Intravenous anesthesia aid decision-making method and device and electronic equipment thereof

Abstract

The invention provides an intravenous anesthesia aid decision-making method and device and electronic equipment, and relates to the technical field of medical information processing, and the method comprises the steps: obtaining the preoperative medical information of a patient; based on the preoperative medical information of the patient, making a preliminary intravenous anesthesia strategy in an auxiliary manner; acquiring intraoperative medical data of a patient through video monitoring equipment and an acceleration sensor mounted at a key part of the body of the patient; based on the intraoperative medical data of the patient, judging whether the patient is abnormal in the operation or not; when it is judged that abnormity exists in the patient during the operation based on the medical data of the patient during the operation, an intravenous anesthesia adjustment strategy is generated based on the medical information of the patient before the operation and the medical data of the patient during the operation, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the preliminary intravenous anesthesia strategy. By integrating the preoperative detailed medical information of the patient, the preliminary intravenous anesthesia strategy can be accurately assisted to be formulated, and the scientificity and individuation of the anesthesia scheme are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information processing, and in particular to an intravenous anesthesia decision-making assistance method, device and electronic equipment. Background Art

[0002] With the continuous advancement of modern medical technology, more and more examinations and treatment processes are beginning to pursue comfortable and painless diagnosis and treatment experiences, such as gastroenteroscopy, hysteroscopy, bronchoscopy, and ERCP surgery. Most of these diagnosis and treatment methods rely on intravenous anesthesia technology to ensure that patients remain painless and relaxed throughout the diagnosis and treatment process, thereby improving diagnosis and treatment efficiency and patient satisfaction. This type of diagnosis and treatment activities are usually characterized by "short, frequent, and fast", that is, short diagnosis and treatment time, high frequency, and fast operation, which places extremely high demands on the work efficiency and accuracy of anesthesiologists.

[0003] However, in actual work, anesthesiologists face tremendous work pressure. They not only need to make accurate medical decisions in a short period of time to ensure the safety of patients, but also need to complete tedious paperwork. This makes it difficult for anesthesiologists to conduct a comprehensive and detailed assessment of the health status of each patient, increasing medical risks. At the same time, due to the compactness of the diagnosis and treatment process, the recording of various types of information is prone to omissions or errors, further exacerbating the uncertainty of medical safety.

[0004] Therefore, an intravenous anesthesia decision-making assistance method, device and electronic equipment are proposed. Summary of the invention

[0005] This manual provides an intravenous anesthesia decision-making assistance method, device and electronic equipment. By integrating the patient's detailed preoperative medical information, it can accurately assist in formulating a preliminary intravenous anesthesia strategy to ensure the scientific nature and personalization of the anesthesia plan.

[0006] This manual provides a method for assisting decision-making in intravenous anesthesia, including:

[0007] Obtaining patients’ preoperative medical information;

[0008] Assist in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information;

[0009] Obtain the patient's intraoperative medical data through video monitoring equipment and acceleration sensors installed on key parts of the patient's body;

[0010] Determining whether there is any abnormality during the patient's operation based on the patient's intraoperative medical data;

[0011] When it is determined that abnormalities occur during the patient's operation based on the patient's intraoperative medical data, an intravenous anesthesia adjustment strategy is generated based on the patient's preoperative medical information and the patient's intraoperative medical data, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the initial intravenous anesthesia strategy.

[0012] Optionally, obtaining the patient's preoperative medical information includes:

[0013] The voice collection equipment is used to collect the conversation data between doctors and patients in the examination room;

[0014] Preprocessing the condition conversation data, and recognizing the preprocessed condition conversation data through a deep neural network model to obtain a condition conversation text;

[0015] The key information of the medical conversation text is annotated through a natural language processing model combined with a medical terminology library, and the annotated key information is screened and sorted to obtain the patient's preoperative medical information.

[0016] Optionally, the assisting in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information includes:

[0017] The patient's preoperative medical information includes the patient's existing disease information;

[0018] The type of anesthetic drug, anesthetic dosage and additional medication interval are set based on the patient's existing disease information.

[0019] Optionally, judging whether there is an abnormality during the operation of the patient based on the intraoperative medical data of the patient includes:

[0020] The intraoperative medical data of the patient includes an intraoperative facial image of the patient;

[0021] Preprocessing the intraoperative facial image of the patient, and analyzing the preprocessed intraoperative facial image of the patient to extract key feature point information of the patient's face;

[0022] The anesthesia depth judgment model is used to judge whether the key feature point information on the patient's face shows a painful expression.

