An operating room record generation method and system

Abstract

The application relates to the technical field of data processing, and particularly discloses a kind of operating room record generation method and system, its method includes: real-time collection patient's vital sign data, surgical equipment operation data, audio and video recording data in operating room;Patient's vital sign data, surgical equipment operation data, audio and video recording data in operating room are timestamped and corrected, and the complete record data of patient's surgery is obtained;Based on the electronic medical record of patient and big data analysis method, the key item category of patient's surgery record is analyzed, and the key record data of operating room is extracted in the complete record data of patient's surgery based on the key item category of patient's surgery record;Based on pre-defined rules and logic, the key record data of operating room is integrated, and the operating room record report is generated in combination with the electronic medical record of patient;The efficiency and quality of operating room record generation are improved, and the overall efficiency and quality of medical work are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a method and system for generating operating room records. BACKGROUND

[0002] Currently, with the rapid development of medical informatization, the operating room record generation technology has become a key link to improve the quality and efficiency of surgery. Traditional methods rely on manual entry or single device data integration, but with the breakthrough of multi-modal data acquisition technology (such as vital sign monitors, surgical robots, 4K audio-video recording devices, etc.), the industry is accelerating the transformation towards intelligent and automated direction. Currently, the operating room record generation technology has become a research hotspot, and its core lies in the fusion of multi-source data (vital signs, device parameters, audio-video, etc.), through time-space alignment, semantic analysis and machine learning algorithms, to realize panoramic recording and intelligent analysis of the surgical process. This technology provides important support for surgical quality assessment and scientific research data mining.

[0003] However, current operating room record generation mainly relies on manual entry or single device data integration. In traditional methods, medical staff need to manually record the surgical process through paper forms or electronic documents, which is time-consuming and prone to missing critical information. Some hospitals use electronic health record (EHR) systems to integrate single type data such as vital signs, but cannot integrate multi-modal information such as surgical device parameters, audio-video recordings. Vital signs, device parameters, audio-video recordings are stored separately, lack a unified time reference, and machine learning models have difficulty dynamically correlating time series data, resulting in poor data correlation (such as blood pressure drop misaligned with instrument operation time). A few automated tools attempt to extract information through rule engines or simple machine learning, but are limited by data alignment accuracy and semantic understanding ability, making it difficult to meet clinical needs. This results in the need for manual annotation of surgical type, complications and other core fields, which is time-consuming and prone to missing important details.

[0004] Therefore, the present application proposes a method and system for generating operating room records. SUMMARY

[0005] The application provides a method and system for generating operating room records, which comprises: collecting patient vital sign data, operating equipment operation data, and audio and video recording data in the operating room in real time, comprehensively covering key information in the operation process and laying a foundation for subsequent accurate generation of operating room records. These multi-dimensional data can reflect the actual situation of the operation from different angles, ensuring the completeness and accuracy of the records. Secondly, timestamp alignment and correction are performed on various data to obtain complete operation record data, so that data from different sources are accurately matched in the time dimension. This helps to clearly present the sequence and synchronization of each link in the operation, avoids understanding deviation of the operation process due to time disorder, and improves the logicality and readability of the records. According to the patient electronic medical record and the big data analysis method, the key item category of the operation record is determined, and the key record data in the operating room is extracted from the key item category to realize accurate screening of massive data. Focusing on key information can highlight the key points and reduce unnecessary data interference, making the records more targeted and convenient for medical staff to quickly obtain key content. Then, the key record data in the operating room is integrated based on predefined rules and logic, and the operating room record report is generated in combination with the electronic medical record, ensuring the standardization and scientificity of the report generation. The predefined rules ensure that the data integration is orderly and meets the medical professional logic, and the combination with the electronic medical record further enriches the report content, providing comprehensive and accurate information for operation summary, subsequent treatment, and medical research. Finally, the method improves the efficiency and quality of the generation of operating room records, reduces the workload of manual sorting and recording through an automatic data processing process, reduces the risk of human error, improves the overall efficiency and quality of medical work, and helps the development of medical decision-making and research.

[0006] The application provides a method for generating operating room records, comprising:

[0007] S1: collecting patient vital sign data, operating equipment operation data, and audio and video recording data in the operating room in real time;

[0008] S2: performing timestamp alignment and correction on the patient vital sign data, the operating equipment operation data, and the audio and video recording data in the operating room to obtain complete operation record data of the patient;

[0009] S3: analyzing the key item category of the operation record of the patient based on the electronic medical record of the patient and the big data analysis method, and extracting the key record data in the operating room from the key item category of the operation record of the patient in the complete operation record data of the patient;

[0010] S4: integrating the key record data in the operating room based on predefined rules and logic, and generating an operating room record report in combination with the electronic medical record of the patient.

[0011] Preferably, S1: collecting patient vital sign data, operating equipment operation data, and audio and video recording data in the operating room in real time, comprises:

[0012] Multiple vital sign monitors are used to collect patients' vital sign data in real time;

[0013] Real-time collection of operating parameters and operational status data of all surgical equipment in the operating room as surgical equipment operation data;

[0014] The audio and video data of the operation is recorded by cameras and microphones installed in the operating room to monitor the operation and the patients.

[0015] Preferably, S2: The patient's vital signs data, surgical equipment operation data, and audio / video recordings in the operating room are timestamped and corrected to obtain complete surgical record data for the patient, including:

[0016] The patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room are time-stamped and aligned to obtain multi-source aligned recording data of the operating room;

[0017] Identify all data gap periods for each type of record data in the multi-source aligned record data of the operating room, and take the partial record data of all types of record data except for a single type of record data in the multi-source aligned record data of the operating room in each data gap period of the current type of record data as the multi-source reference record data of the corresponding type of record data in the corresponding data gap period;

[0018] Based on the multi-source reference record data and adjacent time period reference record data for each type of record data in each data gap period, the gap data of each type of record data is filled to obtain the complete record data of each type of record data, and the multi-source aligned complete record data of the operating room is obtained.

[0019] Horizontal and vertical corrections were performed on each segment of differentially aligned record data in the multi-source aligned complete record data of the operating room to obtain the patient's complete surgical record data.

[0020] Preferably, the patient's vital signs data, surgical equipment operation data, and audio / video recordings in the operating room are time-stamped and aligned to obtain multi-source aligned recording data of the operating room, including:

[0021] Data cleaning is performed on the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain clean vital signs data, clean surgical equipment operation data, and clean audio and video recording data in the operating room.

[0022] By aligning the timestamps of the patient's pure vital signs data, pure surgical equipment operation data, and pure audio and video recording data in the operating room, multi-source aligned recording data of the operating room is obtained.

[0023] Preferably, based on multi-source reference record data and adjacent time-period reference record data for each type of record data in each data gap period, gap data filling is performed on each type of record data to obtain complete record data for each type of record data, and multi-source aligned complete record data of the operating room is obtained, including:

[0024] The missing reference value of multi-source reference record data for each type of record data in each data gap period is calculated, and the missing reference value of reference record data in adjacent periods for each type of record data in each data gap period is also calculated.

