A method and system for monitoring intraoperative blood pressure data based on thyroid disease

Abstract

The application discloses a kind of monitoring method and system based on intraoperative blood pressure data of thyroid disease, it is related to thyroid surgery technical field.The method steps include: collecting the related data of the blood pressure of thyroid disease patient intraoperative influence;After the pre-processing of related data, extract the multidimensional feature of blood pressure intraoperative influence;According to the multidimensional feature of blood pressure preoperative influence and the multidimensional feature of blood pressure intraoperative influence, obtain cause analysis result;According to cause analysis result and patient blood pressure threshold, carry out graded blood pressure alarm.The application is by collecting blood pressure data, electrocardiogram data and skin conductance data, carries out multidimensional feature extraction, and is based on the comparison of multidimensional feature before operation and intraoperative, realizes the quantitative score of cause of blood pressure rise, simultaneously based on the patient blood pressure threshold of matching operation stage realizes the accurate alarm of patient blood pressure, such that not only can realize the early warning of blood pressure, can also give corresponding cause, provide reliable data support for accurate antihypertensive.

Description

Technical Field

[0001] This application relates to the field of thyroid surgery technology, specifically a method and system for monitoring intraoperative blood pressure data in thyroid diseases. Background Technology

[0002] Thyroid surgery is prone to acute hypertension and drastic blood pressure fluctuations due to the unique anatomy of the neck, intraoperative glandular traction, tracheal irritation, pain stress, and frequent autonomic nerve fluctuations. Sudden intraoperative hypertension can easily induce serious complications such as surgical site bleeding, blurred vision, arrhythmia, and myocardial ischemia, directly affecting surgical safety and prognosis. Traditional blood pressure monitoring methods during thyroid surgery often trigger alarms based on real-time blood pressure readings exceeding the target range, which has the following shortcomings in practical application: Elevated blood pressure is a direct indicator. Before blood pressure exceeds the standard, there are already precursors such as neurological disorders and physical stress. Alarms are only issued after blood pressure exceeds the standard, which has a significant lag. Moreover, the use of a fixed static warning threshold for blood pressure exceeding the standard can easily lead to over-warning during surgery due to low-risk, slight fluctuations. This results in poor clinical applicability. Furthermore, the causes of blood pressure exceeding the standard are often based on the doctor's subjective speculation, which has a large margin of error and cannot achieve precise and effective blood pressure reduction. Summary of the Invention

[0003] In view of the deficiencies in the existing technology, the technical problem to be solved by this application is: how to achieve early warning of blood pressure, and while maintaining the accuracy of blood pressure warning, to accurately locate the causes of blood pressure exceeding the standard.

[0004] To achieve the above objectives, in a first aspect, embodiments of this application provide a method for monitoring intraoperative blood pressure data based on thyroid diseases, the method comprising the following steps: Data on the impact of blood pressure during surgery in patients with thyroid disease were collected. This data included blood pressure data, electrocardiogram data, and skin conductance data. After preprocessing the relevant data, multidimensional features affecting blood pressure during the operation were extracted; Based on the multidimensional characteristics of preoperative and intraoperative blood pressure effects, the causative factor analysis results were obtained. Based on the results of the precipitating factor analysis and the patient's blood pressure threshold, graded blood pressure alerts are issued.

[0005] In conjunction with the first aspect, in one embodiment, the multidimensional features affecting blood pressure during the extraction procedure include: Based on the preprocessed blood pressure data, the rate of blood pressure rise and the peak blood pressure amplitude are obtained. Based on the preprocessed ECG data, the temporal mean of heart rate, the temporal mean of low-frequency / high-frequency ratio, and the slope of the gradual increase in heart rate were obtained. Based on the preprocessed skin conductance data, the amplitude of skin conductance changes is obtained.

[0006] In conjunction with the first aspect, in one embodiment, the process of obtaining the causative factor analysis results based on the multidimensional characteristics affecting blood pressure preoperatively and intraoperatively includes: Based on the preoperative multidimensional characteristics affecting blood pressure, the intraoperative multidimensional characteristics affecting blood pressure were scored; Obtain the trigger matching score based on the scoring results; Based on the trigger matching score and preset threshold, the trigger analysis results are obtained.

