Report quality control processing method, medical data processing system and electronic equipment

Abstract

The invention provides a report quality control processing method, a medical data processing system and electronic device.The medical data processing system comprises an artificial intelligence module, a quality control system, a plurality of inspection systems and a pathology system.The artificial intelligence module obtains inspection data output by all the inspection systems; performing report quality detection on each inspection data according to a preset quality control index to obtain an initial quality control result of each inspection data, and sending the initial quality control result to a quality control system; the quality control system obtains a pathological diagnosis result output by the pathological system; and the quality control system determines a target quality control result of each piece of inspection data according to the initial quality control result of each piece of inspection data and the pathological diagnosis result. The inspection data is subjected to quality control according to the format requirement and the content requirement of the data through the quality control index, the initial quality control result is obtained, the inspection data is further subjected to quality control in combination with the pathological diagnosis result output by the pathological system and the initial quality control result, and the accuracy of report quality control processing is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a report quality control processing method, a medical data processing system, and an electronic device. Background Technology

[0002] Imaging medical diagnosis and report quality control is a very important part of the medical field, which can help diagnostic personnel make accurate diagnoses and treatments based on pathological results.

[0003] Existing report quality control methods rely on manual random sampling followed by quality control judgment. This method depends on the personal experience of diagnostic personnel, which not only takes a long time and is inefficient, but also cannot fully cover the diagnostic results of multiple examination systems. The risk of misdiagnosis, missed diagnosis, and overdiagnosis is too high, resulting in low accuracy of report quality control processing. Summary of the Invention

[0004] The purpose of this application is to address the shortcomings of the prior art by providing a report quality control processing method, a medical data processing system, and an electronic device to solve the problem of low accuracy in report quality control processing in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, embodiments of this application provide a report quality control processing method applied to a medical data processing system, the medical data processing system including: an artificial intelligence module, a quality control system, multiple examination systems, and a pathology system, the method including:

[0007] The artificial intelligence module acquires the inspection data output by each inspection system, performs report quality detection on each inspection data according to preset quality control indicators, obtains the initial quality control results of each inspection data, and sends the initial quality control results to the quality control system. The quality control indicators are used to indicate the format requirements and content requirements of the inspection data.

[0008] The quality control system acquires the pathological diagnosis results output by the pathology system;

[0009] The quality control system determines the target quality control result for each examination data based on the initial quality control results of each examination data and the pathological diagnosis results.

[0010] As one possible implementation, the step of performing report quality checks on each inspection data according to preset quality control indicators to obtain the initial quality control results of each inspection data includes:

[0011] Obtain the basic information of the user corresponding to the inspection data;

[0012] Based on the basic information and the quality control indicators, the inspection data are reported for quality inspection to obtain the initial quality control results. The inspection data includes inspection findings and inspection conclusions.

[0013] As one possible implementation, the step of performing report quality checks on each inspection data based on the basic information and the quality control indicators to obtain the initial quality control result includes:

[0014] Obtain the mapping relationship between each of the inspection data and the quality control indicators, as well as the correlation relationship between the quality control indicators and the basic information;

[0015] Based on the mapping relationship and the correlation relationship, determine the quality control result corresponding to the quality control indicator;

[0016] The initial quality control result is obtained based on the quality control results corresponding to the quality control indicators.

[0017] As one possible implementation, the quality control indicators are multiple, and the method further includes:

[0018] Based on the quality control results corresponding to each of the quality control indicators, the inspection data are evaluated and analyzed to obtain the evaluation results of each of the inspection data.

[0019] Based on the evaluation results of each of the aforementioned inspection data, determine whether each of the aforementioned inspection data meets the quality control requirements;

[0020] If so, then obtain the pathological diagnosis result output by the pathology system.

[0021] As one possible implementation, the step of evaluating and analyzing each inspection data based on the quality control results corresponding to each of the quality control indicators to obtain the evaluation results of each of the inspection data includes:

[0022] Obtain the evaluation weights and scoring criteria corresponding to each of the quality control indicators;

[0023] Based on the evaluation weights, scoring standards, and quality control results corresponding to each quality control indicator, the inspection data are evaluated and analyzed to obtain the evaluation results of each inspection data.

