Clinical data entry method and device, electronic equipment and storage medium

Abstract

The invention discloses a clinical data entry method and device, electronic equipment and a storage medium, and relates to the technical field of data entry, and the method comprises the steps: obtaining clinical data of an HIS hospital information management system and form data of an EDC electronic data collection system, carrying out the desensitization processing of the clinical data, obtaining desensitized data, and storing the desensitized data in a database; on the basis of the form data, constructing cue words; inputting the desensitization data and the cue word into a preset multi-mode large model, and guiding the multi-mode large model to perform structured processing on the desensitization data through the cue word to obtain structured data; and verifying the structured data based on the standard data format of the form data, and inputting the verified structured data into the EDC system. According to the invention, the universality of the data entry method between different HIS systems and different EDC systems is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data entry, and in particular to a clinical data entry method, device, electronic device and storage medium. Background Art

[0002] The EDC (Electronic Data Capture) system is a data collection and management system used for clinical trials and other research projects. It is a software tool for electronically collecting, storing, managing and analyzing research data. In the process of entering clinical data into the EDC system through traditional operations, it is necessary to directly connect the HIS (Hospital Information System) to the EDC system, so that the clinical data can be directly imported from the HIS to the EDC system. However, each hospital has its own HIS, and each manufacturer has its own EDC system software. Different HISs are difficult to meet the data format requirements of different EDC systems. Directly connecting the HIS to the EDC system can only cover fixed hospitals and fixed manufacturers in a small range. This method is not universal.

[0003] Therefore, how to achieve highly universal data entry between different HIS and different EDC systems is a problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of this application is to provide a clinical data entry method, device, electronic device and storage medium, aiming to solve the technical problem of how to achieve highly universal data entry between different HIS and different EDC systems.

[0005] To achieve the above objectives, the present application proposes a clinical data entry method, the method comprising:

[0006] Acquire clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, perform desensitization processing on the clinical data to obtain desensitized data, and construct prompt words based on the form data;

[0007] Inputting the desensitized data and the prompt word into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data;

[0008] The structured data is verified based on the standard data format of the form data, and the verified structured data is entered into the EDC system.

[0009] In one embodiment, the step of guiding the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data includes:

[0010] Identify the indicator name and indicator content in the desensitized data through the multimodal large model to obtain candidate indicator items in the desensitized data;

[0011] The multimodal large model is guided by the prompt word to convert each candidate indicator item into the structured data.

[0012] In one embodiment, the step of guiding the multimodal large model to convert each candidate index item into the structured data through the prompt word includes:

[0013] Determine the target indicator name in the prompt word through the multimodal large model, and screen the candidate indicator items based on the target indicator name to obtain the indicator items to be converted, wherein the indicator items to be converted are candidate indicator items whose indicator names are consistent with the target indicator names;

[0014] The indicator item to be converted is converted into structured data by referring to the conversion rules in the prompt word through the multimodal large model.

[0015] In one embodiment, the step of obtaining clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system includes:

[0016] Capturing the screen interface of the HIS to obtain the clinical data;

[0017] A preset form in the EDC system is obtained, and metadata of the preset form is extracted to obtain the form data.

[0018] In one embodiment, the step of performing desensitization processing on the clinical data to obtain desensitized data includes:

[0019] Identify the text content in the clinical data to obtain a text recognition result, and use the area where the field in the text recognition result is consistent with the preset field as the area to be desensitized in the clinical data;

[0020] The area to be desensitized is fuzzy processed to obtain desensitized data.

[0021] In one embodiment, the step of verifying the structured data based on the standard data format of the form data includes:

[0022] Acquire the standard data format of the form data and the data format to be verified of the structured data;

[0023] The standard data format is compared with the data format to be verified, and when the standard data format is consistent with the data format to be verified, it is determined that the structured data has passed the verification.

