System and method for collecting and analyzing data of patients with blood diseases

Through the combination of multi-dimensional acquisition module and management analysis module, the data sets of patients with hematological diseases are processed using hierarchical clustering methods to generate medical treatment and trend data groups, solving the problems of errors and low efficiency of data integration in traditional systems, and achieving efficient and accurate data management and analysis improve the efficiency and quality of medical treatment.

CN118824453BActive Publication Date: 2024-11-15JILIN UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411297714.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-15
Estimated Expiration
2044-09-18

AI Technical Summary

Technical Problem

When managing long-term treatment data, traditional hematological patients' data collection and analysis system requires integration with the hospital's internal electronic medical record system and drug management system many times, resulting in data errors and leaks difficult to detect in a timely manner, and the accuracy and consistency of the data cannot be ensured. Data analysis Inefficient.

Method used

A method for data collection and analysis of patients with hematology is designed. Through the multi-dimensional acquisition module network, the medical record system and the clinical information system are connected to the medical client, the electronic medical record system and the clinical information system, and the patient data set, the medical record data set and the treatment data set are constructed, and the hierarchical clustering method is used to generate clustering. Class structure, calculates the similarity between clusters, merges or processs new clusters independently, generates medical visit data groups and trend data groups, and provides evaluation reports.

Benefits of technology

It realizes intelligent management of patient data, reduces data errors and omissions, improves data analysis efficiency, ensures the accuracy and consistency of medical data, and makes medical staff more efficient and better quality during medical treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118824453B_ABST
    Figure CN118824453B_ABST
Patent Text Reader

Abstract

The present invention discloses a blood disease patient data collection and analysis system and method, and relates to the technical field of medical data management. The system includes a multi-dimensional collection module and a management analysis module. The multi-dimensional collection module is used to connect a medical consultation client, an electronic medical record system, and a clinical information system through a network, and a data set is formed by classification. The management analysis module constructs a new cluster or updates the cluster structure according to the patient data set. All clusters correspond to each different blood disease patient, and each cluster is configured with an independent consultation code. A single consultation code corresponds to all identity information, medical record information, and clinical treatment information of the same blood disease patient, so that intelligent management of patient data is achieved, which is not easy to make mistakes. The management analysis module analyzes and generates a medical consultation data group and a trend data group, integrates the treatment information of the same patient, analyzes the change trend of the patient's blood indicators before and after treatment, and generates an evaluation report in combination, which can make medical staff more efficient during medical consultation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical data management, and in particular to a system and method for collecting and analyzing data of patients with blood diseases. Background Art

[0002] Hematological diseases are a class of diseases involving the blood, bone marrow and lymphatic system, including various types of leukemia, lymphoma, myelodysplastic syndrome, multiple myeloma, aplastic anemia, etc. Hematological diseases are characterized by an abnormal increase or decrease in hematopoietic cells in the bone marrow, resulting in abnormal numbers of red blood cells, white blood cells and platelets in the blood, which in turn causes various symptoms and complications. Common symptoms of patients with hematological diseases include fatigue, weakness, bleeding or bruising, repeated infections, fever, sweating, weight loss, etc. Since hematological diseases affect normal blood function, they may cause various complications such as anemia, bleeding tendency, infection, etc. The diagnosis of hematological diseases usually requires blood tests, bone marrow biopsies, imaging tests, etc. Blood tests can detect the number of red blood cells, white blood cells and platelets in the blood, as well as the hemoglobin content, etc. Bone marrow biopsies can check the type and number of cells in the bone marrow, as well as whether there are abnormal cells. Imaging tests such as X-rays, CT, MRI, etc. can help doctors understand the scope and severity of the disease. Common treatments for hematological diseases include chemotherapy, radiotherapy, targeted therapy, immunotherapy, hematopoietic stem cell transplantation, etc. Chemotherapy and radiation therapy are the most commonly used treatments that kill or inhibit the growth of abnormal cells. Targeted therapy and immunotherapy are newer treatments that target specific molecules or cells to reduce damage to normal cells. Hematopoietic stem cell transplantation is a potential treatment that replaces the patient's abnormal hematopoietic system to restore normal blood function.

