial key blood glucose value is greater than the importance threshold of 0.78, the initial key blood glucose value is used as the first target key blood glucose value. Therefore, the first target key blood glucose value in the blood glucose curve of each dietary pattern can be finally determined.

[0122] It should be noted that there are differences between the blood sugar curves of normal people with irregular diet and those of diabetic monitoring subjects with irregular diet. The main difference is that diabetic monitoring subjects have impaired glucose tolerance, higher fasting blood sugar, less steep postprandial blood sugar fluctuations, longer duration of high blood sugar, and limited blood sugar reduction. Therefore, based on this characteristic, the blood sugar curves of irregular diet can be analyzed.

[0123] S305. Analyze the blood glucose curves of each irregular diet to determine the second importance of each initial key blood glucose value in each irregular diet blood glucose curve, and determine the second target key blood glucose value in each irregular diet blood glucose curve based on the second importance and the importance threshold.

[0124] First, determine the variance of blood glucose values ​​in each irregular diet blood glucose curve , respectively determine the first-order backward difference value of each initial key blood glucose value in each irregular diet blood glucose curve (i.e. the blood sugar curve of irregular diet The first-order backward difference of the initial key blood glucose values) and the average blood glucose value corresponding to the blood glucose curve of all dietary patterns are determined , which is the average value calculated based on the blood sugar values ​​of the blood sugar curves of all dietary patterns.

[0125] Secondly, determine the initial key blood sugar values ​​in each irregular diet blood sugar curve (i.e. the first The fourth difference between the initial key blood sugar value and the average blood sugar value , respectively according to the natural exponential function And the fourth difference, determine the function adjustment value .

[0126] Then, determine the fifth product of the function adjustment value and the corresponding variance respectively , and respectively according to the fifth product The first-order backward difference value of the corresponding initial key blood glucose value The second importance of each initial key blood glucose value in each irregular diet blood glucose curve is obtained by the ratio of . Specifically, the calculation formula is:

[0127]

[0128] Where, This is the blood sugar curve of irregular diet The second importance of each initial key blood sugar value can be calculated based on the above formula to obtain the second importance of each initial key blood sugar value in each irregular diet blood sugar curve. It is a hyperparameter to prevent the denominator from being 0. It should be noted that when the blood glucose curve of the monitored subject with irregular diet is greater than the average blood glucose value corresponding to the blood glucose curve of the regular diet, , indicating that the initial key blood sugar value is more affected by irregular diet, and it can also reflect that the more abnormal the blood sugar level is, the more important the abnormal information is. There will be negative values, so through the natural exponential function Make adjustments, the bigger the more important; They respectively represent the local changes in the initial key blood sugar value (local fluctuations will not be very steep) and the changes over a certain long period of time. The changes over a certain long period of time will be more obvious, especially when the diet is more irregular.

[0129] In the embodiment of the present application, the second importance of each initial key blood glucose value is compared with the importance threshold, exemplarily the importance threshold is 0.78. When the second importance of a certain initial key blood glucose value is greater than the importance threshold 0.78, the initial key blood glucose value is used as the second target key blood glucose value, thereby ultimately determining the second target key blood glucose value in the blood glucose curve of each irregular diet. It should be noted that the final target key blood glucose value includes the first target key blood glucose value and the second target key blood glucose value.

[0130] In one embodiment, in step S400, after determining the final target key blood glucose value, that is, after determining the first target key blood glucose value and the second target key blood glucose value, a first target data segment in the corresponding blood glucose curve for a regular diet can be determined as a key data segment based on the first target key blood glucose value, and data segments other than the first target data segment in the blood glucose curve for a regular diet can be non-key data segments. Furthermore, based on the second target key blood glucose value, a second target data segment in the corresponding blood glucose curve for an irregular diet can be determined as a key data segment, and data segments other than the second target data segment in the blood glucose curve for an irregular diet can be non-key data segments. Therefore, ultimately, based on the final target key blood glucose value, key data segments (including key data segments in the blood glucose curve for a regular diet and key data segments in the blood glucose curve for an irregular diet) and non-key data segments (including non-key data segments in the blood glucose curve for a regular diet and non-key data segments in the blood glucose curve for an irregular diet) in each blood glucose curve can be determined. It should be noted that the principles for determining the first target data segment and the second target data segment are similar. Taking the first target data segment as an example, when a first target critical blood glucose value A is obtained, the first target critical blood glucose value A can be used as the first target data segment, or a specified radius can be set to determine the data segment within the specified radius of the first target critical blood glucose value A as the first target data segment, without specific limitation.

[0131] Finally, the data is protected using encryption methods with different strategies. Specifically, a first encryption is performed on the critical data segment. For example, AES deep encryption is used, and AES-256 uses a 14-round key for encryption protection. When setting a specified radius, the first target data segment is guaranteed to be a multiple of 16 bytes, because the AES (Advanced Encryption Standard) encryption algorithm requires the size of the encrypted data block to be 128 bits (16 bytes). In addition, a second encryption is performed on the non-critical data segment. The second encryption level is less than the first encryption level, for example, using AES-128 with a 10-round key for encryption protection. It should be noted that AES is an existing method and will not be described in detail. The original key can be used to decrypt and restore the blood glucose curve.

