Multi-center special disease database system construction method

Abstract

The invention discloses a multi-center special disease database system construction method, which comprises the following steps: S1, establishing a data collection center, and acquiring detection and treatment text data of a plurality of hospitals on the same type of special diseases through the data collection center; s2, establishing an evaluation objective function by taking a treatment result in the treatment text data as a guide and selecting a cure rate, a treatment cycle and other treatment results as standards for the same type of special diseases; s3, selecting treatment text data corresponding to the optimal treatment result as treatment standard data according to the established evaluation objective function, and storing the treatment text data in a database; s4, taking detection text data corresponding to the treatment text data as detection reference file data of the same type of special diseases, and storing the detection text data into a database; and S5, carrying out statistics on the detection reference file data of the same type of special diseases, summarizing a detection reference data value range of the same type of special diseases, and issuing the detection reference data value range to a hospital terminal for a plurality of hospitals to detect reference indexes of the same type of special diseases.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical record data classification and analysis, and specifically relates to a method for constructing a multi-center disease-specific database system. Background Art

[0002] Hospitals face numerous challenges in disease-specific management and clinical decision-making. Standardized, accurate disease-specific data provides hospitals with convenient disease-specific management tools, helping doctors quickly understand a patient's condition, treatment plan, and prognosis. Different medical institutions and research teams use varying data standards and formats, resulting in insufficient data standardization. This makes data comparison and integration difficult, reducing database quality and usability. A standardized disease-specific database can serve as the foundation and basis for clinical decision support systems, providing doctors with scientific, personalized diagnosis and treatment plans and guidance, thereby improving healthcare quality and patient satisfaction.

[0003] The establishment of specialized disease databases among existing hospitals lacks unified standards for judging specialized disease data, resulting in a lack of effective communication of specialized disease data among different hospitals, affecting the effective development of specialized disease treatment effects. Summary of the Invention

[0004] In order to solve the problem that the establishment of specialized disease databases among existing hospitals lacks unified standards for judging specialized disease data, resulting in a lack of effective communication of specialized disease data among different hospitals, the present invention provides a method for constructing a multi-center specialized disease database system.

[0005] In order to achieve the above technical objectives, the technical solutions adopted by the present invention are as follows:

[0006] A method for constructing a multi-center disease-specific database system, comprising the steps of:

[0007] S1. Establish a data collection center to obtain text data on the testing and treatment of the same type of specialized diseases from multiple hospitals;

[0008] S2. Using the treatment results in the treatment text data as a guide, for the same type of disease, select cure rate, treatment cycle and other treatment results as criteria to establish an evaluation objective function;

[0009] S3. Obtain the optimal treatment results of the same type of treatment in each hospital based on the established evaluation objective function, and select the treatment text data corresponding to the optimal treatment results as treatment standard data and store them in the database;

[0010] S4. Storing the test text data corresponding to the treatment text data as test reference file data for the same type of disease in the database;

[0011] S5. Collect statistics on the detection reference file data of the same type of special disease, summarize the detection reference data value range of the same type of special disease, and send the detection reference data value range to the hospital terminal to provide reference indicators for multiple hospitals to detect the same type of special disease.

[0012] Furthermore, when the data collection center obtains the same type of special disease in step S1, it will use the string matching method to query multiple hospitals to match the names of the same type of special disease with each other, and then query the indexed detection and treatment text data in each hospital database based on the names of the same type of special disease.

[0013] Furthermore, the string matching method includes constructing a partial matching table and KMP string matching;

[0014] Constructing a partial matching table to store a data group consisting of key fields for querying the same type of special disease by the data collection center;

[0015] KMP string matching is used as the key field to query the indexed test and treatment text data in each hospital database.

[0016] Furthermore, the detailed steps of constructing the partial matching table include:

[0017] Build a partial match table for the key field and return an array that records the maximum prefix and suffix lengths of the substring before each position;

[0018] Initialize prefix length;

[0019] Traverse the pattern string, starting from the second character;

[0020] If the characters do not match, update the prefix length;

[0021] If the characters match, the prefix length is increased by 1;

[0022] Update the key field partial match table.

