A medical record quality monitoring method and system based on big data

Abstract

The present invention discloses a medical record quality monitoring method and system based on big data, the method comprising: creating a medical record connotation quality control system database and formulating quality control rules, collecting medical record data and inputting it into the medical record connotation quality control system database; scoring the medical record data using a preset medical record quality scoring system, determining qualified attributes of the medical record data based on the scoring results, and determining medical record availability based on the qualified attributes; screening out valid medical records based on medical record availability, determining time specification parameters and content specification parameters based on quality control rules, and performing quality control processing on valid medical records using the time specification parameters and content specification parameters; determining medical record defects based on the quality control results, performing feedback modification processing based on the medical record defects, and performing second-order final quality control on valid medical records. Effective quality control work can be performed on each medical record quickly and accurately according to quality control requirements, thereby improving work efficiency while also improving practicality, standardizing medical behavior, and enhancing medical record quality.

Description

Technical Field

[0001] The present invention relates to the technical field of medical quality management, and in particular to a medical record quality monitoring method and system based on big data. Background Art

[0002] Currently, medical records hold a crucial and unique position in my country's healthcare system. As the primary medical document that documents the complete course of a patient's illness, from onset to development, diagnosis, treatment, and outcome, they are the primary source of information. On the one hand, their quality largely reflects the physician's diagnostic and treatment expertise and serves as crucial evidence for handling medical malpractice and legal disputes. On the other hand, the vast amount of diagnostic and treatment data integrated into medical records serves as a core resource for supporting clinical decision-making and medical research, impacting the effectiveness and ultimate impact of data reuse. Consequently, hospitals have long invested significant manpower and resources in medical record quality control, with limited success. The reasons for this are: first, manual review is inefficient, inaccurate, and time-consuming, making it difficult to fully cover discharge records and resulting in missed issues. Second, outdated quality control processes and weak management prevent real-time tracking and feedback, leading to a backlog of existing issues and the frequent emergence of new ones, resulting in ineffective results. Summary of the Invention

[0003] In response to the problems shown above, the present invention provides a medical record quality monitoring method and system based on big data to solve the problems mentioned in the background technology, such as low efficiency and poor accuracy of manual review, which is too time-consuming, difficult to cover all discharge medical records, and causes problems to be missed.

[0004] A method for monitoring the quality of medical records based on big data, comprising the following steps:

[0005] Create a medical record content quality control system database and formulate quality control rules, collect medical record data and input it into the medical record content quality control system database;

[0006] Score the medical record data using a preset medical record quality scoring system, determine the qualified attributes of the medical record data based on the scoring results, and determine the usability of the medical record based on the qualified attributes;

[0007] Filter out valid medical records based on their availability, determine time specification parameters and content specification parameters based on quality control rules, and perform quality control on valid medical records using these parameters.

[0008] Determine medical record defects based on quality control results, provide feedback and make modifications based on medical record defects, and conduct second-level final quality control on valid medical records.

[0009] Preferably, the creation of a medical record content quality control system database and formulation of quality control rules include:

[0010] Determine the standard data structure of medical record data, and design data table fields and data table relationships based on the standard data structure;

[0011] Use SQL statements to create database and table structures based on data table fields and data table relationships, and build a medical record content quality control system database based on the database and table structures;

[0012] Determine quality control objectives based on medical record writing standards and medical record quality evaluation standards;

[0013] Quality control rules are formulated based on the quality control objectives and the professional review opinions of senior qualified doctors from tertiary hospitals.

[0014] Preferably, the collection of medical record data and inputting it into the medical record content quality control system database includes:

[0015] Identify the data sources of multiple medical business systems and collect medical data from multiple data sources using data extraction technology in accordance with communication and interoperability standards;

[0016] Clean and quantify medical data, determine the data items of diagnosis and treatment plan and treatment process, screen and classify medical data according to the data items, and obtain high-quality medical record data;

[0017] Load high-quality pathology data into the medical record content quality control system database.

[0018] Preferably, the step of scoring the medical record data using a preset medical record quality scoring system, determining the qualified attributes of the medical record data according to the scoring results, and determining the usability of the medical record based on the qualified attributes includes:

[0019] Obtain multiple scoring criteria based on the hospital medical record scoring work model, and build a preset medical record quality scoring system based on the multiple scoring criteria;

[0020] Compare and score the medical record data using a preset medical record quality scoring system, obtain the scoring results, and determine the passing score distribution and failing score distribution of the medical record data based on the scoring results;

[0021] Determine the qualified attributes of the medical record data based on the passing score distribution and the failing score distribution, wherein the qualified attributes include: fully qualified, partially qualified, partially qualified, and fully unqualified;

[0022] The data value of medical record data and the degree of consistency with the diagnosis and treatment process are determined based on the qualified attributes, and the availability of medical records is determined based on the degree of consistency between the data value and the diagnosis and treatment process.