[0003] At present, when traditional blood disease patient data collection and analysis systems manage long-term treatment data, they need to be integrated with the hospital's internal electronic medical record system and drug management system many times. Errors and omissions are difficult to detect in a timely manner, and the accuracy and consistency of the data cannot be ensured. In addition, in actual use, it is necessary to manually review medical record data many times and make multiple comparisons to judge the treatment effect, which makes data analysis inefficient. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a system and method for collecting and analyzing data on patients with blood diseases, which has the advantages of intelligent management of patient data, less prone to errors and omissions, and better medical quality. It solves the problem that data errors and omissions are difficult to detect and trend analysis efficiency is low in traditional data collection and analysis systems for patients with blood diseases.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for collecting and analyzing data of patients with blood diseases comprises the following steps:

[0007] Step 1: The hematological patient enters his identity information through the medical client. The multi-dimensional acquisition module connects to the medical client through the network and obtains the identity information to form a patient data set.

[0008] Step 2: The management and analysis module constructs new clusters based on the patient data set and calculates the identity information and clustering structure of blood disease patients in the new clusters The similarity between other clusters in , if the similarity When it is 100%, the new cluster is merged into the clustering structure In the historical cluster, if the similarity If it does not reach 100%, cluster the new clusters into the cluster structure , and update the clustering structure ;

[0009] Step 3: Whenever new data is added to the electronic medical record system and clinical information system, the multi-dimensional acquisition module obtains the medical record information and clinical treatment information of the blood disease patients, and then forms the medical record data set and the treatment data set;

[0010] Step 4: Management analysis module based on cluster structure , medical record data set and treatment data set, analyze and generate the visit data set , integrating the identity information, medical history information and clinical treatment information of the same blood disease patient;

[0011] Step 5: Management analysis module based on cluster structure , medical record data set and treatment data set, analyze and generate trend data set , obtain the difference in red blood cell concentration, white blood cell count and platelet count before and after treatment for each blood disease patient;

[0012] Step 6: The management and analysis module groups the patient data into and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system via the network.

[0013] Preferably, in step 2, if the clustering structure When only medical record information or clinical treatment information exists in a single cluster, it means that there are errors or omissions in the data integration process of the electronic medical record system and the clinical information system, and the erroneous or missing medical record information or clinical treatment information is transmitted back to the electronic medical record system and the clinical information system to remind management personnel to make corrections and supplements in a timely manner.

[0014] Preferably, in step 2, the cluster structure All clusters in the data correspond to different blood disease patients, and each cluster is configured with an independent medical consultation code. A single medical consultation code corresponds to all the identity information, medical record information, and clinical treatment information of the same blood disease patient.

[0015] A data collection and analysis system for patients with blood diseases, comprising a multi-dimensional collection module and a management and analysis module;

[0016] The multi-dimensional acquisition module includes a patient data unit, a medical record data unit and a treatment data unit. The patient data unit is connected to the medical client through the network to collect patient data sets, and the patient data sets include the identity information of all blood disease patients. The medical record data unit is connected to the electronic medical record system through the network to collect medical record data sets, and the medical record data sets include the medical record information of all blood disease patients. The treatment data unit is connected to the clinical information system through the network to collect treatment data sets, and the treatment data sets include the clinical treatment information of all blood disease patients. The multi-dimensional acquisition module transmits the patient data sets, medical record data sets and treatment data sets to the management and analysis module through the network;

[0017] The management and analysis module includes a data proofreading unit, a trend analysis unit and a treatment evaluation unit. The data proofreading unit generates a clustering structure based on the patient data set, the medical record data set and the treatment data set. and visit data group , and transmitted to the patient client and clinical information system through the network, the trend analysis unit is based on the cluster structure , medical record data set and treatment data set, analyze and generate trend data set and transmitted to the patient client and clinical information system through the network. The treatment evaluation unit groups the patient data into and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system via the network.