[0024] As one possible implementation, the quality control system determines the target quality control result for each examination data based on the initial quality control result of each examination data and the pathological diagnosis result, including:

[0025] Identify the target inspection data belonging to the same inspection area from among the various inspection data;

[0026] Using the pathological diagnosis results, the initial quality control results of each examination data, and the target examination data in each examination data, the target quality control results of each examination data are determined.

[0027] As one possible implementation, the target quality control results for each examination data are determined using the pathological diagnosis results, the initial quality control results of each examination data, and the target examination data within each examination data, including:

[0028] The pathological diagnosis results are compared with the target examination data in each examination data, and combined with the initial quality control results of each examination data, to determine whether the examination results for the same examination site in each examination data are consistent, and to determine the target quality control results of each examination data.

[0029] As one possible implementation, after determining the target quality control results for each inspection data point, the method further includes:

[0030] Based on the target quality control results, the user's pathological information, and examination information, a prompt message is determined, which is used to remind the user to follow up.

[0031] Secondly, embodiments of this application provide a medical data processing system, which includes: an artificial intelligence module, a quality control system, multiple examination systems, and a pathology system;

[0032] The artificial intelligence module is used to execute the report quality control processing method executed by any one of the artificial intelligence modules in the first aspect above;

[0033] The quality control system is used to execute the report quality control processing method executed by any of the quality control systems in the first aspect above;

[0034] Each of the aforementioned inspection systems is used to output inspection data;

[0035] The pathology system is used to output pathological diagnostic results.

[0036] Thirdly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the report quality control processing method as described in any of the first aspects above.

[0037] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the report quality control processing method as described in any of the first aspects above.

[0038] According to the report quality control processing method, medical data processing system, and electronic device of this application, the artificial intelligence module acquires the examination data output by each examination system, and performs report quality detection on each examination data according to preset quality control indicators to obtain the initial quality control results of each examination data. The initial quality control results are then sent to the quality control system. The quality control system acquires the pathological diagnosis results output by the pathology system, and determines the target quality control results for each examination data based on the initial quality control results and the pathological diagnosis results. According to the embodiments of this application, the examination data is quality controlled based on the format and content requirements of the data according to the quality control indicators to obtain the initial quality control results. Furthermore, the examination data is further quality controlled by combining the pathological diagnosis results output by the pathology system with the initial quality control results. This process can be implemented using the medical data processing system, an artificial intelligence system, saving diagnostic time for report quality control and improving diagnostic efficiency. Moreover, by combining the pathological diagnosis results from multiple dimensions to perform quality control on the examination data, the probability of misdiagnosis, missed diagnosis, and overdiagnosis is reduced, thereby improving the accuracy of report quality control processing. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This paper illustrates a schematic diagram of the architecture of a medical data processing system provided in an embodiment of this application.

[0041] Figure 2 A schematic flowchart of a report quality control processing method provided in an embodiment of this application is shown;

[0042] Figure 3 A flowchart illustrating a method for determining initial quality control results provided in an embodiment of this application is shown.

[0043] Figure 4 A flowchart illustrating a quality control assessment method provided in an embodiment of this application is shown.

[0044] Figure 5 The diagram illustrates the architecture of a method for determining whether inspection data meets quality control requirements, as provided in an embodiment of this application.

[0045] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0047] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0048] To enable those skilled in the art to utilize the content of this application, and in conjunction with the specific application scenario of "report quality control," the following implementation methods are provided. For those skilled in the art, the general principles defined herein can be applied to other embodiments and application scenarios without departing from the spirit and scope of this application. Although this application primarily describes report quality control processing methods and medical data processing systems, it should be understood that this is merely an exemplary embodiment.

[0049] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0050] With the significant improvement in the capabilities of large-scale natural language processing, multi-turn question answering in human-computer interaction, and deep learning in big data to assist medical decision-making, imaging medical diagnosis and report quality control have become a very important part of the medical field.