[0024] In one embodiment, the step of entering the verified structured data into the EDC system includes:

[0025] A target interface corresponding to the EDC system is called based on the standard data format, and the verified structured data is entered into the EDC system through the target interface.

[0026] In addition, to achieve the above-mentioned purpose, the present application also proposes a clinical data entry device, the clinical data entry device comprising:

[0027] A preparation module is used to obtain clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, perform desensitization processing on the clinical data to obtain desensitized data, and construct prompt words based on the form data;

[0028] A processing module, used for inputting the desensitized data and the prompt word into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data;

[0029] An input module is used to verify the structured data based on the standard data format of the form data, and enter the verified structured data into the EDC system.

[0030] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the clinical data entry method described above.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the clinical data entry method described above are implemented.

[0032] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the clinical data entry method described above are implemented.

[0033] One or more technical solutions proposed in this application have at least the following technical effects:

[0034] The present application first obtains clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, desensitizes the clinical data to obtain desensitized data, and constructs prompt words based on the form data, so as to provide guidance and context information for subsequent data structured processing by constructing prompt words, thereby ensuring that the clinical data can be processed in accordance with the requirements of the EDC system; the desensitized data and the prompt words are input into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt words to obtain structured data, so as to utilize the processing capability of the multimodal large model to convert unstructured clinical data into structured data that can be accepted and processed by the EDC system, thereby improving the accuracy and efficiency of clinical data entry; the structured data is verified based on the standard data format of the form data, and the verified structured data is entered into the EDC system, thereby ensuring that only structured clinical data that conforms to the preset standard data format of the EDC system can be entered, thereby ensuring the quality and consistency of data in the EDC system.

[0035] In summary, the present application extracts clinical data from the HIS system, and finally enters the structured clinical data that conforms to the preset standard data format of the EDC system into the EDC system through prompt words, desensitization processing, structuring processing and format verification constructed based on the preset form data in the EDC system, so as to convert clinical data in different formats in different HIS into structured data in the format required by the EDC system for entry, thereby improving the universality of the data entry method between different HIS and different EDC systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A flowchart of the first embodiment of the clinical data entry method of the present application is provided;

[0039] Figure 2 A flowchart of the second embodiment of the clinical data entry method of this application is provided;

[0040] Figure 3 A system architecture diagram of the clinical data entry method provided in Example 2 of the present application;

[0041] Figure 4 A brief flowchart of the clinical data entry method provided in Example 2 of the present application;

[0042] Figure 5 This is a schematic diagram of the module structure of the clinical data entry device according to an embodiment of the present application;

[0043] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the clinical data entry method in the embodiment of the present application.

[0044] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0045] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0046] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0047] The main solution of the embodiment of the present application is: obtaining clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, desensitizing the clinical data to obtain desensitized data, and constructing prompt words based on the form data; inputting the desensitized data and the prompt words into a preset multimodal large model to guide the multimodal large model to perform structured processing on the desensitized data through the prompt words to obtain structured data; verifying the structured data based on the standard data format of the form data, and entering the verified structured data into the EDC system.

[0048] In the process of entering clinical data into the EDC system, the existing technology requires that the HIS be directly connected to the EDC system, so that the clinical data can be directly imported from the HIS into the EDC system. However, each hospital has its own HIS, and each manufacturer has its own EDC system software. Different HISs are difficult to meet the data format requirements of different EDC systems. Directly connecting the HIS to the EDC system can only cover a small range of fixed hospitals and fixed manufacturers, and this method is not universal. Therefore, how to achieve highly universal data entry between different HISs and different EDC systems is a problem that needs to be solved urgently.

[0049] The present application provides a solution, which extracts clinical data from the HIS system, and finally enters the structured clinical data that conforms to the preset standard data format of the EDC system into the EDC system through prompt words, desensitization processing, structuring processing and format verification constructed based on the preset form data in the EDC system, so as to convert the clinical data of different formats in different HIS into structured data in the format required by the EDC system for entry, thereby improving the universality of the data entry method between different HIS and different EDC systems.