[0023] Preferably, before screening out valid medical records based on medical record availability, determining time specification parameters and content specification parameters based on quality control rules, and performing quality control processing on the valid medical records using the time specification parameters and content specification parameters, the method further includes:

[0024] Obtain free text from medical records, extract descriptive content from the free text, and structure the free text according to the treatment process using NIP technology;

[0025] Determine multiple data nodes based on the processing results. Use predefined text extraction technology based on professional medical terminology to extract important parameters from each data node;

[0026] Perform context matching and semantic analysis on important parameters to obtain the entity concepts corresponding to each data node;

[0027] The current quality control content of each data node is determined based on the entity concept corresponding to each data node.

[0028] Preferably, valid medical records are screened out based on medical record availability, time specification parameters and content specification parameters are determined based on quality control rules, and quality control processing is performed on the valid medical records using the time specification parameters and content specification parameters, including:

[0029] Screen out reliable medical records, pending verification medical records, and unreliable medical records based on medical record availability, obtain manual verification results of pending verification medical records, screen out verified medical records based on manual verification results, and confirm verified medical records and reliable medical records as valid medical records;

[0030] Determine the standard registration time parameters and standard execution time parameters for each treatment process according to the quality control rules, and determine the time specification parameters based on the standard registration time parameters and standard execution time parameters;

[0031] Obtain statistical behavior parameters and result status description parameters of each treatment process, and determine content specification parameters of each treatment process based on the statistical behavior parameters and result status description parameters;

[0032] Determine the quality control standards based on the time specification parameters and content specification parameters, and determine the data quality control requirements for each data node based on the quality control standards;

[0033] According to the data quality control requirements for each data node, valid medical records are quality controlled and defects and anomalies are located and feedback is provided.

[0034] Preferably, the method of determining medical record defects based on quality control results, performing feedback and modification based on the medical record defects, and performing a second-order final quality control on the valid medical records includes:

[0035] Determine the quality parameters of each link based on the quality control results, determine the medical record defects based on the quality parameters of each link, determine the modification parameters based on the medical record defects and provide reminder feedback;

[0036] Receive the attending physician's revisions to the disease defects and replace the original medical record content to generate a quality-controlled medical record;

[0037] Obtain effective quality evaluation indicators for the second-order final quality control, and conduct second-order final quality control on the medical records after quality control based on the effective quality evaluation indicators;

[0038] The final qualified judgment result of the medical record after quality control is determined based on the second-level quality control results, and a data view is generated based on the final qualified judgment result for display.

[0039] Preferably, determining the data value of the medical record data and the degree of consistency with the diagnosis and treatment process based on the qualified attributes, and determining the usability of the medical record based on the data value and the degree of consistency with the diagnosis and treatment process, includes:

[0040] Determine the patient's diagnosed disease based on medical record data, obtain the medical record sequence corresponding to the diagnosed disease, and obtain the diagnosis and treatment process of the diagnosed disease based on the medical record sequence;

[0041] Determine the examination items based on the diagnosis and treatment process, and determine the parameters for the complete examination results of each examination item based on the hierarchical model of the examination items;

[0042] The diagnostic vocabulary feature vector and diagnostic vocabulary feature frequency are determined based on the parameters of the improved examination results through the bag-of-words model;

[0043] Determine the current vocabulary feature summary amount and vocabulary feature scanning frequency based on the qualified attributes and the item result description parameters of each inspection item;

[0044] Determine the differences in vocabulary feature clustering and vocabulary feature frequency distribution based on the diagnostic vocabulary feature vectors, diagnostic vocabulary feature frequencies, current vocabulary feature summary, and vocabulary feature scanning frequencies;

[0045] Determine the data value of each inspection item based on the differences in vocabulary feature clustering and vocabulary feature frequency distribution;

[0046] Determine the total data value of medical record data based on the individual weight of each examination item in the diagnosis and treatment process;

[0047] Obtain clinical pathways and review pathways for diagnosis and treatment processes related to the disease, and determine scheduling medical resources and timing control features based on these pathways;

[0048] Construct a workflow model for disease-related diagnosis and treatment processes based on scheduling medical resources and timing control features;

[0049] Determine fixed diagnosis and treatment parameters and changeable diagnosis and treatment parameters according to the workflow model, and obtain corresponding data of the fixed diagnosis and treatment parameters and the changeable diagnosis and treatment parameters in the medical record data respectively;

[0050] Determine the record missing attributes of the corresponding data of the fixed diagnosis and treatment parameters and the changeable diagnosis and treatment parameters in the medical record data according to the qualified attributes;

[0051] Determine the consistency of medical record data with the diagnosis and treatment process based on the missing record attributes, and determine complete and missing medical records based on the total data value of the medical record data and the consistency of the diagnosis and treatment process;

[0052] Complete medical records are identified as usable medical records, and missing medical records are identified as unusable medical records.