[0051] Existing report quality control methods have the following main problems: (1) Specific internal quality control of reports needs to be described in the form of rules, which involves a lot of repetitive work and makes doctors' work merely a formality; (2) Due to the isolation between various application systems, it is impossible to integrate data from different application systems; (3) An artificial intelligence model can only solve one task and cannot solve multiple tasks. In the medical field, the accuracy of diagnosis is usually judged by pathology, and doctors need to find appropriate examination results based on the patient's matching pathology results and require patients to follow up. Existing technologies cannot do the above.

[0052] Furthermore, the highly repetitive nature of imaging medicine tasks easily leads to increased diagnostic error rates. For example, in ultrasound diagnostics, most hospitals lack a physician review process, resulting in higher risks of misdiagnosis and missed diagnosis, longer diagnostic times, and reliance on individual physician experience. In radiology, ultrasound, and endoscopy, quality control is limited to manual random sampling of examination reports and images, which cannot provide full coverage and is inefficient. This leads to reports being sent to clinical departments, only to be retrieved after clinicians report problems, further reducing the trust in the reports from the examination departments. Moreover, physicians are prone to overlooking crucial information such as lesions and space-occupying lesions during image acquisition or interpretation, especially junior physicians. In conclusion, the accuracy of existing report quality control methods is not high.

[0053] To address the aforementioned issues, this application provides a medical data processing system based on artificial intelligence technology. This system integrates multiple AI applications, including an AI module, a quality control system, various examination systems, and a pathology system. The system performs quality control on the examination data output by each examination system, saving diagnostic time in report quality control and improving diagnostic efficiency. Furthermore, by combining pathological diagnostic results with multi-dimensional quality control of examination data, the system reduces the probability of misdiagnosis, missed diagnosis, and overdiagnosis, thereby improving the accuracy of report quality control processing.

[0054] Figure 1 A schematic diagram of the architecture of a medical data processing system provided in an embodiment of this application is shown. (Refer to...) Figure 1As shown, the medical data processing system 10 includes an artificial intelligence module 101, a quality control system 102, multiple examination systems 103, and a pathology system 104. For example, the examination system 103 includes a radiology system, an ultrasound system, and an endoscopy system. The examination system 103, also known as the data acquisition system, is used to perform report quality checks on each examination data based on pre-set quality control indicators. Furthermore, using the pathological diagnosis results output by the pathology system 104 as the gold standard, further quality control processing is performed on each examination data. Specifically, quality control is applied to unreasonable aspects of the examination data, such as missing, incorrect, or inappropriate descriptions of examination findings; examination conclusions that cannot derive lesion descriptions from examination findings; and inconsistencies between data descriptions of examined organs, locations, lesions, units, data, and conclusions.

[0055] Based on this, the medical data processing system provided in this application integrates examination data from multiple sources, including radiology, ultrasound, and endoscopy, to match and construct a cross-report quality control processing method between these three sources. It also enables the use of a large language model to find matching examinations based on pathological diagnosis results, reminding patients to undergo follow-up. Thus, this large language model of the medical data processing system can meet the service requirements of multiple different applications.

[0056] The following is in conjunction with the above. Figure 1 The content described in the illustrated medical data processing system 10 provides a detailed explanation of the report quality control processing method provided in the embodiments of this application.

[0057] Figure 2 A schematic flowchart of a report quality control processing method provided in an embodiment of this application is shown. (Refer to...) Figure 2 As shown, the executing entity of this method is the aforementioned medical data processing system 10, and the method specifically includes the following steps:

[0058] S201. The artificial intelligence module acquires the inspection data output by each inspection system, performs report quality inspection on each inspection data according to the preset quality control indicators, obtains the initial quality control results of each inspection data, and sends the initial quality control results to the quality control system. The quality control indicators are used to indicate the format requirements and content requirements of the inspection data.

