Intelligent early warning system for post-anesthesia complications of surgical patient

Abstract

The invention relates to the technical field of post-anesthesia complication monitoring, in particular to an intelligent pre-warning system for post-anesthesia complication of a surgical patient. The system obtains an intraoperative risk degree according to the size and change of intraoperative body index data of a patient in each first preset time period and past medical history scores and allergy history scores of the patient, and further judges an intraoperative anesthesia complication patient and an intraoperative normal patient in real time; according to the size of the post-operation body index data, the consciousness state score, the nervous system score, the wound recovery score and the waking state of the normal patient in each second preset time period and the post-operation risk degree of the normal patient in the operation, the post-operation risk degree is obtained, and then the post-operation anesthesia complication patient and the normal patient in the operation are judged in real time. According to the method, the intraoperative risk degree and the postoperative risk degree are accurately obtained in real time, so that the post-anesthesia complications of the patient are accurately detected in time, measures are taken in time, and the harm of the post-anesthesia complications is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of post-anesthesia complication monitoring technology, specifically to an intelligent early warning system for post-anesthesia complications in surgical patients. Background Technology

[0002] Surgical anesthesia is an indispensable and crucial part of modern surgery, directly affecting patient safety and surgical outcomes. However, while anesthetic drugs suppress consciousness and pain sensation, they also have varying degrees of inhibitory effects on the respiratory, circulatory, and nervous systems, potentially leading to various postoperative complications such as respiratory depression, hypotension, bradycardia, delayed awakening, and postoperative cognitive impairment. These complications not only interfere with normal physiological functions, prolong recovery, and increase medical costs, but can also be life-threatening in severe cases.

[0003] Currently, the monitoring and early warning of post-anesthesia complications in surgical patients in clinical practice mainly relies on medical staff making manual judgments based on regular rounds, reviewing monitoring equipment data, and combining this with their personal clinical experience. This approach is highly dependent on subjective experience, lacks objective quantitative standards, and has limited information integration capabilities, easily leading to "information silos." Furthermore, it fails to consider that the development of post-anesthesia complications is a dynamic process, with early physiological changes often subtle and fleeting. Existing methods struggle to capture these subtle abnormal trends in a timely manner and provide prospective warnings. Often, complications are only discovered after obvious clinical symptoms have emerged, missing the optimal window for intervention and prevention. Therefore, current methods are insufficient for timely and accurate detection of post-anesthesia complications in surgical patients. Summary of the Invention

[0004] To address the technical problem of current methods' inability to detect post-anesthesia complications in surgical patients in a timely and accurate manner, the present invention aims to provide an intelligent early warning system for post-anesthesia complications in surgical patients. The specific technical solution adopted is as follows: This invention provides an intelligent early warning system for post-anesthesia complications in surgical patients. The system includes: The data acquisition module is used to acquire the patient's past medical history score and allergy history score; to acquire various intraoperative physical indicators of the patient during the operation in real time; and to acquire various postoperative physical indicators, consciousness status score, neurological system score and wound recovery score of the patient in real time. The intraoperative anesthesia complication analysis module is used to divide the first preset time period in real time during the operation. Based on the magnitude and changes of each patient's intraoperative physical index data in each first preset time period, as well as each patient's past medical history score and allergy history score, the module obtains the intraoperative risk level of each patient in each first preset time period. Based on the intraoperative risk level, the module can identify patients with intraoperative anesthesia complications and patients with normal intraoperative outcomes in real time. The postoperative anesthesia complication analysis module is used to divide the second preset time period in real time after surgery. Based on the magnitude of each postoperative physical indicator data, consciousness status score, neurological system score, wound recovery score and awake status of each normal patient in each second preset time period, as well as the magnitude and changes of the intraoperative risk level of each normal patient, the module obtains the postoperative risk level of each normal patient in each second preset time period. Based on the postoperative risk level, the module can identify patients with postoperative anesthesia complications and normal patients in real time.

[0005] Furthermore, the method for obtaining the degree of intraoperative risk is as follows: For any patient and any first preset time period of that patient, the degree of abnormality of the patient's physical indicators during the first preset time period is obtained based on the magnitude and changes of each intraoperative physical indicator data within the first preset time period. The sum of the patient's past medical history score and allergy history score is used as the patient's baseline score. The result of normalizing the sum of the abnormality of the physical indicators and the baseline score is used as the intraoperative risk level of the patient in the first preset time period.

[0006] Furthermore, the method for obtaining the degree of abnormality of the aforementioned physical indicators is as follows: For any intraoperative physical indicator data of the patient, the mean of the difference of the intraoperative physical indicator data at any adjacent time within the first preset time period is obtained as the degree of change of the intraoperative physical indicator data of the patient within the first preset time period. The normal range of this type of intraoperative physical indicator data is taken as the target range, and the intraoperative physical indicator data of this patient that is not within the target range during the first preset time period is taken as the first abnormal indicator data. The minimum value of each first abnormal indicator data that exceeds the target range is taken as the abnormal analysis value; The result of normalizing the product of the number of first abnormal indicator data, the mean of the abnormal analysis value, and the degree of change is used as the local abnormality of the intraoperative physical indicator data of the patient within the first preset time period. The mean of the local abnormality of all intraoperative physical indicators of the patient within the first preset time period is taken as the degree of abnormality of the patient's physical indicators within the first preset time period.