[0050] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes an electronic device as an example to illustrate this embodiment and the following embodiments.

[0051] Based on this, the present application embodiment provides a clinical data entry method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the clinical data entry method of the present application.

[0052] In this embodiment, the clinical data entry method is applied to a clinical data entry system, and the clinical data entry method includes steps S10 to S30:

[0053] Step S10, obtaining clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, desensitizing the clinical data to obtain desensitized data, and constructing prompt words based on the form data;

[0054] It should be noted that clinical data refers to patient medical records, diagnosis, treatment and other medical-related information intercepted from HIS; form data refers to the preset fields and format requirements for entering clinical data related to the eCRF (Electronic Case Report Form) created in the EDC system; desensitized data refers to clinical data from which the patient's personal sensitive information has been removed; prompt words refer to instructions generated according to the requirements of the eCRF-related form data in the EDC system, which are used to guide the multimodal large model to convert clinical data into structured data.

[0055] It is understandable that, in the process of connecting different HIS and different EDC systems, directly connecting HIS and EDC systems may lead to the risk of leakage of patient privacy information, and there are often data errors and omissions entered into the EDC system due to the format of clinical data not matching the EDC system. Therefore, step S10 is performed to ensure that patient privacy information will not be leaked during the subsequent processing and use of clinical data through desensitization processing. At the same time, by constructing prompt words, guidance and contextual information are provided for subsequent data structuring processing, avoiding data errors and omissions in the process of clinical data entry, ensuring that clinical data can be accurately converted into structured data required by the EDC system in accordance with the requirements of the EDC system, thereby improving the accuracy and efficiency of data entry.

[0056] Exemplarily, clinical data of HIS and form data of EDC system are obtained, clinical data is desensitized to obtain desensitized data, and prompt words are constructed based on the obtained form data as follows:

[0057] "You are a professional clinical CRA expert. For the input {{{#sys.image#}}}, extract the data content of the corresponding form based on the following form metadata. Please check carefully, do not miss the extraction of input data items, and do not add or expand them at will. Keep it consistent with the original input data and output it in json format;

[0058] {'Table Name':['Demographic Data'],'Field Name':{'Demographic Data':['Date of Birth','Age','Gender','Ethnicity','Department of Admission']},'Option Name':{'Demographic Data':{'Date of Birth':[],'Age':[],'Gender':['Male','Female'],'Ethnicity':['Han','Other','Unknown']}}};

[0059] {'Table Name':['History of previous combined use of anti-infective drugs'],'Field Name':{'History of previous combined use of anti-infective drugs':['Serial Number','Drug Name (Generic Name)','Reason for medication','Start Date (yy-mm-dd)','Whether it continues','End Date (yy-mm-dd)','Dose per dose','Frequency of medication','Route of administration']},'Option Name':{'History of previous combined use of anti-infective drugs':{'Serial Number':[],'Drug Name (Generic Name)':[],'Reason for medication':[],'Start Date (yy-mm-dd)':[],'Whether it continues':[],'End Date (yy-mm-dd)':[],'Dose per dose':[],'Frequency of medication':[],'Route of administration':[]}}}"

[0060] Among them, sys.image is the desensitized data of HIS input into the multimodal large model.

[0061] Step S20, inputting the desensitized data and the prompt word into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data;

[0062] It should be noted that a multimodal big model refers to a machine learning model that can process multiple different types of data. This machine learning model can understand and analyze data from different sources and formats, including text, images, videos, etc., and convert these data into a structured form, thereby improving the flexibility of obtaining clinical data; structured data refers to data organized in the data format required by the EDC system, which is convenient for the EDC system to store, query and analyze.

[0063] It is understandable that, in the traditional clinical data entry process, the clinical data in the HIS is difficult to be effectively utilized by the EDC system due to data format mismatch, so step S20 is performed to convert the unstructured clinical data into structured data that is easy for the EDC system to process and analyze, thereby improving the quality and availability of the data entered into the EDC system.

