Ultrasonic report process quality control management system

Abstract

The invention relates to the technical field of ultrasonic report quality control management, and discloses an ultrasonic report process quality control management system, which comprises an ultrasonic report automation module, an ultrasonic report quality control module, an ultrasonic report analysis module and an ultrasonic report output module, the ultrasonic text information is converted into a structured data format to form ultrasonic text information, the ultrasonic report quality control module is used for establishing a quality control rule engine to evaluate report quality and generating a corresponding quality control report according to an evaluation result, and the ultrasonic report analysis module is used for extracting corresponding ultrasonic lesion information aiming at qualified ultrasonic report information and sending the extracted ultrasonic lesion information to the server. And the ultrasonic report output module is used for outputting the ultrasonic lesion information and the recommended treatment opinions, and the accuracy and efficiency of medical diagnosis are improved by combining ultrasonic report quality control and process quality control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ultrasonic report quality control management, in particular to an ultrasonic report process quality control management system. BACKGROUND

[0002] An ultrasonic report is a detailed record formed by a doctor after checking the internal structure of a patient's body through ultrasonic technology. Its content usually includes image description, measurement data, abnormal findings, and diagnostic opinions. The report first checks the patient's basic information, then describes the structure, size, location, echo characteristics, and blood flow observed under two-dimensional ultrasound or color Doppler. Key measurement data are listed in the report, and any abnormal findings such as lumps, cysts, and stones are pointed out, along with their specific characteristics. Based on these observations, the doctor will give a preliminary diagnosis or suggestion, which may include confirming the disease, excluding the possibility, proposing further examination or treatment plan. In addition, the report will mention the limitations of the ultrasonic examination and may give follow-up suggestions. Finally, the report will have the signatures of the examining doctor and the quality control doctor to ensure its accuracy and reliability. When interpreting an ultrasonic report, it should be combined with the patient's clinical manifestations and other examination results for comprehensive judgment.

[0003] Traditional ultrasonic report quality relies on manual control, and it is difficult to grasp the quality of ultrasonic reports, which has the problems of low accuracy and poor efficiency, etc., thereby making it difficult for clinicians to quickly judge the condition, which may lead to misdiagnosis or missed diagnosis. SUMMARY

[0004] (I) Technical problems solved

[0005] In view of the deficiencies in the prior art, the present application provides an ultrasonic report process quality control management system, which has the advantages of improving the accuracy and efficiency of medical diagnosis by combining ultrasonic report quality control and process control. The system uses natural language processing technology to automatically structure the ultrasonic report, and monitors the report text logic in real time through a rule engine to ensure the quality of the report.

[0006] (II) Technical solutions

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solutions: an ultrasonic report process quality control management system, comprising an ultrasonic report automation module, an ultrasonic report quality control module, an ultrasonic report analysis module, and an ultrasonic report output module;

[0008] The ultrasonic report automation module is used to automatically analyze the text information in the ultrasonic report and convert it into a structured data format to form ultrasonic text information;

[0009] The ultrasonic report quality control module is used to establish a quality control rule engine to evaluate the quality of the report, and generate a corresponding quality control report according to the evaluation result;

[0010] The ultrasound report analysis module is configured to extract corresponding ultrasound lesion information for qualified ultrasound report information, and match recommended treatment opinions according to the corresponding ultrasound lesion information.

[0011] The ultrasound report output module is configured to output the ultrasound lesion information and the recommended treatment opinions.

[0012] Preferably, the ultrasound report automation module performs deep analysis on the report content by calling an advanced NLP algorithm.

[0013] Preferably, the specific steps of the quality control rule engine for evaluating the report quality are as follows:

[0014] Step one, establishing basic rules;

[0015] Step two, obtaining historical ultrasound information data to form a historical ultrasound information dataset;

[0016] Step three, extracting historical key features from the historical ultrasound information dataset;

[0017] Step four, calculating a current ultrasound report quality index based on the historical key features to perform quality evaluation.

