An early determination method of infusion extravasation and related equipment

Abstract

The application discloses a kind of early determination methods and related equipment of infusion extravasation, the method constructs local space temperature gradient distribution around infusion puncture point, and establishes the space temperature distribution model that can update with time with puncture point as center, time series analysis is carried out to the space temperature distribution model in preset time window, and characteristic parameters such as temperature gradient change quantity and abnormal temperature region space diffusion rate are extracted.By comparing the characteristic parameters with preset determination threshold, and combining duration condition, early risk state of infusion extravasation is determined and early warning signal is output.The application realizes early, continuous and objective identification of infusion extravasation risk by jointly analyzing the space distribution characteristics and time evolution law of skin temperature, does not depend on patient complaint or artificial patrol, and can effectively reduce false alarm rate.

Description

Technical Field

[0001] This specification relates to the field of medical safety monitoring technology, and more specifically, this application relates to an early detection method and related equipment for intravenous extravasation. Background Technology

[0002] Intravenous infusion is one of the most commonly used treatment methods in clinical practice. However, extravasation remains a high-risk complication that is difficult to detect in a timely manner. This is especially true in patients under general anesthesia, those with impaired consciousness, the elderly, and children, as they are unable to complain of discomfort, making the risk of extravasation more easily overlooked. In critically ill patients with coagulation disorders or significant local edema, increased vascular permeability makes leakage at the puncture site more likely. Furthermore, infusion puncture sites are often obscured by surgical drapes, blankets, or fixation devices, making it difficult for nursing staff to visually detect abnormalities in a timely manner.

[0003] When extravasation occurs during the infusion of irritating drugs such as vasoactive drugs, chemotherapy drugs, hypertonic solutions, or contrast agents, it may cause serious complications such as tissue necrosis and compartment syndrome in a short period of time, resulting in irreversible medical damage.

[0004] In related technologies, extravasation detection mainly relies on manual rounds, patient complaints, or visual observation, which has a significant time lag and is insufficient to meet the clinical need for early risk warning. While some solutions use single-point temperature sensors for monitoring, they only reflect local instantaneous temperature changes and cannot describe the spatial diffusion characteristics of extravasated fluid in subcutaneous tissue. Furthermore, they are susceptible to environmental and individual differences, resulting in a high false alarm rate. Other solutions based on near-infrared or bioelectrical impedance analysis are complex and costly, making them difficult to implement in routine clinical settings.

[0005] Therefore, there is an urgent need for a method based on quantifiable physiological parameters that can identify the risk of extravasation during infusion in an early, continuous, and objective manner in order to improve the safety of infusion therapy. Summary of the Invention

[0006] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0007] Firstly, this application proposes a method for early detection of intravenous extravasation, including: A local spatial temperature gradient distribution is formed within a pre-defined monitoring area around the infusion puncture site; Centered on the above-mentioned infusion puncture point, a spatial temperature distribution model is constructed based on the above-mentioned local spatial temperature gradient distribution, and the above-mentioned spatial temperature distribution model is updated at multiple consecutive time points to obtain the spatial changes of abnormal temperature areas within the above-mentioned monitoring area. Within a preset time window, a time series analysis is performed on the above spatial temperature distribution model to extract characteristic parameters including at least the temperature gradient change between the puncture point center and the surrounding area, as well as the spatial diffusion rate of the abnormal temperature area. The above-mentioned characteristic parameters are compared with preset judgment thresholds. When at least one of the above-mentioned characteristic parameters meets the abnormal judgment condition and continues to exceed the preset time threshold, it is judged as an early risk state of infusion extravasation, and an early warning signal is output.

[0008] In one feasible implementation, the formation of a local spatial temperature gradient distribution within the preset monitoring area around the infusion puncture site includes: Skin temperature data were acquired at multiple locations within a pre-defined monitoring area around the infusion puncture site; The skin temperature at the location corresponding to the above-mentioned infusion puncture point is used as the reference temperature; The temperature difference between the above-mentioned reference temperature and the skin temperature at multiple differential locations in the surrounding area is calculated to form a local spatial temperature gradient distribution.

[0009] In one feasible implementation, the characteristic is that, The aforementioned differential positions are distributed circumferentially or radially along the aforementioned infusion puncture point, and the distance between the aforementioned differential positions and the aforementioned infusion puncture point is within a preset range.