[0059] Optionally, the artificial intelligence module 101, also known as the AI ​​module, in the medical data processing system 10, can verify examination data from multiple examinations performed on the same patient by multiple examination systems 103, even for the same body part, by checking and verifying the consistency of the examination data from different examination systems 103 for the same body part. Based on this, the AI ​​module 101 can detect whether each examination data meets the format and content requirements according to pre-set quality control indicators, obtain the initial quality control results for each examination data, and send the initial quality control results to the quality control system 102.

[0060] S202. The quality control system obtains the pathological diagnosis results output by the pathology system.

[0061] Optionally, the pathology system 104 outputs a pathological diagnosis result and sends it to the quality control system 102. In the quality control system 102, the pathological diagnosis result output by the pathology system 104 is used as the gold standard, and the pathological diagnosis result is verified against the examination data output by different examination systems 103.

[0062] S203. The quality control system determines the target quality control result for each examination data based on the initial quality control results and pathological diagnosis results.

[0063] Optionally, in the quality control system 102, the pathological diagnosis results output by the pathology system 104 are used to verify the examination data output by the pathological diagnosis results and the radiology system, the examination data output by the pathology diagnosis results and the endoscopy system, and the examination data output by the pathology diagnosis results and the ultrasound system, respectively, to determine the examination of the examination system corresponding to the pathological diagnosis results, and to determine whether the examination is for the same site / organ, and to use the quality control system 102 to evaluate whether the doctor's examination conclusion is accurate, so as to determine the target quality control results for each examination data.

[0064] Based on this, according to the report quality control processing method provided in the embodiments of this application, the artificial intelligence module obtains the examination data output by each examination system, and performs report quality detection on each examination data according to preset quality control indicators to obtain the initial quality control results of each examination data. The initial quality control results are then sent to the quality control system. The quality control system obtains the pathological diagnosis results output by the pathology system, and determines the target quality control results of each examination data based on the initial quality control results and the pathological diagnosis results. According to the embodiments of this application, the examination data is quality controlled based on the format and content requirements of the data according to the quality control indicators to obtain the initial quality control results. Furthermore, the examination data is further quality controlled by combining the pathological diagnosis results output by the pathology system with the initial quality control results. This process can be implemented using an artificial intelligence system based on a medical data processing system, saving diagnostic time for report quality control and improving diagnostic efficiency. Moreover, by combining the pathological diagnosis results from multiple dimensions to perform quality control on the examination data, the probability of misdiagnosis, missed diagnosis, and overdiagnosis is reduced, thereby improving the accuracy of report quality control processing.

[0065] As one possible implementation, step S201 above performs report quality checks on each inspection data according to preset quality control indicators to obtain the initial quality control results of each inspection data, including:

[0066] Obtain basic information about the users corresponding to the inspection data; perform report quality testing on each inspection data based on the basic information and quality control indicators to obtain initial quality control results, whereby the inspection data includes inspection findings and inspection conclusions.

[0067] For example, the user's basic information includes the user's gender, age, and image number. Several pre-defined quality control indicators are set, including: whether there are typos in the examination data, whether the organ description does not match the user's gender, whether the examination data does not include all currently examined sites, whether there are incorrect diagnoses of typical lesions, and whether organs that have been removed and have clear imaging findings are still described as normal organs in the examination data.

[0068] Figure 3 This illustration shows a flowchart of a method for determining initial quality control results according to an embodiment of this application. Optionally, as... Figure 3 As shown, the above steps involve performing report quality checks on each inspection data based on basic information and quality control indicators to obtain initial quality control results. Specifically, the steps include the following:

[0069] S301. Obtain the mapping relationship between each inspection data and quality control indicators, as well as the correlation between quality control indicators and basic information.

[0070] For example, in the field of report quality control, the mapping relationship between inspection data and quality control indicators refers to the process of corresponding and comparing the actually collected inspection data with pre-set quality control standards or indicators. The correlation between quality control indicators and user background information refers to combining the evaluation results of quality control indicators with the user's specific background information to more comprehensively understand and interpret the meaning and impact of the quality control data. Based on the above mapping and correlation relationships, it can be ensured that inspection data is correctly evaluated to determine whether the inspection data meets quality requirements.