[0053] Preferably, after creating the medical record content quality control system database and formulating quality control rules, it also includes:

[0054] Determine multiple quality control items and the primary quality control logic and secondary quality control logic for each quality control item according to quality control rules;

[0055] Respectively obtain the quality control forms and quality control data characteristics of the first-level quality control logic and the second-level quality control logic, and determine the quality control factors of the first-level quality control logic and the second-level quality control logic according to the quality control forms and quality control data characteristics;

[0056] Determine common quality control factors and independent quality control factors based on quality control factors, and construct a universal expression based on the common quality control factors;

[0057] Construct the characteristic expressions of the first-level quality control logic and the second-level quality control logic according to the independent quality control factors;

[0058] Obtain the rule configuration parameters of the quality control rules, and substitute the rule configuration parameters into the general expression and characteristic expression to generate coarse-grained quality control rules and fine-grained quality control rules;

[0059] Determine the post-quality control form of the quality control object through coarse-grained quality control rules and fine-grained quality control rules, and determine the rule attributes of the coarse-grained quality control rules and fine-grained quality control rules based on the post-quality control form. The rule attributes include: rules for in-process intervention in medical record completion, rules for pre-reminders for medical record filling, and rules for post-quality control of medical record content;

[0060] The quality control feedback form is set according to the respective rule attributes of the coarse-grained quality control rules and the fine-grained quality control rules, and the quality control feedback form is associated with the quality control rules to provide feedback on various medical record defects in the quality control process of the medical record data.

[0061] A medical record quality monitoring system based on big data, the system comprising:

[0062] Creation module, used to create a medical record content quality control system database and formulate quality control rules, collect medical record data and input it into the medical record content quality control system database;

[0063] A determination module is used to score the medical record data using a preset medical record quality scoring system, determine the qualified attributes of the medical record data based on the scoring results, and determine the usability of the medical record based on the qualified attributes;

[0064] The first quality control module is used to screen out valid medical records based on their availability, determine time specification parameters and content specification parameters based on quality control rules, and perform quality control processing on the valid medical records using the time specification parameters and content specification parameters;

[0065] The second quality control module is used to determine medical record defects based on quality control results, provide feedback and modification based on medical record defects, and perform second-order final quality control on valid medical records.

[0066] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0067] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0069] Figure 1 This is a workflow diagram of a medical record quality monitoring method based on big data provided by the present invention;

[0070] Figure 2 Another workflow diagram of a medical record quality monitoring method based on big data provided by the present invention;

[0071] Figure 3 Another workflow diagram of the medical record quality monitoring method based on big data provided by the present invention;

[0072] Figure 4 This is a structural diagram of a medical record quality monitoring system based on big data provided by the present invention. DETAILED DESCRIPTION

[0073] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0074] Currently, medical records hold a crucial and unique position in my country's healthcare system as original medical documents that document the complete process of a patient's illness, including its onset, progression, diagnosis, treatment, and outcome. On the one hand, their quality largely reflects the physician's diagnostic and treatment expertise and serves as crucial evidence for handling medical malpractice and legal disputes. On the other hand, the vast amount of diagnostic and treatment data integrated into medical records serves as a core resource for supporting clinical decision-making and medical research, impacting the effectiveness and ultimate impact of data secondary utilization. Consequently, hospitals have long invested significant human and material resources in medical record quality control, with limited success. The reasons for this are: first, manual review is inefficient, inaccurate, and time-consuming, making it difficult to fully cover all discharge records, leading to missed issues. Second, quality control processes lag behind, management is weak, and real-time tracking and feedback are impossible, resulting in a backlog of existing issues and the frequent emergence of new ones, resulting in ineffective results. To address these issues, this embodiment discloses a method for monitoring medical record quality based on big data.

[0075] A method for monitoring the quality of medical records based on big data, such as Figure 1 As shown, the following steps are included:

[0076] Step S101: Create a medical record content quality control system database and formulate quality control rules, collect medical record data and input it into the medical record content quality control system database;

[0077] Step S102: Score the medical record data using a preset medical record quality scoring system, determine the qualified attributes of the medical record data based on the scoring results, and determine the usability of the medical record based on the qualified attributes;

[0078] Step S103: Filter out valid medical records based on their availability, determine time specification parameters and content specification parameters based on quality control rules, and perform quality control on the valid medical records using the time specification parameters and content specification parameters;

[0079] Step S104: Determine medical record defects based on the quality control results, perform feedback and modification based on the medical record defects, and perform second-order final quality control on the valid medical records.

[0080] The working principle of the above technical solution is: create a medical record content quality control system database and formulate quality control rules, collect medical record data and input it into the medical record content quality control system database; score the medical record data through a preset medical record quality scoring system, determine the qualified attributes of the medical record data based on the scoring results, and determine the availability of the medical records based on the qualified attributes; screen out valid medical records based on the availability of medical records, determine the time specification parameters and content specification parameters based on the quality control rules, and perform quality control processing on the valid medical records through the time specification parameters and content specification parameters; determine medical record defects based on the quality control results, perform feedback and modification processing based on the medical record defects, and perform second-order terminal quality control on the valid medical records.

