An intelligent medical information sharing system and method based on cloud computing

Abstract

The present invention discloses an intelligent medical information sharing system and method based on cloud computing, which belongs to the technical field of medical information sharing. The present invention includes a cloud server, a plurality of medical information request sharing terminals, a medical information standardization processing module, a medical information application analysis module and a medical information sharing module; the medical information standardization processing module is used to perform standardization processing on the called medical information; the medical information application analysis module is used to screen and process the called medical information to obtain the target medical information; the medical information sharing module is used to search for the associated medical information of the target medical information. In the data fusion processing process, the present invention determines the weight of each medical data by the relationship between two random medical data, and can eliminate the data with large errors in the medical data, thereby improving the sharing value of the medical information while improving the effect of the medical information standardization processing.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information sharing, and in particular to an intelligent medical information sharing system and method based on cloud computing. Background Art

[0002] With the development of information technology and the transformation of the medical industry, medical data sharing has gradually become the focus of people's attention. Medical data sharing is conducive to improving medical quality and efficiency and promoting medical research and scientific development.

[0003] However, in the process of medical data sharing, due to the differences in data formats and standards among different medical institutions, the shared data may be inconsistent and inaccurate, which will affect the application and analysis of medical data, thereby reducing the data sharing effect. At the same time, when medical data is shared, it is impossible to effectively screen the shared data, which increases the analysis time of medical data and the search for related data of shared data, that is, the use effect of shared data cannot be guaranteed. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent medical information sharing system and method based on cloud computing to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent medical information sharing system based on cloud computing, the system comprising a cloud server, a plurality of medical information request sharing terminals, a medical information standardization processing module, a medical information application analysis module and a medical information sharing module;

[0006] The cloud server and the medical information request sharing terminal communicate with each other, and the cloud server is used to store the medical information uploaded by the medical information request sharing terminal. The cloud server is also used to search for shared medical information matching the sharing request information according to the sharing request information sent by the medical information request sharing terminal, and the medical information includes electronic medical record data, medical imaging data, laboratory data and public health data;

[0007] The medical information request sharing terminal is used to upload medical information whose sharing coefficient is within a preset range to the cloud server, and the medical information request sharing terminal is also used to call the shared medical information matching the sharing request information;

[0008] The medical information standardization processing module is used to perform data cleaning and data fusion processing on the called medical information according to the accuracy level of each medical device equipped in the hospital to which the called medical information belongs, and standardize the called medical information based on the processing results;

[0009] The medical information application analysis module is used to perform application analysis on the medical information called by the medical information request sharing terminal, and based on the analysis result, screen and process the called medical information to obtain the target medical information;

[0010] The medical information sharing module analyzes the related medical information of the target medical information according to the analysis results of the application that calls the medical information, searches for the related medical information of the target medical information based on the analysis results, and feeds back the target medical information and the found related medical information to the corresponding medical information request sharing terminal through the cloud server.

[0011] Furthermore, the specific prediction method of the sharing coefficient is:

[0012] Search for the same type of medical information to be uploaded, and number each of the found medical information. The numbering result is: j = 1, 2, ..., m; m represents the total number of numbers, and the number Y of times the medical information with the same type of number j is used as electronic medical record data 1j , the number of times Y acts as medical imaging data 2j , the number of times Y acts as laboratory data 3j , and the number of times Y serves as public health data 4j To obtain;

[0013] Combined with the total number of times the same type of medical information with number j is called, X j , construct the prediction model R = (1 / m)*∑[γ1*(Y 1j / X j )+γ2*(Y 2j / X j )+γ3*(Y 3j / X j )+γ4*(Y 4j / X j )] The sharing coefficient of the medical information to be uploaded is predicted, where γ1, γ2, γ3, and γ4 all represent weight values ​​and γ1+γ2+γ3+γ4=1, ∑ represents the summation symbol, the subscript of ∑ is j=1, and the superscript is m. According to the sharing coefficient of the medical information to be uploaded, the medical data can be screened and processed from the source to avoid storing too much useless medical information in the cloud server.

[0014] Furthermore, the medical information standardization processing module includes a medical data cleaning processing unit, a medical data quality assessment unit and a calling medical information standardization processing unit;

[0015] The medical data cleaning processing unit acquires the historical medical data generated by each medical device to obtain the historical medical data set of each medical device, and cleans the historical medical data set of each medical device according to the reference value of each medical examination index formulated in the hospital to which the medical information belongs and the accuracy level of each medical device, wherein the accuracy level includes the first level, the second level and the third level;

[0016] The medical data quality assessment unit calculates the ratio between the total number of medical data that has been cleaned but not retained in the historical medical data set and the total number of medical data stored in the historical medical data set to obtain a quality index of the medical data generated by each medical device in the hospital to which the medical information belongs;

[0017] The called medical information standardization processing unit determines the historical medical data that needs to be fused according to the quality index of the medical data generated by each medical device in the hospital to which the called medical information belongs, and standardizes the called medical information based on the data fusion processing result.