[0023] Optionally, judging whether there is an abnormality during the operation of the patient based on the intraoperative medical data of the patient further includes:

[0024] The intraoperative medical data of the patient includes intraoperative body movement data of the patient;

[0025] Preprocessing the intraoperative body motion data of the patient, and analyzing the preprocessed intraoperative body motion data of the patient to extract body motion characteristic parameters of the patient;

[0026] The body movement characteristic parameters of the anesthesia depth judgment model are used to determine whether the patient's body movement characteristic parameters show abnormal body movement.

[0027] Optionally, judging whether there is an abnormality during the operation of the patient based on the intraoperative medical data of the patient further includes:

[0028] The intraoperative medical data of the patient includes intraoperative vital signs data of the patient;

[0029] The patient's intraoperative vital sign data are compared with vital sign parameter standards to determine whether the patient's intraoperative vital sign data fluctuates abnormally.

[0030] Optionally, when it is determined that an abnormality exists during the operation of the patient based on the intraoperative medical data of the patient, an intravenous anesthesia adjustment strategy is generated based on the preoperative medical information of the patient and the intraoperative medical data of the patient, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the preliminary intravenous anesthesia strategy, including:

[0031] The patient's postoperative early warning strategy is obtained by combining the patient's preoperative medical information, the patient's intraoperative medical information, the initial intravenous anesthesia strategy and the adjusted intravenous anesthesia strategy, and the patient's postoperative early warning strategy is pushed to medical staff to assist in formulating the patient's rehabilitation strategy.

[0032] This specification provides an intravenous anesthesia decision-making support device, including:

[0033] Preoperative acquisition module, used to obtain the patient's preoperative medical information;

[0034] A preliminary formulation module, used to assist in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information;

[0035] The intraoperative acquisition module is used to obtain the patient's intraoperative medical data through video monitoring equipment and acceleration sensors installed on key parts of the patient's body;

[0036] An abnormality judgment module, used for judging whether there is abnormality during the patient's operation based on the patient's intraoperative medical data;

[0037] The auxiliary adjustment module is used to generate an intravenous anesthesia adjustment strategy based on the patient's preoperative medical information and the patient's intraoperative medical data when it is determined that abnormalities exist during the patient's operation based on the patient's intraoperative medical data, and immediately push the intravenous anesthesia adjustment strategy to medical staff to assist in adjusting the preliminary intravenous anesthesia strategy.

[0038] Optionally, the preoperative acquisition module includes:

[0039] The voice collection equipment is used to collect the conversation data between doctors and patients in the examination room;

[0040] Preprocessing the condition conversation data, and recognizing the preprocessed condition conversation data through a deep neural network model to obtain a condition conversation text;

[0041] The key information of the medical conversation text is annotated through a natural language processing model combined with a medical terminology library, and the annotated key information is screened and sorted to obtain the patient's preoperative medical information.

[0042] Optionally, the preliminary formulation module includes:

[0043] The patient's preoperative medical information includes the patient's existing disease information;

[0044] The type of anesthetic drug, anesthetic dosage and additional medication interval are set based on the patient's existing disease information.

[0045] Optionally, the abnormality judgment module includes:

[0046] The intraoperative medical data of the patient includes an intraoperative facial image of the patient;

[0047] Preprocessing the intraoperative facial image of the patient, and analyzing the preprocessed intraoperative facial image of the patient to extract key feature point information of the patient's face;

[0048] The anesthesia depth judgment model is used to judge whether the key feature point information on the patient's face shows a painful expression.

[0049] Optionally, the abnormality judgment module further includes:

[0050] The intraoperative medical data of the patient includes intraoperative body movement data of the patient;

[0051] Preprocessing the intraoperative body motion data of the patient, and analyzing the preprocessed intraoperative body motion data of the patient to extract body motion characteristic parameters of the patient;

[0052] The body movement characteristic parameters of the anesthesia depth judgment model are used to determine whether the patient's body movement characteristic parameters show abnormal body movement.

[0053] Optionally, the abnormality judgment module further includes:

[0054] The intraoperative medical data of the patient includes intraoperative vital signs data of the patient;

[0055] The patient's intraoperative vital sign data are compared with vital sign parameter standards to determine whether the patient's intraoperative vital sign data fluctuates abnormally.

[0056] Optionally, after the auxiliary adjustment module, the following steps are included:

[0057] The patient's postoperative early warning strategy is obtained by combining the patient's preoperative medical information, the patient's intraoperative medical information, the initial intravenous anesthesia strategy and the adjusted intravenous anesthesia strategy, and the patient's postoperative early warning strategy is pushed to medical staff to assist in formulating the patient's rehabilitation strategy.

[0058] This specification also provides an electronic device, wherein the electronic device includes:

[0059] processor; and,

[0060] A memory storing computer executable instructions, which when executed cause the processor to perform any of the above methods.

[0061] The present specification also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, any of the above methods is implemented.