[0007] In conjunction with the first aspect, in one embodiment, the process of scoring the multidimensional characteristics affecting blood pressure during surgery based on preoperative multidimensional characteristics includes: Based on the amplitude of changes in skin conductance during the operation, and compared with the amplitude of changes in skin conductance before the operation, the amplitude of the intraoperative deviation is determined as the deviation amount of skin conductance change trend. According to the preset linear mapping logic between the deviation amount of skin conductance change trend and the score, the deviation score of skin conductance change trend is obtained. Based on the mean heart rate time series during the operation, and compared with the mean heart rate time series before the operation, the intraoperative deviation amplitude is determined as abnormal heart rate fluctuation. According to the preset linear mapping logic between abnormal heart rate fluctuation amount and score, the abnormal heart rate fluctuation score is obtained. Based on the intraoperative low-frequency / high-frequency ratio time series mean, and compared with the preoperative low-frequency / high-frequency ratio time series mean, the intraoperative deviation amplitude is determined as the autonomic rhythm mutation amount. According to the preset linear mapping logic between the autonomic rhythm mutation amount and the score, the autonomic rhythm mutation score is obtained. Based on the slope of the progressive heart rate increase during the operation, and compared with the slope of the progressive heart rate increase before the operation, the intraoperative deviation range is determined as the progressive heart rate increase deviation amount. According to the preset linear mapping logic between the progressive heart rate increase deviation amount and the score, the progressive heart rate increase deviation score is obtained. Based on the intraoperative blood pressure rise rate, compare it with the preoperative blood pressure rise rate to determine the intraoperative deviation range, which is used as the short-term blood pressure rise rate deviation. According to the preset linear mapping logic between the short-term blood pressure rise rate deviation and the score, the short-term blood pressure rise rate score is obtained. Based on the intraoperative blood pressure peak amplitude, the intraoperative deviation amplitude is determined by comparing it with the preoperative blood pressure peak amplitude. This deviation is used as the short-term blood pressure fluctuation peak deviation. Based on the preset linear mapping logic between the short-term blood pressure fluctuation peak deviation and the score, the short-term blood pressure fluctuation peak deviation score is obtained.

[0008] In conjunction with the first aspect, in one embodiment, the trigger matching score includes a mental stress trigger matching score, a vagus nerve block trigger matching score, and a tracheal traction reflex trigger matching score; wherein the mental stress trigger matching score is obtained by weighted summation of skin conductance change trend deviation score and abnormal heart rate fluctuation score; The vagal nerve block type induced cause matching score is obtained by weighted summation of autonomic rhythm mutation score and heart rate progressive increase deviation score; The tracheal traction reflex-type precipitation matching score is obtained by weighted summation of the short-term blood pressure rise rate score and the short-term blood pressure fluctuation peak offset score.

[0009] In conjunction with the first aspect, in one embodiment, the process of obtaining the cause analysis results based on the cause matching score and a preset threshold includes: When the matching score of stress-related triggers is greater than a preset threshold, stress-related triggers are identified. When the matching score of vagal nerve block type precipitate is greater than the preset threshold, vagal nerve block type precipitate is identified. When the tracheal traction reflex type precipitate matching score is greater than the preset threshold, the tracheal traction reflex type precipitate is identified.

[0010] In conjunction with the first aspect, in one embodiment, the patient's blood pressure threshold is obtained as follows: Blood pressure data were collected for a set duration while the patient was in a quiet, unstimulated, drug-free, and blood pressure-free environment. After removing blood pressure data that deviated from twice the standard deviation of the mean systolic blood pressure, valid systolic blood pressure data were obtained. After obtaining the mean systolic blood pressure and standard deviation of systolic blood pressure from effective systolic blood pressure data, the systolic blood pressure threshold is obtained, and its calculation formula is: Systolic blood pressure threshold = mean systolic blood pressure + dynamic coefficient × standard deviation of systolic blood pressure; After removing blood pressure data that deviated from twice the standard deviation of the mean diastolic blood pressure, the effective diastolic blood pressure data were obtained. After obtaining the mean and standard deviation of diastolic blood pressure from the effective diastolic blood pressure data, the diastolic blood pressure threshold is obtained, and its calculation formula is as follows: Diastolic blood pressure threshold = mean diastolic blood pressure + dynamic coefficient × standard deviation of diastolic blood pressure

[0011] In conjunction with the first aspect, in one embodiment, the dynamic coefficient is adjusted based on the surgical stage; the surgical stage includes skin incision, gland separation, tracheal traction, tissue suturing, and tube removal. During the skin incision stage, the dynamic coefficient is set to 1.5; during the gland separation and tracheal traction stage, the dynamic coefficient is set to 2.0; during the tissue suturing stage, the dynamic coefficient is set to 1.6; and during the tube removal stage, the dynamic coefficient is set to 1.8.

[0012] In conjunction with the first aspect, in one embodiment, the process of grading blood pressure alarms based on the precipitating factor analysis results and the patient's blood pressure threshold includes: A yellow alert is issued when a stress-related trigger occurs and the patient's real-time blood pressure is within the systolic and diastolic blood pressure thresholds. An orange alert is issued when vagal nerve block or mental stress triggers occur, and the systolic blood pressure threshold is less than the patient's real-time systolic blood pressure and less than the sum of the systolic blood pressure threshold and 0.5 times the standard deviation of systolic blood pressure, or the diastolic blood pressure threshold is less than the patient's real-time diastolic blood pressure and less than the sum of the diastolic blood pressure threshold and 0.5 times the standard deviation of diastolic blood pressure. A red alert is issued when a tracheal traction reflex trigger occurs and the patient's real-time systolic blood pressure is greater than or equal to the sum of the systolic blood pressure threshold and 0.5 times the standard deviation of systolic blood pressure, or the patient's real-time diastolic blood pressure is greater than or equal to the sum of the diastolic blood pressure threshold and 0.5 times the standard deviation of diastolic blood pressure.

