Medical record quality control method, system, terminal and storage medium

Abstract

This invention provides a method, system, terminal, and storage medium for medical record quality control. The method includes: acquiring medical record documents written by doctors and performing structured processing on the medical record documents to obtain structured information; acquiring monitoring content for each structural item in the structured information and acquiring quality standards for each structural item; performing quality testing on the corresponding monitoring content according to the quality standards to obtain a quality score, and generating a medical record quality control result based on the quality score; and providing writing error reminders to the medical record documents based on the quality control result. In this embodiment, the medical record quality control result can be automatically generated based on the quality score, and writing error reminders can be effectively provided automatically based on the quality control result, achieving real-time quality control of medical record documents without the need for manual quality control, thus improving the efficiency of medical record quality control.

Description

Technical Field

[0001] This invention relates to the field of smart healthcare technology, and in particular to a method, system, terminal, and storage medium for medical record quality control. Background Technology

[0002] Medical records refer to the sum of written materials, charts, images, slides, and other data generated by medical personnel during medical activities. They are legally significant documents and powerful evidence in cases of reversed burden of proof. With the rapid development of information technology, electronic medical record systems have become increasingly widespread in hospitals at all levels. Compared to traditional paper medical records, electronic medical records offer advantages such as ease of writing, convenient interaction, and flexible access. Their emergence has facilitated writing and searching for medical personnel, improving work efficiency. However, it has also revealed some issues with the quality of medical records and has become an important component of medical quality management. The in-depth application of electronic medical records has provided a new platform for medical record quality control, making real-time quality control of electronic medical records possible—how to effectively manage the quality of electronic medical records has become a new challenge for hospital quality management departments.

[0003] In the current medical record quality control process, manual quality control is generally relied upon, which results in long processing times and low accuracy, thus reducing the efficiency of medical record quality control. Summary of the Invention

[0004] The purpose of this invention is to provide a medical record quality control method, system, terminal, and storage medium, aiming to solve the problem of low efficiency in existing medical record quality control.

[0005] This invention is implemented as follows: a medical record quality control method, the method comprising:

[0006] Obtain medical records written by doctors and perform structured processing on the medical records to obtain structured medical record information;

[0007] The monitoring content of each structural item in the structured information of the medical record is obtained respectively, and the quality standard of each structural item is obtained respectively;

[0008] The corresponding monitoring content is subjected to quality testing according to the quality standards to obtain a quality score, and the medical record quality control result of the medical record document is generated based on the quality score.

[0009] Based on the medical record quality control results, errors in the medical record documents will be highlighted.

[0010] Preferably, the step of acquiring the monitoring content of each structural item in the structured information of the medical record includes:

[0011] The content of each structural item in the structured information of the medical record is obtained respectively, and the structural entity type is determined according to the item identifier of each structural item;

[0012] For each structural item, entity identification is performed according to the type of each structural entity, and the monitoring content of each structural item is determined based on the entity identification results.

[0013] Preferably, the step of identifying entities based on their types and determining the monitoring content for each structural item based on the entity identification results includes:

[0014] The content of each structural item is identified by the item column to obtain the structural item column, and the entity type of each structural item column is matched with the structural entity type.

[0015] If the entity type of any of the structure item columns matches the structure entity type, then the content corresponding to the structure item column is determined as the first monitoring sub-content.

[0016] For each structural item content, the unmatched structural entity types are matched with the entity types of each word in the structural item content, and the second monitoring sub-content is determined based on the word matching results. The monitoring content includes the first monitoring sub-content and the second monitoring sub-content.

[0017] If any of the structural entity types does not match the entity types in the structural item column and the entity types of each word, then a missing item prompt will be added to the monitored content according to the structural entity type.

[0018] Preferably, the step of performing quality testing on the corresponding monitoring content according to the quality standard includes:

[0019] If the quality standard includes a range of parameter values, then determine whether the parameter values ​​in the monitored content are within the range of parameter values;

[0020] If the parameter value in the monitored content is not within the range of the parameter value, then query the deduction value of the parameter value range, and mark the monitored content with a deduction based on the deduction value of the parameter value range;

[0021] If the quality standard includes data item detection conditions, then determine whether the monitoring content stores the data content corresponding to each data item detection condition;

[0022] If the monitored content does not contain the data content corresponding to the data item detection condition, then the deduction value of the data item detection condition is queried, and the monitored content is marked with a deduction based on the deduction value of the data item detection condition.

