Method and system for monitoring sensitive indicators of blood circulation in a limb after orthopedic surgery

Abstract

The present application relates to the technical field of physiological parameter monitoring, in particular to a postoperative limb blood circulation sensitive index monitoring method and system for orthopedics, comprising the following steps: acquiring blood flow velocity sequence, temperature and electromyographic signal of distal part of patient's affected limb, comparing trend direction and fluctuation characteristics, monitoring body position change response, screening signals with consistent direction, tracking state change within a period, analyzing frequency and distribution, and obtaining blood circulation sensitive index sequence.In the present application, by fusing trend characteristics of blood flow, temperature and electromyographic signal, the correlation structure of body position change and period fluctuation is constructed, dynamic index sequence is generated according to signal direction consistency, frequency change and time distribution, and full tracking and stage identification of blood circulation state are completed, so that the sensitive index has trend response characteristics and period adaptation ability, the coherence of data screening and the stable performance of monitoring results are enhanced, and the index maintains stable tracking and regular extraction ability in multi-stage scenarios.

Description

Technical Field

[0001] This invention relates to the field of physiological parameter monitoring technology, and in particular to methods and systems for monitoring sensitive indicators of limb blood circulation after orthopedic surgery. Background Technology

[0002] The field of physiological parameter monitoring technology mainly involves technical methods for real-time or periodic collection and quantification of key human vital signs. Its core aspects include the acquisition and analysis of physiological indicators such as blood flow velocity measurement, blood pressure change detection, blood oxygen saturation assessment, body temperature sensing, and heart rate monitoring. This typically involves the collaborative work of physical sensors, biosignal conversion elements, and data output devices to construct a complete human physiological state assessment process. This technical method emphasizes continuous measurement of physiological signals, quantitative standard setting of indicators, and timely synchronization of data recording. It relies on clinically preset parameters to achieve monitoring and intervention of disease processes and tracking of postoperative recovery. Among these methods, the monitoring of limb blood circulation after traditional orthopedic surgery is crucial. Sensitive indicator monitoring methods refer to the preliminary assessment of blood circulation status after a patient undergoes orthopedic surgery. This is achieved by setting monitoring sites, such as the distal part of the limb, and using infrared temperature probes to measure changes in skin surface temperature or ultrasound Doppler ultrasound to collect blood flow velocity signals. These methods are combined with observation of limb color, assessment of indentation recovery speed, and evaluation of local swelling. However, the sensitive indicators for blood circulation in this method are usually set based on the doctor's experience, lacking a unified selection standard. The monitoring method mainly relies on manual periodic inspections, and the collection frequency depends on the ward work schedule or special observation needs. This method lacks a data-driven indicator setting system and a structural support for a comprehensive limb blood circulation management plan.

[0003] Current technologies for assessing blood circulation status rely on periodic observation of a single parameter. The monitoring content is limited to data representing specific locations and lacks correlation assessment of responses in dynamic situations such as changes in body position or prolonged bed rest. In the postoperative stage, when the condition fluctuates frequently, the lack of trend continuity analysis makes it difficult to identify the temporal distribution patterns and signal evolution patterns during the change of indicators. This results in arbitrary parameter selection, delayed indicator response, and high degree of information fragmentation, making it impossible to support the full-process identification and regular extraction of sensitive indicators of postoperative blood circulation. Summary of the Invention

[0004] To address the technical problems existing in the prior art, embodiments of the present invention provide a method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery; To achieve the above objectives, the present invention adopts the following technical solution: a method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery, comprising the following steps: S1: Obtain baseline characteristics of blood flow velocity, surface temperature and electromyography signals in the distal part of the affected limb of the postoperative bedridden patient, analyze the trend direction, duration and fluctuation amplitude in the same segment, and obtain the postoperative limb physiological signal characteristic group. S2: Based on the postoperative limb physiological signal characteristic group, monitor the signal response status during the process of changing the body position from supine to lateral and from raised to lowered, analyze the continuation of blood flow direction, the delay of temperature response and the fluctuation of electromyographic frequency, and obtain the body position-related circulatory response group. S3: Based on the body position-related circulatory response group, compare the trend direction, start and end time and duration of blood flow, temperature and electromyography signals in the differentiated body position stages, identify the signal content that recurs between stages and whose direction does not change, and obtain a list of blood circulation indicators. S4: Based on the blood circulation index list, track the changes in the index status within the monitoring period, analyze the directional changes, fluctuation frequency and duration of adjacent time periods, and obtain the dynamic status group of blood circulation sensitive indicators. S5: Based on the dynamic state group of the blood circulation sensitive indicators, analyze the frequency of occurrence, directional consistency and distribution time of the indicators within the monitoring period to obtain the output sequence of blood circulation sensitive indicators.

[0005] As a further aspect of the present invention, the postoperative limb physiological signal feature group includes the blood flow velocity trend direction, surface temperature change direction, and electromyographic signal baseline characteristic fluctuation amplitude; the body position influence on circulatory response group includes blood flow direction continuity, temperature response lag time, and electromyographic frequency continuity; the blood circulation index list includes trend direction consistency, start and end time correspondence, and signal source type; the blood circulation sensitive index dynamic state group includes trend reversal performance, duration change, fluctuation frequency distribution, fluctuation time series, and turning frequency series; and the blood circulation sensitive index output sequence includes index occurrence frequency, duration range, trend repetition performance, change segment coverage, and change interval characteristics.

[0006] As a further aspect of the present invention, the blood flow direction continuity refers to the fact that the trend of blood flow velocity change remains consistent and continuous for a period of time before and after the body position change. The temperature response delay refers to the phenomenon that after a change in body position occurs, the surface temperature change has a time lag, and the response only begins after a certain lag time.

[0007] As a further aspect of the present invention, the differentiated body position stage refers to the stage interval formed by the patient's differentiated body position change process; The change in indicator status refers to the change in the trend direction, duration, and frequency of fluctuations of the same sensitive indicator between adjacent time periods throughout the entire monitoring period.