[0064] In a feasible implementation manner, the step of performing structured processing on the desensitized data by using the multimodal large model to obtain structured data in step S20 may include steps S21 to S22:

[0065] Step S21, identifying the indicator name and indicator content in the desensitized data through the multimodal large model to obtain each candidate indicator item in the desensitized data;

[0066] It should be noted that each candidate indicator item refers to an independent data segment that may contain useful information identified by the multimodal large model in the desensitized data. The independent data segment may include the indicator name in the original clinical data such as date of birth, age, gender, ethnicity, and admission department, as well as the specific content of the indicator name.

[0067] It is understandable that since the process of identifying indicator items in the desensitized data may lead to omission of indicator item identification or incorrect identification, step S21 is performed to ensure that all potentially useful information in the desensitized data can be correctly identified and extracted, thereby improving the accuracy and comprehensiveness of indicator item extraction and ensuring that the data source for subsequent structured processing is complete and reliable.

[0068] Step S22: guiding the multimodal large model to convert each candidate index item into the structured data through the prompt word.

[0069] It is understandable that due to the non-uniform format in the traditional indicator item conversion process, the converted data is difficult for the EDC system to use, so step S22 is performed to ensure that each candidate indicator item is converted into structured data that meets the format requirements of the EDC system, thereby improving the degree of automation of data entry and data quality.

[0070] In this embodiment, by adopting data recognition and data conversion of a multimodal large model, it is possible to accurately extract and convert structured data that meets the format requirements of the EDC system from unstructured desensitized data, reduce manual intervention in the clinical data entry process, thereby improving the level of automation in data processing, and ensuring the accuracy and consistency of the data, providing a high-quality data foundation for clinical research and decision support.

[0071] In a feasible implementation, step S22 may include steps S221 to S222:

[0072] Step S221, determining the target indicator name in the prompt word through the multimodal large model, and screening the candidate indicator items based on the target indicator name to obtain the indicator items to be converted, wherein the indicator items to be converted are candidate indicator items whose indicator names are consistent with the target indicator names;

[0073] It should be noted that the target indicator name refers to the name information about the indicator content in the prompt word constructed according to the form data requirements of the EDC system; the indicator items to be converted refer to the indicator items that are prepared to be converted into structured data after screening.

[0074] It is understandable that, in the process of converting clinical data into structured data required by the EDC system, some irrelevant information not needed by the EDC system will be converted, thereby increasing the operating power consumption of the system. Therefore, step S221 is performed to avoid erroneously converting irrelevant information in the clinical data that is not needed by the EDC system into structured data, ensuring that only indicator items that meet the requirements of the EDC system are structured, thereby improving the pertinence and accuracy of data conversion, reducing the generation of invalid data, and reducing the power consumption of structured processing.

[0075] Exemplarily, when the target indicator names in the prompt words are determined by the multimodal large model to be "date of birth", "age", "gender", and "ethnicity", and the indicator names corresponding to the candidate indicator items in the desensitized data are "efficacy evaluation date", "clinical efficacy", "microbiological efficacy", "whether the patient is alive", "date of birth", "age", "gender", and "ethnicity", the candidate indicator items are screened based on the target indicator items, and the indicator items to be converted are "date of birth", "age", "gender", and "ethnicity" whose indicator names in the desensitized data are consistent with the target indicator names.

[0076] Step S222: converting the indicator item to be converted into structured data by referring to the conversion rule in the prompt word through the multimodal large model.

[0077] It should be noted that the conversion rule refers to the instruction defined in the prompt word, which is used to guide the multimodal large model to map the data items to be converted into the structured data format required by the EDC system.

[0078] In this embodiment, a multimodal large model under the guidance of prompt words is used to accurately extract and convert structured data that meets the requirements of the EDC system from unstructured candidate indicator items, thereby avoiding data entry errors and improving the automation level and data quality of clinical data processing during the data entry process.