[0081] The beneficial effects of the above technical solution are: by implementing quality control rules and creating a database to effectively and intelligently and automatically control the collected medical record data, all medical records can be quality-controlled without omission based on big data collection, thus avoiding the omission of problems. Furthermore, by replacing manual quality control with intelligent models, each medical record can be quickly and accurately quality-controlled according to quality control requirements, improving work efficiency and practicality, standardizing medical behavior, and improving medical record quality. This solves the problem mentioned in the existing technology that manual review is inefficient, inaccurate, and time-consuming, making it difficult to cover all discharge medical records and causing problems to be missed.

[0082] In one embodiment, Figure 2 As shown, the creation of a medical record content quality control system database and the formulation of quality control rules include:

[0083] Step S201: Determine the standard data structure of medical record data, and design data table fields and data table relationships based on the standard data structure;

[0084] Step S202: Create a database and table structure using SQL statements based on the data table fields and data table relationships, and build a medical record content quality control system database based on the database and table structure;

[0085] Step S203: Determine quality control objectives based on medical record writing standards and medical record quality evaluation standards;

[0086] Step S204: Develop quality control rules based on the quality control objectives and the professional review opinions of senior quality control doctors from tertiary hospitals.

[0087] The beneficial effects of the above technical solution are: using SQL statements to create databases and table structures to build a medical record content quality control system database, and combining quality control objectives and professional review opinions of senior quality control doctors in tertiary hospitals as standards to formulate quality control rules, which can ensure the professionalism and standardization of the rules and improve the credibility of the quality control rules.

[0088] In one embodiment, the collecting of medical record data and inputting it into the medical record content quality control system database includes:

[0089] Identify the data sources of multiple medical business systems and collect medical data from multiple data sources using data extraction technology in accordance with communication and interoperability standards;

[0090] Clean and quantify medical data, determine the data items of diagnosis and treatment plan and treatment process, screen and classify medical data according to the data items, and obtain high-quality medical record data;

[0091] Load high-quality pathology data into the medical record content quality control system database.

[0092] The beneficial effects of the above technical solution are: collecting medical data from the data source of the medical business system according to the communication and interoperability standards and preprocessing it can improve the consistency and accuracy of the data. Furthermore, screening and classifying the medical data according to the data items can improve the data quality of the medical record content quality control system database and ensure that the data is representative.

[0093] In one embodiment, Figure 3 As shown, the medical record data is scored using a preset medical record quality scoring system, the qualified attributes of the medical record data are determined according to the scoring results, and the medical record usability is determined based on the qualified attributes, including:

[0094] Step S301: Acquire multiple scoring criteria based on the hospital medical record scoring work mode, and construct a preset medical record quality scoring system based on the multiple scoring criteria;

[0095] Step S302: Compare and score the medical record data using a preset medical record quality scoring system, obtain the scoring results, and determine the passing score distribution and failing score distribution of the medical record data based on the scoring results;

[0096] Step S303: determining the qualified attributes of the medical record data based on the passing score distribution and the failing score distribution, wherein the qualified attributes include: fully qualified, partially qualified, partially qualified, and fully unqualified;

[0097] Step S304: Determine the data value of the medical record data and the degree of consistency with the diagnosis and treatment process based on the qualified attributes, and determine the availability of the medical record based on the data value and the degree of consistency with the diagnosis and treatment process.

[0098] The beneficial effects of the above technical solution are: constructing a preset medical record quality scoring system based on multiple scoring standards, scoring the quality of medical records, determining the passing score distribution and failing score distribution and qualified attributes of the medical record data, being able to quickly understand the medical record data and improve diagnosis and treatment efficiency. At the same time, it improves the usability of medical records and their adaptability to other medical records, and reduces medical errors caused by manual recording errors and missing information.

[0099] In one embodiment, before selecting valid medical records based on medical record availability, determining time specification parameters and content specification parameters based on quality control rules, and performing quality control processing on the valid medical records using the time specification parameters and content specification parameters, the method further includes:

[0100] Obtain free text from medical records, extract descriptive content from the free text, and structure the free text according to the treatment process using NIP technology;

[0101] Determine multiple data nodes based on the processing results. Use predefined text extraction technology based on professional medical terminology to extract important parameters from each data node;

[0102] Perform context matching and semantic analysis on important parameters to obtain the entity concepts corresponding to each data node;

[0103] The current quality control content of each data node is determined based on the entity concept corresponding to each data node.

[0104] The beneficial effects of the above technical solution are: obtaining the descriptive content of the free text of the medical record and performing structured processing, extracting important parameters in each data node and performing semantic analysis processing, being able to more accurately understand the content of the medical record, determining the current quality control content of each data node, being able to quickly locate problems and correct them, reducing redundant steps and errors in data processing, and thus improving overall data processing efficiency.

