An intelligent early warning system for autonomous discrimination of vasospasm from obstruction

Abstract

This invention relates to an intelligent early warning system for autonomously differentiating between vasospasm and obstruction, belonging to the field of postoperative monitoring technology in microsurgery. Existing monitoring methods rely on manual observation or intermittent equipment detection, resulting in poor continuity and accuracy. Furthermore, the mismatch between rigid sensors and microvascular mechanics can easily cause secondary damage, leading to blind spots in postoperative monitoring. This invention employs an ultra-soft, self-powered conformal bioelectronic interface that adheres to the outer wall of the microartery, converting the kinetic energy of the vessel wall into a voltage signal based on the energy-as-information paradigm. The signal conversion is enhanced through a composite layer design with nanotextures and high porosity. A dual-channel intelligent diagnostic framework, synergistically combining a morphology-driven shape spasm index and a physically driven obstruction index, distinguishes between vasospasm and mechanical obstruction. Closed-loop monitoring is achieved by combining wireless transmission and a graded early warning terminal. This invention avoids damage to the vascular endothelium from rigid sensors, improves the ability to respond to weak signals and enhances monitoring accuracy, provides interpretable diagnostic evidence, and strengthens the targeting of clinical interventions.

Description

Technical Field

[0001] This invention belongs to the field of postoperative monitoring technology in microsurgery, and relates to an intelligent early warning system for autonomously differentiating between vasospasm and obstruction. Background Technology

[0002] Microsurgical reconstruction techniques, such as finger replantation and free flap transplantation, rely heavily on maintaining the patency of microvessels. Postoperative vascular crisis caused by vasospasm and obstruction is a major cause of graft ischemia and necrosis and surgical failure. Clinical data shows that the first 48 hours postoperatively are a critical window for rescue, requiring intervention before irreversible vascular damage occurs. However, current clinical monitoring methods have significant limitations: manual observation by medical staff relies on subjective experience and has poor timeliness; traditional equipment such as laser speckle contrast imaging (LSCI), Doppler ultrasound, and near-infrared spectroscopy (NIRS) are intermittent, dependent on operator skills, and unable to perform continuous in-situ monitoring, making it difficult to capture the dynamic evolution of rapid vascular occlusion and creating blind spots in postoperative monitoring.

[0003] To achieve continuous in-situ monitoring, implantable bioelectronics has become a cutting-edge field, but it still faces multiple technical bottlenecks. First, traditional rigid sensors have Young's modulus on the order of gigapascals, which is severely mismatched with the mechanical properties of soft biological tissue, which are on the order of kilopascals. When encapsulating microarteries, they are prone to stress concentration, leading to endothelial damage and secondary thrombosis. Second, existing flexible sensing technologies struggle to balance miniaturization and high sensitivity. Microarteries with a diameter of about 1 mm have large curvature and small pulsation amplitude, making it difficult to effectively capture weak hemodynamic signals. Third, self-powered technologies mostly rely on the pulsation of large blood vessels or skeletal muscle movement for energy supply, while the mechanical energy conversion efficiency of small blood vessels is low, which cannot meet the needs of long-term continuous monitoring.

[0004] To address the aforementioned shortcomings, there is an urgent need for a monitoring and method that combines ultra-soft conformal characteristics, high sensitivity, and intelligent diagnostic capabilities to overcome the bottleneck in monitoring vascular crises after microsurgery and improve the success rate of rescue. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide an intelligent early warning system for autonomously identifying vascular spasm and obstruction.

[0006] To achieve the above objectives, the present invention provides the following technical solution: An intelligent early warning system for autonomously differentiating between vasospasm and obstruction includes an ultra-soft self-powered conformal bioelectronic interface, a signal processing module, a dual-channel intelligent diagnostic module, and a visualization terminal; The ultra-soft, self-powered, conformal bioelectronic interface is conformally wrapped around the outer wall of the microartery and configured to convert the kinetic and potential energy of the vessel wall into voltage signals. The signal processing module is electrically connected to the ultra-soft self-powered conformal bioelectronic interface and is configured to preprocess the voltage signal; The dual-channel intelligent diagnostic module is communicatively connected to the signal processing module and is configured to calculate the shape spasm index and obstruction index based on the voltage signal to distinguish between vasospasm and mechanical obstruction. The visualization terminal is wirelessly connected to the dual-channel intelligent diagnostic module and is configured to display real-time diagnostic results and early warning status.