[0079] Step S30, verifying the structured data based on the standard data format of the form data, and entering the verified structured data into the EDC system.

[0080] It should be noted that the standard data format refers to the data entry format specified by the EDC system.

[0081] It is understandable that after being structured by the multimodal large model, the data may still not meet the format requirements of the EDC system, so step S30 is performed to avoid data entry errors and data quality problems caused by incorrect or incomplete data format, thereby ensuring that only accurate data that meets the standard data format of the EDC system is entered into the system, thereby improving the accuracy and reliability of data entry.

[0082] In a feasible implementation manner, the step of verifying the structured data based on the standard data format of the form data in step S30 may include steps S31 to S32:

[0083] Step S31, obtaining the standard data format of the form data and the data format to be verified of the structured data;

[0084] It should be noted that the data format to be verified refers to the data format formed during the conversion of structured data, which may contain errors in the conversion process or parts that do not conform to the standard data format.

[0085] It is understandable that since the problem of incorrect data format after structuring may occur during the process of structuring data in a multimodal large model, step S31 is performed to obtain the data format of the structured data and the data format required by the EDC system, thereby providing an effective judgment basis for verifying the data format of the structured data.

[0086] Step S32, comparing the standard data format with the data format to be verified, and when the standard data format is consistent with the data format to be verified, determining that the structured data passes the verification.

[0087] It should be noted that after the structured data is verified, a verification report is generated and output. If the standard data format is inconsistent with the data format to be verified, an error prompt signal is output to help users quickly discover and correct data problems and ensure the quality of structured data.

[0088] It is understandable that since errors may occur in the format of the structured data during the process of structured data processing in the multimodal large model, making the structured data difficult to use in the EDC system, step S32 is performed to avoid the problem of mismatch in the format of the structured data and ensure that only data that meets the format requirements of the EDC system can be entered into the EDC system.

[0089] In this embodiment, by performing data format identification and data format comparison on structured data, it is ensured that the structured data is format-checked before being entered into the EDC system, thereby avoiding data format errors that result in invalid data with mismatched formats being entered into the EDC system, thereby improving the accuracy and reliability of data entry.

[0090] In a feasible implementation manner, the step of entering the verified structured data into the EDC system in step S30 may include step S33:

[0091] Step S33: calling a target interface corresponding to the EDC system based on the standard data format, and entering the verified structured data into the EDC system through the target interface.

[0092] It should be noted that the target interface refers to the data entry interface corresponding to the EDC system, and the data entry interface is used to enter the verified structured data into the EDC system.

[0093] In this implementation, structured data is entered into the EDC system through interface calls, thereby avoiding errors and inefficiencies that may occur during traditional manual data entry and achieving automated data entry. At the same time, by matching the standard data format with the target interface, the accuracy and consistency of the data during transmission are ensured, the efficiency of data entry is improved, and the accuracy and integrity of the data in the EDC system are guaranteed.

[0094] In this embodiment, a clinical data entry method is proposed, which extracts clinical data from the HIS system, and finally enters the structured clinical data that conforms to the preset standard data format of the EDC system into the EDC system through prompt words, desensitization processing, structuring processing and format verification based on the preset form data in the EDC system, so as to convert the clinical data in different formats in different HIS into structured data in the format required by the EDC system for entry, thereby improving the universality of the data entry method between different HIS and different EDC systems.

[0095] In a feasible implementation, the step of performing desensitization processing on the clinical data to obtain desensitized data in step S20 may include steps S201 to S202:

[0096] Step S201, identifying the text content in the clinical data to obtain a text recognition result, and taking the area where the field in the text recognition result is consistent with the preset field as the area to be desensitized in the clinical data;

[0097] It should be noted that text content refers to text information in clinical data, such as patient names, medical records, etc.; text recognition results refer to field contents extracted from clinical data through OCR (Optical Character Recognition) technology; the area to be desensitized refers to the area in the clinical data that records patient sensitive information, which is the area where the field content consistent with the preset field is located in the text recognition results.