[0007] Furthermore, the method for real-time identification of patients with intraoperative anesthetic complications and those with normal intraoperative outcomes based on intraoperative risk levels is as follows: For any patient, the intraoperative risk level of the patient is obtained in real time for each first preset time period. When the patient's intraoperative risk level exceeds the preset intraoperative risk level threshold, the patient is determined to have intraoperative anesthesia complications. When the patient's intraoperative risk level is less than or equal to the preset intraoperative risk level threshold, the patient is judged to be a normal patient during the operation.

[0008] Furthermore, the method for obtaining the postoperative risk level is as follows: For any patient who is normal during surgery and any second preset time period of the patient who is normal during surgery, the first risk index of anesthetic complications for the second preset time period is obtained based on the magnitude of each postoperative physical indicator data within the second preset time period. Based on the consciousness score, neurological score, wound recovery score, and conscious status of the normal patient during the second preset time period, the second risk index of anesthetic complications during the second preset time period is obtained. Based on the magnitude and changes in the intraoperative risk level of the normal patient during the operation, obtain the anesthesia reference risk index for the normal patient during the operation. The result of normalizing the sum of the first risk index of anesthesia complications, the second risk index of anesthesia complications, and the anesthesia reference risk index is used as the postoperative risk level for the second preset time period.

[0009] Furthermore, the method for obtaining the first risk index of anesthetic complications is as follows: For any postoperative physical indicator data of any patient who is normal during surgery and any second preset time period, any postoperative physical indicator data that exceeds the normal range of the postoperative physical indicator data within the second preset time period shall be regarded as the second abnormal indicator data. All times corresponding to the second abnormal indicator data are regarded as abnormal times. The ratio of the duration corresponding to the abnormal time to the total duration of the second preset time period is used as the degree of abnormality of the postoperative physical indicator data within the second preset time period. The result of normalizing the product of the mean of the second abnormal indicator data, the number of second abnormal indicator data, and the degree of abnormality is used as the risk analysis value of this type of postoperative physical indicator data within the second preset time period. The sum of the risk analysis values ​​of all postoperative physical indicators within the second preset time period is used as the first risk index for anesthesia complications during the second preset time period.

[0010] Furthermore, the method for obtaining the second risk index for anesthetic complications is as follows: For any second preset time period of any normal patient during surgery, when the normal patient during surgery is awake during the second preset time period, the awakening status score for the second preset time period is set to 0. When a normal patient is unconscious during the second preset time period, the awakening status score for the second preset time period is set to 1. The mean scores of consciousness, neurological system, wound recovery, and conscious state of the patients during the second preset time period were summed and normalized. This result was used as the second risk index for anesthetic complications during the second preset time period.

[0011] Furthermore, the method for obtaining the anesthesia reference risk index is as follows: For any patient who is normal during surgery, the intraoperative risk level of the patient is arranged according to the time sequence of the corresponding first preset time period and fitted into a curve; The difference between the maximum and minimum intraoperative risk levels in the curve is taken as the degree of intraoperative risk fluctuation. The curve is divided into local curve segments by extreme points; Take the last local curve segment of the curve as the target curve segment, and obtain the average slope of the tangents of all intraoperative risk levels on the target curve segment as the overall slope of the target curve. The result of normalizing the product of the degree of intraoperative risk fluctuation, the overall slope, and the mean of all intraoperative risk levels on the target curve segment is used as the anesthesia reference risk index for the normal patient during the operation.

[0012] Furthermore, the method for real-time identification of patients with postoperative anesthesia complications and normal postoperative patients based on postoperative risk levels is as follows: For any patient who is normal during surgery, the postoperative risk level of the patient is obtained in real time for each first preset time period. When the postoperative risk level of the patient is greater than the preset postoperative risk level threshold, the patient is judged to be a patient with postoperative anesthesia complications. When the postoperative risk level of a patient who is normal during the operation is less than or equal to a preset postoperative risk level threshold, the patient who is normal during the operation is judged to be a normal postoperative patient.

[0013] Furthermore, the initial time after the surgery is the end time of the surgery.