[0007] Furthermore, the ultra-soft self-powered conformal bioelectronic interface comprises, from bottom to top, a bottom encapsulation layer, a first stretchable gold nanowire electrode layer, a polydimethylsiloxane nanowire triboelectric layer, an electrospun polyvinylidene fluoride and gold nanowire composite layer, a second stretchable gold nanowire electrode layer, and a top encapsulation layer. The triboelectric layer of polydimethylsiloxane nanowires has a nanotextured surface, and the electrospun polyvinylidene fluoride and gold nanowire composite layer has a high porosity structure. The total thickness of the ultra-soft, self-powered, conformal bioelectronic interface is less than 130 μm, and its Young's modulus is matched with that of the microartery to achieve mechanical stealth.

[0008] Furthermore, the ultra-soft self-powered conformal bioelectronic interface operates based on the contact-separation mode of a triboelectric nanogenerator, and its open-circuit output voltage... Satisfy the following formula:

[0009] in, express t Open-circuit output voltage at any given time This represents the triboelectric charge density on the surface of polydimethylsiloxane nanowires. express t The instantaneous effective equivalent displacement between the triboelectric nanowire array and the counter electrode caused by the constant pulsation of blood vessels. It represents the vacuum permittivity.

[0010] Furthermore, the dual-channel intelligent diagnostic module is configured to perform the following steps: The pulse wave area (PWA) is calculated as the time integral of the voltage signal over one cardiac cycle. The PWA represents the total biomechanical energy transferred from the vessel wall to the sensor. The PWA is monotonically calibrated with the vessel wall kinetic energy / downstream perfusion, and is therefore used as an energy proxy indicator. The obstruction index is calculated based on the pulse wave area, and mechanical obstruction is determined when the pulse wave area drops to a preset energy threshold. The waveform distortion features during vasospasm were located using occlusion sensitivity thermography, including sharpening of the contraction peak and disappearance of the diabetic wave notch. The shape spasm index is calculated based on the waveform distortion characteristics to quantify the degree of vasospasm.

[0011] Furthermore, the dual-channel intelligent diagnostic module adopts a spatiotemporal deep learning architecture, which includes a one-dimensional convolutional neural network layer and a bidirectional long short-term memory network layer. The one-dimensional convolutional neural network layer is configured to extract local spatial features of the voltage signal, and the bidirectional long short-term memory network layer is configured to capture the temporal dependence of the pulse wave. The dual-channel intelligent diagnostic module has a significant ability to distinguish between three states: normal, vasospasm, and mechanical obstruction.

[0012] Furthermore, the visualization terminal is a custom-developed smartphone application configured to display warning status via hierarchical identifiers: The first identifier indicates a normal state, the second identifier indicates a vasospasm warning state, and the third identifier indicates a mechanical obstruction critical state; the visualization terminal is also configured to display an occlusion heat map of the shape spasm index and a physical diagnostic card of the obstruction index.

[0013] An intelligent early warning method for autonomously differentiating between vasospasm and obstruction includes the following steps: Voltage signals of vascular pulsation are acquired through an ultra-soft bioelectronic interface conformally wrapped around the outer wall of microarteries; The voltage signal is preprocessed to remove baseline drift and motion artifacts; the pulse wave area of ​​the voltage signal is calculated as an energy, i.e., information index. The morphological and energy characteristics of the voltage signal are analyzed simultaneously using a dual-channel intelligent diagnostic framework. The morphological characteristics are used to calculate the shape spasm index, and the energy characteristics are used to calculate the obstruction index. Based on the shape spasm index and obstruction index, the probability of vascular status is output, and the warning information is displayed through a visualization terminal.