[0023] For each monitoring item, the sum of the values ​​between each deduction mark is calculated to obtain the total deduction value, and the difference between the quality score threshold and the total deduction value is calculated to obtain the quality score.

[0024] Preferably, the step of generating the medical record quality control result based on the quality score includes:

[0025] If the quality score is less than the quality score threshold, then the structural item and deduction factor corresponding to the quality score are obtained to obtain the deduction information;

[0026] The quality score, the doctor's number, the medical record document's identifier, and the deduction information are stored to obtain the medical record quality control result.

[0027] Preferably, the step of providing error reminders for the medical record documents based on the medical record quality control results includes:

[0028] If any of the quality scores is less than the quality score threshold, the monitoring content corresponding to the quality score is highlighted, and the deduction factor corresponding to the quality score is obtained.

[0029] Based on the obtained deduction factors, a prompt message is generated, and the monitoring content corresponding to the quality score is marked according to the prompt message.

[0030] Preferably, before obtaining the medical records written by the doctor, the process further includes:

[0031] Based on the doctor's ID, query the historical deduction records and calculate the reminder priority for each historical deduction factor in the historical deduction records;

[0032] Based on the reminder priority, the target factor among the historical deduction factors is determined, and the pre-reminder items and pre-reminder information are determined based on the target factor;

[0033] The doctor's current medical record template is given a pre-reminder based on the pre-reminder item and the pre-reminder information.

[0034] Another objective of this invention is to provide a medical record quality control system, the system comprising:

[0035] The structured module is used to acquire medical records written by doctors and perform structured processing on the medical records to obtain structured medical record information.

[0036] The standard acquisition module is used to acquire the monitoring content of each structural item in the structured information of the medical record, and to acquire the quality standard of each structural item.

[0037] The quality inspection module is used to perform quality inspection on the corresponding monitoring content according to the quality standard, obtain a quality score, and generate the medical record quality control result of the medical record document based on the quality score.

[0038] The error alert module is used to provide writing error alerts for the medical record documents based on the medical record quality control results.

[0039] Another objective of this invention is to provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0040] Another objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0041] In this embodiment of the invention, by performing structured processing on medical records, the structured information in the medical records can be effectively obtained. By separately obtaining the monitoring content of each structural item in the structured information of the medical records, the accuracy of quality detection is effectively improved. Based on quality standards, the corresponding monitoring content is subjected to quality detection to detect the data quality of each monitoring content and obtain a quality score. Based on the quality score, the medical record quality control result can be automatically generated. Based on the medical record quality control result, the writing error reminders of the medical records can be effectively and automatically provided to achieve real-time quality control of the medical records without the need for manual quality control, thus improving the efficiency of medical record quality control. Attached Figure Description

[0042] Figure 1 This is a flowchart of the medical record quality control method provided in the first embodiment of the present invention;

[0043] Figure 2 This is a schematic diagram of the structured analysis results provided in the first embodiment of the present invention;

[0044] Figure 3 This is a schematic diagram of the quality standard provided in the first embodiment of the present invention;

[0045] Figure 4 This is a schematic diagram of the admission record provided in the first embodiment of the present invention;

[0046] Figure 5 This is a schematic diagram of write-time quality control provided in the first embodiment of the present invention;

[0047] Figure 6 This is a flowchart of the medical record quality control method provided in the second embodiment of the present invention;

[0048] Figure 7 This is a schematic diagram of the medical record quality control system provided in the third embodiment of the present invention;

[0049] Figure 8This is a schematic diagram of the structure of the terminal device provided in the fourth embodiment of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0051] Existing medical record quality control processes only focus on the required completion time and mandatory fields specified in the medical records. This low-level quality control lacks in-depth, intrinsic quality control. For example, it doesn't require males to have endometritis, family history to include "health, illness, and death information of immediate family members," and diagnostic codes to conform to ICD-10 standards. Furthermore, it fails to provide timely and intelligent reminders for medical staff to correct errors and ensure accurate completion. This invention, based on medical record quality control results, can effectively and automatically provide error reminders for medical records, achieving real-time quality control without the need for manual intervention, thus improving the efficiency of medical record quality control.