[0098] It is understandable that since manual recognition of text content has the problems of low recognition efficiency and high recognition error rate, step S201 is performed to achieve rapid and accurate recognition of sensitive information in clinical data through automated text recognition and area determination, providing an accurate data basis for subsequent desensitization processing.

[0099] Step S202, performing fuzzy processing on the area to be desensitized to obtain desensitized data.

[0100] It should be noted that obfuscation processing refers to the use of technical means to process sensitive information so that the sensitive information cannot be accurately identified, thereby protecting the privacy of patients.

[0101] It is understandable that, since some of the patient's private information needs to be shielded based on compliance considerations, step S202 is performed to ensure patient privacy and data security by blurring sensitive information, thereby meeting high standards of compliance requirements.

[0102] In this implementation, by fuzzifying the patient privacy part in the clinical data, the automation level of processing the patient privacy information in the clinical data is improved, manual intervention is reduced, and the security of the patient privacy information is ensured.

[0103] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , Figure 2 This is a flowchart of the second embodiment of the clinical data entry method of the present application.

[0104] The step of obtaining the clinical data of the HIS hospital information management system and the form data of the EDC electronic data collection system in step S10 may include steps S01 to S02:

[0105] Step S01, capturing the screen interface of the HIS to obtain the clinical data;

[0106] It is understandable that since the traditional direct connection between the HIS system and the EDC system requires direct access to the HIS database, it may lead to the risk of leakage of patient privacy information. Therefore, step S01 is performed to capture the HIS screen interface to obtain the HIS clinical data without accessing the HIS database, thereby reducing the risk of leakage of patient privacy information and improving the security of obtaining clinical data in the HIS.

[0107] Exemplarily, the screen interface of the HIS is monitored in real time through a screen capture tool, such as PyAutoGUI, OpenCV, etc., and the monitored screen interface is captured to obtain a screenshot, that is, the clinical data of the HIS.

[0108] Step S02, obtaining a preset form in the EDC system, and extracting metadata of the preset form to obtain the form data.

[0109] It should be noted that the preset form refers to a standard form in the EDC system for receiving input data, and the standard form may be an eCRF; metadata refers to the descriptive information of the preset form in the EDC.

[0110] It is understandable that since manual determination of the form data of the EDC system will result in low efficiency and high error rate, step S02 is performed to achieve fast and accurate acquisition of the form data of the EDC system through automated form acquisition and metadata extraction, thereby improving the efficiency and quality of form data processing, while also reducing the tediousness of manual operations, making the acquisition of form data more efficient and accurate.

[0111] In this embodiment, by adopting screen capture technology and metadata extraction technology, clinical data is obtained from the HIS and form data is obtained from the EDC system, providing an accurate data basis for subsequent data processing and analysis. At the same time, by automatically acquiring clinical data and form data, rapid data integration and processing are achieved, thereby improving the efficiency of data management during the clinical data entry process.

[0112] For example, to help understand the implementation process of the clinical data entry method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A system architecture diagram of a clinical data entry method is provided, specifically:

[0113] CRC (Clinical Research Coordinator) operates HIS to display screen data, obtains target data through data collection agent, and obtains captured screen data, i.e., clinical data of HIS. The captured screen data is desensitized by data desensitization processing agent to obtain desensitized data, i.e., desensitized data. The data processing agent uses a multimodal model to process data, i.e., the desensitized data is structured through a multimodal large model to obtain structured data. The structured data is verified by a data verifier, and the verified data, i.e., the verified structured data, is called through the EDC data entry interface calling agent API, i.e., the target interface, and the verified data is entered into the EDC system.

