Medical record paperless generation and quality control method and system based on markup language

Abstract

The invention discloses a medical record paperless generation and quality control method and system based on markup language, and aims to improve the efficiency and accuracy of medical record information processing. The method comprises the following steps: firstly, acquiring image information of an electronic medical record, extracting medical record information and converting the medical record information into XML format data; secondly, converting the XML format data into HTML format data by using an XSLT technology; then, selecting an optimal conversion tool to generate a PDF file through pre-selecting a PDF conversion tool and determining the performance of the PDF conversion tool; and finally, performing data accuracy and integrity inspection on the PDF file by using an anomaly detection algorithm, and correcting the data according to an inspection result. According to the invention, paperless processing and quality control of the medical record information are realized through the markup language, and the efficiency and precision of medical record management are improved. Therefore, the method has important application value in the field of medical informatization.

Description

Technical Field

[0001] This invention relates to the field of paperless medical record technology, and in particular to a method and system for paperless medical record generation and quality control based on markup language. Background Technology

[0002] With the rapid development of information technology, the healthcare industry is gradually moving towards a new era of digital transformation. Among the key aspects of this transformation is the technology for generating paperless medical records and its quality control. This technology is based on two important markup languages: XML (Extensible Markup Language) and HTML (Hypertext Markup Language).

[0003] In the healthcare industry, the standardization and digitization of medical records are crucial for improving doctor-patient communication efficiency, ensuring medical quality, and managing medical records. XML-based paperless medical record generation technology can effectively organize structured and unstructured data within medical records. Due to XML's strong self-descriptive properties, it facilitates quick understanding and retrieval by healthcare professionals. Furthermore, XML's flexibility enables remote transmission of medical record information and its application across multiple platforms.

[0004] The application of HTML in the generation of paperless medical records mainly lies in the presentation of these documents. Medical institutions can display medical record information on various devices, including computers, tablets, and mobile devices. This transformation not only enhances the readability of the documents but also enables medical staff to browse and share medical record information online.

[0005] The goal of generating paperless medical records is to define a strict XML Schema and use a specific algorithm to quickly and accurately convert XML and HTML-based document types into standard PDF documents, while simultaneously validating the format and content of the documents during generation.

[0006] The generation of standardized paperless medical record documents is only the first step; ensuring the quality and content of these documents is equally crucial. This involves the application of content quality control technology. Content quality control primarily refers to the monitoring and evaluation of the accuracy, completeness, and compliance of medical record document content. In this process, XML and HTML-based document structures can greatly simplify quality control work because their structured nature allows automated detection tools to easily identify errors and omissions in the documents. Summary of the Invention

[0007] To address at least one of the aforementioned technical problems, this invention proposes a method and system for paperless generation and quality control of medical records based on markup language.

[0008] The first aspect of this invention provides a method for paperless generation and quality control of medical records based on markup language, comprising:

[0009] The image information of the electronic medical record is acquired, the medical record information is extracted from the image information, and the medical record information is converted into an XML data structure to obtain XML format medical record data;

[0010] Converting XML format medical record data into HTML format medical record data based on XSLT technology;

[0011] Multiple PDF conversion tools are pre-selected, the data conversion performance of each tool is determined, and the preferred PDF conversion tool is determined based on the data conversion performance.

[0012] The preferred PDF conversion tool is used to generate PDF files from HTML format medical record data.

[0013] The PDF file is tested for data accuracy and integrity using an anomaly detection algorithm. The test results are then used to correct the data in the PDF file.

[0014] In this solution, the steps of acquiring image information from electronic medical records, extracting medical record information from the image information, and converting the medical record information into an XML data structure to obtain XML format medical record data are as follows:

[0015] Electronic medical records are obtained through the hospital information system, converted into digital images to obtain image information of the electronic medical records, and the image information is preprocessed, including noise removal, adjustment of image brightness and contrast;

[0016] The text content of the preprocessed image information is extracted using optical character recognition technology, and key information of the text content is identified based on natural language processing technology. The key information includes the patient's name, gender, age, medical history, and diagnosis result.

[0017] The disease image data is extracted from the image information using computer vision technology;

[0018] Based on the key information and medical image data, a preset XML data template is used to organize and arrange the key information and medical image data according to the preset XML data template to obtain medical record data in XML format;

[0019] Add notes and attributes to the XML format medical record data, construct a database, and store the XML format medical record data in the database.

[0020] In this solution, the conversion of XML format medical record data into HTML format medical record data based on XSLT technology specifically involves:

[0021] Create an XSLT stylesheet, define a medical record template in the stylesheet, use XPath expressions to select nodes in the XML format medical record data, and map the nodes to HTML attributes;

[0022] The XSLT processor loads XML format medical record data and XSLT style sheets, and then passes the XML format medical record data and XSLT style sheets to the processor for conversion to obtain HTML format medical record data.

[0023] In this solution, the process of pre-selecting multiple PDF conversion tools, determining the data conversion performance of each tool, and then determining the preferred PDF conversion tool based on the data conversion performance is as follows:

[0024] Multiple PDF conversion tools are pre-selected, and a preset number of HTML format medical record data are prepared. The preset number of HTML format medical record data is imported into each PDF conversion tool for conversion to obtain test PDF format medical record data.

[0025] Get the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data;

[0026] A hash algorithm is introduced to calculate the hash values ​​of text data and image data in the preset number of HTML format medical record data and test PDF format medical record data, so as to obtain HTML format medical record hash data and PDF format medical record hash data.

[0027] The similarity data is obtained by comparing the HTML format medical record hash data with the PDF format medical record hash data;

[0028] The conversion accuracy of each PDF conversion tool for HTML format medical record data is calculated based on the similarity data.