[0052] To illustrate the technical solution described in this invention, specific embodiments are described below.

[0053] Example 1

[0054] Please see Figure 1 This is a flowchart of a medical record quality control method provided in the first embodiment of the present invention. This medical record quality control method can be applied to any terminal device or system, and includes the following steps:

[0055] Step S10: Obtain the medical record document written by the doctor, and perform structured processing on the medical record document to obtain structured medical record information;

[0056] This embodiment, from the perspective of strengthening medical quality management, standardizing medical service behavior, and ensuring medical safety, helps hospitals establish a multi-dimensional quality management indicator system covering basic quality, process quality, and final quality. It uses data acquisition technology to collect and integrate basic data (departments, patients, physicians, etc.) and business data (medical orders, diagnoses, medical records, consultations, surgeries, blood transfusions, examinations, tests, etc.) from management and clinical systems operating across platforms or heterogeneously within the hospital in real time. It uses data warehouse technology to extract data such as relational data and text data from the hospital's scattered and heterogeneous data sources, and through cleaning, transformation, and integration, loads them into the data warehouse to achieve the integration of all medical quality data (including outpatient, inpatient, and discharged).

[0057] Intelligent applications require high-quality medical data as support; therefore, data standardization and structured governance are the foundation for achieving intelligent management of medical quality. Data governance mainly relies on authoritative domestic and international clinical guidelines to build a unified terminology database. Natural Language Processing (NLP) is used to transform unstructured electronic medical record text into standardized, structured data that can be used for knowledge graph construction and diagnostic model building, enabling structured expressions of disease diagnosis, examination and testing, symptoms and signs, drug names, surgical procedures, etc.

[0058] Structured information such as disease diagnosis, examination and testing, symptoms and signs, drug names, and surgical procedures are used to create separate indexes for disease diagnosis, examination and testing, symptoms and signs, drugs, and surgery, which are then stored in Elasticsearch.

[0059] Taking the chief complaint in the admission record as an example, the structured analysis results of "Chief complaint: Right-sided facial spasm for 2 years." are as follows: Figure 2 In this step, medical records written by medical staff are acquired in real time. These records can be electronic or paper-based. The medical staff include doctors and nurses. When the records are paper-based, an image of the paper record is acquired, and text recognition is performed on the image to obtain the medical record document. By performing structured processing on the medical record document, the structured information in the document can be effectively obtained.

[0060] Step S20: Obtain the monitoring content of each structural item in the structured information of the medical record, and obtain the quality standard of each structural item.

[0061] Optionally, in this step, obtaining the monitoring content of each structural item in the structured information of the medical record includes:

[0062] The content of each structural item in the structured information of the medical record is obtained respectively, and the structural entity type is determined according to the item identifier of each structural item;

[0063] The system includes pre-configured structure items, the content and number of which can be customized as needed. For example, please refer to [link to relevant documentation]. Figure 2 For the admission record, the structure includes "chief complaint", "present illness", "past medical history", "personal and family history", "physical examination", "auxiliary examination" and "diagnosis", etc. The item identifiers of each structure are matched with the type lookup table to obtain the structure entity type. The type lookup table stores the correspondence between different item identifiers and corresponding structure entity types.

[0064] For each structural item, entity identification is performed based on the type of each structural entity, and the monitoring content of each structural item is determined based on the entity identification results; wherein, entity identification is performed based on the type of each structural entity to determine the monitoring content of the corresponding structural item in each structural item content.

[0065] Furthermore, in this step, the entity identification based on each structural entity type, and the determination of the monitoring content for each structural item based on the entity identification results, includes:

[0066] The content of each structural item is identified by the item column to obtain the structural item column, and the entity type of each structural item column is matched with the structural entity type.

[0067] Among them, by identifying the item column of each structural item, the presence of an item column can be detected in the content of each structural item. In this step, image recognition or text recognition can be used to locate and identify the item column in order to determine the position of the structural item column. By recognizing the title stored in the content of each structural item through text recognition, the position of the structural item column corresponding to each title can be determined. Based on the title or position in the structural item column, the entity type of each structural item column can be determined.

