Postoperative early warning device and method based on intelligent wearable equipment

Through smart wearable devices, the incidence of vagus nerve reflexes is quantified, and the postoperative warning is provided, which solves the problem of failure to effectively warning in the existing technology and improves the patient's sense of security and satisfaction.

CN119073937APending Publication Date: 2024-12-06马鞍山市人民医院
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411408211.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-10
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art has failed to effectively quantify the incidence of postoperative vagus reflexes, resulting in low patient sense of safety and satisfaction, and it is difficult to detect worsening vital signs in a timely manner.

Method used

The patient's sensor-like parameters were collected through intelligent wearable devices, similar patients were screened, time-domain trend values ​​and standard trend matrix were calculated, vagus reflex occurrence values ​​were quantified, and postoperative warning results were provided.

Benefits of technology

Timely warning of postoperative vagus reflexes is achieved, reducing the incidence of complications, and improving patient sense of safety and satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119073937A_ABST
    Figure CN119073937A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of medical instruments, and particularly discloses a postoperative early warning device and method based on intelligent wearable equipment, and the device comprises a screening module which is used for screening all similar patients; the first calculation module is used for obtaining time domain trend values of all types of sensor parameters of the patient based on all types of sensor parameters of the patient intelligent wearable device at all moments within a preset time period before the current moment; the construction module is used for obtaining an analysis trend matrix of the patient based on all similar patients; the second calculation module is used for obtaining a vagus nerve reflex occurrence value of the patient based on the analysis trend matrix of the patient; and the early warning module is used for obtaining a postoperative early warning result of the intelligent wearable equipment of the patient based on the vagus nerve reflex occurrence value of the patient. According to the method, the possibility of the vagus nerve reflex of the patient after the current moment is quantified, the postoperative complications and the vagus nerve reflex occurrence rate are reduced, and the safety and satisfaction of the patient are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a postoperative early warning device and method based on a smart wearable device. Background Art

[0002] At present, in the process of coronary heart disease patients receiving transradial coronary artery intervention, due to the long puncture route for patients, anticoagulants need to be used during the operation to prevent thrombosis, and compression will be performed on the punctured artery for 2-6 hours after the operation to stop bleeding; however, due to factors such as unsmooth puncture, repeated punctures, and vascular malformations of patients, subcutaneous hematomas are common in clinical patients after surgery; therefore, it is very easy for patients to develop peripheral vascular complications such as radial artery spasm, occlusion, forearm hematoma, local bleeding, and compartment syndrome. At the same time, postoperative patients will have an increased incidence of vagal reflexes due to nervous emotions, postoperative urine retention, long fasting time, insufficient blood volume, pain, etc., which may endanger the patient's life in severe cases. However, subcutaneous hematomas are sometimes inevitable in clinical practice, so timely detection of the deterioration of patients' vital signs is particularly important to reduce postoperative complications and the incidence of vagal reflexes.

[0003] However, there is currently no postoperative warning device and method based on smart wearable devices that can quantify the possibility of vagal reflexes occurring in patients after the current moment, and it does not reduce the incidence of postoperative complications and vagal reflexes, making it difficult to improve patients' sense of security and satisfaction.

[0004] Therefore, the present invention proposes a postoperative early warning device and method based on a smart wearable device. Summary of the invention

[0005] The present invention provides a postoperative early warning device and method based on a smart wearable device, which is used to obtain all similar patients according to all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment, and realizes the selection of some historical patients whose postoperative physiological signals and health data are similar to the patient from all historical patients in the database, and obtains the time domain trend values ​​of all sensor-like parameters of the patient according to all sensor-like parameters of the patient's smart wearable device at all moments in a preset time period before the current moment, and realizes the quantification of the comprehensive development trend of each sensor-like parameter of the patient in the time domain, and then obtains the standard trend matrix of the patient according to the time domain trend values ​​of all sensor-like parameters of all similar patients, which is convenient for subsequent determination The patient's analysis trend matrix is ​​obtained based on the time domain trend values ​​of all sensor parameters of the patient and the patient's standard trend matrix, which is convenient for the subsequent calculation of the patient's vagus nerve reflex occurrence value. Then, the patient's vagus nerve reflex occurrence value is obtained based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients, thereby quantifying the possibility of the patient's vagus nerve reflex occurring after the current moment. Finally, based on the patient's vagus nerve reflex occurrence value, the postoperative warning results of the patient's smart wearable device are obtained, which helps medical staff to detect the deterioration of the patient's vital signs early, reduce postoperative complications, reduce the incidence of vagus nerve reflex, and improve the patient's sense of security and satisfaction.

[0006] The present invention provides a postoperative early warning device based on a smart wearable device, comprising:

[0007] A screening module, used to obtain all similar patients based on all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment;

[0008] A first calculation module is used to obtain the time domain trend value of all sensor parameters of the patient based on all sensor parameters of the patient's smart wearable device at all times within a preset time period before the current time;

[0009] A building block is used to obtain a standard trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of all similar patients, and to obtain an analysis trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of the patient and the standard trend matrix of the patient;

[0010] A second calculation module is used to obtain the patient's vagus nerve reflex occurrence value based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients;

[0011] The early warning module is used to obtain the postoperative early warning results of the patient's smart wearable device based on the patient's vagus nerve reflex occurrence value.

[0012] Preferably, the postoperative warning device based on the smart wearable device, the screening module includes:

[0013] The first acquisition submodule is used to obtain all sensor parameters of the patient's smart wearable device at each moment in a preset time period before the current moment, wherein all sensor parameters include heart rate parameters, blood pressure parameters, body temperature parameters and blood oxygen saturation parameters;

[0014] The judgment submodule is used to take all historical patients in the database as reference patients. If the value difference between each type of sensor parameter of the patient's smart wearable device at the initial moment within the preset time period before the current moment and the corresponding type of sensor parameter of each reference patient's smart wearable device at each moment in the entire postoperative warning time period is less than the corresponding type of sensor parameter difference threshold, it is determined that the patient and the corresponding reference patient are similar in the corresponding type of sensor parameter at the corresponding moment;

[0015] The screening submodule is used to determine that the corresponding reference patient is a similar patient when the patient is determined to be similar to each reference patient in all sensor-like parameters at any time.