[0071] S302. Based on the mapping and correlation relationships, determine the quality control results corresponding to the quality control indicators.

[0072] For example, determining quality control results based on mapping relationships involves data standardization, indicator definition, data mapping, rule application, and result evaluation. Data standardization ensures that all collected inspection data is processed according to unified standards or protocols, such as consistent data formats and units, for comparison purposes. Indicator definition clarifies the specific content of quality control indicators and is a key parameter for measuring the performance of report quality control processing. Data mapping maps the actual inspection data to correspond to the requirements of the quality control indicators. Rule application involves analyzing the inspection data using the quality control indicators to determine the mapping results. Result evaluation assesses the data quality of the inspection data based on the mapping results, determining whether there are typos, inconsistencies, or other problems in the inspection data.

[0073] For example, determining quality control results based on correlations involves developing more personalized quality control indicators based on specific user conditions, such as age, gender, and health status. For instance, in the medical field, the normal ranges for certain physiological indicators may differ for patients of different ages; therefore, these potential differences must be considered when processing reports for quality control.

[0074] For example, each inspection data and quality control indicator is input into the artificial intelligence module 101. The artificial intelligence module 101 extracts the mapping relationship between each inspection data and the quality control indicator, as well as the correlation relationship between the quality control indicator and the basic information. Based on the mapping relationship and the correlation relationship, it performs quality control processing on each inspection data and outputs the quality control results corresponding to each quality control indicator. For example, if the currently input inspection data includes CT imaging findings and CT imaging conclusions, the artificial intelligence module 101 will perform quality detection on the CT imaging findings and CT imaging conclusions based on the quality control indicator "whether there are typos in the inspection data", determine whether there are typos in the currently input inspection data, and obtain the quality control result corresponding to the quality control indicator "whether there are typos in the inspection data". This quality control result includes no typos and typos. Furthermore, if typos are present, it can determine the number of typos and the location of the typos in the CT imaging findings and CT imaging conclusions.

[0075] For example, taking the currently input examination data, which includes CT imaging findings and conclusions, as an example, the artificial intelligence module 101 will perform quality checks on the CT imaging findings and conclusions based on the quality control indicator of "organ description not matching user gender." This will determine whether there are cases where the organ descriptions do not match the user's gender in the currently input examination data, and obtain the quality control result corresponding to this indicator. This result includes cases where there are no cases where the organ descriptions do not match the gender, and cases where there are cases where the organ descriptions do not match the gender. For example, if the user corresponding to the examination data is female, and the examination data mentions descriptions such as "both lungs," "trachea and each lobe and segmental bronchus," and "no significantly enlarged lymph nodes seen in the bilateral hilum and mediastinum," these descriptions are applicable to the anatomical structures and physiological characteristics of women. Therefore, the obtained quality control result is that there are no cases where the organ descriptions do not match the gender.

[0076] For example, continuing with the example that the currently input examination data includes CT imaging findings and CT imaging conclusions, the artificial intelligence module 101 will perform quality checks on the CT imaging findings and CT imaging conclusions based on the quality control indicator "the examination data does not include all the currently examined areas" to determine whether the currently input examination data includes all the currently examined areas, and obtain the quality control result corresponding to the quality control indicator "the examination data does not include all the currently examined areas". This quality control result includes all the currently examined areas, covers most of the major examination areas, and does not include all the currently examined areas. For example, the examination data includes the thoracic cavity, lungs, trachea and bronchi, hilum and mediastinum, heart and blood vessels, pleura and pleural cavity, thoracic bones and soft tissues, thyroid gland, liver, and cardia-fundus. Based on the above, it can be seen that the main sites included in the current examination data are the chest, thyroid gland and liver. However, it should be noted that the "cardia-fundus" mentioned in the examination data may have been discovered through other imaging examinations, such as gastroscopy, rather than directly through CT scan. Therefore, the quality control result covers most of the major examination sites, but depending on the patient's examination purpose and the doctor's instructions, some specific sites may not be mentioned.