[0062] In the present invention, by integrating the patient's detailed preoperative medical information, it is possible to accurately assist in formulating a preliminary intravenous anesthesia strategy to ensure the scientificity and personalization of the anesthesia plan. At the same time, during the operation, the patient's medical data, including facial images, body movement data, and vital signs data, are obtained in real time through video monitoring equipment and acceleration sensors, so that it can be quickly determined whether the patient has an abnormal reaction. Once an abnormality is found, the system can immediately generate an adjustment strategy based on preoperative and intraoperative information, and push it to medical staff in real time so that they can respond quickly and adjust the anesthesia plan to ensure the safety of the patient and the smooth progress of the operation. In addition, the method can also combine preoperative and intraoperative information and the adjustment of anesthesia strategies to provide patients with postoperative early warning strategies, assist medical staff in formulating rehabilitation plans, and thus improve the quality and efficiency of overall medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments 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 these drawings without creative work.

[0064] Figure 1 A schematic diagram of the principle of an intravenous anesthesia decision-making assistance method provided in an embodiment of this specification;

[0065] Figure 2 A schematic diagram of the structure of an intravenous anesthesia decision support device provided in an embodiment of this specification;

[0066] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0067] Figure 4 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of the present specification. DETAILED DESCRIPTION

[0068] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0069] The following is combined with Figure 1-4 The exemplary embodiments of the present invention are described more fully. However, the exemplary embodiments can be implemented in various forms, and it should not be understood that the present invention is limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments can make the present invention more comprehensive and complete, and it is more convenient to fully convey the inventive concept to those skilled in the art. The same reference numerals in the figures represent the same or similar elements, components or parts, and thus their repeated description will be omitted.

[0070] Under the premise of being consistent with the technical concept of the present invention, the features, structures, characteristics or other details described in a specific embodiment do not exclude that they can be combined in one or more other embodiments in a suitable manner.

[0071] In the description of specific embodiments, the features, structures, characteristics or other details described in the present invention are intended to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics or other details.

[0072] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0073] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0074] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0075] Figure 1 A schematic diagram of the principle of an intravenous anesthesia decision-making assistance method provided in an embodiment of this specification, the method may include:

[0076] S110: Obtaining the patient's preoperative medical information;

[0077] In the specific implementation of this specification, the patient's preoperative medical information is fully obtained, including but not limited to the patient's age, gender, weight, past medical history, allergy history, current health status, laboratory test results (such as blood routine, liver and kidney function, etc.), electrocardiogram data, and scheduled surgical methods, etc. This information is collected through an electronic medical record system or manually input to provide basic data support for the subsequent formulation of anesthesia plans.

[0078] Optionally, the S110 includes:

[0079] The voice collection equipment is used to collect the conversation data between doctors and patients in the examination room;

[0080] Preprocessing the condition conversation data, and recognizing the preprocessed condition conversation data through a deep neural network model to obtain a condition conversation text;

[0081] The key information of the medical conversation text is annotated through a natural language processing model combined with a medical terminology library, and the annotated key information is screened and sorted to obtain the patient's preoperative medical information.

[0082] In the specific implementation of this specification, a highly sensitive voice acquisition device is deployed in the examination room, which can clearly and accurately capture the medical condition dialogue between the doctor and the patient, providing an original and rich data basis for subsequent information processing. The voice acquisition device is designed to be hidden and not affect the naturalness of the doctor-patient communication, ensuring the authenticity and integrity of the dialogue content. The collected medical condition dialogue data then enters the preprocessing stage, including removing noise, enhancing voice clarity, and segmenting continuous voice signals into independent sentences or word units for subsequent processing and analysis. The preprocessing technology ensures the purity and consistency of the data format, laying a solid foundation for the subsequent deep neural network model recognition. The preprocessed medical condition dialogue data is recognized using a deep neural network model. This model has been trained with a large amount of medical dialogue data, and can accurately convert voice signals into text form, that is, medical condition dialogue text, and capture subtle changes and features in the voice, thereby significantly improving the accuracy and efficiency of recognition. After obtaining the medical condition dialogue text, the natural language processing model is used in combination with the medical terminology library to annotate key information, and key information related to the patient's condition, medical history, allergy history, medication, etc. is identified. The marked key information needs to be further screened and sorted, including merging duplicate information, removing irrelevant details, and organizing the information according to a specific logical structure to facilitate subsequent medical decision-making and record-keeping.

[0083] The preoperative medical information obtained from patients provides valuable reference for doctors to formulate treatment plans, assess surgical risks, and perform postoperative care. It also lays a solid foundation for the information management of medical institutions and the establishment of patient health records.