[0029] The data conversion performance of each PDF conversion tool is evaluated based on the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data and the conversion accuracy of each PDF conversion tool for HTML format medical record data.

[0030] The preferred PDF conversion tool is determined based on the conversion performance.

[0031] In this solution, the step of generating a PDF file from the HTML format medical record data using the preferred PDF conversion tool specifically involves:

[0032] The HTML format medical record data is imported into the preferred PDF conversion tool. The HTML string in the HTML format medical record data is passed to an instance of the HTML class for conversion to obtain a PDF medical record file.

[0033] The preferred PDF conversion tool tracks data records during the PDF conversion process through its logs.

[0034] The integrity of the HTML format medical record data conversion is determined based on the data records. Based on the integrity, it is determined whether a re-conversion is needed, resulting in a secondary conversion evaluation plan.

[0035] In this solution, the step of performing data accuracy and integrity checks on the PDF file based on anomaly detection algorithms, obtaining the check results, and then correcting the data in the PDF file based on the check results, specifically involves:

[0036] The text data in the PDF file and HTML format medical record data is identified using natural language processing methods to obtain PDF text data and HTML text data;

[0037] The accuracy of the PDF file's data is determined by comparing the PDF text data with the HTML text data.

[0038] The structural integrity of the table data in the PDF file is checked by the structural data inspection method. The integrity of the rows and columns and the accuracy of the data format are judged to obtain the table inspection results.

[0039] The sharpness of the image data in the PDF file is detected by an image data inspection method, and the image inspection results are obtained.

[0040] Preset the weighting of data accuracy, table inspection results, and image inspection results in the PDF file to the quality of the PDF file;

[0041] The quality of the PDF file is assessed based on the weighted data and the data accuracy, table inspection results, and image inspection results of the PDF file, and an evaluation score is obtained.

[0042] If the evaluation score is lower than the preset value, the PDF file will be marked as a file requiring data correction.

[0043] The data to be corrected is compared with the HTML format medical record data. Outliers in the data to be corrected are marked, and the marked data is manually corrected.

[0044] A second aspect of the present invention also provides a paperless medical record generation and quality control system based on markup language. The system includes a memory and a processor. The memory includes a program for a paperless medical record generation and quality control method based on markup language. When the processor executes the program, the program performs the following steps:

[0045] The image information of the electronic medical record is acquired, the medical record information is extracted from the image information, and the medical record information is converted into an XML data structure to obtain XML format medical record data;

[0046] Converting XML format medical record data into HTML format medical record data based on XSLT technology;

[0047] Multiple PDF conversion tools are pre-selected, the data conversion performance of each tool is determined, and the preferred PDF conversion tool is determined based on the data conversion performance.

[0048] The preferred PDF conversion tool is used to generate PDF files from HTML format medical record data.

[0049] The PDF file is tested for data accuracy and integrity using an anomaly detection algorithm. The test results are then used to correct the data in the PDF file.

[0050] In this solution, the conversion of XML format medical record data into HTML format medical record data based on XSLT technology specifically involves:

[0051] Create an XSLT stylesheet, define a medical record template in the stylesheet, use XPath expressions to select nodes in the XML format medical record data, and map the nodes to HTML attributes;

[0052] The XSLT processor loads XML format medical record data and XSLT style sheets, and then passes the XML format medical record data and XSLT style sheets to the processor for conversion to obtain HTML format medical record data.

[0053] In this solution, the process of pre-selecting multiple PDF conversion tools, determining the data conversion performance of each tool, and then determining the preferred PDF conversion tool based on the data conversion performance is as follows:

[0054] Multiple PDF conversion tools are pre-selected, and a preset number of HTML format medical record data are prepared. The preset number of HTML format medical record data is imported into each PDF conversion tool for conversion to obtain test PDF format medical record data.

[0055] Get the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data;

[0056] A hash algorithm is introduced to calculate the hash values ​​of text data and image data in the preset number of HTML format medical record data and test PDF format medical record data, so as to obtain HTML format medical record hash data and PDF format medical record hash data.

[0057] The similarity data is obtained by comparing the HTML format medical record hash data with the PDF format medical record hash data;

[0058] The conversion accuracy of each PDF conversion tool for HTML format medical record data is calculated based on the similarity data.

[0059] The data conversion performance of each PDF conversion tool is evaluated based on the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data and the conversion accuracy of each PDF conversion tool for HTML format medical record data.

[0060] The preferred PDF conversion tool is determined based on the conversion performance.

[0061] In this solution, the step of generating a PDF file from the HTML format medical record data using the preferred PDF conversion tool specifically involves:

[0062] The HTML format medical record data is imported into the preferred PDF conversion tool. The HTML string in the HTML format medical record data is passed to an instance of the HTML class for conversion to obtain a PDF medical record file.

[0063] The preferred PDF conversion tool tracks data records during the PDF conversion process through its logs.

[0064] The integrity of the HTML format medical record data conversion is determined based on the data records. Based on the integrity, it is determined whether a re-conversion is needed, resulting in a secondary conversion evaluation plan.

