Method and system for predicting post-induced hypotension of patient

Abstract

The invention relates to a method and system for predicting post-induced hypotension of a patient, and belongs to the technical field of hypotension prediction.The method comprises the steps that original data reflecting the cardiovascular autonomic nerve regulation capacity of the patient is obtained; preprocessing the original data to obtain target data, and calculating a target pressure reflex sensitivity BRS and a target pressure reflex effective index BEI based on the target data and the same-direction change sequence of the continuous heartbeat; inputting the target pressure reflex sensitivity BRS, the target pressure reflex effective index BEI and the patient baseline data into a Logistic regression model to obtain a hypotension risk probability; and determining a hypotension risk level of the patient based on the hypotension risk probability and a preset threshold range. According to the method, the target pressure reflex sensitivity BRS and the target pressure reflex effective index BEI serve as predictive factors, so that the probability of predicting hypotension of a patient can be improved before the patient receives anesthesia induction.

Description

Technical Field

[0001] The present invention belongs to the technical field of hypotension prediction, and in particular relates to a method and system for predicting post-induced hypotension in patients. Background Art

[0002] Anesthesia induction is the critical initial stage of surgical procedures. However, post-induction hypotension (PIH) is a common and potentially serious complication. PIH is closely associated with a significantly increased risk of postoperative acute kidney injury, myocardial injury, brain damage, and even death. Therefore, how to better predict post-induction hypotension in patients is an urgent issue. Summary of the Invention

[0003] In view of the above shortcomings of the existing technology, the present invention aims to provide a method and system for predicting post-induction hypotension in patients. This method uses the target baroreflex sensitivity (BRS) and the target baroreflex effectiveness index (BEI) as predictive factors, thereby improving the probability of hypotension in patients before anesthesia induction.

[0004] In a first aspect of the present invention, a method for predicting induced hypotension in a patient is proposed, comprising: S1, obtaining original data reflecting the patient's cardiovascular autonomic nervous regulation ability; S2, preprocessing the original data to obtain target data, and calculating the target baroreflex sensitivity BRS and the target baroreflex effectiveness index BEI based on the target data and the same-direction change sequence of continuous heartbeats; S3, inputting the target baroreflex sensitivity BRS, the target baroreflex effectiveness index BEI and the patient's baseline data into a logistic regression model to obtain the hypotension risk probability; S4, determining the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

[0005] Furthermore, the original data is preprocessed to obtain target data, including: denoising the original data to obtain first data; parsing the first data and determining the key fields of the first data after parsing; when it is determined that the status of the target field in the key field is BAD, discarding the first data containing the target field status as BAD; and using the discarded first data as the target data.

[0006] Furthermore, based on the target data and the sequence of unidirectional changes in continuous heartbeats, a target baroreflex sensitivity (BRS) is calculated, including: identifying the systolic blood pressure value of each heartbeat from the target data to obtain a systolic blood pressure sequence, and identifying the heartbeat interval corresponding to each heartbeat from the target data to obtain a heartbeat interval sequence; determining a valid sequence based on the systolic blood pressure sequence and the heartbeat interval sequence, and calculating a regression slope based on the systolic blood pressure sequence and the heartbeat interval sequence; determining the baroreflex sensitivity (BRS) of each sequence in the valid sequence based on the regression slope; and taking the average value of the baroreflex sensitivity (BRS) of all sequences in the valid sequence as the target baroreflex sensitivity (BRS); wherein, when determining the baroreflex sensitivity (BRS) of each sequence in the valid sequence, the regression quality of the baroreflex sensitivity (BRS) of each sequence is detected based on the correlation coefficient between the systolic blood pressure and the heartbeat interval of the heartbeat, and when the regression quality is unqualified, the sequence with unqualified regression quality is discarded.

[0007] Furthermore, a valid sequence is determined based on the systolic pressure sequence and the heartbeat interval sequence, including: determining the systolic pressure change and the heartbeat interval change of the heartbeat based on the systolic pressure sequence and the heartbeat interval sequence, and judging whether they are changes in the same direction based on the systolic pressure change and the heartbeat interval change; identifying a sequence of same-direction changes of heartbeats that is greater than or equal to a preset number of times in a row from the systolic pressure sequence and the heartbeat interval sequence, and using the identified sequence as the valid sequence.

[0008] Furthermore, calculating the target pressure reflex effective index BEI includes: obtaining a continuous blood pressure increase sequence and a continuous blood pressure decrease sequence, and determining the total number of sequences of the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence; determining an effective adjustment sequence and the number of effective adjustment sequences based on the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence; and calculating the target pressure reflex effective index BEI based on the number of effective adjustment sequences and the total number of sequences.