[0013] Secondly, embodiments of this application provide a monitoring system based on intraoperative blood pressure data for thyroid diseases, the system comprising: The data acquisition module is used to collect the aforementioned intraoperative data related to blood pressure. The feature extraction module is used to extract the aforementioned multidimensional features affecting blood pressure based on relevant data on intraoperative blood pressure. The precipitation analysis module is used to: execute the above-mentioned process of obtaining precipitation analysis results based on the multidimensional characteristics of preoperative and intraoperative blood pressure effects; A personalized blood pressure threshold localization module is used to perform the above-mentioned method of obtaining the patient's blood pressure threshold; The graded blood pressure alarm module is used to execute the above-mentioned process of graded blood pressure alarm based on the cause analysis results and the patient's blood pressure threshold.

[0014] Compared with the prior art, the advantages of this application are: (1) By collecting blood pressure data, electrocardiogram data and skin conductance data, multidimensional features are extracted, and based on the comparison of multidimensional features before and during the operation, the quantitative scoring of the causes of blood pressure elevation is realized. At the same time, based on the blood pressure threshold of the patient in the matching surgical stage, the patient's blood pressure is accurately alerted. This not only enables early warning of blood pressure, but also provides the corresponding causes, providing reliable data support for accurate blood pressure reduction.

[0015] (2) Based on the patient’s preoperative blood pressure data and the surgical stage of thyroid surgery, a differentiated dynamic coefficient is configured to obtain the appropriate patient blood pressure threshold, avoid the defects of traditional static threshold alarm, realize the distinction between physiological small fluctuations and pathological high-risk abnormalities, effectively reduce the probability of over-warning and missed warning, and realize refined risk control for different patients at different surgical stages. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of a method for monitoring intraoperative blood pressure data based on thyroid disease, as described in this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] In a first aspect, embodiments of this application provide a method for monitoring intraoperative blood pressure data based on thyroid diseases, referring to... Figure 1 The method includes the following steps: S1. Collect relevant data on blood pressure during surgery in patients with thyroid diseases (blood pressure data, electrocardiogram data, and skin conductance data). S2. After preprocessing the relevant data, extract the multidimensional features that affect blood pressure during the operation; S3. Based on the multidimensional characteristics of preoperative and intraoperative blood pressure effects, obtain the results of the causative factor analysis. S4. Based on the results of the precipitating factor analysis and the patient's blood pressure threshold, graded blood pressure alarms are issued.

[0022] By collecting blood pressure, electrocardiogram, and skin conductance data, multidimensional features are extracted. Based on the comparison of multidimensional features before and during surgery, quantitative scoring of the causes of elevated blood pressure is achieved. At the same time, based on the patient's blood pressure threshold matched to the surgical stage, accurate blood pressure warning is achieved. This not only enables early warning of blood pressure but also identifies the corresponding causes, providing reliable data support for precise blood pressure reduction.

[0023] In one embodiment, the acquisition device is clock-aligned before collecting relevant data on blood pressure during surgery in patients with thyroid disease. The blood pressure data acquisition device can be an upper limb continuous non-invasive blood pressure module, the electrocardiogram (ECG) data acquisition device can be an ECG module, and the skin conductance data acquisition device can be a palm skin conductance sensor.

[0024] Based on this, after acquiring the relevant data, the preprocessing method for blood pressure data includes: reading continuous blood pressure waveform data frame by frame, first determining the integrity of a single frame waveform, and removing incomplete frames with waveform distortion (integrity < 60%); then comparing the time sequence values ​​before and after frame by frame, and removing frames with sudden abnormal jumps (single frame values ​​deviating from the mean before and after by 30%); and interpolating and repairing the intermittent and missing effective blood pressure waveforms (taking the mean of the before and after frames for interpolation) to retain normal physiological fluctuation data of the human body and avoid loss of effective signals due to excessive cleaning.

[0025] Furthermore, based on the preprocessed blood pressure data, the real-time rate of change of blood pressure is obtained, and then the following features are acquired: Rate of blood pressure rise: The slope of continuous blood pressure changes over a 10-second window; Peak blood pressure amplitude: The maximum real-time blood pressure during the operation within a 10-second window.