[0065] This invention discloses a method and system for paperless generation and quality control of medical records based on markup language, aiming to improve the efficiency and accuracy of medical record information processing. First, image information from electronic medical records is acquired, medical record information is extracted, and converted into XML format data. Second, XSLT technology is used to convert the XML format data into HTML format data. Then, by pre-selecting PDF conversion tools and determining their performance, the optimal conversion tool is selected to generate a PDF file. Finally, an anomaly detection algorithm is used to verify the accuracy and integrity of the data in the PDF file, and the data is corrected based on the verification results. This invention achieves paperless processing and quality control of medical record information through markup language, improving the efficiency and accuracy of medical record management. Therefore, this invention has significant application value in the field of medical informatics. Attached Figure Description

[0066] Figure 1 A flowchart of a paperless medical record generation and quality control method based on markup language according to the present invention is shown;

[0067] Figure 2A flowchart illustrating the process of determining a preferred PDF conversion tool according to the present invention is shown;

[0068] Figure 3 This invention illustrates a flowchart of how to generate PDF files from HTML-formatted medical record data.

[0069] Figure 4 The diagram shows a block diagram of a paperless medical record generation and quality control system based on markup language according to the present invention. Detailed Implementation

[0070] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0071] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0072] Figure 1 The flowchart of a paperless medical record generation and quality control method based on markup language according to the present invention is shown.

[0073] like Figure 1 As shown, the first aspect of the present invention provides a method for paperless generation and quality control of medical records based on markup language, comprising:

[0074] S102, acquire image information of electronic medical records, extract medical record information from the image information, convert the medical record information into an XML data structure, and obtain XML format medical record data;

[0075] S104, Based on XSLT technology, convert XML format medical record data into HTML format medical record data;

[0076] S106: Pre-select multiple PDF conversion tools, determine the data conversion performance of each conversion tool, and determine the preferred PDF conversion tool based on the data conversion performance;

[0077] S108, Generate a PDF file from the HTML format medical record data using the preferred PDF conversion tool;

[0078] S110, The PDF file is subjected to data accuracy and integrity checks based on an anomaly detection algorithm to obtain the check results, and the PDF file is corrected according to the check results.

[0079] It should be noted that the process involves acquiring image information from electronic medical records, extracting the relevant information, and converting this information into an XML data structure to obtain XML-formatted medical record data. Next, XSLT technology is used to convert the XML data into HTML format for further processing. Then, multiple PDF conversion tools are pre-selected, and their data conversion performance is evaluated to determine the optimal tool, ensuring the efficiency and quality of the generated PDF file. Next, the selected PDF conversion tool is used to convert the HTML data into a PDF file. Finally, an anomaly detection algorithm is used to verify the accuracy and completeness of the generated PDF file. Based on the verification results, necessary data corrections are performed to ensure the accuracy and completeness of the generated electronic medical record data. This series of steps enables efficient extraction and conversion of medical record information, rapid generation of PDF files, and ensures the accuracy and completeness of the generated electronic medical record data through quality control measures, thereby achieving end-to-end management of paperless medical record processing.

[0080] According to an embodiment of the present invention, the steps of acquiring image information of paper medical records, extracting medical record information from the image information, and converting the medical record information into an XML data structure to obtain XML format medical record data are as follows:

[0081] Electronic medical records are obtained through the hospital information system, converted into digital images to obtain image information of the electronic medical records, and the image information is preprocessed, including noise removal, adjustment of image brightness and contrast;

[0082] The text content of the preprocessed image information is extracted using optical character recognition technology, and key information of the text content is identified based on natural language processing technology. The key information includes the patient's name, gender, age, medical history, and diagnosis result.

[0083] The disease image data is extracted from the image information using computer vision technology;

[0084] Based on the key information and medical image data, a preset XML data template is used to organize and arrange the key information and medical image data according to the preset XML data template to obtain medical record data in XML format;

[0085] Add notes and attributes to the XML format medical record data, construct a database, and store the XML format medical record data in the database.

[0086] It should be noted that by employing technologies such as image processing and optical character recognition, efficient extraction and organization of medical record data from electronic medical records to XML format medical record data have been achieved. This allows key information and patient image data to be stored in a structured manner in the database, providing a reliable foundation for subsequent paperless medical record processing. The XML format medical record data ensures data integrity and scalability, facilitating subsequent processing and analysis.

[0087] According to an embodiment of the present invention, the conversion of XML format medical record data into HTML format medical record data based on XSLT technology specifically includes:

[0088] Create an XSLT stylesheet, define a medical record template in the stylesheet, use XPath expressions to select nodes in the XML format medical record data, and map the nodes to HTML attributes;

[0089] The XSLT processor loads XML format medical record data and XSLT style sheets, and then passes the XML format medical record data and XSLT style sheets to the processor for conversion to obtain HTML format medical record data.

[0090] It should be noted that XSLT (eXtensible Stylesheet Language Transformations) technology is used. XSLT is an XML-based language used to transform XML documents. By writing XSLT stylesheets, XML data can be converted into HTML documents. This not only allows for the intuitive display of medical record information in web browsers, but also enables the use of CSS (Cascading Style Sheets) for aesthetically pleasing style design.

[0091] Figure 2 A flowchart illustrating the present invention for determining a preferred PDF conversion tool is shown.

[0092] According to an embodiment of the present invention, the process of pre-selecting multiple PDF conversion tools, determining the data conversion performance of each conversion tool, and determining the preferred PDF conversion tool based on the data conversion performance specifically involves:

[0093] S202: Pre-select multiple PDF conversion tools, prepare a preset number of HTML format medical record data, import the preset number of HTML format medical record data into each PDF conversion tool for conversion, and obtain test PDF format medical record data;

[0094] S204, Obtain the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data;

[0095] S206, A hash algorithm is introduced to calculate the hash values ​​of text data and image data in the preset number of HTML format medical record data and test PDF format medical record data, to obtain HTML format medical record hash data and PDF format medical record hash data;

[0096] S208, compare the HTML format medical record hash data with the PDF format medical record hash data to obtain similarity data;

[0097] S210, Calculate the conversion accuracy of each PDF conversion tool for HTML format medical record data based on the similarity data;

[0098] S212, evaluate the data conversion performance of each PDF conversion tool based on the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data and the conversion accuracy of each PDF conversion tool for HTML format medical record data;

[0099] S214, Determine the preferred PDF conversion tool based on the conversion performance.