[0009] Furthermore, based on the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence, an effective adjustment sequence is determined, including: from the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence, a sequence that simultaneously satisfies the conditions that the absolute change in the heartbeat interval change is greater than a preset threshold, the systolic pressure change and the heartbeat interval change are in the same direction, and the square of the correlation coefficient between the systolic pressure and the heartbeat interval is greater than the coefficient threshold is determined, and used as the effective adjustment sequence.

[0010] Furthermore, the preset threshold range includes multiple ones, wherein, based on the hypotension risk probability and the preset threshold range, the patient's hypotension risk level is determined, including: when it is judged that the hypotension risk probability is within the first preset threshold range, the patient's hypotension risk level is determined to be level one; when it is judged that the hypotension risk probability is within the second preset threshold range, the patient's hypotension risk level is determined to be level two; when it is judged that the hypotension risk probability is within the third preset threshold range, the patient's hypotension risk level is determined to be level three; wherein, the method also includes: when the patient's hypotension risk level is determined, executing the corresponding anesthesia plan based on the hypotension risk level.

[0011] In a second aspect of the present invention, a system for predicting induced hypotension in patients is proposed, comprising: an acquisition module for acquiring raw data reflecting the patient's cardiovascular autonomic nervous regulation ability; a calculation module for preprocessing the raw data to obtain target data, and calculating the target baroreflex sensitivity BRS and the target baroreflex effective index BEI based on the target data and the same direction change sequence of continuous heartbeats; an acquisition module for inputting the target baroreflex sensitivity BRS, the target baroreflex effective index BEI and the patient's baseline data into a logistic regression model to obtain the probability of hypotension risk; and a determination module for determining the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

[0012] In a third aspect of the present invention, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the methods described in the first aspect of the present invention.

[0013] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to the first aspect of the present invention.

[0014] The beneficial effects of the present invention are as follows:

[0015] The method and system for predicting post-induced hypotension in patients disclosed herein obtain raw data reflecting the patient's cardiovascular autonomic nervous system regulation capacity; preprocess the raw data to obtain target data; and calculate the target baroreflex sensitivity (BRS) and target baroreflex effectiveness index (BEI) based on the target data and a sequence of unidirectional changes in continuous heartbeats; input the target baroreflex sensitivity (BRS), target baroreflex effectiveness index (BEI), and the patient's baseline data into a logistic regression model to determine the probability of hypotension risk; and determine the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range. This method, using the target baroreflex sensitivity (BRS) and target baroreflex effectiveness index (BEI) as predictive factors, improves the prediction of the probability of hypotension in patients before they undergo anesthesia induction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are only for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. Throughout the drawings, the same reference numerals represent the same components. Obviously, the drawings described below are only some of the embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings.

[0017] Figure 1 is a flow chart of a method for predicting post-induced hypotension in a patient according to one embodiment of the present invention;

[0018] Figure 2 is a flow chart of a method for predicting post-induced hypotension in a patient according to a specific embodiment of the present invention;

[0019] Figure 3 is a structural block diagram of a system for predicting induced hypotension in a patient according to an embodiment of the present invention;

[0020] Figure 4 It is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the scope of protection of the present invention.

[0022] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0023] In the description of the present invention, it should be noted that, unless otherwise expressly specified and limited, the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second" and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance. The terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the internal parts of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of methods and systems consistent with certain aspects of the present invention, as detailed in the appended claims.

[0025] The present invention provides a method, system and related equipment for predicting post-induced hypotension in patients. Specifically, the method, system and related equipment for predicting post-induced hypotension in patients according to an embodiment of the present invention are described below with reference to the accompanying drawings.

[0026] Figure 1 This is a flow chart of a method for predicting post-induced hypotension in a patient according to one embodiment of the present invention. It should be noted that the method for predicting post-induced hypotension in a patient according to an embodiment of the present invention can be applied to a system for predicting post-induced hypotension in a patient according to an embodiment of the present invention. The system for predicting post-induced hypotension in a patient can be configured on an electronic device or on a server. This embodiment of the present application is not limited to this.

[0027] like Figure 1 As shown, methods for predicting post-induction hypotension in patients include:

[0028] S110, obtaining original data reflecting the patient's cardiovascular autonomic nervous system regulation ability.

[0029] In an embodiment of the present invention, raw data reflecting the patient's cardiovascular autonomic nervous system regulation ability can be obtained through the device.

