Intelligent diagnosis and treatment method and system based on individualized blood pressure management and storable medium

Abstract

The invention provides an intelligent diagnosis and treatment method, system and equipment based on individualized blood pressure management, a computer readable storage medium and application thereof, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring blood pressure, electroencephalogram signals, cerebral blood flow velocity and arterial blood pressure data of a subject; analyzing based on the electroencephalogram signal and cerebral blood flow velocity data of the subject to obtain a neurovascular coupling index; obtaining an individualized blood pressure range based on the nerve and blood vessel coupling index and the arterial blood pressure data of the subject; whether the blood pressure of the subject is within the individualized blood pressure range or not is judged, and when the blood pressure of the subject is not within the individualized blood pressure range, information prompt for blood pressure control is output. According to the method disclosed by the invention, the blood pressure management is guided by determining the individualized blood pressure range of the cardiovascular and cerebrovascular disease patient, valuable resources are provided for researchers and clinicians in the field of cardiovascular and cerebrovascular disease diagnosis and treatment, and the method has important scientific research significance and clinical value.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent medical treatment, and more specifically, relates to an intelligent diagnosis and treatment method, system, device, computer-readable storage medium and application thereof based on individualized blood pressure management. Background Art

[0002] The burden of cardiovascular and cerebrovascular diseases in my country is heavy, and hypertension is the most common risk factor among patients with cardiovascular and cerebrovascular diseases in my country. However, it is still unclear how the perioperative blood pressure of cardiovascular and cerebrovascular patients should be managed, especially for patients after acute ischemic stroke revascularization. Several randomized controlled trials have attempted to determine whether lower blood pressure target values ​​can further improve the prognosis of patients with cerebral infarction, but none of them have obtained positive results. Because there are obvious individual differences in stroke risk factors between different patients; and in the acute phase of cerebral infarction, neurometabolism, cerebrovascular reactivity, blood-brain barrier permeability, etc. are always in dynamic changes, so the management model of setting a "one size fits all" blood pressure target value may not be appropriate. Individualized and precise blood pressure management methods are an urgent need for the management of acute cerebral infarction.

[0003] Neurovascular coupling (NVC) refers to the ability of increased neuronal electrical activity to increase cerebral blood flow. Impaired NVC is involved in the development of a variety of neurological diseases, including cerebral infarction. The inventor's team found that the NVC function on the side of the narrowed intracranial large blood vessels is worse than that on the healthy side. The relatively intact NVC function reflects the relatively minimal structural damage to the neurovascular unit. Therefore, the longer the blood pressure is within the relatively intact range of NVC function, the more conducive it is to improving the patient's neurological function. How to determine the individualized blood pressure range that is most conducive to the recovery of neurological function through real-time monitoring and calculation of multiple physiological parameters is an urgent problem to be solved. Summary of the invention

[0004] This application targets patients with cardiovascular and cerebrovascular diseases, especially those in the acute stage after cerebral infarction and revascularization, and uses multi-parameter physiological function monitoring, phase-amplitude cross-frequency coupling, and Granger causality analysis to quantitatively evaluate resting-state NVC function, and determine the individualized blood pressure range based on this. It also verifies the advantages and mechanisms of individualized blood pressure management strategies over fixed target blood pressure management from the clinical, neuroimaging, and biomarker levels, laying the foundation for individualized treatment of patients with cardiovascular and cerebrovascular diseases, especially those in the acute stage after cerebral infarction and revascularization.

[0005] The first aspect of the present application discloses an intelligent diagnosis and treatment method based on individualized blood pressure management, the method comprising: S1: Obtain the blood pressure, EEG signal, cerebral blood flow velocity and arterial blood pressure data of the subjects; S2: The neurovascular coupling index is obtained based on the subjects' EEG signals and cerebral blood flow velocity data using phase-amplitude cross-frequency coupling and / or Granger causality analysis; S3: Obtain individualized blood pressure range based on the subject's neurovascular coupling index and arterial blood pressure data; S4: Determine whether the subject's blood pressure is within the individualized blood pressure range, and when the subject's blood pressure is not within the individualized blood pressure range, output a message prompting for blood pressure control.

[0006] Furthermore, the phase-amplitude cross-frequency coupling is used to describe the relationship between the phase of the low-frequency component in the cerebral blood flow velocity waveform and the amplitude modulation of the high-frequency component of the EEG signal; Preferably, the relationship of the amplitude modulation is quantified by a modulation coefficient, and the step of calculating the modulation coefficient comprises: S21: selecting low-frequency components in the cerebral blood flow velocity waveform and high-frequency components of the electroencephalogram signal to obtain a filtered cerebral blood flow velocity and a filtered electroencephalogram signal; Preferably, the low-frequency component in the cerebral blood flow velocity waveform is 0-0.10 Hz, and the high-frequency component of the EEG signal is 13-30 Hz; S22: performing Hilbert transform based on the filtered cerebral blood flow velocity and the filtered electroencephalogram signal to obtain a phase sequence of the cerebral blood flow velocity and an amplitude sequence of the electroencephalogram signal; S23: constructing a first composite complex-valued signal based on the phase sequence of the cerebral blood flow velocity and the amplitude sequence of the electroencephalogram signal; S24: introducing a random time delay into the first composite complex-valued signal to obtain a second composite complex-valued signal with a random shift in the amplitude sequence; S25: Calculate the modulation coefficient as the normalized difference between the first composite complex-valued signal and the second composite complex-valued signal.