[0014] The present invention has the following beneficial effects: This invention first divides the surgical procedure into a first preset time period in real time, which facilitates the real-time, accurate, and efficient analysis of each patient's risk of anesthetic complications during surgery. Then, based on the magnitude and changes of various intraoperative physical indicators within each first preset time period, as well as each patient's medical history and allergy history scores, the intraoperative risk level for each patient in each first preset time period is obtained, accurately reflecting the degree of anesthetic complications for each patient within each first preset time period. Furthermore, based on the intraoperative risk level, patients with intraoperative anesthetic complications and those with normal intraoperative outcomes are accurately identified in real time, ensuring that patients with intraoperative anesthetic complications are detected promptly and accurately, facilitating timely intervention and reducing the harm of anesthetic complications. This also allows for the analysis of postoperative anesthetic complications. This invention integrates multi-source data to comprehensively capture various factors influencing postoperative complications. Simultaneously, it predicts postoperative anesthetic complication risks based on historical intraoperative data, enabling more precise determination of anesthetic complication risks. This significantly improves the accuracy of anesthetic complication prediction and real-time dynamic risk assessment, facilitating early warning and intervention, and effectively reducing the risk of anesthetic complications. By integrating multi-source data to comprehensively capture various factors influencing postoperative complications and predicting postoperative anesthetic complication risks based on historical intraoperative data, the invention significantly improves the accuracy of anesthetic complication prediction and real-time dynamic risk assessment, facilitating early warning and intervention, and effectively reducing the risk of anesthetic complications. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A structural block diagram of an intelligent early warning system for post-anesthesia complications in surgical patients, provided in one embodiment of the present invention; Figure 2 A flowchart illustrating a method for obtaining the degree of intraoperative risk according to an embodiment of the present invention; Figure 3 A flowchart illustrating a method for obtaining postoperative risk level according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a computer device provided according to an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent early warning system for post-anesthesia complications in surgical patients proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of an intelligent early warning system for post-anesthesia complications in surgical patients provided by the present invention.

[0020] Example 1: This invention proposes an intelligent early warning system for post-anesthesia complications in surgical patients. Please refer to [link / reference]. Figure 1 The diagram illustrates a structural block diagram of an intelligent early warning system for post-anesthesia complications in surgical patients according to an embodiment of the present invention. The system includes: a data acquisition module 10, an intraoperative anesthesia complication analysis module 20, and a postoperative anesthesia complication analysis module 30.

[0021] The data acquisition module 10 is used to acquire the patient's past medical history score and allergy history score; to acquire various intraoperative physical indicators during the patient's surgery in real time; and to acquire various postoperative physical indicators, consciousness status score, neurological system score and wound recovery score after the patient's surgery in real time.

[0022] Specifically, to accurately analyze each patient's anesthetic response during or after surgery, and to promptly and accurately identify various post-anesthesia complications so that timely measures can be taken to prevent unexpected health issues, this embodiment first integrates the patient's electronic medical record to obtain their past medical history and allergy history. Then, it scores the past medical history based on the degree of influence of the past medical history on the surgical anesthesia. A score of 0 is set for no influence; a score of 1 is set for a slight influence; and a score of 3 is set for a greater than slight influence. Furthermore, an allergy history score of 0 is set when the patient has no history of allergies to anesthetic-related drugs; and an allergy history score of 1 is set when the patient has a history of allergies to anesthetic-related drugs. It should be noted that the implementer can set the past medical history score and allergy history score according to the actual situation; no limitation is imposed here. This process then obtains the past medical history score and allergy history score for each patient.

[0023] To analyze the effects of anesthesia on patients during and after surgery in real time, and to promptly detect any adverse effects of anesthesia on the patient's body, this embodiment acquires various intraoperative physical indicators during the surgery in real time. Simultaneously, it acquires various postoperative physical indicators, consciousness status scores, neurological system scores, and wound recovery scores. In this embodiment, intraoperative physical indicators include heart rate, blood pressure, and blood oxygen saturation; postoperative physical indicators include respiratory rate, heart rate, and blood pressure. It is known that the patient's consciousness status, neurological system, and wound recovery status can indirectly reflect the patient's postoperative anesthesia recovery, which is beneficial for further analysis of postoperative anesthesia risks. Therefore, this embodiment uses the Glasgow Coma Scale to score the patient's consciousness status, acquiring each patient's consciousness status score in real time; and uses a muscle strength grading standard to score the patient's neurological system, acquiring each patient's neurological system score in real time. The Glasgow Coma Scale and the muscle strength grading standard are well-known and will not be elaborated further. The patient's wound recovery is scored by observing the condition of the surgical wound. Each patient's wound recovery score is acquired in real time: a score of 1 is set when the surgical wound has no redness, swelling, bleeding, or exudate; a score of 2 is set when the surgical wound has mild redness and swelling over a small area, with no bleeding or exudate; and a score of 3 is set when the surgical wound has severe redness and swelling over a large area, with bleeding or exudate. The implementer can set the consciousness status score, nervous system score, and wound recovery score according to the actual situation; this is not limited here. In this embodiment, the time interval between two adjacent data acquisition moments is set to 1 second; however, the implementer can set the time interval between two adjacent data acquisition moments according to the actual situation; this is not limited here.

[0024] It should be noted that the initial postoperative time is the end time of the surgery. In this embodiment, the postoperative anesthesia risk observation period is set to 24 hours. The implementer can set the postoperative anesthesia risk observation period according to the actual situation, and there is no limitation here.

[0025] The intraoperative anesthesia complication analysis module 20 is used to divide the first preset time period in real time during the operation. Based on the magnitude and changes of each patient's intraoperative physical index data in each first preset time period, as well as each patient's past medical history score and allergy history score, the module obtains the intraoperative risk level of each patient in each first preset time period. Based on the intraoperative risk level, the module can identify patients with intraoperative anesthesia complications and patients with normal intraoperative outcomes in real time.

