Preoperative anesthesia visit system
By designing a preoperative anesthesia visit system and using machine learning models to automatically generate ASA scores, the existing preoperative visits are solved, and the comprehensiveness, accuracy and efficiency of preoperative evaluation are achieved.
Patent Information
- Application Number
- CN202410966334.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-19
AI Technical Summary
The existing preoperative visit process is inefficient, information is prone to omission or inaccurate recording, which affects the comprehensiveness and accuracy of the assessment, and the ASA score depends on the doctor's subjective experience, resulting in insufficient objectivity and consistency.
Design a preoperative anesthesia visit system, including a medical history inquiry module, a physical examination module, a test report reading module and an ASA scoring module, use machine learning models to automatically generate ASA scores, integrate data to generate comprehensive reports, reduce human subjective judgments, and ensure Objectivity and consistency of ratings.
It improves the efficiency of visits, avoids information omissions, ensures the comprehensiveness and accuracy of preoperative evaluation, reduces the work burden of doctors, provides comprehensive and timely information support for anesthesia preparations, and improves the quality and efficiency of preoperative preparations.
Smart Images

Figure CN118983048A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of medical information and artificial intelligence technology, and in particular to a preoperative anesthesia visiting system. Background Art
[0002] The existing preoperative visit process usually requires doctors to inquire about the patient's medical history, conduct physical examinations and record information manually. The whole process is time-consuming, labor-intensive and inefficient. Especially when there are many patients, the doctor's workload is too heavy and it is difficult to ensure that every patient can receive a full preoperative evaluation. In addition, due to human factors, the collection of the patient's medical history information and physical examination data during the existing preoperative visit process may miss important content or record inaccurately, affecting the comprehensiveness and accuracy of the preoperative evaluation.
[0003] In addition, in the existing preoperative visit method, the ASA score mainly relies on the doctor's subjective experience and judgment. There are inconsistencies in the scoring standards among different doctors, which affects the objectivity and consistency of the scoring.
[0004] Therefore, it is necessary to propose a preoperative anesthesia visit system to reduce the workload of doctors, improve visit efficiency, avoid missing information, ensure the comprehensiveness and accuracy of preoperative evaluation, reduce the influence of human subjective judgment, ensure the objectivity and consistency of scoring, and realize the intelligence, integration, automation, standardization and efficiency of preoperative visits, provide doctors with comprehensive and timely patient information support, and improve the quality and efficiency of preoperative preparations. Summary of the invention
[0005] The present invention provides a preoperative anesthesia visiting system to reduce the workload of doctors, improve visiting efficiency, avoid missing information, ensure the comprehensiveness and accuracy of preoperative evaluation, reduce the influence of human subjective judgment, and ensure the objectivity and consistency of scoring.
[0006] The present invention provides a preoperative anesthesia visiting system, comprising:
[0007] A medical history inquiry module, the medical history inquiry module is used to ask a series of preset standardized questions to the first user, and obtain the medical history information of the first user based on the first user's answers;
[0008] A physical examination module, the physical examination module is used to perform a physical examination on the first user and obtain physical examination data of the first user, the physical examination data including mouth opening degree and neck mobility;
[0009] A test report reading module, the test report reading module is used to read the test report of the first user, the test report records the medical test results of the first user;
[0010] An ASA scoring module, the ASA scoring module is used to generate an ASA score for the first user based on the medical history information, the physical examination data, the medical test results, and a trained and verified machine learning model;
[0011] A data reporting module, wherein the data reporting module is used to integrate the medical history information, the physical examination data and the ASA score to generate a comprehensive report, and transmit the comprehensive report to the second user.
[0012] Optionally, the preoperative anesthesia visiting system further includes:
[0013] An informed consent module, the informed consent module is used to provide an electronic informed consent for the first user to read, receive the electronic signature of the first user, and save the signed electronic informed consent;
[0014] The data reporting module is also used to integrate the signed electronic informed consent form into the comprehensive report.