[0018] Preferably, in the step one, the basic rules include:

[0019] Mandatory item check: patient basic information, examination site, doctor signature, field cannot be empty;

[0020] Unit specification: set fixed units for each numerical value, and unify case;

[0021] Terminology standard: set standard language, and disable colloquial description;

[0022] Time logic: check date cannot be later than report date, and follow-up suggestion needs to be clear about time range.

[0023] Preferably, in the step two, the composition of the historical ultrasound information dataset is represented by the following formula: [LScs1, LScs2, LScs3, ···, LScsn], wherein LScs1 represents the first historical ultrasound information data in the historical ultrasound information dataset, LScs2 represents the second historical ultrasound information data in the historical ultrasound information dataset, LScsn represents the nth historical ultrasound information data in the historical ultrasound information dataset, and n represents the total number of obtained ultrasound information data. n n

[0024] Preferably, the historical key features include: historical report content, historical image clarity, and historical image integrity.

[0025] ​​Preferably, the formula for calculating the ultrasound report quality index in step four is:

[0026]

[0027] In the formula, Zlzs represents the ultrasound report quality index, LSnr represents the historical report content of the current report direction, DQnr represents the current report content of the current report direction, TXqx represents the historical image definition of the current report direction, DQqx represents the current image definition of the current report direction, TXwz represents the historical image integrity of the current report direction, and DQwz represents the current image integrity of the current report direction.

[0028] α1, α2, and α3 represent weights, and α1+α2+α3=1.

[0029] represents the ratio of the historical standard to the current actual value, and evaluates the content integrity of the current report.

[0030] represents the ratio of the historical average definition to the current actual definition, and evaluates the definition of the current image.

[0031] represents the ratio of the historical average integrity to the current actual integrity, and evaluates the integrity of the current image.

[0032] Preferably, the ultrasound report quality control module is internally provided with an ultrasound report quality index threshold value, and the ultrasound report quality control module compares the calculated ultrasound report quality index with the ultrasound report quality index threshold value, wherein when the ultrasound report quality index is greater than the ultrasound report quality index threshold value, it represents that the current report is unqualified, and when the ultrasound report quality index is not greater than the ultrasound report quality index threshold value, it represents that the current report is qualified.

[0033] Preferably, the ultrasound report quality control module feeds back the unqualified report to the doctor through a feedback window.

[0034] The ultrasound report quality control module sends the qualified report to the ultrasound report analysis module.

[0035] Preferably, the ultrasound report analysis module matches the lesion information displayed in the current ultrasound report with the lesion information in the historical ultrasound information data set, extracts the treatment scheme corresponding to the lesion information in the historical ultrasound information data set that is consistent with the current lesion information as the recommended treatment opinion.

[0036] Compared with the prior art, the present application provides an ultrasound report process quality control management system, which has the following beneficial effects:

[0037] 1、The present application significantly improves the quality of ultrasound reports and medical safety through automatic analysis, intelligent quality control rule engine and data-driven analysis. First, the automatic module uses NLP technology to convert unstructured text into structured data, ensuring accurate extraction of key information and reducing human errors. Second, the quality control rule engine uses basic rules such as mandatory item checking, unit specification, and term standardization to enforce report format and content, avoiding medical risks caused by missing information or ambiguous expressions. Meanwhile, based on historical data quality index calculation, the report quality is objectively quantified, and unqualified reports are quickly identified and fed back to the doctor, forming a closed-loop improvement mechanism. This standardized and intelligent quality control process not only improves the standardization and completeness of the report, but also reduces the risk of misdiagnosis and missed diagnosis through historical data comparison and threshold warning, providing technical support for patient safety.