[0023] Furthermore, the detailed steps of KMP string matching include:

[0024] Search for a key field in a text string and return the starting position of the key field in the text. If not found, return -1.

[0025] Construct a partial matching table of key fields for the same type of disease;

[0026] Iterate over a text string;

[0027] If the characters do not match, update the prefix length;

[0028] If the characters match, the prefix length is increased by 1;

[0029] If the prefix length is equal to the key field string length, it means the match is successful and the starting position is returned.

[0030] Furthermore, establishing the evaluation objective function as a single-objective optimization function or a multi-objective optimization function;

[0031] The single-objective optimization function selects any one of the objectives of cure rate, treatment cycle and other treatment results as the optimal solution;

[0032] The multi-objective optimization function selects cure rate, treatment cycle and other treatment results as the optimal solution for objective function optimization.

[0033] Furthermore, the multi-objective optimization function is expressed as:

[0034] max f(x)=(f1(x),f2(x),f3(x))

[0035] x=(x1,x2,...,x n ) is the decision variable vector, f i (x) is the [i]th objective function, f1(x), f2(x), and f3(x) correspond to the cure rate, treatment cycle, and other treatment outcomes, respectively; f1(x) and f3(x) correspond to the cure rate and other treatment outcomes, which are positively correlated with the multi-objective optimization function, and the results obtained are positive numbers; f2(x) corresponds to the treatment cycle, which is negatively correlated with the multi-objective optimization function. The results obtained are multiplied by negative 1 and then arranged to obtain the optimal value of the target optimization result.

[0036] Furthermore, in step S3, in order to comprehensively consider the impact of the cure rate, treatment cycle and other treatment results of the special disease on the evaluation results, the weighted coefficient method is used to comprehensively calculate the optimal treatment results of the same type in different hospitals.

[0037] Furthermore, the weighted coefficient method is calculated as follows:

[0038] Weighted sum = a*x+b*y+c*z,

[0039] Among them, a, b and c represent the cure rate, treatment cycle and other treatment results respectively; x, y and z correspond to the corresponding coefficients of a, b and c, and x, y and z are the experts' evaluation of the importance of the cure rate, treatment cycle and other treatment results in the entire weighted sum. The sum of x, y and z is 1.

[0040] Furthermore, other treatment outcomes include minimizing the degree of harm to the human body during the treatment process, simplifying the treatment process, and reducing treatment costs.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] By establishing a data collection center between multiple hospitals, we can obtain textual data on the detection and treatment of the same type of specialized diseases. Guided by treatment results, we select cure rate, treatment cycle, and other treatment results as criteria to establish an evaluation objective function for the same type of specialized diseases. We then solve for the optimal treatment outcome for the same type of disease and store the corresponding textual data in the database as standard treatment data. This data is then distributed to hospital terminals, providing reference indicators for multiple hospitals testing the same type of specialized diseases. This unifies the criteria for determining specialized disease data across existing hospital databases, ensuring effective communication of specialized disease data between hospitals and improving the effective development of specialized disease treatment outcomes. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is an overall flow chart of a method for constructing a multi-center disease-specific database system in an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and drawings. The contents mentioned in the embodiments are not intended to limit the present invention.

[0045] like Figure 1 As shown, this embodiment provides a method for constructing a multi-center disease database system, including the following steps:

[0046] S1. Establish a data collection center to obtain text data on the testing and treatment of the same type of specialized diseases from multiple hospitals;

[0047] S2. Using the treatment results in the treatment text data as a guide, for the same type of disease, select cure rate, treatment cycle and other treatment results as criteria to establish an evaluation objective function;

[0048] S3. Obtain the optimal treatment results of the same type of treatment in each hospital based on the established evaluation objective function, and select the treatment text data corresponding to the optimal treatment results as treatment standard data and store them in the database;

[0049] S4. Storing the test text data corresponding to the treatment text data as test reference file data for the same type of disease in the database;

[0050] S5. Collect statistics on the detection reference file data of the same type of special disease, summarize the detection reference data value range of the same type of special disease, and send the detection reference data value range to the hospital terminal to provide reference indicators for multiple hospitals to detect the same type of special disease.

