Medical archive management method and system

Abstract

The invention discloses a medical archive management method and system, relates to the technical field of big data analysis, and generates a comprehensive feature vector set Fp. The method comprises the following steps: obtaining the similarity XS of a historical case and a patient through the feature comparison with the historical case, calculating the feature aggregation degree of the historical case, obtaining the feature concentration degree D, and generating a feature concentration degree associated data set R through the integration of the feature concentration degree D. A tree-shaped association graph is established on the basis, so that a doctor is helped to quickly identify the most relevant historical cases when managing and retrieving the patient archives, and the management efficiency of the medical archives is optimized; particularly, the method has remarkable advantages in overcoming the defects that in existing medical archive management, retrieval efficiency is low, data organization is loose, and patients and historical cases cannot be effectively associated. A doctor can quickly locate historical cases highly matched with the features of the patient, retrieval time is greatly shortened, and the accuracy of personalized medical decision making is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a medical archive management method and system. Background Art

[0002] The medical information system is one of the important infrastructures in the current medical industry. It aims to improve the management and utilization efficiency of medical resources through information technology. The medical record management system is a vital branch responsible for recording and managing patients' medical records. With the continuous accumulation of medical data, simple storage and simple retrieval can no longer meet the needs of modern medicine, especially the refined management needs for individual patient characteristics are becoming more and more important.

[0003] However, in the current medical record management system, most of the patient's files exist in the form of linear data storage, lacking multi-dimensional classification and intelligent analysis tools for different patient characteristics. Existing systems can often only filter data based on a simple single dimension, such as sorting by disease type or medical history time, and for cross-analysis involving multiple dimensions, such as age, gender and duration of illness, the processing capacity of existing systems is limited. When doctors conduct group disease research, they often need to rely on manual or external tools to reprocess the data, which not only takes a lot of time, but also easily leads to data loss or processing errors. In addition, for some patient groups with special disease processes, it is impossible to quickly locate similar case files, which limits the medical team's reference to historical cases when making decisions. Summary of the invention

[0004] In view of the deficiencies of the prior art, the present invention provides a medical archive management method and system, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a medical archive management method and system, comprising the following steps:

[0006] S1. By establishing a communication channel between the hospital registration system and the electronic medical record system, patient information is extracted, including personal information, diagnosis results, examination reports, treatment records and patient complication records, to form a feature vector set Fp;

[0007] S2. Extract the patient type based on the feature vector set Fp, and then compare it with the case characteristics of the same patient type in the historical cases to obtain the similarity XS between the historical cases and the feature vector set Fp, and form a case similarity matrix S;

[0008] S3, classifying the patients by similarity level according to the obtained case similarity matrix S, and establishing the association relationship between the patients and the historical cases in the case similarity matrix S, and generating a classification result set C;

[0009] S4. Analyze the relationship between the patient and the historical cases according to the classification result set C and the similarity matrix S, obtain the feature concentration D by calculating all the historical cases in the classification, and then integrate the feature concentration D to form a feature concentration association data set R;

[0010] S5. Sort the feature concentration correlation data set R, obtain the sorted feature concentration correlation data set R, and establish a tree-like correlation diagram.

[0011] Preferably, said S1 includes S11;

[0012] S11. By establishing a communication channel between the hospital registration system and the electronic medical record system, extract patient information, including personal information, diagnosis results, examination reports, treatment records and patient complication records;

[0013] Among them, personal information includes age A, gender G and medical history MH; diagnosis results include disease diagnosis DIA, blood sugar fluctuation rate BGV and blood pressure BP; treatment records include medication frequency MED and treatment cycle TE; patient complication records include the number of complications CN and illness duration D;

[0014] Among them, medical history MH specifically indicates the length of time since the patient's illness began; disease diagnosis DIA specifically indicates the standardized diagnostic value of the disease; disease duration D specifically indicates the duration of complications;

[0015] Personal information, diagnosis results, examination reports, treatment records and patient complication records are simultaneously dimensionlessly processed and then integrated to form a feature vector set Fp = {A, G, MH, DIA, BGV, BP, MED, TE, CN, D}.