[0030] The device may be a CNAP device. The raw data includes but is not limited to hemodynamic data, time points, blood pressure, etc.

[0031] In other words, the CNAP device can be used to perform a passive leg raise test and collect hemodynamic data (especially the change in stroke volume ΔSV).

[0032] For example, the process for performing a passive leg raise test and collecting hemodynamic data in an environment with appropriate temperature, humidity, and lighting includes the following: ① Starting position: The patient's upper body is elevated 45°, with the legs horizontal. This is the baseline measurement position. ② Passive leg raise test procedure: The patient's legs are rapidly raised 45°, while ensuring that the torso (upper body) remains horizontal. This maneuver is equivalent to rapidly "autologous retransfusion" of blood from the lower body to the central circulation (heart and great vessels). ③ Data observation and recording: Within one minute after the leg raise is completed, changes in stroke volume automatically calculated by the CNAP device are closely observed and recorded. The core metric recorded is ΔSV (the change in SV after the leg raise compared to the baseline SV).

[0033] The sampling frequency of the CNAP device is 100Hz. This means that the device collects 100 data points per second, providing a data stream with very high temporal resolution. Each data point in the CNAP device's output parameters contains rich information, including time point, systolic blood pressure, diastolic blood pressure, mean arterial pressure, stroke volume, cardiac output, cardiac index, and more. The data format of the CNAP device's output data is LVU.

[0034] S120 , preprocessing the original data to obtain target data, and calculating the target baroreflex sensitivity BRS and the target baroreflex effectiveness index BEI based on the target data and the same-direction change sequence of continuous heartbeats.

[0035] In an embodiment of the present invention, once raw data is acquired, the raw data may be preprocessed to obtain target data. Based on the target data and the co-directional change sequence of consecutive heartbeats, the target baroreflex sensitivity (BRS) and target baroreflex effectiveness index (BEI) are calculated. For specific implementations, please refer to the subsequent embodiments.

[0036] Before preprocessing the original data, the data format of the original data may be converted into a standard structured format.

[0037] S130, inputting the target baroreflex sensitivity BRS, the target baroreflex effectiveness index BEI, and the patient's baseline data into a logistic regression model to obtain the risk probability of hypotension.

[0038] In an embodiment of the present invention, once the target baroreflex sensitivity (BRS) and target baroreflex effectiveness index (BEI) are obtained, the target baroreflex sensitivity (BRS), target baroreflex effectiveness index (BEI), and patient baseline data can be used as inputs to a logistic regression model, which then outputs a hypotension risk probability. For specific implementation methods, please refer to the subsequent embodiments.

[0039] Among them, the patient's baseline data includes but is not limited to age, gender, weight, height, BMI, medical history, medication history, etc.

[0040] S140: Determine the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

[0041] Among them, the preset threshold range includes multiple ones.

[0042] That is, when the hypotension risk probability is obtained, it can be determined that the hypotension risk probability is within a specific preset threshold range, and then the corresponding hypotension risk level is determined based on the specific preset threshold range. Specific implementation methods can be referred to the subsequent embodiments.

[0043] According to an embodiment of the present invention, a method for predicting post-induction hypotension in a patient involves obtaining raw data reflecting the patient's cardiovascular autonomic nervous system regulation capacity; preprocessing the raw data to obtain target data, and calculating a target baroreflex sensitivity (BRS) and a target baroreflex effectiveness index (BEI) based on the target data and a sequence of unidirectional changes in continuous heartbeats; inputting the target baroreflex sensitivity (BRS), target baroreflex effectiveness index (BEI), and the patient's baseline data into a logistic regression model to obtain a hypotension risk probability; and determining the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range. This method uses the target baroreflex sensitivity (BRS) and target baroreflex effectiveness index (BEI) as predictive factors, thereby improving the prediction of the probability of hypotension in patients before they undergo anesthesia induction.

[0044] In order to make it easier for those skilled in the art to understand the present invention, Figure 2 A method for predicting post-induced hypotension in a patient according to a specific embodiment of the present invention is as follows. Figure 2 As shown, the method for predicting post-induction hypotension in a patient comprises:

[0045] S210, obtaining original data reflecting the patient's cardiovascular autonomic nervous system regulation ability.

[0046] In the embodiment of the present invention, the implementation of step S210 of the present invention may refer to the implementation of step S110 described above, and the present invention will not elaborate on this.

[0047] S220, preprocessing the original data to obtain target data.