[0018] Preferably, the expression of the patient data set is , 1 to Indicates that there are patients with blood diseases in the medical client name, to express The identity information of patients with blood diseases includes the patient's name, age, gender, ID number, medical insurance card account number, mobile phone number and biometric information. Indicates the time point when a blood disease patient enters his / her identity information through the medical consultation client.

[0019] Preferably, the expression of the medical record data set is , 1 to Indicates that there are patients with blood diseases in the electronic medical record system name, to express The medical records of patients with blood diseases include identity information, previous diseases, surgical history, family medical history and medical records. Indicates the time point when the electronic medical record system updates the medical record information.

[0020] Preferably, the expression of the treatment data set is , 1 to Indicates that there are patients with blood diseases in the clinical information system name, to express Clinical treatment information of patients with blood diseases, including identity information, treatment drug records and treatment response records, Indicates the time point when the clinical information system updates clinical treatment information.

[0021] Preferably, the data proofreading unit generates a clustering structure by analyzing a hierarchical clustering method. , the calculation process is as follows:

[0022] Based on patient data The identity information of patients with blood diseases is constructed clusters;

[0023] Based on the medical record data Medical records of patients with blood diseases, clusters;

[0024] According to the treatment data Clinical treatment information of patients with blood diseases, clusters;

[0025] Calculate the similarity between all clusters , and its calculation formula is as follows:

[0026] ;

[0027] In the formula, Indicates similarity, Indicates the patient data set The identity information of patients with blood diseases Indicates the medical record dataset Medical records of patients with blood diseases, Indicates the treatment data set Clinical treatment information of patients with blood diseases, Indicates Name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information and The similarity of the name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information, previous illness, surgical history, family medical history, and medical records of patients with blood diseases. Indicates Treatment medication records, treatment response records and the first The similarity of the previous diseases, surgical history, family medical history, and medical records of the blood disease patients. Indicates Name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information and Similarity of the name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information, treatment drug records, and treatment response records of blood disease patients;

[0028] Set up classification standards , classification standard When the similarity of two or more clusters is 100%, they are clustered and merged into one cluster;

[0029] ;

[0030] In the formula, represents the clustering structure, According to the classification standard , all clusters with 100% similarity in the patient data set, medical record data set, and treatment data set are merged, and the multiple clusters formed are the clustering structure.

[0031] Preferably, the data checking unit is based on the cluster structure , analyze and generate the medical visit data set , and its calculation formula is as follows:

[0032] ;

[0033] In the formula, represents the medical visit data group, Indicates the sequential fusion of cluster structures The identity information, medical record information and clinical treatment information of the blood disease patients in each cluster, and the identity information, medical record information and clinical treatment information in a single cluster are the medical treatment data set of a single blood disease patient.

[0034] Preferably, the trend data set The calculation formula is as follows:

[0035] ;

[0036] In the formula, Represents a trend data group, Represents the medical record dataset The red blood cell concentration values ​​before treatment in the medical records of patients with blood diseases, Represents the medical record dataset The red blood cell concentration values ​​after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in red blood cell concentration before and after treatment of blood disease patients in a single cluster, Represents the medical record dataset The white blood cell count values ​​before treatment in the medical records of patients with blood diseases, Represents the medical record dataset The white blood cell count values ​​after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in white blood cell counts before and after treatment for patients with blood diseases in a single cluster, Represents the medical record dataset Platelet counts before treatment in the medical records of patients with blood diseases, Represents the medical record dataset Platelet counts after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in platelet counts before and after treatment for hematological patients in a single cluster, and the trend data set includes a cluster structure The difference in red blood cell concentration, white blood cell count and platelet count before and after treatment in patients with blood diseases.