[0084] Specifically, a comprehensive preoperative medical knowledge base is constructed. This knowledge base not only contains various common preoperative medical terms, such as "hypertension", "diabetes", "heart disease", "hepatitis", etc., but also covers a wide range of common medical history expressions, such as "smoking history", "drinking history", "eating habits" and other lifestyle-related, as well as key information in family medical history. Each term and expression has a clear definition and annotation in the knowledge base, such as the name of the disease corresponds to its professional medical explanation, and the vocabulary related to lifestyle is related to its possible health impact. In addition, the knowledge base also includes common time expressions related to these terms, such as "X-year medical history" and "recent onset", so that the information of the time dimension can be accurately captured in the subsequent information extraction. For the text content converted by speech recognition technology, natural language processing technology (NLP) is used for in-depth analysis. NLP technology can identify and understand the semantics and contextual relationships in the text, so as to achieve effective extraction of key information. Combined with the preoperative medical knowledge base constructed above, the NLP system can intelligently match and annotate the medical terms and medical history expressions in the text. For example, when the system recognizes that the text contains a statement such as "the patient has suffered from hypertension for 5 years", the NLP system can not only accurately mark the key medical history information of "hypertension", but also accurately extract and mark the time information related to the medical history of "5 years" through the time expression rules in the knowledge base. This improves the accuracy and efficiency of preoperative patient information extraction, provides doctors with more comprehensive and accurate patient medical history data, helps doctors more accurately assess patients' surgical risks, and develop more personalized preoperative preparation and postoperative care plans. At the same time, this also provides strong support for the information management of medical institutions and the establishment of patient health records.

[0085] S120: Assisting in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information;

[0086] Optionally, the S120 includes:

[0087] The patient's preoperative medical information includes the patient's existing disease information;

[0088] The type of anesthetic drug, anesthetic dosage and additional medication interval are set based on the patient's existing disease information.

[0089] In the specific implementation of this specification, the patient's preoperative medical information includes but is not limited to the chronic diseases (such as hypertension, diabetes, heart disease, etc.) that the patient currently suffers from or has suffered from, acute diseases (such as infection, trauma, etc.), and any disease state that may affect the anesthetic effect or increase the risk of surgery (such as respiratory diseases, liver diseases, etc.). This information is collected by detailed inquiry of medical history, consultation of medical records, and necessary medical examinations, and is reviewed and confirmed by professional doctors to ensure its accuracy and completeness. Based on a detailed analysis of the patient's existing disease information, a personalized anesthetic drug category is set. Different disease states may have different reactions to specific anesthetic drugs, so it is crucial to choose the right anesthetic drug. For example, for patients with coronary heart disease, it is necessary to choose anesthetic drugs that have less impact on the cardiovascular system; and for patients with renal insufficiency, the effect of anesthetic drugs on renal function needs to be considered. At the same time, the size of the anesthetic dose is directly related to the patient's depth of anesthesia and safety. According to factors such as the patient's weight, age, disease state, and type of surgery, the anesthetic dose that can ensure the smooth progress of the operation and minimize the risk is calculated, and the appropriate administration speed is set to avoid circulatory instability caused by too fast administration speed. In addition, the patient's basic information and disease information also affect the setting of additional medication intervals and additional dosages.

[0090] S130: Obtaining the patient's intraoperative medical data through video monitoring equipment and acceleration sensors installed on key parts of the patient's body;

[0091] In the specific implementation of this specification, the body motion monitoring technology mainly relies on acceleration sensors. These precision sensors are cleverly placed in multiple key parts of the patient's body, including but not limited to the wrists, ankles and torso. The selection of these locations is intended to maximize the capture of any slight movements of the patient's body. When the patient moves during surgery or treatment, the acceleration sensor can quickly and keenly detect the acceleration change signals caused by these movements. Subsequently, these signals are converted into electrical signals and further converted into digital signals through an analog-to-digital converter for subsequent data processing. In this process, advanced filtering technology is used to pre-process the raw data to effectively remove possible noise interference and ensure the accuracy and reliability of the data.

[0092] Facial expression monitoring technology combines the advantages of high-definition cameras and image recognition technology. The high-definition camera is installed in a position where it can capture the patient's face clearly and without obstruction to ensure the integrity and accuracy of the field of view. The camera continuously captures the patient's facial images at a certain frame rate (for example, 30 frames per second or higher), providing a rich data basis for subsequent expression analysis. During the image data collection process, meticulous preprocessing is also carried out, including adjusting key parameters such as image brightness and contrast to ensure the clarity and stability of image quality. These preprocessing steps are crucial for subsequent feature extraction and expression recognition, and they can significantly improve the accuracy and efficiency of recognition.

[0093] S140: judging whether there is any abnormality during the operation of the patient based on the intraoperative medical data of the patient;

[0094] Optionally, the S140 includes:

[0095] The intraoperative medical data of the patient includes an intraoperative facial image of the patient;

[0096] Preprocessing the intraoperative facial image of the patient, and analyzing the preprocessed intraoperative facial image of the patient to extract key feature point information of the patient's face;

[0097] The anesthesia depth judgment model is used to judge whether the key feature point information on the patient's face shows a painful expression.