[0016] Preferably, S2 includes S21 and S22;

[0017] S21, extracting patient type information based on the feature vector set Fp, including the disease diagnosis DIA, blood sugar fluctuation rate BGV and the number of complications CN, to form the patient type T of the current patient, and then matching the patient type T with the case type information in the historical case library, wherein the matching is performed by inputting the patient type T as a matching item into the historical case library for retrieval, obtaining historical case samples including the patient type T, and forming a matching historical case feature collection Fhist;

[0018] The historical case feature collection Fhist is specifically a two-dimensional matrix, including several historical case samples. The specific format of the historical case feature collection Fhist is as follows:

[0019]

[0020] Where m represents the total number of historical case samples.

[0021] Preferably, S22, calculate the similarity XS between each case sample and the patient type T of the current patient in the feature vector set Fp according to the acquired historical case feature set Fhist, and combine the current patient type T with several historical case samples in the historical case feature set Fhist to form a case similarity matrix S = {XS i,j};

[0022] The similarity XS is obtained by the following calculation formula:

[0023]

[0024] In the formula, XS i,j Fp represents the similarity between the i-th patient and the j-th historical case sample in the historical case feature set Fhist, i,k represents the kth characteristic parameter of the i-th patient, Fhist j，k represents the kth feature parameter of the jth historical case sample in the historical case feature set Fhist, m represents the total number of features, specifically the length of the feature vector set Fp, α k Represents the weight coefficient of the kth feature parameter.

[0025] Preferably, said S3 includes S31 and S32;

[0026] S31, classifying the patients by similarity level according to the obtained case similarity matrix S, specifically by matching the similarity XS between the patient i and the historical case sample j in the case similarity matrix S with the preset upper threshold SZ and lower threshold XZ of the similarity evaluation, to obtain the association relationship between the patient i and the historical case sample j;

[0027] The association relationship is specifically obtained through the following matching method:

[0028] When the similarity XS i,j When ≥ the upper threshold SZ, the association relationship between patient i and historical case sample j is obtained as a first-level association relationship, and the association level between patient i and historical case sample j is marked as GJ=1;

[0029] When the lower threshold XZ ≤ similarity XS i,jWhen the upper threshold SZ is less than the upper threshold, the association relationship between patient i and historical case sample j is obtained as a secondary association relationship, and the association level GJ between patient i and historical case sample j is marked as 2;

[0030] When the similarity XS i,j When < the lower limit threshold XZ, the association relationship between the patient i and the historical case sample j is obtained as a third-level association relationship, and the association level GJ between the patient i and the historical case sample j is marked as 3.

[0031] Preferably, S32, the historical case samples with correlation level GJ=3 in the historical case feature collection Fhist are eliminated, and the historical case samples with correlation level GJ=1 and correlation level GJ=2 are retained, and then the historical case feature collection Fhist is sorted according to the correlation level GJ, and the historical case feature collection Fhist in list form is obtained, and the historical case feature collection Fhist is cut with the historical case sample with correlation level GJ=1 that appears last in the historical case feature collection Fhist, and divided into the historical case feature collection Fhist1 with correlation level GJ=1 and the historical case feature collection Fhist2 with correlation level GJ=2, forming a classification result set C={Fhist1, Fhist2}.

[0032] Preferably, S4, analyzing the patient's relationship with historical cases according to the classification result set C and the similarity matrix S, and obtaining the feature concentration D={D1, D2} by calculating all historical cases in the classification, and specifically obtaining the feature concentration D1 of the first-level associated historical case feature set Fhist1 and the feature concentration D2 of the second-level associated historical case feature set Fhist2 by comparing the feature vector set Fp of the current patient with the classification result set C;

[0033] Among them, the calculated feature concentration D1 is subscript-associated with the first-level associated historical case feature collection Fhist1, and the calculated feature concentration D2 is subscript-associated with the first-level associated historical case feature collection Fhist2 to form a feature concentration association data set R={R1, R2}, wherein R1 represents the first feature concentration association data set, specifically R1={D1∪Fhist1}; R2 represents the second feature concentration association data set, specifically R2={D2∪Fhist2}.

[0034] Preferably, the feature concentration D1 of the first-level associated historical case feature collection Fhist1 and the feature concentration D2 of the second-level associated historical case feature collection Fhist2 are obtained by the following calculation formula:

[0035]

[0036] Where n1 and n2 represent the total number of historical case samples in the first-level associated historical case feature set Fhist1 and the second-level associated historical case feature set Fhist2, respectively, j represents the jth historical case sample, m is the total number of features, Fhist1 j,w and Fhist2 j,w represents the wth feature value of the jth historical case sample in the first-level associated historical case feature set Fhist1 and the second-level associated historical case feature set Fhist2, respectively. w Represents the wth feature parameter in the feature vector set Fp.