[0007] Furthermore, the Granger causality analysis obtains a Granger causality index reflecting the change in cerebral blood flow velocity caused by the EEG signal; the calculation steps of the Granger causality index include: S26: Establishing the first autoregressive model for describing the self-relationship of cerebral blood flow velocity; S27: Establish a second autoregressive model to describe the changes in cerebral blood flow velocity caused by changes in EEG signals; S28: The F-test is used to compare the goodness of fit of the first autoregressive model and the second autoregressive model. The calculated F value is the Granger causality index.

[0008] Further, the first autoregressive model is:

[0009] Among them, CBFV is cerebral blood flow velocity, m is the model order, a i is the first parameter, ε t is the residual of the first autoregressive model; Optionally, the second autoregressive model is:

[0010] Among them, CBFV is cerebral blood flow velocity, EEG is EEG signal, m is model order, ai is the first parameter, bi is the second parameter, ε' t is the residual of the second autoregressive model; Optionally, the calculation formula of the F value is:

[0011] Among them, RSSx is the residual sum of squares of the first autoregressive model, RSS'x is the residual sum of squares of the second autoregressive model, m is the model order, and T is the number of observations of the second autoregressive model.

[0012] Further, the step of obtaining an individualized blood pressure range based on the subject's neurovascular coupling index and arterial blood pressure data includes: S31: Divide a fixed time period into one window, calculate the average value of the modulation coefficient of each conduction of the EEG signal in each window and / or the average value of the Granger causality index, the average value of the modulation coefficient of each conduction of the EEG signal is the first neural coupling index, the average value of the Granger causality index is the second neural coupling index, and calculate the average blood pressure corresponding to each window; Preferably, the fixed time period is 300 seconds; S32: moving one window at every fixed time interval, and recalculating the first neural coupling index, the second neural coupling index and the corresponding average blood pressure; Preferably, the fixed time interval is 10 seconds; S33: Plotting the first neural coupling index, the second neural coupling index and the corresponding average blood pressure obtained during the whole monitoring process, with the average blood pressure as the x-axis and the first neural coupling index and / or the second neural coupling index as the y-axis, fitting a quadratic function curve to obtain a neural coupling index-average blood pressure curve; S34: The average value of the ordinate of the top of the neural coupling index-mean blood pressure curve of all subjects included in the cohort study was used as the first cut-off point for diagnosing impaired neurovascular coupling; Preferably, the average value of the ordinate of the apex of the neural coupling index-mean blood pressure curve of the subjects who developed large-area cerebral infarction and / or symptomatic hemorrhagic transformation after vascular recanalization treatment is selected as the second cut-off point for diagnosing impaired neurovascular coupling; S35: Determine the two intersection points corresponding to the vertical coordinates of the neural coupling index-average blood pressure curve of S33 and the first cut point or the second cut point of S34. The average blood pressure range corresponding to these two intersection points is the individualized blood pressure range of the subject.

[0013] Furthermore, the method further comprises: S36: Calculate the duration of the subject's blood pressure being higher and / or lower than the individualized blood pressure range within a fixed period of time after vascular recanalization treatment, and statistically analyze the correlation between the duration and the classic neurovascular coupling function evaluation to determine the neuroprotective effect of the individualized blood pressure range; Optionally, the method further includes S37: calculating the correlation between the duration and the subject's oxidative stress level and blood-brain barrier permeability, and determining the neuroprotective effect of individualized blood pressure management.

[0014] Furthermore, the method further comprises: S38: Set a fixed target blood pressure range, calculate the duration of blood pressure above and / or below the individualized blood pressure range within a fixed period of time after vascular recanalization treatment, and the duration of blood pressure above and / or below the fixed target blood pressure range, compare the correlation between the two types of duration and neurological function and imaging outcomes, and determine the advantages of individualized blood pressure management over fixed target blood pressure; Preferably, the fixed target blood pressure range is 120-140 mmHg; Preferably, the neurological function and imaging outcomes include any one or more of the following: functional independence, ischemic stroke tissue volume progression, and symptomatic hemorrhagic transformation.

[0015] The second aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call program instructions, and when the program instructions are executed, it is used to execute the method steps disclosed in the first aspect above.

[0016] The third aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method steps disclosed in the first aspect are implemented.

[0017] The fourth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the method disclosed in the first aspect when executed by a processor.

[0018] This application has the following beneficial effects: 1. The method disclosed in this application avoids the defect of "one-size-fits-all" management of patients with fixed blood pressure target values. By integrating three physiological monitoring data, namely EEG signals, cerebral blood flow velocity and arterial blood pressure, the resting NVC function is quantitatively evaluated and the individualized optimal blood pressure range is determined to guide blood pressure management.