[0014] Furthermore, the step of calculating the pulse wave area includes: Identify the start and end points of a single cardiac cycle; perform time integration on the absolute value of the voltage signal within that cycle; and establish a linear mapping relationship between the pulse wave area and the tissue blood perfusion level.

[0015] Furthermore, the dual-channel intelligent diagnostic framework adopts a dual-rate preprocessing strategy to align high-frequency morphological data and low-frequency wireless monitoring data into a multi-channel feature tensor. The dual-channel intelligent diagnostic framework has a lower false negative rate than a preset threshold for detecting mechanical obstruction.

[0016] Furthermore, the preprocessing steps include filtering and analog-to-digital conversion; the warning information displayed on the visualization terminal includes real-time probability curves and physical diagnostic criteria.

[0017] The beneficial effects of this invention are as follows: (1) This invention effectively solves several technical problems in microvascular monitoring after microsurgery. First, by constructing an ultra-soft, self-powered conformal bioelectronic interface, mechanical matching between the device and microvessels is achieved. This interface has extremely low bending stiffness and ultra-thin characteristics, which can seamlessly fit the outer wall of a microartery with a diameter of about 1 mm. While ensuring stable contact, it does not generate additional mechanical constraints, fundamentally avoiding the risk of endothelial damage caused by sensor rigidity, and significantly improving implantation biocompatibility. Based on the biomechanical paradigm of energy as information, this invention establishes a deterministic correlation between physical signals and tissue perfusion. By introducing the pulse wave area as a quantitative indicator, it not only overcomes the limitation of traditional strain sensors that only rely on instantaneous amplitude, but also achieves precise mapping of hemodynamic energy at the physical level, enabling the system to maintain high-reliability monitoring capabilities even under extreme conditions of weak vascular pulsation or severe signal attenuation.

[0018] (2) The pioneering dual-channel intelligent diagnostic framework, through the coordinated morphology-driven shape spasm index and the physical-driven obstruction index, enables the system to decouple and analyze vascular crises from two orthogonal dimensions: waveform distortion and energy loss. This multi-dimensional diagnostic logic not only accurately distinguishes between two crises with distinctly different pathological characteristics—intrinsic vascular spasm and extrinsic mechanical obstruction—but also provides visualized physical diagnostic evidence, greatly enhancing the credibility and interpretability of clinical decisions. By integrating wireless transmission and a graded early warning terminal, a complete closed loop from in-situ microartery sensing to bedside clinical intervention is constructed. The system can automatically filter motion artifacts and physiological noise, output vascular status probabilities in real time, and transform complex hemodynamic data into intuitive early warning information, effectively eliminating postoperative monitoring blind spots and saving valuable golden rescue time for medical staff.

[0019] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0020] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein: Figure 1 Motivations and application scenarios for clinical research; Figure 2 For structural form and material properties; Figure 3 For layered disassembly Figure 2 The structure showcases the multi-layered structural morphology and material properties; Figure 4 To match the effect image; Figure 5 This is a schematic diagram of the working principle; Figure 6 For integrated analysis system diagram; Figure 7 It is a visual interface. Detailed Implementation

[0021] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0022] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0023] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0024] Figure 1Motivation and application scenarios for clinical research. Reconstructed micro-arteries (such as in finger replantation and flap transplantation surgery) are often deeply buried under thick layers of tissue, and vascular spasm or obstruction cannot be seen with the naked eye, creating a diagnostic blind spot.

[0025] Figure 2 This section describes the structural morphology and material properties. The layered disassembly diagram shows the multi-layered structure, which includes a triboelectric layer of polydimethylsiloxane nanowires, an electrospun polyvinylidene fluoride nanofiber layer, and stretchable gold nanowire electrodes, all encapsulated within an ultra-soft polyurethane interlayer.

[0026] Figure 3 For structural form and material properties. Layered dissection. Figure 2 The structure exhibits a multi-layered design, including a triboelectric layer of polydimethylsiloxane nanowires, an electrospun polyvinylidene fluoride nanofiber layer, and a stretchable gold nanowire electrode, all encapsulated within an ultra-soft polyurethane interlayer.