[0037] Preferably, S5, sorting according to the feature concentration association data set R, including using bubble sort to sort the feature concentration D1 and feature concentration D2 in the feature concentration association data set R as a basis, obtaining the sorted feature concentration association data set R to establish a tree association graph, including establishing an association node of the root node according to the sorted feature concentration association data set R, wherein the root node is the patient's feature vector set Fp, and the association node includes a first association node and a second association node;

[0038] The first association node is specifically a first feature concentration association data set R1 in the feature concentration association data set R; the second association node is specifically a second feature concentration association data set R2 in the feature concentration association data set R.

[0039] A medical archive management method and system.

[0040] The present invention provides a medical archive management method and system, which has the following beneficial effects:

[0041] (1) By generating a comprehensive feature vector set Fp. By comparing the features with those of historical cases, the similarity XS between historical cases and patients is obtained, the feature aggregation degree of historical cases is calculated, the feature concentration D is obtained, and the feature concentration association data set R is generated by integrating the feature concentration D. Based on this, a tree-like association diagram is established to help doctors quickly identify the most relevant historical cases when managing and retrieving patient files, optimizing the management efficiency of medical files, especially in solving the shortcomings of low retrieval efficiency, loose data organization, and inability to effectively associate patients with historical cases in existing medical file management. Doctors can quickly locate historical cases that are highly matched with patient characteristics, greatly shortening the retrieval time and improving the accuracy of personalized medical decision-making. At the same time, the establishment of a tree-like association diagram displays the historical cases associated with patients at different levels in a hierarchical structure, providing doctors with an intuitive and orderly file management view, further enhancing the utilization efficiency and pertinence of historical cases.

[0042] (2) By accurately classifying the case similarity matrix S according to the similarity level, the association relationship between patients and historical case samples can be divided into different association levels. The classified historical cases are further sorted according to the association level to generate the classification result set C, and the historical case set is segmented based on the association level to form a clear hierarchical structure, which effectively solves the problem that the traditional medical archive management cannot effectively distinguish the association strength between cases and patients, resulting in too much data and low retrieval efficiency. Through the similarity level classification and the setting of association level GJ, the system can accurately eliminate irrelevant historical cases and ensure that only the cases with the most reference value for patient diagnosis and treatment are retained, thereby significantly improving the utilization and accuracy of the data. At the same time, the hierarchical sorting and cutting mechanism further simplifies the review and management process of historical cases, allowing doctors to quickly locate the most relevant reference files in complex historical cases, optimizing the support for medical decision-making.

[0043] (3) By analyzing the classification result set C and the similarity matrix S, the feature concentration D of the historical cases is further calculated, and the feature concentration is associated with the corresponding historical case feature set to generate the feature concentration association data set R. On this basis, after sorting the feature concentration by bubble sort, the system constructs a tree association diagram based on the patient feature vector set Fp, in which the sorted historical case samples are presented in a hierarchical manner, with the first-level associated historical case samples close to the patient node, and the second-level associated historical case samples are arranged in sequence according to the similarity. This hierarchical structure can intuitively reflect the similarity between different historical cases and patient characteristics, and solves the problem that the traditional medical archive management cannot effectively visualize the correlation between historical cases and patients, resulting in complicated information and difficulty in quickly distinguishing highly associated cases. By constructing a tree association diagram, the system can help doctors intuitively and quickly view historical cases that are highly correlated with patient characteristics based on the sorting results of the feature concentration D, so that doctors can not only see the quantitative results of the similarity, but also directly obtain specific case characteristics, significantly improving the accuracy and efficiency of personalized medical decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of the steps of a medical archive management method of the present invention;

[0045] Figure 2 The figure is a schematic diagram of a medical record management system according to the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] Example 1

[0048] The present invention provides a medical record management method, please refer to Figure 1 , including the following steps:

[0049] S1. By establishing a communication channel between the hospital registration system and the electronic medical record system, patient information is extracted, including personal information, diagnosis results, examination reports, treatment records and patient complication records, to form a feature vector set Fp;

[0050] S2. Extract the patient type based on the feature vector set Fp, and then compare it with the case characteristics of the same patient type in the historical cases to obtain the similarity XS between the historical cases and the feature vector set Fp, and form a case similarity matrix S;

[0051] S3, classifying the patients by similarity level according to the obtained case similarity matrix S, and establishing the association relationship between the patients and the historical cases in the case similarity matrix S, and generating a classification result set C;

[0052] S4. Analyze the relationship between the patient and the historical cases according to the classification result set C and the similarity matrix S, obtain the feature concentration D by calculating all the historical cases in the classification, and then integrate the feature concentration D to form a feature concentration association data set R;

[0053] S5. Sort the feature concentration correlation data set R, obtain the sorted feature concentration correlation data set R, and establish a tree-like correlation diagram.