[0018] Furthermore, the specific method of the medical data cleaning processing unit for cleaning the historical medical data set of each medical device is:

[0019] Numbering is performed on each medical device equipped in the hospital to which the medical information is called, and the numbering result is: i=1, 2, ..., n; n represents the total number of medical devices equipped in the hospital to which the medical information is called, and numbering is performed on each medical examination indicator, and the numbering result is: p=1, 2, ..., q; q represents the total number of medical examination indicators, and the medical device is matched with the medical examination indicator. If the medical examination indicator numbered p comes from the medical device numbered i, then the medical device numbered i and the medical examination indicator numbered p are successfully matched. If the medical examination indicator numbered p does not come from the medical device numbered i, then the medical device numbered i and the medical examination indicator numbered p are not successfully matched;

[0020] When the match is successful, according to the accuracy level of the medical device numbered i, the reference value variation range of the medical examination index numbered p is [a p -f i *0.1,a p +f i *0.1] to determine, randomly select a medical data from the historical medical data set of the medical device numbered i, and determine whether the selected medical data is in [a p -f*0.1,a p +f*0.1], if it is within the range, the selected medical data will not be cleaned, if not, the selected medical data will be cleaned, where a pIndicates calling the reference value of the medical examination index numbered p set by the hospital to which the medical information belongs, f i Indicates the accuracy level of the medical device numbered i.

[0021] Furthermore, the specific method of calling the medical information standardization processing unit to perform standardization processing on the called medical information is:

[0022] According to T ip =(a p -f i *0.1)*(1+G i ) and T′ ip =(a p +f i *0.1)*(1-G i ) determines the historical medical data that needs to be processed by data fusion, where G i represents the quality index of medical data generated by medical device number i, T ip Indicates the first reference limit value of the medical examination index numbered p, T′ ip Indicates the second reference limit value of the medical examination index numbered p;

[0023] Determine whether the medical data cleaned and retained in the historical medical data set is within the first set range or the second set range. If so, it is necessary to perform data fusion processing on the corresponding medical data. If not, it is not necessary to perform data fusion processing on the corresponding medical data. The first set range ∈ [a p -f i *0.1,T ip ], the second setting range ∈[T′ ip ,a p +f i *0.1];

[0024] The medical data within the first set range is put into a set M, and the redundant data in the set M is deleted to obtain a set M′; the medical data within the second set range is put into a set N, and the redundant data in the set N is deleted to obtain a set N′;

[0025] Calculate the difference between any two medical data stored in the set M′, and let the weights of the two medical data corresponding to the minimum difference be CEILING(r / 2,1), where r represents the total number of medical data stored in the set M′, the CEILING function is an upward rounding function, and 1 represents the rounding cardinality. Then delete the two medical data corresponding to the minimum difference from the set M′ to obtain the set M′1. Repeat the operation until the weights of the medical data stored in the set M′ are all determined;

[0026] According to Q1=∑{W c *U c *(k c +1) / [∑W c *(k c +1)]} predicts the weighted fusion estimate of the medical data in the set M, where c = 1, 2, ..., C, represents the serial number corresponding to each medical data stored in the set M', C represents the total number of medical data stored in the set M', and W c represents the weight corresponding to the medical data numbered c, k c represents the total number of data that exist in the redundant data deleted from the set M and are the same as the medical data numbered c, U c represents the specific value corresponding to the medical data numbered c, ∑ represents the summation symbol, the subscript is c=1, the superscript is C, and the specific values ​​of the medical data stored in the set M are all modified to Q1; by predicting the weighted fusion estimate of the medical data, in the process of realizing the standardized processing of medical information, some fuzzy data can also be identified and adjusted. Fuzzy data refers to medical data located near the reference value of the indicator, which is conducive to improving the sharing effect of medical information;

[0027] In the data fusion process, based on the determined weights of each medical data, the data with large errors in the medical data can be eliminated;

[0028] Construct prediction model Q2 = ∑{W′ z *U′ z *(k′ z +1) / [∑W′ z *(k′ z +1)]} predicts the weighted fusion estimate of the medical data in set N, where z = 1, 2, ..., Z, represents the serial number corresponding to each medical data stored in set N', Z represents the total number of medical data stored in set N', and W' z represents the weight corresponding to the medical data numbered z, k′ z represents the total number of data that exist in the redundant data deleted from set N and are the same as the medical data numbered z, U′ z It represents the specific value corresponding to the medical data numbered z, ∑ represents the summation symbol, the subscript is z=1, and the superscript is Z. The specific values ​​of the medical data stored in the set N are all modified to Q21 to achieve standardized processing of the called medical information, ensuring that the called medical information after standardized processing has more shared value.