[0025] For each type of record data, all reference record data exceeding the fill-in reference threshold during each data gap period are used as fill-in reference data for each type of record data during each data gap period.

[0026] Based on the reference data for filling gaps in each data gap period for each type of record data and the preset gap data filling model for each type of record data, gap data filling is performed for each type of record data to obtain the complete record data for each type of record data;

[0027] All types of record data are re-timestamped to obtain multi-source aligned complete record data of the operating room.

[0028] Preferably, horizontal and vertical corrections are performed on each segment of differentially aligned record data in the multi-source aligned complete record data of the operating room to obtain the patient's complete surgical record data, including:

[0029] The multi-source aligned complete record data of the operating room is divided into time periods to obtain multi-segment aligned record data;

[0030] Calculate the information alignment degree of each segment of the alignment record data;

[0031] From all the segment alignment record data, select all segment alignment record data with an information alignment degree greater than the information alignment degree threshold as all segment differential sub-alignment record data;

[0032] Based on the preset horizontal and vertical correction model, all segment differential sub-aligned record data are corrected horizontally and vertically to obtain the patient's complete surgical record data.

[0033] Preferably, the operating room record generation system according to any of the above operating room record generation methods includes:

[0034] The multi-source data collection module is used to collect patients' vital signs data, surgical equipment operation data, and audio and video recording data in the operating room in real time.

[0035] The alignment and correction module is used to align and correct the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain the patient's complete surgical record data.

[0036] The key record extraction module is used to analyze the key items of the patient's surgical record based on the patient's electronic medical record and big data analysis, and to extract the key operating room record data from the patient's complete surgical record data based on the key items of the patient's surgical record.

[0037] The data estimation and integration module is used to integrate key operating room record data based on predefined rules and logic, and generate operating room record reports by combining the patient's electronic medical record.

[0038] The beneficial effects of this invention compared to existing technologies are as follows: It collects patient vital signs data, surgical equipment operation data, and audio-visual recordings from the operating room in real time, comprehensively covering key information during the surgical process and laying the foundation for accurate subsequent generation of operating room records. This multi-dimensional data reflects the actual surgical situation from different perspectives, ensuring the completeness and accuracy of the record. Secondly, it aligns and corrects the timestamps of various data to obtain complete surgical record data, ensuring precise matching of data from different sources in the time dimension. This helps to clearly present the sequence and synchronization of each stage of the surgery, avoiding misunderstandings of the surgical process due to time discrepancies, and improving the logic and readability of the record. Based on the patient's electronic medical record and big data analysis, key categories of surgical records are determined, and key operating room record data is extracted from them, achieving precise screening of massive amounts of data. Focusing on key information highlights the important points while reducing unnecessary data interference, making the record more targeted and facilitating quick access to key content for medical staff. Then, based on predefined rules and logic, the key operating room record data is integrated and combined with the electronic medical record to generate an operating room record report, ensuring the standardization and scientific nature of the report generation. Predefined rules ensure that data integration is organized and conforms to medical professional logic. Combined with electronic medical records, this further enriches the report content, providing comprehensive and accurate information for surgical summaries, subsequent treatment, and medical research. Finally, this method improves the efficiency and quality of operating room record generation. Through automated data processing, it reduces the workload of manual data organization and recording, lowers the risk of human error, and enhances the overall efficiency and quality of medical work, thus supporting medical decision-making and research. This invention, combined with the characteristics of artificial intelligence technology, focuses on major public needs such as healthcare, and is conducive to forming significant application scenarios with strong demonstration effects, large influence, and wide-ranging impact, providing support for promoting medical-engineering integration and scientific research.

[0039] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0040] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0041] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0042] Figure 1 This is a flowchart of an operating room record generation method according to an embodiment of the present invention. Detailed Implementation

[0043] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0044] Example 1: This invention provides a method for generating operating room records, referencing... Figure 1 ,include:

[0045] S1: Real-time collection of patient vital signs data, surgical equipment operation data, and audio and video recording data in the operating room;

[0046] S2: Time-stamp align and correct the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain the patient's complete surgical record data;

[0047] S3: Based on the patient's electronic medical record and big data analysis, the key categories of the patient's surgical record are analyzed, and the key operating room record data is extracted from the patient's complete surgical record data based on the key categories of the patient's surgical record.

[0048] S4: Integrate key operating room record data based on predefined rules and logic, and generate operating room record reports by combining them with the patient's electronic medical record.

[0049] In this embodiment, the patient's vital signs data refers to the data obtained by monitoring various basic physiological indicators of the patient's body during the operation, such as heart rate, blood pressure, blood oxygen saturation, and body temperature.

[0050] In this embodiment, the surgical equipment operation data refers to the data generated by various surgical devices during the operation of the surgery, covering the device's operating parameters, status information, etc., such as the frequency of use of surgical instruments, energy output intensity, and gas flow rate and concentration of anesthesia equipment.

[0051] In this embodiment, the audio and video recording data in the operating room is obtained by recording the entire surgical process using audio and video equipment installed in the operating room. It comprehensively records the surgical scene, the operations of medical staff, and their conversations, providing intuitive evidence for subsequent review and analysis of the surgical procedure. For example, if there are questions about a particular step in the surgery, the audio and video recording data can be reviewed to clarify the situation.

[0052] In this embodiment, the patient's complete surgical record data integrates various aspects of the patient's information during the surgical process, including vital signs data, surgical equipment operation data, audio and video recording data, and may also include medical staff's operation records, medication records, etc.

[0053] In this embodiment, key categories of the patient's surgical record are analyzed based on the patient's electronic medical record and big data analytics. This involves leveraging the patient's existing electronic medical record information and combining it with big data analytics to mine and summarize key information categories closely related to the patient's current surgery from a large amount of data from similar surgical cases. The electronic medical record contains information such as the patient's past medical history, allergy history, and diagnostic results. Big data analytics, through statistical analysis of numerous surgical records, identifies items of significant importance for evaluating the surgery, such as the type of surgery, key operational steps, and special circumstances that occurred during the procedure.

[0054] In this embodiment, the key item categories in the patient's surgical record clearly define the information categories that are significant and representative of the patient's surgery. These categories are key parts extracted from the complete surgical record data, which helps to focus on core information and improve the efficiency of subsequent data processing and analysis. For example, "intraoperative blood loss" and "number of times key instruments were used" are identified as key item categories in the surgical record.

[0055] In this embodiment, extracting key operating room record data from the patient's complete surgical record data based on key item categories in the surgical record involves filtering out specific data corresponding to the determined key item categories from the complete surgical record data, which contains various aspects of information. For example, if "intraoperative blood loss" is a key item category, the accurate recorded value of intraoperative blood loss is found from various data in the complete surgical record data. This extracted set of data constitutes the key operating room record data.

[0056] In this embodiment, the critical operating room record data is data directly related to the key information of the surgery extracted from the complete surgical record data. It removes a large amount of redundant information and retains only the data that is of key value for evaluating the surgery and generating reports.