[0068] If the entity type of any of the structure item columns matches the structure entity type, then the content corresponding to the structure item column is determined as the first monitoring sub-content.

[0069] If the entity type of any structural item column matches the structural entity type, then the content corresponding to that structural item column is determined to be the content that needs to be monitored for the current structural item.

[0070] For each structural item content, the unmatched structural entity types are matched with the entity types of each word in the structural item content, and the second monitoring sub-content is determined based on the word matching results. The monitoring content includes the first monitoring sub-content and the second monitoring sub-content.

[0071] Specifically, by performing word matching between the unmatched structural entity types and the entity types of each word in the content of the structural item, it is determined whether each word in the content of the structural item belongs to the content that needs to be monitored in the current structural item.

[0072] In this step, the set of associated types is determined based on the type of each structural entity, and the entity type of each word in the content of the structural item is matched with the set of associated types. The words that are successfully matched are determined as the second monitoring sub-content.

[0073] If any of the structural entity types does not match the entity types in the structural item column and the entity types of each word, then a missing message is added to the monitored content according to the structural entity type.

[0074] If any structural entity type does not match the entity type in the structural item column or the entity type of each word, it is determined that no content belonging to the current structural item that needs to be monitored was found in the monitoring content. Therefore, by adding a missing item prompt to the monitoring content, medical staff are alerted that the content that needs to be monitored is missing in the medical record.

[0075] Step S30: Perform quality inspection on the corresponding monitoring content according to the quality standard, obtain a quality score, and generate the medical record quality control result of the medical record document based on the quality score;

[0076] Among them, quality testing is carried out on the corresponding monitoring content based on quality standards to detect the data quality of each monitoring content and obtain a quality score;

[0077] Optionally, in this step, the quality inspection of the corresponding monitoring content according to the quality standard includes:

[0078] If the quality standard includes a range of parameter values, then determine whether the parameter values ​​in the monitored content are within the range of parameter values;

[0079] If the parameter value in the monitored content is not within the range of the parameter value, then query the deduction value of the parameter value range, and mark the monitored content with a deduction based on the deduction value of the parameter value range;

[0080] If the quality standard includes data item detection conditions, then determine whether the monitoring content stores the data content corresponding to each data item detection condition;

[0081] If the monitored content does not contain the data content corresponding to the data item detection condition, then the deduction value of the data item detection condition is queried, and the monitored content is marked with a deduction based on the deduction value of the data item detection condition.

[0082] For each monitoring item, the sum of the values ​​between each deduction mark is calculated to obtain the total deduction value, and the difference between the quality score threshold and the total deduction value is calculated to obtain the quality score;

[0083] Please see Figure 3The quality standards for each structural item can be set according to requirements. For example, the quality standards for the structural item "chief complaint" include data item detection conditions, which are: "1. Concise and to the point, not exceeding 20 sub-items; 2. The chief complaint reflects symptoms + (location) + duration". If the monitoring content does not store the data content corresponding to the data item detection conditions, the deduction value of the data item detection conditions is queried, and the monitoring content is marked with a deduction value based on the deduction value of the data item detection conditions. The quality score threshold can be set according to requirements, for example, the quality score threshold can be set to 10 points or 20 points, etc.

[0084] Further, in this step, generating the medical record quality control result of the medical record document based on the quality score includes:

[0085] If the quality score is less than the quality score threshold, then the structural item and deduction factor corresponding to the quality score are obtained to obtain the deduction information;

[0086] If the quality score is less than the quality score threshold, it is determined that the monitoring content corresponding to the quality score is abnormal. The deduction information is obtained by obtaining the structural items and deduction factors corresponding to the quality score and combining the obtained structural items and deduction factors.

[0087] The quality score, the doctor's number, the medical record document's identifier, and the deduction information are stored to obtain the medical record document's quality control result.

[0088] Among them, the results of medical record quality control effectively facilitate the viewing of information such as abnormal deduction factors, structural items, and corresponding writing doctors in medical record documents.