[0029] Further, the medical information application analysis module includes an application analysis unit and a medical information screening unit;

[0030] The application analysis unit determines the application object of the medical information called by the medical information request sharing terminal, the application object includes medical decision-making, teaching and scientific research, the determined application object is the target application object, and the target application object is transmitted to the medical information screening unit;

[0031] The medical information screening unit obtains the standardized processing status of the called medical information, and based on the obtained information, predicts the matching degree between the called medical information after the standardized processing and each application object, and based on the prediction result, screens the called medical information to obtain the target medical information.

[0032] Furthermore, the specific method of the medical information screening unit to screen the called medical information is:

[0033] The ratio between the number of times the medical data in the called medical information is modified and the total number of medical data in the called medical information is calculated to obtain the sharing accuracy of the called medical information, and the difference between the sharing accuracy of the called medical information and the sharing accuracy required by the target application object is calculated. If the difference is within the error range, all the medical data stored in the called medical information are retained, and the called medical information is now the target medical information;

[0034] If the difference is not within the error range, all the modified medical data in the called medical information are filtered out, and the unfiltered called medical information in the called medical information is the target medical information;

[0035] By screening the medical data twice, the analysis time of the medical information request sharing terminal for the medical data can be effectively reduced.

[0036] Further, the medical information sharing module includes an analysis unit, a related medical information search unit and a medical information sharing unit;

[0037] The analysis unit analyzes the associated medical information of the target medical information according to the target application object of the called medical information. If the target application object is a hospital terminal, the associated medical information of the target medical information is the historical medical information of the owner of the called medical information. If the target application object is a scientific research terminal or a teaching terminal, the associated medical information of the target medical information is the same type of medical information as the called medical information.

[0038] The associated medical information searching unit searches for associated medical information of the target medical information according to the analysis result of the analyzing unit;

[0039] The medical information sharing unit feeds back the target medical information and the found related medical information to the corresponding medical information request sharing terminal through the cloud server.

[0040] An intelligent medical information sharing method based on cloud computing, the method comprising:

[0041] S10: selectively storing the medical information uploaded by the medical information request sharing terminal through the cloud server;

[0042] S20: The cloud server determines the called medical information according to the sharing request information sent by the medical information request sharing terminal, performs data cleaning and data fusion processing on the called medical information according to the accuracy level of each medical device equipped in the hospital to which the called medical information belongs, and performs standardization processing on the called medical information based on the processing result;

[0043] S30: screening and processing the called medical information according to the application object of calling the medical information to obtain the target medical information;

[0044] S40: searching for the associated medical information of the target medical information according to the application object that calls the medical information, and feeding back the target medical information and the found associated medical information to the corresponding medical information request sharing terminal through the cloud server.

[0045] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0046] 1. Before storing medical information, the present invention predicts the sharing coefficient of the medical information to be uploaded based on the calling status of similar medical information to be uploaded, thereby screening and processing medical data from the source, avoiding storage of too much useless medical information in the cloud server, and improving the sharing effect of medical information while ensuring the sharing rate of medical information.

[0047] 2. The present invention identifies ambiguous medical data through the accuracy level of each medical device and the reference value of each medical examination indicator, and realizes the standardized processing of the called medical information by performing data fusion processing on the identified medical data. In the data fusion processing process, the weight of each medical data is determined through the relationship between two random medical data, and the data with large errors in the medical data can be eliminated. While improving the standardized processing effect of medical information, the shared value of medical information is improved.