[0027] Figure 4 The illustration shows the effect of fitting the device. It also includes a schematic diagram and actual photos of the ultra-soft, ultra-thin sensing interface seamlessly wrapping around a tiny artery approximately 1 mm in diameter.

[0028] Figure 5 This is a diagram illustrating the working principle. It utilizes the interarterial gap changes during arterial contraction and relaxation to achieve the conversion of biomechanical signals into electrical signals.

[0029] Figure 6 This is a diagram of the integrated analysis system. In the diagnostic process, the raw hemodynamic signals are processed by the intelligent analysis system to determine the probability of occurrence of three states: normal blood vessel, spasm, and blockage.

[0030] Figure 7 It features a visual interface. Real-time test results are presented on a customized mobile operating interface, outputting intuitive clinical early warning information (green: normal status; yellow: risk warning; red: crisis status).

[0031] Example 1: Fabrication and System Integration of an Ultra-Soft Self-Powered Conformal Bioelectronic Interface Preparation process: 1. Preparation of triboelectric layer of polydimethylsiloxane nanowires: Polydimethylsiloxane precursor (Dow Corning Sylgard 184) and curing agent were mixed at a mass ratio of 10:1 and degassed under vacuum for 1.8 × 10⁻⁶ mm. 3 s. Spin-coated onto a silicon mold (8.33 r / s) to form 2.0 × 10 -5 m thick film, cured at 333K for 7.2×10 3 s. Sputtering 1.0 × 10 -8 Using a gold layer as an etching mask, a 5.0 × 10⁻⁶ m layer was prepared by inductively coupled plasma reactive ion etching. -6m-long nanowire array, etching parameters: power 4.0 × 10⁻⁶ 2 W, bias voltage 1.0 × 10 2 V, pressure 1.5 Pa, gas composition is argon (1.5 × 10⁻⁶). -5 m 3 / s), oxygen (1.0×10 -5 m 3 / s) and carbon tetrafluoride (3.0×10 -5 m 3 / s).

[0032] 2. Preparation of electrospun polyvinylidene fluoride-gold nanowire composite layer: Polyvinylidene fluoride powder (molecular weight 3.0 × 10⁻⁶) was used to prepare the composite layer. 5 Da) is soluble in a mixed solvent of N,N-dimethylformamide and acetone in a volume ratio of 3:2 (concentration 1.2 × 10⁻⁶). 2 kg / m 3 ), magnetic stirring 2.16×10 4 s. Electrospinning parameters: receiving distance 1.5×10 -1 m, voltage 1.8×10 4 V, propulsion speed 1.0 × 10 -11 m 3 / s, roller speed 5.0×10 1 r / s to obtain oriented fibers. Additionally, polyvinylpyrrolidone nanofibers (concentration 8.0 × 10 kg / m²) were used. 3 As a sacrificial template, it sputters 5.0 × 10 -8 After the gold layer is applied, the template is dissolved in deionized water to obtain a stretchable gold nanowire network, which is then hot-pressed and integrated with the polyvinylidene fluoride layer.

[0033] 3. Package integration: using 1.0×10 -5 A five-layer conformal encapsulation of a 5.0×10⁻⁶ m thick biocompatible polyurethane elastomer is performed, with the structure consisting of: a bottom encapsulation layer (polyurethane), a first stretchable gold nanowire electrode layer (5.0×10⁻⁶ m thick), and the following layers: a bottom encapsulation layer (polyurethane), a first stretchable gold nanowire electrode layer (5.0×10⁻⁶ m thick), and a second layer -8 m), polydimethylsiloxane nanowire triboelectric layer (thickness 2.0 × 10 m) -5 m), electrospun polyvinylidene fluoride and gold nanowire composite layer (thickness 1.5×10 m). -5 m), second stretchable gold nanowire electrode layer (thickness 5.0 × 10 m), -8 m), top encapsulation layer (polyurethane). Total thickness 1.25 × 10 -4 m, equivalent Young's modulus 2.0 × 10 5 Pa, with a diameter of 1.0 × 10 -3 m-microarterial biomechanical matching.