[0089] Step S40: Based on the medical record quality control results, provide writing error reminders for the medical record documents;

[0090] Among them, the system provides writing error reminders for medical records based on the results of medical record quality control, so as to achieve the effect of real-time medical record quality control. When abnormalities are detected in the medical records written by doctors, doctors can be reminded to make corrections in real time, which improves the efficiency of medical record quality control.

[0091] Optionally, in this step, the step of providing error reminders for the medical record documents based on the medical record quality control results includes:

[0092] If any of the quality scores is less than the quality score threshold, the monitoring content corresponding to the quality score is highlighted, and the deduction factor corresponding to the quality score is obtained.

[0093] Among them, by highlighting the monitored content, doctors are promptly reminded to check the highlighted content, thereby achieving the effect of real-time reminder of errors in medical record writing;

[0094] Based on the obtained deduction factors, a prompt message is generated, and based on the prompt message, the monitoring content corresponding to the quality score is marked with information.

[0095] Among them, information is marked on the monitoring content corresponding to the quality score based on the prompt information, so as to remind doctors to supplement or modify the monitoring content.

[0096] In this embodiment, intrinsic quality control can be carried out from aspects such as content completeness, logical consistency, diagnostic adequacy, and drug interactions. By understanding the semantics of medical records, defective content can be found and the causes can be identified, thus realizing comprehensive quality control and review of clinical medical records.

[0097] Taking the quality monitoring of admission records as an example, in addition to monitoring the completion of admission records within 24 hours after the patient's admission, it can also fully cover the monitoring of the content from general items, chief complaint, present illness history, past medical history, personal history, family history, physical examination, auxiliary examinations to diagnosis.

[0098] For example, please see Figure 4 As required, family history must include "the health, illness and death of immediate family members". The platform judges the family history according to the rule base and gives the judgment result, so that medical workers can make modifications immediately, saving time and energy.

[0099] Please see Figure 5 This embodiment, based on big data technology, utilizes the patient's full-document medical record information to achieve real-time quality control, providing timely reminders and corrections for medical staff. This makes it easy for medical staff to write correct medical records and difficult to write incorrect ones, improving the quality of hospital medical records and saving valuable time for medical staff. Outpatient, inpatient, and discharge medical records are collected. Data cleaning is performed on these records using Extract-Transform-Load (ETL) technology. The cleaned data is then standardized, and unstructured data is extracted using Natural Language Processing (NLP). The extracted structured data is then stored in big data, facilitating rapid searching of the structured data. This big data storage and rapid searching facilitate on-the-spot quality control of the medical records written by clinicians.

[0100] In this embodiment, by performing structured processing on medical records, the structured information in the medical records can be effectively obtained. By obtaining the monitoring content of each structural item in the structured information of the medical records, the accuracy of quality detection is effectively improved. Based on the quality standards, the corresponding monitoring content is subjected to quality detection to detect the data quality of each monitoring content and obtain a quality score. Based on the quality score, the medical record quality control result can be automatically generated. Based on the medical record quality control result, the writing error reminder can be effectively and automatically provided to the medical records, so as to achieve the real-time quality control effect of the medical records, without the need for manual quality control, thus improving the efficiency of medical record quality control.

[0101] Example 2

[0102] Please see Figure 6 This is a flowchart of a medical record quality control method provided in the second embodiment of the present invention. This embodiment is used to further refine the steps before step S10 in the first embodiment, including the following steps:

[0103] Step S50: Query the historical deduction records according to the doctor's number, and calculate the reminder priority of each historical deduction factor in the historical deduction records respectively;

[0104] Among them, the doctor's number is matched with the historical quality control database to obtain the historical deduction record. The historical quality control database stores the correspondence between different doctor numbers and corresponding historical deduction records. By calculating the reminder priority of each historical deduction factor in the historical deduction record, the accuracy of subsequent target factor determination is improved.

[0105] In this step, the recording time of each historical deduction factor is obtained, and each historical deduction factor is filtered according to the preset duration and recording time. The preset duration can be set according to the needs, for example, the preset duration can be set to 1 week, 1 month or 2 months, etc.