[0026] For electrocardiogram (ECG) data, the preprocessing method includes: performing power frequency filtering and electromyography (EMG) interference removal operations on the ECG data in sequence, filtering out 50Hz power frequency interference signals and removing EMG interference signals with an amplitude greater than 2mV, in order to obtain clean and distortion-free ECG waveform time series data.

[0027] Furthermore, based on the preprocessed ECG data, real-time heart rate values, low-frequency component values, and high-frequency component values ​​of heart rate variability are extracted second by second, and the time series features of the low-frequency / high-frequency ratio are generated second by second.

[0028] Based on this, the following features are obtained: Heart rate time-series mean: the arithmetic mean of all real-time heart rates per second within a 10-second window; Low-frequency / high-frequency ratio time-series mean: the arithmetic mean of all second-by-second low-frequency / high-frequency ratios within a 10-second window; Heart rate progressive rate increase slope: The linear slope of the temporal change of heart rate fitted within a single 10-second observation window is used to characterize the real-time progressive rate of increase of heart rate during surgery.

[0029] For skin conductance data (skin conductance values), the preprocessing methods include: smoothing and filtering the skin conductance data to remove high-frequency jitter noise and retain continuous, stable skin conductance time series data with undistorted signal morphology.

[0030] Furthermore, based on the preprocessed skin conductance data, the amplitude of intraoperative skin conductance changes was statistically analyzed within a continuous 10-second synchronous time window.

[0031] In one embodiment, the preoperative multidimensional characteristics affecting blood pressure also include: blood pressure rise rate, peak blood pressure amplitude, temporal mean heart rate, temporal mean low-frequency / high-frequency ratio, slope of progressive heart rate increase, and amplitude of skin conductance changes. These preoperative multidimensional characteristics affecting blood pressure are obtained when the patient is in a resting state upon entering the operating room, without stimulation, without drug intervention, and without elevated blood pressure (exceeding normal standards, such as systolic blood pressure ≥140 mmHg or diastolic blood pressure ≥90 mmHg).

[0032] In one embodiment, the process for obtaining the causative factor analysis results based on the multidimensional characteristics affecting blood pressure preoperatively and intraoperatively includes: Based on the preoperative multidimensional characteristics affecting blood pressure, the intraoperative multidimensional characteristics affecting blood pressure are scored; the specific steps include: Based on the amplitude of changes in skin conductance during the operation, and compared with the amplitude of changes in skin conductance before the operation, the intraoperative offset amplitude is determined (the intraoperative offset amplitude is obtained by obtaining the absolute difference between the intraoperative feature value and the preoperative feature value, and dividing the absolute difference by the preoperative feature value, i.e., obtaining the intraoperative offset amplitude), which is used as the skin conductance change trend offset. According to the preset linear mapping logic between the skin conductance change trend offset and the score (e.g., the score is 0-100 points, and the maximum skin conductance change trend offset is set to 50%, when it is ≥50%, it is recorded as 100 points), the skin conductance change trend offset score is obtained. Based on the mean heart rate time series during the operation, and compared with the mean heart rate time series before the operation, the intraoperative deviation amplitude is determined as abnormal heart rate fluctuation. According to the preset linear mapping logic between abnormal heart rate fluctuation amount and score (e.g., the score is 0-100 points, and the maximum abnormal heart rate fluctuation amount is set to 30%, and when it is ≥30%, it is recorded as 100 points), the abnormal heart rate fluctuation score is obtained. Based on the intraoperative mean of the low-frequency / high-frequency ratio, and compared with the preoperative mean of the low-frequency / high-frequency ratio, the intraoperative deviation amplitude is determined as the autonomic rhythm mutation amount. According to the linear mapping logic between the preset autonomic rhythm mutation amount and the score (e.g., the score is 0-100 points, and the maximum autonomic rhythm mutation amount is set to 80%, when it is ≥80%, it is recorded as 100 points), the autonomic rhythm mutation score is obtained. Based on the slope of the progressive heart rate increase during the operation, and compared with the slope of the progressive heart rate increase before the operation, the intraoperative deviation range is determined as the progressive heart rate increase deviation amount. According to the preset linear mapping logic between the progressive heart rate increase deviation amount and the score (e.g., the score is 0-100 points, and the maximum progressive heart rate increase deviation amount is set to 25 beats / min, when it is ≥25 beats / min, it is recorded as 100 points), the progressive heart rate increase deviation score is obtained. Based on the intraoperative blood pressure rise rate, compare it with the preoperative blood pressure rise rate to determine the intraoperative deviation range, which is used as the short-term blood pressure rise rate deviation. According to the preset linear mapping logic between the short-term blood pressure rise rate deviation and the score (e.g., the score is 0-100 points, and the maximum short-term blood pressure rise rate deviation is set to 3 mmHg / s, and when it is ≥3 mmHg / s, it is recorded as 100 points), the short-term blood pressure rise rate score is obtained. Based on the intraoperative blood pressure peak amplitude, compare it with the preoperative blood pressure peak amplitude to determine the intraoperative deviation amplitude, which is used as the short-term blood pressure fluctuation peak deviation. According to the preset linear mapping logic between the short-term blood pressure fluctuation peak deviation and the score (e.g., the score is 0-100 points, and the maximum short-term blood pressure fluctuation peak deviation is set to 25%, and when it is ≥25%, it is recorded as 100 points), the short-term blood pressure fluctuation peak deviation score is obtained.