[0077] For example, continuing with the above-mentioned current input examination data including CT imaging findings and CT imaging conclusions, the artificial intelligence module 101 will perform quality checks on the CT imaging findings and CT imaging conclusions based on the quality control indicator of "typical lesion diagnosis error" to determine whether there is a typical lesion diagnosis error in the current input examination data, and obtain the quality control result corresponding to the quality control indicator of "typical lesion diagnosis error". This quality control result includes the presence of typical lesion diagnosis errors and the absence of typical lesion diagnosis errors. For example, a preliminary diagnosis or explanation is given for each observed abnormality in the examination data, such as nodular lesion in the lower lobe of the right lung: possibly an old lesion; small nodular shadows in both lungs: similar to before, follow-up is recommended; bullae in the middle lobe of the right lung and the left lung; a small amount of chronic inflammation in the subpleural region of the upper lobe of the left lung; sclerosis of the aorta and coronary arteries; multiple thyroid nodules, please combine with ultrasound examination; malignant tumor of the cardia-fundus with multiple surrounding lymph node metastases; multiple liver metastases, please combine with relevant abdominal examinations. Based on the above description, the preliminary diagnosis or interpretation in the examined data appears to be reasonable, and there are no typical lesion diagnosis errors. Therefore, the quality control result obtained is that there are no typical lesion diagnosis errors.

[0078] For example, continuing with the above-mentioned current input examination data including CT imaging findings and CT imaging conclusions, the artificial intelligence module 101 will perform quality checks on the CT imaging findings and CT imaging conclusions based on the quality control indicator of "the organ has been removed and its imaging manifestation is clear, but it is still described as a normal organ in the examination data" to determine whether there is an organ that has been removed and its imaging manifestation is clear, but it is still described as a normal organ in the current input examination data.

[0079] S303. Based on the quality control results corresponding to the quality control indicators, obtain the initial quality control results.

[0080] For example, based on the quality control results corresponding to each quality control indicator, including whether there are typos in the currently input examination data, whether there are cases where the organ description does not match the gender, whether all the currently examined sites are included, whether there are typical lesion diagnosis errors, and whether there are organs that have been removed and whose imaging manifestations are clear, but are still described as normal organs, the quality control results of the examination data are comprehensively judged based on the above content, and the initial quality control results of each examination data are obtained.

[0081] Based on this, the mapping relationship between each inspection data and quality control indicators, as well as the correlation between quality control indicators and basic information, are used to conduct report quality inspection, ensuring the effectiveness of report quality control processing and the reliability of initial quality control results.

[0082] Figure 4 A flowchart illustrating a quality control assessment method provided in an embodiment of this application is shown. (Refer to...) Figure 4As shown, this quality control assessment method specifically includes the following steps:

[0083] S401. Evaluate and analyze each inspection data based on the quality control results corresponding to each quality control indicator to obtain the evaluation results of each inspection data.

[0084] Optionally, step S401 specifically includes: obtaining the evaluation weight and scoring standard corresponding to each quality control indicator; evaluating and analyzing each inspection data according to the evaluation weight, scoring standard and quality control results corresponding to each quality control indicator, and obtaining the evaluation results of each inspection data.

[0085] For example, the evaluation weights and scoring standards corresponding to each quality control indicator can be set according to actual application needs. The evaluation weights corresponding to each quality control indicator can be the same or different. For example, an evaluation system with a full score of 100 points can be constructed based on the evaluation weights and scoring standards corresponding to each quality control indicator. The evaluation weights corresponding to each quality control indicator are the same, and each quality control indicator accounts for 20 points. Scoring is based on the quality control results corresponding to each quality control indicator. Specifically, 2 points are deducted for each typo, 20 points are deducted for an organ description that does not match the gender, 2 points are deducted for not including all the currently examined parts, and 20 points are deducted for a typical lesion diagnosis error, etc. Furthermore, if the final evaluation result of the examination data, that is, the final score, is lower than a preset threshold, such as 60 points, then the examination data is determined to be unqualified.

[0086] S402. Based on the evaluation results of each inspection data, determine whether each inspection data meets the quality control requirements.