[0037] Compared with the prior art, the blood disease patient data collection and analysis system and method provided by the present invention have the following beneficial effects:

[0038] The present invention connects the medical client, the electronic medical record system and the clinical information system through a multi-dimensional acquisition module network, classifies the patient data set, the medical record data set and the treatment data set, and transmits them to the management and analysis module. The management and analysis module constructs a new cluster based on the patient data set, calculates the identity information and clustering structure of the blood disease patients in the new cluster The similarity between other clusters in , if the similarity When it is 100%, the new cluster is merged into the clustering structure The historical cluster in the cluster indicates that the patient with blood disease has established a medical record in the hospital system. It is necessary to merge the new cluster and the historical cluster into one cluster. If it does not reach 100%, cluster the new clusters into the cluster structure , and update the clustering structure , indicating that the patient with blood disease has not established a medical record in the hospital system, and the new cluster needs to be added independently to the clustering structure If the clustering structure When only medical record information or clinical treatment information exists in a single cluster, it indicates that there are errors or omissions in the data integration process between the electronic medical record system and the clinical information system, and the erroneous medical record information or clinical treatment information is transmitted back to the electronic medical record system and the clinical information system to remind the management personnel to correct and supplement it in time. All clusters in the system correspond to different blood disease patients, and each cluster is configured with an independent medical treatment code. A single medical treatment code corresponds to all the identity information, medical record information and clinical treatment information of the same blood disease patient, thereby realizing intelligent management of patient data and preventing errors and omissions.

[0039] The present invention manages and analyzes the module according to the cluster structure , medical record data set and treatment data set, analyze and generate the visit data set and trend data groups , combining the identity information, medical history information and clinical treatment information of the same blood disease patient, the difference in red blood cell concentration, white blood cell count and platelet count before and after treatment of each blood disease patient is obtained. The management and analysis module groups the visit data into and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system through the network. With trend analysis, it can make medical staff more efficient and provide better quality medical treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a step diagram of the method of the present invention;

[0041] Figure 2 Schematic diagram of the process of the system of the present invention. DETAILED DESCRIPTION

[0042] 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.

[0043] Because the traditional blood disease patient data collection and analysis system needs to be integrated with the hospital's internal electronic medical record system and drug management system many times when managing long-term treatment data, it is difficult to find errors and omissions in the data integration process, and the accuracy and consistency of the data cannot be ensured. In addition, in the actual use process, it is necessary to manually check the medical record data many times and compare them many times to judge the treatment effect, and the data analysis efficiency is low. Therefore, a blood disease patient data collection and analysis system and method are provided. Please refer to Figure 2 ,The system includes a multi-dimensional acquisition module and a management and analysis module;

[0044] The multi-dimensional acquisition module includes patient data unit, medical record data unit and treatment data unit.

[0045] The patient data unit collects patient data sets through a network connection to the medical consultation client. The medical consultation client can be set as an application software APP, a mini-program or a webpage according to the actual usage scenario. The patient data set includes the identity information of all blood disease patients. The identity information includes the patient's name, age, gender, ID number, medical insurance card account number, mobile phone number and biometric information. The biometric information is not limited to the patient's blood type, fingerprint, and facial features. When a blood disease patient enters his or her identity information through the medical consultation client, the seven types of information, namely name, age, gender, ID number, medical insurance card account number, mobile phone number and biometric information, are indispensable. Collecting identity information helps to quickly classify all blood disease patients in the future;

[0046] The medical record data unit collects medical record data sets through a network connection to the electronic medical record system. The medical record data set includes the medical record information of all blood disease patients, including previous diseases, surgical history, family medical history and medical records. The data mostly comes from hospital outpatient and emergency departments. The data content includes diagnosis and treatment results, treatment plans, test orders, medical images, etc. The medical record information is helpful for the subsequent rapid evaluation of the change trend of the patient's blood indicators before and after treatment;

[0047] The treatment data unit collects treatment data sets through a network connection to the clinical information system. The treatment data sets include clinical treatment information of all hematological patients. Clinical treatment information includes treatment drug records and treatment response records. Most of the data comes from the hospital inpatient department. The data content includes nursing records, clinical condition records, symptom responses, etc. Clinical treatment information helps doctors accurately judge the patient's condition and adjust the treatment plan in time.