[0034] System Integration: The ultra-soft, self-powered, conformal bioelectronic interface connects to the signal processing module via a low-power Bluetooth module (Bluetooth 5.0 protocol). The signal chain includes: a 16-bit analog-to-digital converter (sampling rate 1.0 × 10³ Hz) → a 0.5-10 Hz bandpass filter → wavelet transform denoising (db4 wavelet, 5-level decomposition). The dual-channel intelligent diagnostic module is deployed on an embedded processor (ARM Cortex-A72 architecture), using a runtime deep learning architecture: a one-dimensional convolutional neural network layer (6.4 × 10³ Hz). 1 Spatial features are extracted using convolutional kernels (size 3, stride 1), and bidirectional long short-term memory network layers (1.28×10⁻⁶). 2 (Hidden unit) captures temporal dependencies. The visualization terminal is an Android 11 smartphone application that displays three levels of warning status (normal, spasm warning, obstruction emergency) and physical diagnostic evidence.

[0035] Example 2: Implementation Process of Intelligent Early Warning Method Workflow: 1. Signal Acquisition and Preprocessing: The interface conformally wraps around the microartery, and the open-circuit voltage is output based on the contact-separation mode of the triboelectric nanogenerator. ,in Triboelectric charge density on the surface of polydimethylsiloxane nanowires (unit: C / m) 2 ), The instantaneous effective equivalent contact-separation displacement (in meters) between the triboelectric nanowire array and the counter electrode at time t due to vascular pulsation. The vacuum permittivity is 8.85 × 10⁻⁶. -12 F / m). After the signal is bandpass filtered from 0.5 to 10 Hz, the start and end points of the cardiac cycle (t1, t2) are identified using an adaptive thresholding method (the adaptive threshold is set to 30% of the peak amplitude detected in the current sliding window).

[0036] 2. Energy characteristic calculation: The pulse wave area is obtained by integrating the absolute value of the voltage in a single cycle. (unit: A linear mapping was established between the perfusion value and the perfusion value obtained from laser speckle contrast imaging (LSCI). The calibration relationship was obtained through fitting in vivo stepwise compression experiments (see Example 3). Mechanical obstruction was defined as a decrease in PWA to 20% of baseline, and the obstruction index was defined as... .

[0037] 3. Morphological feature calculation: Occlusion sensitivity heatmap is used to locate waveform distortion: when the half-peak width of the systolic peak is reduced by ≥30% and the amplitude of the dicrotic notch is <10% of the systolic peak, it is determined to be vasospasm. The Shape Spasm Index (SSI) is calculated as the ratio of the duration of the distorted region to the total cycle.

[0038] 4. Dual-channel diagnostics: Dual-rate preprocessing will convert 1.0×10 3 The Hz high-frequency data and 5.0×10Hz wireless data are aligned to form a 100Hz dual-channel tensor (dimensions: [number of samples, time step, 2]). A one-dimensional convolutional neural network extracts local features, and a bidirectional long short-term memory network analyzes temporal evolution, outputting three types of state probabilities. The preset false negative rate for mechanical obstruction detection is ≤5%.

[0039] 5. Early warning feedback: The smartphone application dynamically displays: a PWA decrease of >80% triggers an obstruction crisis (red interface), and an SSI >0.4 triggers a spasm warning (yellow interface). Simultaneously, a heat map and physical diagnostic card (including the percentage decrease in PWA and energy loss threshold) are pushed.

[0040] Example 3: In-vivo verification and performance testing This embodiment combines Embodiment 1 and Embodiment 2 to verify the overall system performance using a rabbit ear central artery model.

[0041] Experimental setup: Six male New Zealand white rabbits (weighing 2.5–3.0 kg) were anesthetized by inhalation of isoflurane (2–3% concentration) to surgically expose the marginal auricular artery (1.0 × 10 mm in diameter). -3 The sensor wraps around the outer wall of the artery and is simultaneously operated with LSCI (exposure time 1.0 × 10 m). -2 (s, frame rate 1.0×10fps) to monitor downstream irrigation.