[0019] 2. The method disclosed in the present application utilizes phase-amplitude cross-frequency coupling and / or Granger causality analysis to evaluate the relationship between EEG signals and cerebral blood flow velocity, and quantifies the degree of neurovascular coupling through modulation coefficient and Granger causality index, thereby achieving theoretical innovation in the definition of neurovascular coupling index. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the 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 work.

[0021] Figure 1 It is a flowchart of an intelligent diagnosis and treatment method based on individualized blood pressure management provided by the first aspect of an embodiment of the present invention; Figure 2 is a schematic diagram of an intelligent diagnosis and treatment system based on individualized blood pressure management provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention; Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention; Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention; Figure 6 is a schematic diagram of individualized blood pressure based on resting neurovascular coupling monitoring provided by an embodiment of the present invention, Figure 6 (a) The index reflecting the neurovascular coupling function is recorded as NVCx, and the NVCx-BP curve is drawn. The abscissa of the curve vertex is the blood pressure when the coupling function is optimal; Figure 6 (b) in the figure assumes that NVCx is always impaired in patients with large-area cerebral infarction or symptomatic hemorrhagic transformation regardless of blood pressure changes. The ordinate of the vertex of the NVCx-BP curve (red) of these two types of patients is used as the diagnostic cut-off point (NVCx') indicating impaired NVC function. For other patients with cerebral infarction, the optimal blood pressure range (green) is between y=NVCx' and the intersection of the curve. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0023] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 creative work are within the scope of protection of the present invention.

[0025] Figure 1 An intelligent diagnosis and treatment method based on individualized blood pressure management is provided in an embodiment of the present invention, and the method comprises: S1: Obtain the blood pressure, EEG signal, cerebral blood flow velocity and arterial blood pressure data of the subjects; In one embodiment, the inclusion criteria for subjects include: 1) Age 18-80 years old, regardless of gender; 2) Acute ischemic stroke confirmed by CT or MRI; 3) Receiving intravenous thrombolysis and / or endovascular treatment, with blood flow in the responsible artery reaching mTICI 2b-3 level; 4) Being able to start multimodal monitoring within 4 hours after vascular recanalization; 5) mRS score ≤ 2 points before the onset of the disease; 6) The responsible vessel is the M1 segment of the middle cerebral artery or the internal carotid artery on the unilateral side.

[0026] In one embodiment, the exclusion criteria for subjects include: 1) Hemorrhagic stroke confirmed by CT or MRI before the start of multimodal monitoring; 2) Cerebrovascular malformation, intracranial tumor, brain abscess or other major non-vascular brain disease (such as multiple sclerosis) diagnosed by clear imaging evidence; 3) Stroke caused by arteritis, migraine, vasospasm, drug abuse or neurological genetic disease (such as mitochondrial encephalomyopathy, CADASIL); 4) Poor temporal window sound transmission, unable to complete TCD cerebral blood flow monitoring; 5) Unable to cooperate with monitoring and follow-up due to impaired consciousness, delirium, mental disorder, cognitive impairment; 6) Upper limb artery stenosis, occlusion, dissection, arteriovenous fistula, making radial artery pressure measurement unreliable; 7) Severe heart failure (NYHA grade III-IV), or left ventricular ejection fraction <35%, or in the past 3 8) Patients diagnosed with acute coronary syndrome within 1 month; 9) Patients with previous or current aortic dissection; 10) Patients with frequent premature ventricular beats or other malignant arrhythmias; 11) Patients who are pregnant or planning to become pregnant; 12) Failure to obtain informed consent from the subjects.

[0027] In one embodiment, the baseline characteristics of the subjects are collected, including: age, gender, stroke risk factors (hypertension, diabetes, coronary heart disease, hyperlipidemia, atrial fibrillation, smoking history, drinking history), etiology classification of the current cerebral infarction, NIHSS score, responsible vessel, mTICI classification after vascular recanalization, time from onset to recanalization, time from recanalization to start of multimodal monitoring, blood pressure, heart rate, blood sugar, serum total protein, albumin, total cholesterol, low-density lipoprotein, high-density lipoprotein, homocysteine, glycosylated hemoglobin on admission, arterial blood pH, CO2 partial pressure, O2 partial pressure, HCO3 - concentration, serum estradiol, and progesterone levels.

[0028] In one embodiment, multimodal monitoring is used to obtain the subject's EEG signal, cerebral blood flow velocity and arterial blood pressure data. The multimodal monitoring includes: ① Monitoring preparation All tests were conducted in a quiet, constant temperature (20-24°C) ward with curtains to block light. The subjects were in a supine position and were monitored while awake and with their eyes closed.

[0029] ② CBFV The DWL dual-channel transcranial Doppler diagnostic instrument (Compumedics DWL, Germany) was used to monitor cerebral blood flow. Two 2MHz probes were placed on the bilateral temporal windows, fixed with a head frame, and the bilateral middle cerebral arteries were detected, with a sampling depth of 40-60mm and a sampling volume of 8-10mm.