[0048] The multi-dimensional acquisition module transmits the patient data set, medical record data set and treatment data set to the management and analysis module through the network, and transmits the patient data from different systems to the management and analysis module for further analysis and integration;

[0049] The management and analysis module includes a data proofreading unit, a trend analysis unit, and a treatment evaluation unit;

[0050] The data proofreading unit generates a clustering structure through hierarchical clustering analysis ,The hierarchical clustering method is suitable for situations where the number of clusters does not need to be pre-specified, and different levels of clustering structures can be freely formed. In the actual application process, each level can be divided according to monthly and annual periods, which helps hospitals to efficiently manage a large amount of patient information;

[0051] The expression of the patient dataset is , 1 to Indicates that there are patients with blood diseases in the medical client name, to express The identity information of patients with blood diseases includes the patient's name, age, gender, ID number, medical insurance card account number, mobile phone number and biometric information. Indicates the time when the blood disease patient enters the identity information through the medical consultation client;

[0052] The expression of the medical record dataset is: , 1 to Indicates that there are patients with blood diseases in the electronic medical record system name, to express The medical records of patients with blood diseases include identity information, previous diseases, surgical history, family medical history and medical records. Indicates the time point when the electronic medical record system updates the medical record information;

[0053] The expression of the treatment data set is , 1 to Indicates that there are patients with blood diseases in the clinical information system name, to express Clinical treatment information of patients with blood diseases, including identity information, treatment drug records and treatment response records, Indicates the time point when the clinical information system updates clinical treatment information;

[0054] Cluster structure The calculation process is as follows:

[0055] Based on patient data The identity information of patients with blood diseases is constructed clusters;

[0056] Based on the medical record data Medical records of patients with blood diseases, clusters;

[0057] According to the treatment data Clinical treatment information of patients with blood diseases, clusters;

[0058] Calculate the similarity between all clusters , and its calculation formula is as follows:

[0059] ;

[0060] In the formula, Indicates similarity, Indicates the patient data set The identity information of patients with blood diseases Indicates the medical record dataset Medical records of patients with blood diseases, Indicates the treatment data set Clinical treatment information of patients with blood diseases, Indicates The names of patients with different types of blood diseases, their given names, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information and The similarity of the name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information, previous illness, surgical history, family medical history, and medical records of patients with blood diseases. Indicates Treatment medication records, treatment response records and the first The similarity of the previous diseases, surgical history, family medical history, and medical records of the blood disease patients. Indicates Name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information and Similarity of the name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information, treatment drug records, and treatment response records of blood disease patients;

[0061] Set up classification standards , classification standard When the similarity of two or more clusters is 100%, they are clustered and merged into one cluster;

[0062] ;

[0063] In the formula, represents the clustering structure, According to the classification standard , merge all clusters with 100% similarity in the patient data set, medical record data set and treatment data set, and the multiple clusters formed are the cluster structure. Each cluster corresponds to different blood disease patient information. When facing patients with the same name, it can also avoid errors and omissions in the data integration process, intelligently manage patient data, and it is not easy to make mistakes. The data proofreading unit will use the network to convert the cluster structure The data is transmitted back to the clinical information system, so that medical staff can check all the patient's treatment records through the clinical information system;

[0064] Data verification unit based on cluster structure , analyze and generate the medical visit data set , and its calculation formula is as follows:

[0065] ;

[0066] In the formula, represents the medical visit data group, Indicates the sequential fusion of cluster structures The identity information, medical history information and clinical treatment information of the blood disease patients in each cluster, the identity information, medical history information and clinical treatment information in a single cluster are the medical treatment data group of a single blood disease patient, and the data proofreading unit transmits the medical treatment data group to the patient through the network. The data is sent back to the medical client, so that patients can check all treatment records through the medical client.