[0057] In this embodiment, the predefined rules and logic are a set of pre-established standards and processes used to regulate the way data is processed and analyzed. These rules and logic are formulated based on medical expertise, industry standards, and actual business needs, such as specifying how to integrate key data from different types of surgeries and the criteria for judging the logical relationships between data.

[0058] In this embodiment, key operating room record data is integrated based on predefined rules and logic, and an operating room record report is generated by combining it with the patient's electronic medical record. This involves organizing, summarizing, and analyzing the extracted key operating room record data according to pre-set rules and logic, arranging the relevant data in a specific structure and order. Simultaneously, relevant information from the patient's electronic medical record, such as basic health status and diagnostic information, is incorporated, ultimately forming a comprehensive and systematic operating room record report.

[0059] In this embodiment, the operating room record report is a document generated after integrating and analyzing key information from the surgical procedure. It presents important surgical-related content in a standardized format. The report content is generated based on key operating room record data and the patient's electronic medical record, covering basic surgical information, the patient's intraoperative condition, key operational steps, equipment usage, any special circumstances that occurred, and their handling measures.

[0060] The beneficial effects of the above technologies are as follows: Real-time collection of patient vital signs data, surgical equipment operation data, and audio-visual recordings within the operating room comprehensively covers key information during the surgical process, laying the foundation for accurate subsequent generation of operating room records. This multi-dimensional data reflects the actual surgical situation from different perspectives, ensuring the completeness and accuracy of the record. Secondly, time-stamp alignment and correction of various data types yield complete surgical record data, ensuring precise matching of data from different sources in the time dimension. This helps to clearly present the sequence and synchronization of each stage of the surgery, avoiding misunderstandings of the surgical process due to time discrepancies, and improving the logic and readability of the record. Based on the patient's electronic medical record and big data analysis, key categories of surgical records are determined, and key operating room record data is extracted from them, achieving precise screening of massive amounts of data. Focusing on key information highlights important points while reducing unnecessary data interference, making the record more targeted and facilitating quick access to key content for medical staff. Then, based on predefined rules and logic, key operating room record data is integrated and combined with electronic medical records to generate an operating room record report, ensuring the standardization and scientific rigor of the report generation. Predefined rules ensure that data integration is organized and conforms to medical professional logic. Combined with electronic medical records, this further enriches the report content, providing comprehensive and accurate information for surgical summaries, follow-up treatments, and medical research. Finally, this method improves the efficiency and quality of operating room record generation. Through automated data processing workflows, it reduces the workload of manual data organization and recording, lowers the risk of human error, improves the overall efficiency and quality of medical work, and supports medical decision-making and research.

[0061] Example 2: Based on Example 1, S1: Real-time collection of patient vital signs data, surgical equipment operation data, and audio-visual recording data in the operating room, including:

[0062] Multiple vital sign monitors are used to collect patients' vital sign data in real time;

[0063] Real-time collection of operating parameters and operational status data of all surgical equipment in the operating room as surgical equipment operation data;

[0064] The audio and video data of the operation is recorded by cameras and microphones installed in the operating room to monitor the operation and the patients.

[0065] In this embodiment, the vital signs monitor is a medical device specifically designed for real-time measurement and monitoring of a patient's vital signs. It can continuously track and detect multiple key vital signs simultaneously or separately, such as heart rate, blood pressure, respiratory rate, and body temperature, providing medical staff with intuitive and real-time information about the patient's physical function. For example, during surgery, the vital signs monitor operates continuously, feeding back the patient's various vital signs data to medical staff in real time. If any indicator becomes abnormal, the monitor may issue an alarm.

[0066] In this embodiment, the patient's vital signs data refers to a series of data reflecting the patient's basic physiological state, obtained through devices such as vital signs monitors. This data includes, but is not limited to, heart rate (representing the number of times the heart beats per minute), blood pressure (divided into systolic and diastolic pressure, reflecting the pressure within blood vessels during heart contraction and relaxation), blood oxygen saturation (the percentage of oxygenated hemoglobin bound to oxygen in the blood relative to all hemoglobin that can bind oxygen), respiratory rate (the number of breaths per minute), and body temperature.

[0067] In this embodiment, the operating parameters and operational status data of the surgical equipment refer to the various operational settings and real-time working status information of the equipment during the surgical procedure. Operating parameters vary depending on the type of equipment; for example, the laser power and pulse frequency of a laser surgical device, and the cutting speed and force of a scalpel, determine how the equipment performs the surgical operation. Operational status data reflects whether the equipment is working properly, including its start-up, operation, pause, and fault states, as well as the working status of its internal components, such as motor speed and the degree of wear on instruments.

[0068] In this embodiment, the operational status data of the surgical equipment mainly focuses on information related to the equipment's own working condition. It covers the equipment's current status, such as whether it is operating normally, in standby mode, or experiencing a fault alarm. It also includes the operational status of key internal components, such as whether the operating parameters of the equipment's power system and control system are within normal ranges, as well as data on the equipment's runtime and cumulative usage count.

[0069] In this embodiment, the medical monitoring audio and video data refers to the data recorded by specialized audio and video acquisition equipment in a medical setting, documenting the interactions between doctors, patients, and related personnel, as well as the surrounding environment. The video portion records the scene inside the operating room, including visual information such as the doctor's procedures, the patient's condition, and the use of surgical equipment; the audio portion records sound information such as dialogues between doctors and patients, communication among medical staff, and sounds generated by the operation of equipment.

[0070] The beneficial effects of the above technical solutions are as follows: By utilizing multiple vital sign monitors to collect patient vital sign data in real time, it is possible to comprehensively and meticulously monitor the patient's physical condition from multiple dimensions, such as heart rate, blood pressure, and blood oxygen saturation. This provides medical staff with rich and accurate data support for real-time monitoring of changes in the patient's vital signs during surgery, enabling timely detection of potential health risks and the implementation of corresponding measures to ensure the safety of the surgery. Real-time collection of operating parameters and operational status data of all surgical equipment in the operating room serves as the surgical equipment operation data, allowing medical staff and technicians to understand the equipment's working status in real time. If an equipment exhibits abnormal operating status or its parameters deviate from the normal range, the problematic equipment can be quickly located and addressed promptly, preventing equipment failure from affecting the surgical process and ensuring the stable operation of surgical equipment, thus providing strong support for the smooth conduct of the surgery. Based on the audio and video data of the medical staff and patients monitored during the surgery recorded by cameras and microphones installed in the operating room, the entire surgical process is recorded completely and intuitively, including the doctor's operating steps and communication between the doctor and patient. This not only helps in post-operative review of the surgical procedure, summarizing lessons learned, and improving surgical skills, but also provides objective and truthful evidence in special circumstances such as medical disputes, safeguarding the legitimate rights and interests of both doctors and patients. Furthermore, the audio and video recording data, combined with the other two types of data, constitutes a comprehensive and detailed surgical record data source, laying a solid foundation for generating high-quality operating room record reports.