[0026] Specifically, in practice, the time span for the occurrence of post-anesthesia complications varies among different patients. During surgery, the patient's physical condition is constantly changing, and some post-anesthesia complications may initially manifest as subtle changes in physical indicators that are not very noticeable and easily overlooked. Therefore, to accurately and promptly analyze the anesthetic risks during surgery, this embodiment first divides the surgical process into a first preset time period in real time. In this embodiment, the duration of the first preset time period is set to 5 minutes. The implementer can set the duration of the first preset time period according to the actual situation; no limitation is imposed here. That is, the first preset time period is divided sequentially from the start of the surgery. It should be noted that there are no other times between two adjacent first preset time periods; that is, two adjacent first preset time periods must be sequentially continuous and non-overlapping.

[0027] Furthermore, considering the vast differences in basic medical information among patients, the risk of post-anesthesia complications faced by each patient is unique. Therefore, this embodiment combines the patient's basic medical information with changes in various intraoperative physical indicators during the surgery to capture potential complication risks during the operation, enabling timely warnings and preventing unexpected complications. Further, this embodiment obtains the intraoperative risk level for each patient in each first preset time period based on the magnitude and changes of various intraoperative physical indicators, as well as the patient's medical history and allergy history scores. The higher the intraoperative risk level, the more likely the patient is to experience anesthetic complications within the corresponding first preset time period. Thus, this embodiment uses the intraoperative risk level to distinguish between patients with intraoperative anesthetic complications and those with normal intraoperative outcomes in real time.

[0028] Preferably, in one feasible embodiment, the method for obtaining the intraoperative risk level is described in [reference needed]. Figure 2 The document presents a flowchart of a method for obtaining intraoperative risk level provided in this embodiment, which includes the following steps: Step S201: For any patient and any first preset time period of the patient, based on the magnitude and changes of each intraoperative physical indicator data of the patient within the first preset time period, obtain the degree of abnormality of the patient's physical indicators within the first preset time period.

[0029] The greater the change in a patient's intraoperative physical indicators within a certain first preset time period, and the more and greater the number of intraoperative physical indicators exceeding the normal range, the greater the risk of anesthetic complications for that patient within that first preset time period. Therefore, this embodiment obtains the degree of abnormality of the patient's physical indicators within that first preset time period based on the magnitude and changes of each type of intraoperative physical indicator data. The greater the degree of abnormality of the physical indicators, the greater the risk of anesthetic complications for that patient within that first preset time period.

[0030] In one possible implementation of this embodiment, the method for obtaining the degree of abnormality of the physical indicators is as follows: for any intraoperative physical indicator data of the patient, the mean of the absolute values ​​of the differences between the intraoperative physical indicator data of the patient at any adjacent time within the first preset time period is obtained as the degree of change of the intraoperative physical indicator data of the patient within the first preset time period; the greater the degree of change, the more abnormal the intraoperative physical indicator data of the patient is within the first preset time period. The normal range of the intraoperative physical indicator data is taken as the target range. The intraoperative physical indicator data of the patient that is not within the target range during the first preset time period is taken as the first abnormal indicator data. The minimum value of each first abnormal indicator data that exceeds the target range is taken as the abnormal analysis value. When the abnormal analysis value is larger and there are more first abnormal indicator data, it indicates that there is more abnormality in the intraoperative physical indicator data during the first preset time period. To accurately characterize the abnormality of the intraoperative physical indicator data within the first preset time period, this embodiment normalizes the product of the number of first abnormal indicator data, the mean of the abnormal analysis value, and the degree of change, as the local abnormality degree of the intraoperative physical indicator data of the patient within the first preset time period. This embodiment normalizes the product of the number of first abnormal indicator data, the mean of the abnormal analysis value, and the degree of change using the norm normalization function; thus, the local abnormality degree of each intraoperative physical indicator data of the patient within the first preset time period is obtained. In order to comprehensively characterize the abnormality of the patient's physical indicators within the first preset time period, this embodiment takes the average of the local abnormality of all intraoperative physical indicator data of the patient within the first preset time period as the degree of abnormality of the patient's physical indicators within the first preset time period.

[0031] Step S202: The sum of the patient's past medical history score and allergy history score is used as the patient's baseline score.

[0032] For any patient, a higher score for both past medical history and allergy history indicates a greater risk of anesthetic complications during surgery. Therefore, in this embodiment, the sum of the patient's past medical history and allergy history scores is used as the patient's baseline score. A higher baseline score indicates a greater risk of anesthetic complications.

[0033] Step S203: The result of adding the abnormality of the physical indicators and the baseline score and normalizing the sum is used as the intraoperative risk level of the patient in the first preset time period.

[0034] It is known that the greater the degree of abnormality in physical indicators, the greater the risk of anesthetic complications for the corresponding patient within the corresponding first preset time period; conversely, the higher the baseline score, the more likely the patient is to have an anesthetic complications. Therefore, in this embodiment, for any patient and any first preset time period, the sum of the patient's abnormal physical indicators for that first preset time period and the patient's baseline score, followed by normalization, is used as the intraoperative risk level for that patient during that first preset time period. This embodiment uses a normalization function to normalize the sum of the patient's abnormal physical indicators for that first preset time period and the patient's baseline score.