[0033] At this point, the scoring of multidimensional characteristics affecting blood pressure during surgery can be achieved.

[0034] Based on the scoring results, obtain the trigger matching score (psychological stress trigger matching score, vagus nerve block trigger matching score, and tracheal traction reflex trigger matching score); the calculation formula for the psychological stress trigger matching score is as follows: ; In the formula, Matching scores for stress-related triggers. The score represents the shift in the trend of skin conductance changes. This represents the score for abnormal heart rate fluctuations. The formula for calculating the evoked cause matching score for vagal nerve block is: ; In the formula, For vagal nerve block-related precipitating factor matching scores, This represents the score for autonomic nervous system rhythm mutations. The score for the progressive increase in heart rate; The formula for calculating the tracheal traction reflex type evoked cause matching score is: ; In the formula, For tracheal traction reflex-related trigger matching score, The score represents the rate of increase in blood pressure over short periods. This represents the peak deviation score of short-term blood pressure fluctuations.

[0035] Based on the trigger matching score and preset thresholds, the trigger analysis results are obtained; as detailed below: When the score matching the stress-related trigger is greater than a preset threshold (e.g., ≥80 points), a stress-related trigger is identified. When the matching score of vagal nerve block type precipitate is greater than the preset threshold (e.g., ≥85 points), vagal nerve block type precipitate is identified. When the tracheal traction reflex type induced factor matching score is greater than the preset threshold (e.g., ≥90 points), the tracheal traction reflex type induced factor is identified. This type of tracheal traction reflex induced factor is only involved in the determination during the tracheal traction surgery stage.

[0036] In one embodiment, the above-mentioned patient blood pressure threshold is obtained as follows: Blood pressure data were collected for a set duration (e.g., 5 minutes) while the patient was in a quiet, unstimulated, drug-free, and blood pressure-free state. After removing blood pressure data that deviated from twice the standard deviation of the mean systolic blood pressure, valid systolic blood pressure data were obtained. After obtaining the mean systolic blood pressure and standard deviation of systolic blood pressure from effective systolic blood pressure data, the systolic blood pressure threshold is obtained, and its calculation formula is: Systolic blood pressure threshold = mean systolic blood pressure + dynamic coefficient × standard deviation of systolic blood pressure; After removing blood pressure data that deviated from twice the standard deviation of the mean diastolic blood pressure, the effective diastolic blood pressure data were obtained. After obtaining the mean and standard deviation of diastolic blood pressure from the effective diastolic blood pressure data, the diastolic blood pressure threshold is obtained, and its calculation formula is as follows: Diastolic blood pressure threshold = mean diastolic blood pressure + dynamic coefficient × standard deviation of diastolic blood pressure

[0037] The above dynamic coefficients are adjusted based on the surgical stage (skin incision, gland separation, tracheal retraction, tissue suturing, extubation), such as: Skin incision stage: The dynamic coefficient is set to 1.5. At this stage, only the skin and subcutaneous tissue are superficially incised. The intensity of mechanical stimulation is weak, the activity of intraoperative nerve reflexes is low, and the probability and risk level of abnormal blood pressure rise are the lowest. Therefore, the minimum dynamic coefficient is configured to avoid excessive warning. During the gland separation and tracheal traction stage: the dynamic coefficient is set to 2.0. This stage is a high-risk window period for thyroid surgery. Gland separation and tracheal traction will directly stimulate the vagus nerve and sympathetic nerve plexus in the neck, which can easily induce severe nerve reflexes and acute blood pressure spikes. The sudden rise in blood pressure is strong and the risk level is the highest. Therefore, the maximum dynamic coefficient is configured to amplify the individualized early warning threshold error tolerance range in order to accurately capture high-risk blood pressure abnormalities. Tissue suturing stage: The dynamic coefficient is set to 1.6. This stage mainly involves wound alignment and subcutaneous tissue and skin suturing. There is no deep gland stimulation or tracheal traction. The mechanical stimulation is mild and the nerve reflex activity is low. There are only slight blood pressure fluctuations induced by mild pain stress. The risk of blood pressure rise and suddenness is lower than in the traction and awakening stages. Therefore, a low to medium dynamic coefficient is set to suit the low fluctuation and low risk scenario of postoperative wound suturing. During the extubation procedure: the dynamic coefficient is set to 1.8. During this stage, the patient's anesthesia depth decreases, autonomic nerve function recovers, airway stimulation and pain stress are superimposed, nerve reflexes are highly active, and blood pressure fluctuates frequently. However, compared with the direct mechanical traction stimulation during surgery, the intensity and suddenness of blood pressure rise are lower. Therefore, a moderately high dynamic coefficient is set to adapt to the special physiological fluctuation risks during the recovery stage.