[0098] In the specific implementation of this specification, the collected facial images are analyzed using image processing technology to extract features related to painful expressions. This includes the movement features of facial muscles such as frowning, closed eyelids, and drooping mouth corners. By identifying the position changes of key facial feature points, these expression features are quantified to determine whether the patient has a painful expression.

[0099] Optionally, the S140 further includes:

[0100] The intraoperative medical data of the patient includes intraoperative body movement data of the patient;

[0101] Preprocessing the intraoperative body motion data of the patient, and analyzing the preprocessed intraoperative body motion data of the patient to extract body motion characteristic parameters of the patient;

[0102] The body movement characteristic parameters of the anesthesia depth judgment model are used to determine whether the patient's body movement characteristic parameters show abnormal body movement.

[0103] In the specific implementation of this specification, the pre-processed body movement data is deeply analyzed to extract key characteristic parameters, such as the amplitude, frequency, and duration of the body movement. When the patient is monitored to have large and frequent body movements, this may mean that the current anesthesia depth is not enough and the patient still feels some pain or discomfort. On the contrary, if only occasional small body movements are observed, it may be a normal physiological reflex. At this time, it is necessary to further analyze factors such as its frequency and duration to make a more accurate judgment.

[0104] Anesthesia depth judgment models include support vector machines (SVM), artificial neural networks (ANN), etc., which can output judgment results about anesthesia depth based on input feature data.

[0105] Optionally, the S140 further includes:

[0106] The intraoperative medical data of the patient includes intraoperative vital signs data of the patient;

[0107] The patient's intraoperative vital sign data are compared with vital sign parameter standards to determine whether the patient's intraoperative vital sign data fluctuates abnormally.

[0108] In a specific implementation of this specification, a professional multi-parameter monitor is used to continuously and accurately monitor the patient's heart rate, blood pressure, blood oxygen saturation and other key vital signs, and the patient's vital signs data is instantly transmitted to a terminal device that can be easily accessed by medical staff, such as a central monitoring station or a mobile anesthesia workstation, to ensure the timeliness and availability of the information.

[0109] In order to effectively evaluate the changes in patients' vital signs, scientific and reasonable change degree assessment indicators are set for each key parameter. Specifically, for heart rate, it is set within a period of time after administration (for example, 1 minute to 10 minutes). If the heart rate increases or decreases by more than 10% compared with the baseline value before administration, it is considered that the heart rate has changed significantly, which may indicate the effect of the drug or the progression of the disease. For blood pressure, pay attention to the fluctuation range of systolic and diastolic blood pressure, and set systolic blood pressure fluctuations exceeding 20 mmHg or diastolic blood pressure fluctuations exceeding 10 mmHg as the standard for significant changes, which helps to detect potential hemodynamic instability in a timely manner. As for blood oxygen saturation, when its value is monitored to drop below 95%, it is considered to have changed significantly, which may mean that the patient's oxygenation function is impaired and immediate intervention is required.

[0110] After the first dose, a reasonable monitoring period is set according to the drug's onset time and expected duration of action, and the change trajectory of each vital sign parameter is continuously recorded. This includes recording the initial value before administration, the maximum and minimum values ​​observed during the monitoring period, and the final stable value. By recording these key data points in detail, the degree of impact of the drug on the patient's vital signs can be evaluated, providing strong data support for timely adjustment of treatment plans or emergency medical measures. This systematic monitoring and recording method not only improves the efficiency and quality of anesthesia work, but also provides a solid guarantee for patient safety.

[0111] S150: When it is determined that abnormalities occur during the patient's operation based on the patient's intraoperative medical data, an intravenous anesthesia adjustment strategy is generated based on the patient's preoperative medical information and the patient's intraoperative medical data, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the initial intravenous anesthesia strategy.

[0112] In a specific implementation of the present specification, multi-dimensional data such as the standardized time of disappearance of body movement, the degree of change of vital signs (including fluctuations in key indicators such as heart rate, blood pressure, and blood oxygen saturation), the patient's underlying disease condition, and the last medication status are used as input variables and input into the decision-making model to predict the appropriate subsequent dosage and interval time.

[0113] Specifically, for patients with certain underlying diseases such as heart disease, the decision model will automatically recommend a lower initial dose based on their medical history and current health status, and suggest a slower dosing rate, while shortening the monitoring interval of vital signs to ensure safety. During subsequent treatment, if the decision model predicts that the patient's body movement disappears quickly or vital signs change significantly, such as abnormal fluctuations in heart rate, a sharp drop in blood pressure, or a significant decrease in blood oxygen saturation, the treatment strategy will be automatically adjusted, which may include reducing subsequent doses, extending dosing intervals, or taking other necessary medical interventions.