[0054] In this embodiment, by establishing a communication channel between the hospital registration system and the electronic medical record system, the patient's personal information, diagnosis and examination information, treatment records and patient complications are extracted to generate a comprehensive feature vector set Fp. By comparing the features with the historical cases, the similarity XS between the historical cases and the patients is obtained, and the case similarity matrix S is further generated, providing the patient with an accurate similarity level classification and correlation analysis of the historical cases, and generating a classification result set C. Then, based on the classification result set C and the similarity matrix S, the feature aggregation degree of the historical cases is calculated to obtain the feature concentration D, and the feature concentration association data set R is generated by integrating the feature concentration D. By sorting the feature concentration association data set R and establishing a tree association graph based on this, it helps doctors quickly identify the most relevant historical cases when managing and retrieving patient files, optimizes the management efficiency of medical files, and especially shows significant advantages in solving the shortcomings of low retrieval efficiency, loose data organization and inability to effectively associate patients with historical cases in existing medical file management. By calculating and analyzing the feature vector set Fp and feature concentration D, doctors can quickly locate historical cases that are highly matched with patient characteristics, greatly shortening the search time and improving the accuracy of personalized medical decision-making. At the same time, the establishment of a tree-like association diagram displays the historical cases associated with patients at different levels in a hierarchical structure, providing doctors with an intuitive and orderly archive management view, further enhancing the efficiency and pertinence of the use of historical cases.

[0055] Example 2

[0056] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the S1 includes S11;

[0057] S11. By establishing a communication channel between the hospital registration system and the electronic medical record system, extract patient information, including personal information, diagnosis results, examination reports, treatment records and patient complication records;

[0058] Among them, personal information includes age A, gender G and medical history MH; diagnosis results include disease diagnosis DIA, blood sugar fluctuation rate BGV and blood pressure BP; treatment records include medication frequency MED and treatment cycle TE; patient complication records include the number of complications CN and illness duration D;

[0059] Among them, medical history MH specifically indicates the length of time since the patient's illness began; symptom diagnosis DIA specifically indicates the standardized diagnostic value of the symptom, which can be classified according to the severity of the disease, such as 0 for no symptoms, 1 for mild, 2 for moderate, and 3 for severe; illness duration D specifically indicates the duration of complications;

[0060] Personal information, diagnosis results, examination reports, treatment records and patient complication records are simultaneously dimensionlessly processed and then integrated to form a feature vector set Fp = {A, G, MH, DIA, BGV, BP, MED, TE, CN, D}.

[0061] The S2 includes S21 and S22;

[0062] S21, extracting patient type information based on the feature vector set Fp, including the disease diagnosis DIA, blood sugar fluctuation rate BGV and the number of complications CN, to form the patient type T of the current patient, and then matching the patient type T with the case type information in the historical case library, wherein the matching is performed by inputting the patient type T as a matching item into the historical case library for retrieval, obtaining historical case samples including the patient type T, and forming a matching historical case feature collection Fhist;

[0063] The historical case feature collection Fhist is specifically a two-dimensional matrix, including several historical case samples. The specific format of the historical case feature collection Fhist is as follows:

[0064]

[0065] Where m represents the total number of historical case samples.

[0066] S22, calculate the similarity XS between each case sample and the patient type T of the current patient in the feature vector set Fp according to the acquired historical case feature set Fhist, and combine the current patient type T with several historical case samples in the historical case feature set Fhist to form a case similarity matrix S = {XS i,j};

[0067] The similarity XS is obtained by the following calculation formula:

[0068]

[0069] In the formula, XS i,j Fp represents the similarity between the i-th patient and the j-th historical case sample in the historical case feature set Fhist, i,k represents the kth characteristic parameter of the i-th patient, Fhist j，k represents the kth feature parameter of the jth historical case sample in the historical case feature set Fhist, m represents the total number of features, specifically the length of the feature vector set Fp, α k Represents the weight coefficient of the kth feature parameter.

