Information interaction control method and system of vital sign monitor

Abstract

The invention relates to the technical field of vital sign monitoring, in particular to an information interaction control method and system of a vital sign monitor. The method comprises the following steps that physiological signals are synchronously collected through a sensor array, wherein the physiological signals comprise electrocardio waveform data, electric volume pulse wave data, motion acceleration data and body surface temperature data; time alignment is conducted on the electrocardiogram waveform data, the electric volume pulse wave data and the motion acceleration data based on a clock synchronization protocol, matrix construction is conducted, and a synchronous vital sign matrix is generated; carrying out risk change trajectory construction of a pathological trajectory on the filtering data and the historical case data, generating a vital sign risk trajectory, and carrying out super-boundary judgment on the vital sign risk trajectory; by means of the high-precision synchronization mechanism, it is ensured that the internal relevance of electrocardio, pulse waves, movement and temperature data is accurately captured.

Description

Technical Field

[0001] The present invention relates to the technical field of vital sign monitoring, and in particular to an information interaction control method and system for a vital sign monitor. Background Art

[0002] The information interaction control method of existing vital signs monitors has significant defects: multi-source physiological signals (ECG / photoplethysmography / acceleration) have timestamp drift due to hardware clock asynchrony, and need to rely on fixed delay compensation, which cannot dynamically adapt to the device crystal oscillator drift, resulting in the failure of motion interference suppression; the signal processing channel selection mechanism is rigid, and only statically switches the filtering mode based on the acceleration threshold, ignoring the dynamic characteristics of the motion spectrum entropy value (0.5-10Hz) and the covariance of physiological signals, resulting in excessive filtering in static scenes or residual artifacts in motion scenes; risk warning relies on a single threshold cutoff (such as ECG risk >80%), which cannot identify early risk gradient trends; data traceability is weak, and only the current data fragment is stored when the clinical alarm is triggered. There is a lack of full-process node marking, which makes it impossible to reproduce and analyze false positive events. Summary of the Invention

[0003] Based on this, it is necessary to provide an information interaction control method and system for a vital signs monitor to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for information interaction control of a vital signs monitor is provided, the method comprising the following steps: Step S1: synchronously collecting physiological signals through a sensor array, wherein the physiological signals include electrocardiogram waveform data, capacitance product pulse wave data, motion acceleration data and body surface temperature data; Step S2: Time-aligning the ECG waveform data, capacitance product pulse wave data, and motion acceleration data based on the clock synchronization protocol, and constructing a matrix to generate a synchronized vital sign matrix; Step S3: Calculating a motion divergence value based on the synchronized vital sign matrix and the motion acceleration data, selecting a processing channel based on the motion divergence value, and performing a filtering operation to obtain filtered data; Step S4: Execute the risk change trajectory of the pathology trajectory on the filtered data and the historical case data to generate the vital sign risk trajectory, and perform an out-of-bounds judgment on the vital sign risk trajectory; when the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered.

[0005] In this specification, an information interaction control system of a vital signs monitor is provided, which is used to execute the above-mentioned information interaction control method based on the vital signs monitor. The information interaction control system of the vital signs monitor includes: A multi-source synchronous acquisition module is used to synchronously acquire physiological signals through a sensor array, wherein the physiological signals include electrocardiogram waveform data, capacitance product pulse wave data, motion acceleration data and body surface temperature data; The timing alignment and feature matrix construction module is used to time-align ECG waveform data, capacitance product pulse wave data, and motion acceleration data based on the clock synchronization protocol, and to construct a matrix to generate a synchronized vital sign matrix; A motion interference perception and filtering channel selection module is used to calculate the motion divergence value based on the synchronized vital sign matrix and motion acceleration data, perform filtering operations, and select a processing channel based on the motion divergence value to obtain filtered data; The pathology evolution analysis and clinical early warning module is used to construct the risk change trajectory of the pathology trajectory based on the filtered data and historical case data, generate the vital sign risk trajectory, and make out-of-bounds judgments on the vital sign risk trajectory; when the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered.

[0006] The beneficial effects of the present invention are that, on the one hand, the motion divergence value is dynamically calculated through motion acceleration data, and the optimal filtering channel is intelligently selected to perform signal processing based on this, thereby improving the purity of the electrocardiogram waveform and pulse wave signal under motion interference; further, the adaptive filtering strategy based on real-time motion status effectively overcomes the limitations of traditional fixed filtering in dynamic scenarios.