[0132] In an embodiment of the present application, by analyzing and determining the key data segments and non-key data segments in the blood glucose curve, encryption strategies with different encryption levels are used to encrypt the key data segments and non-key data segments respectively. This can reduce the cost of computing resources and time, improve efficiency, and have higher feasibility and practicality on the basis of ensuring the security of medical care and physical examination data protection.

[0133] Reference Figure 3 , shows a structural block diagram of a medical care and physical examination data protection system according to an embodiment of the present application, which may include:

[0134] An acquisition module, used to obtain blood glucose curves of several monitored subjects;

[0135] A first determination module is used to perform fluctuation analysis on each blood glucose curve to determine a number of initial key blood glucose values ​​corresponding to each blood glucose curve;

[0136] The second determination module is used to analyze the importance of several initial key blood glucose values ​​corresponding to each blood glucose curve and determine the final target key blood glucose value corresponding to each blood glucose curve;

[0137] The encryption module is used to determine the key data segments and non-key data segments in each blood glucose curve according to the final target key blood glucose value, perform a first encryption on the key data segments and a second encryption on the non-key data segments; the encryption level of the first encryption is greater than the encryption level of the second encryption.

[0138] In the embodiment of the present application, the functions of each module in the system can be referred to the corresponding description in the above method and will not be repeated here.

[0139] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0140] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for protecting medical care and physical examination data, characterized in that: The method comprises: Obtaining medical care and physical examination data, the medical care and physical examination data including blood glucose curves of several monitored subjects; Perform fluctuation analysis on the blood glucose curves respectively to determine several initial key blood glucose values ​​corresponding to each blood glucose curve; Performing importance analysis on several initial key blood glucose values ​​corresponding to each blood glucose curve to determine the final target key blood glucose value corresponding to each blood glucose curve; specifically including: Classifying each blood glucose curve to determine at least one blood glucose curve for a regular diet and at least one blood glucose curve for an irregular diet; Clustering the blood glucose curves for each dietary pattern to determine a number of clusters corresponding to each dietary pattern blood glucose curve; and determining at least one key cluster from the clusters corresponding to each dietary pattern blood glucose curve based on characteristic analysis of meal times; Analyze the key clusters separately to determine the degree of abnormal blood glucose change for each initial key blood glucose value in each key cluster and the blood glucose recovery capacity coefficient of each key cluster; Determine the first importance of each initial key blood glucose value in each key cluster based on the degree of abnormal blood glucose change and the blood glucose recovery capacity coefficient, and determine the first target key blood glucose value in the blood glucose curve of each dietary pattern based on the first importance and the importance threshold; Analyzing each blood glucose curve of the irregular diet, determining the second importance of each initial key blood glucose value in each blood glucose curve of the irregular diet, and determining a second target key blood glucose value in each blood glucose curve of the irregular diet based on the second importance and the importance threshold; The final target critical blood sugar value includes a first target critical blood sugar value and a second target critical blood sugar value; Analyze the blood sugar curves of each irregular diet and determine the second most important level of each initial key blood sugar value in each irregular diet blood sugar curve, including: Determine the variance of the blood glucose values ​​in each irregular diet blood glucose curve, determine the first-order backward difference value of each initial key blood glucose value in each irregular diet blood glucose curve, and determine the average blood glucose value corresponding to all regular diet blood glucose curves; Determining the fourth difference between each initial key blood glucose value and the average blood glucose value in each blood glucose curve of the irregular diet, and determining the function adjustment value based on the natural exponential function and the fourth difference; Determining the fifth product of the function adjustment value and the corresponding variance, and obtaining the second importance of each initial key blood glucose value in each irregular diet blood glucose curve based on the ratio of the fifth product to the first-order backward difference value of the corresponding initial key blood glucose value; According to the final target critical blood glucose value, the critical data segments and non-critical data segments in each blood glucose curve are determined, the critical data segments are first encrypted and the non-critical data segments are second encrypted; the encryption level of the first encryption is greater than the encryption level of the second encryption.

2. The medical care and physical examination data protection method according to claim 1 is characterized by: The performing fluctuation analysis on the blood glucose curves to determine the initial key blood glucose values ​​corresponding to each blood glucose curve includes: In each of the blood glucose curves, a plurality of first candidate blood glucose values ​​within a preset neighborhood radius corresponding to each blood glucose value are determined, and an average candidate blood glucose value corresponding to each preset neighborhood radius is determined based on the plurality of first candidate blood glucose values, wherein the first candidate blood glucose values ​​include the blood glucose value; determining a fluctuation parameter of each blood glucose value in each of the blood glucose curves according to the candidate blood glucose average value, each of the first candidate blood glucose values, and the number of the first candidate blood glucose values; determining the relative importance of each blood glucose value in each blood glucose curve according to the first difference between each blood glucose value in each blood glucose curve and the standard fasting blood glucose value; A weighted calculation is performed based on the fluctuation parameters of each blood glucose value in each blood glucose curve, the relative importance of each blood glucose value, and the preset weight to determine the criticality of each blood glucose value in each blood glucose curve, and based on the criticality and the critical threshold, a number of initial critical blood glucose values ​​corresponding to each blood glucose curve are determined.