[0008] As a further aspect of the present invention, the specific steps of S1 are as follows: S101: Obtain the blood flow velocity sequence, surface temperature change direction, and electromyographic signal baseline characteristics of the distal part of the affected limb of a bedridden patient after surgery. Synchronize the three types of signals under a unified time line, detect continuous sampling segments of each type of signal, exclude data segments with broken time intervals, and obtain a time-aligned signal sequence group. S102: Based on the time-aligned signal sequence group, extract the direction of change, duration and frequency fluctuation range of each type of signal within the same time period. According to the rising and falling trend of blood flow velocity, the directional response of temperature change and the high and low distribution of electromyographic frequency, compare the trend direction among the three types of signals to obtain a set of trend-consistent intervals. S103: Based on the set of trend-consistent intervals, analyze the direction and duration of change of the three types of signals in each segment, identify data segments that simultaneously have directional consistency and continuous performance characteristics in the same interval, and obtain the postoperative limb physiological signal feature group.

[0009] As a further aspect of the present invention, the specific steps of S2 are as follows: S201: Based on the postoperative limb physiological signal feature group, during the positional switching from supine to lateral and from elevated to drooping, extract the blood flow velocity direction, surface temperature change and electromyographic signal baseline feature data, and obtain the continuous state set of positional stage signals according to the continuous performance of the parameters in the previous and subsequent positional states in a time sequence. S202: Based on the continuous state set of body position stage signals, compare the performance of blood flow direction change continuity, temperature response delay and electromyography frequency fluctuation between the previous and previous body positions, and filter out signal items that show direction shift and fluctuation amplification during the switching process to obtain the body position change response signal set. S203: Based on the set of body position change response signals, track the fluctuation trends and response trajectories of blood flow, temperature, and electromyography signals during the transformation process, align the temporal changes of the signals, and obtain the body position effect circulatory response group.

[0010] As a further aspect of the present invention, the specific steps of S3 are as follows: S301: Based on the body position effect circulatory response group, extract continuous data frames of blood flow velocity, surface temperature and electromyography frequency in the differential body position change stage, compare the fluctuation start time and duration of each type of signal according to the same time segment to obtain the stage trend comparison segment. S302: Based on the aforementioned stage trend comparison fragments, select sequences in blood flow, temperature, and electromyography that show consistent fluctuation directions in multiple stages, extract data segments with overlapping start and end times and concentrated interval variation ranges, and obtain a group of sequences with overlapping trend directions. S303: Based on the trend direction coincidence sequence group, split the data frame according to the signal source, extract the signal performance of each type of signal that has the same direction and appears in the same change segment, analyze the response distribution according to the time overlap relationship, and obtain a list of blood circulation indicators.

[0011] As a further aspect of the present invention, the specific steps of S4 are as follows: S401: Based on each type of data in the blood circulation index list, track and monitor blood flow velocity, surface temperature and electromyography frequency within the monitoring period, extract continuous sequences for each data item according to time period, and retrieve the change characteristics of trend direction, duration of change and fluctuation frequency in adjacent time periods to obtain time period trend sequence group; S402: Based on the time period trend sequence group, identify data frames with trend reversal, duration extension and fluctuation increase in the preceding and following stages, compare the range of trend behavior and fluctuation density within the time period, and obtain a set of trend change signals; S403: Based on the trend mutation signal set, extract the duration of continuous fluctuations and the frequency of turning according to the monitored object, retrieve the time distribution and change repetition rate of the corresponding sequence of the same object in the differentiated time period, extract the index sequence with continuous change characteristics, and obtain the dynamic state group of blood circulation sensitive indicators.

[0012] As a further aspect of the present invention, the specific steps of S5 are as follows: S501: Based on the monitoring objects in the dynamic state group of blood circulation sensitive indicators, extract the continuous time series of each type of indicator within the monitoring period, track the occurrence frequency, continuous segments and directional changes of the indicators in the same period, analyze whether the same directional changes occur repeatedly in multiple stages, and obtain the trend direction continuation sequence. S502: Based on the trend direction continuation sequence, identify the time range covered by the direction continuation of the indicator in the differentiated stage, retrieve the interval time between adjacent stages and the trend duration, and compare the time performance of the indicator in multiple stages to obtain the trend coverage time set. S503: Based on the trend coverage time set, analyze the time distribution of each type of indicator within the cycle, identify indicators that have a consistent trend in multiple time periods, analyze the duration and interval characteristics within the cycle, extract indicator data that are continuous and consistent in direction, and obtain the output sequence of blood circulation sensitive indicators.