[0048] In an embodiment of the present invention, the original data is denoised to obtain first data; the first data is parsed, and the key fields of the parsed first data are determined; when it is determined that the status of the target field in the key field is BAD, the first data containing the target field status of BAD is discarded; and the first data after discarding is used as the target data.

[0049] For example, the parsed first data contains: timestamp, systolic_pressure, diastolic_pressure, mean_arterial_pressure, stroke_volume (SV), cardiac_output (CO), cardiac_index (CI), and status. It can then be determined whether the status field is BAD. If so, the first data is discarded and used as the target data.

[0050] S230 , calculating the target baroreflex sensitivity (BRS) based on the target data and the same-direction change sequence of continuous heartbeats.

[0051] In an embodiment of the present invention, the systolic blood pressure value of each heartbeat is identified from the target data to obtain a systolic blood pressure sequence, and the heartbeat interval corresponding to each heartbeat is identified from the target data to obtain a heartbeat interval sequence; a valid sequence is determined based on the systolic blood pressure sequence and the heartbeat interval sequence, and a regression slope is calculated based on the systolic blood pressure sequence and the heartbeat interval sequence; the baroreflex sensitivity (BRS) of each sequence in the valid sequence is determined based on the regression slope; and the average value of the baroreflex sensitivity (BRS) of all sequences in the valid sequence is used as the target baroreflex sensitivity (BRS).

[0052] Among them, the systolic blood pressure value SBP of each heartbeat is identified from the target data to form a systolic blood pressure sequence, that is, , , ,..., . Indicates the systolic blood pressure value for heartbeat i.

[0053] Among them, the heartbeat interval RR corresponding to each heartbeat is identified from the target data to form a heartbeat interval sequence, that is, , , ,..., .in, Indicates the heartbeat interval between i and i+1.

[0054] In an embodiment of the present invention, based on the systolic pressure sequence and the heartbeat interval sequence, the systolic pressure change and the heartbeat interval change of the heartbeat are determined, and based on the systolic pressure change and the heartbeat interval change, it is determined whether they are changes in the same direction; a sequence of same-direction changes of heartbeats greater than or equal to a preset number of consecutive times is identified from the systolic pressure sequence and the heartbeat interval sequence, and the identified sequence is used as a valid sequence.

[0055] Among them, according to , get the systolic blood pressure change from heartbeat i to heartbeat i+1 .

[0056] Among them, according to , get the heartbeat interval change from heartbeat i to heartbeat i+1 .

[0057] in, and The values ​​are all positive or negative, indicating changes in the same direction.

[0058] Among them, the systolic pressure sequence and heartbeat interval sequence are scanned to identify ≥3 consecutive heartbeats, which correspond to and Same sign (same direction) and both satisfy The required sequence is identified and the recognized sequence is regarded as a valid sequence.

[0059] Among them, according to a = ∑ [ （ SBP i − SBP − )(RR i -RR − ） ] ∑ （ SBP i − SBP − ） 2 , calculate the regression slope a, where , , where n represents the length of the sequence, that is, the number of systolic blood pressures contained in the sequence.

[0060] Among them, according to , determine the baroreflex sensitivity (BRS) of each sequence in the valid sequence. That is, the absolute value of the regression slope a is used as the baroreflex sensitivity (BRS) of each sequence in the valid sequence.

[0061] In an embodiment of the present invention, when determining the baroreflex sensitivity (BRS) of each sequence in a valid sequence, the regression quality of the baroreflex sensitivity (BRS) of each sequence is detected based on the correlation coefficient between the systolic pressure of the heartbeat and the heartbeat interval, and if the regression quality is unqualified, the sequence with unqualified regression quality is discarded.

[0062] Among them, according to r = ∑ [ （ SBP i − SBP − )(RR i -RR − ） ] √ [ ∑ （ SBP i − SBP − ） 2 × ∑ (RR i -RR − ） 2 ] , determine the correlation coefficient r between the systolic pressure of the heartbeat and the heartbeat interval.

[0063] Among them, in meeting In the case of determining the regression quality of the baroreflex sensitivity BRS sequence is qualified, In this case, the regression quality of the baroreflex sensitivity BRS of the determined sequence was unsatisfactory.

[0064] S240, calculating the target baroreflex effectiveness index BEI.

[0065] In an embodiment of the present invention, a continuous blood pressure increase sequence and a continuous blood pressure decrease sequence are obtained, and the total number of blood pressure increase sequences and blood pressure decrease sequences is determined; based on the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence, the effective adjustment sequence and the number of effective adjustment sequences are determined; based on the number of effective adjustment sequences and the total number of sequences, the target pressure reflex effective index BEI is calculated.