[0016] Preferably, the postoperative warning device based on the smart wearable device also includes:

[0017] The alarm module is used to control the red light of the patient's smart wearable device to turn on when at least one type of sensor parameter among all types of sensor parameters of the patient's smart wearable device at the current moment is not within the corresponding type of sensor parameter range.

[0018] Preferably, the postoperative warning device based on the smart wearable device, the first calculation module includes:

[0019] A processing submodule is used to take two adjacent moments of the patient's smart wearable device within a preset time period before the current moment as a group of adjacent moments of the patient, obtain all groups of adjacent moments of the patient, and take the quotient between the numerical difference of each type of sensor parameter at two moments in each group of adjacent moments of the patient and the preset time interval value as the trend value of the corresponding type of sensor parameter of the corresponding group of adjacent moments of the patient;

[0020] The first calculation submodule is used to obtain the time domain trend value of each type of sensor parameter of the patient based on the trend value of each type of sensor parameter of all groups of adjacent moments of the patient.

[0021] Preferably, in the postoperative early warning device based on the smart wearable device, the first calculation submodule obtains the time domain trend value of each type of sensor parameter of the patient based on the trend value of each type of sensor parameter at all groups of adjacent moments of the patient, including:

[0022]

[0023] Among them, β is the time domain trend value of the patient's current calculation sensor parameter, α is the number of groups of all groups of patients at adjacent moments, and μ x The standard deviation of the trend value of the current calculated class sensor parameter at adjacent moments for all groups of patients, μ z is the mean value of the trend value of the current calculated class sensor parameters of all groups of patients at adjacent moments, μ max is the maximum value of the trend value of the current calculated class sensor parameters of all groups of patients at adjacent moments, μ min is the minimum value of the trend values ​​of the current calculation type sensor parameters of all groups of patients at adjacent moments, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0024] Preferably, the postoperative warning device based on the smart wearable device comprises:

[0025] The preprocessing submodule is used to take the moment when the patient is similar to each similar patient in all types of sensor parameters as the similar moment of the corresponding similar patients, and judge whether the length of the remaining time period after the first similar moment of each similar patient's smart wearable device in the entire postoperative warning time period is greater than the length of the preset time period. If so, the time period with the same length as the preset time period is intercepted from the corresponding remaining time period from the front to the back, and regarded as the similar time period of the corresponding similar patients; otherwise, the corresponding remaining time period is filled, and the obtained filled remaining time period is regarded as the similar time period of the corresponding similar patients;

[0026] The first construction submodule is used to obtain the time domain trend value of all class sensor parameters of each similar patient based on all class sensor parameters of each similar patient's smart wearable device at all times in a similar time period, and to define the ordinal values ​​of all similar patients from 1 in descending order according to the sum of the time domain trend values ​​of all class sensor parameters of each similar patient, and obtain the ordinal definition result. Based on the time domain trend values ​​of all class sensor parameters of all similar patients and the ordinal definition results, the standard trend matrix of the patient is obtained, which is:

[0027]

[0028] Wherein, Q is the standard trend matrix of the patient, w1 is the time domain trend value of the heart rate parameter of the similar patient whose ordinal definition result is 1, r1 is the time domain trend value of the blood pressure parameter of the similar patient whose ordinal definition result is 1, h1 is the time domain trend value of the body temperature parameter of the similar patient whose ordinal definition result is 1, b1 is the time domain trend value of the blood oxygen saturation parameter of the similar patient whose ordinal definition result is 1, w2 is the time domain trend value of the heart rate parameter of the similar patient whose ordinal definition result is 2, r2 is the time domain trend value of the blood pressure parameter of the similar patient whose ordinal definition result is 2, h2 is the time domain trend value of the body temperature parameter of the similar patient whose ordinal definition result is 2, b2 is the time domain trend value of the blood oxygen saturation parameter of the similar patient whose ordinal definition result is 2, w n The time domain trend value of the heart rate parameter of similar patients with ordinal definition result n, r n The time domain trend value of the blood pressure parameter of similar patients with ordinal definition result n, h n The temporal trend value of the temperature parameter of similar patients with ordinal definition result n, b n The time domain trend value of the blood oxygen saturation parameter of similar patients with ordinal definition result n, where n is the total number of similar patients;

[0029] The second construction submodule is used to obtain the patient's analysis trend matrix based on the time-domain trend values ​​of all sensor-like parameters of the patient and the patient's standard trend matrix.

[0030] Preferably, the postoperative warning device based on the smart wearable device, the second building block includes:

[0031] a preprocessing unit, configured to use the difference between the sum of the time-domain trend values ​​of all the class sensor parameters of each similar patient and the sum of the time-domain trend values ​​of all the class sensor parameters of the patient as the trend difference between the patient and each similar patient, and use the similar patient corresponding to the minimum value of the trend difference between the patient and all the similar patients as the replacement patient;

[0032] The second construction unit is used to replace all matrix elements of the matrix column corresponding to the replacement patient in the patient's standard trend matrix with the time domain trend value of the corresponding class sensor parameter of the patient, so as to obtain the patient's analysis trend matrix.