[0067] Trend analysis unit based on cluster structure , medical record data set and treatment data set, analyze and generate trend data set and transmitted to the patient client and clinical information system through the network;

[0068] Trend Data Group The calculation formula is as follows:

[0069] ;

[0070] In the formula, Represents a trend data group, Represents the medical record dataset The red blood cell concentration values ​​before treatment in the medical records of patients with blood diseases, Represents the medical record dataset The red blood cell concentration values ​​after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in red blood cell concentration before and after treatment of blood disease patients in a single cluster, Represents the medical record dataset The white blood cell count values ​​before treatment in the medical records of patients with blood diseases, Represents the medical record dataset The white blood cell count values ​​after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in white blood cell counts before and after treatment for patients with blood diseases in a single cluster, Represents the medical record dataset Platelet counts before treatment in the medical records of patients with blood diseases, Represents the medical record dataset Platelet counts after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in platelet counts before and after treatment for hematological patients in a single cluster, and the trend data set includes a cluster structure The red blood cell concentration difference, white blood cell count difference and platelet count difference before and after treatment of patients with blood diseases. Different types of blood diseases, such as leukemia, lymphoma, myelodysplastic syndrome, multiple myeloma, etc., will affect the number of red blood cells, white blood cells and platelets and show different hematological changes. The red blood cell concentration difference, white blood cell count difference and platelet count difference before and after treatment are automatically calculated, which improves the system trend analysis ability;

[0071] The treatment assessment unit will be the patient data group and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system through the network. There is no need for manual review of medical records and multiple comparisons to determine the treatment effect. With trend analysis, medical staff can be more efficient and provide better quality medical treatment.

[0072] The above blood disease patient data collection and analysis system applies the blood disease patient data collection and analysis method, please refer to Figure 1 , the method comprises the following steps:

[0073] Step 1: The hematological patient enters his identity information through the medical client. The multi-dimensional acquisition module connects to the medical client through the network and obtains the identity information to form a patient data set.

[0074] Step 2: The management and analysis module constructs new clusters based on the patient data set and calculates the identity information and clustering structure of blood disease patients in the new clusters The similarity between other clusters in , if the similarity When it is 100%, the new cluster is merged into the clustering structure The historical cluster in the cluster indicates that the patient with blood disease has established a medical record in the hospital system. It is necessary to merge the new cluster and the historical cluster into one cluster. If it does not reach 100%, cluster the new clusters into the cluster structure , and update the clustering structure , indicating that the patient with blood disease has not established a medical record in the hospital system, and the new cluster needs to be added independently to the clustering structure middle;

[0075] If the clustering structure When only medical record information or clinical treatment information exists in a single cluster, it indicates that there are errors or omissions in the data integration process between the electronic medical record system and the clinical information system, and the erroneous or missing medical record information or clinical treatment information is transmitted back to the electronic medical record system and the clinical information system to remind the management personnel to make corrections and supplements in time;

[0076] Cluster structure All clusters in the system correspond to different blood disease patients, and each cluster is configured with an independent consultation code. A single consultation code corresponds to all the identity information, medical history information and clinical treatment information of the same blood disease patient, and intelligent management of patient data is not prone to errors and omissions.

[0077] Step 3: Whenever new data is added to the electronic medical record system and clinical information system, the multi-dimensional acquisition module obtains the medical record information and clinical treatment information of the blood disease patients, and then forms the medical record data set and the treatment data set;

[0078] Step 4: Management analysis module based on cluster structure , medical record data set and treatment data set, analyze and generate the visit data set , integrating the identity information, medical history information and clinical treatment information of the same blood disease patient;

[0079] Step 5: Management analysis module based on cluster structure , medical record data set and treatment data set, analyze and generate trend data set , obtain the difference in red blood cell concentration, white blood cell count and platelet count before and after treatment for each blood disease patient. Under trend analysis, medical staff can be more efficient and have better quality when they are seeing a doctor.