[0015] Optionally, the ASA scoring module includes:
[0016] A data processing unit, the data processing unit is used to extract key features from the medical history information, the physical examination data and the medical test report, and after processing missing values and abnormal values, normalize the numerical features and perform one-hot encoding or label encoding on the categorical features; wherein the key features include age, gender, previous medical history, drug use, mouth opening, and neck mobility;
[0017] A machine learning model, wherein the machine learning model is used to receive the data processed by the data processing unit, make predictions and generate an ASA score for the first user; wherein the machine learning model includes a random forest model, a support vector machine model, and a gradient boosting decision tree model.
[0018] Optionally, the medical history inquiry module includes:
[0019] A speech unit, the speech unit being used to ask a series of preset standardized questions to the first user in a natural language form and to record the natural language answers of the first user;
[0020] a natural language processing unit, the natural language processing unit being configured to extract the medical history information of the first user based on the natural language answer of the first user;
[0021] A medical history database, wherein the medical history database is used to store and manage the medical history information of the first user.
[0022] Optionally, the physical examination module includes:
[0023] A camera, the camera being used to capture the maximum range of the first user's mouth opening;
[0024] a sensor, the sensor being used to measure a range of motion of the neck of the first user;
[0025] A physical analysis unit, which generates physical examination data of the first user based on the data collected by the camera and the sensor;
[0026] A storage unit, wherein the storage unit is used to store the physical examination data.
[0027] Optionally, the informed consent module includes:
[0028] An electronic signature unit, the electronic signature unit is used to provide an electronic informed consent form for the first user to read, and receive the electronic signature of the first user, the electronic signature method includes a biometric signature or a signature directly drawn on a touch screen device;
[0029] A data encryption unit, the data encryption unit is used to perform blockchain encryption on the signed electronic informed consent form;
[0030] A cloud storage unit is used to store the signed electronic informed consent form and back it up regularly.
[0031] Optionally, the data reporting module includes:
[0032] An integration unit, the integration unit is used to integrate the medical history information, the physical examination data and the ASA score, and generate a comprehensive report, the data format of the comprehensive report includes PDF, XML and JSON;
[0033] An encryption and compression unit, configured to encrypt and / or compress the comprehensive report;
[0034] A transmission unit, wherein the transmission unit is used to transmit the comprehensive report to the second user through an encrypted channel.
[0035] Optionally, the medical history inquiry module further includes:
[0036] A text processing unit is used to receive text data typed on a keyboard or written on a handwriting board, and extract the medical history information of the first user based on the text data.
[0037] Optionally, the ASA scoring module further includes:
[0038] A model training unit, the model training unit is used to train the machine learning model using a historical data set, and optimize the hyperparameters of the machine learning model through cross-validation and grid search;
[0039] A model verification unit, the model verification unit is used to evaluate the prediction performance of the machine learning model after being trained by the model training unit using a verification set, wherein the evaluation indicators include accuracy, recall and F1 score;
[0040] A model updating unit, the model updating unit is used to periodically retrain the machine learning model using a new data set;
[0041] A performance monitoring unit, wherein the performance monitoring unit is used to monitor the predictive performance of the machine learning model in real time.
[0042] Optionally, the preoperative anesthesia visiting system further includes:
[0043] an identity recognition unit, the identity recognition unit being used to read the identity information of the first user based on the medical insurance card inserted by the first user, and to collect a real-time image of the first user;
[0044] An identity verification unit, the identity verification unit is used to collect the facial information of the second user and / or read the information of the work license plate, and match it with the pre-stored identity information of the second user to verify the identity of the second user.
[0045] The present invention provides a preoperative anesthesia visit system, wherein the medical history information of a first user is collected through a medical history inquiry module, the physical examination data of the first user is collected through a physical examination module, the medical examination results of the first user are obtained through a test report reading module, and the ASA scoring module obtains the ASA score of the first user based on the collected medical history information, physical examination data and medical examination results, using a trained and verified machine learning model, and finally the data reporting module integrates the medical history information, physical examination data, medical examination results, and ASA scores and transmits them to a second user. The present invention reduces the workload of doctors and improves the efficiency of visits through the integrated preoperative visit system, through the automatic collection of medical history information and physical examination data, while avoiding information omissions, ensuring the comprehensiveness and accuracy of preoperative evaluation, and through the ASA scoring module, using a model trained by machine learning, completing the automatic generation of ASA scores, reducing the influence of human subjective judgment, ensuring the objectivity and consistency of the scores, providing doctors with comprehensive and timely patient information support, and improving the quality and efficiency of preoperative preparations. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.