[0033] Preferably, the postoperative warning device based on the smart wearable device, the second calculation module includes:

[0034] The second acquisition submodule is used to obtain the vagus nerve reflex occurrence results of all similar patients, and judge whether the vagus nerve reflex occurrence result of each similar patient is the occurrence of vagus nerve reflex. If so, 1 is used as the vagus nerve reflex occurrence score of the corresponding similar patient, otherwise, 0 is used as the vagus nerve reflex occurrence score of the corresponding similar patient;

[0035] The second calculation submodule is used to obtain the patient's vagus nerve reflex occurrence value based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence score values ​​of all similar patients, that is:

[0036]

[0037] Among them, τ is the patient's vagus nerve reflex occurrence value, The number of similar patients with a score of 1 for vagal reflex occurrence, is the number of patients with a vagal reflex score of 0 among all similar patients, Q is the rank of the patient's standard trend matrix, E is the rank of the patient's analytical trend matrix, n is the total number of similar patients, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0038] Preferably, in a postoperative warning device based on a smart wearable device, the warning module obtains a postoperative warning result of the patient's smart wearable device based on the patient's vagus nerve reflex occurrence value, comprising:

[0039] Determine whether the patient's vagus nerve reflex occurrence value is greater than the preset vagus nerve reflex occurrence value threshold. If so, control the patient's smart wearable device to turn on the red light; otherwise, control the patient's smart wearable device to turn on the green light.

[0040] The present invention provides a postoperative warning method based on a smart wearable device, which is applied to implement any one of claims 1 to 9 of a postoperative warning device based on a smart wearable device, comprising:

[0041] S1: Obtain all similar patients based on all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment;

[0042] S2: based on all sensor-like parameters of the patient's smart wearable device at all times within a preset time period before the current time, obtaining the time domain trend values ​​of all sensor-like parameters of the patient;

[0043] S3: obtaining a standard trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of all similar patients, and obtaining an analysis trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of the patient and the standard trend matrix of the patient;

[0044] S4: based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients, the patient's vagus nerve reflex occurrence value is obtained;

[0045] S5: Based on the patient's vagus nerve reflex occurrence value, obtain the postoperative warning results of the patient's smart wearable device.

[0046] The beneficial effects of the present invention compared with the prior art are as follows: according to all the sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment, all similar patients are obtained, and some historical patients whose postoperative physiological signals and health data are similar to the patient are screened out from all historical patients in the database; according to all the sensor-like parameters of the patient's smart wearable device at all moments in a preset time period before the current moment, the time-domain trend values ​​of all the sensor-like parameters of the patient are obtained, and the comprehensive development trend of each sensor-like parameter of the patient in the time domain is quantified, and then according to the time-domain trend values ​​of all the sensor-like parameters of all similar patients, the standard trend matrix of the patient is obtained, which is convenient for the subsequent determination of the patient's classification The analysis trend matrix of the patient is obtained according to the time domain trend values ​​of all sensor parameters of the patient and the standard trend matrix of the patient, which is convenient for the calculation of the vagus nerve reflex occurrence value of the subsequent patient. Then, according to the analysis trend matrix of the patient, the standard trend matrix of the patient and the vagus nerve reflex occurrence results of all similar patients, the vagus nerve reflex occurrence value of the patient is obtained, which realizes the quantification of the possibility of vagus nerve reflex occurrence in the patient after the current moment. Finally, according to the vagus nerve reflex occurrence value of the patient, the postoperative warning result of the patient's smart wearable device is obtained, which helps medical staff to detect the deterioration of the patient's vital signs early, reduce postoperative complications, reduce the incidence of vagus nerve reflex, and improve the patient's sense of security and satisfaction.

[0047] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structure specifically pointed out in the written application document.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 This is a schematic diagram of a postoperative warning device based on a smart wearable device in an embodiment of the present invention;

[0051] Figure 2 This is a flow chart of a postoperative warning method based on a smart wearable device in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0053] Embodiment 1:

[0054] The present invention provides a postoperative warning device based on a smart wearable device, referring to Figure 1 ,include:

[0055] A screening module, used to obtain all similar patients based on all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment;

[0056] A first calculation module is used to obtain the time domain trend value of all sensor parameters of the patient based on all sensor parameters of the patient's smart wearable device at all times within a preset time period before the current time;

[0057] A building block is used to obtain a standard trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of all similar patients, and to obtain an analysis trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of the patient and the standard trend matrix of the patient;

[0058] A second calculation module is used to obtain the patient's vagus nerve reflex occurrence value based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients;

[0059] The early warning module is used to obtain the postoperative early warning results of the patient's smart wearable device based on the patient's vagus nerve reflex occurrence value.

[0060] In this embodiment, the patient's smart wearable device is a smart medical device that can be worn on the patient. The smart wearable device can collect the patient's physiological signals and health data through built-in sensors and data processing technology, and provide post-operative warning services.

[0061] In this embodiment, the preset time period is a time period preset to obtain all sensor parameters of the patient's smart wearable device.

[0062] In this embodiment, each moment is a moment selected from a preset time period before the current moment, and the time length between each adjacent moment is the same.

[0063] In this embodiment, similar patients are some historical patients whose postoperative physiological signals and health data are similar to those of the patient, screened out from historical patients in the database based on all sensor parameters of the patient's smart wearable device at each moment in a preset time period before the current moment.

[0064] In this embodiment, the time domain trend value of all sensor-like parameters of the patient is a numerical value obtained based on all sensor-like parameters of the patient's smart wearable device at all times within a preset time period before the current moment, which can characterize the comprehensive development trend of all sensor-like parameters of the patient in the time domain.

[0065] In this embodiment, the time domain trend value of all sensor-like parameters of similar patients is a numerical value obtained based on all sensor-like parameters of similar patients' smart wearable devices at all times in a similar time period, which can characterize the comprehensive development trend of all sensor-like parameters of similar patients in the time domain.

[0066] In this embodiment, the standard trend matrix of the patient is a matrix constructed by taking the time domain trend values ​​of all sensor-like parameters of all similar patients as matrix elements, and can reflect the comprehensive development trend of all sensor-like parameters of all similar patients in the time domain.