[0013] A postoperative limb blood circulation sensitive indicator monitoring system for orthopedic surgery includes: The signal acquisition module acquires baseline characteristics of blood flow velocity, surface temperature and electromyography signals in the distal part of the affected limb of the postoperative bedridden patient, aligns the data time, analyzes the trend direction, duration and fluctuation amplitude within the same segment, and obtains the postoperative limb physiological signal characteristic group. The postural response module monitors the signal response status during the process of changing the body position from supine to lateral and from raised to lowered, based on the postoperative limb physiological signal characteristic group. It analyzes the continuity of blood flow direction, the delay of temperature response and the fluctuation of electromyographic frequency to obtain the body position-related circulatory response group. Based on the body position effect circulatory response group, the indicator extraction module compares the trend direction, start and end time and duration of blood flow, temperature and electromyography signals in the differentiated body position stages, identifies the signal content that recurs between stages and whose direction does not change, and obtains a list of blood circulation indicators. The status recognition module tracks the status changes of each indicator in the blood circulation indicator list within the monitoring period, analyzes the directional changes, fluctuation frequency and duration of adjacent time periods, extracts the indicator data of repeated status changes, and obtains the dynamic status group of blood circulation sensitive indicators. The results output module analyzes the frequency of occurrence, directional consistency and distribution time of the indicators in the dynamic state group of blood circulation sensitive indicators based on the data in the group, and obtains the output sequence of blood circulation sensitive indicators.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by integrating the trend characteristics of blood flow, temperature and electromyography signals, a correlation structure between body position changes and periodic fluctuations is constructed. Based on the consistency of signal direction, frequency changes and time distribution, a dynamic index sequence is generated to complete the full-process tracking and stage identification of blood circulation status. This enables sensitive indicators to have trend response characteristics and periodic adaptability, enhances the coherence of data screening and the stable performance of monitoring results, and promotes the ability of indicators to maintain stable tracking and pattern extraction in multi-stage scenarios. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the steps of the present invention; Figure 2 This is a detailed schematic diagram of S1 of the present invention; Figure 3 This is a detailed schematic diagram of S2 of the present invention; Figure 4 This is a detailed schematic diagram of S3 of the present invention; Figure 5 This is a detailed schematic diagram of S4 of the present invention; Figure 6 This is a detailed schematic diagram of S5 of the present invention; Figure 7 This is a system module diagram of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0018] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0019] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0020] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0021] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0022] Please see Figure 1 This invention provides a method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery, including the following steps: S1: Obtain the blood flow velocity sequence, surface temperature change direction and electromyographic signal baseline characteristics of the distal part of the affected limb of the postoperative bedridden patient. In each time period, align the data by time and analyze the trend consistency within the same time period. Compare the trend direction, duration and frequency fluctuation amplitude item by item to identify the signal manifestations that show synchronous changes and persist, and obtain the postoperative limb physiological signal characteristic group. S2: Based on the postoperative limb physiological signal characteristics group, during the process of changing the body position from supine to lateral and from raised to naturally hanging down, the continuity of blood flow direction, temperature response lag time and electromyographic signal baseline characteristics before and after the change of body position are analyzed. The response of signal changes in adjacent stages is compared, and signal parameters that show directional shift and enhanced fluctuation during the body position change stage are identified to obtain the body position-affected circulatory response group. S3: Based on the circulatory response group affected by body position, the comparison was carried out around the duration of changes, the start and end points of fluctuations, and the trend direction during the differential body position change phase. The changes in blood flow, temperature, and electromyography data during the differential body position phase were compared. The signal performance that repeatedly showed consistent trends and corresponding start and end points during the identification phase was identified. The source signal type was distinguished, and the monitoring direction was analyzed based on the consistency of trend direction and time correspondence to obtain a list of blood circulation indicators. S4: Based on each type of data in the list of blood circulation indicators, continuously track the same indicators within the monitoring period, compare the trend changes of indicators in adjacent time periods within each period, and identify the monitoring objects that have changed according to the manifestation of trend reversal, duration extension and fluctuation frequency increase. Add the sequence distribution of continuous fluctuation time and reversal frequency in the trend change process to obtain the dynamic state group of blood circulation sensitive indicators. S5: Based on the monitoring objects in the dynamic state group of blood circulation sensitive indicators, focus on the frequency of occurrence, continuous segments and repeated trend performance of indicators within the monitoring period, compare each parameter that shows the same trend in multiple stages, and analyze the performance characteristics of indicators within the period by comparing the coverage of change periods and the interval between adjacent changes, and obtain the output sequence of blood circulation sensitive indicators.

[0023] The postoperative limb physiological signal characteristics group includes the blood flow velocity trend direction, surface temperature change direction, and baseline characteristic fluctuation amplitude of electromyography signals. The body position influences the circulatory response group, including the continuity of blood flow direction, temperature response lag time, and continuous state of electromyography frequency. The list of blood circulation indicators includes the consistency of trend direction, the correspondence between start and end times, and the type of signal source. The dynamic state group of blood circulation sensitive indicators includes trend reversal performance, duration changes, distribution of fluctuation frequency, fluctuation time series, and turning frequency series. The output sequence of blood circulation sensitive indicators includes the frequency of indicator occurrence, the range of continuous segments, the recurrence of trends, the coverage of change segments, and the characteristics of change intervals.

[0024] Please see Figure 2 The specific steps of S1 are as follows: S101: Obtain the blood flow velocity sequence, surface temperature change direction, and electromyographic signal baseline characteristics of the distal part of the affected limb of a bedridden patient after surgery. Synchronize the three types of signals under a unified time line, detect continuous sampling segments of each type of signal, exclude data segments with broken time intervals, and obtain a time-aligned signal sequence group. First, multiple sensors were implanted in the dorsalis pedis artery, the skin surface of the distal extremities, and the belly of the gastrocnemius muscle in postoperative bedridden patients to collect blood flow velocity, surface temperature, and electromyography (EMG) signals at sampling frequencies of 50Hz, 1Hz, and 1000Hz, respectively. Due to the different frequencies, there was a time axis inconsistency. Therefore, the EMG signal, with the highest sampling frequency, was used as a reference. The blood flow and temperature signals were upsampled using cubic polynomial interpolation to ensure that the number of data points collected per second matched the EMG signal, thus aligning them on the same time axis. After frequency processing, continuity was assessed for each signal type, and the time difference between two adjacent sets of valid data was calculated. If the interval exceeded 0.5 seconds... If the signal is considered to be discontinuous, the data within 1 second before and after the corresponding position will not be included in the subsequent analysis to eliminate the interference of abnormal boundaries on trend analysis. The remaining data are directly spliced ​​to form a continuous segment. For example, in a 30-minute acquisition, if the blood flow signal is missing for 1.2 seconds at 15 minutes and 20 seconds, the segment between 19 seconds and 21 seconds at 15 minutes will be removed. The signal sequences before and after the missing signal will continue the analysis process. At the same time, the temperature signal is interpolated from 1Hz to 1000Hz to keep it consistent with other signals in time. Finally, the three types of signals are expanded according to a unified sampling rhythm, and discontinuous interference segments are eliminated to obtain a time-aligned signal sequence group.