[0066] Among them, obtain the continuous increase sequence of blood pressure, that is, ≥3 consecutive heartbeats, .

[0067] Among them, obtain the continuous blood pressure drop sequence, that is, ≥3 consecutive heartbeats, .

[0068] In an embodiment of the present invention, from a sequence of continuously increasing blood pressure and a sequence of continuously decreasing blood pressure, a sequence is identified that satisfies the conditions that the absolute change in heartbeat interval is greater than a preset threshold, the systolic pressure change and the heartbeat interval change in the same direction, and the square of the correlation coefficient between the systolic pressure and the heartbeat interval is greater than the coefficient threshold. This sequence is then identified as a valid adjustment sequence. The number of valid adjustment sequences is then determined.

[0069] The absolute change in heart rate between beats must be greater than a preset threshold, which can be understood as: |ΔRR| ≥ 6 ms, where the absolute change in the RR interval is at least 6 milliseconds (the RR interval represents the heart rate interval, measured in milliseconds). This ensures that the heart rate changes are significant enough to avoid misinterpreting small fluctuations.

[0070] Among them, the change of systolic blood pressure and the change of heart rate interval change in the same direction, which can be understood as follows: for BEI+ sequence (SBP rises): RR interval must be prolonged (i.e. heart rate slows down), i.e. SBP↑→RR↑. For BEI- sequence (SBP falls): RR interval must be shortened (i.e. heart rate speeds up), i.e. SBP↓→RR↓

[0071] Among them, the square of the correlation coefficient between the systolic pressure of the heartbeat and the heartbeat interval is greater than the coefficient threshold, which can be understood as: according to r = ∑ [ （ SBP i − SBP − )(RR i -RR − ） ] √ [ ∑ （ SBP i − SBP − ） 2 × ∑ (RR i -RR − ） 2 ] , determine the correlation coefficient r between the systolic pressure of the heartbeat and the heartbeat interval, that is, satisfy situation.

[0072] In an embodiment of the present invention, when the number of effective adjustment sequences and the total number of sequences are obtained, the ratio of the number of effective adjustment sequences to the total number of sequences may be used as the target baroreflex effectiveness index BEI.

[0073] S250, input the target baroreflex sensitivity BRS, the target baroreflex effectiveness index BEI and the patient's baseline data into a logistic regression model to obtain the risk probability of hypotension.

[0074] In an embodiment of the present invention, when the target baroreflex sensitivity BRS, the target baroreflex effective index BEI and the patient baseline data are obtained, the target baroreflex sensitivity BRS, the target baroreflex effective index BEI and the patient baseline data can be preprocessed. For example, the missing values ​​in the target baroreflex sensitivity BRS, the target baroreflex effective index BEI and the patient baseline number can be reasonably processed (such as deletion, mean / median filling), and the abnormal values ​​in the target baroreflex sensitivity BRS, the target baroreflex effective index BEI and the patient baseline number (such as extreme values ​​caused by signal interference) are detected and processed. Then, the preprocessed target baroreflex sensitivity BRS, the target baroreflex effective index BEI and the patient baseline data are input into the trained logistic regression model to obtain the risk probability of hypotension.

[0075] S260: Determine the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

[0076] Among them, the preset threshold range includes multiple ones.

[0077] In an embodiment of the present invention, when the probability of hypotension risk is judged to be within the first preset threshold range, the patient's hypotension risk level is determined to be level one; when the probability of hypotension risk is judged to be within the second preset threshold range, the patient's hypotension risk level is determined to be level two; when the probability of hypotension risk is judged to be within the third preset threshold range, the patient's hypotension risk level is determined to be level three.

[0078] Among them, the higher the risk level of hypotension, the higher the risk.

[0079] S270: When the patient's hypotension risk level is determined, a corresponding anesthesia plan is executed based on the hypotension risk level.

[0080] For example, if the patient's hypotension risk level is determined to be level one, the risk of hypotension is low and the conventional induction process can be used. If the patient's hypotension risk level is determined to be level two, the risk of hypotension is moderate and it is recommended to prepare pressor drugs in advance and monitor closely. If the patient's hypotension risk level is determined to be level three, the risk of hypotension is high and it is recommended to select a hemodynamically stable induction regimen, slow the induction rate, and prepare vasoactive drug pretreatment in advance.