[0087] Optionally, in step S203 above, the quality control system determines the target quality control result for each examination data based on the initial quality control results and pathological diagnosis results, including:

[0088] Identify the target examination data for the same examination site in each examination data set; compare the pathological diagnosis results with the target examination data in each examination data set, and combine this with the initial quality control results of each examination data set to determine whether the examination results for the same examination site in each examination data set are consistent, and determine the target quality control results for each examination data set.

[0089] For example, a user may undergo multiple different examinations during the same hospitalization period. For instance, a visit for gastric cancer may involve an endoscopy, an abdominal CT scan, a chest CT scan, and a head CT scan. In such cases, it is necessary to perform quality control processing on data from different sites and different examination systems, and to compare the pathological diagnosis results with the target examination data in each examination to ensure that the examination results obtained from the target examination data for the same site are consistent, thereby further improving the accuracy of the report quality control processing.

[0090] Figure 5 This illustration shows an architectural diagram of a method for determining whether inspection data meets quality control requirements, as provided in an embodiment of this application. For example, as... Figure 5 As shown, for historical examination data from multiple examination systems 103 over a certain period of time, the system can extract the user's basic information, including gender, age, image number, examination findings, and examination conclusions. With the basic information synchronized, the quality control system 102 can still unify the user's historical examination data and input all historical examination data into the artificial intelligence module 101 after organizing them into individual records. The artificial intelligence module 101 uses this module to perform quality checks on examination data for the same area, not only determining which examinations belong to the same area but also comparing the examination data for the same area to determine whether the examination data meets quality control requirements. Furthermore, different examinations of the same area can be displayed in the quality control system 102.

[0091] Therefore, the consistency of examination results is an important indicator of quality control. By comparing the examination data of the same examination site multiple times, it can be determined whether the examination results for the same examination site are consistent in each examination data. This can reduce misdiagnosis or missed diagnosis caused by examination variations, and thus improve the accuracy of clinical decision-making.

[0092] As one possible implementation, after determining the target quality control results for each examination data, the method further includes: determining prompt information based on the target quality control results, the user's pathological information, and examination information, and using the prompt information to remind the user to follow up.

[0093] For example, all examination findings and conclusions are simultaneously input into the artificial intelligence module 101 to determine whether the findings and conclusions are correct when pathological diagnosis is used as the gold standard, thereby determining the target quality control result for each examination data. Subsequently, based on the target quality control result, and combined with the user's pathological and examination information, such as examination time, prompts are generated, and follow-up requirements and suggestions are provided to the user to remind them of follow-up in a timely manner.

[0094] Based on this, by combining the user's pathological and examination information, more personalized follow-up suggestions can be provided. Appropriate follow-up plans can be developed for different users' health conditions. Furthermore, through regular follow-up reminders, medical resources can be rationally allocated according to the user's actual situation, thereby improving the pertinence and effectiveness of health management.

[0095] According to the embodiments of this application, multiple information systems, including the artificial intelligence module 101, the quality control system 102, multiple examination systems 103, and the pathology system 104, are integrated into a single AI model, namely the medical data processing system 10. This reduces the cost of model deployment and management, and the output data from multiple information systems can be mutually quality controlled and managed. During the report quality control process, the format and content of each examination data are quality controlled and scored, improving the standardization of report diagnostic and writing capabilities, reducing the report recall rate, and thus enabling the shift from sampling quality control to fully automated quality control. Furthermore, based on the target quality control results, the user's pathology information, and examination information, follow-up reminders for the user can be implemented.

[0096] This application also provides an electronic device 600, such as... Figure 6 The diagram shown is a schematic representation of the structure of an electronic device 600 provided in an embodiment of this application. It includes a processor 601 and a memory 602, and optionally, a bus 603. The memory 602 stores machine-readable instructions executable by the processor 601. When the electronic device 600 is running, the processor 601 and the memory 602 communicate via the bus 603. When the machine-readable instructions are executed by the processor 601, they perform the steps of any of the above-described report quality control processing methods.

[0097] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of any of the above-mentioned report quality control processing methods.