[0071] Example 3: Based on Example 1, S2: The patient's vital signs data, surgical equipment operation data, and audio-visual recording data in the operating room are time-stamped and corrected to obtain the patient's complete surgical record data, including:

[0072] The patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room are time-stamped and aligned to obtain multi-source aligned recording data of the operating room;

[0073] Identify all data gap periods for each type of record data in the multi-source aligned record data of the operating room, and take the partial record data of all types of record data except for a single type of record data in the multi-source aligned record data of the operating room in each data gap period of the current type of record data as the multi-source reference record data of the corresponding type of record data in the corresponding data gap period;

[0074] Based on the multi-source reference record data and adjacent time period reference record data for each type of record data in each data gap period, the gap data of each type of record data is filled to obtain the complete record data of each type of record data, and the multi-source aligned complete record data of the operating room is obtained.

[0075] Horizontal and vertical corrections were performed on each segment of differentially aligned record data in the multi-source aligned complete record data of the operating room to obtain the patient's complete surgical record data.

[0076] In this embodiment, operating room multi-source aligned recording data refers to the process of calibrating and integrating various types of recording data from different sources related to the operating room in terms of time or logic through specific methods, so that these data can correspond to each other and collaboratively present comprehensive information about the surgical process.

[0077] In this embodiment, the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room are each types of recorded data.

[0078] In this embodiment, the data gap period refers to the time period during which one or more types of recorded data are missing during the recording of surgery-related data. This may be due to equipment malfunction, signal interference, human error, or other reasons, resulting in one or more of the following being incompletely recorded within a certain time period: patient vital signs data, surgical equipment operation data, or operating room audio-visual recording data. For example, a brief malfunction of the vital signs monitor may cause the patient's blood pressure data to be missing for a few minutes; these few minutes constitute the data gap period.

[0079] In this embodiment, complete recorded data for each type of data refers to all data recorded from the start to the end of the surgery, under ideal conditions without data loss or interruption, including patient vital signs data, surgical equipment operation data, and audio-visual recordings in the operating room. For example, complete surgical equipment operation data should include information such as all changes in operating parameters and changes in operating status from equipment startup to shutdown.

[0080] In this embodiment, the multi-source aligned complete record data of the operating room is a complete dataset that ensures accurate temporal and logical correspondence between various types of record data after alignment processing, and that there are no data gaps. For example, when conducting surgical debriefing, doctors can use this data to accurately view the detailed correlation between patient vital signs, surgical procedures, and equipment operation at a specific point in time.

[0081] In this embodiment, the differentiated sub-aligned record data is a subset of data with specific differences selected from the multi-source aligned record data or the complete multi-source aligned record data of the operating room according to specific needs or conditions. This subset of data is then re-aligned to obtain the record data. For example, to address the differences between complex and routine surgeries, a relevant subset of data from the complex surgery portion is selected, and various types of data within it are re-aligned to form differentiated sub-aligned record data, enabling the specialized study of special situations and patterns during complex surgeries.

[0082] The beneficial effects of the above technical solutions are as follows: By aligning, filling gaps, and correcting different types of surgical data with timestamps, the quality of surgical record data is greatly improved. Timestamp alignment synchronizes vital signs, equipment operation, and audio / video recording data in time, ensuring clear correlations between data points, facilitating a comprehensive understanding of the surgical process, and avoiding analytical errors caused by time misalignment. Identifying data gap periods and acquiring multi-source reference records allows for filling gaps by utilizing the relationships between multiple data points, fully exploring data value, and ensuring record integrity. Filling gaps based on multi-source and adjacent time period reference data, combined with data trend analysis, makes the supplementary content more realistic and enhances data authenticity. Horizontal and vertical corrections are performed on differentiated sub-aligned record data, ensuring logical consistency across different data points horizontally and ensuring coherent and reasonable time series for individual data points vertically, further improving data accuracy. High-quality, complete surgical record data provides reliable evidence for surgical debriefing, experience summarization, medical research, and handling of medical disputes, enhancing the scientific rigor and precision of medical work.

[0083] Example 4: Based on Example 3, the patient's vital signs data, surgical equipment operation data, and audio / video recording data in the operating room are timestamped to obtain multi-source aligned recording data of the operating room, including:

[0084] Data cleaning is performed on the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain clean vital signs data, clean surgical equipment operation data, and clean audio and video recording data in the operating room.

[0085] By aligning the timestamps of the patient's pure vital signs data, pure surgical equipment operation data, and pure audio and video recording data in the operating room, multi-source aligned recording data of the operating room is obtained.

[0086] In this embodiment, data cleaning of patient vital sign data, surgical equipment operation data, and audio / video recordings in the operating room refers to the use of specific data processing techniques and methods to sort and purify these three types of raw data to improve data quality. During the acquisition process, raw data may be affected by various factors, resulting in erroneous values, duplicate values, or incomplete information. For example, patient vital sign data may contain abnormal blood pressure values ​​or missing heart rate records due to temporary malfunctions or signal interference from monitoring equipment. During cleaning, these errors are identified and corrected or missing values ​​are filled based on medical knowledge and the normal measurement range of the equipment, thereby obtaining pure vital sign data that accurately reflects the patient's true physical condition. For surgical equipment operation data, due to the instability of the equipment itself or data transmission problems, there may be erroneous recordings of operating parameters or jumps in operating status data. Through data cleaning, these problems are identified and corrected using the operating principles of the equipment and historical normal data patterns, resulting in pure surgical equipment operation data that accurately presents the actual operation of the surgical equipment. Audio / video recordings in the operating room may contain blurry images or unclear audio segments due to changes in lighting or noise. After data cleaning, image enhancement and noise reduction techniques were used to improve audio and video quality, resulting in clean audio and video recordings from the operating room that clearly present the scene and sound information during the surgery. The overall data cleaning process aims to provide a reliable data foundation for subsequent data analysis and surgical evaluation.

[0087] The beneficial effects of the above technical solution are as follows: The data cleaning process handles patient vital sign data, surgical equipment operation data, and operating room audio-visual recordings, removing potential noise, errors, or duplicate data. For vital sign data, it eliminates outliers caused by instrument interference, ensuring the data accurately reflects the patient's physical condition. For surgical equipment operation data, it corrects erroneous parameters caused by equipment malfunctions, ensuring the data accurately reflects the equipment's operating status. For audio-visual recordings, it filters out irrelevant noise or blurry images. The cleaned data significantly improves data quality, providing a reliable foundation for subsequent analysis and processing. Timestamp alignment of this cleaned data ensures strict time-series matching of data from different sources. This not only more accurately correlates patient status, equipment operation, and medical staff behavior during surgery, facilitating a comprehensive and clear review of the surgical process, but also provides an accurate data foundation for time-series data analysis. High-quality, multi-source aligned operating room recordings help improve the accuracy of surgical debriefing, assist in medical decision-making, and provide more reliable data samples for medical research, thus promoting the advancement and development of medical technology.