[0106] In this step, historical deduction factors within one week of the current time point are obtained, and the factor identifier corresponding to each historical deduction factor is queried. The priority coefficient is determined based on the factor identifier of each historical deduction factor, and the reminder priority of each historical deduction factor is determined based on the number of deductions and the priority coefficient. In this step, the factor identifier of each historical deduction factor is matched with the coefficient lookup table to obtain the priority coefficient. The coefficient lookup table stores the correspondence between different factor identifiers and their corresponding priority coefficients.

[0107] Step S60: Determine the target factor among the historical deduction factors according to the reminder priority, and determine the pre-reminder item and pre-reminder information according to the target factor;

[0108] Specifically, the historical deduction factors corresponding to the highest reminder priority are identified as target factors, and the structural items corresponding to the target factors are queried. The structural items corresponding to the target factors are identified as pre-reminder items, and the pre-reminder information is determined according to the identifier of the pre-reminder item. The pre-reminder information is used to remind doctors to pay attention to the monitoring content that needs to be filled in or selected when writing the pre-reminder item.

[0109] Step S70: Provide a pre-reminder to the doctor's current medical record template based on the pre-reminder item and the pre-reminder information;

[0110] Specifically, in the doctor's current medical record template, a text prompt is provided for the pre-reminder item based on the pre-reminder information, so as to achieve the effect of pre-reminder when the doctor writes the medical record.

[0111] In this embodiment, the system can effectively remind doctors of common errors or omissions in the process of writing medical records before they are written, thus preventing the same errors from recurring in the current writing process and improving the accuracy of medical record writing. This effectively achieves the effect of early quality control.

[0112] Example 3

[0113] Please see Figure 7 This is a schematic diagram of the structure of a medical record quality control system 100 provided in the third embodiment of the present invention, including: a structured module 10, a standard acquisition module 11, a quality detection module 12, and an error reminder module 13, wherein:

[0114] The structuring module 10 is used to acquire medical records written by doctors and perform structuring processing on the medical records to obtain structured medical record information.

[0115] The standard acquisition module 11 is used to acquire the monitoring content of each structural item in the structured information of the medical record, and to acquire the quality standard of each structural item.

[0116] Optionally, the standard acquisition module 11 is also used to: acquire the content of each structural item in the structured information of the medical record, and determine the structural entity type according to the item identifier of each structural item;

[0117] For each structural item, entity identification is performed according to the type of each structural entity, and the monitoring content of each structural item is determined based on the entity identification results.

[0118] Furthermore, the standard acquisition module 11 is also used to: identify the item column of each structural item content to obtain the structural item column, and match the entity type of each structural item column with the structural entity type respectively;

[0119] If the entity type of any of the structure item columns matches the structure entity type, then the content corresponding to the structure item column is determined as the first monitoring sub-content.

[0120] For each structural item content, the unmatched structural entity types are matched with the entity types of each word in the structural item content, and the second monitoring sub-content is determined based on the word matching results. The monitoring content includes the first monitoring sub-content and the second monitoring sub-content.

[0121] If any of the structural entity types does not match the entity types in the structural item column and the entity types of each word, then a missing item prompt will be added to the monitored content according to the structural entity type.

[0122] The quality inspection module 12 is used to perform quality inspection on the corresponding monitoring content according to the quality standard, obtain a quality score, and generate the medical record quality control result of the medical record document based on the quality score.

[0123] Optionally, the quality inspection module 12 is further configured to: if the quality standard includes a range of parameter values, determine whether the parameter values ​​in the monitored content are within the range of parameter values;

[0124] If the parameter value in the monitored content is not within the range of the parameter value, then query the deduction value of the parameter value range, and mark the monitored content with a deduction based on the deduction value of the parameter value range;

[0125] If the quality standard includes data item detection conditions, then determine whether the monitoring content stores the data content corresponding to each data item detection condition;

[0126] If the monitored content does not contain the data content corresponding to the data item detection condition, then the deduction value of the data item detection condition is queried, and the monitored content is marked with a deduction based on the deduction value of the data item detection condition.

[0127] For each monitoring item, the sum of the values ​​between each deduction mark is calculated to obtain the total deduction value, and the difference between the quality score threshold and the total deduction value is calculated to obtain the quality score.