[0100] It should be noted that a predetermined number of HTML format medical record data were prepared, and then this HTML format medical record data was imported into each PDF conversion tool for conversion to obtain corresponding test PDF format medical record data. Next, the average conversion time of each PDF conversion tool for the predetermined number of HTML format medical record data was obtained as an indicator of conversion efficiency. Then, a hash algorithm was introduced to calculate the hash values ​​of the text and image data in the predetermined number of HTML format medical record data and the corresponding test PDF format medical record data, obtaining the hash values ​​of the HTML format medical record data and the PDF format medical record data respectively. Subsequently, by comparing these hash values, the similarity data of the HTML format medical record data and the PDF format medical record data was obtained, thereby evaluating the conversion accuracy of each PDF conversion tool for the HTML format medical record data. Finally, based on the average conversion time and conversion accuracy of each PDF conversion tool for the HTML format medical record data, the data conversion performance of each conversion tool was evaluated. Taking into account both conversion efficiency and accuracy, the optimal PDF conversion tool was determined. This series of operations can evaluate the performance of different PDF conversion tools through quantitative indicators, providing a basis for selecting the most suitable tool and ensuring the efficiency and quality of the subsequently generated PDF files.

[0101] Figure 3 The flowchart illustrating the present invention generates PDF files from HTML format medical record data is shown.

[0102] According to an embodiment of the present invention, the step of generating a PDF file from HTML format medical record data using the preferred PDF conversion tool specifically includes:

[0103] S302, import the HTML format medical record data into the preferred PDF conversion tool, and obtain a PDF medical record file by passing the HTML string in the HTML format medical record data to an instance of the HTML class for conversion;

[0104] S304, Track data records during the PDF conversion process through the log records of the preferred PDF conversion tool;

[0105] S306, based on the data records, determine the integrity of the HTML format medical record data conversion, and based on the integrity, determine whether a re-conversion is needed to obtain a secondary conversion evaluation plan.

[0106] It should be noted that the integrity of the HTML format medical record data conversion is judged based on the data records. If problems are found in the conversion, a secondary conversion evaluation plan is formulated based on the records. The conversion needs to be repeated to ensure that the generated PDF file is complete and accurate. This ensures the effective conversion of HTML format medical record data into PDF files. The conversion process is monitored and feedback is provided through a quality control mechanism to ensure that the generated PDF file meets the expected quality standards.

[0107] According to an embodiment of the present invention, the step of performing data accuracy and integrity checks on the PDF file based on an anomaly detection algorithm, obtaining the check results, and then performing data correction on the PDF file based on the check results specifically involves:

[0108] The text data in the PDF file and HTML format medical record data is identified using natural language processing methods to obtain PDF text data and HTML text data;

[0109] The accuracy of the PDF file's data is determined by comparing the PDF text data with the HTML text data.

[0110] The structural integrity of the table data in the PDF file is checked by the structural data inspection method. The integrity of the rows and columns and the accuracy of the data format are judged to obtain the table inspection results.

[0111] The sharpness of the image data in the PDF file is detected by an image data inspection method, and the image inspection results are obtained.

[0112] Preset the weighting of data accuracy, table inspection results, and image inspection results in the PDF file to the quality of the PDF file;

[0113] The quality of the PDF file is assessed based on the weighted data and the data accuracy, table inspection results, and image inspection results of the PDF file, and an evaluation score is obtained.

[0114] If the evaluation score is lower than the preset value, the PDF file will be marked as a file requiring data correction.

[0115] The data to be corrected is compared with the HTML format medical record data. Outliers in the data to be corrected are marked, and the marked data is manually corrected.

[0116] It should be noted that, through natural language processing methods, text data in PDF and HTML format medical record data is accurately identified and extracted, forming a comparable dataset. Secondly, structural data verification methods are applied to the tabular data in the PDF files to ensure the integrity of rows and columns and the accuracy of data format, guaranteeing the reliability of the tabular data. Simultaneously, image data verification methods are used to evaluate the image clarity in the PDF files, further ensuring the quality of image data. These verification results are comprehensively evaluated using preset weighted data to form an overall quality score for the PDF files. If the score is lower than a preset value, the PDF file is marked as requiring data correction. Files marked as requiring data correction are further compared with HTML format medical record data; outliers are identified and marked. Subsequently, through manual correction, these outliers are corrected to ensure the accuracy of the data in the PDF files. By effectively utilizing technologies such as natural language processing, structural data verification, and image data verification, comprehensive monitoring and correction of PDF file quality is achieved. Through a combination of automated and manual correction, the high quality and integrity of electronic medical record data are ensured.

[0117] According to an embodiment of the present invention, it further includes:

[0118] Obtain a predetermined number of PDF medical record files from the target hospital area, and perform data cleaning and data standardization processing on the PDF medical record files;

[0119] Medical record information is extracted from PDF medical record files after data cleaning and standardization. The medical record information includes patient name, age, gender, medical history, and diagnosis results.

[0120] Identify entities in medical record information based on natural language processing technology; the entities include diseases, symptoms, and medications.