[0047] Figure 1 A structural block diagram of a preoperative anesthesia visit system according to an embodiment of the present invention;
[0048] Figure 2 The structure block diagram of the preoperative anesthesia visiting system according to one embodiment of the present invention.
[0049] Reference numerals:
[0050] 100-medical history inquiry module; 110-speech unit; 120-natural language processing unit; 130-medical record database unit;
[0051] 200-physical examination module; 210-camera; 220-sensor; 230-physical analysis unit; 240-storage unit;
[0052] 300-test report reading module;
[0053] 400-ASA scoring module; 410-data processing unit; 420-machine learning model;
[0054] 500-data reporting module; 510-integration unit; 520-encryption compression unit; 530-transmission unit;
[0055] 600-informed consent module; 610-electronic signature unit; 620-data encryption unit; 630-cloud storage unit. DETAILED DESCRIPTION
[0056] The following is a further detailed description of the preoperative anesthesia visit system proposed by the present invention in conjunction with the accompanying drawings and specific embodiments. According to the following description, the advantages and features of the present invention will be clearer. It should be noted that the drawings are in a very simplified form and use non-precise proportions, which are only used to conveniently and clearly assist in explaining the purpose of the embodiments of the present invention. In order to make the purposes, features and advantages of the present invention more obvious and easy to understand, please refer to the accompanying drawings. It should be noted that the structure, proportion, size, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no technical substantive significance. Any structural modification, change in proportional relationship or adjustment of size, without affecting the efficacy and purpose that can be achieved by the present invention, should still fall within the scope of the technical content disclosed by the present invention.
[0057] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0058] In the description of the present invention, it should be understood that the terms "center", "height", "thickness", "up", "down", "vertical", "horizontal", "top", "bottom", "inside", "outside", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In the description of the present invention, unless otherwise specified, "plurality" means two or more.
[0059] In the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", and "fixed" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0060] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.
[0061] See also Figure 1 , Figure 1 The structure block diagram of the preoperative anesthesia visit system of one embodiment of the present invention includes: a medical history inquiry module 100, a physical examination module 200, a test report reading module 300, an ASA scoring module 400 and a data reporting module 500.
[0062] The medical history inquiry module 100 is used to ask a series of preset standardized questions to the first user, and obtain the medical history information of the first user based on the first user's answers; specifically, after the patient logs in to the system as the first user, the system will automatically enter the medical history inquiry module 100 and ask the patient a series of standardized questions, such as: "Do you have a history of allergies?", "Do you have underlying diseases such as hypertension, diabetes, etc.?", etc. It should be noted that the standardized questions asked to the first user can be set according to the doctor's requirements and the patient's actual situation, and no specific limitation is made here.
[0063] The physical examination module 200 is used to perform a physical examination on the first user and obtain the physical examination data of the first user, the physical examination data including mouth opening degree and neck mobility; in other embodiments, the physical examination data may also include other vital signs data of the patient, such as heart rate, blood pressure, etc., which are not specifically limited here.
[0064] The test report reading module 300 is used to read the test report of the first user, which records the medical test results of the first user. Specifically, the medical test results include chemical composition analysis of biological samples such as blood, urine, and feces, or microbiological and pathological tests. Considering that the medical history information obtained by the medical history inquiry module 100 through inquiry may not be completely correct, the first user may not know enough about his or her own health, resulting in errors in the medical history information that are inconsistent with the actual situation, therefore, obtaining the test report of the first user through the test report reading module 300 can obtain more accurate health data of the first user.