[0051] When the data collection center obtains the same type of special disease in step S1, it will use the string matching method to query multiple hospitals to match the names of the same type of special disease, and then query the indexed detection and treatment text data in each hospital database based on the names of the same type of special disease.

[0052] The string matching method includes building a partial matching table and KMP string matching;

[0053] Constructing a partial matching table to store a data group consisting of key fields for querying the same type of special disease by the data collection center;

[0054] KMP string matching is used as the key field to query the indexed test and treatment text data in each hospital database.

[0055] The detailed steps to build a partial match table include:

[0056] Build a partial match table for the key field and return an array that records the maximum prefix and suffix lengths of the substring before each position;

[0057] Initialize prefix length;

[0058] Traverse the pattern string, starting from the second character;

[0059] If the characters do not match, update the prefix length;

[0060] If the characters match, the prefix length is increased by 1;

[0061] Update the key field partial match table.

[0062] The detailed steps of KMP string matching include:

[0063] Search for a key field in a text string and return the starting position of the key field in the text. If not found, return -1.

[0064] Construct a partial matching table of key fields for the same type of disease;

[0065] Iterate over a text string;

[0066] If the characters do not match, update the prefix length;

[0067] If the characters match, the prefix length is increased by 1;

[0068] If the prefix length is equal to the key field string length, it means the match is successful and the starting position is returned.

[0069] Establishing the evaluation objective function as a single-objective optimization function or a multi-objective optimization function;

[0070] The single-objective optimization function selects any one of the objectives of cure rate, treatment cycle and other treatment results as the optimal solution;

[0071] The multi-objective optimization function selects cure rate, treatment cycle and other treatment results as the optimal solution for objective function optimization.

[0072] The multi-objective optimization function is expressed as:

[0073] max f(x)=(f1(x),f2(x),f3(x))

[0074] x=(x1,x2,...,x n ) is the decision variable vector, f i (x) is the [i]th objective function, f1(x), f2(x), and f3(x) correspond to the cure rate, treatment cycle, and other treatment outcomes, respectively; f1(x) and f3(x) correspond to the cure rate and other treatment outcomes, which are positively correlated with the multi-objective optimization function, and the results obtained are positive numbers; f2(x) corresponds to the treatment cycle, which is negatively correlated with the multi-objective optimization function. The results obtained are multiplied by negative 1 and then arranged to obtain the optimal value of the target optimization result.

[0075] In step S3, in order to comprehensively consider the impact of the cure rate, treatment cycle and other treatment results of the special disease on the evaluation results, the weighted coefficient method is used to comprehensively calculate the optimal treatment results of the same type in different hospitals.

[0076] Calculation formula of weighted coefficient method:

[0077] Weighted sum = a*x+b*y+c*z,

[0078] Among them, a, b and c represent the cure rate, treatment cycle and other treatment results respectively; x, y and z correspond to the corresponding coefficients of a, b and c, and x, y and z are the experts' evaluation of the importance of the cure rate, treatment cycle and other treatment results in the entire weighted sum. The sum of x, y and z is 1.

[0079] Other treatment outcomes include minimizing the harm of the treatment process to the human body, simplifying the treatment process, and reducing the cost of treatment.

[0080] Compared with the prior art, the present invention has the following beneficial effects:

[0081] By establishing a data collection center between multiple hospitals, we can obtain textual data on the detection and treatment of the same type of specialized diseases. Guided by treatment results, we select cure rate, treatment cycle, and other treatment results as criteria to establish an evaluation objective function for the same type of specialized diseases. We then solve for the optimal treatment outcome for the same type of disease and store the corresponding textual data in the database as standard treatment data. This data is then distributed to hospital terminals, providing reference indicators for multiple hospitals testing the same type of specialized diseases. This unifies the criteria for determining specialized disease data across existing hospital databases, ensuring effective communication of specialized disease data between hospitals and improving the effective development of specialized disease treatment outcomes.