[0048] 3. The present invention selectively filters and processes the called medical data according to the difference between the sharing accuracy of the called medical information and the sharing accuracy required by the target application object. Screening the medical data twice can effectively reduce the analysis time of the medical data by the medical information request sharing terminal. The present invention searches for the related medical information of the target medical information according to the target application object of the called medical information, which is conducive to ensuring that the medical information fed back to the medical information request sharing terminal can meet the user's needs, further improving the use effect of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 It is a schematic diagram of the working principle structure of an intelligent medical information sharing system and method based on cloud computing of the present invention;

[0051] Figure 2 It is a schematic diagram of the workflow of an intelligent medical information sharing system and method based on cloud computing of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] See also Figure 1 and Figure 2 , the present invention provides a technical solution: an intelligent medical information sharing system based on cloud computing, the system includes a cloud server, a number of medical information request sharing terminals, a medical information standardization processing module, a medical information application analysis module and a medical information sharing module;

[0054] The cloud server and the medical information request sharing terminal communicate with each other. The cloud server is used to store the medical information uploaded by the medical information request sharing terminal. The cloud server is also used to search for shared medical information matching the sharing request information according to the sharing request information sent by the medical information request sharing terminal. The medical information includes electronic medical record data, medical imaging data, laboratory data and public health data.

[0055] The medical information request sharing terminal is used to upload the medical information whose sharing coefficient is within a preset range to the cloud server. The medical information request sharing terminal is also used to call the shared medical information matching the sharing request information. The preset range is ∈ [0.8, 1]. The medical information request sharing terminal includes hospital terminals, scientific research terminals and teaching terminals.

[0056] The specific prediction method of the sharing coefficient is:

[0057] Search for the same type of medical information to be uploaded, and number each of the found medical information. The numbering result is: j = 1, 2, ..., m; m represents the total number of numbers, and the number Y of times the medical information with the same type of number j is used as electronic medical record data 1j , the number of times Y acts as medical imaging data 2j , the number of times Y acts as laboratory data 3j , and the number of times Y serves as public health data 4j Obtaining, calculating the content similarity between the called medical information and the medical information to be uploaded, if the calculated content similarity is ≥ 0.9, content similarity = (image similarity + text similarity) / 2, and the calculation methods of image similarity and text similarity are both existing technologies, then the called medical information is called medical information of the same type as the medical information to be uploaded;

[0058] Combined with the total number of times the same type of medical information with number j is called, X j , construct the prediction model R = (1 / m)*∑[γ1*(Y 1j / X j )+γ2*(Y 2j / X j )+γ3*(Y 3j / X j )+γ4*(Y 4j / X j )] predicts the sharing coefficient of the medical information to be uploaded, where γ1, γ2, γ3, and γ4 all represent weight values ​​and γ1+γ2+γ3+γ4=1, ∑ represents the summation symbol, the subscript of ∑ is j=1, and the superscript is m;

[0059] The medical information standardization processing module is used to perform data cleaning and data fusion processing on the called medical information according to the accuracy level of each medical device equipped in the hospital to which the called medical information belongs, and standardize the called medical information based on the processing results;

[0060] The medical information standardization processing module includes a medical data cleaning processing unit, a medical data quality assessment unit and a calling medical information standardization processing unit;

[0061] The medical data cleaning processing unit acquires the historical medical data generated by each medical device to obtain the historical medical data set of each medical device, and cleans the historical medical data set of each medical device according to the reference values ​​of each medical examination index formulated by the hospital to which the medical information belongs and the accuracy level of each medical device. The accuracy levels include the first level, the second level and the third level. The first level refers to the error value of the medical device between 0 and 0.1 (including 0.1), the second level refers to the error value of the medical device between 0.1 and 0.2 (including 0.2), and the third level refers to the error value of the medical device greater than 0.2. The specific method is:

[0062] Numbering is performed on each medical device equipped in the hospital to which the medical information is called, and the numbering result is: i=1, 2, ..., n; n represents the total number of medical devices equipped in the hospital to which the medical information is called, and numbering is performed on each medical examination indicator, and the numbering result is: p=1, 2, ..., q; q represents the total number of medical examination indicators, and the medical device is matched with the medical examination indicator. If the medical examination indicator numbered p comes from the medical device numbered i, then the medical device numbered i and the medical examination indicator numbered p are successfully matched. If the medical examination indicator numbered p does not come from the medical device numbered i, then the medical device numbered i and the medical examination indicator numbered p are not successfully matched;

[0063] When the match is successful, according to the accuracy level of the medical device numbered i, the reference value variation range of the medical examination index numbered p is [a p -f i *0.1,a p +f i *0.1] to determine, randomly select a medical data from the historical medical data set of the medical device numbered i, and determine whether the selected medical data is in [a p -f*0.1,a p +f*0.1], if it is within the range, the selected medical data will not be cleaned, if not, the selected medical data will be cleaned, where a p Indicates calling the reference value of the medical examination index numbered p set by the hospital to which the medical information belongs, f i Indicates the accuracy level of the medical device numbered i. When the accuracy level of the medical device numbered i is the first level, f i =1, when the accuracy level of the medical device numbered i is the second level, f i =2, when the accuracy level of the medical device numbered i is the third level, f i =3;