[0025] S102: Based on time-aligned signal sequence groups, extract the direction of change, duration and frequency fluctuation range of each type of signal within the same time period. According to the rising and falling trend of blood flow velocity, the directional response of temperature change and the high and low distribution of electromyographic frequency, compare the trend direction among the three types of signals to obtain a set of trend-consistent intervals. First, sliding window feature extraction is performed on each type of signal in the time-aligned signal sequence group. The sliding window duration is set to 5 seconds and the sliding step size is 1 second. Within each window, the signal data is linearly fitted using the least squares method, and the slope value of the fitted line is obtained to represent the direction of change. If the fitted slope of blood flow velocity is positive and the absolute value is greater than 0.1, it is determined to be an upward trend; if it is negative and the absolute value is greater than 0.1, it is determined to be a downward trend; and if the absolute value is less than or equal to 0.1, it is determined to be stationary. Similarly, the trend determination is performed on the direction of temperature change and electromyography frequency. At the same time, the difference between the maximum and minimum values ​​of the signal within the window is calculated as the frequency fluctuation range, and the time span during which the trend remains unchanged in multiple consecutive windows is counted as the duration. Subsequently, the process performs logical comparison of multi-signal trends. Based on the physiological law of postoperative limb circulation recovery, a trend consistency determination logic is constructed. When blood flow velocity shows a trend of... If the surface temperature changes in a positive direction and the baseline characteristics of the electromyography (EMG) signal are in a low-frequency distribution (below the preset muscle tension threshold of 50 Hz), then the three types of signals are determined to have positive consistency in a physiological sense. Conversely, if blood flow decreases, temperature drops, and the EMG signal is high-frequency, then it is determined to have negative consistency. This process involves matching the change direction characteristics of the three types of signals within the same time period using the above logic. For example, within a 5-second time window, the calculated blood flow velocity slope is 2.5 (i.e., rising state), the surface temperature slope is 0.05 (i.e., rising state), and the mean value of the baseline characteristics of the EMG signal is 35 Hz (i.e., low-frequency state). Substituting these parameters into the judgment logic, if they meet the positive consistency standard, the start and end points of this time period are recorded. If the consistency condition is met for three consecutive windows (i.e., more than 3 seconds), then this continuous time area is marked as a valid interval, resulting in a set of trend-consistent intervals.

[0026] S103: Based on the set of trend-consistent intervals, analyze the direction and duration of change of three types of signals in each segment, identify data segments that have both directional consistency and continuous performance characteristics in the same interval, and obtain the postoperative limb physiological signal feature group. First, for each marked trend-consistent interval, refined feature verification and data extraction are performed. The specific direction of change of the three types of signals within the interval is read to confirm that no signal exhibits a directional reversal spike throughout the entire interval duration. If a signal within the interval suddenly shows a brief negative slope within a certain second and then recovers to a positive slope, even though the overall trend is upward, the interval will be cut off at the reversal point according to the requirement of continuous performance characteristics, retaining only the two sub-intervals with pure direction before and after. Next, the duration of the interval is further filtered, setting the minimum effective physiological response threshold to 10 seconds. This threshold is set with reference to the average response latency of vascular smooth muscle to neural regulation. If a segment remains after despiking... If the length is less than 10 seconds, it is removed from the set. For the segments that meet the conditions, the core feature parameters are extracted, including the average blood flow acceleration, total temperature rise, average variance of electromyography frequency, and the start and end timestamps of the segment. Taking actual data as an example, a trend-consistent interval of 45 seconds is processed. At the 20th to 22nd second, the electromyography signal shows a brief high-frequency fluctuation due to the patient's cough. This discontinuity is identified and the original interval is split into two segments: 0 to 20 seconds and 22 to 45 seconds. Since the 0 to 20 second segment is longer than the 10-second threshold and the three types of signals are always in the same direction, this segment is retained. Finally, the detailed data of these two segments and their calculated average acceleration, temperature rise, and other parameters are packaged to obtain the postoperative limb physiological signal feature group.

[0027] Please see Figure 3 The specific steps of S2 are as follows: S201: Based on the postoperative limb physiological signal feature group, during the positional transition from supine to lateral and from elevated to drooping, the blood flow velocity direction, surface temperature change and electromyographic signal baseline feature data are extracted. According to the continuous performance of the parameters in the previous and subsequent positional states, the continuous state set of positional stage signals is obtained. First, the time window for specific positional changes is identified using position sensors or time stamps recorded in the nursing log. For example, this could be the process of changing from a supine to a lateral decubitus position, or from raising the affected limb 30 degrees to letting it hang naturally. Within the timeframe of 30 seconds before each change event and 60 seconds after the change, corresponding blood flow, temperature, and electromyography (EMG) data are extracted from the postoperative limb physiological signal characteristic set. Then, this process constructs a control sequence of the pre- and post-positional states in chronological order. The mean signal value during the stable phase before the change (the first 10 seconds) and the dynamic signal trajectory during the response phase after the change (the last 30 seconds) are calculated, with a focus on the continuous performance of the signal at the moment of state transition, i.e., whether there is any [missing information]. In cases of a sharp drop, a sudden surge, or a smooth transition, a complete state transition curve is formed by splicing the ending value of the previous state with the starting trend of the next state. For example, when a patient lowers their limb from an elevated position to a hanging position, data before and after the switching moment is extracted. Before the switching, the blood flow velocity is maintained at 15 cm / s. After the switching action occurs, the blood flow velocity surges to 35 cm / s within 5 seconds due to the influence of gravity, then falls back to 25 cm / s and remains stable. At the same time, the electromyographic frequency jumps instantaneously from 30 Hz in the relaxed state to 80 Hz in the contracted state to maintain posture. These data sequences, which include the entire process from stability to sudden change and then back to stability, are structured and stored to obtain a continuous state set of postural phase signals.