[0007] On the other hand, by integrating real-time filtered data with historical case data, a vital sign risk trajectory that evolves over time is constructed; by quantitatively characterizing the dynamic changing trends of cardiovascular and circulatory system risks, early warning of pathological risks is achieved; in particular, the risk trajectory's out-of-bounds judgment mechanism can instantly trigger clinical alarms when the risk exceeds the safety threshold, thereby gaining a crucial time window for intervention in critical and severe illnesses.

[0008] Finally, the synchronous acquisition of the sensor array is combined with the clock synchronization protocol to construct a vital signs matrix, providing a spatiotemporally aligned data foundation for multimodal signal fusion analysis; this high-precision synchronization mechanism ensures that the inherent correlation between ECG, pulse wave, motion and temperature data is accurately captured. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic flow chart of the steps of an information interaction control method for a vital signs monitor; Figure 2 Demonstrate the filtering effect of ECG waveform data; Figure 3 Demonstrate the filtering effect of plethysmography data; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0010] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of the present invention.

[0011] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0012] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0013] To achieve this, please refer to Figures 1 to 3 , an information interaction control method for a vital signs monitor, the method comprising the following steps: Step S1: synchronously collecting physiological signals through a sensor array, wherein the physiological signals include electrocardiogram waveform data, capacitance product pulse wave data, motion acceleration data and body surface temperature data; In an embodiment of the present invention, during the vital signs monitoring process, four types of original physiological signals are collected in parallel at a fixed sampling frequency (e.g., 250 Hz) through a hardware-level synchronized sensor array: the voltage timing signal generated by the ECG lead (ECG waveform data), the light absorption intensity timing signal captured by the photoelectric sensor (capacitance product pulse wave data), the spatial acceleration vector output by the three-axis accelerometer (motion acceleration data), and the body surface temperature scalar value measured by the thermistor (body surface temperature data).

[0014] Step S2: Time-aligning the ECG waveform data, capacitance product pulse wave data, and motion acceleration data based on the clock synchronization protocol, and constructing a matrix to generate a synchronized vital sign matrix; In the embodiment of the present invention, a precise clock synchronization protocol (such as IEEE 1588 PTP) is used to synchronize the asynchronously collected ECG waveform sequence { }、Capacitance pulse wave sequence{ } and motion acceleration sequence { Perform time axis calibration: First, extract the hardware timestamps of each signal and uniformly map them to the reference time axis through the clock offset compensation algorithm. , then based on the highest sampling rate (such as ECG 250Hz), perform cubic spline interpolation on the pulse wave (usually 100Hz) and acceleration (usually 50Hz) data to generate a strictly aligned equal interval sequence { }; Finally, press timestamp Construct synchronized vital signs matrix SVM; In one implementation of the embodiment of the present invention, a reference time is set At 4ms intervals (250Hz), the original data is: ECG: Time collection value ; Pulse Wave: Time collection value (unitless light intensity); Acceleration: Time collection value ; After clock compensation and interpolation, Generate synchronization vectors at all times and finally construct a 10-second data matrix { } (2500 rows × 6 columns).

[0015] Step S3: Calculating a motion divergence value based on the synchronized vital sign matrix and the motion acceleration data, selecting a processing channel based on the motion divergence value, and performing a filtering operation to obtain filtered data; In an embodiment of the present invention, the synchronized vital sign matrix = is time-aligned with the three-axis motion acceleration data (sampling frequency is 50 Hz), the root mean square (RMS) value of the acceleration vector is calculated as the motion intensity indicator, and the difference between the motion signal and the vital sign signal is quantified based on covariance analysis to obtain the motion divergence value (range 0-1, the larger the value, the more significant the motion interference); then, according to a preset threshold (such as the divergence value > 0.7), a high signal-to-noise ratio processing channel is selected (such as preferentially using the channel index optimized by the motion compensation algorithm), and an adaptive filtering operation is performed to suppress high-frequency noise and motion artifacts, and finally the filtered vital sign time series data is output.

[0016] In one implementation of the present invention, assume that the synchronized vital sign matrix includes 10 seconds of sampled data (sampling rate 100 Hz) for heart rate (70 bpm ± 2 bpm), respiratory rate (16 bpm ± 1 bpm), and SpO2 (98% ± 1%), and the motion acceleration data is the acceleration vectors of the x-axis (0.8 g), y-axis (0.6 g), and z-axis (0.7 g). After calculation, the motion divergence value is 0.82 (based on the covariance between the RMS acceleration and the heart rate signal), which exceeds the threshold of 0.75. Therefore, the second real-time filtering channel is selected for processing, and the noise variance of the original heart rate signal is reduced from 0.15 bpm² to 0.05 bpm², obtaining a smooth filtered data sequence.