[0105] In one embodiment, valid medical records are screened based on medical record availability, time specification parameters and content specification parameters are determined based on quality control rules, and quality control processing is performed on the valid medical records using the time specification parameters and content specification parameters, including:

[0106] Screen out reliable medical records, pending verification medical records, and unreliable medical records based on medical record availability, obtain manual verification results of pending verification medical records, screen out verified medical records based on manual verification results, and confirm verified medical records and reliable medical records as valid medical records;

[0107] Determine the standard registration time parameters and standard execution time parameters for each treatment process according to the quality control rules, and determine the time specification parameters based on the standard registration time parameters and standard execution time parameters;

[0108] Obtain statistical behavior parameters and result status description parameters of each treatment process, and determine content specification parameters of each treatment process based on the statistical behavior parameters and result status description parameters;

[0109] Determine the quality control standards based on the time specification parameters and content specification parameters, and determine the data quality control requirements for each data node based on the quality control standards;

[0110] According to the data quality control requirements for each data node, valid medical records are quality controlled and defects and anomalies are located and feedback is provided.

[0111] The beneficial effects of the above technical solution are: determining the quality control standards based on the time specification parameters and content specification parameters, thereby determining the data quality control requirements for each data node, which can ensure the accuracy and consistency of the data. At the same time, it makes the source and processing of the data more transparent. Furthermore, quality control processing of valid medical records and defect and anomaly positioning and feedback can be performed, which can enhance the integrity and standardization of medical records.

[0112] In one embodiment, determining medical record defects based on quality control results, performing feedback and modification based on the medical record defects, and performing a second-order final quality control on valid medical records include:

[0113] Determine the quality parameters of each link based on the quality control results, determine the medical record defects based on the quality parameters of each link, determine the modification parameters based on the medical record defects and provide reminder feedback;

[0114] Receive the attending physician's revisions to the disease defects and replace the original medical record content to generate a quality-controlled medical record;

[0115] Obtain effective quality evaluation indicators for the second-order final quality control, and conduct second-order final quality control on the medical records after quality control based on the effective quality evaluation indicators;

[0116] The final qualified judgment result of the medical record after quality control is determined based on the second-level quality control results, and a data view is generated based on the final qualified judgment result for display.

[0117] The beneficial effects of the above technical solution are: determining medical record defects based on quality control results, and determining modification parameters and reminder feedback, which can ensure the accuracy and completeness of medical records. Furthermore, the medical records after quality control are subjected to second-order final quality control based on the effective quality evaluation indicators of the second-order final quality control, so as to determine the final qualified judgment results of the medical records and perform visual display, which can improve the qualification and credibility of the medical records.

[0118] In one embodiment, determining the data value of the medical record data and the degree of consistency with the diagnosis and treatment process based on the qualified attributes, and determining the usability of the medical record based on the data value and the degree of consistency with the diagnosis and treatment process, includes:

[0119] Determine the patient's diagnosed disease based on medical record data, obtain the medical record sequence corresponding to the diagnosed disease, and obtain the diagnosis and treatment process of the diagnosed disease based on the medical record sequence;

[0120] Determine the examination items based on the diagnosis and treatment process, and determine the parameters for the complete examination results of each examination item based on the hierarchical model of the examination items;

[0121] The diagnostic vocabulary feature vector and diagnostic vocabulary feature frequency are determined based on the parameters of the improved examination results through the bag-of-words model;

[0122] Determine the current vocabulary feature summary amount and vocabulary feature scanning frequency based on the qualified attributes and the item result description parameters of each inspection item;

[0123] Determine the differences in vocabulary feature clustering and vocabulary feature frequency distribution based on the diagnostic vocabulary feature vectors, diagnostic vocabulary feature frequencies, current vocabulary feature summary, and vocabulary feature scanning frequencies;

[0124] Determine the data value of each inspection item based on the differences in vocabulary feature clustering and vocabulary feature frequency distribution;

[0125] Determine the total data value of medical record data based on the individual weight of each examination item in the diagnosis and treatment process;

[0126] Obtain clinical pathways and review pathways for diagnosis and treatment processes related to the disease, and determine scheduling medical resources and timing control features based on these pathways;

[0127] Construct a workflow model for disease-related diagnosis and treatment processes based on scheduling medical resources and timing control features;

[0128] Determine fixed diagnosis and treatment parameters and changeable diagnosis and treatment parameters according to the workflow model, and obtain corresponding data of the fixed diagnosis and treatment parameters and the changeable diagnosis and treatment parameters in the medical record data respectively;

[0129] Determine the record missing attributes of the corresponding data of the fixed diagnosis and treatment parameters and the changeable diagnosis and treatment parameters in the medical record data according to the qualified attributes;

[0130] Determine the consistency of medical record data with the diagnosis and treatment process based on the missing record attributes, and determine complete and missing medical records based on the total data value of the medical record data and the consistency of the diagnosis and treatment process;

[0131] Complete medical records are identified as usable medical records, and missing medical records are identified as unusable medical records.

[0132] The beneficial effects of the above technical solution are: by determining the data value of each examination item based on the differences in vocabulary feature clustering and vocabulary feature frequency distribution, and then determining the total value of the medical record data, the record data on the medical record text can be compared with features and word frequency vectors based on the result parameters of the standard examination items to perform value assessment, thereby judging the patient's examination application on each examination item, improving the judgment accuracy and reliability, and further, by checking the missing attributes of the records in the case data, the patient's actual diagnosis and treatment steps in the diagnosis and treatment process can be intuitively determined, and then the degree of consistency with the diagnosis and treatment process can be judged, which lays a reference foundation for the subsequent qualitative usability of medical records and improves practicality.