[0035] At this point, the intraoperative risk level for each patient in each first preset time period is obtained.

[0036] Preferably, in one feasible embodiment of this method, the method for real-time determination of patients with intraoperative anesthesia complications and normal patients based on intraoperative risk level is as follows: For any patient, the intraoperative risk level of the patient is acquired in real time for each first preset time period. It is known that the higher the intraoperative risk level, the more likely the patient is to have anesthesia complications in the corresponding first preset time period. Therefore, this embodiment sets a preset intraoperative risk level threshold of 0.6. The implementer can set the size of the preset intraoperative risk level threshold according to the actual situation, which is not limited here. When the patient's intraoperative risk level is greater than the preset intraoperative risk level threshold, the patient is determined to be a patient with intraoperative anesthesia complications, and an early warning is issued simultaneously to remind medical staff to pay close attention to the patient's anesthesia status. When the patient's intraoperative risk level is less than or equal to the preset intraoperative risk level threshold, the patient is determined to be a normal patient during surgery.

[0037] Thus, patients with intraoperative anesthetic complications and those who were normal during the operation can be accurately identified.

[0038] The postoperative anesthesia complication analysis module 30 is used to divide the second preset time period in real time after surgery. Based on the magnitude of each postoperative physical indicator data, consciousness status score, neurological system score, wound recovery score and awake status of each normal patient in each second preset time period, as well as the magnitude and changes of the intraoperative risk level of each normal patient, the module obtains the postoperative risk level of each normal patient in each second preset time period. Based on the postoperative risk level, the module can determine patients with postoperative anesthesia complications and normal patients in real time.

[0039] Specifically, it is known that different patients have certain individual differences, and the timing of the onset of anesthetic complications will also vary. Some patients may experience them during surgery, while others may experience them after surgery. Therefore, the absence of anesthetic complications during surgery does not mean that postoperative anesthetic complications will not occur. At the same time, the occurrence of some anesthetic complications is a gradual process, and the residual effects of anesthetic drugs gradually fade after surgery. That is, the body begins to recover from the anesthesia and surgical trauma after surgery, and the immune system, endocrine system, and other systems will undergo a series of adjustments. These changes may lead to the emergence of new anesthetic risk factors, which in turn may trigger anesthetic complications. Therefore, it is necessary to monitor the changes in various physical indicators and overall recovery of normal patients after surgery to provide timely warnings of postoperative anesthetic complications.

[0040] To accurately and promptly analyze the anesthesia risk of normal patients after surgery, this embodiment first divides the procedure into a second preset time period in real time after the operation. This embodiment sets the duration of the second preset time period to 2 hours, but the implementer can set the duration according to the actual situation; no limitation is imposed here. That is, the second preset time period is divided sequentially from the start of the operation. It should be noted that there are no other times between two adjacent second preset time periods; that is, two adjacent second preset time periods must be sequentially continuous and non-overlapping.

[0041] It is known that the more abnormal the postoperative physical indicators of a normally functioning patient are within a second pre-defined time period, the more likely the patient is to experience anesthetic complications within that time period. Furthermore, higher consciousness scores, neurological scores, and wound recovery scores for a normally functioning patient within that second pre-defined time period, coupled with the patient being unconscious during that period, also indicate a higher likelihood of anesthetic complications. Additionally, greater changes in intraoperative risk levels, especially if the final trend of increasing intraoperative risk, suggest a higher likelihood of anesthetic complications. Normal patients are more likely to experience anesthetic complications in the subsequent postoperative stage. Therefore, this embodiment obtains the postoperative risk level of each normal patient in each second preset time period based on the magnitude of each postoperative physical indicator data, consciousness status score, neurological system score, wound recovery score, and awake status, as well as the magnitude and changes of the intraoperative risk level of each normal patient. The higher the postoperative risk level, the more likely the normal patient is to experience anesthetic complications in the corresponding second preset time period. Therefore, this embodiment determines patients with postoperative anesthetic complications and normal patients in real time based on the postoperative risk level.

[0042] Preferably, in one feasible embodiment, the method for obtaining the postoperative risk level is described in [reference needed]. Figure 3 The document presents a flowchart of a method for obtaining postoperative risk level provided in this embodiment, which includes the following steps: Step S301: For any patient who is normal during surgery and any second preset time period of the patient who is normal during surgery, obtain the first risk index of anesthesia complications for the second preset time period based on the magnitude of each postoperative physical indicator data within the second preset time period.

[0043] Among them, the higher the first risk index for anesthetic complications, the more likely anesthetic complications are to occur in the corresponding second preset time period for normal patients during surgery.