[0067] In this embodiment, the patient's analysis trend matrix is ​​a matrix obtained based on the time domain trend values ​​of all sensor-like parameters of the patient and the patient's standard trend matrix, which can reflect the comprehensive development trend of all sensor-like parameters of the patient in the time domain and the comprehensive development trend of all sensor-like parameters of all similar patients in the time domain.

[0068] In this embodiment, the vagus nerve reflex occurrence result of similar patients is the result of whether the postoperative vagus nerve reflex occurs in the similar patients during the entire postoperative warning time period, wherein the vagus nerve reflex occurrence result of similar patients includes the occurrence of vagus nerve reflex and the non-occurrence of vagus nerve reflex.

[0069] In this embodiment, the patient's vagus nerve reflex occurrence value is a predicted value of the possibility of the patient's vagus nerve reflex occurring after the current moment based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients.

[0070] In this embodiment, the postoperative warning result of the patient's smart wearable device is the result of controlling the red light and green light of the patient's smart wearable device based on all sensor parameters of the patient's smart wearable device at the current moment and the patient's vagus nerve reflex occurrence value.

[0071] The beneficial effects of the above technology are as follows: according to all the sensor-like parameters of the patient's smart wearable device at each moment in the preset time period before the current moment, all similar patients are obtained, and some historical patients whose postoperative physiological signals and health data are similar to the patient are screened out from all historical patients in the database; according to all the sensor-like parameters of the patient's smart wearable device at all moments in the preset time period before the current moment, the time domain trend values ​​of all the sensor-like parameters of the patient are obtained, and the comprehensive development trend of each type of sensor parameter of the patient in the time domain is quantified, and then according to the time domain trend values ​​of all the sensor-like parameters of all similar patients, the standard trend matrix of the patient is obtained, which is convenient for the subsequent determination of the patient's analysis trend matrix According to the time domain trend values ​​of all sensor parameters of the patient and the standard trend matrix of the patient, the analysis trend matrix of the patient is obtained, which is convenient for the calculation of the vagus nerve reflex occurrence value of the subsequent patient. Then, according to the analysis trend matrix of the patient, the standard trend matrix of the patient and the vagus nerve reflex occurrence results of all similar patients, the vagus nerve reflex occurrence value of the patient is obtained, which realizes the quantification of the possibility of vagus nerve reflex occurrence after the current moment. Finally, according to the vagus nerve reflex occurrence value of the patient, the postoperative early warning result of the patient's smart wearable device is obtained, which helps medical staff to detect the deterioration of the patient's vital signs early, reduce postoperative complications, reduce the incidence of vagus nerve reflex, and improve the patient's sense of security and satisfaction.

[0072] Embodiment 2:

[0073] On the basis of Example 1, the postoperative warning device based on the smart wearable device, the screening module includes:

[0074] The first acquisition submodule is used to obtain all sensor parameters of the patient's smart wearable device at each moment in a preset time period before the current moment, wherein all sensor parameters include heart rate parameters, blood pressure parameters, body temperature parameters and blood oxygen saturation parameters;

[0075] The judgment submodule is used to take all historical patients in the database as reference patients. If the value difference between each type of sensor parameter of the patient's smart wearable device at the initial moment within the preset time period before the current moment and the corresponding type of sensor parameter of each reference patient's smart wearable device at each moment in the entire postoperative warning time period is less than the corresponding type of sensor parameter difference threshold, it is determined that the patient and the corresponding reference patient are similar in the corresponding type of sensor parameter at the corresponding moment;

[0076] The screening submodule is used to determine that the corresponding reference patient is a similar patient when the patient is determined to be similar to each reference patient in all sensor-like parameters at any time.

[0077] In this embodiment, the heart rate parameter is the heart rate of the patient collected by the patient's smart wearable device at each moment in a preset time period before the current moment, and the heart rate unit is beats / minute.

[0078] In this embodiment, the blood pressure parameter is the blood pressure of the patient collected by the patient's smart wearable device at each moment in a preset time period before the current moment, and the blood pressure unit is millimeters of mercury (mmHg).

[0079] In this embodiment, the body temperature parameter is the body temperature of the patient collected by the patient's smart wearable device at each moment in a preset time period before the current moment, and the body temperature unit is Celsius.

[0080] In this embodiment, the blood oxygen saturation parameter is the blood oxygen saturation of the patient collected by the patient's smart wearable device at each moment in a preset time period before the current moment, and the unit of blood oxygen saturation is %.

[0081] In this embodiment, the database is a pre-set database containing a large amount of historical patient data (patients who have previously used smart wearable devices to complete postoperative warnings).

[0082] In this embodiment, the initial moment is the first moment in a preset time period before the current moment.

[0083] In this embodiment, the entire postoperative warning time period is the entire warning time period for the reference patient to perform postoperative warning based on the smart wearable device, wherein the warning time period starts when the reference patient puts on the smart wearable device and ends when the reference patient takes off the smart wearable device.

[0084] In this embodiment, each type of sensor parameter difference threshold is a pre-set sensor parameter difference threshold used to determine whether the patient and each reference patient are similar in each type of sensor parameter at each moment (at each moment during the entire postoperative warning time period), and each type of sensor parameter corresponds to a separate sensor parameter difference threshold.

[0085] The beneficial effects of the above technology are: clarifying the specific parameter items of all types of sensor parameters of the patient's smart wearable device at each moment in the preset time period before the current moment, and based on all historical patients in the database and each type of sensor parameters of the patient's smart wearable device at the initial moment in the preset time period before the current moment, it is possible to screen out some historical patients whose postoperative physiological signals and health data are similar to those of the patient from all historical patients in the database, which facilitates the construction of a standard trend matrix for subsequent patients.