[0017] Step S4: Execute the risk change trajectory of the pathology trajectory on the filtered data and the historical case data to generate the vital sign risk trajectory, and perform an out-of-bounds judgment on the vital sign risk trajectory; when the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered.

[0018] In an embodiment of the present invention, the filtered vital sign data output from step S3 is aligned with a historical case database (medical course data of similar patients) using dynamic time warping (DTW), and the transition probability of the current vital sign sequence relative to the historical pathological trajectory is calculated. A continuous risk value sequence (ranging from 0 to 100, i.e., the vital sign risk trajectory) is constructed in a probability-weighted manner. An out-of-bounds judgment is made in conjunction with a preset clinical threshold (e.g., a static threshold > 85 or a dynamic threshold > 3 times the standard deviation). If five consecutive sampling points exceed the bounds, a clinical alarm is triggered.

[0019] In one implementation of an embodiment of the present invention, assuming that the current filtered data is a 10-minute heart rate sequence (mean 72 bpm, fluctuation ±3 bpm) and SpO2 sequence (mean 94%, fluctuation ±1%), and the historical case database matches the exacerbation data of three similar pneumonia patients; after HMM calculation, its transition probability shows that the current state transitions to high risk with a probability of 0.78, and the constructed risk value sequence reaches 89.2 (threshold 85) at t=125 seconds, and the subsequent four sampling points (interval 0.1 seconds) continue to be higher than 89.5 (standard deviation 2.1, dynamic threshold 87.3).

[0020] As described above, a Level 2 alarm (code ALM-03) is triggered, and the out-of-bounds parameters are recorded as [heart rate risk weight: 0.6, SpO2 risk weight: 0.4, duration: 0.5 seconds].

[0021] Preferably, step S2 includes the following steps: Performing normalization processing on the ECG waveform data to extract a first synchronous time series; performing the same time calibration on the plethysmographic data to extract a second synchronized time series; Performing clock compensation on the original timestamp of the motion acceleration data to extract the third synchronous time series; The first synchronized time series, the second synchronized time series, and the third synchronized time series are subjected to the same interpolation resampling to generate a first aligned ECG sequence, a second aligned PPG sequence, and a third aligned acceleration sequence, respectively; The first aligned ECG sequence, the second aligned PPG sequence and the third aligned acceleration sequence are used to construct a synchronized vital sign matrix.

[0022] In one implementation of an embodiment of the present invention, assuming that the original sampling point of the ECG waveform data is 500 Hz and the value range is [-1.5 mV, 1.5 mV], Z-score normalization is performed (mean is 0, standard deviation is 1), and the sequence within the time window of 0-2 seconds is extracted as the first synchronized time series. For example, the normalized value is 0.8 at t=1.0 second.

[0023] In another implementation of the embodiment of the present invention, time calibration is performed on the plethysmographic data (original sampling rate 100 Hz), linear interpolation is used to compensate for device delay (preset delay 20 ms), and a sequence of the same time window 0-2 seconds is extracted as the second synchronized time series. For example, the calibration value at t=1.0 second is 1024 photoplethysmographic units.

[0024] In another implementation of the embodiment of the present invention, clock compensation is performed on the motion acceleration data (three-axis original sampling rate 50 Hz, timestamp offset 5 ms), the time base is adjusted by subtracting the fixed offset, and a third synchronous time series is extracted. For example, the x-axis compensation value is 0.5 g at t = 1.0 second.

[0025] In another implementation of the embodiment of the present invention, the first, second, and third synchronized time series are uniformly resampled to a common sampling rate of 100 Hz by linear interpolation to generate a first aligned ECG sequence (e.g., after resampling, the value at t = 1.0 second is 0.75), a second aligned PPG sequence (the value at t = 1.0 second is 1010 units), and a third aligned acceleration sequence (the x-axis value at t = 1.0 second is 0.48 g).

[0026] In another implementation of the embodiment of the present invention, the above-mentioned alignment sequence is integrated into a synchronized vital sign matrix according to time points, and the matrix dimension is N×3 (N is the number of sampling points). For example, at t=1.0 second, the row vector is [0.75, 1010, 0.48].