[0114] For further information, please refer to Figure 4 , Figure 4 A brief flow chart of a clinical data entry method is provided, specifically:

[0115] Through user operation of HIS display screen data, the screen capture tool is called at the user layer to capture the image, that is, the clinical data of HIS, and the prompt is automatically linked in the automatic link prompt layer, that is, the prompt word is constructed based on the form data of the EDC system. The automatically linked prompt and the captured image, that is, the prompt word and clinical data are input into the multimodal model processing layer, that is, the multimodal large model, so as to perform structured processing on the captured image through the multimodal large model to obtain structured data, for example: extract the information such as "date of birth: August 1, 2000, age: 24, gender: male, height: 172, weight: 56" in the image, that is, the candidate indicator items, and output the structured data as follows:

[0116] {"Corresponding form name":["Demographic data"],"Option name":{"Demographic data":{"Date of birth":"2000.08.01","Age":"24","Gender":"Male","Ethnicity":"Han"}}}

[0117] The structured data is transmitted to the structured data output layer, so that the target interface is called at the structured data output layer to enter the structured data into the corresponding "demographic" form of the EDC system.

[0118] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the clinical data entry method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0119] This application also provides a clinical data entry device, please refer to Figure 5 , the clinical data entry device comprises:

[0120] A preparation module 10 is used to obtain clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, perform desensitization processing on the clinical data to obtain desensitized data, and construct prompt words based on the form data;

[0121] A processing module 20, for inputting the desensitized data and the prompt word into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data;

[0122] The input module 30 is used to verify the structured data based on the standard data format of the form data, and input the verified structured data into the EDC system.

[0123] Optionally, the processing module 20 is further used for:

[0124] Identify the indicator name and indicator content in the desensitized data through the multimodal large model to obtain candidate indicator items in the desensitized data;

[0125] The multimodal large model is guided by the prompt word to convert each candidate indicator item into the structured data.

[0126] Optionally, the processing module 20 is further used for:

[0127] Determine the target indicator name in the prompt word through the multimodal large model, and screen the candidate indicator items based on the target indicator name to obtain the indicator items to be converted, wherein the indicator items to be converted are candidate indicator items whose indicator names are consistent with the target indicator names;

[0128] The indicator item to be converted is converted into structured data by referring to the conversion rules in the prompt word through the multimodal large model.

[0129] Optionally, the preparation module 10 is further used for:

[0130] Capturing the screen interface of the HIS to obtain the clinical data;

[0131] A preset form in the EDC system is obtained, and metadata of the preset form is extracted to obtain the form data.

[0132] Optionally, the preparation module 10 is further used for:

[0133] Identify the text content in the clinical data to obtain a text recognition result, and use the area where the field in the text recognition result is consistent with the preset field as the area to be desensitized in the clinical data;

[0134] The area to be desensitized is fuzzy processed to obtain desensitized data.

[0135] Optionally, the input module 30 is further used for:

[0136] Acquire the standard data format of the form data and the data format to be verified of the structured data;

[0137] The standard data format is compared with the data format to be verified, and when the standard data format is consistent with the data format to be verified, it is determined that the structured data has passed the verification.

[0138] Optionally, the input module 30 is further used for:

[0139] A target interface corresponding to the EDC system is called based on the standard data format, and the verified structured data is entered into the EDC system through the target interface.

[0140] The clinical data entry device provided by the present application adopts the clinical data entry method in the above embodiment, which can solve the technical problem of how to achieve highly universal data entry between different HIS and different EDC systems. Compared with the prior art, the beneficial effects of the clinical data entry device provided by the present application are the same as the beneficial effects of the clinical data entry method provided by the above embodiment, and the other technical features in the clinical data entry device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0141] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the clinical data entry method in the above-mentioned embodiment one.

[0142] Reference below Figure 6 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0143] like Figure 6 As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0144] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0145] The electronic device provided by the present application adopts the clinical data entry method in the above embodiment, which can solve the technical problem of how to achieve highly universal data entry between different HIS and different EDC systems. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the clinical data entry method provided by the above embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0146] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0147] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0148] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the clinical data entry method in the above-mentioned embodiment.