[0028] S202: Based on the continuous state set of signals during the body position phase, compare the performance of blood flow direction change continuity, temperature response delay and electromyographic frequency fluctuation between the previous and subsequent body positions, and screen the signal items that show direction shift and fluctuation amplification during the switching process to obtain the body position change response signal set. First, differential calculations are performed on each set of data in the continuous state set of the body position phase signal to calculate the continuity of blood flow direction changes. This involves comparing the blood flow slope at the beginning of the subsequent body position with the blood flow slope at the end of the previous body position. If the signs of the two are opposite (e.g., from positive to negative) and the absolute value of the difference exceeds a preset flow velocity change benchmark of 2.0 cm / s², a direction shift is determined. Second, the temperature response delay is calculated, which is the time difference between the moment of body position change and the moment when the surface temperature change rate exceeds 0.01 degrees Celsius / second. If this delay is within the physiologically reasonable range of 5 to 60 seconds, it is considered a valid response. Third, electromyographic frequency fluctuations are calculated... The ratio of the frequency variance in the first 10 seconds after the change in position to the variance in the previous position is calculated. If the ratio is greater than 2, it is considered an increase in fluctuation. Signals that simultaneously meet the above screening conditions are marked. For example, in a record of changing from supine to lateral decubitus, the blood flow velocity slope changes from 0 to -2.5, and the absolute value of the difference is 2.5, which is greater than the baseline value of 2.0, satisfying the direction shift condition. The temperature begins to decrease 25 seconds after the change in position, satisfying the delay condition. The electromyographic variance ratio is 3.5, which is greater than 2, satisfying the condition of increased fluctuation. This set of signals clearly reflects the direct impact of the change in position on limb circulation and is therefore selected to obtain the set of response signals to the change in position.

[0029] S203: Based on the body position change response signal set, track the fluctuation trend and response trajectory of blood flow, temperature, and electromyography signals during the transformation process, align the temporal changes of the signals, and obtain the body position effect circulatory response group. First, the temporal alignment and trajectory modeling of multidimensional signals are performed. Since blood flow, temperature, and electromyography (EMG) respond differently to changes in body position, the moment of body position switching is taken as the zero point. The response trajectories of the three types of signals are mapped onto a unified relative time axis. By calculating the time points when each type of signal reaches its peak or trough, a time difference spectrum between stimulus and response is constructed. This process further analyzes the morphology of the fluctuation trend and classifies the response trajectory into damped oscillation type, divergent type, or step type. By superimposing the trajectories of the three types of signals under the same body position change event, a complete cyclic response view is formed. For example, the EMG surge moment, the blood flow extreme moment, and the temperature inflection point moment are arranged in sequence to form a chain reaction chain from EMG leader to blood flow follower to temperature lag. These trajectory data sets that have undergone temporal calibration and morphological classification are integrated to obtain the cyclic response group affected by body position.

[0030] Please see Figure 4 The specific steps of S3 are as follows: S301: Based on the circulatory response group affected by body position, continuous data frames of blood flow velocity, surface temperature and electromyography frequency are extracted during the differential body position change phase. The fluctuation start time and duration of each type of signal are compared according to the same time segment to obtain the phase trend control segment. First, for different types of body position changes, such as the elevation to lowering and the supine to lateral position, corresponding continuous data frames are extracted. The data frames for each type of body position change are divided into several standardized time segments, for example, every 5 seconds. Within each segment, the specific moment when blood flow, temperature, and electromyography signals begin to fluctuate significantly (i.e., exceed 5% of the baseline value) is identified as the fluctuation onset point, and the time required for the fluctuation amplitude to return to within 5% of the baseline value is identified as the duration. Subsequently, this process is compared horizontally between different body position change stages. For example, comparing whether the onset point of blood flow velocity fluctuation in the elevation to lowering stage and the supine to lateral position stage are at the same position on the relative time axis, and whether the duration is similar, this comparison identifies signal segments that show similar time characteristics under different body position challenges. These data segments that have been confirmed to be comparable are marked to obtain stage trend comparison segments.

[0031] S302: Based on phase trend comparison fragments, sequences in blood flow, temperature, and electromyography that show consistent fluctuation directions in multiple phases are selected, and data segments with overlapping start and end times and concentrated interval variation ranges are extracted to obtain a group of sequences with overlapping trend directions. First, cross-stage consistency screening is performed based on the phase trend comparison segments. The core logic is to find common circulatory features that are not limited by specific body position types. Signal sequences that maintain a consistent direction of fluctuation in at least two different phases of body position change are retrieved. For example, regardless of limb movement, if the blood flow velocity always shows a pattern of first decreasing and then increasing, the sequence meets the directional consistency condition. On this basis, the process further calculates the overlap of the start and end times of these sequences in different phases, setting the overlap threshold to 0.8 seconds. That is, the difference between the start and end times of fluctuation in different phases must be less than 0.8 seconds. At the same time, the time interval between adjacent fluctuation peaks is calculated. If the variation range of this interval is concentrated within 10% of the mean, it is judged as interval concentration. This process extracts data segments that meet all the above conditions of directional consistency, start and end overlap, and interval concentration. For example, data analysis shows that in three different body position changes, the blood flow signal begins to decrease 3 seconds after the movement and lasts for 15 seconds. The decreasing trend is highly similar. These three data segments are then extracted as a group of strongly correlated evidence, resulting in a trend direction overlap sequence group.

[0032] S303: Based on trend direction coincidence sequence groups, data frames are split according to signal source, and the signal performance of each type of signal that has the same direction and appears in the same change segment is extracted. The response distribution is analyzed according to the time overlap relationship to obtain a list of blood circulation indicators. First, various types of sensors were placed on the dorsalis pedis artery, the skin surface of the distal extremities, and the belly of the gastrocnemius muscle in postoperative bedridden patients to collect blood flow velocity, surface temperature, and electromyography (EMG) signals, respectively. The sampling frequencies for the three types of signals were set to 50 Hz for blood flow, 1 Hz for temperature, and 1000 Hz for EMG. Due to the different sampling frequencies, to eliminate the influence of time axis misalignment, the EMG signal with the highest sampling frequency was used as the time reference. Temperature and blood flow signals were supplemented with data points per second using a cubic polynomial interpolation method, ensuring that the amount of data collected per second was consistent with the EMG signal, thus synchronizing the three types of signals in time. After this processing, a continuity check was performed on each type of signal. By traversing the time series, the interval between every two adjacent valid data points was calculated. If the time interval exceeded 0.5 seconds, the current sequence was considered interrupted. In this case, to avoid abnormalities at the beginning and end affecting the overall trend judgment, the data within 1 second before and after the interruption were excluded, and only the remaining continuous portion was retained for subsequent analysis. For example, in a 30-minute data acquisition, if the blood flow signal has a 1.2-second interruption at 15 minutes and 20 seconds, the segment between 15 minutes and 19 seconds and 21 seconds will not be used, and the data from the two time periods before and after will be processed as two independent segments. The original sampling frequency of the temperature signal is 1Hz, and it needs to be supplemented with data per second to 1000 to achieve consistency with the electromyographic signal in terms of temporal distribution, thus obtaining a list of blood circulation indicators.