[0027] Preferably, the mathematical expression of the synchronized vital signs matrix includes: in, To synchronize the vital signs matrix, is the timestamp, Represented as the first aligned ECG sequence, Expressed as the second aligned PPG sequence, Expressed as the third aligned acceleration sequence, Expressed as X-axis motion acceleration, Expressed as the Y-axis motion acceleration, Expressed as Z-axis motion acceleration.

[0028] In one implementation of the embodiment of the present invention, assuming t=3.2s, is -0.35 (the original value is -0.4mV), is 850, is 920, , , They are 0.48g, -0.12g, and 1.05g respectively, so the SVM expression is [3200, -0.35, 850, 920, 0.48, -0.12, 1.05].

[0029] Preferably, step S3 includes the following steps: Step S31: performing a three-axis acceleration analysis based on the synchronized vital sign matrix and motion acceleration data, and calculating the motion divergence value; Step S32: selecting a processing channel based on the motion divergence value; when the motion divergence value is greater than a preset threshold, it is determined to be in a motion state and the first real-time filtering channel is activated; when the motion divergence value is less than or equal to the preset threshold, it is determined to be in a stationary state and the second real-time filtering channel is activated; Step S33: performing a filtering operation through the first real-time filtering channel or the second real-time filtering channel to obtain filtered data.

[0030] In the embodiment of the present invention, the sliding root mean square (RMS) of the acceleration vector modulus is calculated based on the three-axis acceleration data in the synchronized vital sign matrix as the exercise intensity index (window length 0.5 seconds), and the covariance between the electrocardiogram (ECG) sequence and the acceleration modulus is extracted to generate the motion divergence value. .Will and the preset threshold θ (θ=0.35), if >θ (judged to be in motion state), activate the first real-time filtering channel (using normalized least mean square adaptive filter, step size parameter 0.02, cutoff frequency 0.1-10 Hz), otherwise activate the second real-time filtering channel (static Butterworth low-pass filter, cutoff frequency 5 Hz); step S33 performs the filtering operation of the selected channel on the target physiological signal and outputs the noise-suppressed filtered data sequence.

[0031] Preferably, step S31 includes the following steps: Calculate the three-axis acceleration based on the synchronized vital sign matrix, and perform the variance mean within the time window to obtain the dynamic variance; Extract acceleration vectors from the synchronized vital sign matrix and calculate the Shannon entropy of the extracted acceleration vectors in the 0.5-10 Hz frequency band to obtain the spectral entropy value; The dynamic variance and spectral entropy values ​​are combined to obtain the motion divergence value.

[0032] The specific operation is as follows: Calculate the acceleration vector modulus using a sliding window (window length 0.5 seconds, step length 10ms) The mean of the variance of all Sample variance , and then take the arithmetic mean of the variance of 5 consecutive windows to get the dynamic variance ; Perform fast Fourier transform (FFT, sampling rate 100Hz) on the acceleration vector modulus of the same window, extract the spectrum energy distribution in the 0.5-10Hz band, and normalize the energy probability Substitute into the Shannon entropy formula Get the spectrum entropy value; the dynamic variance and spectral entropy Divide by the preset reference value (assuming Normalize and then perform weighted summation Generate motion divergence values .

[0033] In another implementation of the embodiment of the present invention, the weighted sum ratio is 7:3, which is determined based on conventional experience and can sometimes be further determined based on actual conditions.

[0034] Preferably, step S33 includes the following steps: Using motion acceleration data as a noise reference signal, the ECG waveform data is input into a first real-time filtering channel to perform reverse elimination of ECG waveform jitter and clutter to generate a first purified ECG signal; the capacitance product pulse wave data is input into the first real-time filtering channel to be decomposed into an AC component and a DC component, motion interference is suppressed on the AC component, and then component-recombined with the DC component to obtain a first purified pulse wave signal; Alternatively, a fixed frequency window filter is applied to the ECG waveform data input into the second real-time filtering channel, retaining the clinically effective band of 0.5-40 Hz, and directly outputting a second purified ECG signal; a smoothing filter is performed on the capacitance pulse wave data input into the second real-time filtering channel to generate a second purified pulse wave signal; The first cleaned ECG signal and the first cleaned pulse wave signal, or the second cleaned ECG signal and the second cleaned pulse wave signal are combined into filtered data.