[0149] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0150] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0151] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device: obtains clinical data from an HIS hospital information management system and form data from an EDC electronic data collection system, desensitizes the clinical data to obtain desensitized data, and constructs prompt words based on the form data; inputs the desensitized data and the prompt words into a preset multimodal large model to guide the multimodal large model to perform structured processing on the desensitized data through the prompt words to obtain structured data; verifies the structured data based on the standard data format of the form data, and enters the verified structured data into the EDC system.

[0152] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0155] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned clinical data entry method, and can solve the technical problem of how to achieve highly universal data entry between different HIS and different EDC systems. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the clinical data entry method provided by the above-mentioned embodiment, and will not be repeated here.

[0156] The present application also provides a computer program product, comprising a computer program, which implements the steps of the clinical data entry method as described above when executed by a processor.

[0157] The computer program product provided by this application can solve the technical problem of how to achieve highly universal data entry between different HIS and different EDC systems. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the clinical data entry method provided in the above embodiment, which will not be repeated here.

[0158] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A clinical data entry method, characterized in that: The clinical data entry method comprises: Acquire clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, perform desensitization processing on the clinical data to obtain desensitized data, and construct prompt words based on the form data; Inputting the desensitized data and the prompt word into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data; The structured data is verified based on the standard data format of the form data, and the verified structured data is entered into the EDC system.

2. The clinical data entry method according to claim 1, characterized in that: The step of guiding the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data includes: Identify the indicator name and indicator content in the desensitized data through the multimodal large model to obtain candidate indicator items in the desensitized data; The multimodal large model is guided by the prompt word to convert each candidate indicator item into the structured data.

3. The clinical data entry method according to claim 2, characterized in that: The step of guiding the multimodal large model to convert each candidate index item into the structured data through the prompt word includes: Determine the target indicator name in the prompt word through the multimodal large model, and screen the candidate indicator items based on the target indicator name to obtain the indicator items to be converted, wherein the indicator items to be converted are candidate indicator items whose indicator names are consistent with the target indicator names; The indicator item to be converted is converted into structured data by referring to the conversion rules in the prompt word through the multimodal large model.

4. The clinical data entry method according to claim 1, characterized in that: The steps of obtaining clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system include: Capturing the screen interface of the HIS to obtain the clinical data; A preset form in the EDC system is obtained, and metadata of the preset form is extracted to obtain the form data.

5. The clinical data entry method according to claim 1, characterized in that: The step of performing desensitization processing on the clinical data to obtain desensitized data comprises: Identify the text content in the clinical data to obtain a text recognition result, and use the area where the field in the text recognition result is consistent with the preset field as the area to be desensitized in the clinical data; The area to be desensitized is fuzzy processed to obtain desensitized data.

6. The clinical data entry method according to claim 1, characterized in that: The step of verifying the structured data based on the standard data format of the form data includes: Acquire the standard data format of the form data and the data format to be verified of the structured data; The standard data format is compared with the data format to be verified, and when the standard data format is consistent with the data format to be verified, it is determined that the structured data has passed the verification.

7. The clinical data entry method according to claim 1, characterized in that: The step of entering the verified structured data into the EDC system comprises: A target interface corresponding to the EDC system is called based on the standard data format, and the verified structured data is entered into the EDC system through the target interface.

8. A clinical data entry device, characterized in that: The clinical data entry device comprises: A preparation module is used to obtain clinical data from the HIS hospital information management system and form data from the EDC electronic data collection system, perform desensitization processing on the clinical data to obtain desensitized data, and construct prompt words based on the form data; A processing module, used for inputting the desensitized data and the prompt word into a preset multimodal large model, so as to guide the multimodal large model to perform structured processing on the desensitized data through the prompt word to obtain structured data; An input module is used to verify the structured data based on the standard data format of the form data, and enter the verified structured data into the EDC system.

9. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the clinical data entry method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the clinical data entry method according to any one of claims 1 to 7 are implemented.

Images