[0080] Step 6: The management and analysis module groups the patient data into and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system via the network.

[0081] 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 method for collecting and analyzing data of patients with blood diseases. It is characterized in that The following steps are involved: Step 1: The hematological patient enters his identity information through the medical client. The multi-dimensional acquisition module connects to the medical client through the network and obtains the identity information to form a patient data set. Step 2: The management and analysis module constructs new clusters based on the patient data set and calculates the identity information and clustering structure of blood disease patients in the new clusters The similarity between other clusters in , if the similarity When it is 100%, the new cluster is merged into the clustering structure In the historical cluster, if the similarity If it does not reach 100%, cluster the new clusters into the cluster structure , and update the clustering structure ; Step 3: Whenever new data is added to the electronic medical record system and clinical information system, the multi-dimensional acquisition module obtains the medical record information and clinical treatment information of the blood disease patients, and then forms the medical record data set and the treatment data set; Step 4: Management analysis module based on cluster structure , medical record data set and treatment data set, analyze and generate the visit data set , integrating the identity information, medical history information and clinical treatment information of the same blood disease patient; Step 5: Management analysis module based on cluster structure , medical record data set and treatment data set, analyze and generate trend data set , obtain the difference in red blood cell concentration, white blood cell count and platelet count before and after treatment for each blood disease patient; Step 6: The management and analysis module groups the patient data into and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system via the network.

2. The method for collecting and analyzing data of patients with blood diseases according to claim 1, It is characterized in that In step 2, if the clustering structure When only medical record information or clinical treatment information exists in a single cluster, it means that there are errors or omissions in the data integration process of the electronic medical record system and the clinical information system, and the erroneous or missing medical record information or clinical treatment information is transmitted back to the electronic medical record system and the clinical information system to remind management personnel to make corrections and supplements in a timely manner.

3. The method for collecting and analyzing data of patients with blood diseases according to claim 2, It is characterized in that In the step 2, the clustering structure All clusters in the data correspond to different blood disease patients, and each cluster is configured with an independent medical consultation code. A single medical consultation code corresponds to all the identity information, medical record information, and clinical treatment information of the same blood disease patient.

4. A system for collecting and analyzing data of patients with blood diseases, applied to the method for collecting and analyzing data of patients with blood diseases according to any one of claims 1 to 3, It is characterized in that Includes multi-dimensional acquisition module and management and analysis module; The multi-dimensional acquisition module includes a patient data unit, a medical record data unit and a treatment data unit. The patient data unit is connected to the medical client through the network to collect patient data sets, and the patient data sets include the identity information of all blood disease patients. The medical record data unit is connected to the electronic medical record system through the network to collect medical record data sets, and the medical record data sets include the medical record information of all blood disease patients. The treatment data unit is connected to the clinical information system through the network to collect treatment data sets, and the treatment data sets include the clinical treatment information of all blood disease patients. The multi-dimensional acquisition module transmits the patient data sets, medical record data sets and treatment data sets to the management and analysis module through the network; The management and analysis module includes a data proofreading unit, a trend analysis unit and a treatment evaluation unit. The data proofreading unit generates a clustering structure based on the patient data set, the medical record data set and the treatment data set. and visit data group , and transmitted to the patient client and clinical information system through the network, the trend analysis unit is based on the clustering structure , medical record data set and treatment data set, analyze and generate trend data set and transmitted to the patient client and clinical information system through the network. The treatment evaluation unit groups the patient data into and trend data groups The combination generates an evaluation report and transmits it to the patient client and clinical information system via the network.