[0121] The relationships between the entities are evaluated to obtain relationship data;

[0122] A knowledge graph is constructed based on the entities and the relationship data, with the entities as nodes of the knowledge graph and the relationship data as edges between the nodes, to obtain a case knowledge graph;

[0123] Obtain the PDF medical record data of the currently visiting patient and extract entities from the PDF medical record data of the currently visiting patient;

[0124] Based on knowledge graph technology, entities in the PDF medical record data of the current patient are compared and analyzed with the case knowledge graph to find similar data of the current patient's condition to other patients in the case knowledge graph;

[0125] Based on the similar data, treatment plans, medication selections, and examination suggestions are recommended to obtain an auxiliary consultation plan.

[0126] It should be noted that the acquired PDF medical record files undergo data cleaning and standardization, including removing duplicate data, unifying the format, and handling missing values, to ensure data quality and consistency. Text mining and natural language processing techniques are used to extract relationships between entities from the medical record information, such as the relationship between illness and medication, and the relationship between symptoms and diseases. These relationships are then evaluated and confirmed, forming connections between nodes in a knowledge graph. Using the identified entities as nodes and the relationship data as edges, a case knowledge graph is constructed. This step, by organizing case information into a graph format, forms a structured medical knowledge base. The PDF medical record data of the current patients... The system extracts entities for matching and comparative analysis to find data similar to other patients' conditions, including similar diseases, symptoms, and medications. Based on the matched similar data and existing medical knowledge, it uses reasoning and decision-making algorithms to generate auxiliary consultation plans, including treatment suggestions, drug selection, and examination recommendations, providing doctors with personalized diagnostic and treatment references. This constructs an auxiliary consultation system based on a medical knowledge graph, enabling doctors to make diagnostic and treatment decisions more quickly and accurately, improving the quality and efficiency of medical services. The natural language processing technologies include named entity recognition and relation extraction; the relation data includes diagnostic relations, treatment relations, and symptom relations.

[0127] Figure 4 The diagram shows a block diagram of a paperless medical record generation and quality control system based on markup language according to the present invention.

[0128] A second aspect of the present invention also provides a paperless medical record generation and quality control system 4 based on markup language. The system includes a memory 41 and a processor 42. The memory includes a program for a paperless medical record generation and quality control method based on markup language. When the processor executes the program, the program performs the following steps:

[0129] The image information of the electronic medical record is acquired, the medical record information is extracted from the image information, and the medical record information is converted into an XML data structure to obtain XML format medical record data;

[0130] Converting XML format medical record data into HTML format medical record data based on XSLT technology;

[0131] Multiple PDF conversion tools are pre-selected, the data conversion performance of each tool is determined, and the preferred PDF conversion tool is determined based on the data conversion performance.

[0132] The preferred PDF conversion tool is used to generate PDF files from HTML format medical record data.

[0133] The PDF file is tested for data accuracy and integrity using an anomaly detection algorithm. The test results are then used to correct the data in the PDF file.

[0134] It should be noted that the process involves acquiring image information from electronic medical records, extracting the relevant information, and converting this information into an XML data structure to obtain XML-formatted medical record data. Next, XSLT technology is used to convert the XML data into HTML format for further processing. Then, multiple PDF conversion tools are pre-selected, and their data conversion performance is evaluated to determine the optimal tool, ensuring the efficiency and quality of the generated PDF file. Next, the selected PDF conversion tool is used to convert the HTML data into a PDF file. Finally, an anomaly detection algorithm is used to verify the accuracy and completeness of the generated PDF file. Based on the verification results, necessary data corrections are performed to ensure the accuracy and completeness of the generated electronic medical record data. This series of steps enables efficient extraction and conversion of medical record information, rapid generation of PDF files, and ensures the accuracy and completeness of the generated electronic medical record data through quality control measures, thereby achieving end-to-end management of paperless medical record processing.

[0135] According to an embodiment of the present invention, the steps of acquiring image information of paper medical records, extracting medical record information from the image information, and converting the medical record information into an XML data structure to obtain XML format medical record data are as follows:

[0136] Electronic medical records are obtained through the hospital information system, converted into digital images to obtain image information of the electronic medical records, and the image information is preprocessed, including noise removal, adjustment of image brightness and contrast;

[0137] The text content of the preprocessed image information is extracted using optical character recognition technology, and key information of the text content is identified based on natural language processing technology. The key information includes the patient's name, gender, age, medical history, and diagnosis result.

[0138] The disease image data is extracted from the image information using computer vision technology;

[0139] Based on the key information and medical image data, a preset XML data template is used to organize and arrange the key information and medical image data according to the preset XML data template to obtain medical record data in XML format;

[0140] Add notes and attributes to the XML format medical record data, construct a database, and store the XML format medical record data in the database.

[0141] It should be noted that by employing technologies such as image processing and optical character recognition, efficient extraction and organization of medical record data from electronic medical records to XML format medical record data have been achieved. This allows key information and patient image data to be stored in a structured manner in the database, providing a reliable foundation for subsequent paperless medical record processing. The XML format medical record data ensures data integrity and scalability, facilitating subsequent processing and analysis.

[0142] According to an embodiment of the present invention, the conversion of XML format medical record data into HTML format medical record data based on XSLT technology specifically includes:

[0143] Create an XSLT stylesheet, define a medical record template in the stylesheet, use XPath expressions to select nodes in the XML format medical record data, and map the nodes to HTML attributes;

[0144] The XSLT processor loads XML format medical record data and XSLT style sheets, and then passes the XML format medical record data and XSLT style sheets to the processor for conversion to obtain HTML format medical record data.

[0145] It should be noted that XSLT (eXtensible Stylesheet Language Transformations) technology is used. XSLT is an XML-based language used to transform XML documents. By writing XSLT stylesheets, XML data can be converted into HTML documents. This not only allows for the intuitive display of medical record information in web browsers, but also enables the use of CSS (Cascading Style Sheets) for aesthetically pleasing style design.