[0030] ③ EEG Before placing the electrodes, the subjects were required to wash their hair or clean their scalp with alcohol or scrub to make the impedance between the electrodes and the scalp 0.1-5.0 kΩ. Silver / silver chloride disc electrodes were used, and 19-conductor electrodes were placed according to the international 10-20 system. Nicolet EEG monitoring system (Natus, USA) was used to collect EEG and EKG simultaneously.

[0031] ④ ABP After enrollment, the patients first measured the brachial artery cuff pressure on both sides, measured 3 times on each side and took the average value. If the systolic pressure on both sides differed by more than 20 mmHg, the side with higher pressure was selected to monitor the beat-to-beat arterial pressure (ABP). Using Arrow Arterial Catheterization Kit (Teleflex, USA), puncture was performed at the most obvious part of the radial artery pulsation close to the wrist crease, the guide wire was exchanged, and the arterial pressure tube was inserted. The high-pressure heparin lactate sodium Ringer's solution and disposable pressure sensor were connected, and connected to Mindray BeneVision N17 monitor (Mindray, Shenzhen). After zeroing, the three-way of the arterial pressure tube was opened to display the arterial pressure waveform.

[0032] ⑤ Signal acquisition and storage CBFV, EEG, and signals were collected synchronously, and the multi-mode monitoring signals were input into the Nicolet EEG V44 amplifier (Natus, USA) with a sampling rate of 512Hz. After the signal stabilized, the CBFV+EEG+ABP monitoring time was no less than 4 hours; ABP monitoring was performed until 24 hours after vascular recanalization. The multi-mode monitoring signals were stored in edf format using NicoletOne Monitor 5.94 software (Natus, USA), saved in a dedicated mobile hard disk, and backed up regularly.

[0033] S2: The neurovascular coupling index is obtained based on the subjects' EEG signals and cerebral blood flow velocity data using phase-amplitude cross-frequency coupling and / or Granger causality analysis; The phase-amplitude cross-frequency coupling is used to describe the relationship between the phase of the low-frequency component in the cerebral blood flow velocity waveform and the amplitude modulation of the high-frequency component of the EEG signal; The relationship of the amplitude modulation is quantified by a modulation coefficient, and the steps of calculating the modulation coefficient include: S21: selecting low-frequency components in the cerebral blood flow velocity waveform and high-frequency components of the electroencephalogram signal to obtain a filtered cerebral blood flow velocity and a filtered electroencephalogram signal; In one embodiment, the low-frequency component in the cerebral blood flow velocity waveform is 0-0.10 Hz, and the high-frequency component of the EEG signal is 13-30 Hz; S22: performing Hilbert transform based on the filtered cerebral blood flow velocity and the filtered electroencephalogram signal to obtain a phase sequence of the cerebral blood flow velocity and an amplitude sequence of the electroencephalogram signal; S23: constructing a first composite complex-valued signal based on the phase sequence of the cerebral blood flow velocity and the amplitude sequence of the electroencephalogram signal; S24: introducing a random time delay into the first composite complex-valued signal to obtain a second composite complex-valued signal with a random shift in the amplitude sequence; S25: Calculate the modulation coefficient as the normalized difference between the first composite complex-valued signal and the second composite complex-valued signal.

[0034] In a specific embodiment, the phase-amplitude cross-frequency coupling (PAC) analysis step includes: S201: Signal preprocessing The CBFV signal was filtered with a bandpass of 0.0055-0.10 Hz (Chebyshev Type II filter). The EEG signal was filtered with a notch filter to remove linear noise and a bandpass filter of 0.5-70 Hz. Independent component analysis (ICA) was used to remove electrooculographic and electrocardiographic artifacts.

[0035] S202: Calculate PAC modulation index (MI) PAC is used to describe the relationship between the phase of the low-frequency component (0-0.10Hz) in the CBFV waveform and the amplitude modulation of the high-frequency component (13-30Hz) of the EEG. After filtering the CBFV and EEG according to the above frequency bands, the phase sequence of CBFV(t) and the amplitude sequence of EEG(t) AEEG(t) are extracted through Hilbert transform, and a composite complex-valued signal is constructed:

[0036] The mean value of z(t) is denoted as Mreal.

[0037] In order to obtain the distribution without coupling relationship between AEEG and φCBFV, a composite signal with random displacement of amplitude sequence relative to the corresponding phase sequence is constructed, that is, a random time delay τ is introduced to construct a composite complex valued signal The mean of z(t, τ) is denoted by μ and the standard deviation is denoted by σ.