[0044] In one possible implementation of this embodiment, the method for obtaining the first risk index of anesthesia complications is as follows: For any postoperative physical indicator data of any normal patient during surgery and any second preset time period, all postoperative physical indicator data exceeding the normal range within the second preset time period are considered as second abnormal indicator data; the time corresponding to the second abnormal indicator data is considered as abnormal time; the ratio of the duration corresponding to the abnormal time to the total duration of the second preset time period is used as the abnormal proportion of the postoperative physical indicator data within the second preset time period; the higher the abnormal proportion, the greater the abnormality of the postoperative physical indicator data within the second preset time period. The more abnormal the indicator data, the larger and more numerous the second abnormal indicator data, the more abnormal the postoperative physical indicator data is within the second preset time period. Therefore, in this embodiment, the normalized result of the product of the mean of the second abnormal indicator data, the number of second abnormal indicator data, and the degree of abnormality is used as the risk analysis value of the postoperative physical indicator data within the second preset time period. In this embodiment, the normalization function is used to normalize the product of the mean of the second abnormal indicator data, the number of second abnormal indicator data, and the degree of abnormality. Thus, the risk analysis value of each type of postoperative physical indicator data within the second preset time period is obtained. The higher the risk analysis value, the more abnormal the corresponding postoperative physical indicators are within the second preset time period. In order to comprehensively characterize the abnormality of the postoperative physical indicators within the second preset time period, this embodiment uses the sum of the risk analysis values ​​of all postoperative physical indicators within the second preset time period as the first risk index of anesthesia complications within the second preset time period.

[0045] At this point, the first risk index of anesthetic complications for each second pre-set time period of each normal patient during surgery is obtained.

[0046] Step S302: Based on the consciousness score, neurological score, wound recovery score, and awake state of the normal patient during the second preset time period, obtain the second risk index of anesthetic complications for the second preset time period.

[0047] Among them, the higher the second risk index for anesthetic complications, the more likely anesthetic complications are to occur in the corresponding second preset time period for normal patients during surgery.

[0048] In one possible implementation of this embodiment, the method for obtaining the second risk index of anesthesia complications is as follows: For any normal patient during surgery, at any second preset time period, if the normal patient is conscious during the second preset time period, the conscious state score for that second preset time period is set to 0; if the normal patient is unconscious during the second preset time period, the conscious state score for that second preset time period is set to 1. The implementer can set the conscious state score according to the actual situation, and there is no limitation here. It is known that when the conscious state score, neurological system score, wound recovery score, and conscious state score of the normal patient during the second preset time period are higher, it indicates that the normal patient during the second preset time period has a higher risk of anesthesia complications. In order to more accurately analyze the anesthesia risk of the normal patient during the second preset time period, the mean of the conscious state score, the mean of the neurological system score, the mean of the wound recovery score, and the conscious state score of the normal patient during the second preset time period are added together and normalized, and the result is used as the second risk index of anesthesia complications for that second preset time period. In this embodiment, the mean scores of consciousness, nervous system, wound recovery, and conscious state are normalized using the norm normalization function.

[0049] At this point, the second risk index of anesthetic complications for each second pre-set time period is obtained for each normal patient during surgery.

[0050] Step S303: Based on the magnitude and changes in the intraoperative risk level of the normal patient during the operation, obtain the anesthesia reference risk index for the normal patient during the operation.

[0051] Among them, the higher the anesthesia reference risk index, the greater the possibility that a normal patient during surgery will experience anesthetic complications after surgery.

[0052] In one possible implementation of this embodiment, the method for obtaining the anesthesia reference risk index is as follows: For any patient with normal intraoperative risk, the intraoperative risk level of the patient is arranged according to the time sequence of the corresponding first preset time period and fitted into a curve; wherein, the method of fitting the curve is a known technique and will not be described in detail. The difference between the maximum and minimum intraoperative risk levels in the curve is obtained as the intraoperative risk fluctuation level; the greater the intraoperative risk fluctuation level, the more unstable the risk of anesthesia complications during the operation of the patient with normal intraoperative risk, indirectly reflecting that the risk of postoperative anesthesia complications of the patient with normal intraoperative risk is more likely; further, the curve is divided by extreme points (i.e., the curve is divided by extreme points) to obtain local curve segments; the last local curve segment is taken as the target curve segment, and the mean of the slopes of the tangents of all intraoperative risk levels on the target curve segment is obtained as the overall slope of the target curve; the greater the overall slope, the more the anesthesia risk of the patient with normal intraoperative risk gradually increases in the later stage of the operation, i.e., it shows an upward trend, indirectly indicating that the postoperative anesthesia risk of the patient with normal intraoperative risk may be greater. A higher intraoperative risk level on the target curve segment indicates a potentially higher postoperative anesthesia risk for the patient who was otherwise healthy during the operation. Therefore, this embodiment normalizes the product of the intraoperative risk fluctuation, the overall slope, and the mean of all intraoperative risk levels on the target curve segment, using this product as the anesthesia reference risk index for the patient who was otherwise healthy during the operation. This embodiment normalizes the product of the intraoperative risk fluctuation, the overall slope, and the mean of all intraoperative risk levels on the target curve segment using the norm normalization function.

[0053] At this point, the anesthesia reference risk index for each normal patient during surgery is obtained.

[0054] Step S304: The sum of the first risk index of anesthesia complications, the second risk index of anesthesia complications, and the anesthesia reference risk index, and the result after normalization, is used as the postoperative risk level for the second preset time period.