[0098] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0099] Furthermore, the functional units 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. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0100] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A report quality control processing method, characterized in that, The method is applied to a medical data processing system, which includes an artificial intelligence module, a quality control system, multiple examination systems, and a pathology system. The artificial intelligence module acquires the inspection data output by each inspection system, performs report quality detection on each inspection data according to preset quality control indicators, obtains the initial quality control results of each inspection data, and sends the initial quality control results to the quality control system. The quality control indicators are used to indicate the format requirements and content requirements of the inspection data. The quality control system acquires the pathological diagnosis results output by the pathology system; The quality control system determines the target quality control result for each examination data based on the initial quality control results of each examination data and the pathological diagnosis results.

2. The report quality control processing method according to claim 1, characterized in that, The process of performing report quality checks on each inspection data according to preset quality control indicators to obtain initial quality control results for each inspection data includes: Obtain the basic information of the user corresponding to the inspection data; Based on the basic information and the quality control indicators, the inspection data are reported for quality inspection to obtain the initial quality control results. The inspection data includes inspection findings and inspection conclusions.

3. The report quality control processing method according to claim 2, characterized in that, The process of reporting quality checks on each inspection data based on the basic information and the quality control indicators to obtain the initial quality control results includes: Obtain the mapping relationship between each of the inspection data and the quality control indicators, as well as the correlation relationship between the quality control indicators and the basic information; Based on the mapping relationship and the correlation relationship, determine the quality control result corresponding to the quality control indicator; The initial quality control result is obtained based on the quality control results corresponding to the quality control indicators.

4. The report quality control processing method according to claim 1, characterized in that, The quality control indicators are multiple, and the method further includes: Based on the quality control results corresponding to each of the quality control indicators, the inspection data are evaluated and analyzed to obtain the evaluation results of each of the inspection data. Based on the evaluation results of each of the inspection data, determine whether each of the inspection data meets the quality control requirements.

5. The report quality control processing method according to claim 4, characterized in that, The evaluation and analysis of each inspection data based on the quality control results corresponding to each quality control indicator, to obtain the evaluation results of each inspection data, includes: Obtain the evaluation weights and scoring criteria corresponding to each of the quality control indicators; Based on the evaluation weights, scoring standards, and quality control results corresponding to each quality control indicator, the inspection data are evaluated and analyzed to obtain the evaluation results of each inspection data.

6. The report quality control processing method according to claim 1, characterized in that, The quality control system determines the target quality control results for each examination data point based on the initial quality control results and the pathological diagnosis results, including: Identify the target inspection data belonging to the same inspection area from among the various inspection data; Using the pathological diagnosis results, the initial quality control results of each examination data, and the target examination data in each examination data, the target quality control results of each examination data are determined.

7. The report quality control processing method according to claim 6, characterized in that, The utilization of the pathological diagnosis results, the initial quality control results of each examination data, and the target examination data in each examination data includes: The pathological diagnosis results are compared with the target examination data in each examination data, and combined with the initial quality control results of each examination data, to determine whether the examination results for the same examination site in each examination data are consistent, and to determine the target quality control results of each examination data.

8. The report quality control processing method according to claim 1, characterized in that, After determining the target quality control results for each inspection data point, the method further includes: Based on the target quality control results, the user's pathological information, and examination information, a prompt message is determined, which is used to remind the user to follow up.

9. A medical data processing system, characterized in that, The medical data processing system includes: an artificial intelligence module, a quality control system, multiple examination systems, and a pathology system; The artificial intelligence module is used to execute the report quality control processing method executed by any one of the artificial intelligence modules in claims 1-8; The quality control system is used to execute the report quality control processing method executed by any one of the quality control systems in claims 1-8; Each of the aforementioned inspection systems is used to output inspection data; The pathology system is used to output pathological diagnostic results.

10. An electronic device, characterized in that, include: A processor and a memory, the memory storing machine-readable instructions executable by the processor, wherein when the electronic device is running, the processor executes the machine-readable instructions to perform the steps of the report quality control processing method as described in any one of claims 1 to 8.

Images