[0082] The above describes in detail the method for constructing a multi-center disease-specific database system provided by this application. The description of the specific embodiments is only intended to help understand the method and core concept of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and such improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A method for constructing a multi-center disease database system, characterized in that: Including steps: S1. Establish a data collection center to obtain text data on the testing and treatment of the same type of specialized diseases from multiple hospitals; S2. Using the treatment results in the treatment text data as a guide, for the same type of disease, select cure rate, treatment cycle and other treatment results as criteria to establish an evaluation objective function; S3. Obtain the optimal treatment results of the same type of treatment in each hospital based on the established evaluation objective function, and select the treatment text data corresponding to the optimal treatment results as treatment standard data and store them in the database; S4. Storing the test text data corresponding to the treatment text data as test reference file data for the same type of disease in the database; S5. Collect statistics on the detection reference file data of the same type of special disease, summarize the detection reference data value range of the same type of special disease, and send the detection reference data value range to the hospital terminal to provide reference indicators for multiple hospitals to detect the same type of special disease.

2. A method for constructing a multi-center disease database system according to claim 1, characterized in that: When the data collection center obtains the same type of special disease in step S1, it will use the string matching method to query multiple hospitals to match the names of the same type of special disease, and then query the indexed detection and treatment text data in each hospital database based on the names of the same type of special disease.

3. The method for constructing a multi-center disease database system according to claim 2, characterized in that: The string matching method includes building a partial matching table and KMP string matching; Constructing a partial matching table to store a data group consisting of key fields for querying the same type of special disease by the data collection center; KMP string matching is used as the key field to query the indexed test and treatment text data in each hospital database.

4. The method for constructing a multi-center disease database system according to claim 3, characterized in that: The detailed steps to build a partial match table include: Build a partial match table for the key field and return an array that records the maximum prefix and suffix lengths of the substring before each position; Initialize prefix length; Traverse the pattern string, starting from the second character; If the characters do not match, update the prefix length; If the characters match, the prefix length is increased by 1; Update the key field partial match table.

5. The method for constructing a multi-center disease-specific database system according to claim 4, characterized in that: The detailed steps of KMP string matching include: Search for a key field in a text string and return the starting position of the key field in the text. If not found, return -1. Construct a partial matching table of key fields for the same type of disease; Iterate over a text string; If the characters do not match, update the prefix length; If the characters match, the prefix length is increased by 1; If the prefix length is equal to the key field string length, it means the match is successful and the starting position is returned.

6. A method for constructing a multi-center disease-specific database system according to claim 5, characterized in that: Establishing the evaluation objective function as a single-objective optimization function or a multi-objective optimization function; The single-objective optimization function selects any one of the objectives of cure rate, treatment cycle and other treatment results as the optimal solution; The multi-objective optimization function selects cure rate, treatment cycle and other treatment results as the optimal solution for objective function optimization.

7. The method for constructing a multi-center disease-specific database system according to claim 6, characterized in that: The multi-objective optimization function is expressed as: maxf(x)=(f1(x),f2(x),f3(x)) x=(x1,x2,...,x n ) is the decision variable vector, f i (x) is the [i]th objective function, f1(x), f2(x), and f3(x) correspond to the cure rate, treatment cycle, and other treatment outcomes, respectively; f1(x) and f3(x) correspond to the cure rate and other treatment outcomes, which are positively correlated with the multi-objective optimization function, and the results obtained are positive numbers; f2(x) corresponds to the treatment cycle, which is negatively correlated with the multi-objective optimization function. The results obtained are multiplied by negative 1 and then arranged to obtain the optimal value of the target optimization result.

8. The method for constructing a multi-center disease-specific database system according to claim 7, characterized in that: In step S3, in order to comprehensively consider the impact of the cure rate, treatment cycle and other treatment results of the special disease on the evaluation results, the weighted coefficient method is used to comprehensively calculate the optimal treatment results of the same type in different hospitals.

9. The method for constructing a multi-center disease-specific database system according to claim 8, characterized in that: Calculation formula of weighted coefficient method: Weighted sum = a*x+b*y+c*z, Among them, a, b and c represent the cure rate, treatment cycle and other treatment results respectively; x, y and z correspond to the corresponding coefficients of a, b and c, and x, y and z are the experts' evaluation of the importance of the cure rate, treatment cycle and other treatment results in the entire weighted sum. The sum of x, y and z is 1.

Images