[0038] This approach, based on the patient's preoperative blood pressure data and the surgical stage of thyroid surgery, configures differentiated dynamic coefficients to obtain a blood pressure threshold suitable for the patient. This avoids the shortcomings of traditional static threshold alarms, distinguishes between physiological minor fluctuations and pathological high-risk abnormalities, effectively reduces the probability of over-warning and missed warnings, and enables refined risk control for different patients at different surgical stages.

[0039] Based on this, the process for graded blood pressure alerts, according to the results of the precipitating factor analysis and the patient's blood pressure threshold, includes: A yellow alert is issued when a stressful trigger occurs and the patient's real-time blood pressure is within the systolic and diastolic blood pressure thresholds. This indicates a risk of increased blood pressure, hence the warning yellow alert. At this time, the execution plan is pushed according to the anesthesia method. For example, when performing cervical plexus sedation, it is recommended to appropriately increase the sedation depth; when performing general anesthesia, it is recommended to maintain the basic anesthesia depth and add short-acting sedative drugs.

[0040] An orange alert is issued when vagal nerve block or mental stress triggers occur, and the systolic blood pressure threshold is less than the patient's real-time systolic blood pressure and less than the sum of the systolic blood pressure threshold and 0.5 times the standard deviation of systolic blood pressure, or the diastolic blood pressure threshold is less than the patient's real-time diastolic blood pressure and less than the sum of the diastolic blood pressure threshold and 0.5 times the standard deviation of diastolic blood pressure. When a vagal nerve block-type trigger appears in the orange alert, the execution plan is pushed according to the anesthesia method, such as screening for contraindications to medication such as atrioventricular block, severe heart failure, and persistent hypotension. If there are no contraindications, diltiazem hydrochloride targeted intervention is prepared.

[0041] A red alert is issued when a tracheal traction reflex trigger occurs, and the patient's real-time systolic blood pressure is ≥ the sum of the systolic blood pressure threshold and 0.5 times the standard deviation of systolic blood pressure, or the patient's real-time diastolic blood pressure is ≥ the sum of the diastolic blood pressure threshold and 0.5 times the standard deviation of diastolic blood pressure. If a tracheal traction reflex trigger occurs at this time, mechanical stimulation should be immediately suspended during the period when the procedure can be paused (as determined by the physician). After deepening the anesthesia, a short-acting antihypertensive drug should be infused.

[0042] This not only provides alerts based on the patient's blood pressure status but also identifies corresponding triggers, improving the efficiency of blood pressure reduction. Furthermore, if the three triggers mentioned above are not present, they can be ruled out, narrowing down the scope of consideration for doctors when developing a blood pressure-lowering plan.

[0043] As explained in detail, the aforementioned vagal nerve blockade-type inducing factors refer to the neurogenic abnormal blood pressure rise during general anesthesia for thyroid surgery. This refers to the inhibition of vagal nerve conduction function and a sustained decrease in tension caused by intraoperative neck manipulation and fluctuations in the depth of anesthesia, which disrupts the inherent balance of the autonomic nervous system, leading to relative excitation of the sympathetic nervous system and disorder of the autonomic nervous system rhythm. This gradually induces a pathological physiological process of increased heart rate, peripheral vasoconstriction, and elevated blood pressure. This is distinct from the active blocking effect of exogenous drugs and is an endogenous vagal nerve function inhibition state synergistically induced by surgical stress and anesthesia.

[0044] Furthermore, the pathophysiological mechanisms of vagal nerve block-type triggers include: Under normal physiological conditions, the vagus nerve (parasympathetic nerve) and the sympathetic nerve antagonize each other. When vagus nerve tone is dominant, it can inhibit heart rate, dilate peripheral blood vessels, and maintain stable blood pressure. During general anesthesia for thyroid surgery, the patient's autonomic nervous system regulation ability is weakened. When vagus nerve function is inhibited and tone is continuously reduced, the antagonistic effect on the sympathetic nerve is greatly diminished, resulting in relative activation of the sympathetic nerve and imbalance of autonomic nervous rhythm. This leads to a progressive increase in heart rate and an increase in peripheral vascular resistance, ultimately resulting in a delayed and persistent increase in blood pressure.