[0035] In one implementation of the embodiment of the present invention, differential filtering is performed based on channel selection: if the first real-time filtering channel (motion state) is activated, then 1) Using the three-axis acceleration vector modulus (sampling rate 100 Hz) as the noise reference signal, the normalized least mean square (NLMS) adaptive filter (step size 0.02, order 32) is applied to the ECG sequence (normalized voltage sequence), and the motion artifacts are offset in real time by adjusting the filter weight to output the first purified ECG signal; 2) The sequence (light intensity unit) is band-pass filtered (0.5-8 Hz) to separate the alternating current (AC) component and the direct current (DC) component. The AC component is scaled by applying a motion suppression coefficient based on acceleration covariance (e.g., weight 0.85), and then recombined with the DC component to generate the first purified pulse wave signal (e.g., original PPG value 850 → AC=120 / DC=730 → AC=102 after suppression → recombined value 832); The reorganization formula is Of course, the weight formula is determined by conventional experience and can sometimes be further determined based on actual conditions.

[0036] If the second real-time filter channel is activated (static state), then 1) Directly perform a 5th-order Butterworth bandpass filter (0.5-40 Hz) on the ECG sequence to retain the clinical band and output the second purified ECG signal; 2) Yes The sequence (window length 15 points, polynomial order 3) is denoised to generate a second purified pulse wave signal; Finally, the ECG and pulse wave signals of the same channel are merged into filtered data according to the timestamp.

[0037] The specific operations are as follows: The input variables are: ECG sequence segment: [-0.35,-0.41,-0.38]; Sequence fragment: [850,845,848]; Reference noise: [0.87g, 0.89g, 0.85g]; The intermediate steps of the processing are: ECG output after NLMS filtering: [-0.32, -0.37, -0.35] (motion artifact suppression rate 18%); See also Figure 2, showing the filtering process of an ECG sequence. The red curve indicates an abnormal valley of -0.41 in the original ECG signal at t=3200ms (exceeding the static threshold of -0.35). After NLMS adaptive filtering, the red dashed filtered signal suppresses the valley to -0.32 (an improvement of 0.09 units). At t=3210ms, the original signal of -0.41 is filtered to -0.37. (Motion artifact suppression rate 18%). PPG decomposition: DC component = 830, AC component = [20, 15, 18]; After motor inhibition, AC = [17, 12.75, 15.3]; reconstructed PPG = [847, 842.75, 845.3].

[0038] See also Figure 3 The green dashed line represents the original PPG signal, and the green solid line represents the filtered data. The original PPG signal drops to 840 units at t=3210ms (a decrease of 5 units from the previous point). After AC / DC decomposition (DC component 830 units, AC component 15 units) and motion suppression (weight 0.85), the AC component is compressed to 12.75 units, resulting in a reconstructed output of 842.75 units (error <0.5%). The deviation between the filtered value of 845.3 and the original value of 848 at t=3220ms is due to dynamic acceleration covariance compensation (compensation coefficient 0.92). The resulting PPG sequence signal-to-noise ratio improves from 12dB to 28dB.

[0039] The output filtered data is: [t=3200ms:ECG=-0.32,PPG=847]; [t=3210ms:ECG=-0.37,PPG=842.75]; [t=3220ms:ECG=-0.35,PPG=845.3].

[0040] Preferably, step S4 includes the following steps: Step S41: constructing a risk change trajectory of the pathology trajectory on the filtered data and the historical case data to generate a vital sign risk trajectory, wherein the vital sign risk trajectory includes an electrocardiogram risk sub-trajectory and a blood flow risk sub-trajectory; Step S42: Performing an out-of-bounds judgment based on the ECG risk sub-trajectory and the blood flow risk sub-trajectory. When the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered to obtain vital sign alarm data. Step S43: trace the entire process based on the vital signs alarm data and mark the key nodes of the detector; generate a report using the key nodes of the detector to obtain a full-process report of the vital signs detector.

[0041] In an embodiment of the present invention, the Mahalanobis distance of the QRS complex slope change rate and ST segment offset is calculated by comparing the ECG signal in the filtered data with similar pathological ECG templates in a historical case library (such as ventricular premature beat exacerbation trajectories). The perfusion index is simultaneously extracted from the blood flow signal (PPG, light intensity sequence) and correlated with the historical low perfusion risk template to generate a blood flow risk sub-trajectory. Step S42 sets a dual threshold mechanism to trigger a clinical alarm and generate structured alarm data containing a timestamp, out-of-bounds type, and risk level.