[0114] The decision criteria also take into full account individual differences in patients and differences in drug metabolism and kinetics, ensuring that the treatment plan is both in line with scientific principles and reflects humane care. For example, for the elderly or patients with impaired liver and kidney function, the system may recommend a more cautious dosing regimen to avoid drug accumulation and adverse reactions.

[0115] Optionally, when it is determined that an abnormality exists during the operation of the patient based on the intraoperative medical data of the patient, an intravenous anesthesia adjustment strategy is generated based on the preoperative medical information of the patient and the intraoperative medical data of the patient, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the preliminary intravenous anesthesia strategy, including:

[0116] The patient's postoperative early warning strategy is obtained by combining the patient's preoperative medical information, the patient's intraoperative medical information, the initial intravenous anesthesia strategy and the adjusted intravenous anesthesia strategy, and the patient's postoperative early warning strategy is pushed to medical staff to assist in formulating the patient's rehabilitation strategy.

[0117] In the specific implementation of this specification, the patient's comprehensive medical information includes his detailed health status before the operation, the medical data updated in real time during the operation, the intravenous anesthesia strategy initially formulated according to the operation progress and the patient's response, and the anesthesia strategy adjustment made according to actual needs during the operation. This information together forms the basis for the formulation of the patient's postoperative early warning strategy.

[0118] Specifically, preoperative medical information covers the patient's age, gender, underlying diseases (such as cardiovascular disease, respiratory system disease, etc.), allergy history, previous surgical history and anesthesia history, etc. This information is crucial for assessing the patient's tolerance to anesthesia and predicting possible complications after surgery. Intraoperative medical information includes the type of surgery, operation time, blood loss, blood transfusion, real-time monitoring data of vital signs (such as heart rate, blood pressure, blood oxygen saturation), and the type, dosage and use time of anesthetic drugs. These data provide a direct basis for assessing the physiological impact of surgery on patients and adjusting anesthesia strategies.

[0119] The initial intravenous anesthesia strategy is formulated based on the patient's preoperative evaluation and surgical needs, including the type, dosage, administration method, and maintenance of anesthesia depth of anesthetic drugs. However, due to various unforeseen situations that may occur during surgery, such as drastic fluctuations in the patient's vital signs, prolonged surgery time, or increased surgical difficulty, in actual operations, the initial anesthesia strategy will be adjusted as necessary based on real-time feedback from intraoperative medical information to ensure the safety of the patient and the smooth progress of the operation.

[0120] Based on the above information, personalized postoperative early warning strategies are automatically generated by comprehensively considering the individual differences of patients, the degree of surgical trauma, the metabolic characteristics of anesthetic drugs, and various risk factors that may occur during the operation. These strategies include the prediction of possible complications (such as lung infection, cardiovascular events, postoperative pain, etc.) after surgery, as well as early warning of abnormal changes in vital signs that may occur during postoperative rehabilitation. These early warning strategies are promptly pushed to the medical staff responsible for the postoperative rehabilitation of patients so that they can develop more scientific and reasonable rehabilitation plans based on the specific conditions of the patients. This will not only help reduce the incidence of postoperative complications in patients and improve the quality of rehabilitation, but also optimize the allocation of medical resources and improve the overall level of medical services.

[0121] In the present invention, by integrating the patient's detailed preoperative medical information, it is possible to accurately assist in formulating a preliminary intravenous anesthesia strategy to ensure the scientificity and personalization of the anesthesia plan. At the same time, during the operation, the patient's medical data, including facial images, body movement data, and vital signs data, are obtained in real time through video monitoring equipment and acceleration sensors, so that it can be quickly determined whether the patient has an abnormal reaction. Once an abnormality is found, the system can immediately generate an adjustment strategy based on preoperative and intraoperative information, and push it to medical staff in real time so that they can respond quickly and adjust the anesthesia plan to ensure the safety of the patient and the smooth progress of the operation. In addition, the method can also combine preoperative and intraoperative information and the adjustment of anesthesia strategies to provide patients with postoperative early warning strategies, assist medical staff in formulating rehabilitation plans, and thus improve the quality and efficiency of overall medical services.