3. The method for protecting medical care and physical examination data according to claim 2, characterized in that: The determining of the fluctuation parameter of each blood glucose value in each blood glucose curve according to the candidate average blood glucose value, each of the first candidate blood glucose values, and the number of the first candidate blood glucose values ​​includes: determining a first absolute value of a second difference between each of the first candidate blood glucose values ​​and the corresponding candidate blood glucose average value in each blood glucose curve; The fluctuation parameter of each blood glucose value in each blood glucose curve is determined by summing and averaging the first absolute value and the number of the first candidate blood glucose values.

4. The medical care and physical examination data protection method according to claim 1 is characterized by: The classifying and processing the blood glucose curves to determine the blood glucose curves of regular diet and the blood glucose curves of irregular diet includes: Determining a first curve from all the blood glucose curves, and determining each second curve except the first curve, and respectively determining the Spearman correlation coefficient between the first curve and each second curve and the degree of fluctuation of the first curve; Summing and averaging the Spearman correlation coefficient and the number of the second curves to determine an average Spearman correlation coefficient value, and determining a calculation result based on the inverse of the average Spearman correlation coefficient value and a natural exponential function; Determining the blood glucose curve rhythm disorder index of the first curve based on the first product of the calculation result and the fluctuation degree and a normalization function, and returning to the step of determining the first curve from all the blood glucose curves until the blood glucose curve rhythm disorder index of each of the blood glucose curves is obtained; The blood glucose curve with a rhythm disorder index greater than or equal to the disorder threshold is regarded as a blood glucose curve with irregular diet, and the blood glucose curve with a rhythm disorder index less than the disorder threshold is regarded as a blood glucose curve with regular diet.

5. The medical care and physical examination data protection method according to claim 1 is characterized by: Analyzing the key clusters separately to determine the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster includes: Determining, in each of the key clusters, a time interval between the lowest initial key blood glucose value and the highest initial key blood glucose value, and a plurality of second candidate blood glucose values ​​within a preset neighborhood radius corresponding to each initial key blood glucose value, where the second candidate blood glucose values ​​include the initial key blood glucose value; Determining a second absolute value of a first-order backward difference value of each second candidate blood glucose value, and summing and averaging the second absolute value and the number of the second candidate blood glucose values ​​to determine a blood glucose change degree of each initial key blood glucose value in each key cluster; Determining a third difference between the highest initial key blood glucose value in each key cluster and each initial key blood glucose value in the key cluster, and determining a second product of the highest initial key blood glucose value, the degree of blood glucose change corresponding to each initial key blood glucose value in the key cluster, and the time interval; The degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster is determined according to the ratio of the second product to the third difference.

6. The medical care and physical examination data protection method according to claim 1, characterized in that: Analyzing the key clusters separately to determine the blood glucose recovery ability coefficient of each key cluster includes: Calculating a blood glucose plateau value using the blood glucose values ​​other than the initial key blood glucose value in each of the blood glucose curves, and determining a recovery time for the highest initial key blood glucose value in each of the key clusters to recover to the corresponding blood glucose plateau value; Determine the difference between two adjacent blood glucose values ​​in each blood glucose curve within the recovery time, and sum and average the difference values ​​and the number of the difference values ​​to obtain a difference average value; The third product of the recovery time and half of the recovery time is determined in each of the key clusters, and the blood glucose recovery ability coefficient of each key cluster is determined based on the ratio of the difference average value to the third product.

7. The medical care and physical examination data protection method according to claim 1 is characterized by: Determining the first importance of each initial key blood glucose value in each key cluster according to the abnormal blood glucose change degree and the blood glucose recovery ability coefficient includes: respectively determining the fourth product of the inverse of the blood glucose recovery capacity coefficient of each key cluster and the degree of abnormal blood glucose change of each initial key blood glucose value in each key cluster; The first importance of each initial key blood glucose value in each key cluster is determined according to the fourth product and the normalization function.

8. A medical care and physical examination data protection system, characterized in that: The method for protecting medical care and physical examination data according to claim 1 comprises: An acquisition module, used to obtain blood glucose curves of several monitored subjects; a first determining module, configured to perform fluctuation analysis on each of the blood glucose curves to determine a plurality of initial key blood glucose values ​​corresponding to each of the blood glucose curves; a second determining module, configured to analyze the importance of a plurality of initial key blood glucose values ​​corresponding to each of the blood glucose curves, and determine a final target key blood glucose value corresponding to each of the blood glucose curves; An encryption module is used to determine the key data segments and non-key data segments in each of the blood glucose curves based on the final target critical blood glucose value, perform a first encryption on the key data segments, and perform a second encryption on the non-key data segments; the encryption level of the first encryption is greater than the encryption level of the second encryption.

Images