[0045] Secondly, embodiments of this application provide a monitoring system based on intraoperative blood pressure data for thyroid diseases, the system comprising: The data acquisition module is used to collect the aforementioned intraoperative data related to blood pressure. The feature extraction module is used to extract the aforementioned multidimensional features affecting blood pressure based on relevant data on intraoperative blood pressure. The precipitation analysis module is used to: execute the above-mentioned process of obtaining precipitation analysis results based on the multidimensional characteristics of preoperative and intraoperative blood pressure effects; A personalized blood pressure threshold localization module is used to perform the above-mentioned method of obtaining the patient's blood pressure threshold; The graded blood pressure alarm module is used to execute the above-mentioned process of graded blood pressure alarm based on the cause analysis results and the patient's blood pressure threshold.

[0046] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0047] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0048] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0049] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0050] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0051] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0052] The above are merely specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the scope of the claims.

Claims

1. A method for monitoring intraoperative blood pressure data based on thyroid diseases, characterized in that, The method includes the following steps: Data on the impact of blood pressure during surgery in patients with thyroid disease were collected. This data included blood pressure data, electrocardiogram data, and skin conductance data. After preprocessing the relevant data, multidimensional features affecting blood pressure during the operation were extracted. These multidimensional features include the rate of blood pressure rise, peak blood pressure amplitude, temporal mean heart rate, temporal mean low-frequency / high-frequency ratio, slope of gradual increase in heart rate, and amplitude of skin conductance changes. Based on the multidimensional characteristics of preoperative and intraoperative blood pressure effects, the causative factor analysis results were obtained. Based on the results of the precipitating factor analysis and the patient's blood pressure threshold, graded blood pressure alerts are issued. The process for obtaining the causative factor analysis results based on the multidimensional characteristics affecting blood pressure preoperatively and intraoperatively includes: Based on the preoperative multidimensional characteristics affecting blood pressure, the intraoperative multidimensional characteristics affecting blood pressure were scored; Obtain the trigger matching score based on the scoring results; Based on the trigger matching score and preset threshold, the trigger analysis results are obtained; The trigger matching scores include mental stress trigger matching scores, vagus nerve block trigger matching scores, and tracheal traction reflex trigger matching scores.

2. The method for monitoring intraoperative blood pressure data based on thyroid diseases according to claim 1, characterized in that, The multidimensional characteristics affecting blood pressure during the extraction procedure include: Based on the preprocessed blood pressure data, the rate of blood pressure rise and the peak blood pressure amplitude are obtained. Based on the preprocessed ECG data, the temporal mean of heart rate, the temporal mean of low-frequency / high-frequency ratio, and the slope of the gradual increase in heart rate were obtained. Based on the preprocessed skin conductance data, the amplitude of skin conductance changes is obtained.

3. The method for monitoring intraoperative blood pressure data based on thyroid diseases according to claim 2, characterized in that, The process of scoring the multidimensional characteristics affecting blood pressure during surgery based on the preoperative multidimensional characteristics affecting blood pressure includes: Based on the amplitude of changes in skin conductance during the operation, and compared with the amplitude of changes in skin conductance before the operation, the amplitude of the intraoperative deviation is determined as the deviation amount of skin conductance change trend. According to the preset linear mapping logic between the deviation amount of skin conductance change trend and the score, the deviation score of skin conductance change trend is obtained. Based on the mean heart rate time series during the operation, and compared with the mean heart rate time series before the operation, the intraoperative deviation amplitude is determined as abnormal heart rate fluctuation. According to the preset linear mapping logic between abnormal heart rate fluctuation amount and score, the abnormal heart rate fluctuation score is obtained. Based on the intraoperative low-frequency / high-frequency ratio time series mean, and compared with the preoperative low-frequency / high-frequency ratio time series mean, the intraoperative deviation amplitude is determined as the autonomic rhythm mutation amount. According to the preset linear mapping logic between the autonomic rhythm mutation amount and the score, the autonomic rhythm mutation score is obtained. Based on the slope of the progressive heart rate increase during the operation, and compared with the slope of the progressive heart rate increase before the operation, the intraoperative deviation range is determined as the progressive heart rate increase deviation amount. According to the preset linear mapping logic between the progressive heart rate increase deviation amount and the score, the progressive heart rate increase deviation score is obtained. Based on the intraoperative blood pressure rise rate, compare it with the preoperative blood pressure rise rate to determine the intraoperative deviation range, which is used as the short-term blood pressure rise rate deviation. According to the preset linear mapping logic between the short-term blood pressure rise rate deviation and the score, the short-term blood pressure rise rate score is obtained. Based on the intraoperative blood pressure peak amplitude, the intraoperative deviation amplitude is determined by comparing it with the preoperative blood pressure peak amplitude. This deviation is used as the short-term blood pressure fluctuation peak deviation. Based on the preset linear mapping logic between the short-term blood pressure fluctuation peak deviation and the score, the short-term blood pressure fluctuation peak deviation score is obtained.