[0070] In this embodiment, by extracting the patient's personal information, diagnosis results, examination reports, treatment records, and patient complication records, and performing dimensionless processing on all data, they are integrated into a feature vector set Fp. On this basis, the patient's patient type T is extracted and generated, and by matching the patient type with the historical case feature collection Fhist in the historical case library, accurate and efficient historical case retrieval is achieved. By calculating the similarity XS between each historical case sample and the patient's patient type, a case similarity matrix S is generated, which optimizes the process of formulating personalized treatment plans. In addition, more accurate historical case stratification can be achieved, which significantly improves the management efficiency of medical archives and promotes the precise development of personalized diagnosis and treatment.

[0071] Example 3

[0072] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S3 includes S31 and S32;

[0073] S31, classifying the patients by similarity level according to the obtained case similarity matrix S, specifically by matching the similarity XS between the patient i and the historical case sample j in the case similarity matrix S with the preset upper threshold SZ and lower threshold XZ of the similarity evaluation, to obtain the association relationship between the patient i and the historical case sample j;

[0074] The association relationship is specifically obtained through the following matching method:

[0075] When the similarity XS i,j When ≥ the upper threshold SZ, the association relationship between patient i and historical case sample j is obtained as a first-level association relationship, and the association level between patient i and historical case sample j is marked as GJ=1;

[0076] When the lower threshold XZ ≤ similarity XS i,j When the upper threshold SZ is less than the upper threshold, the association relationship between patient i and historical case sample j is obtained as a secondary association relationship, and the association level GJ between patient i and historical case sample j is marked as 2;

[0077] When the similarity XS i,j When < the lower limit threshold XZ, the association relationship between the patient i and the historical case sample j is obtained as a third-level association relationship, and the association level GJ between the patient i and the historical case sample j is marked as 3.

[0078] S32. Eliminate the historical case samples with correlation level GJ=3 in the historical case feature collection Fhist, retain the historical case samples with correlation level GJ=1 and correlation level GJ=2, and then sort the historical case feature collection Fhist according to the correlation level GJ to obtain the historical case feature collection Fhist in list form, and cut the historical case feature collection Fhist with the historical case sample with correlation level GJ=1 that appears last in the historical case feature collection Fhist into the historical case feature collection Fhist1 with correlation level GJ=1 and the historical case feature collection Fhist2 with correlation level GJ=2, forming the classification result set C={Fhist1, Fhist2}.

[0079] In this embodiment, by accurately classifying the similarity level of the case similarity matrix S, the association relationship between the patient and the historical case sample can be divided into different association levels, and each historical case sample can be classified according to the upper threshold SZ and the lower threshold XZ of the similarity evaluation. Through a clear classification strategy, the system divides highly related historical cases into first-level association relationships, second-related cases into second-level association relationships, and eliminates case samples with weak association with patients, thereby optimizing the screening process of historical cases. Subsequently, the system further sorts the classified historical cases according to the association level, generates a classification result set C, and divides the historical case set based on the association level to form a clear hierarchical structure, effectively solving the problem that the traditional medical archive management cannot effectively distinguish the association strength between cases and patients, resulting in excessively redundant data and low retrieval efficiency. Through the similarity level classification and the setting of the association level GJ, the system can accurately eliminate insignificant historical cases, ensuring that only the cases with the most reference value for patient diagnosis and treatment are retained, thereby significantly improving the utilization and accuracy of the data. At the same time, the hierarchical sorting and cutting mechanism further simplifies the process of reviewing and managing historical cases, allowing doctors to quickly locate the most relevant reference files among complex historical cases, thereby optimizing support for medical decision-making.

[0080] Example 4

[0081] This embodiment is explained in Example 1, please refer to Figure 1 Specifically: S4, according to the classification result set C and the similarity matrix S, analyze the patient's relationship with the historical cases, and obtain the feature concentration D = {D1, D2} by calculating all the historical cases in the classification. Specifically, by comparing the feature vector set Fp of the current patient with the classification result set C, the feature concentration D1 of the first-level associated historical case feature set Fhist1 and the feature concentration D2 of the second-level associated historical case feature set Fhist2 are obtained;

[0082] Among them, the calculated feature concentration D1 is subscript-associated with the first-level associated historical case feature collection Fhist1, and the calculated feature concentration D2 is subscript-associated with the first-level associated historical case feature collection Fhist2 to form a feature concentration association data set R={R1, R2}, wherein R1 represents the first feature concentration association data set, specifically R1={D1∪Fhist1}; R2 represents the second feature concentration association data set, specifically R2={D2∪Fhist2}.