[0146] According to an embodiment of the present invention, the process of pre-selecting multiple PDF conversion tools, determining the data conversion performance of each conversion tool, and determining the preferred PDF conversion tool based on the data conversion performance specifically involves:

[0147] Multiple PDF conversion tools are pre-selected, and a preset number of HTML format medical record data are prepared. The preset number of HTML format medical record data is imported into each PDF conversion tool for conversion to obtain test PDF format medical record data.

[0148] Get the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data;

[0149] A hash algorithm is introduced to calculate the hash values ​​of text data and image data in the preset number of HTML format medical record data and test PDF format medical record data, so as to obtain HTML format medical record hash data and PDF format medical record hash data.

[0150] The similarity data is obtained by comparing the HTML format medical record hash data with the PDF format medical record hash data;

[0151] The conversion accuracy of each PDF conversion tool for HTML format medical record data is calculated based on the similarity data.

[0152] The data conversion performance of each PDF conversion tool is evaluated based on the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data and the conversion accuracy of each PDF conversion tool for HTML format medical record data.

[0153] The preferred PDF conversion tool is determined based on the conversion performance.

[0154] It should be noted that a predetermined number of HTML format medical record data were prepared, and then this HTML format medical record data was imported into each PDF conversion tool for conversion to obtain corresponding test PDF format medical record data. Next, the average conversion time of each PDF conversion tool for the predetermined number of HTML format medical record data was obtained as an indicator of conversion efficiency. Then, a hash algorithm was introduced to calculate the hash values ​​of the text and image data in the predetermined number of HTML format medical record data and the corresponding test PDF format medical record data, obtaining the hash values ​​of the HTML format medical record data and the PDF format medical record data respectively. Subsequently, by comparing these hash values, the similarity data of the HTML format medical record data and the PDF format medical record data was obtained, thereby evaluating the conversion accuracy of each PDF conversion tool for the HTML format medical record data. Finally, based on the average conversion time and conversion accuracy of each PDF conversion tool for the HTML format medical record data, the data conversion performance of each conversion tool was evaluated. Taking into account both conversion efficiency and accuracy, the optimal PDF conversion tool was determined. This series of operations can evaluate the performance of different PDF conversion tools through quantitative indicators, providing a basis for selecting the most suitable tool and ensuring the efficiency and quality of the subsequently generated PDF files.

[0155] According to an embodiment of the present invention, the step of generating a PDF file from HTML format medical record data using the preferred PDF conversion tool specifically includes:

[0156] The HTML format medical record data is imported into the preferred PDF conversion tool. The HTML string in the HTML format medical record data is passed to an instance of the HTML class for conversion to obtain a PDF medical record file.

[0157] The preferred PDF conversion tool tracks data records during the PDF conversion process through its logs.

[0158] The integrity of the HTML format medical record data conversion is determined based on the data records. Based on the integrity, it is determined whether a re-conversion is needed, resulting in a secondary conversion evaluation plan.

[0159] It should be noted that the integrity of the HTML format medical record data conversion is judged based on the data records. If problems are found in the conversion, a secondary conversion evaluation plan is formulated based on the records. The conversion needs to be repeated to ensure that the generated PDF file is complete and accurate. This ensures the effective conversion of HTML format medical record data into PDF files. The conversion process is monitored and feedback is provided through a quality control mechanism to ensure that the generated PDF file meets the expected quality standards.

[0160] According to an embodiment of the present invention, the step of performing data accuracy and integrity checks on the PDF file based on an anomaly detection algorithm, obtaining the check results, and then performing data correction on the PDF file based on the check results specifically involves:

[0161] The text data in the PDF file and HTML format medical record data is identified using natural language processing methods to obtain PDF text data and HTML text data;

[0162] The accuracy of the PDF file's data is determined by comparing the PDF text data with the HTML text data.

[0163] The structural integrity of the table data in the PDF file is checked by the structural data inspection method. The integrity of the rows and columns and the accuracy of the data format are judged to obtain the table inspection results.

[0164] The sharpness of the image data in the PDF file is detected by an image data inspection method, and the image inspection results are obtained.

[0165] Preset the weighting of data accuracy, table inspection results, and image inspection results in the PDF file to the quality of the PDF file;

[0166] The quality of the PDF file is assessed based on the weighted data and the data accuracy, table inspection results, and image inspection results of the PDF file, and an evaluation score is obtained.

[0167] If the evaluation score is lower than the preset value, the PDF file will be marked as a file requiring data correction.

[0168] The data to be corrected is compared with the HTML format medical record data. Outliers in the data to be corrected are marked, and the marked data is manually corrected.

[0169] It should be noted that, through natural language processing methods, text data in PDF and HTML format medical record data is accurately identified and extracted, forming a comparable dataset. Secondly, structural data verification methods are applied to the tabular data in the PDF files to ensure the integrity of rows and columns and the accuracy of data format, guaranteeing the reliability of the tabular data. Simultaneously, image data verification methods are used to evaluate the image clarity in the PDF files, further ensuring the quality of image data. These verification results are comprehensively evaluated using preset weighted data to form an overall quality score for the PDF files. If the score is lower than a preset value, the PDF file is marked as requiring data correction. Files marked as requiring data correction are further compared with HTML format medical record data; outliers are identified and marked. Subsequently, through manual correction, these outliers are corrected to ensure the accuracy of the data in the PDF files. By effectively utilizing technologies such as natural language processing, structural data verification, and image data verification, comprehensive monitoring and correction of PDF file quality is achieved. Through a combination of automated and manual correction, the high quality and integrity of electronic medical record data are ensured.