[0133] In one embodiment, after creating a medical record content quality control system database and formulating quality control rules, the following steps are also included:

[0134] Determine multiple quality control items and the primary quality control logic and secondary quality control logic for each quality control item according to quality control rules;

[0135] Respectively obtain the quality control forms and quality control data characteristics of the first-level quality control logic and the second-level quality control logic, and determine the quality control factors of the first-level quality control logic and the second-level quality control logic according to the quality control forms and quality control data characteristics;

[0136] Determine common quality control factors and independent quality control factors based on quality control factors, and construct a universal expression based on the common quality control factors;

[0137] Construct the characteristic expressions of the first-level quality control logic and the second-level quality control logic according to the independent quality control factors;

[0138] Obtain the rule configuration parameters of the quality control rules, and substitute the rule configuration parameters into the general expression and characteristic expression to generate coarse-grained quality control rules and fine-grained quality control rules;

[0139] Determine the post-quality control form of the quality control object through coarse-grained quality control rules and fine-grained quality control rules, and determine the rule attributes of the coarse-grained quality control rules and fine-grained quality control rules based on the post-quality control form. The rule attributes include: rules for in-process intervention in medical record completion, rules for pre-reminders for medical record filling, and rules for post-quality control of medical record content;

[0140] The quality control feedback form is set according to the respective rule attributes of the coarse-grained quality control rules and the fine-grained quality control rules, and the quality control feedback form is associated with the quality control rules to provide feedback on various medical record defects in the quality control process of the medical record data.

[0141] The beneficial effects of the above technical solution are: by qualitatively characterizing the rule attributes of coarse-grained quality control rules and fine-grained quality control rules and providing quality control feedback, the real-time medical records filled out by doctors can be tracked and feedback can be provided in a timely manner, and the low-quality problems of medical records can be avoided by penetrating from the data surface to the causes of the problems, thereby avoiding the backlog of old problems and the frequent emergence of new problems, and improving practicality and reliability.

[0142] In one embodiment, this embodiment also discloses a medical record quality monitoring system based on big data, such as Figure 4 As shown, the system includes:

[0143] Creation module 401, for creating a medical record content quality control system database and formulating quality control rules, collecting medical record data and inputting it into the medical record content quality control system database;

[0144] Determination module 402, for scoring the medical record data using a preset medical record quality scoring system, determining qualified attributes of the medical record data based on the scoring results, and determining the usability of the medical record based on the qualified attributes;

[0145] The first quality control module 403 is used to screen out valid medical records based on their availability, determine time specification parameters and content specification parameters based on quality control rules, and perform quality control processing on the valid medical records using the time specification parameters and content specification parameters;

[0146] The second quality control module 404 is used to determine medical record defects based on the quality control results, perform feedback modification based on the medical record defects, and perform second-order final quality control on the valid medical records.

[0147] The working principle and beneficial effects of the above technical solution have been explained in the method embodiment and will not be repeated here.

[0148] Those skilled in the art should understand that the first and second in the present invention simply refer to different application stages.

[0149] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0150] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for monitoring the quality of medical records based on big data, characterized in that: The following steps are involved: S1. Create a medical record content quality control system database and formulate quality control rules, collect medical record data and input it into the medical record content quality control system database; S2. Scoring the medical record data using a pre-set medical record quality scoring system, determining the qualified attributes of the medical record data based on the scoring results, and determining the usability of the medical record based on the qualified attributes; S3. Filter out valid medical records based on their availability, determine time specification parameters and content specification parameters based on quality control rules, and perform quality control on the valid medical records using the time specification parameters and content specification parameters; S4. Determine medical record deficiencies based on quality control results, provide feedback and make corrections based on these deficiencies, and conduct secondary final quality control on valid medical records; in Step S2 includes: obtaining multiple scoring standards according to the hospital medical record scoring work model, and constructing a preset medical record quality scoring system according to the multiple scoring standards; Compare and score the medical record data using a preset medical record quality scoring system, obtain the scoring results, and determine the passing score distribution and failing score distribution of the medical record data based on the scoring results; Determine the qualified attributes of the medical record data based on the passing score distribution and the failing score distribution, wherein the qualified attributes include: fully qualified, partially qualified, partially qualified, and fully unqualified; Determine the data value of medical record data and the degree of consistency with the diagnosis and treatment process based on qualified attributes, and determine the usability of medical records based on the data value and the degree of consistency with the diagnosis and treatment process; The method of determining the data value of medical record data and the degree of consistency with the diagnosis and treatment process based on qualified attributes, and determining the usability of medical records based on the data value and the degree of consistency with the diagnosis and treatment process, includes: Determine the patient's diagnosed disease based on medical record data, obtain the medical record sequence corresponding to the diagnosed disease, and obtain the diagnosis and treatment process of the diagnosed disease based on the medical record sequence; determine the examination items based on the diagnosis and treatment process, and determine the complete examination result parameters for each examination item based on the hierarchical model of the examination items; The diagnostic vocabulary feature vector and diagnostic vocabulary feature frequency are determined based on the parameters of the improved examination results through the bag-of-words model; Determine the current vocabulary feature summary amount and vocabulary feature scanning frequency based on the qualified attributes and the item result description parameters of each inspection item; determine the vocabulary feature clustering difference and vocabulary feature frequency distribution difference based on the diagnostic vocabulary feature vector and diagnostic vocabulary feature frequency and the current vocabulary feature summary amount and vocabulary feature scanning frequency; determine the data value of each inspection item based on the vocabulary feature clustering difference and vocabulary feature frequency distribution difference; Determine the total data value of medical record data based on the individual weight of each examination item in the diagnosis and treatment process; Obtain clinical pathways and review pathways for diagnosis and treatment processes related to the disease, and determine scheduling medical resources and timing control features based on the clinical pathways and review pathways; construct a workflow model for diagnosis and treatment processes related to the disease based on scheduling medical resources and timing control features; determine fixed and changeable diagnosis and treatment parameters based on the workflow model, and obtain the corresponding data for the fixed and changeable diagnosis and treatment parameters in the medical record data; Determine the record missing attributes of the corresponding data of the fixed diagnosis and treatment parameters and the changeable diagnosis and treatment parameters in the medical record data based on the qualified attributes; determine the consistency of the diagnosis and treatment process of the medical record data based on the record missing attributes; and determine the complete medical records and missing medical records based on the total data value of the medical record data and the consistency of the diagnosis and treatment process; Complete medical records are identified as usable medical records, and missing medical records are identified as unusable medical records.