[0064] The medical data quality assessment unit calculates the ratio between the total number of medical data that has been cleaned but not retained in the historical medical data set and the total number of medical data stored in the historical medical data set, and obtains the quality index of the medical data generated by each medical device in the hospital to which the medical information belongs;

[0065] The medical information standardization processing unit determines the historical medical data that needs to be processed by data fusion according to the quality index of the medical data generated by each medical device in the hospital to which the medical information belongs, and performs standardized processing on the medical information based on the data fusion processing result. The specific method is as follows:

[0066] According to T ip =(a p -f i *0.1)*(1+G i ) and T′ ip =(a p +f i *0.1)*(1-G i ) determines the historical medical data that needs to be processed by data fusion, where G i represents the quality index of medical data generated by medical device number i, T ip Indicates the first reference limit value of the medical examination index numbered p, T′ ip Indicates the second reference limit value of the medical examination index numbered p;

[0067] Determine whether the medical data cleaned and retained in the historical medical data set is within the first set range or the second set range. If so, it is necessary to perform data fusion processing on the corresponding medical data. If not, it is not necessary to perform data fusion processing on the corresponding medical data. The first set range ∈ [a p -f i *0.1,T ip ], the second setting range ∈[T′ ip ,a p +f i *0.1];

[0068] The medical data within the first set range is put into a set M, and the redundant data in the set M is deleted to obtain a set M′; the medical data within the second set range is put into a set N, and the redundant data in the set N is deleted to obtain a set N′;

[0069] Calculate the difference between any two medical data stored in the set M′, and let the weights of the two medical data corresponding to the minimum difference be CEILING(r / 2,1), where r represents the total number of medical data stored in the set M′, the CEILING function is an upward rounding function, and 1 represents the rounding cardinality. Then, delete the two medical data corresponding to the minimum difference from the set M′ to obtain the set M′1;

[0070] Calculate the difference between any two medical data stored in the set M′1, and let the weights of the two medical data corresponding to the minimum difference be CEILING((r-2) / 2,1), where r-2 represents the total number of medical data stored in M′1. Then delete the two medical data corresponding to the minimum difference from the set M′1 to obtain the set M′2. Repeat the operation until the weights of the medical data stored in the set M′ are all determined.

[0071] According to Q1=∑{W c *U c *(k c +1) / [∑W c *(k c +1)]} predicts the weighted fusion estimate of the medical data in the set M, where c = 1, 2, ..., C, represents the serial number corresponding to each medical data stored in the set M', C represents the total number of medical data stored in the set M', and W c represents the weight corresponding to the medical data numbered c, k c represents the total number of data that exist in the redundant data deleted from the set M and are the same as the medical data numbered c, U c represents the specific value corresponding to the medical data numbered c, ∑ represents the summation symbol, the subscript is c=1, the superscript is C, and the specific values ​​of the medical data stored in the set M are all modified to Q1;

[0072] Construct prediction model Q2 = ∑{W′ z *U′ z *(k′ z +1) / [∑W′ z *(k′ z +1)]} predicts the weighted fusion estimate of the medical data in set N, where z = 1, 2, ..., Z, represents the serial number corresponding to each medical data stored in set N', Z represents the total number of medical data stored in set N', and W' z represents the weight corresponding to the medical data numbered z, k′ z represents the total number of data that exist in the redundant data deleted from set N and are the same as the medical data numbered z, U′ zrepresents the specific value corresponding to the medical data numbered z, ∑ represents the summation symbol, the subscript is z=1, the superscript is Z, and the specific values ​​of the medical data stored in the set N are all modified to Q21;

[0073] The medical information application analysis module is used to perform application analysis on the medical information called by the medical information request sharing terminal, and based on the analysis results, screen and process the called medical information to obtain the target medical information;

[0074] The medical information application analysis module includes an application analysis unit and a medical information screening unit;

[0075] The application analysis unit determines the application object of the medical information called by the medical information request sharing terminal, the application object includes medical decision-making, teaching and scientific research, the determined application object is the target application object, and the target application object is transmitted to the medical information screening unit;

[0076] The medical information screening unit obtains the standardized processing of the called medical information, and based on the obtained information, predicts the matching degree between the called medical information after the standardized processing and each application object, and based on the prediction result, screens the called medical information to obtain the target medical information. The specific method is as follows:

[0077] The ratio between the number of times the medical data in the called medical information is modified and the total number of medical data in the called medical information is calculated to obtain the sharing accuracy of the called medical information, and the difference between the sharing accuracy of the called medical information and the sharing accuracy required by the target application object is calculated. If the difference is within the error range, all the medical data stored in the called medical information are retained, and the called medical information is now the target medical information;

[0078] If the difference is not within the error range, all the modified medical data in the called medical information are filtered out, and the unfiltered called medical information in the called medical information is the target medical information;

[0079] The medical information sharing module analyzes the associated medical information of the target medical information according to the analysis results of the application that calls the medical information, searches for the associated medical information of the target medical information based on the analysis results, and feeds back the target medical information and the found associated medical information to the corresponding medical information request sharing terminal through the cloud server;

[0080] The medical information sharing module includes an analysis unit, a related medical information search unit and a medical information sharing unit;

[0081] The analysis unit analyzes the associated medical information of the target medical information according to the target application object of the called medical information. If the target application object is a hospital terminal, the associated medical information of the target medical information is the historical medical information of the owner of the called medical information. If the target application object is a scientific research terminal and a teaching terminal, the associated medical information of the target medical information is the same type of medical information as the called medical information. Randomly select other medical information in the cloud server. Other medical information refers to medical information other than the called medical information in the cloud server. Calculate the content similarity between the target medical information and the selected medical information. If the calculated content similarity is ≥0.9, the selected medical information is called the same type of medical information as the called medical information.

[0082] The related medical information searching unit searches for related medical information of the target medical information according to the analysis result of the analyzing unit;

[0083] The medical information sharing unit feeds back the target medical information and the found related medical information to the corresponding medical information request sharing terminal through the cloud server.

[0084] An intelligent medical information sharing method based on cloud computing, the method comprising:

[0085] S10: selectively storing the medical information uploaded by the medical information request sharing terminal through the cloud server;

[0086] S20: The cloud server determines the called medical information according to the sharing request information sent by the medical information request sharing terminal, performs data cleaning and data fusion processing on the called medical information according to the accuracy level of each medical device equipped in the hospital to which the called medical information belongs, and performs standardization processing on the called medical information based on the processing result;

[0087] S30: screening and processing the called medical information according to the application object of calling the medical information to obtain the target medical information;

[0088] S40: searching for the associated medical information of the target medical information according to the application object that calls the medical information, and feeding back the target medical information and the found associated medical information to the corresponding medical information request sharing terminal through the cloud server.

[0089] Example 1: Assume that the total number of times the same type of medical information called with the ID number 1 is called is X1=40, and the number of times the same type of medical information called with the ID number 1 is used as electronic medical record data is Y 11 = 20, the number of times the same type of medical information numbered 2 is used as medical imaging data Y 21 = 15, the number of times the same type of medical information with the ID number 1 is used as laboratory data is Y 31= 10, the number of times the same type of medical information with the ID number 1 is used as public health data is Y 41 =8, the number of similar medical information to be uploaded is 1, γ1=γ2=γ3=γ4=0.25, then the sharing coefficient of the medical information to be uploaded is:

[0090] R=(1 / m)*∑[γ1*(Y 1j / X j )+γ2*(Y 2j / X j )+γ3*(Y 3j / X j )+γ4*(Y 4j / X j )]=0.3;

[0091] Assume that the preset range of the sharing coefficient is: 0.8≤sharing coefficient≤1;

[0092] Since 0.3<0.8, the medical information request sharing terminal does not transmit the medical information to be uploaded to the cloud server.