[0170] According to an embodiment of the present invention, it further includes:

[0171] Obtain a predetermined number of PDF medical record files from the target hospital area, and perform data cleaning and data standardization processing on the PDF medical record files;

[0172] Medical record information is extracted from PDF medical record files after data cleaning and standardization. The medical record information includes patient name, age, gender, medical history, and diagnosis results.

[0173] Identify entities in medical record information based on natural language processing technology; the entities include diseases, symptoms, and medications.

[0174] The relationships between the entities are evaluated to obtain relationship data;

[0175] A knowledge graph is constructed based on the entities and the relationship data, with the entities as nodes of the knowledge graph and the relationship data as edges between the nodes, to obtain a case knowledge graph;

[0176] Obtain the PDF medical record data of the currently visiting patient and extract entities from the PDF medical record data of the currently visiting patient;

[0177] Based on knowledge graph technology, entities in the PDF medical record data of the current patient are compared and analyzed with the case knowledge graph to find similar data of the current patient's condition to other patients in the case knowledge graph;

[0178] Based on the similar data, treatment plans, medication selections, and examination suggestions are recommended to obtain an auxiliary consultation plan.

[0179] It should be noted that the acquired PDF medical record files undergo data cleaning and standardization, including removing duplicate data, unifying the format, and handling missing values, to ensure data quality and consistency. Text mining and natural language processing techniques are used to extract relationships between entities from the medical record information, such as the relationship between illness and medication, and the relationship between symptoms and diseases. These relationships are then evaluated and confirmed, forming connections between nodes in a knowledge graph. Using the identified entities as nodes and the relationship data as edges, a case knowledge graph is constructed. This step, by organizing case information into a graph format, forms a structured medical knowledge base. The PDF medical record data of the current patients... The system extracts entities for matching and comparative analysis to find data similar to other patients' conditions, including similar diseases, symptoms, and medications. Based on the matched similar data and existing medical knowledge, it uses reasoning and decision-making algorithms to generate auxiliary consultation plans, including treatment suggestions, drug selection, and examination recommendations, providing doctors with personalized diagnostic and treatment references. This constructs an auxiliary consultation system based on a medical knowledge graph, enabling doctors to make diagnostic and treatment decisions more quickly and accurately, improving the quality and efficiency of medical services. The natural language processing technologies include named entity recognition and relation extraction; the relation data includes diagnostic relations, treatment relations, and symptom relations.

[0180] This invention discloses a method and system for paperless generation and quality control of medical records based on markup language, aiming to improve the efficiency and accuracy of medical record information processing. First, image information from electronic medical records is acquired, medical record information is extracted, and converted into XML format data. Second, XSLT technology is used to convert the XML format data into HTML format data. Then, by pre-selecting PDF conversion tools and determining their performance, the optimal conversion tool is selected to generate a PDF file. Finally, an anomaly detection algorithm is used to verify the accuracy and integrity of the data in the PDF file, and the data is corrected based on the verification results. This invention achieves paperless processing and quality control of medical record information through markup language, improving the efficiency and accuracy of medical record management. Therefore, this invention has significant application value in the field of medical informatics.

[0181] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0182] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0183] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0184] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0185] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, 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 methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0186] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for paperless generation and quality control of medical records based on markup language, characterized in that, Includes the following steps: The image information of the electronic medical record is acquired, the medical record information is extracted from the image information, and the medical record information is converted into an XML data structure to obtain XML format medical record data; Converting XML format medical record data into HTML format medical record data based on XSLT technology; Multiple PDF conversion tools are pre-selected, the data conversion performance of each tool is determined, and the preferred PDF conversion tool is determined based on the data conversion performance. The preferred PDF conversion tool is used to generate PDF files from HTML format medical record data. The PDF file is tested for data accuracy and integrity using an anomaly detection algorithm. The test results are then used to correct the data in the PDF file.

2. The method for paperless generation and quality control of medical records based on markup language according to claim 1, characterized in that, The process of acquiring image information from electronic medical records, extracting medical record information from the image information, and converting the medical record information into an XML data structure to obtain XML format medical record data is as follows: Electronic medical records are obtained through the hospital information system, converted into digital images to obtain image information of the electronic medical records, and the image information is preprocessed, including noise removal, adjustment of image brightness and contrast; The text content of the preprocessed image information is extracted using optical character recognition technology, and key information of the text content is identified based on natural language processing technology. The key information includes the patient's name, gender, age, medical history, and diagnosis result. The disease image data is extracted from the image information using computer vision technology; Based on the key information and medical image data, a preset XML data template is used to organize and arrange the key information and medical image data according to the preset XML data template to obtain medical record data in XML format; Add notes and attributes to the XML format medical record data, construct a database, and store the XML format medical record data in the database.

3. The method for paperless generation and quality control of medical records based on markup language according to claim 1, characterized in that, The conversion of XML format medical record data into HTML format medical record data based on XSLT technology specifically involves: Create an XSLT stylesheet, define a medical record template in the stylesheet, use XPath expressions to select nodes in the XML format medical record data, and map the nodes to HTML attributes; The XSLT processor loads XML format medical record data and XSLT style sheets, and then passes the XML format medical record data and XSLT style sheets to the processor for conversion to obtain HTML format medical record data.