2. The method for monitoring medical record quality based on big data according to claim 1, characterized in that: The creation of a medical record content quality control system database and the formulation of quality control rules include: Determine the standard data structure of medical record data, and design data table fields and data table relationships based on the standard data structure; Use SQL statements to create database and table structures based on data table fields and data table relationships, and build a medical record content quality control system database based on the database and table structures; Determine quality control objectives based on medical record writing standards and medical record quality evaluation standards; Quality control rules are formulated based on the quality control objectives and the professional review opinions of senior qualified doctors from tertiary hospitals.

3. The method for monitoring medical record quality based on big data according to claim 1, characterized in that: The collection of medical record data and input into the medical record content quality control system database includes: Identify the data sources of multiple medical business systems and collect medical data from multiple data sources using data extraction technology in accordance with communication and interoperability standards; Clean and quantify medical data, determine the data items of diagnosis and treatment plan and treatment process, screen and classify medical data according to the data items, and obtain high-quality medical record data; Load high-quality pathology data into the medical record content quality control system database.

4. The method for monitoring medical record quality based on big data according to claim 1, characterized in that: After valid medical records are screened out based on their availability, time specification parameters and content specification parameters are determined based on quality control rules, and quality control processing is performed on the valid medical records using the time specification parameters and content specification parameters, the following steps are also included: Obtain free text from medical records, extract descriptive content from the free text, and structure the free text according to the treatment process using NIP technology; Determine multiple data nodes based on the processing results, and use a predefined text extraction technology based on a professional medical terminology library to extract important parameters from each data node; Perform context matching and semantic analysis on important parameters to obtain the entity concepts corresponding to each data node; The current quality control content of each data node is determined based on the entity concept corresponding to each data node.

5. The method for monitoring medical record quality based on big data according to claim 4, characterized in that: Valid medical records are screened out based on their availability, and time and content specification parameters are determined based on quality control rules. Qualification control is then performed on valid medical records using these parameters, including: Screen out reliable medical records, pending verification medical records, and unreliable medical records based on medical record availability, obtain manual verification results of pending verification medical records, screen out verified medical records based on manual verification results, and confirm verified medical records and reliable medical records as valid medical records; Determine the standard registration time parameters and standard execution time parameters for each treatment process according to the quality control rules, and determine the time specification parameters based on the standard registration time parameters and standard execution time parameters; Obtain statistical behavior parameters and result status description parameters of each treatment process, and determine content specification parameters of each treatment process based on the statistical behavior parameters and result status description parameters; Determine the quality control standards based on the time specification parameters and content specification parameters, and determine the data quality control requirements for each data node based on the quality control standards; According to the data quality control requirements for each data node, valid medical records are quality controlled and defects and anomalies are located and feedback is provided.

6. The method for monitoring medical records quality based on big data according to claim 1, characterized in that: The aforementioned process of determining medical record defects based on quality control results, providing feedback and modification based on medical record defects, and conducting secondary final quality control on valid medical records includes: Determine the quality parameters of each link based on the quality control results, determine the medical record defects based on the quality parameters of each link, determine the modification parameters based on the medical record defects and provide reminder feedback; Receive the attending physician's revisions to the disease defects and replace the original medical record content to generate a quality-controlled medical record; Obtain effective quality evaluation indicators for the second-order final quality control, and conduct second-order final quality control on the medical records after quality control based on the effective quality evaluation indicators; The final qualified judgment result of the medical record after quality control is determined based on the second-level quality control results, and a data view is generated based on the final qualified judgment result for display.