[0065] The ASA scoring module 400 is used to generate an ASA score for the first user based on the medical history information collected by the medical history inquiry module 100, the physical examination data collected by the physical examination module 200, the medical test results read by the test report reading module 300, and a trained and verified machine learning model; the ASA score is explained here: The ASA grading standard refers to the six levels into which the American Society of Anesthesiologists (ASA) classifies patients according to their physical condition and surgical risk before anesthesia.
[0066] The data reporting model 500 is used to integrate medical history information, physical examination data, medical test results and ASA scores to generate a comprehensive report, and transmit the comprehensive report to the second user. As the second user, the anesthesiologist receives the comprehensive report and can fully understand the patient's health status and risk assessment before surgery, so as to formulate a reasonable anesthesia plan.
[0067] The preoperative anesthesia visit system provided by the above embodiment realizes the automatic collection of the patient's medical history information and physical examination data through the medical history inquiry module 100 and the physical examination module 200, which reduces the doctor's workload and improves the visit efficiency. At the same time, the system's automatic collection avoids data omission compared to manual collection, and can ensure the comprehensiveness and accuracy of the preoperative evaluation. In addition, the test report reading module 300 reads the test report of the first user to obtain the medical test results of the first user, avoids incorrect acquisition of medical history information, and ensures that the acquired information is more comprehensive and accurate; the ASA score of the patient is automatically generated through the machine learning model, eliminating the influence of human subjective judgment, and ensuring the objectivity and consistency of the score. The data reporting module 500 integrates the patient's medical history information, physical examination data, ASA score and generates a comprehensive report. By consulting the comprehensive report, not only can the ASA score result be consulted, but also the data of various physical examinations and the results of medical examinations can be consulted, which can enable the anesthesiologist to fully understand the patient's health status and preoperative risks, and improve the quality and efficiency of preoperative preparations.
[0068] See also Figure 2 , a preoperative anesthesia visiting system according to another embodiment of the present invention is described in detail.
[0069] In some embodiments, the preoperative visit system provided by the present invention also includes an informed consent module 600, which is used to provide an electronic informed consent form for the first user to read, receive the first user's electronic signature and save the signed electronic informed consent form; the data reporting module 500 is also used to integrate the signed electronic informed consent form into the comprehensive report.
[0070] The existing preoperative visit process uses a paper-based informed consent form. The signing and archiving process of the paper-based informed consent form is complicated and prone to risks such as irregular signing, document loss or damage. It is also inconvenient to archive and review, which increases management difficulty and data security risks.
[0071] In the above embodiment, the informed consent module 600 is provided to provide an electronic informed consent form. The patient can read the detailed preoperative information and risk notification through the system. After reading, the patient can sign the electronic informed consent form through the electronic signature function. The signed electronic informed consent form is automatically archived, which simplifies the signing and management process of the informed consent form, avoids the risk of file loss and damage, and improves the convenience of signing and the security of management. The signed electronic informed consent form is integrated into a comprehensive report and sent to the anesthesiologist, which is more convenient to review. While ensuring the compliance and integrity of preoperative preparations, it reduces management difficulty and data security risks.
[0072] In some embodiments, the ASA scoring module 400 includes a data processing unit 410 and a machine learning model 420. The data processing unit 410 is used to extract key features from medical history information, physical examination data, and medical test reports, such as gender, age, past medical history, drug use, mouth opening, neck mobility, etc.; perform data cleaning on the extracted key features, process missing values and outliers, and ensure the integrity and accuracy of the data; perform normalization on numerical features and encoding on categorical features. Normalization is used to eliminate the impact of dimensions between different features, and feature encoding is used to convert categorical features into numerical features that can be understood by the machine learning model 420. It should be noted that feature encoding can use unique hot encoding or label encoding, which is not specifically limited here.
[0073] The machine learning model 420 is used to receive and use the data processed by the data processing unit 410 to predict and generate the ASA score of the first user. It should be noted that the machine learning model 420 can use a random forest (RandomForest) model or a gradient boosted decision tree (GBDT) model or a support vector machine (SVM) model, which is not specifically limited here. According to the experimental results, the random forest model performs best.