[0093] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0094] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent medical information sharing system based on cloud computing, characterized by: The system includes a cloud server, several medical information request sharing terminals, a medical information standardization processing module, a medical information application analysis module and a medical information sharing module; The cloud server and the medical information request sharing terminal communicate with each other, and the cloud server is used to store the medical information uploaded by the medical information request sharing terminal. The cloud server is also used to search for shared medical information matching the sharing request information according to the sharing request information sent by the medical information request sharing terminal, and the medical information includes electronic medical record data, medical imaging data, laboratory data and public health data; The medical information request sharing terminal is used to upload medical information whose sharing coefficient is within a preset range to the cloud server. The medical information request sharing terminal is also used to call the shared medical information matching the sharing request information. The specific prediction method of the sharing coefficient is: Search for the same type of medical information to be uploaded, and number each of the found medical information. The numbering result is: j = 1, 2, ..., m; m represents the total number, and the number Y of times the medical information with the same type of number j is used as electronic medical record data 1j , the number of times Y acts as medical imaging data 2j , the number of times Y acts as laboratory data 3j , and the number of times Y acts as public health data 4j To obtain; Combined with the total number of times the same type of medical information with number j is called, X j , construct the prediction model R=(1 / m)*∑[γ1*(Y 1j / X j )+γ2*(Y 2j / X j )+γ3*(Y 3j / X j )+γ4*(Y 4j / X j )] predicts the sharing coefficient of the medical information to be uploaded, where γ1, γ2, γ3, and γ4 all represent weight values ​​and γ1+γ2+γ3+γ4=1, ∑ represents the summation symbol, the subscript of ∑ is j=1, and the superscript is m; The medical information standardization processing module is used to perform data cleaning and data fusion processing on the called medical information according to the accuracy level of each medical device equipped in the hospital to which the called medical information belongs, and standardize the called medical information based on the processing results; The medical information standardization processing module includes a medical data cleaning processing unit, a medical data quality assessment unit and a calling medical information standardization processing unit; The medical data cleaning processing unit acquires the historical medical data generated by each medical device to obtain the historical medical data set of each medical device, and cleans the historical medical data set of each medical device according to the reference value of each medical examination index formulated in the hospital to which the medical information belongs and the accuracy level of each medical device, wherein the accuracy level includes the first level, the second level and the third level; The medical data quality assessment unit calculates the ratio between the total number of medical data that has been cleaned but not retained in the historical medical data set and the total number of medical data stored in the historical medical data set to obtain a quality index of the medical data generated by each medical device in the hospital to which the medical information belongs; The called medical information standardization processing unit determines the historical medical data that needs to be processed by data fusion according to the quality index of the medical data generated by each medical device in the hospital to which the called medical information belongs, and performs standardization processing on the called medical information based on the data fusion processing result; The medical information application analysis module is used to perform application analysis on the medical information called by the medical information request sharing terminal, and based on the analysis result, screen and process the called medical information to obtain the target medical information; The medical information sharing module analyzes the related medical information of the target medical information according to the analysis results of the application that calls the medical information, searches for the related medical information of the target medical information based on the analysis results, and feeds back the target medical information and the found related medical information to the corresponding medical information request sharing terminal through the cloud server.

2. The intelligent medical information sharing system based on cloud computing according to claim 1, characterized in that: The specific method for the medical data cleaning processing unit to clean the historical medical data sets of each medical device is: Each medical examination indicator is numbered, and the numbering result is: p=1,2,…,q; q represents the total number of medical examination indicators, and the medical equipment is matched with the medical examination indicators. If the medical examination indicator numbered p comes from the medical equipment numbered i, then the medical equipment numbered i and the medical examination indicator numbered p are successfully matched. If the medical examination indicator numbered p does not come from the medical equipment numbered i, then the medical equipment numbered i and the medical examination indicator numbered p are not successfully matched. When the match is successful, according to the accuracy level of the medical device numbered i, the reference value variation range of the medical examination index numbered p is [a p -f i *0.1,a p +f i *0.1] to determine, randomly select a medical data from the historical medical data set of the medical device numbered i, and determine whether the selected medical data is in [a p -f*0.1,a p +f*0.1], if it is within the range, the selected medical data will not be cleaned, if not, the selected medical data will be cleaned, where a p It means calling the reference value of the medical examination index numbered p formulated by the hospital to which the medical information belongs.