4. The method for paperless generation and quality control of medical records based on markup language according to claim 1, characterized in that, The process involves pre-selecting multiple PDF conversion tools, determining the data conversion performance of each tool, and then determining the preferred PDF conversion tool based on the data conversion performance. Specifically: Multiple PDF conversion tools are pre-selected, and a preset number of HTML format medical record data are prepared. The preset number of HTML format medical record data is imported into each PDF conversion tool for conversion to obtain test PDF format medical record data. Get the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data; A hash algorithm is introduced to calculate the hash values ​​of text data and image data in the preset number of HTML format medical record data and test PDF format medical record data, so as to obtain HTML format medical record hash data and PDF format medical record hash data. The similarity data is obtained by comparing the HTML format medical record hash data with the PDF format medical record hash data; The conversion accuracy of each PDF conversion tool for HTML format medical record data is calculated based on the similarity data. The data conversion performance of each PDF conversion tool is evaluated based on the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data and the conversion accuracy of each PDF conversion tool for HTML format medical record data. The preferred PDF conversion tool is determined based on the conversion performance.

5. The method for paperless generation and quality control of medical records based on markup language according to claim 1, characterized in that, The step of generating PDF files from HTML-formatted medical record data using the preferred PDF conversion tool specifically involves: The HTML format medical record data is imported into the preferred PDF conversion tool. The HTML string in the HTML format medical record data is passed to an instance of the HTML class for conversion to obtain a PDF medical record file. The preferred PDF conversion tool tracks data records during the PDF conversion process through its logs. The integrity of the HTML format medical record data conversion is determined based on the data records. Based on the integrity, it is determined whether a re-conversion is needed, resulting in a secondary conversion evaluation plan.

6. The method for paperless generation and quality control of medical records based on markup language according to claim 1, characterized in that, The method involves performing data accuracy and integrity checks on the PDF file based on an anomaly detection algorithm, obtaining the check results, and then correcting the data in the PDF file according to the check results. Specifically: The text data in the PDF file and HTML format medical record data is identified using natural language processing methods to obtain PDF text data and HTML text data; The accuracy of the PDF file's data is determined by comparing the PDF text data with the HTML text data. The structural integrity of the table data in the PDF file is checked by the structural data inspection method. The integrity of the rows and columns and the accuracy of the data format are judged to obtain the table inspection results. The sharpness of the image data in the PDF file is detected by an image data inspection method, and the image inspection results are obtained. Preset the weighting of data accuracy, table inspection results, and image inspection results in the PDF file to the quality of the PDF file; The quality of the PDF file is assessed based on the weighted data and the data accuracy, table inspection results, and image inspection results of the PDF file, and an evaluation score is obtained. If the evaluation score is lower than the preset value, the PDF file will be marked as a file requiring data correction. The data to be corrected is compared with the HTML format medical record data. Outliers in the data to be corrected are marked, and the marked data is manually corrected.

7. A paperless medical record generation and quality control system based on markup language, characterized in that, The markup language-based paperless medical record generation and quality control system includes a storage device and a processor. The storage device includes a markup language-based paperless medical record generation and quality control method program. When the markup language-based paperless medical record generation and quality control method program is executed by the processor, the following steps are implemented: The image information of the electronic medical record is acquired, the medical record information is extracted from the image information, and the medical record information is converted into an XML data structure to obtain XML format medical record data; Converting XML format medical record data into HTML format medical record data based on XSLT technology; Multiple PDF conversion tools are pre-selected, the data conversion performance of each tool is determined, and the preferred PDF conversion tool is determined based on the data conversion performance. The preferred PDF conversion tool is used to generate PDF files from HTML format medical record data. The PDF file is tested for data accuracy and integrity using an anomaly detection algorithm. The test results are then used to correct the data in the PDF file.

8. The paperless medical record generation and quality control system based on markup language according to claim 7, characterized in that, The conversion of XML format medical record data into HTML format medical record data based on XSLT technology specifically involves: Create an XSLT stylesheet, define a medical record template in the stylesheet, use XPath expressions to select nodes in the XML format medical record data, and map the nodes to HTML attributes; The XSLT processor loads XML format medical record data and XSLT style sheets, and then passes the XML format medical record data and XSLT style sheets to the processor for conversion to obtain HTML format medical record data.

9. A paperless medical record generation and quality control system based on markup language according to claim 7, characterized in that, The process involves pre-selecting multiple PDF conversion tools, determining the data conversion performance of each tool, and then determining the preferred PDF conversion tool based on the data conversion performance. Specifically: Multiple PDF conversion tools are pre-selected, and a preset number of HTML format medical record data are prepared. The preset number of HTML format medical record data is imported into each PDF conversion tool for conversion to obtain test PDF format medical record data. Get the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data; A hash algorithm is introduced to calculate the hash values ​​of text data and image data in the preset number of HTML format medical record data and test PDF format medical record data, so as to obtain HTML format medical record hash data and PDF format medical record hash data. The similarity data is obtained by comparing the HTML format medical record hash data with the PDF format medical record hash data; The conversion accuracy of each PDF conversion tool for HTML format medical record data is calculated based on the similarity data. The data conversion performance of each PDF conversion tool is evaluated based on the average conversion time of each PDF conversion tool for a preset number of HTML format medical record data and the conversion accuracy of each PDF conversion tool for HTML format medical record data. The preferred PDF conversion tool is determined based on the conversion performance.

10. A paperless medical record generation and quality control system based on markup language according to claim 7, characterized in that, The step of generating PDF files from HTML-formatted medical record data using the preferred PDF conversion tool specifically involves: The HTML format medical record data is imported into the preferred PDF conversion tool. The HTML string in the HTML format medical record data is passed to an instance of the HTML class for conversion to obtain a PDF medical record file. The preferred PDF conversion tool tracks data records during the PDF conversion process through its logs. The integrity of the HTML format medical record data conversion is determined based on the data records. Based on the integrity, it is determined whether a re-conversion is needed, resulting in a secondary conversion evaluation plan.

Images