[0042] Preferably, constructing a risk change trajectory of a pathology trajectory for the filtered data and the historical case data includes the following steps: Obtain historical case data; superimpose surface temperature data on the filtered data to generate a fused vital sign sequence; Extract ECG features and blood flow features based on the fused vital sign sequence; ECG feature sequence analysis is performed on the ECG features and historical case data, and a cardiovascular risk score is output. The cardiovascular risk score is subjected to a temporal analysis of cardiac electrical activity, and a risk change trajectory is constructed using the timestamp as the horizontal axis and the predicted value of the cardiovascular risk score as the vertical axis to obtain an ECG risk sub-trajectory. Blood flow characteristics and historical case data were combined for blood pressure analysis, and organ parameters SpO2-PWV were used to quantify the risk score of circulatory failure. The circulatory failure risk score was subjected to a time series analysis of the circulatory system, and a risk change trajectory was constructed with the timestamp as the horizontal axis and the predicted value of the circulatory failure risk score as the vertical axis to obtain the blood flow risk sub-trajectory.

[0043] In one implementation of the present invention, historical case data (including time series such as ECG waveforms, blood oxygen saturation, and pulse wave velocity for similar patients) is retrieved from a medical database. The filtered data (ECG and pulse wave signals) are aligned with surface temperature sensor data (sampling rate 1 Hz) using timestamps and linearly interpolated to a uniform frequency of 100 Hz to form a six-dimensional fused vital sign sequence [ECG, PPG, Temp]. ECG features are then extracted: QRS amplitude (mV), ST-segment slope (mV / s), RR interval coefficient of variation (%); and blood flow features: perfusion index (PI) (%), pulse wave rise time (ms), and SpO2 value (%). Risk score analysis is then performed on the real-time ECG features, and an ECG risk sub-trajectory is constructed with the timestamp as the horizontal axis and the 30-second sliding window mean as the vertical axis. The blood flow features are then combined with historical data to calculate the SpO2-PWV organ parameter.

[0044] The specific operations are as follows: 1) Assume the input data is: Filtered ECG signal: QRS amplitude = 1.1 mV, ST slope = 0.6 mV / s, RR interval variation = 12%; Filtered pulse wave: PI=1.2%, SpO2=96%; Body surface temperature: 36.8℃; Patient's basic data: blood pressure BP=120 / 80mmHg, age=65 years old.

[0045] 2) The cardiovascular risk score is: Risk score = 0.3×1.1+0.5×0.6+0.2×12=0.33+0.3+2.4=3.03 → Normalized to percentage: 3.03×20=60.6 points.

[0046] The circulatory failure risk score is: PWV=0.8× =0.8× 5≈0.8×9.01=7.21m / s (K=0.8) Decision tree judgment: PI=1.2%>1.0 (not triggering + points), PWV=7.21<10 (not triggering + points) → basic risk value 40 points.

[0047] 3) Assume that during the monitoring period from 115 seconds to 125 seconds, the ECG risk score shows a continuous upward trend (115 seconds: 58.2 points; 120 seconds: 60.6 points; 125 seconds: 62.1 points), and the blood flow risk score increases simultaneously (115 seconds: 38.5%; 120 seconds: 40.0%; 125 seconds: 41.2%). At 120 seconds, the ECG risk exceeds the preset threshold of 60 points for the first time.

[0048] Key points: An alarm is triggered when the ECG risk is >60 minutes or the blood flow risk is >45 minutes for five consecutive minutes. In this case, the ECG risk first exceeded the threshold (60.6>60) at 120 seconds, but did not continuously exceed the limit, so no alarm was triggered.

[0049] In another implementation of an embodiment of the present invention, the threshold is determined based on conventional experience. The present invention sets the threshold of the ECG risk value to 80 and the threshold of the blood flow risk value to 75. However, in this embodiment, the ECG risk is set to >60 points or the blood flow risk is set to >45. Sometimes, further determination can be made based on actual conditions.

[0050] Preferably, step S42 includes the following steps: Generate ECG risk values ​​and blood flow risk values ​​for the ECG risk sub-trajectory and the blood flow risk sub-trajectory respectively; When the ECG risk value is greater than 80% or the blood flow risk value is greater than 75%, it is determined to be the first out-of-bounds, and the first-level clinical alarm is activated, with local sound and light warnings; When the ECG risk value is greater than 80% and the blood flow risk value is greater than 75%, it is judged as the second out-of-limit. On the basis of activating the first-level clinical alarm, the second-level clinical alarm is triggered simultaneously, and a risk positioning report is pushed to the medical staff.