4. The method for monitoring intraoperative blood pressure data based on thyroid diseases according to claim 3, characterized in that, The stress-related trigger matching score is obtained by weighted summation of the skin conductance change trend offset score and the heart rate abnormal fluctuation score. The vagal nerve block type induced cause matching score is obtained by weighted summation of autonomic rhythm mutation score and heart rate progressive increase deviation score; The tracheal traction reflex-type precipitation matching score is obtained by weighted summation of the short-term blood pressure rise rate score and the short-term blood pressure fluctuation peak offset score.

5. A method for monitoring intraoperative blood pressure data based on thyroid disease according to claim 4, characterized in that, The process of obtaining the cause analysis results based on the cause matching score and preset threshold includes: When the matching score of stress-related triggers is greater than a preset threshold, stress-related triggers are identified. When the matching score of vagal nerve block type precipitate is greater than the preset threshold, vagal nerve block type precipitate is identified. When the tracheal traction reflex type precipitate matching score is greater than the preset threshold, the tracheal traction reflex type precipitate is identified.

6. The method for monitoring intraoperative blood pressure data based on thyroid disease according to claim 5, characterized in that, The method for obtaining the patient's blood pressure threshold is as follows: Blood pressure data were collected for a set duration while the patient was in a quiet, unstimulated, drug-free, and blood pressure-free environment. After removing blood pressure data that deviated from twice the standard deviation of the mean systolic blood pressure, valid systolic blood pressure data were obtained. After obtaining the mean systolic blood pressure and standard deviation of systolic blood pressure from effective systolic blood pressure data, the systolic blood pressure threshold is obtained, and its calculation formula is: Systolic blood pressure threshold = mean systolic blood pressure + dynamic coefficient × standard deviation of systolic blood pressure; After removing blood pressure data that deviated from twice the standard deviation of the mean diastolic blood pressure, the effective diastolic blood pressure data were obtained. After obtaining the mean and standard deviation of diastolic blood pressure from the effective diastolic blood pressure data, the diastolic blood pressure threshold is obtained, and its calculation formula is as follows: Diastolic blood pressure threshold = mean diastolic blood pressure + dynamic coefficient × standard deviation of diastolic blood pressure 7. A method for monitoring intraoperative blood pressure data based on thyroid disease according to claim 6, characterized in that, The dynamic coefficient is adjusted based on the surgical stage, which includes skin incision, gland separation, tracheal traction, tissue suturing, and tube removal. During the skin incision stage, the dynamic coefficient is set to 1.5; during the gland separation and tracheal traction stage, the dynamic coefficient is set to 2.0; during the tissue suturing stage, the dynamic coefficient is set to 1.6; and during the tube removal stage, the dynamic coefficient is set to 1.

8.

8. A method for monitoring intraoperative blood pressure data based on thyroid disease according to claim 7, characterized in that, The process for grading blood pressure alerts based on the results of causal analysis and the patient's blood pressure threshold includes: A yellow alert is issued when a stress-related trigger occurs and the patient's real-time systolic blood pressure is below the systolic blood pressure threshold and the patient's real-time diastolic blood pressure is below the diastolic blood pressure threshold. An orange alert is issued when vagal nerve block or mental stress triggers occur, and the systolic blood pressure threshold is less than the patient's real-time systolic blood pressure and less than the sum of the systolic blood pressure threshold and 0.5 times the standard deviation of systolic blood pressure, or the diastolic blood pressure threshold is less than the patient's real-time diastolic blood pressure and less than the sum of the diastolic blood pressure threshold and 0.5 times the standard deviation of diastolic blood pressure. During tracheal traction surgery, a red alert is issued when a tracheal traction reflex-type trigger occurs, and the patient's real-time systolic blood pressure is greater than or equal to the sum of the systolic blood pressure threshold and 0.5 times the standard deviation of systolic blood pressure, or the patient's real-time diastolic blood pressure is greater than or equal to the sum of the diastolic blood pressure threshold and 0.5 times the standard deviation of diastolic blood pressure.

9. A monitoring system for intraoperative blood pressure data based on thyroid diseases, applied to the monitoring method for intraoperative blood pressure data based on thyroid diseases as described in claim 8, characterized in that, The system includes: The data acquisition module is used to collect relevant data affecting blood pressure during surgery. The feature extraction module is used to extract multidimensional features that affect blood pressure during surgery based on relevant data on intraoperative blood pressure. The causation analysis module is used to: execute the process of obtaining causation analysis results based on the multidimensional characteristics of preoperative and intraoperative blood pressure effects; A personalized blood pressure threshold localization module is used to: execute the method of obtaining the patient's blood pressure threshold; The graded blood pressure alarm module is used to execute a process of graded blood pressure alarms based on the results of causal analysis and the patient's blood pressure threshold.

Images