[0038] 2、The present application significantly optimizes the efficiency of clinical decision-making and management of medical resources through data analysis and intelligent recommendation. On the one hand, the analysis module uses historical ultrasound data sets to match current lesion information and extract historical treatment plans as recommended opinions, providing evidence-based medical reference for doctors, reducing diagnostic subjectivity and improving treatment specificity. On the other hand, the generation of structured data and quality index facilitates subsequent data mining and statistical analysis, helping hospital management to identify high-frequency lesion types, optimize examination processes, and reasonably allocate medical resources. In addition, the automatic transfer and standardized output of qualified reports shorten the report processing time and reduce labor costs, while precise quality control reduces repeated examinations and ineffective treatments. This whole-chain optimization from data to decision not only improves the efficiency of medical services, but also enhances the controllability of medical services and patient satisfaction through scientific basis and resource management. BRIEF DESCRIPTION OF DRAWINGS

[0039] Fig. 1 is a schematic diagram of the system of the present application;

[0040] Fig. 2 is a schematic diagram of the process of establishing a quality control rule engine in the system of the present application. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0042] Please refer to Figs. 1-2 An ultrasound report process quality control management system, comprising an ultrasound report automation module, an ultrasound report quality control module, an ultrasound report analysis module and an ultrasound report output module;

[0043] The ultrasound report automation module is used to automatically parse the text information in the ultrasound report and convert it into a structured data format to form ultrasound text information;

[0044] The ultrasound report automation module parses the report content by calling advanced NLP algorithms; first, the report text is decomposed into individual words through word segmentation technology; then, key entity information such as examination site, lesion characteristics, and measurement values is accurately identified using named entity recognition technology; next, the logical relationships between the components in the text are understood through dependency relationship analysis to construct a complete semantic framework; finally, the extracted key information is organized and filled according to the pre-defined structured template to generate structured data;

[0045] The ultrasound report automation module parses the report content by calling advanced NLP algorithms to convert unstructured text information into structured data format. First, the report text is decomposed into individual words through word segmentation technology, and then key information such as examination site, lesion characteristics, and measurement values is accurately extracted using named entity recognition technology. This not only improves the accuracy and completeness of the data, but also provides a solid foundation for subsequent quality control analysis. Next, dependency relationship analysis helps understand the logical relationships between text components to construct a complete semantic framework, making the report content clearer and easier to understand, reducing misunderstandings or errors caused by ambiguous semantics. Finally, the extracted key information is organized and filled according to the pre-defined template to generate structured data, greatly improving the efficiency and standardization of data processing, facilitating subsequent data mining, statistical analysis, and quality control. The entire automated parsing process not only saves labor costs and improves work efficiency, but also enhances the accuracy and reliability of the report by reducing human errors, providing strong technical support for ultrasound report process quality control management, and helping to improve medical service quality and patient satisfaction;

[0046] The ultrasound report quality control module is used to establish a quality control rule engine to evaluate the quality of the report and generate a corresponding quality control report based on the evaluation results;

[0047] The specific steps for establishing a quality control rule engine to evaluate the quality of the report are as follows:

[0048] Step one, establish basic rules, including:

[0049] Mandatory item check: patient basic information, examination site, doctor signature, field cannot be empty;

[0050] Unit specification: set fixed units for each value, and unify case;

[0051] Terminology: Set standard terminology, disable colloquial descriptions, such as "looks like benign" should be changed to "benign may be";

[0052] Time logic: Check that the date is not later than the report date, and the follow-up suggestion needs to be clear about the time range;

[0053] Step two, obtain historical ultrasound information data, and form a historical ultrasound information data set. The composition of the historical ultrasound information data set is represented by the formula: [LScs1, LScs2, LScs3,..., LScs n ], where LScs1 represents the first historical ultrasound information data in the historical ultrasound information data set, LScs n represents the nth historical ultrasound information data in the historical ultrasound information data set, and n represents the total number of obtained ultrasound information data;

[0054] Step three, extract historical key features from the historical ultrasound information data set. The historical key features include: historical report content, historical image clarity, and historical image integrity;

[0055] Step four, calculate the current ultrasound report quality index based on the historical key features to perform quality evaluation. The calculation formula of the ultrasound report quality index is:

[0056]

[0057] In the formula, ZLzs represents the ultrasound report quality index, LSnr represents the historical report content in the current report direction, DQnr represents the current report content in the current report direction, TXqx represents the historical image clarity in the current report direction, DQqx represents the current image clarity in the current report direction, TXwz represents the historical image integrity in the current report direction, and DQwz represents the current image integrity in the current report direction;

[0058] α1, α2, α3 represent weights, and α1+α2+α3=1;

[0059] represents the ratio of historical standards to current actual values, and evaluates the content integrity of the current report;

[0060] represents the ratio of historical average clarity to current actual clarity, and evaluates the clarity of the current image;

[0061] represents the ratio of historical average integrity to current actual integrity, and evaluates the integrity of the current image;

[0062] The ultrasonic report quality control module evaluates the report quality by establishing a quality control rule engine and generates a corresponding quality control report according to the evaluation result. First, by establishing basic rules such as mandatory item check, unit specification, terminology standard and time logic, the completeness, standardization and accuracy of the report are ensured, and the medical risks caused by missing information or unclear expression are reduced. Second, historical ultrasonic information data is obtained and key features are extracted, so that the quality control rule engine can intelligently analyze based on historical data, provide a scientific basis for the quality evaluation of the current report, and objectively and quantitatively reflect the quality level of the report by calculating the ultrasonic report quality index, helping management personnel to quickly identify problem reports and make targeted improvements. Not only does it effectively improve the accuracy and standardization of the report, but also provides strong technical support for the process quality control management of the ultrasonic report through data-driven and intelligent analysis, which helps to improve the quality of medical services and patient satisfaction;

[0063] The ultrasonic report quality control module is internally provided with an ultrasonic report quality index threshold value. The ultrasonic report quality control module compares the calculated ultrasonic report quality index with the ultrasonic report quality index threshold value. When the ultrasonic report quality index is greater than the ultrasonic report quality index threshold value, it represents that the current report is unqualified. When the ultrasonic report quality index is not greater than the ultrasonic report quality index threshold value, it represents that the current report is qualified.

[0064] The ultrasonic report quality control module feeds back the unqualified report to the doctor through the feedback window;

[0065] The ultrasonic report quality control module sends the qualified report to the ultrasonic report analysis module;

[0066] The ultrasonic report analysis module matches the lesion information displayed in the current ultrasonic report with the lesion information in the historical ultrasonic information data set, extracts the treatment scheme corresponding to the lesion information in the historical ultrasonic information data set that matches the current lesion information as the recommended treatment opinion;

[0067] The ultrasonic report output module is used to output the ultrasonic lesion information and the recommended treatment opinion;

[0068] The analysis module can extract the treatment scheme that matches the current lesion as the recommended treatment opinion by matching the lesion information of the current ultrasonic report with the related information in the historical data set. This process not only improves the accuracy of diagnosis and the pertinence of treatment, but also reduces the deviation of human judgment through the reference of historical data. Through data-driven intelligent analysis and standardized output, the quality and management efficiency of the ultrasonic report are improved, which provides a scientific basis for clinical decision-making, helps to optimize the allocation of medical resources, improves the treatment effect and satisfaction of patients, reduces the medical risk, and enhances the standardization and controllability of medical services.

[0069] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and adaptions can be effected without departing from the spirit and scope of the present application, which is not limited to the exact construction and arrangement described. It is intended, therefore, to cover all modifications and adaptions that fall within the scope of the claims and their equivalents.

Claims

1. An ultrasound reporting process quality control management system, characterized by: The ultrasound report automation module, the ultrasound report quality control module, the ultrasound report analysis module and the ultrasound report output module are included. The ultrasound report automation module is used for automatically analyzing text information in the ultrasound report and converting the text information into a structured data format to form ultrasound text information. The ultrasound report quality control module is used for establishing a quality control rule engine to evaluate the report quality and generating a corresponding quality control report according to the evaluation result. The ultrasound report analysis module is used for extracting corresponding ultrasound lesion information from qualified ultrasound report information and matching recommended treatment opinions according to the corresponding ultrasound lesion information. The ultrasound report output module is used for outputting the ultrasound lesion information and the recommended treatment opinions.