7. The method for monitoring medical record quality based on big data according to claim 1, characterized in that: After creating the medical record content quality control system database and formulating quality control rules, it also includes: Determine multiple quality control items and the primary quality control logic and secondary quality control logic for each quality control item according to quality control rules; Respectively obtain the quality control forms and quality control data characteristics of the first-level quality control logic and the second-level quality control logic, and determine the quality control factors of the first-level quality control logic and the second-level quality control logic according to the quality control forms and quality control data characteristics; Determine common quality control factors and independent quality control factors based on quality control factors, and construct a universal expression based on the common quality control factors; Construct the characteristic expressions of the first-level quality control logic and the second-level quality control logic according to the independent quality control factors; Obtain the rule configuration parameters of the quality control rules, and substitute the rule configuration parameters into the general expression and characteristic expression to generate coarse-grained quality control rules and fine-grained quality control rules; Determine the post-quality control form of the quality control object through coarse-grained quality control rules and fine-grained quality control rules, and determine the rule attributes of the coarse-grained quality control rules and fine-grained quality control rules based on the post-quality control form. The rule attributes include: rules for in-process intervention in medical record completion, rules for pre-reminders for medical record filling, and rules for post-quality control of medical record content; The quality control feedback form is set according to the respective rule attributes of the coarse-grained quality control rules and the fine-grained quality control rules, and the quality control feedback form is associated with the quality control rules to provide feedback on various medical record defects in the quality control process of the medical record data.

8. A medical record quality monitoring system based on big data, characterized by: The system includes: Creation module, used to create a medical record content quality control system database and formulate quality control rules, collect medical record data and input it into the medical record content quality control system database; A determination module is used to score the medical record data using a preset medical record quality scoring system, determine the qualified attributes of the medical record data based on the scoring results, and determine the usability of the medical record based on the qualified attributes; The first quality control module is used to screen out valid medical records based on their availability, determine time specification parameters and content specification parameters based on quality control rules, and perform quality control processing on the valid medical records using the time specification parameters and content specification parameters; The second quality control module is used to determine medical record defects based on quality control results, provide feedback and modification based on medical record defects, and perform second-order final quality control on valid medical records; The determination module includes: obtaining multiple scoring standards based on the hospital medical record scoring work model, and constructing a preset medical record quality scoring system based on the multiple scoring standards; Compare and score the medical record data using a preset medical record quality scoring system, obtain the scoring results, and determine the passing score distribution and failing score distribution of the medical record data based on the scoring results; Determine the qualified attributes of the medical record data based on the passing score distribution and the failing score distribution, wherein the qualified attributes include: fully qualified, partially qualified, partially qualified, and fully unqualified; Determine the data value of medical record data and the degree of consistency with the diagnosis and treatment process based on qualified attributes, and determine the usability of medical records based on the data value and the degree of consistency with the diagnosis and treatment process; The method of determining the data value of medical record data and the degree of consistency with the diagnosis and treatment process based on qualified attributes, and determining the usability of medical records based on the data value and the degree of consistency with the diagnosis and treatment process, includes: Determine the patient's diagnosed disease based on medical record data, obtain the medical record sequence corresponding to the diagnosed disease, and obtain the diagnosis and treatment process of the diagnosed disease based on the medical record sequence; determine the examination items based on the diagnosis and treatment process, and determine the complete examination result parameters for each examination item based on the hierarchical model of the examination items; The diagnostic vocabulary feature vector and diagnostic vocabulary feature frequency are determined based on the parameters of the improved examination results through the bag-of-words model; Determine the current vocabulary feature summary amount and vocabulary feature scanning frequency based on the qualified attributes and the item result description parameters of each inspection item; determine the vocabulary feature clustering difference and vocabulary feature frequency distribution difference based on the diagnostic vocabulary feature vector and diagnostic vocabulary feature frequency and the current vocabulary feature summary amount and vocabulary feature scanning frequency; determine the data value of each inspection item based on the vocabulary feature clustering difference and vocabulary feature frequency distribution difference; Determine the total data value of medical record data based on the individual weight of each examination item in the diagnosis and treatment process; Obtain clinical pathways and review pathways for diagnosis and treatment processes related to the disease, and determine scheduling medical resources and timing control features based on the clinical pathways and review pathways; construct a workflow model for diagnosis and treatment processes related to the disease based on scheduling medical resources and timing control features; determine fixed and changeable diagnosis and treatment parameters based on the workflow model, and obtain the corresponding data for the fixed and changeable diagnosis and treatment parameters in the medical record data; Determine the record missing attributes of the corresponding data of fixed diagnosis and treatment parameters and changeable diagnosis and treatment parameters in the medical record data based on the qualified attributes; determine the consistency of the diagnosis and treatment process of the medical record data based on the record missing attributes; and determine complete medical records and missing medical records based on the total data value of the medical record data and the consistency of the diagnosis and treatment process; Complete medical records are identified as usable medical records, and missing medical records are identified as unusable medical records.

Images