[0074] The preoperative anesthesia visiting system provided in the above embodiment generates an ASA score through the data processing unit 410 and the machine learning model 420, which reduces the influence of human subjective judgment and ensures the objectivity and consistency of the score.
[0075] In some embodiments, the medical history inquiry module 100 provided by the present invention includes a speech unit 110, a natural language processing unit 120, and a medical history database 130. The speech unit 110 is used to ask a series of preset standardized questions to the first user in the form of natural language, and record the natural language answers of the first user. The speech unit 110 realizes natural language communication with the patient. The natural language processing unit 120 is used to extract the medical history information of the first user based on the natural language answers of the first user, automatically extract the medical history information of the patient, and ensure the accuracy and comprehensiveness of the record. The medical history database 130 is used to store and manage the medical history information of the first user.
[0076] In the above embodiment, the speech unit 110 is combined with the natural language processing unit 120 to achieve natural language communication with the patient and automatically extract the patient's medical history information.
[0077] In some embodiments, the preoperative anesthesia visiting system provided by the present invention includes a camera 210, a sensor 220, a physical analysis unit 230 and a storage unit 240. The camera 210 is used to capture the maximum range of the first user's mouth opening; the sensor 220 is used to measure the range of movement of the first user's neck; the physical analysis unit 230 generates the physical examination data of the first user based on the data collected by the camera 210 and the sensor 220, without the need for a doctor to perform a physical examination on the patient and record the physical examination data; the storage unit 240 is used to store the physical examination data.
[0078] The preoperative anesthesia visit system provided in the above embodiment automatically obtains the physical examination data of the first user through the camera 210, the sensor 220 and the physical analysis unit 230. There is no need for the doctor to perform a physical examination on the patient and record the physical examination data, which reduces the doctor's workload, improves the visit efficiency, and avoids the omission of important physical examination data or inaccurate physical examination data recording, thereby ensuring the comprehensiveness and accuracy of the physical examination data recording.
[0079] In some embodiments, the informed consent module 600 provided by the present invention includes an electronic signature unit 610, a data encryption unit 620 and a cloud storage unit 630. The electronic signature unit 610 is used to provide an electronic informed consent for the first user to read and receive the electronic signature of the first user. The electronic signature method includes a biometric signature or a signature directly drawn on a touch screen device. Specifically, the biometric signature includes a fingerprint signature and a facial recognition signature. The informed consent module 600 combines different signing methods to improve the convenience and security of signing and management. The data encryption unit 620 is used to perform blockchain encryption on the signed electronic informed consent, and utilizes the decentralization and immutability of blockchain technology to ensure the integrity and security of system data. The cloud storage unit 630 is used to store the signed electronic informed consent and back it up regularly to prevent data loss and damage.
[0080] In some embodiments, the data reporting module 500 provided by the present invention includes: an integration unit 510, an encryption and compression unit 520 and a transmission unit 530. The integration unit 510 is used to integrate medical history information, physical examination data and ASA score, and generate a comprehensive report. The data format of the comprehensive report includes PDF, XML and JSON, and comprehensive reports in multiple formats are generated to ensure that the comprehensive report is compatible with different electronic medical record systems and platforms; the encryption and compression unit 520 is used to encrypt and / or compress the comprehensive report. Compression can reduce transmission time, and encryption can improve data security; the transmission unit 530 is used to transmit the comprehensive report to the second user through an encrypted channel. Transmission through an encrypted channel can ensure the confidentiality and integrity of the data during transmission.
[0081] In some embodiments, the medical history inquiry module 100 provided by the present invention further includes a text processing unit, which is used to receive text data input by a keyboard or written on a handwriting board, and extract the medical history information of the first user based on the text data. Specifically, the patient inputs medical history related information through the keyboard, and the text processing unit automatically analyzes the input data and extracts the medical history information, or the patient uses a handwriting board or a touch screen to handwrite and input medical history related information, and the text processing unit converts it into text for processing through handwriting recognition technology, automatically analyzes the converted text and extracts the medical history information. The text processing unit is compatible with a variety of text input methods to adapt to the usage habits and usage needs of different patients.