2. The ultrasound reporting process quality control management system of claim 1, wherein: The ultrasound report automation module is used for calling advanced NLP algorithms to deeply analyze the report content.

3. The ultrasound reporting process quality control management system of claim 2, wherein: The specific steps for establishing the quality control rule engine to evaluate the report quality are as follows: Step one, establishing basic rules; Step two, obtaining historical ultrasound information data to form a historical ultrasound information dataset; Step three, extracting historical key features from the historical ultrasound information dataset; Step four, calculating a current ultrasound report quality index based on the historical key features to evaluate the quality.

4. The ultrasound reporting process quality control management system of claim 3, wherein: In step one, the basic rules include: Mandatory item check: patient basic information, examination site, doctor signature, field cannot be empty; Unit specification: set fixed units for each numerical value, and unify the case; Terminology standard: set standard terminology, and disable colloquial description; Time logic: check the date, which cannot be later than the report date, and follow-up suggestions need to be clear about the time range.

5. The ultrasound reporting process quality control management system of claim 4, wherein: The composition of the historical ultrasound information data set in the second step is represented by the formula: [LScs1, LScs2, LScs3, ···, LScsn], wherein LScs1 represents the first historical ultrasound information data in the historical ultrasound information data set, LScs2 represents the second historical ultrasound information data in the historical ultrasound information data set, LScs3 represents the third historical ultrasound information data in the historical ultrasound information data set, and LScsn represents the nth historical ultrasound information data in the historical ultrasound information data set, wherein n represents the total number of acquired ultrasound information data. n n LScsn represents the nth historical ultrasound information data in the historical ultrasound information data set, wherein n represents the total number of acquired ultrasound information data.​ 6. The ultrasound reporting process quality control management system of claim 5, wherein: The historical key features include: historical report content, historical image clarity, and historical image integrity.

7. The ultrasound reporting process quality control management system of claim 6, wherein: In step four, the calculation formula of the ultrasound report quality index is as follows: In the formula, ZLzs represents the ultrasound report quality index, Lsnr represents the historical report content in the current report direction, DQnr represents the current report content in the current report direction, TXqx represents the historical image clarity in the current report direction, DQqx represents the current image clarity in the current report direction, TXwz represents the historical image integrity in the current report direction, and DQwz represents the current image integrity in the current report direction. α1, α2, and α3 represent weights, and α1+α2+α3=1. representing a ratio of historical standards to current reality, to assess the content integrity of the current report; representing an evaluation of the sharpness of the current image by the ratio of the historical average sharpness to the current actual sharpness; The completeness of the current image is evaluated by the ratio of the historical average completeness and the current actual completeness.

8. The ultrasound reporting process quality control management system of claim 7, wherein: The ultrasound report quality control module is internally provided with an ultrasound report quality index threshold value, and the ultrasound report quality control module compares the calculated ultrasound report quality index with the ultrasound report quality index threshold value.

9. The ultrasound reporting process quality control management system of claim 8, wherein: When the ultrasound report quality index is greater than the ultrasound report quality index threshold value, the current report is unqualified. When the ultrasound report quality index is not greater than the ultrasound report quality index threshold value, the current report is qualified. The ultrasound report quality control module feeds back the unqualified report to the doctor through a feedback window. The ultrasound report quality control module sends the qualified report to the ultrasound report analysis module.

10. The ultrasound reporting process quality control management system of claim 9, wherein: The ultrasound report analysis module matches the lesion information displayed in the current ultrasound report with the lesion information in the historical ultrasound information data set, and extracts the treatment scheme corresponding to the lesion information in the historical ultrasound information data set that is consistent with the current lesion information as the recommended treatment opinion.

Images