[0081] In theory, other technical solutions or methods exist that could achieve similar functions as the present invention for assessing the risk of post-induced hypotension (PIH). Their core purpose is also to reflect the patient's cardiovascular autonomic nervous system function and volume status, thereby inferring their ability to maintain blood pressure and their risk of hypotension. For example, ECG monitoring can be used to obtain HRV indicators to assess autonomic nervous system function, while bedside ultrasound can be used to measure the respiratory variability of the inferior vena cava (IVC) to indirectly assess the patient's volume status. HRV analysis can reflect the dynamic balance between sympathetic and parasympathetic nervous system tone, while IVC variability can, to a certain extent, reflect preoperative blood volume status. Combined assessment of the two has also been used in clinical studies to predict hypotension risk. However, these alternatives have significant disadvantages. First, HRV only indirectly reflects autonomic nervous system function and is highly susceptible to interference from temperature, humidity, light, and even the time of day, resulting in poor stability. Second, ultrasound assessment of IVC requires manual, highly skilled operators, resulting in highly dependent results and poor reproducibility. The procedure is also discontinuous and cumbersome, making automation and batch evaluation difficult. The present invention uses continuous non-invasive blood pressure monitoring equipment to obtain BRS and volume status data in a one-time, non-invasive manner in a resting state, and directly constructs a prediction model in combination with demographic information. It has the advantages of high evaluation efficiency, high degree of automation, and greater prediction accuracy, and is more suitable for clinical promotion and application.

[0082] Another possible alternative is to perform arterial cannulation under local anesthesia before surgery, calculate BRS from invasive arterial pressure monitoring data, and perform a passive leg raise test to assess the patient's volume status. This approach theoretically provides more accurate hemodynamic data than noninvasive methods (CNAP), offering greater parameter reliability and clinical value for certain high-risk patients. However, this approach also has significant limitations. Its core drawback is that it requires an invasive procedure while the patient is awake. Arterial cannulation carries inherent procedural risks (not all elderly patients clinically require it), including puncture failure, bleeding, hematoma, vasospasm, and infection. It also requires a high level of technical expertise from the operator. Furthermore, preoperative implementation of this approach may impact the patient experience, increase procedural complexity, and increase preoperative preparation time, limiting its widespread use in routine preoperative evaluations.

[0083] Therefore, the present invention introduces baroreflex sensitivity (BRS), target baroreflex effectiveness index (BEI), and patient baseline data to construct a method and system that can predict the risk of post-induced hypotension (PIH) in real-time, non-invasively, and individually. This method leverages the advantages of CNAP monitoring equipment to address the shortcomings of previous HRV measurements, which were unable to assess blood pressure. The present invention has the advantage of enabling dynamic assessment of preoperative blood pressure self-regulation, possessing good clinical operability and application potential, and truly meeting the needs of accurate and practical preoperative risk assessment.

[0084] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus the necessary general hardware platform. 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 the present application, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0085] According to one aspect of an embodiment of the present invention, a system for predicting post-induced hypotension in a patient is also provided. Figure 3 is a structural block diagram of a system for predicting post-induced hypotension in a patient according to an embodiment of the present invention; Figure 3 Shown, including:

[0086] An acquisition module 310 is used to acquire raw data reflecting the patient's cardiovascular autonomic nervous system regulation ability;

[0087] The calculation module 320 is used to pre-process the raw data to obtain target data, and calculate the target baroreflex sensitivity BRS and the target baroreflex effectiveness index BEI based on the target data and the same direction change sequence of continuous heartbeats;

[0088] An obtaining module 330 is configured to input the target baroreflex sensitivity BRS, the target baroreflex effectiveness index BEI, and the patient's baseline data into a logistic regression model to obtain a risk probability of hypotension;

[0089] The determination module 340 is configured to determine the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

[0090] According to an embodiment of the present invention, a system for predicting post-induction hypotension in a patient acquires raw data reflecting the patient's cardiovascular autonomic nervous system regulation capacity; preprocesses the raw data to obtain target data, and calculates a target baroreflex sensitivity (BRS) and a target baroreflex effectiveness index (BEI) based on the target data and a sequence of unidirectional changes in continuous heartbeats; inputs the target baroreflex sensitivity (BRS), target baroreflex effectiveness index (BEI), and the patient's baseline data into a logistic regression model to obtain a hypotension risk probability; and determines the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range. Thus, by using the target baroreflex sensitivity (BRS) and target baroreflex effectiveness index (BEI) as predictive factors, the probability of hypotension in a patient can be improved before anesthesia induction.

[0091] Optionally, the computing module 320 is specifically used to denoise the original data to obtain first data; parse the first data and determine the key fields of the first data after parsing; when it is determined that the target field status in the key field is BAD, discard the first data containing the target field status of BAD; and use the first data after discarding as the target data.