[0042] Test process: 1. Simulation of mechanical obstruction: A precision micromanipulator applies 0-2.0 × 10 4 Pa progressive compression (step size 2.0 × 10) 3 Pa). The amplitude of the sensor output waveform decreases with increasing pressure. When the PWA decreases by 82%, an obstruction emergency warning is triggered, which is synchronized with the LSCI perfusion value decreasing by 85%.

[0043] 2. Induction of vasospasm: Local infusion of norepinephrine (concentration 1.0 × 10⁻⁶). -3 g / mL, volume 5.0 × 10 -8 (m³). The half-peak width of the waveform contraction peak decreased by 42%, the dicrotic wave notch disappeared, and the SSI rose to 0.47, triggering a spasm warning, which was consistent with the results of arteriography.

[0044] 3. Long-term stability test: Continuous monitoring at 4.5 × 10 3 The system achieved a 100% detection rate for mechanical obstruction, an 81.2% accuracy rate for vasospasm identification, and an overall accuracy rate of 90.71%. The signal quality index module effectively filtered out respiratory drift (0.2~0.5Hz) and motion artifacts.

[0045] Biocompatibility verification: According to ISO 10993-5 standard, L929 cells and material extracts were co-incubated for 8.64 × 10⁻⁶ days. -4 Cell viability was >95% as determined by the MTT assay, confirming no cytotoxicity.

[0046] Technical effectiveness verification: Mechanical stealth capability: 1.25×10 -4 The ultra-thin design makes the sensor's bending stiffness negligible, and arterial pulsation is unrestricted (radial deformation amplitude 1.0 × 10⁻⁶). -4 m (no attenuation).

[0047] Energy conversion efficiency: The nanotexture and high porosity structure enable a sensitivity of 9.5 mV / mmHg (≈1.27 V / kPa) and a system detection limit of 0.787~135 Pa.

[0048] Diagnostic interpretability: The SSI thermogram clearly marks the waveform distortion area (such as the disappearance of notches), and the BI physical card quantifies the energy loss (such as a decrease of 82% in PWA).

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent early warning system for autonomously differentiating between vasospasm and obstruction, characterized in that: It includes an ultra-soft, self-powered, conformal bioelectronic interface, a signal processing module, a dual-channel intelligent diagnostic module, and a visualization terminal; The ultra-soft, self-powered, conformal bioelectronic interface is conformally wrapped around the outer wall of the microartery and configured to convert the kinetic and potential energy of the vessel wall into voltage signals. The signal processing module is electrically connected to the ultra-soft self-powered conformal bioelectronic interface and is configured to preprocess the voltage signal; The dual-channel intelligent diagnostic module is communicatively connected to the signal processing module and is configured to calculate the shape spasm index and obstruction index based on the voltage signal to distinguish between vasospasm and mechanical obstruction. The visualization terminal is wirelessly connected to the dual-channel intelligent diagnostic module and is configured to display real-time diagnostic results and early warning status.

2. The intelligent early warning system for autonomously differentiating between vasospasm and obstruction according to claim 1, characterized in that: The ultra-soft self-powered conformal bioelectronic interface comprises, from bottom to top, a bottom encapsulation layer, a first stretchable gold nanowire electrode layer, a polydimethylsiloxane nanowire triboelectric layer, an electrospun polyvinylidene fluoride and gold nanowire composite layer, a second stretchable gold nanowire electrode layer, and a top encapsulation layer. The triboelectric layer of polydimethylsiloxane nanowires has a nanotextured surface, and the electrospun polyvinylidene fluoride and gold nanowire composite layer has a high porosity structure. The total thickness of the ultra-soft, self-powered, conformal bioelectronic interface is less than 130 μm, and its Young's modulus is matched with that of the microartery to achieve mechanical stealth.