3. The intelligent medical information sharing system based on cloud computing according to claim 2 is characterized by: The specific method of calling the medical information standardization processing unit to perform standardization processing on the called medical information is: The medical equipment equipped in the hospital to which the medical information is called is numbered, and the numbering result is: i=1,2,…,n; n represents the total number of medical equipment equipped in the hospital to which the medical information is called; According to T ip =(a p -f i *0.1)*(1+G i ) and T´ ip =(a p +f i *0.1)*(1-G i ) determines the historical medical data that needs to be processed by data fusion, where G i represents the quality index of medical data generated by medical device number i, T ip Indicates the first reference limit value of the medical examination index numbered p, T´ ip represents the second reference limit value of the medical examination index numbered p, f i Indicates the accuracy level of the medical device numbered i; Determine whether the medical data cleaned and retained in the historical medical data set is within the first set range or the second set range. If so, it is necessary to perform data fusion processing on the corresponding medical data. If not, it is not necessary to perform data fusion processing on the corresponding medical data. The first set range ∈ [a p -f i *0.1,T ip ], the second setting range∈[T´ ip ,a p +f i *0.1]; The medical data within the first set range is put into a set M, and the redundant data in the set M is deleted to obtain a set M´; the medical data within the second set range is put into a set N, and the redundant data in the set N is deleted to obtain a set N´; Calculate the difference between any two medical data stored in the set M´, and let the weights of the two medical data corresponding to the minimum difference be CEILING(r / 2,1), where r represents the total number of medical data stored in the set M´, the CEILING function is an upward rounding function, and 1 represents the rounding cardinality. Then delete the two medical data corresponding to the minimum difference from the set M´ to obtain the set M´1. Repeat the operation until the weights of the medical data stored in the set M´ are all determined; According to Q1=∑{W c *U c *(k c +1) / [∑W c *(k c +1)]} predicts the weighted fusion estimate of the medical data in the set M, where c=1,2,…,C, represents the number corresponding to each medical data stored in the set M´, C represents the total number of medical data stored in the set M´, and W c represents the weight corresponding to the medical data numbered c, k c represents the total number of data that exist in the redundant data deleted from the set M and are the same as the medical data numbered c, U c represents the specific value corresponding to the medical data numbered c, ∑ represents the summation symbol, the subscript is c=1, the superscript is C, and the specific values ​​of the medical data stored in the set M are all modified to Q1; Construct prediction model Q2=∑{W´ z *U´ z *(k´ z +1) / [∑W´ z *(k´ z +1)]} predicts the weighted fusion estimate of the medical data in set N, where z=1,2,…,Z, represents the serial number of each medical data stored in set N´, Z represents the total number of medical data stored in set N´, and W´ z Indicates the weight corresponding to the medical data numbered z, k´ z represents the total number of data that exist in the redundant data deleted from set N and are the same as the medical data numbered z, U´ z It represents the specific value corresponding to the medical data numbered z, ∑ represents the summation symbol, the subscript is z=1, and the superscript is Z. The specific values ​​of the medical data stored in the set N are all modified to Q21.

4. The intelligent medical information sharing system based on cloud computing according to claim 3 is characterized by: The medical information application analysis module includes an application analysis unit and a medical information screening unit; The application analysis unit determines the application object of the medical information called by the medical information request sharing terminal, the application object includes medical decision-making, teaching and scientific research, the determined application object is the target application object, and the target application object is transmitted to the medical information screening unit; The medical information screening unit obtains the standardized processing status of the called medical information, and based on the obtained information, predicts the matching degree between the called medical information after the standardized processing and each application object, and based on the prediction result, screens the called medical information to obtain the target medical information.

5. The intelligent medical information sharing system based on cloud computing according to claim 4 is characterized in that: The specific method for the medical information screening unit to screen and process the called medical information is: The ratio between the number of times the medical data in the called medical information is modified and the total number of medical data in the called medical information is calculated to obtain the sharing accuracy of the called medical information, and the difference between the sharing accuracy of the called medical information and the sharing accuracy required by the target application object is calculated. If the difference is within the error range, all the medical data stored in the called medical information are retained, and the called medical information is now the target medical information; If the difference is not within the error range, all the modified medical data in the called medical information will be filtered out, and the called medical information that has not been filtered out in the called medical information is the target medical information.

6. The intelligent medical information sharing system based on cloud computing according to claim 5 is characterized by: The medical information sharing module includes an analysis unit, a related medical information search unit and a medical information sharing unit; The analysis unit analyzes the associated medical information of the target medical information according to the target application object of the called medical information. If the target application object is a hospital terminal, the associated medical information of the target medical information is the historical medical information of the owner of the called medical information. If the target application object is a scientific research terminal or a teaching terminal, the associated medical information of the target medical information is the same type of medical information as the called medical information. The associated medical information searching unit searches for associated medical information of the target medical information according to the analysis result of the analyzing unit; The medical information sharing unit feeds back the target medical information and the found related medical information to the corresponding medical information request sharing terminal through the cloud server.

7. A cloud computing-based intelligent medical information sharing method applied to the cloud computing-based intelligent medical information sharing system according to any one of claims 1 to 6, characterized in that: The method comprises: S10: selectively storing the medical information uploaded by the medical information request sharing terminal through the cloud server; S20: The cloud server determines the called medical information according to the sharing request information sent by the medical information request sharing terminal, performs data cleaning and data fusion processing on the called medical information according to the accuracy level of each medical device equipped in the hospital to which the called medical information belongs, and performs standardization processing on the called medical information based on the processing result; S30: screening and processing the called medical information according to the application object of calling the medical information to obtain the target medical information; S40: searching for the associated medical information of the target medical information according to the application object that calls the medical information, and feeding back the target medical information and the found associated medical information to the corresponding medical information request sharing terminal through the cloud server.

Images