[0010] In one feasible implementation, the characteristic is that, The above-mentioned anomaly determination conditions include the above-mentioned temperature gradient change continuing or increasing over multiple consecutive monitoring periods, or the above-mentioned spatial diffusion rate continuing or increasing over multiple consecutive monitoring periods.

[0011] In one feasible implementation, the process of comparing the above-mentioned feature parameters with a preset judgment threshold and continuously making a judgment includes: In each monitoring cycle, the currently acquired feature parameters are compared with the corresponding preset judgment thresholds to determine whether the feature parameters meet the abnormal judgment conditions. When any of the above-mentioned characteristic parameters meets the above-mentioned anomaly determination conditions within a single monitoring period, the monitoring period is marked as an anomaly candidate period, and continuous monitoring timing is started. In multiple consecutive monitoring periods, it is continuously determined whether the above-mentioned characteristic parameters continuously meet the above-mentioned anomaly determination conditions, and the duration of the above-mentioned anomaly candidate periods is accumulated. When the cumulative duration of the above-mentioned abnormal candidate cycles exceeds the preset time threshold, the current state is determined to be an early risk state of infusion extravasation. After determining that the above-mentioned early risk state of extravasation of infusion is identified, a corresponding warning signal is output.

[0012] In one feasible implementation, the aforementioned preset judgment threshold is an individualized adaptive threshold, and its determination process includes: During the baseline establishment phase after the infusion begins, spatial temperature distribution data of the skin area around the infusion puncture site are collected. Based on the above spatial temperature distribution data, the baseline statistical values ​​corresponding to the above characteristic parameters are calculated; Based on the baseline statistics mentioned above, an individualized judgment threshold corresponding to the current patient is determined, which is then used to compare the aforementioned feature parameters with the aforementioned preset judgment threshold.

[0013] In one feasible implementation, the determination of the above-mentioned characteristic parameters further includes verifying the spatial consistency of the abnormal temperature region, wherein the spatial consistency verification includes: Within multiple consecutive monitoring cycles, determine whether the above differential positions that meet the abnormality criteria are spatially adjacent or appear continuously in a direction away from the above infusion puncture point. Only when the aforementioned abnormal temperature regions meet the preset consistency conditions in space will the corresponding characteristic parameters be included in the process of determining the early risk status of infusion extravasation.

[0014] Secondly, the present invention also proposes an early detection system for intravenous extravasation, for implementing the early detection method for intravenous extravasation as described in any one of the first aspects of the claims, comprising: The flexible temperature acquisition unit is used to collect skin temperature data in real time within a preset monitoring area around the infusion puncture point, forming a local spatial temperature gradient distribution. The spatial modeling unit is used to construct a spatial temperature distribution model based on the above-mentioned local spatial temperature gradient distribution, and to track temperature change trends to determine the spatial expansion of abnormal temperature regions. The time analysis unit is used to perform time series analysis on the above spatial temperature distribution model, extract feature parameters including at least the temperature gradient change and spatial diffusion rate, and perform time persistence analysis on them. The judgment and warning unit is used to compare the above-mentioned characteristic parameters with the preset threshold to determine whether the abnormal judgment conditions are met, and to output a warning signal when the preset time threshold is continuously exceeded. The display / alarm terminal is used to receive the aforementioned warning signals and display them in real time or issue alarm prompts.

[0015] Thirdly, the present invention also proposes an electronic device comprising: a memory and a processor, characterized in that the processor is used to execute a computer program stored in the memory to implement the steps of the early determination method for extravasation of infusion as described in any of the first aspects.

[0016] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the early determination method for extravasation of infusion as described in any of the first aspects.