[0088] Example 5: Based on Example 3, using multi-source reference recording data and adjacent time-period reference recording data for each type of recorded data during each data gap period, gap data filling is performed on each type of recorded data to obtain complete recording data for each type of recorded data, and multi-source aligned complete recording data of the operating room is obtained, including:

[0089] The missing reference value of multi-source reference record data for each type of record data in each data gap period is calculated, and the missing reference value of reference record data in adjacent periods for each type of record data in each data gap period is also calculated.

[0090] For each type of record data, all reference record data exceeding the fill-in reference threshold during each data gap period are used as fill-in reference data for each type of record data during each data gap period.

[0091] Based on the reference data for filling gaps in each data gap period for each type of record data and the preset gap data filling model for each type of record data, gap data filling is performed for each type of record data to obtain the complete record data for each type of record data;

[0092] All types of record data are re-timestamped to obtain multi-source aligned complete record data of the operating room.

[0093] In this embodiment, the gap-filling reference value of each type of recorded data for each data gap period is a numerical value used to measure the reliability and practical value of reference recorded data from multiple other data sources for filling the gap during that data gap period. Multi-source reference recorded data may come from data from similar surgical cases at the corresponding time period, or records from other related equipment at the same time. For example, for a patient's vital signs data in a gap period, vital signs data from other patients with similar conditions at the same surgical stage are used as multi-source reference recorded data. A certain algorithm is used to evaluate the applicability of these reference data to fill the current gap, and the resulting applicability is the gap-filling reference value. The higher the value, the more suitable these multi-source reference recorded data are for filling the gap in that period.

[0094] In this embodiment, the reference value for filling the gap in adjacent time periods for each type of recorded data refers to the numerical value assigned to each type of recorded data based on the recorded data in adjacent time periods before and after the data gap, assessing its usability in filling the gap. Because data often has a certain degree of continuity and correlation, data from adjacent time periods may provide valuable information for the gap. For example, the operating status and parameters of surgical equipment usually change in a certain pattern before and after a certain gap. Based on this pattern and the actual recorded data in adjacent time periods, the reference value for filling the gap is analyzed to determine whether and to what extent adjacent time period data can be used to fill the gap.

[0095] In this embodiment, the missing referenceability threshold is a pre-set standard value used to determine whether the missing referenceability value of multi-source reference records or adjacent time period reference records is usable. When the missing referenceability value of a certain reference record is greater than or equal to the threshold, it indicates that it has sufficient reliability and reference value and can be used to fill the corresponding data gap period; if it is lower than the threshold, the reference record is considered unreliable or unsuitable for missing data, and it may be necessary to find other more suitable reference data or adopt other missing data methods. For example, if the missing referenceability threshold is set to 0.6, and the missing referenceability value of a certain multi-source reference record is 0.7, then it can be considered for data missing data.

[0096] In this embodiment, the reference record data includes multi-source reference record data and adjacent time period reference record data. This indicates that when processing data gaps, there are two main sources of reference information available. Multi-source reference record data, leveraging data from other similar scenarios or related devices, provides diverse references for filling in data gaps. Adjacent time period reference record data, based on the inherent correlation between data, obtains information from adjacent time periods of the same data record to attempt to fill the gaps. These two types of reference record data complement each other, providing more comprehensive support for data gap filling.

[0097] In this embodiment, the reference data for filling data gaps in each time period is determined by comprehensively considering the referenceability values ​​of multi-source reference records and adjacent time period reference records, and comparing them with a referenceability threshold. If multiple data sets from the multi-source and adjacent time period reference records meet the referenceability threshold, the final reference data may be determined according to certain rules (such as prioritizing those with higher referenceability values, or combining multiple data sets). For example, for a given time period with data gaps, if one type of multi-source reference record and adjacent time period reference records both meet the referenceability threshold, and the multi-source reference record with the higher referenceability value is selected, it will be chosen as the reference data for that time period.

[0098] In this embodiment, the pre-defined missing data filling model for each type of recorded data is a mathematical model or algorithm pre-defined based on the characteristics and patterns of different types of data (such as patient vital sign data, surgical equipment operation data, and audio-visual recordings in the operating room) for each data gap period. These models consider factors such as the nature of the data, its changing trends, and its correlation with other data. For example, for patient vital sign data, the pre-defined model may combine the patient's basic health condition, the type of surgery, and the general change pattern of vital signs during the surgery to predict and fill the missing values; for surgical equipment operation data, the model may calculate the parameters for the missing period based on the working principle and operating logic of the equipment, as well as historical operation data.

[0099] In this embodiment, based on the missing reference data for each type of recorded data in each data gap period and the preset missing data filling model for each type of recorded data, missing data is filled for each type of recorded data to obtain complete recorded data for each type of recorded data. This involves inputting the determined missing reference data into the corresponding preset missing data filling model. Through the model's calculations and processing, data values ​​are generated to fill the gaps, thus making the originally missing recorded data complete. For example, for a gap in a patient's vital signs data, based on the determined missing reference data, the preset vital signs data gap filling model is used to calculate the predicted vital signs value for that missing period, which is then filled into the gap, ultimately obtaining complete patient vital signs recorded data. This process is repeated for other types of recorded data to ensure that each type of recorded data is complete.

[0100] The beneficial effects of the above technical solution are as follows: By calculating the reference value for filling gaps between multi-source reference records and reference records from adjacent time periods, the reference value of various types of data for filling gaps can be quantitatively evaluated. This helps to accurately screen truly reliable and usable data from numerous potential reference data, avoiding interference from invalid or low-quality data in the filling process, and improving the accuracy and scientific nature of data filling. Determining the reference data for filling gaps based on the reference value threshold further clarifies the data screening criteria. Only reference data exceeding the threshold is selected, ensuring that the data used for filling gaps has high credibility, making the filled records closer to the actual surgical situation, and effectively improving the quality and reliability of the data. Using a pre-set gap data filling model and the screened reference data for filling gaps provides a scientific and reasonable method for the filling operation. This model is designed based on the characteristics and patterns of surgical data, combined with reliable reference data, and can more accurately infer and fill gaps, making each type of record data more complete and providing strong support for a comprehensive presentation of the surgical process. Finally, all complete record data are time-stamp aligned again to ensure that after filling gap data, various types of data remain precisely synchronized in the time dimension. This ensures that the multi-source aligned complete record data in the operating room is consistent in time, making it convenient for medical staff to analyze the surgical situation based on an accurate timeline. It provides a high-quality data foundation for surgical debriefing, medical decision-making, and medical research, thereby enhancing the application value of the entire surgical record.