[0092] Optionally, the calculation module 320 is specifically used to identify the systolic blood pressure value of each heartbeat from the target data to obtain a systolic blood pressure sequence, and to identify the heartbeat interval corresponding to each heartbeat from the target data to obtain a heartbeat interval sequence; determine a valid sequence based on the systolic blood pressure sequence and the heartbeat interval sequence, and calculate a regression slope based on the systolic blood pressure sequence and the heartbeat interval sequence; determine the pressure reflex sensitivity BRS of each sequence in the valid sequence based on the regression slope; and take the average value of the pressure reflex sensitivity BRS of all sequences in the valid sequence as the target pressure reflex sensitivity BRS; wherein, when determining the pressure reflex sensitivity BRS of each sequence in the valid sequence, the regression quality of the pressure reflex sensitivity BRS of each sequence is detected based on the correlation coefficient between the systolic blood pressure and the heartbeat interval of the heartbeat, and when the regression quality is unqualified, the sequence with unqualified regression quality is discarded.

[0093] Optionally, the calculation module 320 is specifically used to determine the systolic pressure change and the heartbeat interval change of the heartbeat based on the systolic pressure sequence and the heartbeat interval sequence, and judge whether they are changes in the same direction based on the systolic pressure change and the heartbeat interval change; identify a sequence of same-direction changes of heartbeats that is greater than or equal to a preset number of times from the systolic pressure sequence and the heartbeat interval sequence, and use the identified sequence as the valid sequence.

[0094] Optionally, the calculation module 320 is specifically used to obtain a continuous blood pressure increase sequence and a continuous blood pressure decrease sequence, and determine the total number of sequences of the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence; determine the effective adjustment sequence and the number of the effective adjustment sequences based on the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence; and calculate the target pressure reflex effective index BEI based on the number of the effective adjustment sequences and the total number of sequences.

[0095] Optionally, the calculation module 320 is specifically used to determine, from the blood pressure continuously increasing sequence and the blood pressure continuously decreasing sequence, a sequence that simultaneously satisfies the conditions that the absolute change in the heartbeat interval change is greater than a preset threshold, the systolic pressure change and the heartbeat interval change are in the same direction, and the square of the correlation coefficient between the systolic pressure and the heartbeat interval is greater than a coefficient threshold, and use it as the effective adjustment sequence.

[0096] Optionally, the preset threshold range includes multiple ones, among which the determination module 340 is specifically used to determine that when the hypotension risk probability is within the first preset threshold range, the patient's hypotension risk level is determined to be level one; when the hypotension risk probability is determined to be within the second preset threshold range, the patient's hypotension risk level is determined to be level two; when the hypotension risk probability is determined to be within the third preset threshold range, the patient's hypotension risk level is determined to be level three; wherein the system also includes an execution module for determining the patient's hypotension risk level and executing a corresponding anesthesia plan based on the hypotension risk level.

[0097] According to one aspect of an embodiment of the present invention, an electronic device is provided.

[0098] Figure 4 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Figure 4 As shown, the electronic device may include one or more ( Figure 4 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a microprocessor (Microprocessor Unit, referred to as MPU) or a programmable logic device (Programmable logic device, referred to as PLD)) and a memory 104 for storing data. In an exemplary embodiment, the electronic device may further include a transmission device 106 and an input / output device 108 for communication functions. It will be understood by those skilled in the art that Figure 4 The structure shown is only for illustration and does not limit the structure of the above terminal device. Figure 4 More or fewer components than shown, or with Figure 4 Equivalent functions or comparisons shown Figure 4Shown are different configurations with more functionality.

[0099] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the method for predicting post-induced hypotension in a patient in an embodiment of the present invention. The processor 102 executes the computer program stored in the memory 104 to execute various functional applications and data processing, thereby implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories may be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0100] Transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a communications provider of a switching device. In one embodiment, transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0101] The present invention provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute a method for predicting post-induced hypotension in a patient.

[0102] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation plans of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, and is not a limitation on the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

[0103] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0104] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limiting the present invention. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0105] Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for predicting post-induced hypotension in a patient, characterized in that: include: S1, obtain the original data reflecting the patient's cardiovascular autonomic nervous system regulation ability; S2, preprocessing the raw data to obtain target data, and calculating a target baroreflex sensitivity (BRS) and a target baroreflex effectiveness index (BEI) based on the target data and a sequence of same-direction changes in continuous heartbeats; S3, inputting the target baroreflex sensitivity (BRS), the target baroreflex effectiveness index (BEI), and the patient's baseline data into a logistic regression model to obtain the risk probability of hypotension; S4. Determine the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

2. The method for predicting post-induced hypotension in a patient according to claim 1, wherein: Preprocessing the original data to obtain target data includes: Denoising the original data to obtain first data; Parsing the first data and determining key fields of the parsed first data; When it is determined that the target field status in the key field is BAD, discarding the first data including the target field status being BAD; The discarded first data is used as the target data.