[0128] Furthermore, the quality detection module 12 is also used to: if the quality score is less than the quality score threshold, obtain the structural item and deduction factor corresponding to the quality score, and obtain deduction information;

[0129] The quality score, the doctor's number, the medical record document's identifier, and the deduction information are stored to obtain the medical record quality control result.

[0130] Error alert module 13 is used to provide writing error alerts for the medical record documents based on the medical record quality control results.

[0131] Optionally, the error alert module 13 is further configured to: if any of the quality scores is less than the quality score threshold, highlight the monitoring content corresponding to the quality score and obtain the deduction factor corresponding to the quality score;

[0132] Based on the obtained deduction factors, a prompt message is generated, and the monitoring content corresponding to the quality score is marked according to the prompt message.

[0133] Furthermore, the error reminder module 13 is also used to: query historical deduction records based on the doctor's number, and calculate the reminder priority of each historical deduction factor in the historical deduction record;

[0134] Based on the reminder priority, the target factor among the historical deduction factors is determined, and the pre-reminder items and pre-reminder information are determined based on the target factor;

[0135] The doctor's current medical record template is given a pre-reminder based on the pre-reminder item and the pre-reminder information.

[0136] In this embodiment, by performing structured processing on medical records, the structured information in the medical records can be effectively obtained. By acquiring the monitoring content of each structural item in the structured information of the medical records, the accuracy of quality detection is effectively improved. Based on quality standards, the corresponding monitoring content is subjected to quality detection to detect the data quality of each monitoring content and obtain a quality score. Based on the quality score, the medical record quality control result can be automatically generated. Based on the medical record quality control result, the writing error reminders of the medical records can be effectively and automatically provided to achieve real-time quality control of medical records without the need for manual quality control, thus improving the efficiency of medical record quality control.

[0137] Example 4

[0138] Figure 8 This is a structural block diagram of a terminal device 2 provided in the fourth embodiment of this application. For example... Figure 8 As shown, the terminal device 2 in this embodiment includes: a processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the processor 20, such as a program for a medical record quality control method. When the processor 20 executes the computer program 22, it implements the steps in the various embodiments of the above-described medical record quality control methods.

[0139] For example, the computer program 22 may be divided into one or more modules, which are stored in the memory 21 and executed by the processor 20 to complete this application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 22 in the terminal device 2. The terminal device may include, but is not limited to, the processor 20 and the memory 21.

[0140] The processor 20 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0141] The memory 21 can be an internal storage unit of the terminal device 2, such as a hard drive or memory of the terminal device 2. The memory 21 can also be an external storage device of the terminal device 2, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the terminal device 2. Furthermore, the memory 21 can include both internal and external storage units of the terminal device 2. The memory 21 is used to store the computer program and other programs and data required by the terminal device. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0142] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0143] If an integrated module is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer-readable storage medium can be non-volatile or volatile. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable storage medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the contents of a computer-readable storage medium may be appropriately added to or subtracted from the contents as required by the legislation and patent practice in a jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, a computer-readable storage medium may not include electrical carrier signals and telecommunication signals.

[0144] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for quality control of medical records, characterized in that, The method includes: Obtain medical records written by doctors and perform structured processing on the medical records to obtain structured medical record information; The monitoring content of each structural item in the structured information of the medical record is obtained respectively, and the quality standard of each structural item is obtained respectively; The corresponding monitoring content is subjected to quality testing according to the quality standards to obtain a quality score, and the medical record quality control result of the medical record document is generated based on the quality score. Based on the medical record quality control results, write error reminders will be provided for the medical record documents; The process of acquiring the monitoring content of each structural item in the structured information of the medical record includes: The content of each structural item in the structured information of the medical record is obtained respectively, and the structural entity type is determined according to the item identifier of each structural item; For each structural item, entity identification is performed according to the type of each structural entity, and the monitoring content of each structural item is determined based on the entity identification results. The step of identifying entities based on their types and determining the monitoring content for each structural item based on the identification results includes: The content of each structural item is identified by the item column to obtain the structural item column, and the entity type of each structural item column is matched with the structural entity type. If the entity type of any of the structure item columns matches the structure entity type, then the content corresponding to the structure item column is determined as the first monitoring sub-content. For each structural item content, the unmatched structural entity types are matched with the entity types of each word in the structural item content, and the second monitoring sub-content is determined based on the word matching results. The monitoring content includes the first monitoring sub-content and the second monitoring sub-content. If any of the structural entity types does not match the entity types in the structural item column and the entity types of each word, then a missing message is added to the monitored content according to the structural entity type. Before obtaining the medical records written by the doctor, the process also includes: Query historical deduction records based on doctor's number, and calculate the reminder priority for each historical deduction factor in the historical deduction record; Based on the reminder priority, the target factor among the historical deduction factors is determined, and the pre-reminder items and pre-reminder information are determined based on the target factor; The doctor's current medical record template is given a pre-reminder based on the pre-reminder item and the pre-reminder information.