[0101] Example 6: Based on Example 5, calculate the fill-in reference value of multi-source reference record data for each type of record data during each data gap period, including:

[0102] ;

[0103] In the formula, This is the referenceability value for filling gaps in multi-source reference record data for a single type of record data in the current calculation of a single data gap period, where n is the total number of all record data types. The weights for calculating information stickiness Let α be the information adhesion between the currently calculated single-type record data and the i-th type of record data in the multi-source reference record data during the currently calculated single data gap period, where α is the calculation weight of information reliability. β represents the information reliability of the i-th record data among the multi-source reference record data in the current single data gap period, where β is the calculation weight for information integrity. This refers to the reliability of information about the i-th type of record data in the preceding time period of the multi-source reference record data within the currently calculated single-type record data during the current single data gap period. This represents the information completeness of the record data in the preceding time period adjacent to the i-th record data in the multi-source reference record data during the currently calculated single-type record data period within the currently calculated single data gap time period. This refers to the reliability of information about the i-th type of record data in the next adjacent time period within the multi-source reference record data of the currently calculated single-type record data during the currently calculated single data gap time period. It represents the information completeness of the record data in the next adjacent time period of the i-th record data in the multi-source reference record data during the current single data gap period.

[0104] In this embodiment, information stickiness is used to measure the degree of correlation and dependence between information from different sources. In an operating room data scenario, for example, patient vital sign data and surgical equipment operation data may be related. If changes in vital signs are closely related to the operation of a specific surgical device, it indicates high information stickiness; conversely, if the correlation is not strong, the stickiness is low. Information stickiness helps to determine the intrinsic connections between different data and provides a basis for the comprehensive analysis of multi-source data.

[0105] In this embodiment, the weight for calculating information stickiness is a relative importance value assigned to information stickiness when calculating the referenceability value of multi-source reference record data for each type of record data in each data gap period. For example, it can be 0.4.

[0106] In this embodiment, information reliability reflects the authenticity and credibility of the information. For operating room recorded data, such as vital sign data, the reliability is low because deviations may occur due to equipment malfunctions; however, if the data has been verified multiple times and the equipment is operating stably, the reliability is high.

[0107] In this embodiment, the weight for calculating information reliability is a weight value assigned to information reliability during the process of calculating the referenceability value of multi-source reference record data for each type of record data in each data gap period. For example, it can be 0.3.

[0108] In this embodiment, information completeness refers to the degree of completeness of the information content, that is, whether the recorded data contains all the necessary information. In an operating room setting, complete surgical record data should cover all key information from the start to the end of the surgery, including the patient's vital signs, the operation of surgical equipment, and audio-visual recordings. If certain time periods or types of data are missing, the information completeness will be low, affecting the understanding and analysis of the overall surgical situation.

[0109] In this embodiment, the weight for calculating information completeness is assigned when calculating the referenceability value of multi-source reference record data for each type of record data during each data gap period. For example, a weight of 0.3 can be used.

[0110] The beneficial effects of the above technical solution are as follows: Calculating the gap-filling reference value using this complex and comprehensive formula brings multiple advantages. It comprehensively considers information cohesion, reliability, and completeness to ensure the scientific rigor of the assessment. Information cohesion considers the degree of internal connection between different data records, enabling the discovery of reference data strongly correlated with the target data; information reliability measures the credibility of the data itself, avoiding the introduction of unreliable data to interfere with gap filling; information completeness focuses on the integrity of data from adjacent time periods, providing a more comprehensive basis for inferring missing data. By setting calculation weights, the influence of each factor on the gap-filling reference value can be flexibly adjusted according to actual needs. Under different surgical scenarios or data types, the importance of certain factors can be highlighted specifically, making the assessment more relevant to the actual situation. This method of accurately calculating the gap-filling reference value of multi-source reference records can precisely filter out the most valuable data for filling gaps from massive amounts of reference data. Only data with high reference values ​​will be used for gap filling, which greatly improves the accuracy and reliability of gap filling, thereby improving the quality of surgical record data and providing more solid and accurate data support for subsequent surgical analysis, research and medical decision-making, thus contributing to the refinement and scientification of the medical process.

[0111] Example 7: Based on Example 5, calculate the fill-in-the-gap reference value of the reference record data in the adjacent time period for each type of record data in each data gap period, including:

[0112] ;

[0113] In the formula, This is the reference value for filling gaps in the reference data of adjacent time periods for the currently calculated single type of record data within the currently calculated single data gap time period. This refers to the reliability of information from the reference record data in the preceding adjacent time period of the currently calculated single data gap period. This refers to the reliability of information about the reference record data in the next adjacent time period after the current single data gap period, based on the currently calculated single type of record data. This refers to the information completeness of the reference record data in the preceding adjacent time period of the currently calculated single data gap period. The completeness of information of the reference record data in the next adjacent time period after the current single data gap period.

[0114] The beneficial effects of the above technical solution are as follows: This formula for calculating the reference value of adjacent time period reference record data comprehensively evaluates the potential value of adjacent time period data in filling the current missing time period data by considering the information reliability and completeness of the reference record data of the preceding and following time periods. Information reliability ensures that the data used is true and credible, avoiding deviations in the filling results due to the introduction of erroneous or unreliable data. Information completeness ensures that the data used for filling has sufficient information, making the inferred missing data more consistent with the actual situation. This formula focuses on the data of the preceding and following time periods closely related to the missing time period, avoiding overly complex calculations and improving computational efficiency. In actual surgical record scenarios, it is crucial to quickly and accurately assess the usability of adjacent time period data. This efficient calculation method can provide timely reference for filling missing data. By accurately calculating the reference value of adjacent time period reference record data, the most valuable adjacent time period data is selected for filling the gaps, greatly improving the quality of missing data filling. This helps to improve surgical record data, making it more accurately reflect the entire surgical process, providing more reliable data support for medical staff's surgical review, disease analysis, and subsequent medical decisions, thereby improving the overall quality and level of medical services.

[0115] Example 8: Based on Example 3, horizontal and vertical corrections are performed on each segment of differentially aligned record data in the multi-source aligned complete record data of the operating room to obtain the patient's complete surgical record data, including:

[0116] The multi-source aligned complete record data of the operating room is divided into time periods to obtain multi-segment aligned record data;

[0117] Calculate the information alignment degree of each segment of the alignment record data;

[0118] From all the segment alignment record data, select all segment alignment record data with an information alignment degree greater than the information alignment degree threshold as all segment differential sub-alignment record data;

[0119] Based on the preset horizontal and vertical correction model, all segment differential sub-aligned record data are corrected horizontally and vertically to obtain the patient's complete surgical record data.

[0120] In this embodiment, dividing the multi-source aligned complete recording data of the operating room into time segments to obtain multiple sub-aligned recording data means dividing the integrated multi-source aligned complete recording data of the operating room into multiple data segments of shorter time periods according to certain time intervals or surgical stages. Each segment is a sub-aligned recording data segment. For example, dividing it into 10-minute segments yields multiple sub-aligned recording data segments of different time periods.

[0121] In this embodiment, the information alignment degree of each segment of aligned record data is used to measure the degree of temporal and logical matching and correspondence between different types of information (such as patient vital signs, surgical equipment operation, audio and video recordings, etc.) in each segment of aligned record data. If the various types of data are closely related and accurately correspond, the information alignment degree is high; otherwise, it is low. For example, in a certain segment of aligned record data, if the changes in patient vital signs are highly consistent with the relevant scenarios of surgical equipment operation and audio and video recordings, its information alignment degree is high.