[0083] The feature concentration D1 of the first-level associated historical case feature collection Fhist1 and the feature concentration D2 of the second-level associated historical case feature collection Fhist2 are obtained by the following calculation formula:

[0084]

[0085] Where n1 and n2 represent the total number of historical case samples in the first-level associated historical case feature set Fhist1 and the second-level associated historical case feature set Fhist2, respectively, j represents the jth historical case sample, m is the total number of features, Fhist1 j,w and Fhist2 j,w represents the wth feature value of the jth historical case sample in the first-level associated historical case feature set Fhist1 and the second-level associated historical case feature set Fhist2, respectively. w Represents the wth feature parameter in the feature vector set Fp.

[0086] Among them, S5, sorting according to the feature concentration association data set R, including using bubble sort to sort the feature concentration D1 and feature concentration D2 in the feature concentration association data set R as the basis, obtaining the sorted feature concentration association data set R to establish a tree association graph, including establishing an association node of the root node according to the sorted feature concentration association data set R, wherein the root node is the patient's feature vector set Fp, and the association node includes a first association node and a second association node;

[0087] The first association node is specifically a first feature concentration association data set R1 in the feature concentration association data set R; the second association node is specifically a second feature concentration association data set R2 in the feature concentration association data set R;

[0088] The first associated node represents the historical case sample in the sorted first-level associated historical case set Fhist1. According to the feature concentration D1 after bubble sorting j The sorting result, feature concentration D1 jHistorical cases with lower moderate scores are ranked at the upper level of the tree, indicating that they have a higher similarity with the patient's characteristics; each first-association node contains two key pieces of information: feature concentration D1 j And the corresponding historical case feature vector Fhist1 j ;

[0089] The second associated node represents the historical case samples in the sorted secondary associated historical case set Fhist2. According to the feature concentration D2 after bubble sorting j The sorting result, feature concentration D2 j Samples with smaller degree are close to the first-level associated nodes, and the feature concentration is D2 j Larger samples are ranked further away; each second-related node also contains feature concentration D2 j And the corresponding historical case feature vector Fhist2 j ;

[0090] In this embodiment, by analyzing the classification result set C and the similarity matrix S, the feature concentration D of the historical cases is further calculated, and the feature concentration is associated with the corresponding historical case feature collection to generate a feature concentration association data set R. On this basis, after sorting the feature concentration by bubble sorting, the system constructs a tree association diagram based on the patient feature vector set Fp, in which the sorted historical case samples are presented in a hierarchical manner, the first-level associated historical case samples are close to the patient node, and the second-level associated historical case samples are arranged in sequence according to the similarity. This hierarchical structure can intuitively reflect the similarity between different historical cases and patient characteristics, and solves the problem that the correlation between historical cases and patients cannot be effectively visualized in traditional medical archive management, resulting in complicated information and difficulty in quickly distinguishing highly associated cases. By constructing a tree association diagram, the system can help doctors intuitively and quickly view historical cases that are highly related to patient characteristics based on the sorting results of the feature concentration D, so that doctors can not only see the quantitative results of the similarity, but also directly obtain specific case characteristics, significantly improving the accuracy and efficiency of personalized medical decision-making.

[0091] Example 5

[0092] A medical records management system, please refer to Figure 2 ,Specifically: it includes vector acquisition module, similarity analysis module, classification ,association module, concentration evaluation module and visualization module;

[0093] The vector acquisition unit extracts patient personal information, diagnosis and examination information, treatment records, and patient progression and complications by establishing a communication channel between the hospital registration system and the electronic medical record system to form a feature vector set Fp;

[0094] The similarity analysis module extracts the patient type based on the feature vector set Fp, and then compares it with the case characteristics of the same patient type in the historical cases to obtain the similarity XS between the historical cases and the feature vector set Fp, forming a case similarity matrix S;

[0095] The classification association module classifies the patients by similarity level according to the acquired case similarity matrix S, and establishes an association relationship between the patients and the historical cases in the case similarity matrix S, and generates a classification result set C;

[0096] The concentration evaluation module analyzes the patient's relationship with the historical cases according to the classification result set C and the similarity matrix S, obtains the feature concentration D by calculating all the historical cases in the classification, and then integrates the feature concentration D to form a feature concentration association data set R;

[0097] The visualization module sorts the feature concentration correlation data set R, obtains the sorted feature concentration correlation data set R, and establishes a tree-like correlation diagram.