[0038]

[0039] Then the normalized difference between z(t) and z(t, τ) is the modulation coefficient MI: The Granger causality analysis obtains a Granger causality index reflecting the change in cerebral blood flow velocity caused by the EEG signal; the calculation steps of the Granger causality index include:

[0040] S26: Establishing the first autoregressive model for describing the self-relationship of cerebral blood flow velocity; The first autoregressive model is:

[0041] S27: Establish a second autoregressive model to describe the changes in cerebral blood flow velocity caused by changes in EEG signals; The second autoregressive model is:

[0042] Among them, CBFV is cerebral blood flow velocity, EEG is EEG signal, m is model order, ai is the first parameter, bi is the second parameter, ε' t is the residual of the second autoregressive model; The calculation formula of F value is:

[0043] Among them, RSSx is the residual sum of squares of the first autoregressive model, RSS'x is the residual sum of squares of the second autoregressive model, m is the model order, and T is the number of observations of the second autoregressive model.

[0044] S28: The F-test is used to compare the goodness of fit of the first autoregressive model and the second autoregressive model. The calculated F value is the Granger causality index.

[0045] In a specific embodiment, the Granger causality (GC) analysis step includes: S203: Signal preprocessing All missing channels or obvious EMG or EGO artifacts were deleted. Data for each EEG and CBFV channel were normalized by subtracting the mean of the channel and dividing by the standard deviation. CBFV signals were bandpass filtered with a frequency of 0.0055–0.4 Hz (Chebyshev Type II filter). EEG signals were notched to remove linear noise and bandpass filtered with a frequency of 0.5–70 Hz. Unit root Augmented Dickey–Fuller tests were used to test the stationarity of EEG and CBFV sequences.

[0046] S204: EEG signal instantaneous amplitude calculation Hilbert transform is used to extract the instantaneous amplitude of the five frequency bands of EEG signals [δ (0.5-4Hz), θ (4-7Hz), α (7-13Hz), β (13-30Hz), γ (30-45Hz)]. Let vt represent the EEG channel, and its complex form Vt (Formula 1) is defined as:

[0047] The virtual signal The Hilbert transform of vt is obtained (Formula 2):

[0048] Where PV is the Cauchy principal value. At any given time point, the instantaneous amplitude At of the EEG signal vt can be calculated as the analytical amplitude of the complex vector Vt, that is (Formula 3):

[0049] S205: Determination of Granger Causality Index (GI) between EEG and CBFV Because EEG causes changes in CBFV, two autoregressive models are assumed: Formula 4 Formula 5 Where m is the model order, ai and bi are parameters, εt and represents the model residual. The statistical significance of the F-test used to compare the goodness of fit of each model can be used to estimate the strength of the Granger causal relationship between CBFV and EEG. At this time, the F-statistic is (Formula 6):

[0050] Where RSSX and RSS'X are the residual sums of squares of the models in equations (4) and (5), respectively, and T is the number of observations used to estimate the binary model in equation (5). The F-statistic approximately follows an F distribution with m degrees of freedom and (T-2m-1) under the null hypothesis. Using the Bayesian information criterion, the optimal order m with a maximum order of m=15 is selected (without downsampling). The F-value calculated according to equation (6) is the Granger causality index (GI) reflecting the causal relationship between EEG→CBFV.

[0051] In summary, the calculation method of neurovascular coupling index (NVCx) is achieved through phase-amplitude cross-frequency coupling (PAC) and Granger causality (GC).

[0052] S3: Individualized blood pressure ranges are obtained based on the subject's neurovascular coupling index and arterial blood pressure data, including: S31: Divide a fixed time period into one window, calculate the average value of the modulation coefficient of each conduction of the EEG signal in each window and / or the average value of the Granger causality index, the average value of the modulation coefficient of each conduction of the EEG signal is the first neural coupling index, the average value of the Granger causality index is the second neural coupling index, and calculate the average blood pressure corresponding to each window; In one embodiment, the fixed time period is 300 seconds; S32: moving one window at every fixed time interval, and recalculating the first neural coupling index, the second neural coupling index and the corresponding average blood pressure; In one embodiment, the fixed time interval is 10 seconds; S33: Plotting the first neural coupling index, the second neural coupling index and the corresponding average blood pressure obtained during the whole monitoring process, with the average blood pressure as the x-axis and the first neural coupling index and / or the second neural coupling index as the y-axis, fitting a quadratic function curve to obtain a neural coupling index-average blood pressure curve; S34: The average value of the ordinate of the top of the neural coupling index-mean blood pressure curve of all subjects included in the cohort study was used as the first cut-off point for diagnosing impaired neurovascular coupling; In one embodiment, the average value of the ordinate of the apex of the neural coupling index-mean blood pressure curve of the subjects who developed large-area cerebral infarction and / or symptomatic hemorrhagic transformation after vascular recanalization treatment is selected as the second cut-off point for diagnosing impaired neurovascular coupling; S35: Determine the two intersection points corresponding to the vertical coordinates of the neural coupling index-average blood pressure curve of S33 and the first cut point or the second cut point of S34. The average blood pressure range corresponding to these two intersection points is the individualized blood pressure range of the subject.