[0033] Please see Figure 5 The specific steps of S4 are as follows: S401: Based on each type of data in the list of blood circulation indicators, track and monitor blood flow velocity, surface temperature and electromyography frequency within the monitoring period. Extract continuous sequences for each data item according to time period, and retrieve the trend direction, duration of change and fluctuation frequency of adjacent time periods to obtain time period trend sequence groups. First, based on a list of blood circulation indicators, full-time tracking was performed during a 24-hour postoperative monitoring period. The monitoring period was divided into 30-minute intervals, resulting in 48 intervals. Continuous sequence data of the specified indicators in the list were extracted within each interval. Subsequently, the process performed a recursive retrieval between adjacent intervals, calculating the differences in the trend direction, duration of change, and frequency of fluctuation of the indicators between the current and previous intervals. By quantifying the changes in these characteristics, a time series reflecting the evolution of the condition was constructed. For example, comparing interval 10 and interval 11, it was found that the average fluctuation frequency of blood flow velocity increased from 0.2 Hz to 0.5 Hz, and the duration of a single fluctuation decreased by 40% (i.e., from 5 seconds to 3 seconds, calculated by dividing the change by the original value). These specific comparative data were recorded to obtain the time-interval trend sequence group.

[0034] S402: Based on the time-period trend sequence group, identify data frames with trend reversal, duration extension and fluctuation frequency increase in the previous and subsequent stages, compare the range of trend behavior and fluctuation density in the time period, and obtain the trend change signal set; First, a strict set of abrupt change identification logic is established to process the time-period trend sequence group, identifying trend reversals. If the product of the average slopes of an indicator in adjacent time periods is negative and the sum of the absolute values ​​of the two slopes exceeds a preset abrupt change benchmark value of 0.5, then a trend reversal is determined. Second, an extended duration is identified; if the duration of monotonic change of the indicator in a later time period is more than 1.5 times that of the previous time period, it is determined to be an extended duration. Finally, an increased number of fluctuations is identified; if the peak fluctuation count in a later time period increases by more than 30% compared to the previous time period, it is determined to be an increased number of fluctuations. This process further calculates... Calculate the range and fluctuation density of these mutation behaviors in the current time period. If the range of change exceeds twice the historical average or the fluctuation density is in the top 5% range, the signal frame is confirmed as a significant mutation. By substituting the aforementioned parameters into the calculation, assuming the slope of the previous time period is 1.2 and the slope of the next time period is -0.8, the product is negative and the sum of the absolute values ​​is 2.0, which is greater than the baseline value of 0.5, confirming the reversal. At the same time, the fluctuation density of the next time period is 12 times per minute, which is much higher than the baseline of 4 times per minute. Extract these data frames containing significant abnormal characteristics to obtain the trend mutation signal set.

[0035] S403: Based on the trend change signal set, extract the duration of continuous fluctuation and the frequency of turning according to the monitored object, retrieve the time distribution and change repetition rate of the corresponding sequence of the same object in the differentiated time period, extract the index sequence with continuous change characteristics, and obtain the dynamic state group of blood circulation sensitive indicators. First, the trend mutation signal set is subjected to longitudinal statistical feature extraction. For each monitored object, the duration of continuous fluctuation and the frequency of turning points in each mutation are calculated. Next, the process retrieves all mutation records of the same type of object throughout the entire monitoring period, analyzes their temporal distribution characteristics, calculates the mean and variance of the time interval between mutation occurrences, and determines whether they exhibit a periodic distribution. At the same time, the repetition rate of the change pattern is calculated, that is, the proportion of a certain mutation waveform appearing in all mutation records. If the repetition rate exceeds 60% and the mutation events show a continuous distribution characteristic on the time axis, i.e., the interval time is less than 2 hours, then the indicator sequence is extracted. Finally, this process integrates these statistically verified indicator sequences with highly dynamic and continuous characteristics to obtain the dynamic state group of blood circulation sensitive indicators.

[0036] Please see Figure 6 The specific steps of S5 are as follows: S501: Based on the monitoring objects in the dynamic state group of blood circulation sensitive indicators, extract the continuous time series of each type of indicator within the monitoring period, track the occurrence frequency, continuous segments and directional changes of the indicators in the same period, analyze whether the same directional changes occur repeatedly in multiple stages, and obtain the trend direction continuation sequence. First, key monitoring targets are identified from the dynamic state group, and their complete time series throughout the entire monitoring period are traced back. The total number of occurrences of the indicator within the period is counted using the sliding window counting method. At the same time, continuous segments in which the indicator maintains a specific state are identified, and the directional change trajectory within each segment is recorded. The core logic is to verify the reproducibility of multiple stages. The monitoring period is divided into three stages: early, middle, and late. It is checked whether a specific directional change is detected in at least two stages. If the change pattern appears in the early stage and reappears in the middle stage, the trend is determined to be continuous. For example, if an indicator shows a negative fluctuation 2 hours after surgery (early stage) and then shows a negative fluctuation of the same magnitude 8 hours after surgery (middle stage), it is confirmed that this negative fluctuation is an inherent and continuous pathological or physiological trend. These two segments and subsequent similar fluctuation sequences are extracted to obtain the trend direction continuation sequence.