5. The blood disease patient data collection and analysis system according to claim 4, It is characterized in that The expression of the patient dataset is , 1 to Indicates that there are patients with blood diseases in the medical client name, to express The identity information of patients with blood diseases includes the patient's name, age, gender, ID number, medical insurance card account number, mobile phone number and biometric information. Indicates the time point when a blood disease patient enters his / her identity information through the medical consultation client.

6. The blood disease patient data collection and analysis system according to claim 5, It is characterized in that The expression of the medical record dataset is: , 1 to Indicates that there are patients with blood diseases in the electronic medical record system name, to express The medical records of patients with blood diseases include identity information, previous diseases, surgical history, family medical history and medical records. Indicates the time point when the electronic medical record system updates the medical record information.

7. The blood disease patient data collection and analysis system according to claim 6, It is characterized in that The expression of the treatment data set is , 1 to Indicates that there are patients with blood diseases in the clinical information system name, to express Clinical treatment information of patients with blood diseases, including identity information, treatment drug records and treatment response records, Indicates the time point when the clinical information system updates clinical treatment information.

8. The blood disease patient data collection and analysis system according to claim 7, It is characterized in that The data proofreading unit generates a clustering structure by analyzing the hierarchical clustering method. , the calculation process is as follows: Based on patient data The identity information of patients with blood diseases is constructed clusters; Based on the medical record data Medical records of patients with blood diseases, clusters; According to the treatment data Clinical treatment information of patients with blood diseases, clusters; Calculate the similarity between all clusters , and its calculation formula is as follows: ; In the formula, Indicates similarity, Indicates the patient data set The identity information of patients with blood diseases Indicates the medical record dataset Medical records of patients with blood diseases, Indicates the treatment data set Clinical treatment information of patients with blood diseases, Indicates Name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information and The similarity of the name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information, previous illness, surgical history, family medical history, and medical records of patients with blood diseases. Indicates Treatment medication records, treatment response records and the first The similarity of the previous diseases, surgical history, family medical history, and medical records of the blood disease patients. Indicates Name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information and Similarity of the name, age, gender, ID number, medical insurance card account number, mobile phone number, biometric information, treatment drug records, and treatment response records of blood disease patients; Set up classification standards , classification standard When the similarity of two or more clusters is 100%, they are clustered and merged into one cluster; ; In the formula, represents the clustering structure, According to the classification standard , all clusters with 100% similarity in the patient data set, medical record data set, and treatment data set are merged, and the multiple clusters formed are the clustering structure.

9. The blood disease patient data collection and analysis system according to claim 8, It is characterized in that The data checking unit is based on the cluster structure , analyze and generate the medical visit data set , and its calculation formula is as follows: ; In the formula, represents the medical visit data group, Indicates the sequential fusion of cluster structures The identity information, medical record information and clinical treatment information of the blood disease patients in each cluster, and the identity information, medical record information and clinical treatment information in a single cluster are the medical treatment data set of a single blood disease patient.

10. The blood disease patient data collection and analysis system according to claim 9, It is characterized in that The trend data set The calculation formula is as follows: ; In the formula, Represents a trend data group, Represents the medical record dataset The red blood cell concentration values ​​before treatment in the medical records of patients with blood diseases, Represents the medical record dataset The red blood cell concentration values ​​after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in red blood cell concentration before and after treatment of blood disease patients in a single cluster, Represents the medical record dataset The white blood cell count values ​​before treatment in the medical records of patients with blood diseases, Represents the medical record dataset The white blood cell count values ​​after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in white blood cell counts before and after treatment for patients with blood diseases in a single cluster, Represents the medical record dataset Platelet counts before treatment in the medical records of patients with blood diseases, Represents the medical record dataset Platelet counts after treatment in the medical records of patients with blood diseases, According to the clustering structure , calculate the difference in platelet counts before and after treatment for hematological patients in a single cluster, and the trend data set includes a cluster structure The difference in red blood cell concentration, white blood cell count and platelet count before and after treatment in patients with blood diseases.