[0122] Figure 2 A schematic diagram of the principle of an intravenous anesthesia decision support device provided in an embodiment of this specification, the device may include:

[0123] The preoperative acquisition module 10 is used to obtain the patient's preoperative medical information;

[0124] A preliminary formulation module 20, for assisting in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information;

[0125] An intraoperative acquisition module 30 is used to acquire the intraoperative medical data of the patient through video monitoring equipment and acceleration sensors installed at key parts of the patient's body;

[0126] An abnormality judgment module 40 is used to judge whether there is an abnormality during the patient's operation based on the patient's intraoperative medical data;

[0127] The auxiliary adjustment module 50 is used to generate an intravenous anesthesia adjustment strategy based on the patient's preoperative medical information and the patient's intraoperative medical data when it is determined that abnormalities exist during the patient's operation based on the patient's intraoperative medical data, and immediately push the intravenous anesthesia adjustment strategy to medical staff to assist in adjusting the initial intravenous anesthesia strategy.

[0128] Optionally, the preoperative acquisition module 10 includes:

[0129] The voice collection equipment is used to collect the conversation data between doctors and patients in the examination room;

[0130] Preprocessing the condition conversation data, and recognizing the preprocessed condition conversation data through a deep neural network model to obtain a condition conversation text;

[0131] The key information of the medical conversation text is annotated through a natural language processing model combined with a medical terminology library, and the annotated key information is screened and sorted to obtain the patient's preoperative medical information.

[0132] Optionally, the preliminary formulation module 20 includes:

[0133] The patient's preoperative medical information includes the patient's existing disease information;

[0134] The type of anesthetic drug, anesthetic dosage and additional medication interval are set based on the patient's existing disease information.

[0135] Optionally, the abnormality judgment module 40 includes:

[0136] The intraoperative medical data of the patient includes an intraoperative facial image of the patient;

[0137] Preprocessing the intraoperative facial image of the patient, and analyzing the preprocessed intraoperative facial image of the patient to extract key feature point information of the patient's face;

[0138] The anesthesia depth judgment model is used to judge whether the key feature point information on the patient's face shows a painful expression.

[0139] Optionally, the abnormality judgment module 40 further includes:

[0140] The intraoperative medical data of the patient includes intraoperative body movement data of the patient;

[0141] Preprocessing the intraoperative body motion data of the patient, and analyzing the preprocessed intraoperative body motion data of the patient to extract body motion characteristic parameters of the patient;

[0142] The body movement characteristic parameters of the anesthesia depth judgment model are used to determine whether the patient's body movement characteristic parameters show abnormal body movement.

[0143] Optionally, the abnormality judgment module 40 further includes:

[0144] The intraoperative medical data of the patient includes intraoperative vital signs data of the patient;

[0145] The patient's intraoperative vital sign data are compared with vital sign parameter standards to determine whether the patient's intraoperative vital sign data fluctuates abnormally.

[0146] Optionally, after the auxiliary adjustment module 50, the following steps are included:

[0147] The patient's postoperative early warning strategy is obtained by combining the patient's preoperative medical information, the patient's intraoperative medical information, the initial intravenous anesthesia strategy and the adjusted intravenous anesthesia strategy, and the patient's postoperative early warning strategy is pushed to medical staff to assist in formulating the patient's rehabilitation strategy.

[0148] The functions of the device in the embodiment of the present invention have been described in the above method embodiment, so for details not provided in the description of this embodiment, please refer to the relevant description in the above embodiment, and no further description will be given here.

[0149] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0150] The following describes an electronic device embodiment of the present invention, which can be regarded as a specific physical implementation of the method and device embodiments of the present invention. The details described in the electronic device embodiment of the present invention should be regarded as a supplement to the above method or device embodiments; details not disclosed in the electronic device embodiment of the present invention can be implemented with reference to the above method or device embodiments.

[0151] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. Figure 3 The electronic device 300 according to the embodiment of the present invention is described. Figure 3 The electronic device 300 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0152] like Figure 3 As shown, the electronic device 300 is in the form of a general computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different system components (including the storage unit 320 and the processing unit 310), a display unit 340, etc.

[0153] The storage unit stores program codes, which can be executed by the processing unit 310, so that the processing unit 310 performs the steps according to various exemplary embodiments of the present invention described in the above processing method section of this specification. For example, the processing unit 310 can perform the following steps: Figure 1 Steps shown.

[0154] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache memory unit 3202 , and may further include a read-only memory unit (ROM) 3203 .

[0155] The storage unit 320 may also include a program / utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0156] Bus 330 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0157] The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable viewers to interact with the electronic device 300, and / or any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 350. Furthermore, the electronic device 300 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 through the bus 330. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0158] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the exemplary embodiments described in the present invention can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation method of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.) or on a network, including a number of instructions to enable a computing device (which can be a personal computer, server, or network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: Figure 1 The method shown.

[0159] Figure 4 A schematic diagram of a computer-readable medium provided in accordance with an embodiment of the present specification.