[0122] In this embodiment, the information alignment threshold is a pre-set standard value used to determine whether the information alignment of sub-aligned record data meets the requirements. When the information alignment of a segment of sub-aligned record data is higher than this threshold, it indicates that the information matching and correspondence of the data in that time period is good; if it is lower than the threshold, it indicates that there may be information alignment problems, and further processing is required. For example, if the information alignment threshold is set to 80%, and the information alignment of a segment of sub-aligned record data is 85%, then it meets the requirements.

[0123] In this embodiment, the preset horizontal and vertical correction model is an algorithm or processing method pre-defined based on the characteristics and patterns of operating room data. "Horizontal" may refer to the calibration between different types of data within the same time period, such as accurately associating patient vital sign data with surgical equipment operation data at the same moment; "vertical" may refer to the consistency correction between data from different time periods, ensuring that changes in data along the time axis are logical. Processing data through this model can improve data accuracy and consistency. The model's input and output during training are, respectively, all segment differentiated sub-aligned record data and the patient's complete surgical record data.

[0124] In this embodiment, based on a preset horizontal and vertical correction model, all segment-differentiated sub-aligned record data are corrected horizontally and vertically to obtain the patient's complete surgical record data. This involves using the preset horizontal and vertical correction model to calibrate and correct each segment of sub-aligned record data, which has been filtered and aligned according to specific difference characteristics, from both horizontal and vertical dimensions. This correction allows for better matching of different types of data across different time periods and maintains consistency and rationality throughout the entire surgical time span, ultimately resulting in complete and accurate surgical record data that reflects the patient's surgical process.

[0125] The beneficial effects of the above technical solutions are as follows: Firstly, dividing the multi-source aligned complete record data from the operating room into time periods breaks down complex data into multiple sub-parts, making subsequent processing more targeted and systematic. This facilitates detailed analysis of data characteristics in each time period and a clear understanding of the surgical stage. Secondly, calculating the information alignment degree of each sub-aligned record data segment and using specific quantitative indicators to measure data alignment quality provides a precise standard for selecting high-quality data, accurately determining which time periods require priority processing, and improving data processing efficiency and accuracy. Thirdly, filtering differentially aligned sub-aligned record data with information alignment degrees exceeding a threshold allows for correction only of key data, avoiding unnecessary operations on good data, saving computational resources and time, and focusing on parts that may affect the accuracy of the record, enhancing the targeting and effectiveness of the correction. Fourthly, using a pre-set horizontal and vertical correction model to correct the filtered data ensures logical consistency of different types of data within the same time period horizontally and ensures the coherence and rationality of individual data points in the time series vertically, significantly improving the quality of surgical record data. This provides a reliable data foundation for surgical review, medical research, and decision-making, helping medical personnel to comprehensively and accurately understand the surgical process and improve the quality and level of medical services.

[0126] Example 9: Based on Example 8, calculate the information alignment degree of each segment of the sub-aligned record data, including:

[0127] ;

[0128] In the formula, IA represents the information alignment degree of the currently calculated single-segment sub-aligned record data, and m represents the total number of all record data types contained in the currently calculated single-segment sub-aligned record data. Let be the similarity between the j-th and i-th record data in the currently calculated single-segment sub-aligned record data. Let p be the weight used to calculate the similarity between the j-th and k-th record data in the currently calculated single-segment aligned record data, where p is the total number of time points contained in the single-segment aligned record data. Let j be the numerical sequence of the j-th type of record data in the currently computed single-segment sub-aligned record data, and , Let j be the reference numerical sequence of the j-th type of record data in the currently calculated single-segment sub-aligned record data, and , Let be the correlation value between the numerical sequence of the j-th type of record data of the currently calculated single-segment sub-aligned record data and the corresponding reference numerical sequence at time point t. The weight for calculating the correlation between the numerical sequence of the j-th type of record data of the currently calculated single-segment aligned record data and the corresponding reference numerical sequence.

[0129] In this embodiment, the similarity between the i-th and j-th types of record data in the currently calculated single-segment aligned record data measures the degree of similarity between these two different types of record data within the currently calculated single-segment aligned record data. For example, in an operating room scenario, the i-th type of record data is the patient's heart rate data, and the j-th type of record data is the operating power data of a certain surgical device. Through a specific algorithm (e.g., feature value extraction to construct vectors, and then using a cosine similarity algorithm to calculate the similarity between feature vectors), the similarity in terms of their changing trends, numerical distribution, etc., within this time period is calculated. The higher the similarity, the closer the correlation between the two in this time period.

[0130] In this embodiment, the weight for calculating the similarity between the i-th and j-th record data in the currently calculated single-segment sub-aligned record data is a relative importance value set for the similarity between the i-th and j-th record data in the currently calculated single-segment sub-aligned record data when calculating the information alignment degree of each segment sub-aligned record data. For example, it can be a value of 0.15.

[0131] In this embodiment, the numerical sequence of each type of recorded data refers to a series of values ​​arranged sequentially over time for each type of recorded data. Taking a patient's blood pressure data as an example, the sequence formed by arranging the blood pressure values ​​corresponding to each measurement point from the start of surgery to the end of the current time period is the numerical sequence of blood pressure recorded data, which intuitively presents the changes of the recorded data over a period of time.

[0132] In this embodiment, the reference numerical sequence for each type of recorded data is a numerical sequence serving as a reference standard, corresponding to the numerical sequence of each type of recorded data. It may be derived statistically from similar recorded data from a large number of past surgical cases, or set according to the ideal variation that the recorded data should exhibit. For example, the reference numerical sequence of normal heart rate changes in patients during a certain type of surgery can be used as a comparison standard for the current surgical patient's heart rate numerical sequence to assess whether the current heart rate data is within a reasonable range.

[0133] In this embodiment, the correlation value between the numerical sequence of the kth type of recorded data in the currently calculated single-segment aligned recorded data and the corresponding reference numerical sequence at time point t is used to analyze the degree of correlation between the value of the kth type of recorded data at time point t and the value of the reference numerical sequence at the same time point t within the currently calculated single-segment aligned recorded data. For example, at time point t, if the patient's actual heart rate value and the value of the corresponding time point in the reference heart rate value sequence are close and have the same trend, it indicates a high correlation; otherwise, it is low. This helps to determine the reasonableness of the currently recorded data at that time point.

[0134] In this embodiment, the weight for calculating the correlation value between the numerical sequence of the kth type of record data in the currently calculated single-segment sub-aligned record data and the corresponding reference numerical sequence is the weight value of the correlation value between the numerical sequence of the kth type of record data in the currently calculated single-segment sub-aligned record data and the corresponding reference numerical sequence when calculating the information alignment degree of each sub-aligned record data. For example, it can be a value of 0.1.