[0082] In some embodiments, the physical examination module 200 provided by the present invention further includes a wearable device, specifically, the wearable device includes a smart watch or a smart bracelet, which is used to monitor and record the physical examination data of the first user in real time, including heart rate, blood pressure, etc. In addition, in other embodiments, the physical examination module 200 may also include a portable ultrasound device, an electronic stethoscope, and other equipment to assist in physical examination and improve the convenience and accuracy of the examination.
[0083] In some embodiments, the machine learning model 420 in the improved preoperative anesthesia visit system of the present invention is also used to receive historical data in the electronic health record and laboratory test results as input data, enrich the data input of the scoring model, and improve the reliability of the scoring results.
[0084] In some embodiments, the ASA scoring module 400 provided by the present invention also includes: a model training unit and a model verification unit. The model training unit is used to train the machine learning model 420 using a historical data set, and optimize the hyperparameters of the learning model through cross-validation and grid search to ensure the robustness and generalization ability of the machine learning model 420; the model verification unit is used to evaluate the prediction performance of the machine learning model 420 after training using a verification set, and the evaluation indicators include accuracy, recall rate and F1 score.
[0085] In some embodiments, the ASA scoring module 400 provided by the present invention also includes a model updating unit and a performance monitoring unit. The model updating unit is used to regularly retrain the machine learning model 420 using a new data set to ensure the accuracy and effectiveness of the machine learning model 420; the performance monitoring unit is used to monitor the predictive performance of the machine learning model 420 in real time. If the performance is found to be degraded, the machine learning model 420 can be adjusted or retrained in time.
[0086] In some embodiments, the preoperative anesthesia visit system provided by the present invention also includes an identity recognition unit and an identity verification unit. The identity recognition unit is used to read the identity information of the first user based on the medical insurance card inserted by the first user, and to collect real-time images of the first user. Specifically, the patient needs to insert the medical insurance card when logging into the system. The system identifies the patient's identity by reading the information in the medical insurance card. The information in the medical insurance card includes the patient's name, ID number, medical insurance number, etc., to ensure the uniqueness and accuracy of the patient's identity; the identity verification unit is used to collect the facial information of the second user and / or read the information on the work ID card, and match it with the pre-stored identity information of the second user to verify the identity of the second user. The doctor When using the system, identity authentication is performed through face recognition technology. The system captures the doctor's facial image through the camera and matches it with the pre-stored doctor's facial data to ensure the uniqueness and accuracy of the doctor's identity. The doctor can also authenticate his identity by swiping his work ID card. The information in the work ID card includes the doctor's name, work number, department, etc. The system reads the information in the work ID card and matches it with the pre-stored identity information of the second user; in addition, the doctor's identity can be further confirmed by reading the information in the work ID card and matching it with the face recognition result. The dual verification method of face recognition and work ID card swiping ensures that the system can only be used by authorized doctors and avoids access by unauthorized personnel.
[0087] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.
Claims
1. A preoperative anesthesia visiting system, characterized in that: include: A medical history inquiry module, the medical history inquiry module is used to ask a series of preset standardized questions to the first user, and obtain the medical history information of the first user based on the first user's answers; A physical examination module, the physical examination module is used to perform a physical examination on the first user and obtain physical examination data of the first user, the physical examination data including mouth opening degree and neck mobility; A test report reading module, the test report reading module is used to read the test report of the first user, the test report records the medical test results of the first user; An ASA scoring module, the ASA scoring module is used to generate an ASA score for the first user based on the medical history information, the physical examination data, the medical test results, and a trained and verified machine learning model; A data reporting module, wherein the data reporting module is used to integrate the medical history information, the physical examination data and the ASA score to generate a comprehensive report, and transmit the comprehensive report to the second user.