3. The intelligent early warning system for autonomously identifying vasospasm and obstruction according to claim 2, characterized in that: The ultra-soft, self-powered, conformal bioelectronic interface operates based on the contact-separation mode of a triboelectric nanogenerator, and its open-circuit output voltage... Satisfy the following formula: in, express t Open-circuit output voltage at any given time This represents the triboelectric charge density on the surface of polydimethylsiloxane nanowires. express t The instantaneous effective equivalent displacement between the triboelectric nanowire array and the counter electrode caused by the constant pulsation of blood vessels. It represents the vacuum permittivity.

4. The intelligent early warning system for autonomously differentiating between vasospasm and obstruction according to claim 1, characterized in that: The dual-channel intelligent diagnostic module is configured to perform the following steps: The time integral of the voltage signal over one cardiac cycle is calculated as the pulse wave area, which represents the total biomechanical energy transferred from the blood vessel wall to the sensor. The obstruction index is calculated based on the pulse wave area, and mechanical obstruction is determined when the pulse wave area drops to a preset energy threshold. The waveform distortion features during vasospasm were located using occlusion sensitivity thermography, including sharpening of the contraction peak and disappearance of the diabetic wave notch. The shape spasm index is calculated based on the waveform distortion characteristics to quantify the degree of vasospasm.

5. The intelligent early warning system for autonomously differentiating between vasospasm and obstruction according to claim 4, characterized in that: The dual-channel intelligent diagnostic module adopts a spatiotemporal deep learning architecture, which includes a one-dimensional convolutional neural network layer and a bidirectional long short-term memory network layer. The one-dimensional convolutional neural network layer is configured to extract local spatial features of the voltage signal, and the bidirectional long short-term memory network layer is configured to capture the temporal dependence of the pulse wave. The dual-channel intelligent diagnostic module has a significant ability to distinguish between three states: normal, vasospasm, and mechanical obstruction.

6. The intelligent early warning system for autonomously differentiating between vasospasm and obstruction according to claim 1, characterized in that: The visualization terminal is a custom-developed smartphone application configured to display warning status via hierarchical identifiers: The first identifier indicates a normal state, the second identifier indicates a vasospasm warning state, and the third identifier indicates a mechanical obstruction critical state; the visualization terminal is also configured to display an occlusion heat map of the shape spasm index and a physical diagnostic card of the obstruction index.

7. An intelligent early warning method for autonomously differentiating between vasospasm and obstruction, characterized in that: Includes the following steps: Voltage signals of vascular pulsation are acquired through an ultra-soft bioelectronic interface conformally wrapped around the outer wall of microarteries; The voltage signal is preprocessed to remove baseline drift and motion artifacts; the pulse wave area of ​​the voltage signal is calculated as an energy, i.e., information index. The morphological and energy characteristics of the voltage signal are analyzed simultaneously using a dual-channel intelligent diagnostic framework. The morphological characteristics are used to calculate the shape spasm index, and the energy characteristics are used to calculate the obstruction index. Based on the shape spasm index and obstruction index, the probability of vascular status is output, and the warning information is displayed through a visualization terminal.

8. The intelligent early warning method for autonomously differentiating between vasospasm and obstruction according to claim 7, characterized in that: The steps for calculating the pulse wave area include: Identify the start and end points of a single cardiac cycle; perform time integration on the absolute value of the voltage signal within that cycle; and establish a linear mapping relationship between the pulse wave area and the tissue blood perfusion level.

9. The intelligent early warning method for autonomously differentiating between vasospasm and obstruction according to claim 7, characterized in that: The dual-channel intelligent diagnostic framework adopts a dual-rate preprocessing strategy to align high-frequency morphological data and low-frequency wireless monitoring data into a multi-channel feature tensor. The dual-channel intelligent diagnostic framework has a lower false negative rate than a preset threshold for detecting mechanical obstruction.

10. The intelligent early warning method for autonomously differentiating between vasospasm and obstruction according to claim 7, characterized in that: The preprocessing steps include filtering and analog-to-digital conversion; the warning information displayed on the visualization terminal includes real-time probability curves and physical diagnostic criteria.

Images