[0160] accomplish Figure 1The computer program of the method shown can be stored on one or more computer readable media. The computer readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0161] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0162] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the viewer computing device, partially on the viewer device, as a stand-alone software package, partially on the viewer computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the viewer computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0163] In summary, the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0164] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0165] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0166] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for assisting decision making for intravenous anesthesia, characterized in that: include: Obtaining patients’ preoperative medical information; Assist in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information; Obtain the patient's intraoperative medical data through video monitoring equipment and acceleration sensors installed on key parts of the patient's body; Determining whether there is any abnormality during the patient's operation based on the patient's intraoperative medical data; When it is determined that abnormalities occur during the patient's operation based on the patient's intraoperative medical data, an intravenous anesthesia adjustment strategy is generated based on the patient's preoperative medical information and the patient's intraoperative medical data, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the initial intravenous anesthesia strategy.

2. The intravenous anesthesia decision-making assistance method according to claim 1, characterized in that: The obtaining of the patient's preoperative medical information includes: The voice collection equipment is used to collect the conversation data between doctors and patients in the examination room; Preprocessing the condition dialogue data, and recognizing the preprocessed condition dialogue data through a deep neural network model to obtain a condition dialogue text; The key information of the medical conversation text is annotated through a natural language processing model combined with a medical terminology library, and the annotated key information is screened and sorted to obtain the patient's preoperative medical information.

3. The intravenous anesthesia decision-making assistance method according to claim 2, characterized in that: The auxiliary formulation of a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information includes: The patient's preoperative medical information includes the patient's existing disease information; The type of anesthetic drug, anesthetic dosage and additional medication interval are set based on the patient's existing disease information.

4. The intravenous anesthesia decision-making assistance method according to claim 3, characterized in that: The determining whether there is an abnormality during the operation of the patient based on the intraoperative medical data of the patient includes: The intraoperative medical data of the patient includes an intraoperative facial image of the patient; Preprocessing the intraoperative facial image of the patient, and analyzing the preprocessed intraoperative facial image of the patient to extract key feature point information of the patient's face; The anesthesia depth judgment model is used to judge whether the key feature point information on the patient's face shows a painful expression.

5. The intravenous anesthesia decision-making assistance method according to claim 4, characterized in that: The determining whether there is an abnormality during the operation of the patient based on the intraoperative medical data of the patient further includes: The intraoperative medical data of the patient includes intraoperative body movement data of the patient; Preprocessing the intraoperative body motion data of the patient, and analyzing the preprocessed intraoperative body motion data of the patient to extract body motion characteristic parameters of the patient; The body movement characteristic parameters of the anesthesia depth judgment model are used to determine whether the patient's body movement characteristic parameters show abnormal body movement.

6. The intravenous anesthesia decision-making assistance method according to claim 5, characterized in that: The determining whether there is an abnormality during the operation of the patient based on the intraoperative medical data of the patient further includes: The intraoperative medical data of the patient includes intraoperative vital signs data of the patient; The patient's intraoperative vital sign data are compared with vital sign parameter standards to determine whether the patient's intraoperative vital sign data fluctuates abnormally.

7. The intravenous anesthesia decision-making assistance method according to claim 6, characterized in that: When it is determined based on the intraoperative medical data of the patient that an abnormality exists during the operation of the patient, an intravenous anesthesia adjustment strategy is generated based on the preoperative medical information of the patient and the intraoperative medical data of the patient, and the intravenous anesthesia adjustment strategy is immediately pushed to medical staff to assist in adjusting the preliminary intravenous anesthesia strategy, including: The patient's postoperative early warning strategy is obtained by combining the patient's preoperative medical information, the patient's intraoperative medical information, the initial intravenous anesthesia strategy and the adjusted intravenous anesthesia strategy, and the patient's postoperative early warning strategy is pushed to medical staff to assist in formulating the patient's rehabilitation strategy.

8. An intravenous anesthesia decision-making support device, characterized in that: include: Preoperative acquisition module, used to obtain the patient's preoperative medical information; A preliminary formulation module, used to assist in formulating a preliminary intravenous anesthesia strategy based on the patient's preoperative medical information; The intraoperative acquisition module is used to obtain the patient's intraoperative medical data through video monitoring equipment and acceleration sensors installed on key parts of the patient's body; An abnormality judgment module, used for judging whether there is an abnormality during the patient's operation based on the patient's intraoperative medical data; The auxiliary adjustment module is used to generate an intravenous anesthesia adjustment strategy based on the patient's preoperative medical information and the patient's intraoperative medical data when it is determined that abnormalities exist during the patient's operation based on the patient's intraoperative medical data, and immediately push the intravenous anesthesia adjustment strategy to medical staff to assist in adjusting the preliminary intravenous anesthesia strategy.

9. An electronic device, wherein: The electronic device includes: processor; and, A memory storing computer executable instructions which, when executed, cause the processor to perform a method according to any one of claims 1-7.

10. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method of any one of claims 1 to 7 is implemented.

Images