[0053] In a specific embodiment, the individualized blood pressure range is determined based on the phase-amplitude cross-frequency coupling and Granger causality, with 300 seconds as one segment (epoch), and the MI and GI of each EEG lead are calculated and averaged, which is equivalent to obtaining NVCx (respectively denoted as NVCx1 and NVCx2) within a window with a width of 300 seconds, and at the same time calculating the average BP (mean blood pressure, MAP) within the window range. NVCx and the corresponding MAP are calculated every 10 seconds when the window moves. The MAP is grouped into groups of 5 mmHg, and the NVCx obtained from a full-length monitoring and the paired MAP group are plotted to obtain the NVCx-MAP curve, which is shown as follows: Figure 6 As shown, a quadratic function curve is fitted, and the MAP corresponding to the vertex of the curve is the optimal MAP.

[0054] All patients who developed large-area cerebral infarction (defined as infarction area ≥ 2 / 3 of the middle cerebral artery basin on one side) or symptomatic hemorrhagic transformation (defined as hematoma with space-occupying effect, combined with impaired consciousness or NIHSS increase of ≥ 4 points) 24 hours after vascular recanalization were selected, and the average vertical coordinate of the apex of the NVCx-MAP curve of these patients was calculated as the cut-off point for diagnosing NVC damage to obtain the individualized optimal MAP range. The above calculation process was implemented using Matlab 2019b software (Mathwork, USA).

[0055] The correlation between the individualized optimal blood pressure ranges obtained according to NVCx1 and NVCx2 and clinical and imaging outcomes was compared to determine the optimal NVC algorithm.

[0056] S4: Determine whether the subject's blood pressure is within the individualized blood pressure range, and when the subject's blood pressure is not within the individualized blood pressure range, output a message prompting for blood pressure control.

[0057] S36: Calculate the duration of time that the subject's blood pressure is higher and / or lower than the individualized blood pressure range within a fixed period of time after vascular recanalization treatment, statistically analyze the correlation between the duration and the classic neurovascular coupling function evaluation, and determine the neuroprotective effect of the individualized blood pressure range.

[0058] In some embodiments, the method further comprises S37: calculating the correlation between the duration and the subject's oxidative stress level and blood-brain barrier permeability, and determining the neuroprotective effect of individualized blood pressure management.

[0059] The classical neurovascular coupling function evaluation is to evaluate the blood flow response of the posterior cerebral artery to visual stimulation. The test is always performed in a dark room. The classical neurovascular coupling function evaluation includes: ① Place two 2MHz TCD probes on the bilateral temporal windows, fix the head frame, and detect the bilateral posterior cerebral arteries with a sampling depth of 65mm and a sampling volume of 8-10mm.

[0060] ② Place a 15-inch monitor 50 cm in front of the subject. The baseline test lasts 2 minutes, and observe the black cross (about 1.5 cm in height and width) in the center of the dark gray background of the monitor.

[0061] ③ After the baseline test, 10 cycles of visual stimulation were given, each cycle lasting 40 seconds. Each cycle consisted of 20 seconds of black and white checkerboard flickering stimulation (ON) and 20 seconds of rest period of the above baseline pattern (OFF).

[0062] ④ The percentage of increased flow velocity in the bilateral posterior cerebral arteries during the stimulation period was calculated compared with the baseline test.

[0063] The oxidative stress level was determined by measuring urinary 8-OHdG. The urine of the subjects was collected 24 hours after cerebral infarction reperfusion and stored at -20°C. The urinary 8-OHdG level was analyzed using an ELISA detection kit (Shanghai Bioengineering).

[0064] The blood-brain barrier permeability imaging and determination comprises: Quantitative dynamic contrast-enhanced imaging (DCE-MRI): (multi-flip angle T1 mask) TR 2472ms, TE 1196ms, layer thickness 5mm, matrix 160×128, flip angles: 3°, 6°, 9°, 12°, 15°; (T1-weighted DCE) flip angle 15°, other parameters are the same as multi-flip angle T1 mask, single scan time 6s, a total of 40 phases, dynamic enhancement scanning time 240s, after the second dynamic enhancement phase of dynamic enhancement scanning, a high-pressure syringe was used to synchronously inject a low molecular weight gadolinium diamide contrast agent Omniscan (GE Company, USA) intravenously, the injection rate was 2ml / s, the dose was 0.1mmol / kg, and 15ml of normal saline was injected at the same rate to flush the catheter.

[0065] A circular region of interest (ROI) with an area of ​​20-40 mm2 was drawn in the center of the superior sagittal sinus to obtain the time-concentration curve. With reference to T1WI, T2WI, and ADC, a circular ROI with an area of ​​20-60 mm2 was manually drawn in the area of ​​the maximum enhancement of the infarct on the T1-weighted DCE image, avoiding softening lesions, cystic changes, hemorrhage, and normal blood vessels as much as possible. The same ROI was drawn on the permeability parameter and T1 perfusion parameter functional color map, and the Extended Tofts Linear two-chamber model was used to fit and calculate the DCE-MRI vascular permeability parameters: transport constant (Ktrans) and partial extracellular extravascular space volume (ve). The higher the Ktrans and ve, the higher the vascular permeability.