[0051] In one implementation of the embodiment of the present invention, the risk values ​​within a 30-second sliding window are calculated for each of the ECG risk sub-trajectory (time series) and the blood flow risk sub-trajectory (time series): Calculate the risk value within a 30-second sliding window for each ECG risk sub-trajectory (time series) and blood flow risk sub-trajectory (time series); the blood flow risk value = the maximum blood flow risk score within the window (e.g., [65, 72, 78, 70] → 78%). Then perform double out-of-bounds judgment: Level 1 alarm: If the ECG risk value is >80% or the blood flow risk value is >75% (e.g. ECG value 82>80), the local audio and visual alarm will be activated immediately (the device triggers a 5Hz beep + red LED flashes); Level 2 alarm: If the ECG risk value is >80% and the blood flow risk value is >75% (e.g. ECG value 82>80 and blood flow value 78>75), in addition to the audio and visual alarm, a JSON report containing key data (including the out-of-bounds timestamp, risk value, and original signal fragment) will be pushed to the medical end.

[0052] The specific operation is as follows, and the input data is: ECG risk sequence: [78,81,85,82,79]; blood flow risk sequence: [72,76,78,74,73]; Risk value calculation: ECG risk value = 90th percentile (after sorting [78, 79, 81, 82, 85] → the 5th value is 85); blood flow risk value = maximum value (78); Transcendental judgment: ECG risk value 85% > 80% → meets the first condition; Blood flow risk value 78% > 75% → meets the first condition; If both ECG>80% and blood flow>75% are met at the same time, the second level alarm is triggered.

[0053] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0054] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. An information interaction control method for a vital signs monitor, characterized in that: The following steps are involved: Step S1: synchronously collecting physiological signals through a sensor array, wherein the physiological signals include electrocardiogram waveform data, capacitance product pulse wave data, motion acceleration data and body surface temperature data; Step S2: Time-aligning the ECG waveform data, capacitance product pulse wave data, and motion acceleration data based on the clock synchronization protocol, and constructing a matrix to generate a synchronized vital sign matrix; Step S3: Calculating a motion divergence value based on the synchronized vital sign matrix and the motion acceleration data, selecting a processing channel based on the motion divergence value, and performing a filtering operation to obtain filtered data; Step S4: Execute the risk change trajectory of the pathology trajectory on the filtered data and the historical case data to generate the vital sign risk trajectory, and perform an out-of-bounds judgment on the vital sign risk trajectory; when the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered.

2. The information interaction control method of the vital signs monitor according to claim 1, characterized in that: Step S2 includes: Performing normalization processing on the ECG waveform data to extract a first synchronous time series; performing the same time calibration on the plethysmographic data to extract a second synchronized time series; Performing clock compensation on the original timestamp of the motion acceleration data to extract the third synchronous time series; The first synchronized time series, the second synchronized time series, and the third synchronized time series are subjected to the same interpolation resampling to generate a first aligned ECG sequence, a second aligned PPG sequence, and a third aligned acceleration sequence, respectively; The first aligned ECG sequence, the second aligned PPG sequence and the third aligned acceleration sequence are used to construct a synchronized vital sign matrix.

3. The information interaction control method of the vital signs monitor according to claim 2, characterized in that: The mathematical expression of the synchronized vital signs matrix includes: in, To synchronize the vital signs matrix, is the timestamp, Represented as the first aligned ECG sequence, Expressed as the second aligned PPG sequence, Expressed as the third aligned acceleration sequence, Expressed as X-axis motion acceleration, Expressed as the Y-axis motion acceleration, Expressed as Z-axis motion acceleration.

4. The information interaction control method of the vital signs monitor according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing a three-axis acceleration analysis based on the synchronized vital sign matrix and motion acceleration data, and calculating the motion divergence value; Step S32: selecting a processing channel based on the motion divergence value; when the motion divergence value is greater than a preset threshold, it is determined to be in a motion state and the first real-time filtering channel is activated; when the motion divergence value is less than or equal to the preset threshold, it is determined to be in a stationary state and the second real-time filtering channel is activated; Step S33: performing a filtering operation through the first real-time filtering channel or the second real-time filtering channel to obtain filtered data.

5. The information interaction control method of the vital signs monitor according to claim 4, characterized in that: Step S31 includes the following: Calculate the three-axis acceleration based on the synchronized vital sign matrix, and perform the variance mean within the time window to obtain the dynamic variance; Extract acceleration vectors from the synchronized vital sign matrix and calculate the Shannon entropy of the extracted acceleration vectors in the 0.5-10 Hz frequency band to obtain the spectral entropy value; The dynamic variance and spectral entropy values ​​are combined to obtain the motion divergence value.