[0098] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A medical records management method, characterized in that: The following steps are involved: S1. By establishing a communication channel between the hospital registration system and the electronic medical record system, extract patient information, including personal information, diagnosis results, examination reports, treatment records and patient complication records. Form the feature vector set Fp; S2. Extract the patient type based on the feature vector set Fp, and then compare it with the case characteristics of the same patient type in the historical cases to obtain the similarity XS between the historical cases and the feature vector set Fp, and form a case similarity matrix S; S3, classifying the patients by similarity level according to the obtained case similarity matrix S, and establishing the association relationship between the patients and the historical cases in the case similarity matrix S, and generating a classification result set C; S4. Analyze the patient's relationship with historical cases based on the classification result set C and the similarity matrix S. Obtain the feature concentration D by calculating all historical cases in the classification, and then integrate the feature concentration D. Composition feature concentration correlation data set R; S5. Sort the feature concentration correlation data set R, obtain the sorted feature concentration correlation data set R, and establish a tree-like correlation diagram.

2. A medical record management method according to claim 1, characterized in that: Said S1 includes S11; S11. By establishing a communication channel between the hospital registration system and the electronic medical record system, extract patient information, including personal information, diagnosis results, examination reports, treatment records and patient complication records; Among them, personal information includes age A, gender G and medical history MH; diagnosis results include disease diagnosis DIA, blood sugar fluctuation rate BGV and blood pressure BP; treatment records include medication frequency MED and treatment cycle TE; patient complication records include the number of complications CN and illness duration D; Among them, medical history MH specifically indicates the length of time since the patient's illness began; disease diagnosis DIA specifically indicates the standardized diagnostic value of the disease; disease duration D specifically indicates the duration of complications; Personal information, diagnosis results, examination reports, treatment records and patient complication records are simultaneously dimensionlessly processed and then integrated to form a feature vector set Fp = {A, G, MH, DIA, BGV, BP, MED, TE, CN, D}.

3. A medical record management method according to claim 1, characterized in that: The S2 includes S21 and S22; S21, extracting patient type information based on the feature vector set Fp, including the disease diagnosis DIA, blood sugar fluctuation rate BGV and the number of complications CN, to form the patient type T of the current patient, and then matching the patient type T with the case type information in the historical case library, wherein the matching is performed by inputting the patient type T as a matching item into the historical case library for retrieval, obtaining historical case samples including the patient type T, and forming a matching historical case feature collection Fhist; The historical case feature collection Fhist is specifically a two-dimensional matrix, including several historical case samples. The specific format of the historical case feature collection Fhist is as follows: Where m represents the total number of historical case samples.

4. A medical record management method according to claim 3, characterized in that: S22, calculate the similarity XS between each case sample and the patient type T of the current patient in the feature vector set Fp according to the acquired historical case feature set Fhist, and combine the current patient type T with several historical case samples in the historical case feature set Fhist to form a case similarity matrix S = {XS i,j }; The similarity XS is obtained by the following calculation formula: In the formula, XS i,j Fp represents the similarity between the i-th patient and the j-th historical case sample in the historical case feature set Fhist, i,k represents the kth characteristic parameter of the i-th patient, Fhist j，k represents the kth feature parameter of the jth historical case sample in the historical case feature set Fhist, m represents the total number of features, specifically the length of the feature vector set Fp, α k Represents the weight coefficient of the kth feature parameter.

5. A medical record management method according to claim 4, characterized in that: The S3 includes S31 and S32; S31, classifying the patients by similarity level according to the obtained case similarity matrix S, specifically by matching the similarity XS between the patient i and the historical case sample j in the case similarity matrix S with the preset upper threshold SZ and lower threshold XZ of the similarity evaluation, to obtain the association relationship between the patient i and the historical case sample j; The association relationship is specifically obtained through the following matching method: When the similarity XS i,j When ≥ the upper threshold SZ, the association relationship between patient i and historical case sample j is obtained as a first-level association relationship, and the association level between patient i and historical case sample j is marked as GJ=1; When the lower threshold XZ ≤ similarity XS i,j When the upper threshold SZ is less than the upper threshold, the association relationship between patient i and historical case sample j is obtained as a secondary association relationship, and the association level GJ between patient i and historical case sample j is marked as 2; When the similarity XS i,j When < the lower limit threshold XZ, the association relationship between the patient i and the historical case sample j is obtained as a third-level association relationship, and the association level GJ between the patient i and the historical case sample j is marked as 3.