[0086] Embodiment 3:

[0087] On the basis of Example 1, the postoperative warning device based on the smart wearable device further includes:

[0088] The alarm module is used to control the red light of the patient's smart wearable device to turn on when at least one type of sensor parameter among all types of sensor parameters of the patient's smart wearable device at the current moment is not within the corresponding type of sensor parameter range.

[0089] In this embodiment, the parameter range of each type of sensor is a pre-set range of each type of sensor parameter used to determine whether to control the red light of the patient's smart wearable device to turn on.

[0090] The beneficial effects of the above technology are: by real-time monitoring of all sensor parameters of the patient's smart wearable device at the current moment and setting the threshold range, abnormal changes in the patient's vital signs can be discovered in time, thereby improving the safety and efficiency of medical monitoring.

[0091] Embodiment 4:

[0092] On the basis of Example 1, the postoperative warning device based on the smart wearable device, the first calculation module includes:

[0093] A processing submodule is used to take two adjacent moments of the patient's smart wearable device within a preset time period before the current moment as a group of adjacent moments of the patient, obtain all groups of adjacent moments of the patient, and take the quotient between the numerical difference of each type of sensor parameter at two moments in each group of adjacent moments of the patient and the preset time interval value as the trend value of the corresponding type of sensor parameter of the corresponding group of adjacent moments of the patient;

[0094] The first calculation submodule is used to obtain the time domain trend value of each type of sensor parameter of the patient based on the trend value of each type of sensor parameter of all groups of adjacent moments of the patient.

[0095] In this embodiment, the preset time interval is the length of the time interval between two adjacent moments of the patient's smart wearable device within a preset time period before the current moment, and the unit of the preset time interval is s.

[0096] The beneficial effects of the above technology are: based on the patient's smart wearable device's all-type sensor parameters at all times within a preset time period before the current moment and the preset time intervals, the trend value of each type of sensor parameter of the patient at all groups of adjacent moments is obtained, and then based on the trend value of each type of sensor parameter of the patient at all groups of adjacent moments, the time domain trend value of each type of sensor parameter of the patient is obtained, thereby realizing the quantification of the comprehensive development trend of each type of sensor parameter of the patient in the time domain.

[0097] Embodiment 5:

[0098] On the basis of Example 4, based on the postoperative warning device of the smart wearable device, the first calculation submodule obtains the time domain trend value of each type of sensor parameter of the patient based on the trend value of each type of sensor parameter at adjacent moments of all groups of the patient, including:

[0099]

[0100] Among them, β is the time domain trend value of the patient's current calculation sensor parameter, α is the number of groups of all groups of patients at adjacent moments, and μ x The standard deviation of the trend value of the current calculated class sensor parameter at adjacent moments for all groups of patients, μ z is the mean value of the trend value of the current calculated class sensor parameters of all groups of patients at adjacent moments, μ max is the maximum value of the trend value of the current calculated class sensor parameters of all groups of patients at adjacent moments, μ min is the minimum value of the trend values ​​of the current calculation type sensor parameters of all groups of patients at adjacent moments, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0101] The beneficial effects of the above technology are: according to the trend values ​​of each type of sensor parameters at adjacent moments of all groups of patients, the time domain trend value of each type of sensor parameters of the patient is obtained, so that the comprehensive development trend of each type of sensor parameters of the patient in the time domain can be quantified. This embodiment gives in detail a specific method for quantifying the comprehensive development trend of each type of sensor parameters of the patient in the time domain.

[0102] Embodiment 6:

[0103] On the basis of Example 2, a postoperative warning device based on a smart wearable device is constructed with modules including:

[0104] The preprocessing submodule is used to take the moment when the patient is similar to each similar patient in all types of sensor parameters as the similar moment of the corresponding similar patients, and judge whether the length of the remaining time period after the first similar moment of each similar patient's smart wearable device in the entire postoperative warning time period is greater than the length of the preset time period. If so, the time period with the same length as the preset time period is intercepted from the corresponding remaining time period from the front to the back, and regarded as the similar time period of the corresponding similar patients; otherwise, the corresponding remaining time period is filled, and the obtained filled remaining time period is regarded as the similar time period of the corresponding similar patients;

[0105] The first construction submodule is used to obtain the time domain trend value of all class sensor parameters of each similar patient based on all class sensor parameters of each similar patient's smart wearable device at all times in a similar time period, and to define the ordinal values ​​of all similar patients from 1 in descending order according to the sum of the time domain trend values ​​of all class sensor parameters of each similar patient, and obtain the ordinal definition result. Based on the time domain trend values ​​of all class sensor parameters of all similar patients and the ordinal definition results, the standard trend matrix of the patient is obtained, which is:

[0106]

[0107] Wherein, Q is the standard trend matrix of the patient, w1 is the time domain trend value of the heart rate parameter of the similar patient whose ordinal definition result is 1, r1 is the time domain trend value of the blood pressure parameter of the similar patient whose ordinal definition result is 1, h1 is the time domain trend value of the body temperature parameter of the similar patient whose ordinal definition result is 1, b1 is the time domain trend value of the blood oxygen saturation parameter of the similar patient whose ordinal definition result is 1, w2 is the time domain trend value of the heart rate parameter of the similar patient whose ordinal definition result is 2, r2 is the time domain trend value of the blood pressure parameter of the similar patient whose ordinal definition result is 2, h2 is the time domain trend value of the body temperature parameter of the similar patient whose ordinal definition result is 2, b2 is the time domain trend value of the blood oxygen saturation parameter of the similar patient whose ordinal definition result is 2, w n The time domain trend value of the heart rate parameter of similar patients with ordinal definition result n, r n The time domain trend value of the blood pressure parameter of similar patients with ordinal definition result n, h n The temporal trend value of the temperature parameter of similar patients with ordinal definition result n, b n The time domain trend value of the blood oxygen saturation parameter of similar patients with ordinal definition result n, where n is the total number of similar patients;

[0108] The second construction submodule is used to obtain the patient's analysis trend matrix based on the time-domain trend values ​​of all sensor-like parameters of the patient and the patient's standard trend matrix.