2. The preoperative anesthesia visiting system according to claim 1, characterized in that: The preoperative anesthesia visiting system also includes: An informed consent module, the informed consent module is used to provide an electronic informed consent for the first user to read, receive the electronic signature of the first user, and save the signed electronic informed consent; The data reporting module is also used to integrate the signed electronic informed consent form into the comprehensive report.
3. The preoperative anesthesia visiting system according to claim 1, characterized in that: The ASA scoring module includes: A data processing unit, the data processing unit is used to extract key features from the medical history information, the physical examination data and the medical test report, and after processing missing values and abnormal values, normalize the numerical features and perform one-hot encoding or label encoding on the categorical features; wherein the key features include age, gender, previous medical history, drug use, mouth opening, and neck mobility; A machine learning model, wherein the machine learning model is used to receive the data processed by the data processing unit, make predictions and generate an ASA score for the first user; wherein the machine learning model includes a random forest model, a support vector machine model, and a gradient boosting decision tree model.
4. The preoperative anesthesia visiting system according to claim 1, characterized in that: The medical history inquiry module includes: A speech unit, the speech unit being used to ask a series of preset standardized questions to the first user in a natural language form and to record the natural language answers of the first user; a natural language processing unit, the natural language processing unit being configured to extract the medical history information of the first user based on the natural language answer of the first user; A medical history database, wherein the medical history database is used to store and manage the medical history information of the first user.
5. The preoperative anesthesia visiting system according to claim 1, characterized in that: The physical examination module comprises: A camera, the camera being used to capture the maximum range of the first user's mouth opening; a sensor, the sensor being used to measure a range of motion of the neck of the first user; A physical analysis unit, which generates physical examination data of the first user based on the data collected by the camera and the sensor; A storage unit, wherein the storage unit is used to store the physical examination data.
6. The preoperative anesthesia visiting system according to claim 2, characterized in that: The informed consent module includes: An electronic signature unit, the electronic signature unit is used to provide an electronic informed consent form for the first user to read, and receive the electronic signature of the first user, the electronic signature method includes a biometric signature or a signature directly drawn on a touch screen device; A data encryption unit, the data encryption unit is used to perform blockchain encryption on the signed electronic informed consent form; A cloud storage unit is used to store the signed electronic informed consent form and back it up regularly.
7. The preoperative visit system according to claim 1, characterized in that: The data reporting module comprises: An integration unit, the integration unit is used to integrate the medical history information, the physical examination data and the ASA score, and generate a comprehensive report, the data format of the comprehensive report includes PDF, XML and JSON; An encryption and compression unit, configured to encrypt and / or compress the comprehensive report; A transmission unit, wherein the transmission unit is used to transmit the comprehensive report to the second user through an encrypted channel.
8. The preoperative anesthesia visiting system according to claim 4, characterized in that: The medical history inquiry module also includes: A text processing unit is used to receive text data typed on a keyboard or written on a handwriting board, and extract the medical history information of the first user based on the text data.
9. The preoperative anesthesia visiting system according to claim 3, characterized in that: The ASA scoring module also includes: A model training unit, the model training unit is used to train the machine learning model using a historical data set, and optimize the hyperparameters of the machine learning model through cross-validation and grid search; A model verification unit, the model verification unit is used to evaluate the prediction performance of the machine learning model after being trained by the model training unit using a verification set, wherein the evaluation indicators include accuracy, recall and F1 score; A model updating unit, the model updating unit is used to periodically retrain the machine learning model using a new data set; A performance monitoring unit, wherein the performance monitoring unit is used to monitor the predictive performance of the machine learning model in real time.
10. The preoperative anesthesia visiting system according to claim 1, characterized in that: The preoperative anesthesia visiting system also includes: an identity recognition unit, the identity recognition unit being used to read the identity information of the first user based on the medical insurance card inserted by the first user, and to collect a real-time image of the first user; An identity verification unit, the identity verification unit is used to collect the facial information of the second user and / or read the information of the work license plate, and match it with the pre-stored identity information of the second user to verify the identity of the second user.
Citation Information
Cited By
Preoperative anesthesia risk assessment method and system based on electronic medical record information
CN119339954A