[0135] The beneficial effects of the above technical solution are as follows: The information alignment calculation formula improves the accuracy and reliability of surgical record data processing in multiple ways. The formula comprehensively considers various factors to measure the information alignment degree of sub-aligned record data. By calculating the similarity between different types of record data and assigning them corresponding calculation weights, it can accurately assess the matching degree between different types of data, highlighting the impact of key data relationships on the overall alignment degree. Simultaneously, by leveraging the correlation and corresponding weights between the numerical sequences of each record data segment and the reference numerical sequence at various time points within a single sub-aligned record data segment, it fully considers the consistency of data in the time dimension. This makes the information alignment degree not only reflect the similarity between data types but also the synchronicity of data changes over time. This comprehensive and detailed calculation method can accurately quantify the information alignment status of each sub-aligned record data segment. Medical personnel can use this accurate alignment degree to clearly understand data quality and identify which sub-aligned record data requires focused attention and correction. This provides a solid and accurate basis for subsequent screening of differentiated sub-aligned record data, and then obtains more accurate complete surgical record data through horizontal and vertical correction, providing highly reliable data support for medical decision-making, surgical review and research, and helping to improve the scientific rigor and precision of the medical process.

[0136] Example 10: Based on Example 1, an operating room record generation system includes:

[0137] The multi-source data collection module is used to collect patients' vital signs data, surgical equipment operation data, and audio and video recording data in the operating room in real time.

[0138] The alignment and correction module is used to align and correct the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain the patient's complete surgical record data.

[0139] The key record extraction module is used to analyze the key items of the patient's surgical record based on the patient's electronic medical record and big data analysis, and to extract the key operating room record data from the patient's complete surgical record data based on the key items of the patient's surgical record.

[0140] The data estimation and integration module is used to integrate key operating room record data based on predefined rules and logic, and generate operating room record reports by combining the patient's electronic medical record.

[0141] The beneficial effects of the above technologies are as follows: Real-time collection of patient vital signs data, surgical equipment operation data, and audio-visual recordings within the operating room comprehensively covers key information during the surgical process, laying the foundation for accurate subsequent generation of operating room records. This multi-dimensional data reflects the actual surgical situation from different perspectives, ensuring the completeness and accuracy of the record. Secondly, time-stamp alignment and correction of various data types yield complete surgical record data, ensuring precise matching of data from different sources in the time dimension. This helps to clearly present the sequence and synchronization of each stage of the surgery, avoiding misunderstandings of the surgical process due to time discrepancies, and improving the logic and readability of the record. Based on the patient's electronic medical record and big data analysis, key categories of surgical records are determined, and key operating room record data is extracted from them, achieving precise screening of massive amounts of data. Focusing on key information highlights important points while reducing unnecessary data interference, making the record more targeted and facilitating quick access to key content for medical staff. Then, based on predefined rules and logic, key operating room record data is integrated and combined with electronic medical records to generate an operating room record report, ensuring the standardization and scientific rigor of the report generation. Predefined rules ensure that data integration is organized and conforms to medical professional logic. Combined with electronic medical records, this further enriches the report content, providing comprehensive and accurate information for surgical summaries, follow-up treatments, and medical research. Finally, this method improves the efficiency and quality of operating room record generation. Through automated data processing workflows, it reduces the workload of manual data organization and recording, lowers the risk of human error, improves the overall efficiency and quality of medical work, and supports medical decision-making and research.

[0142] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for generating operating room records, characterized in that, include: S1: Real-time collection of patient vital signs data, surgical equipment operation data, and audio and video recording data in the operating room; S2: Time-stamp align and correct the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain the patient's complete surgical record data; S3: Based on the patient's electronic medical record and big data analysis, the key categories of the patient's surgical record are analyzed, and the key operating room record data is extracted from the patient's complete surgical record data based on the key categories of the patient's surgical record. S4: Integrate key operating room record data based on predefined rules and logic, and generate operating room record reports by combining them with the patient's electronic medical record; Step S2 involves aligning and correcting the patient's vital signs data, surgical equipment operation data, and audio / video recordings from the operating room using timestamps to obtain complete surgical record data for the patient, including: The patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room are time-stamped and aligned to obtain multi-source aligned recording data of the operating room; Identify all data gap periods for each type of record data in the multi-source aligned record data of the operating room, and take the partial record data of all types of record data except for a single type of record data in the multi-source aligned record data of the operating room in each data gap period of the current type of record data as the multi-source reference record data of the corresponding type of record data in the corresponding data gap period; The missing reference value of multi-source reference record data for each type of record data in each data gap period is calculated, and the missing reference value of reference record data in adjacent periods for each type of record data in each data gap period is also calculated. For each type of record data, all reference record data exceeding the fill-in reference threshold during each data gap period are used as fill-in reference data for each type of record data during each data gap period. Based on the reference data for filling gaps in each data gap period for each type of record data and the preset gap data filling model for each type of record data, gap data filling is performed for each type of record data to obtain the complete record data for each type of record data; All types of record data are re-timestamped to obtain multi-source aligned complete record data of the operating room; The multi-source aligned complete record data of the operating room is divided into time periods to obtain multi-segment aligned record data; Calculate the information alignment degree of each segment of the alignment record data; From all the segment alignment record data, select all segment alignment record data with an information alignment degree greater than the information alignment degree threshold as all segment differential sub-alignment record data; Based on the preset horizontal and vertical correction model, all segment differential sub-aligned record data are corrected horizontally and vertically to obtain the patient's complete surgical record data.

2. The operating room record generation method according to claim 1, characterized in that, S1: Real-time collection of patient vital signs data, surgical equipment operation data, and audio-visual recordings in the operating room, including: Multiple vital sign monitors are used to collect patients' vital sign data in real time; Real-time collection of operating parameters and operational status data of all surgical equipment in the operating room as surgical equipment operation data; The audio and video data of the operation is recorded by cameras and microphones installed in the operating room to monitor the operation and the patients.

3. The operating room record generation method according to claim 1, characterized in that, The patient's vital signs data, surgical equipment operation data, and audio-visual recordings in the operating room are timestamped and aligned to obtain multi-source aligned recording data from the operating room, including: Data cleaning is performed on the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain clean vital signs data, clean surgical equipment operation data, and clean audio and video recording data in the operating room. By aligning the timestamps of the patient's pure vital signs data, pure surgical equipment operation data, and pure audio and video recording data in the operating room, multi-source aligned recording data of the operating room is obtained.

4. The operating room record generation system according to any one of claims 1 to 3, characterized in that, include: The multi-source data collection module is used to collect patients' vital signs data, surgical equipment operation data, and audio and video recording data in the operating room in real time. The alignment and correction module is used to align and correct the patient's vital signs data, surgical equipment operation data, and audio and video recording data in the operating room to obtain the patient's complete surgical record data. The key record extraction module is used to analyze the key items of the patient's surgical record based on the patient's electronic medical record and big data analysis, and to extract the key operating room record data from the patient's complete surgical record data based on the key items of the patient's surgical record. The data estimation and integration module is used to integrate key operating room record data based on predefined rules and logic, and generate operating room record reports by combining the patient's electronic medical record.

Images