[0066] S38: Set a fixed target blood pressure range, calculate the duration of blood pressure above and / or below the individualized blood pressure range within a fixed period of time after vascular recanalization treatment, and the duration of blood pressure above and / or below the fixed target blood pressure range, compare the correlation between the two types of duration and neurological function and imaging outcomes, and determine the advantages of individualized blood pressure management over fixed target blood pressure; In one embodiment, the fixed target blood pressure range is 120-140 mmHg; In one embodiment, the neurological function and imaging outcomes include any one or more of the following: functional independence, ischemic stroke tissue volume progression, and symptomatic hemorrhagic transformation.

[0067] In a specific embodiment, clinical outcomes include: ① Main outcome: Functional independence on the 90th day after onset: modified Rankin Scale (mRS) score of 0-2 points, including completely asymptomatic; or symptoms but no obvious functional impairment, able to complete daily life; or mild disability, no need for assistance, and able to take care of oneself.

[0068] ② Secondary outcomes: Classical NVC evaluation 24 h after recanalization treatment: changes in flow velocity in the posterior cerebral artery induced by visual stimulation.

[0069] Oxidative stress level 24 h after recanalization treatment: urine 8-hydroxy-2'-deoxyguanosine (8-OHdG, oxidative stress biomarker) concentration.

[0070] Blood-brain barrier permeability 24 h after recanalization therapy: transport constant (Ktrans) and fractional extracellular extravascular space volume (ve) measured by DCE-MRI.

[0071] The infarct volume was larger on day 7 after recanalization than that on day 24 after recanalization.

[0072] Symptomatic hemorrhagic transformation (defined as hematoma with mass effect, combined with impaired consciousness or an increase in NIHSS score of ≥4 points) within 7 days after recanalization therapy.

[0073] Figure 2 An intelligent diagnosis and treatment system based on individualized blood pressure management is provided in an embodiment of the present invention, and the system comprises: 101 acquisition unit: used for acquiring blood pressure, electroencephalogram signal, cerebral blood flow velocity and arterial blood pressure data of the subject; 102 Neurovascular coupling index calculation unit: used to obtain the neurovascular coupling index based on the subject's EEG signal and cerebral blood flow velocity data by using phase-amplitude cross-frequency coupling and Granger causality analysis; 103 Individualized blood pressure range calculation unit: used for obtaining an individualized blood pressure range based on the subject's neurovascular coupling index and arterial blood pressure data; 104 Intelligent diagnosis and treatment unit: used to determine whether the blood pressure of the subject is within the individualized blood pressure range, and when the blood pressure of the subject is not within the individualized blood pressure range, output a message prompting blood pressure control.

[0074] In some embodiments, the information prompt is an auxiliary prediction result. The auxiliary prediction result output according to the information prompt includes but is not limited to a paper or electronic report form. The result is only obtained by the intelligent machine based on the relevant data of the subject, and is only used as a reference for medical staff, and is not the final diagnosis result of the subject.

[0075] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may include: one or more processors, and one or more memories; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, the method described above may be executed.

[0076] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, operations and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can be an X86 architecture or an ARM architecture.

[0077] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0078] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as ROM 3030 or hard disk 3070, may store various data or files used for processing and / or communication of the method provided by the present disclosure and program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0079] The embodiment of the present invention also provides a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium provided by an embodiment of the present invention, and a computer readable instruction 4010 is stored on the computer storage medium 4020. When the computer readable instruction 4010 is executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0080] The embodiments of the present disclosure further provide a computer program product or system, including a computer program, which implements the steps of the above method when executed by a processor.

[0081] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0082] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0083] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0084] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0087] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. An intelligent diagnosis and treatment method based on individualized blood pressure management, characterized in that: The method comprises: S1: Obtain the blood pressure, EEG signal, cerebral blood flow velocity and arterial blood pressure data of the subjects; S2: The neurovascular coupling index is obtained based on the subjects' EEG signals and cerebral blood flow velocity data using phase-amplitude cross-frequency coupling and / or Granger causality analysis; S3: Obtain individualized blood pressure range based on the subject's neurovascular coupling index and arterial blood pressure data; S4: Determine whether the subject's blood pressure is within the individualized blood pressure range, and when the subject's blood pressure is not within the individualized blood pressure range, output a message prompting for blood pressure control.

2. The intelligent diagnosis and treatment method based on individualized blood pressure management according to claim 1, characterized in that: The phase-amplitude cross-frequency coupling is used to describe the relationship between the phase of the low-frequency component in the cerebral blood flow velocity waveform and the amplitude modulation of the high-frequency component of the EEG signal; Preferably, the relationship of the amplitude modulation is quantified by a modulation coefficient, and the step of calculating the modulation coefficient comprises: S21: selecting low-frequency components in the cerebral blood flow velocity waveform and high-frequency components of the electroencephalogram signal to obtain a filtered cerebral blood flow velocity and a filtered electroencephalogram signal; Preferably, the low-frequency component in the cerebral blood flow velocity waveform is 0-0.10 Hz, and the high-frequency component of the EEG signal is 13-30 Hz; S22: performing Hilbert transform based on the filtered cerebral blood flow velocity and the filtered electroencephalogram signal to obtain a phase sequence of the cerebral blood flow velocity and an amplitude sequence of the electroencephalogram signal; S23: constructing a first composite complex-valued signal based on the phase sequence of the cerebral blood flow velocity and the amplitude sequence of the electroencephalogram signal; S24: introducing a random time delay into the first composite complex-valued signal to obtain a second composite complex-valued signal with a random shift in the amplitude sequence; S25: Calculate the modulation coefficient as the normalized difference between the first composite complex-valued signal and the second composite complex-valued signal.