6. A medical record management method according to claim 5, characterized in that: S32. Eliminate the historical case samples with correlation level GJ=3 in the historical case feature collection Fhist, retain the historical case samples with correlation level GJ=1 and correlation level GJ=2, and then sort the historical case feature collection Fhist according to the correlation level GJ to obtain the historical case feature collection Fhist in list form, and cut the historical case feature collection Fhist with the historical case sample with correlation level GJ=1 that appears last in the historical case feature collection Fhist into the historical case feature collection Fhist1 with correlation level GJ=1 and the historical case feature collection Fhist2 with correlation level GJ=2, forming the classification result set C={Fhist1, Fhist2}.

7. A medical record management method according to claim 6, characterized in that: in, S4. Analyze the patient's relationship with historical cases based on the classification result set C and the similarity matrix S, and obtain the feature concentration D = {D1, D2} by calculating all historical cases in the classification. Specifically, the feature vector set Fp of the current patient is compared with the classification result set C to obtain the feature concentration D1 of the first-level associated historical case feature set Fhist1 and the feature concentration D2 of the second-level associated historical case feature set Fhist2; Among them, the calculated feature concentration D1 is subscript-associated with the first-level associated historical case feature collection Fhist1, and the calculated feature concentration D2 is subscript-associated with the first-level associated historical case feature collection Fhist2 to form a feature concentration association data set R={R1, R2}, wherein R1 represents the first feature concentration association data set, specifically R1={D1∪Fhist1}; R2 represents the second feature concentration association data set, specifically R2={D2∪Fhist2}.

8. A medical record management method according to claim 7, characterized in that: The feature concentration D1 of the first-level associated historical case feature collection Fhist1 and the feature concentration D2 of the second-level associated historical case feature collection Fhist2 are obtained by the following calculation formula: Where n1 and n2 represent the total number of historical case samples in the first-level associated historical case feature set Fhist1 and the second-level associated historical case feature set Fhist2, respectively, j represents the jth historical case sample, m is the total number of features, Fhist1 j,w and Fhist2 j,w represents the wth feature value of the jth historical case sample in the first-level associated historical case feature set Fhist1 and the second-level associated historical case feature set Fhist2, respectively. w Represents the wth feature parameter in the feature vector set Fp.

9. A medical record management method according to claim 1, characterized in that: in, S5, sorting the feature concentration association data set R, including using bubble sort to sort the feature concentration D1 and feature concentration D2 in the feature concentration association data set R as a basis, obtaining the sorted feature concentration association data set R to establish a tree association graph, including establishing association nodes of the root node according to the sorted feature concentration association data set R, wherein the root node is the patient's feature vector set Fp, and the association nodes include a first association node and a second association node; The first association node is specifically a first feature concentration association data set R1 in the feature concentration association data set R; the second association node is specifically a second feature concentration association data set R2 in the feature concentration association data set R.

10. A medical record management system, applied to a medical record management method according to any one of claims 1 to 9, characterized in that: It includes vector acquisition module, similarity analysis module, classification association module, concentration evaluation module and visualization module; The vector acquisition unit extracts patient personal information, diagnosis and examination information, treatment records, and patient progression and complications by establishing a communication channel between the hospital registration system and the electronic medical record system. Form the feature vector set Fp; The similarity analysis module extracts the patient type based on the feature vector set Fp, and then compares it with the case characteristics of the same patient type in the historical cases to obtain the similarity XS between the historical cases and the feature vector set Fp, forming a case similarity matrix S; The classification association module classifies the patients by similarity level according to the acquired case similarity matrix S, and establishes an association relationship between the patients and the historical cases in the case similarity matrix S, and generates a classification result set C; The concentration evaluation module analyzes the patient's relationship with the historical cases according to the classification result set C and the similarity matrix S, obtains the feature concentration D by calculating all the historical cases in the classification, and then integrates the feature concentration D. Composition feature concentration correlation data set R; The visualization module sorts the feature concentration correlation data set R, obtains the sorted feature concentration correlation data set R, and establishes a tree-like correlation diagram.

Images