[0037] S502: Based on the trend direction continuation sequence, identify the time range covered by the direction continuation of the indicator in the differentiated stage, retrieve the time interval between adjacent stages and the trend duration, and compare the time performance of the indicator in multiple stages to obtain the trend coverage time set. First, a quantitative analysis of the trend direction continuation sequence is performed over time to identify the specific start and end times covered by the trend in each differentiated stage, and the time span covered is calculated, for example, 10 minutes in the early stage and 25 minutes in the middle stage. Then, the interval between two adjacent stages is calculated, i.e., the duration of the trend incubation. At the same time, the duration data of each trend outbreak is extracted to construct a time performance comparison table, and the rate of change of the duration of the same indicator in different stages is compared horizontally. If the duration of the later stage increases significantly compared to the previous stage, such as by 50% (e.g., from 10 minutes to 15 minutes, with a growth rate of 50%), it indicates that the trend is deteriorating or accumulating. This process encapsulates all time distribution parameters of the indicator in a structured way to obtain the trend coverage time set.

[0038] S503: Based on the trend coverage time set, analyze the time distribution of each type of indicator within the cycle, identify indicators that have a consistent trend in multiple time periods, analyze the duration and interval characteristics within the cycle, extract indicator data that are continuous and consistent in direction, and obtain the output sequence of blood circulation sensitive indicators. First, a comprehensive logical judgment is made on the trend coverage time set to analyze the time distribution density of each type of indicator throughout the entire cycle. Indicators with excessively sparse distributions, i.e., those appearing only once a day, are eliminated, while those with a consistent trend across three or more time periods are retained. Next, this process combines duration and interval characteristics for final screening, prioritizing the extraction of indicator data with increasing durations and decreasing intervals, as this represents the approaching risk of circulatory changes. These indicators, which have undergone multiple screenings, exhibit high continuity, and maintain strict consistency in direction, are then prioritized. Finally, the selected core data is packaged to generate a data package containing the indicator name, current state value, trend direction, expected duration, and risk level, resulting in the blood circulation sensitive indicator output sequence.

[0039] Please see Figure 7 A postoperative limb blood circulation sensitive indicator monitoring system for orthopedic surgery includes: The signal acquisition module acquires baseline characteristics of blood flow velocity, surface temperature and electromyography signals in the distal part of the affected limb of the postoperative bedridden patient, aligns the data time, analyzes the trend direction, duration and fluctuation amplitude within the same segment, and obtains the postoperative limb physiological signal characteristic group. The postural response module monitors the signal response status during the process of changing the body position from supine to lateral and from raised to lowered, based on the postoperative limb physiological signal characteristic group. It analyzes the continuity of blood flow direction, the delay of temperature response and the fluctuation of electromyographic frequency to obtain the body position effect circulatory response group. The indicator extraction module is based on the body position effect circulatory response group. It compares the trend direction, start and end time and duration of blood flow, temperature and electromyography signals in the differentiated body position stages, identifies the signal content that recurs between stages and whose direction does not change, and obtains a list of blood circulation indicators. The status recognition module tracks the status changes of each indicator in the blood circulation indicator list within the monitoring period, analyzes the directional changes, fluctuation frequency and duration of adjacent time periods, extracts the indicator data of repeated status changes, and obtains the dynamic status group of blood circulation sensitive indicators. The results output module analyzes the frequency of occurrence, directional consistency, and distribution time of the indicators in the dynamic state group of blood circulation sensitive indicators based on the data in the group, and obtains the output sequence of blood circulation sensitive indicators.

[0040] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery, characterized in that, Includes the following steps: S1: Obtain baseline characteristics of blood flow velocity, surface temperature and electromyography signals in the distal part of the affected limb of the postoperative bedridden patient, analyze the trend direction, duration and fluctuation amplitude in the same segment, and obtain the postoperative limb physiological signal characteristic group. S2: Based on the postoperative limb physiological signal characteristic group, monitor the signal response status during the process of changing the body position from supine to lateral and from raised to lowered, analyze the continuation of blood flow direction, the delay of temperature response and the fluctuation of electromyographic frequency, and obtain the body position-related circulatory response group. S3: Based on the body position-related circulatory response group, compare the trend direction, start and end time and duration of blood flow, temperature and electromyography signals in the differentiated body position stages, identify the signal content that recurs between stages and whose direction does not change, and obtain a list of blood circulation indicators. S4: Based on the blood circulation index list, track the changes in the index status within the monitoring period, analyze the directional changes, fluctuation frequency and duration of adjacent time periods, and obtain the dynamic status group of blood circulation sensitive indicators. S5: Based on the dynamic state group of the blood circulation sensitive indicators, analyze the frequency of occurrence, directional consistency and distribution time of the indicators within the monitoring period to obtain the output sequence of blood circulation sensitive indicators.

2. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The postoperative limb physiological signal feature group includes the blood flow velocity trend direction, surface temperature change direction, and baseline characteristic fluctuation amplitude of electromyography signals. The body position influence on circulatory response group includes the continuity of blood flow direction, temperature response lag time, and continuous state of electromyography frequency. The list of blood circulation indicators includes trend direction consistency, start and end time correspondence, and signal source type. The dynamic state group of blood circulation sensitive indicators includes trend reversal performance, duration change, fluctuation frequency distribution, fluctuation time series, and turning frequency series. The output sequence of blood circulation sensitive indicators includes indicator occurrence frequency, duration range, trend repetition performance, change segment coverage, and change interval characteristics.

3. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The blood flow direction continuity refers to the fact that the trend of blood flow velocity changes remains consistent and continuous for a period of time before and after the change of body position. The temperature response delay refers to the phenomenon that after a change in body position occurs, the surface temperature change has a time lag, and the response only begins after a certain lag time.

4. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The differentiated position phase refers to the phase interval formed by the patient's positional changes. The change in indicator status refers to the change in the trend direction, duration, and frequency of fluctuations of the same sensitive indicator between adjacent time periods throughout the entire monitoring period.

5. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The specific steps of S1 are as follows: S101: Obtain the blood flow velocity sequence, surface temperature change direction, and electromyographic signal baseline characteristics of the distal part of the affected limb of a bedridden patient after surgery. Synchronize the three types of signals under a unified time line, detect continuous sampling segments of each type of signal, exclude data segments with broken time intervals, and obtain a time-aligned signal sequence group. S102: Based on the time-aligned signal sequence group, extract the direction of change, duration and frequency fluctuation range of each type of signal within the same time period. According to the rising and falling trend of blood flow velocity, the directional response of temperature change and the high and low distribution of electromyographic frequency, compare the trend direction among the three types of signals to obtain a set of trend-consistent intervals. S103: Based on the set of trend-consistent intervals, analyze the direction and duration of change of the three types of signals in each segment, identify data segments that simultaneously have directional consistency and continuous performance characteristics in the same interval, and obtain the postoperative limb physiological signal feature group.

6. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The specific steps of S2 are as follows: S201: Based on the postoperative limb physiological signal feature group, during the positional switching from supine to lateral and from elevated to drooping, extract the blood flow velocity direction, surface temperature change and electromyographic signal baseline feature data, and obtain the continuous state set of positional stage signals according to the continuous performance of the parameters in the previous and subsequent positional states in a time sequence. S202: Based on the continuous state set of body position stage signals, compare the performance of blood flow direction change continuity, temperature response delay and electromyography frequency fluctuation between the previous and previous body positions, and filter out signal items that show direction shift and fluctuation amplification during the switching process to obtain the body position change response signal set. S203: Based on the set of body position change response signals, track the fluctuation trends and response trajectories of blood flow, temperature, and electromyography signals during the transformation process, align the temporal changes of the signals, and obtain the body position effect circulatory response group.

7. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The specific steps for S3 are as follows: S301: Based on the body position effect circulatory response group, extract continuous data frames of blood flow velocity, surface temperature and electromyography frequency in the differential body position change stage, compare the fluctuation start time and duration of each type of signal according to the same time segment to obtain the stage trend comparison segment. S302: Based on the aforementioned stage trend comparison fragments, select sequences in blood flow, temperature, and electromyography that show consistent fluctuation directions in multiple stages, extract data segments with overlapping start and end times and concentrated interval variation ranges, and obtain a group of sequences with overlapping trend directions. S303: Based on the trend direction coincidence sequence group, split the data frame according to the signal source, extract the signal performance of each type of signal that has the same direction and appears in the same change segment, analyze the response distribution according to the time overlap relationship, and obtain a list of blood circulation indicators.

8. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The specific steps of S4 are as follows: S401: Based on each type of data in the blood circulation index list, track and monitor blood flow velocity, surface temperature and electromyography frequency within the monitoring period, extract continuous sequences for each data item according to time period, and retrieve the change characteristics of trend direction, duration of change and fluctuation frequency in adjacent time periods to obtain time period trend sequence group; S402: Based on the time period trend sequence group, identify data frames with trend reversal, duration extension and fluctuation increase in the preceding and following stages, compare the range of trend behavior and fluctuation density within the time period, and obtain a set of trend change signals; S403: Based on the trend mutation signal set, extract the duration of continuous fluctuations and the frequency of turning according to the monitored object, retrieve the time distribution and change repetition rate of the corresponding sequence of the same object in the differentiated time period, extract the index sequence with continuous change characteristics, and obtain the dynamic state group of blood circulation sensitive indicators.

9. The method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery according to claim 1, characterized in that, The specific steps of S5 are as follows: S501: Based on the monitoring objects in the dynamic state group of blood circulation sensitive indicators, extract the continuous time series of each type of indicator within the monitoring period, track the occurrence frequency, continuous segments and directional changes of the indicators in the same period, analyze whether the same directional changes occur repeatedly in multiple stages, and obtain the trend direction continuation sequence. S502: Based on the trend direction continuation sequence, identify the time range covered by the direction continuation of the indicator in the differentiated stage, retrieve the interval time between adjacent stages and the trend duration, and compare the time performance of the indicator in multiple stages to obtain the trend coverage time set. S503: Based on the trend coverage time set, analyze the time distribution of each type of indicator within the cycle, identify indicators that have a consistent trend in multiple time periods, analyze the duration and interval characteristics within the cycle, extract indicator data that are continuous and consistent in direction, and obtain the output sequence of blood circulation sensitive indicators.

10. A postoperative limb blood circulation sensitive index monitoring system, characterized in that, The system is used to implement the method for monitoring sensitive indicators of limb blood circulation after orthopedic surgery as described in any one of claims 1-9, the system comprising: The signal acquisition module acquires baseline characteristics of blood flow velocity, surface temperature and electromyography signals in the distal part of the affected limb of the postoperative bedridden patient, aligns the data time, analyzes the trend direction, duration and fluctuation amplitude within the same segment, and obtains the postoperative limb physiological signal characteristic group. The postural response module monitors the signal response status during the process of changing the body position from supine to lateral and from raised to lowered, based on the postoperative limb physiological signal characteristic group. It analyzes the continuity of blood flow direction, the delay of temperature response and the fluctuation of electromyographic frequency to obtain the body position-related circulatory response group. Based on the body position-related circulatory response group, the indicator extraction module compares the trend direction, start and end time and duration of blood flow, temperature and electromyography signals in the differentiated body position stages, identifies the signal content that recurs between stages and whose direction does not change, and obtains a list of blood circulation indicators. The status recognition module tracks the status changes of each indicator in the blood circulation indicator list within the monitoring period, analyzes the directional changes, fluctuation frequency and duration of adjacent time periods, extracts the indicator data of repeated status changes, and obtains the dynamic status group of blood circulation sensitive indicators. The results output module analyzes the frequency of occurrence, directional consistency and distribution time of the indicators in the dynamic state group of blood circulation sensitive indicators based on the data in the group, and obtains the output sequence of blood circulation sensitive indicators.

Images