2. The medical record quality control method as described in claim 1, characterized in that, The quality inspection of the corresponding monitoring content according to the quality standard includes: If the quality standard includes a range of parameter values, then determine whether the parameter values ​​in the monitored content are within the range of parameter values; If the parameter value in the monitored content is not within the range of the parameter value, then query the deduction value of the parameter value range, and mark the monitored content with a deduction based on the deduction value of the parameter value range; If the quality standard includes data item detection conditions, then determine whether the monitoring content stores the data content corresponding to each data item detection condition; If the monitored content does not contain the data content corresponding to the data item detection condition, then the deduction value of the data item detection condition is queried, and the monitored content is marked with a deduction based on the deduction value of the data item detection condition. For each monitoring item, the sum of the values ​​between each deduction mark is calculated to obtain the total deduction value, and the difference between the quality score threshold and the total deduction value is calculated to obtain the quality score.

3. The medical record quality control method as described in claim 2, characterized in that, The process of generating the medical record quality control result based on the quality score includes: If the quality score is less than the quality score threshold, then the structural item and deduction factor corresponding to the quality score are obtained to obtain the deduction information; The quality score, the doctor's number, the medical record document's identifier, and the deduction information are stored to obtain the medical record quality control result.

4. The medical record quality control method as described in claim 3, characterized in that, The step of providing error reminders for medical record documents based on the medical record quality control results includes: If any of the quality scores is less than the quality score threshold, the monitoring content corresponding to the quality score is highlighted, and the deduction factor corresponding to the quality score is obtained. Based on the obtained deduction factors, a prompt message is generated, and the monitoring content corresponding to the quality score is marked according to the prompt message.

5. A medical record quality control system, characterized in that, The system includes: The structured module is used to acquire medical records written by doctors and perform structured processing on the medical records to obtain structured medical record information. The standard acquisition module is used to acquire the monitoring content of each structural item in the structured information of the medical record, and to acquire the quality standard of each structural item. The quality inspection module is used to perform quality inspection on the corresponding monitoring content according to the quality standard, obtain a quality score, and generate the medical record quality control result of the medical record document based on the quality score. The error alert module is used to alert the medical record document to writing errors based on the medical record quality control results; The standard acquisition module is also used to: acquire the content of each structural item in the structured information of the medical record, and determine the structural entity type according to the item identifier of each structural item; For each structural item, entity identification is performed according to the type of each structural entity, and the monitoring content of each structural item is determined based on the entity identification results. The standard acquisition module is also used to: identify the item column of each structural item to obtain the structural item column, and match the entity type of each structural item column with the structural entity type respectively; If the entity type of any of the structure item columns matches the structure entity type, then the content corresponding to the structure item column is determined as the first monitoring sub-content. For each structural item content, the unmatched structural entity types are matched with the entity types of each word in the structural item content, and the second monitoring sub-content is determined based on the word matching results. The monitoring content includes the first monitoring sub-content and the second monitoring sub-content. If any of the structural entity types does not match the entity types in the structural item column and the entity types of each word, then a missing message is added to the monitored content according to the structural entity type. The error alert module is also used to: query historical deduction records based on the doctor's number, and calculate the alert priority of each historical deduction factor in the historical deduction record; Based on the reminder priority, the target factor among the historical deduction factors is determined, and the pre-reminder items and pre-reminder information are determined based on the target factor; The doctor's current medical record template is given a pre-reminder based on the pre-reminder item and the pre-reminder information.

6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 4.

Images