6. The information interaction control method of the vital signs monitor according to claim 4, characterized in that: Step S33 is specifically as follows: Using motion acceleration data as a noise reference signal, the ECG waveform data is input into a first real-time filtering channel to perform reverse elimination of ECG waveform jitter and clutter to generate a first purified ECG signal; the capacitance product pulse wave data is input into the first real-time filtering channel to be decomposed into an AC component and a DC component, motion interference is suppressed on the AC component, and then component-recombined with the DC component to obtain a first purified pulse wave signal; Alternatively, a fixed frequency window filter is applied to the ECG waveform data input into the second real-time filtering channel, retaining the clinically effective band of 0.5-40 Hz, and directly outputting a second purified ECG signal; a smoothing filter is performed on the capacitance pulse wave data input into the second real-time filtering channel to generate a second purified pulse wave signal; The first cleaned ECG signal and the first cleaned pulse wave signal, or the second cleaned ECG signal and the second cleaned pulse wave signal are combined into filtered data.

7. The information interaction control method of the vital signs monitor according to claim 6, characterized in that: Step S4 includes the following: Step S41: constructing a risk change trajectory of the pathology trajectory on the filtered data and the historical case data to generate a vital sign risk trajectory, wherein the vital sign risk trajectory includes an electrocardiogram risk sub-trajectory and a blood flow risk sub-trajectory; Step S42: Performing an out-of-bounds judgment based on the ECG risk sub-trajectory and the blood flow risk sub-trajectory. When the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered to obtain vital sign alarm data. Step S43: trace the entire process based on the vital signs alarm data and mark the key nodes of the detector; generate a report using the key nodes of the detector to obtain a full-process report of the vital signs detector.

8. The information interaction control method of the vital signs monitor according to claim 7, characterized in that: The construction of the risk change trajectory of the pathology trajectory for the filtered data and historical case data includes the following steps: Obtain historical case data; superimpose surface temperature data on the filtered data to generate a fused vital sign sequence; Extract ECG features and blood flow features based on the fused vital sign sequence; ECG feature sequence analysis is performed on the ECG features and historical case data, and a cardiovascular risk score is output. The cardiovascular risk score is subjected to a temporal analysis of cardiac electrical activity, and a risk change trajectory is constructed using the timestamp as the horizontal axis and the predicted value of the cardiovascular risk score as the vertical axis to obtain an ECG risk sub-trajectory. Blood flow characteristics and historical case data were combined for blood pressure analysis, and organ parameters SpO2-PWV were used to quantify the risk score of circulatory failure. The circulatory failure risk score was subjected to a time series analysis of the circulatory system, and a risk change trajectory was constructed with the timestamp as the horizontal axis and the predicted value of the circulatory failure risk score as the vertical axis to obtain the blood flow risk sub-trajectory.

9. The information interaction control method of the vital signs monitor according to claim 7, characterized in that: Step S42 includes the following steps: Generate ECG risk values ​​and blood flow risk values ​​for the ECG risk sub-trajectory and the blood flow risk sub-trajectory respectively; When the ECG risk value is greater than 80% or the blood flow risk value is greater than 75%, it is determined to be the first out-of-bounds, and the first-level clinical alarm is activated, with local sound and light warnings; When the ECG risk value is greater than 80% and the blood flow risk value is greater than 75%, it is judged as the second out-of-limit. On the basis of activating the first-level clinical alarm, the second-level clinical alarm is triggered simultaneously, and a risk positioning report is pushed to the medical staff.

10. An information interaction control system for a vital signs monitor, characterized in that: The information interaction control method for executing the vital signs monitor according to claim 1 comprises: A multi-source synchronous acquisition module is used to synchronously acquire physiological signals through a sensor array, wherein the physiological signals include electrocardiogram waveform data, capacitance product pulse wave data, motion acceleration data and body surface temperature data; The timing alignment and feature matrix construction module is used to time-align ECG waveform data, capacitance product pulse wave data, and motion acceleration data based on the clock synchronization protocol, and to construct a matrix to generate a synchronized vital sign matrix; A motion interference perception and filtering channel selection module is used to calculate the motion divergence value based on the synchronized vital sign matrix and motion acceleration data, perform filtering operations, and select a processing channel based on the motion divergence value to obtain filtered data; The pathology evolution analysis and clinical early warning module is used to construct the risk change trajectory of the pathology trajectory based on the filtered data and historical case data, generate the vital sign risk trajectory, and make out-of-bounds judgments on the vital sign risk trajectory; when the vital sign risk trajectory exceeds the threshold, a clinical alarm is triggered.

Images