[0055] It is known that higher levels of both the primary and secondary risk indices for anesthetic complications indicate a greater likelihood of anesthetic complications occurring in the corresponding second preset time period for patients with normal intraoperative outcomes. Conversely, a higher anesthesia reference risk index indicates a greater probability of postoperative anesthetic complications in patients with normal intraoperative outcomes. To accurately characterize the risk of anesthetic complications for each patient with normal intraoperative outcomes within each second preset time period, this embodiment uses the normalized result of summing the primary, secondary, and anesthesia reference risk indices for any patient with normal intraoperative outcomes within any second preset time period. This sum is then used as the postoperative risk level for that patient with normal intraoperative outcomes within that second preset time period.

[0056] At this point, the postoperative risk level for each second pre-set time period is obtained for each patient who was normal during the operation.

[0057] Preferably, in one feasible embodiment of this method, the method for real-time determination of patients with postoperative anesthesia complications and normal patients based on postoperative risk level is as follows: For any normal patient during surgery, the postoperative risk level of the normal patient during surgery is obtained in real time for each first preset time period. It is known that the higher the postoperative risk level, the more likely the normal patient is to have anesthesia complications in the corresponding second preset time period. Therefore, this embodiment sets a preset postoperative risk level threshold of 0.6. The implementer can set the size of the preset postoperative risk level threshold according to the actual situation, which is not limited here. When the postoperative risk level of the normal patient during surgery is greater than the preset postoperative risk level threshold, the normal patient during surgery is determined to be a patient with postoperative anesthesia complications, and an emergency warning is issued to medical staff simultaneously to provide timely emergency intervention and reduce the risk of anesthesia complications; when the postoperative risk level of the normal patient during surgery is less than or equal to the preset postoperative risk level threshold, the normal patient during surgery is determined to be a normal patient after surgery.

[0058] In summary, this embodiment obtains the intraoperative risk level based on the magnitude and changes of the patient's intraoperative physical indicators, past medical history scores, and allergy history scores within each first preset time period, thereby real-time identification of patients with intraoperative anesthesia complications and those who are normal during surgery. Similarly, based on the magnitude of postoperative physical indicators, consciousness status scores, neurological system scores, wound recovery scores, and awakening status within each second preset time period for patients who are normal during surgery, and considering the intraoperative risk level of these patients, the invention obtains the postoperative risk level, thereby real-time identification of patients with postoperative anesthesia complications and those who are normal after surgery. This invention, by accurately obtaining the intraoperative and postoperative risk levels in real time, enables timely and accurate detection of postoperative anesthesia complications, allowing for prompt intervention and effectively reducing the harm caused by these complications.

[0059] Example 2: This invention also proposes an intelligent early warning device for post-anesthesia complications in surgical patients. The device includes a memory and a processor. The memory stores executable program code, and the processor calls and executes the executable program code to perform the intelligent early warning system for post-anesthesia complications in surgical patients provided in the embodiments of this application. Specifically, the device may be a chip, component, or module. The chip may include a connected processor and memory; the memory stores instructions, and when the processor calls and executes the instructions, the chip can perform the intelligent early warning system for post-anesthesia complications in surgical patients provided in the above embodiments.

[0060] Furthermore, this application also protects a computer device; please refer to [link to relevant documentation]. Figure 4The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the aforementioned intelligent early warning systems for post-anesthesia complications in surgical patients.

[0061] Example 3: The present invention also provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform the aforementioned method steps to implement the intelligent early warning system for post-anesthesia complications of surgical patients provided in the above embodiments.

[0062] Example 4: The present invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to realize the intelligent early warning system for post-anesthesia complications of surgical patients provided in the above embodiments.

[0063] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0064] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An intelligent early warning system for post-anesthesia complications in surgical patients, characterized in that, The system includes: The data acquisition module is used to acquire the patient's past medical history score and allergy history score; to acquire various intraoperative physical indicators of the patient during the operation in real time; and to acquire various postoperative physical indicators, consciousness status score, neurological system score and wound recovery score of the patient in real time. The intraoperative anesthesia complication analysis module is used to divide the first preset time period in real time during the operation. Based on the magnitude and changes of each patient's intraoperative physical index data in each first preset time period, as well as each patient's past medical history score and allergy history score, the module obtains the intraoperative risk level of each patient in each first preset time period. Based on the intraoperative risk level, the module can identify patients with intraoperative anesthesia complications and patients with normal intraoperative outcomes in real time. The postoperative anesthesia complication analysis module is used to divide the second preset time period in real time after surgery. Based on the magnitude of each postoperative physical indicator data, consciousness status score, neurological system score, wound recovery score and awake status of each normal patient in each second preset time period, as well as the magnitude and changes of the intraoperative risk level of each normal patient, the module obtains the postoperative risk level of each normal patient in each second preset time period. Based on the postoperative risk level, the module can identify patients with postoperative anesthesia complications and normal patients in real time.

2. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 1, characterized in that, The method for obtaining the degree of intraoperative risk is as follows: For any patient and any first preset time period of that patient, the degree of abnormality of the patient's physical indicators during the first preset time period is obtained based on the magnitude and changes of each intraoperative physical indicator data within the first preset time period. The sum of the patient's past medical history score and allergy history score is used as the patient's baseline score. The result of normalizing the sum of the abnormality of the physical indicators and the baseline score is used as the intraoperative risk level of the patient in the first preset time period.

3. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 2, characterized in that, The method for obtaining the degree of abnormality of the aforementioned physical indicators is as follows: For any intraoperative physical indicator data of the patient, the mean of the difference of the intraoperative physical indicator data at any adjacent time within the first preset time period is obtained as the degree of change of the intraoperative physical indicator data of the patient within the first preset time period. The normal range of this type of intraoperative physical indicator data is taken as the target range, and the intraoperative physical indicator data of this patient that is not within the target range during the first preset time period is taken as the first abnormal indicator data. The minimum value of each first abnormal indicator data that exceeds the target range is taken as the abnormal analysis value; The result of normalizing the product of the number of first abnormal indicator data, the mean of the abnormal analysis value, and the degree of change is used as the local abnormality of the intraoperative physical indicator data of the patient within the first preset time period. The mean of the local abnormality of all intraoperative physical indicators of the patient within the first preset time period is taken as the degree of abnormality of the patient's physical indicators within the first preset time period.

4. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 1, characterized in that, The method for real-time identification of patients with intraoperative anesthesia complications and those with normal intraoperative outcomes based on intraoperative risk levels is as follows: For any patient, the intraoperative risk level of the patient is obtained in real time for each first preset time period. When the patient's intraoperative risk level exceeds the preset intraoperative risk level threshold, the patient is determined to have intraoperative anesthesia complications. When the patient's intraoperative risk level is less than or equal to the preset intraoperative risk level threshold, the patient is judged to be a normal patient during the operation.

5. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 1, characterized in that, The method for obtaining the postoperative risk level is as follows: For any patient who is normal during surgery and any second preset time period of the patient who is normal during surgery, the first risk index of anesthetic complications for the second preset time period is obtained based on the magnitude of each postoperative physical indicator data within the second preset time period. Based on the consciousness score, neurological score, wound recovery score, and conscious status of the normal patient during the second preset time period, the second risk index of anesthetic complications during the second preset time period is obtained. Based on the magnitude and changes in the intraoperative risk level of the normal patient during the operation, obtain the anesthesia reference risk index for the normal patient during the operation. The result of normalizing the sum of the first risk index of anesthesia complications, the second risk index of anesthesia complications, and the anesthesia reference risk index is used as the postoperative risk level for the second preset time period.

6. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 5, characterized in that, The method for obtaining the first risk index of anesthetic complications is as follows: For any postoperative physical indicator data of any patient who is normal during surgery and any second preset time period, any postoperative physical indicator data that exceeds the normal range of the postoperative physical indicator data within the second preset time period shall be regarded as the second abnormal indicator data. All times corresponding to the second abnormal indicator data are regarded as abnormal times. The ratio of the duration corresponding to the abnormal time to the total duration of the second preset time period is used as the degree of abnormality of the postoperative physical indicator data within the second preset time period. The result of normalizing the product of the mean of the second abnormal indicator data, the number of second abnormal indicator data, and the degree of abnormality is used as the risk analysis value of this type of postoperative physical indicator data within the second preset time period. The sum of the risk analysis values ​​of all postoperative physical indicators within the second preset time period is used as the first risk index for anesthesia complications during the second preset time period.

7. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 5, characterized in that, The method for obtaining the second risk index of anesthesia complications is as follows: For any second preset time period of any normal patient during surgery, when the normal patient during surgery is awake during the second preset time period, the awakening status score for the second preset time period is set to 0. When a normal patient is unconscious during the second preset time period, the awakening status score for the second preset time period is set to 1. The mean scores of consciousness, neurological system, wound recovery, and conscious state of the patients during the second preset time period were summed and normalized. This result was used as the second risk index for anesthetic complications during the second preset time period.

8. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 5, characterized in that, The method for obtaining the anesthesia reference risk index is as follows: For any patient who is normal during surgery, the intraoperative risk level of the patient is arranged according to the time sequence of the corresponding first preset time period and fitted into a curve; The difference between the maximum and minimum intraoperative risk levels in the curve is taken as the degree of intraoperative risk fluctuation. The curve is divided into local curve segments by extreme points; Take the last local curve segment of the curve as the target curve segment, and obtain the average slope of the tangents of all intraoperative risk levels on the target curve segment as the overall slope of the target curve. The result of normalizing the product of the degree of intraoperative risk fluctuation, the overall slope, and the mean of all intraoperative risk levels on the target curve segment is used as the anesthesia reference risk index for the normal patient during the operation.

9. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 1, characterized in that, The method for real-time assessment of patients with postoperative anesthesia complications and normal postoperative patients based on postoperative risk levels is as follows: For any patient who is normal during surgery, the postoperative risk level of the patient is obtained in real time for each first preset time period. When the postoperative risk level of the patient is greater than the preset postoperative risk level threshold, the patient is judged to be a patient with postoperative anesthesia complications. When the postoperative risk level of a patient who is normal during the operation is less than or equal to a preset postoperative risk level threshold, the patient who is normal during the operation is judged to be a normal postoperative patient.

10. The intelligent early warning system for post-anesthesia complications in surgical patients as described in claim 1, characterized in that, The initial time after surgery is the end time of the surgery.

Images