[0017] In summary, this invention achieves comprehensive and continuous monitoring of temperature changes around the infusion puncture site by constructing a local spatial temperature gradient distribution around the puncture point and further establishing a spatial temperature distribution model that can be updated over time. Compared with the prior art, which mainly relies on the naked observation of nursing staff or patient complaints, this invention does not rely on the patient's subjective feedback and is not affected by obstruction of the puncture site. It can identify abnormal changes before extravasation causes obvious clinical manifestations such as swelling or pain, thus significantly advancing the detection time of infusion extravasation. This invention does not judge based solely on temperature changes at a single location or a single time point, but rather uses characteristic parameters such as the magnitude of spatial temperature gradient changes and the spatial diffusion rate of abnormal temperature areas to jointly analyze the amplitude characteristics and development trend of temperature anomalies. This judgment method, which combines spatial distribution characteristics with temporal evolution characteristics, can effectively reflect the objective law of the gradual diffusion of extravasated fluid in subcutaneous tissue, avoiding the false alarm problems caused by changes in ambient temperature, individual differences, or body position adjustments in existing single-point temperature monitoring schemes, and improving the accuracy and reliability of extravasation identification. This invention introduces a continuous assessment mechanism in the risk determination process, triggering an alert only when abnormal characteristics persist within a preset time threshold, thereby suppressing transient interference factors. This time-based determination method allows the system to maintain high sensitivity while ensuring the specificity of the alert, reducing unnecessary alarm frequencies and better meeting the needs of continuous clinical monitoring and actual nursing procedures. The determination method used in this invention is based on the analysis of quantifiable and repeatable skin temperature data. The algorithm logic is clear, easy to implement and standardized, and does not require complex and expensive detection equipment or special operating conditions. It can be applied in various clinical scenarios such as general wards and intensive care environments, demonstrating good scalability and practical value. In summary, this invention, through the joint analysis of spatial temperature distribution and temporal evolution characteristics, achieves early, continuous, and objective determination of the risk of extravasation during infusion, effectively overcoming the shortcomings of prior art, such as delayed extravasation detection, high false alarm rate, and insufficient clinical applicability. It can significantly improve the safety of infusion therapy and reduce the risk of serious medical harm.

[0018] Other advantages, objectives and features of this application will be apparent in part from the description which follows, and in part from what those skilled in the art will understand through study and practice of this application. Attached Figure Description

[0019] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic flowchart of an early detection method for intravenous extravasation provided in an embodiment of this application; Figure 2 This is a schematic diagram of an infusion scenario provided in an embodiment of this application; Figure 3 A schematic diagram of the structure of an early detection system for intravenous extravasation provided in an embodiment of this application; Figure 4 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0020] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0021] Please see Figure 1 This is a flowchart illustrating an early detection method for intravenous extravasation provided in an embodiment of this application, which may specifically include: S110. A local spatial temperature gradient distribution is formed within a preset monitoring area around the infusion puncture point; S120. Taking the above-mentioned infusion puncture point as the center, construct a spatial temperature distribution model based on the above-mentioned local spatial temperature gradient distribution, and update the above-mentioned spatial temperature distribution model at multiple consecutive time points to obtain the spatial changes of the abnormal temperature area within the above-mentioned monitoring area. S130. Within a preset time window, perform time series analysis on the above spatial temperature distribution model and extract characteristic parameters including at least the temperature gradient change between the puncture point center and the surrounding area and the spatial diffusion rate of the abnormal temperature area. S140. The above-mentioned characteristic parameters are compared with the preset judgment threshold. When at least one of the above-mentioned characteristic parameters meets the abnormal judgment condition and continues to exceed the preset time threshold, it is judged as an early risk state of infusion extravasation, and an early warning signal is output.

[0022] For example, in step S110, the system delineates a preset monitoring area around the infusion puncture point and forms a local spatial temperature gradient distribution within this area. Specifically, the system simultaneously acquires skin temperature data at the location corresponding to the puncture point and at multiple locations around it, and uses the skin temperature at the location corresponding to the puncture point as a reference temperature. Then, it calculates the temperature difference between the reference temperature and the temperatures at multiple differential locations around the puncture point, thereby obtaining a local spatial temperature gradient distribution that reflects the temperature difference relationship between the "center and periphery". Under normal infusion conditions, the temperature difference around the puncture point is usually within a relatively stable range. However, once extravasation occurs, the infusion fluid diffuses into the subcutaneous tissue and changes the local temperature field distribution within the interstitial space, causing abnormal changes in the direction, amplitude, or range of the aforementioned temperature gradient distribution. Therefore, this step provides a quantifiable spatial basis for subsequent risk identification.