3. The method for predicting post-induced hypotension in a patient according to claim 2, wherein: Calculating a target baroreflex sensitivity (BRS) based on the target data and a sequence of same-direction changes in continuous heartbeats includes: Identifying the systolic blood pressure value of each heartbeat from the target data to obtain a systolic blood pressure sequence, and identifying the heartbeat interval corresponding to each heartbeat from the target data to obtain a heartbeat interval sequence; determining a valid sequence according to the systolic pressure sequence and the heartbeat interval sequence, and calculating a regression slope according to the systolic pressure sequence and the heartbeat interval sequence; Determine the baroreflex sensitivity (BRS) of each sequence in the valid sequence based on the regression slope; The average value of the baroreflex sensitivity (BRS) of all sequences in the valid sequence is used as the target baroreflex sensitivity (BRS); Among them, when determining the baroreflex sensitivity BRS of each sequence in the valid sequence, the regression quality of the baroreflex sensitivity BRS of each sequence is detected according to the correlation coefficient between the systolic pressure of the heartbeat and the heartbeat interval, and if the regression quality is unqualified, the sequence with unqualified regression quality is discarded.

4. The method for predicting post-induced hypotension in a patient according to claim 3, wherein: Determining a valid sequence according to the systolic pressure sequence and the heartbeat interval sequence includes: Determining changes in systolic pressure and heartbeat intervals of a heartbeat according to the systolic pressure sequence and the heartbeat interval sequence, and determining whether the changes are in the same direction based on the changes in systolic pressure and the heartbeat intervals; A sequence of heartbeats changing in the same direction for a number of consecutive heartbeats greater than or equal to a preset number is identified from the systolic pressure sequence and the heartbeat interval sequence, and the identified sequence is used as the valid sequence.

5. The method for predicting post-induced hypotension in a patient according to claim 3, wherein: Calculate the target baroreflex effectiveness index BEI, including: Acquire a continuous blood pressure increase sequence and a continuous blood pressure decrease sequence, and determine the total number of the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence; determining a valid adjustment sequence and the number of the valid adjustment sequences according to the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence; The target baroreflex effectiveness index BEI is calculated based on the number of the effective adjustment sequences and the total number of sequences.

6. The method for predicting post-induced hypotension in a patient according to claim 5, wherein: Determining an effective adjustment sequence according to the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence includes: From the continuous blood pressure increase sequence and the continuous blood pressure decrease sequence, a sequence that simultaneously satisfies the conditions that the absolute change in the heartbeat interval is greater than a preset threshold, the systolic pressure change and the heartbeat interval change are in the same direction, and the square of the correlation coefficient between the systolic pressure and the heartbeat interval is greater than the coefficient threshold is determined and used as the effective adjustment sequence.

7. The method for predicting post-induced hypotension in a patient according to claim 1, wherein: The preset threshold range includes multiple ones, wherein determining the hypotension risk level of the patient based on the hypotension risk probability and the preset threshold range includes: When the hypotension risk probability is determined to be within a first preset threshold range, determining the patient's hypotension risk level to be level one; When the hypotension risk probability is determined to be within a second preset threshold range, determining that the patient's hypotension risk level is level two; When it is determined that the hypotension risk probability is within a third preset threshold range, determining that the patient's hypotension risk level is level three; The method further comprises: When the hypotension risk level of the patient is determined, a corresponding anesthesia plan is executed based on the hypotension risk level.

8. A system for predicting post-induced hypotension in a patient, characterized in that include: An acquisition module, used to obtain raw data reflecting the patient's cardiovascular autonomic nervous system regulation ability; a calculation module, configured to pre-process the raw data to obtain target data, and calculate a target baroreflex sensitivity (BRS) and a target baroreflex effectiveness index (BEI) based on the target data and a sequence of same-direction changes in continuous heartbeats; An obtaining module is used to input the target baroreflex sensitivity BRS, the target baroreflex effectiveness index BEI and the patient's baseline data into a logistic regression model to obtain the risk probability of hypotension; A determination module is used to determine the patient's hypotension risk level based on the hypotension risk probability and a preset threshold range.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images