[0109] In this embodiment, the remaining time period is the time period after the first similar moment of the smart wearable device of the similar patient within the entire postoperative warning time period.

[0110] In this embodiment, time period padding is to pad the length of the remaining time period to the same as the length of the preset time period, and all types of sensor parameters of similar patients' smart wearable devices at each moment in the padded time period are set to the corresponding type of preset padded sensor parameters (the average of each type of sensor parameter settings of similar patients' smart wearable devices at all moments in the remaining time period before time period padding is performed).

[0111] In this embodiment, based on all sensor-like parameters of each similar patient's smart wearable device at all times in a similar time period, the time domain trend value of all sensor-like parameters of each similar patient is obtained, that is:

[0112] The first calculation module process is repeated for all types of sensor parameters of each similar patient's smart wearable device at all times within a similar time period (only the preset time period before the current moment of the patient's smart wearable device is replaced with the similar patient's smart wearable device in a similar time period, and the rest of the processing steps are the same), and the trend value of each type of sensor parameter at all groups of adjacent moments of each similar patient is obtained, and then the time domain trend value of each type of sensor parameter of the patient is obtained according to the trend value of each type of sensor parameter at all groups of adjacent moments of each similar patient.

[0113] The beneficial effects of the above technology are: according to the length of the remaining time period after the first similar moment of each similar patient's smart wearable device within the entire postoperative warning time period, the similar time period of each similar patient is obtained, and then according to the similar time period of each similar patient, the time domain trend value of all sensor-like parameters of each similar patient is obtained, and according to the time domain trend values ​​of all sensor-like parameters of all similar patients, the standard trend matrix of the patient is obtained, and finally, according to the standard trend matrix of the patient, the analysis trend matrix of the patient is obtained. This embodiment gives in detail a specific method for obtaining the standard trend matrix of the patient according to the time domain trend values ​​of all sensor-like parameters of all similar patients.

[0114] Embodiment 7:

[0115] On the basis of Example 6, the postoperative warning device based on the smart wearable device, the second building submodule includes:

[0116] a preprocessing unit, configured to use the difference between the sum of the time-domain trend values ​​of all the class sensor parameters of each similar patient and the sum of the time-domain trend values ​​of all the class sensor parameters of the patient as the trend difference between the patient and each similar patient, and use the similar patient corresponding to the minimum value of the trend difference between the patient and all the similar patients as the replacement patient;

[0117] The second construction unit is used to replace all matrix elements of the matrix column corresponding to the replacement patient in the patient's standard trend matrix with the time domain trend value of the corresponding class sensor parameter of the patient, so as to obtain the patient's analysis trend matrix.

[0118] The beneficial effect of the above technology is: based on the time domain trend values ​​of all types of sensor parameters of the patient and the standard trend matrix of the patient, the patient's analysis trend matrix is ​​obtained, which is convenient for the subsequent calculation of the patient's vagus nerve reflex occurrence value. This embodiment gives in detail a specific method for obtaining the patient's analysis trend matrix based on the time domain trend values ​​of all types of sensor parameters of the patient and the standard trend matrix of the patient.

[0119] Embodiment 8:

[0120] On the basis of Example 1, the postoperative warning device based on the smart wearable device, the second calculation module includes:

[0121] The second acquisition submodule is used to obtain the vagus nerve reflex occurrence results of all similar patients, and judge whether the vagus nerve reflex occurrence result of each similar patient is the occurrence of vagus nerve reflex. If so, 1 is used as the vagus nerve reflex occurrence score of the corresponding similar patient, otherwise, 0 is used as the vagus nerve reflex occurrence score of the corresponding similar patient;

[0122] The second calculation submodule is used to obtain the patient's vagus nerve reflex occurrence value based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence score values ​​of all similar patients, that is:

[0123]

[0124] Among them, τ is the patient's vagus nerve reflex occurrence value, The number of similar patients with a score of 1 for vagal reflex occurrence, is the number of patients with a vagal reflex score of 0 among all similar patients, Q is the rank of the patient's standard trend matrix, E is the rank of the patient's analytical trend matrix, n is the total number of similar patients, ln is the natural logarithm, and the value of the natural constant e is 2.718.

[0125] The beneficial effects of the above technology are: based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients, the patient's vagus nerve reflex occurrence value is obtained, and the possibility of the patient's vagus nerve reflex occurring after the current moment is quantified. This embodiment gives in detail a specific method for quantifying the possibility of the patient's vagus nerve reflex occurring after the current moment.

[0126] Embodiment 9:

[0127] On the basis of Example 1, based on the postoperative warning device of the smart wearable device, the warning module obtains the postoperative warning result of the patient's smart wearable device based on the patient's vagus nerve reflex occurrence value, including:

[0128] Determine whether the patient's vagus nerve reflex occurrence value is greater than the preset vagus nerve reflex occurrence value threshold. If so, control the patient's smart wearable device to turn on the red light; otherwise, control the patient's smart wearable device to turn on the green light.

[0129] In this embodiment, the preset vagus nerve reflex occurrence value threshold is a pre-set vagus nerve reflex occurrence value threshold used to determine whether the red light or green light of the patient's smart wearable device is on.

[0130] The beneficial effects of the above technology are: according to the patient's vagus nerve reflex occurrence value, the postoperative warning results of the patient's smart wearable device are obtained, which helps medical staff to detect the deterioration of the patient's vital signs early, reduce postoperative complications, reduce the incidence of vagus nerve reflex, and improve the patient's sense of security and satisfaction.