3. The intelligent diagnosis and treatment method based on individualized blood pressure management according to claim 1, characterized in that: The Granger causality analysis obtains a Granger causality index reflecting the change in cerebral blood flow velocity caused by the EEG signal; the calculation steps of the Granger causality index include: S26: Establishing the first autoregressive model for describing the self-relationship of cerebral blood flow velocity; S27: Establish a second autoregressive model to describe the changes in cerebral blood flow velocity caused by changes in EEG signals; S28: The F-test is used to compare the goodness of fit of the first autoregressive model and the second autoregressive model. The calculated F value is the Granger causality index.

4. The intelligent diagnosis and treatment method based on individualized blood pressure management according to claim 3, characterized in that: The first autoregressive model is: Among them, CBFV is the cerebral blood flow velocity, m is the model order, a i is the first parameter, ε t is the residual of the first autoregressive model; Optionally, the second autoregressive model is: Among them, CBFV is cerebral blood flow velocity, EEG is electroencephalogram signal, m is model order, a i is the first parameter, b i is the second parameter, ε' t is the residual of the second autoregressive model; Optionally, the calculation formula of the F value is: Among them, RSSx is the residual sum of squares of the first autoregressive model, RSS'x is the residual sum of squares of the second autoregressive model, m is the model order, and T is the number of observations of the second autoregressive model.

5. The intelligent diagnosis and treatment method based on individualized blood pressure management according to claim 1, characterized in that: The steps for obtaining an individualized blood pressure range based on the subject's neurovascular coupling index and arterial blood pressure data include: S31: Divide a fixed time period into one window, calculate the average value of the modulation coefficient of each conduction of the EEG signal in each window and / or the average value of the Granger causality index, the average value of the modulation coefficient of each conduction of the EEG signal is the first neural coupling index, the average value of the Granger causality index is the second neural coupling index, and calculate the average blood pressure corresponding to each window; Preferably, the fixed time period is 300 seconds; S32: moving one window at every fixed time interval, and recalculating the first neural coupling index, the second neural coupling index and the corresponding average blood pressure; Preferably, the fixed time interval is 10 seconds; S33: Plotting the first neural coupling index, the second neural coupling index and the corresponding average blood pressure obtained during the whole monitoring process, with the average blood pressure as the x-axis and the first neural coupling index and / or the second neural coupling index as the y-axis, fitting a quadratic function curve to obtain a neural coupling index-average blood pressure curve; S34: The average value of the ordinate of the top of the neural coupling index-mean blood pressure curve of all subjects included in the cohort study was used as the first cut-off point for diagnosing impaired neurovascular coupling; Preferably, the average value of the ordinate of the apex of the neural coupling index-mean blood pressure curve of the subjects who developed large-area cerebral infarction and / or symptomatic hemorrhagic transformation after vascular recanalization treatment is selected as the second cut-off point for diagnosing impaired neurovascular coupling; S35: Determine the two intersection points corresponding to the vertical coordinates of the neural coupling index-average blood pressure curve of S33 and the first or second cut-off point of S34. The average blood pressure range corresponding to the two intersection points is the individualized blood pressure range of the subject.

6. The intelligent diagnosis and treatment method based on individualized blood pressure management according to claim 5, characterized in that: The method further comprises: S36: Calculate the duration of the subject's blood pressure being higher and / or lower than the individualized blood pressure range within a fixed period of time after vascular recanalization treatment, and statistically analyze the correlation between the duration and the classic neurovascular coupling function evaluation to determine the neuroprotective effect of the individualized blood pressure range; Optionally, the method further includes S37: calculating the correlation between the duration and the subject's oxidative stress level and blood-brain barrier permeability, and determining the neuroprotective effect of individualized blood pressure management.

7. The intelligent diagnosis and treatment method based on individualized blood pressure management according to claim 1, characterized in that: The method further comprises: S38: Set a fixed target blood pressure range, calculate the duration of blood pressure above and / or below the individualized blood pressure range within a fixed period of time after vascular recanalization treatment, and the duration of blood pressure above and / or below the fixed target blood pressure range, compare the correlation between the two types of duration and neurological function and imaging outcomes, and determine the advantages of individualized blood pressure management over fixed target blood pressure; Preferably, the fixed target blood pressure range is 120-140 mmHg; Preferably, the neurological function and imaging outcomes include any one or more of the following: functional independence, ischemic stroke tissue volume progression, and symptomatic hemorrhagic transformation.

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store program instructions; the processor is used to call program instructions, and when the program instructions are executed, it is used to execute the steps of the method described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images