[0131] Embodiment 10:

[0132] The present invention provides a postoperative warning method based on a smart wearable device, which is applied to implement any one of claims 1 to 9 of a postoperative warning device based on a smart wearable device, with reference to Figure 2 ,include:

[0133] S1: Obtain all similar patients based on all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment;

[0134] S2: based on all sensor-like parameters of the patient's smart wearable device at all times within a preset time period before the current time, obtaining the time domain trend values ​​of all sensor-like parameters of the patient;

[0135] S3: obtaining a standard trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of all similar patients, and obtaining an analysis trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of the patient and the standard trend matrix of the patient;

[0136] S4: based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients, the patient's vagus nerve reflex occurrence value is obtained;

[0137] S5: Based on the patient's vagus nerve reflex occurrence value, obtain the postoperative warning results of the patient's smart wearable device.

[0138] The beneficial effects of the above technology are as follows: according to all the sensor-like parameters of the patient's smart wearable device at each moment in the preset time period before the current moment, all similar patients are obtained, and some historical patients whose postoperative physiological signals and health data are similar to the patient are screened out from all historical patients in the database; according to all the sensor-like parameters of the patient's smart wearable device at all moments in the preset time period before the current moment, the time domain trend values ​​of all the sensor-like parameters of the patient are obtained, and the comprehensive development trend of each type of sensor parameter of the patient in the time domain is quantified, and then according to the time domain trend values ​​of all the sensor-like parameters of all similar patients, the standard trend matrix of the patient is obtained, which is convenient for the subsequent determination of the patient's analysis trend matrix According to the time domain trend values ​​of all sensor parameters of the patient and the standard trend matrix of the patient, the analysis trend matrix of the patient is obtained, which is convenient for the calculation of the vagus nerve reflex occurrence value of the subsequent patient. Then, according to the analysis trend matrix of the patient, the standard trend matrix of the patient and the vagus nerve reflex occurrence results of all similar patients, the vagus nerve reflex occurrence value of the patient is obtained, which realizes the quantification of the possibility of vagus nerve reflex occurrence after the current moment. Finally, according to the vagus nerve reflex occurrence value of the patient, the postoperative early warning result of the patient's smart wearable device is obtained, which helps medical staff to detect the deterioration of the patient's vital signs early, reduce postoperative complications, reduce the incidence of vagus nerve reflex, and improve the patient's sense of security and satisfaction.

[0139] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention, and the present invention is also intended to include these changes and modifications.

Claims

1. A postoperative warning device based on a smart wearable device, characterized in that: include: A screening module, used to obtain all similar patients based on all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment; A first calculation module is used to obtain the time domain trend value of all sensor parameters of the patient based on all sensor parameters of the patient's smart wearable device at all times within a preset time period before the current time; A building block is used to obtain a standard trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of all similar patients, and to obtain an analysis trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of the patient and the standard trend matrix of the patient; A second calculation module is used to obtain the patient's vagus nerve reflex occurrence value based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients; The early warning module is used to obtain the postoperative early warning results of the patient's smart wearable device based on the patient's vagus nerve reflex occurrence value.

2. The postoperative warning device based on smart wearable device according to claim 1, characterized in that: Screening modules include: The first acquisition submodule is used to obtain all sensor parameters of the patient's smart wearable device at each moment in a preset time period before the current moment, wherein all sensor parameters include heart rate parameters, blood pressure parameters, body temperature parameters and blood oxygen saturation parameters; The judgment submodule is used to take all historical patients in the database as reference patients. If the value difference between each type of sensor parameter of the patient's smart wearable device at the initial moment within the preset time period before the current moment and the corresponding type of sensor parameter of each reference patient's smart wearable device at each moment in the entire postoperative warning time period is less than the corresponding type of sensor parameter difference threshold, it is determined that the patient and the corresponding reference patient are similar in the corresponding type of sensor parameter at the corresponding moment; The screening submodule is used to determine that the corresponding reference patient is a similar patient when the patient is determined to be similar to each reference patient in all sensor-like parameters at any time.

3. The postoperative warning device based on smart wearable device according to claim 1, characterized in that: Also includes: The alarm module is used to control the red light of the patient's smart wearable device to turn on when at least one type of sensor parameter among all types of sensor parameters of the patient's smart wearable device at the current moment is not within the corresponding type of sensor parameter range.

4. The postoperative warning device based on smart wearable device according to claim 1, characterized in that: The first computing module includes: A processing submodule is used to take two adjacent moments of the patient's smart wearable device within a preset time period before the current moment as a group of adjacent moments of the patient, obtain all groups of adjacent moments of the patient, and take the quotient between the numerical difference of each type of sensor parameter at two moments in each group of adjacent moments of the patient and the preset time interval value as the trend value of the corresponding type of sensor parameter of the corresponding group of adjacent moments of the patient; The first calculation submodule is used to obtain the time domain trend value of each type of sensor parameter of the patient based on the trend value of each type of sensor parameter of all groups of adjacent moments of the patient.

5. The postoperative warning device based on smart wearable device according to claim 4 is characterized in that: The method of obtaining the time domain trend value of each type of sensor parameter of the patient based on the trend value of each type of sensor parameter of all groups of adjacent moments of the patient by the first calculation submodule comprises: Among them, β is the time domain trend value of the patient's current calculation sensor parameter, α is the number of groups of all groups of patients at adjacent moments, and μ x The standard deviation of the trend value of the current calculated class sensor parameter at adjacent moments for all groups of patients, μ z is the mean value of the trend value of the current calculated class sensor parameters of all groups of patients at adjacent moments, μ max is the maximum value of the trend value of the current calculated class sensor parameters of all groups of patients at adjacent moments, μ min is the minimum value of the trend values ​​of the current calculation type sensor parameters of all groups of patients at adjacent moments, ln is the natural logarithm, and the value of the natural constant e is 2.

718.

6. The postoperative warning device based on smart wearable device according to claim 2, characterized in that: Building blocks, including: The preprocessing submodule is used to take the moment when the patient is similar to each similar patient in all types of sensor parameters as the similar moment of the corresponding similar patients, and judge whether the length of the remaining time period after the first similar moment of each similar patient's smart wearable device in the entire postoperative warning time period is greater than the length of the preset time period. If so, the time period with the same length as the preset time period is intercepted from the corresponding remaining time period from the front to the back, and regarded as the similar time period of the corresponding similar patients; otherwise, the corresponding remaining time period is filled, and the obtained filled remaining time period is regarded as the similar time period of the corresponding similar patients; The first construction submodule is used to obtain the time domain trend value of all class sensor parameters of each similar patient based on all class sensor parameters of each similar patient's smart wearable device at all times in a similar time period, and to define the ordinal values ​​of all similar patients from 1 in descending order according to the sum of the time domain trend values ​​of all class sensor parameters of each similar patient, and obtain the ordinal definition result. Based on the time domain trend values ​​of all class sensor parameters of all similar patients and the ordinal definition results, the standard trend matrix of the patient is obtained, which is: Wherein, Q is the standard trend matrix of the patient, w1 is the time domain trend value of the heart rate parameter of the similar patient whose ordinal definition result is 1, r1 is the time domain trend value of the blood pressure parameter of the similar patient whose ordinal definition result is 1, h1 is the time domain trend value of the body temperature parameter of the similar patient whose ordinal definition result is 1, b1 is the time domain trend value of the blood oxygen saturation parameter of the similar patient whose ordinal definition result is 1, w2 is the time domain trend value of the heart rate parameter of the similar patient whose ordinal definition result is 2, r2 is the time domain trend value of the blood pressure parameter of the similar patient whose ordinal definition result is 2, h2 is the time domain trend value of the body temperature parameter of the similar patient whose ordinal definition result is 2, b2 is the time domain trend value of the blood oxygen saturation parameter of the similar patient whose ordinal definition result is 2, w n The time domain trend value of the heart rate parameter of similar patients with ordinal definition result n, r n The time domain trend value of the blood pressure parameter of similar patients with ordinal definition result n, h n The temporal trend value of the temperature parameter of similar patients with ordinal definition result n, b n The time domain trend value of the blood oxygen saturation parameter of similar patients with ordinal definition result n, where n is the total number of similar patients; The second construction submodule is used to obtain the patient's analysis trend matrix based on the time-domain trend values ​​of all sensor-like parameters of the patient and the patient's standard trend matrix.

7. The postoperative warning device based on smart wearable device according to claim 6, characterized in that: The second building block includes: a preprocessing unit, configured to use the difference between the sum of the time-domain trend values ​​of all the class sensor parameters of each similar patient and the sum of the time-domain trend values ​​of all the class sensor parameters of the patient as the trend difference between the patient and each similar patient, and use the similar patient corresponding to the minimum value of the trend difference between the patient and all the similar patients as the replacement patient; The second construction unit is used to replace all matrix elements of the matrix column corresponding to the replacement patient in the patient's standard trend matrix with the time domain trend value of the corresponding class sensor parameter of the patient, so as to obtain the patient's analysis trend matrix.

8. The postoperative warning device based on smart wearable device according to claim 1, characterized in that: The second computing module includes: The second acquisition submodule is used to obtain the vagus nerve reflex occurrence results of all similar patients, and judge whether the vagus nerve reflex occurrence result of each similar patient is the occurrence of vagus nerve reflex. If so, 1 is used as the vagus nerve reflex occurrence score of the corresponding similar patient, otherwise, 0 is used as the vagus nerve reflex occurrence score of the corresponding similar patient; The second calculation submodule is used to obtain the patient's vagus nerve reflex occurrence value based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence score values ​​of all similar patients, that is: Among them, τ is the patient's vagus nerve reflex occurrence value, The number of similar patients with a score of 1 for vagal reflex occurrence, is the number of patients with a vagal reflex score of 0 among all similar patients, Q is the rank of the patient's standard trend matrix, E is the rank of the patient's analytical trend matrix, n is the total number of similar patients, ln is the natural logarithm, and the value of the natural constant e is 2.

718.

9. The postoperative warning device based on smart wearable device according to claim 1, characterized in that: The method for obtaining the postoperative warning result of the patient's smart wearable device based on the patient's vagus nerve reflex occurrence value by the early warning module includes: Determine whether the patient's vagus nerve reflex occurrence value is greater than the preset vagus nerve reflex occurrence value threshold. If so, control the patient's smart wearable device to turn on the red light; otherwise, control the patient's smart wearable device to turn on the green light.

10. The postoperative warning method based on a smart wearable device according to claim 1, characterized in that: A postoperative warning device based on a smart wearable device, used to implement any one of claims 1 to 9, comprising: S1: Obtain all similar patients based on all sensor-like parameters of the patient's smart wearable device at each moment in a preset time period before the current moment; S2: based on all sensor-like parameters of the patient's smart wearable device at all times within a preset time period before the current time, obtaining the time domain trend values ​​of all sensor-like parameters of the patient; S3: obtaining a standard trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of all similar patients, and obtaining an analysis trend matrix of the patient based on the time-domain trend values ​​of all sensor-like parameters of the patient and the standard trend matrix of the patient; S4: based on the patient's analysis trend matrix, the patient's standard trend matrix and the vagus nerve reflex occurrence results of all similar patients, the patient's vagus nerve reflex occurrence value is obtained; S5: Based on the patient's vagus nerve reflex occurrence value, obtain the postoperative warning results of the patient's smart wearable device.

Citation Information

Cited By

  • Postoperative risk early warning method and system based on machine learning

    CN120432085A