[0023] In step S120, the system constructs a spatial temperature distribution model centered on the infusion puncture point, based on the aforementioned local spatial temperature gradient distribution. This model is updated at multiple consecutive time points to obtain the spatial changes of abnormal temperature areas within the monitoring area. In other words, the system does not merely observe whether the temperature at a single point is abnormal, but rather organizes the temperature information around the puncture point into a "spatial temperature field" that can be updated over time. In each round of sampling updates, the system marks candidate abnormal temperature areas based on the temperature shift at each differential location and records the location, area, or coverage angle of the abnormal temperature area within the monitoring area. At multiple consecutive time points, the system further tracks whether the abnormal temperature area shows a trend of expansion outward from the puncture point and spread from the local area to the periphery. This process corresponds to the spatial behavior characteristics of extravasated fluid diffusion in subcutaneous tissue, enabling the system to distinguish between "single-point occasional temperature disturbances" and "abnormal temperature propagation with a diffusion direction," thereby improving the reliability of early identification.

[0024] In step S130, the system performs time-series analysis on the spatial temperature distribution model within a preset time window to extract characteristic parameters for judgment. These characteristic parameters include at least two types: first, the change in temperature gradient between the puncture point center and the surrounding area, used to characterize the intensity of the temperature anomaly and the magnitude of the center-periphery difference; second, the spatial diffusion rate of the abnormal temperature area, used to characterize the speed or growth trend of the abnormal temperature area expanding within the monitored area over time. By continuously calculating these parameters within the time window, the system can obtain key dynamic characteristics such as whether the temperature anomaly gradually intensifies and whether the abnormal area gradually expands, thereby transforming extravasation risk from a "static judgment" to a "dynamic trend judgment." In practical applications, even if there are differences in basal body temperature, skin temperature, or ambient temperature among different patients, these "change amount" and "diffusion rate" indicators can still more stably reflect the abnormal evolution pattern caused by extravasation.

[0025] In step S140, the system compares the aforementioned characteristic parameters with preset judgment thresholds and makes a final risk judgment based on the duration of the abnormality. When at least one characteristic parameter meets the abnormality judgment condition, and the abnormal state persists for more than the preset time threshold, the system determines it as an early risk state of infusion extravasation and outputs a warning signal. The phrase "persistently exceeding the preset time threshold" is used to suppress false alarms caused by transient disturbances, such as brief patient position adjustments or temperature fluctuations caused by localized blanket obstruction. The warning is only triggered when the abnormality is continuous and stable, thus balancing sensitivity and specificity. The warning signal can be further used to prompt nursing staff to re-examine the puncture site, slow down the infusion rate, assess local swelling, or change the puncture route, thus gaining a window of opportunity for intervention before visible swelling or tissue damage occurs.

[0026] In summary, this invention achieves comprehensive and continuous monitoring of temperature changes around the infusion puncture site by constructing a local spatial temperature gradient distribution around the puncture point and further establishing a spatial temperature distribution model that can be updated over time. Compared with the prior art, which mainly relies on the naked observation of nursing staff or patient complaints, this invention does not rely on the patient's subjective feedback and is not affected by obstruction of the puncture site. It can identify abnormal changes before extravasation causes obvious clinical manifestations such as swelling or pain, thus significantly advancing the detection time of infusion extravasation. This invention does not judge based solely on temperature changes at a single location or a single time point, but rather uses characteristic parameters such as the magnitude of spatial temperature gradient changes and the spatial diffusion rate of abnormal temperature areas to jointly analyze the amplitude characteristics and development trend of temperature anomalies. This judgment method, which combines spatial distribution characteristics with temporal evolution characteristics, can effectively reflect the objective law of the gradual diffusion of extravasated fluid in subcutaneous tissue, avoiding the false alarm problems caused by changes in ambient temperature, individual differences, or body position adjustments in existing single-point temperature monitoring schemes, and improving the accuracy and reliability of extravasation identification. This invention introduces a continuous assessment mechanism in the risk determination process, triggering an alert only when abnormal characteristics persist within a preset time threshold, thereby suppressing transient interference factors. This time-based determination method allows the system to maintain high sensitivity while ensuring the specificity of the alert, reducing unnecessary alarm frequencies and better meeting the needs of continuous clinical monitoring and actual nursing procedures. The determination method used in this invention is based on the analysis of quantifiable and repeatable skin temperature data. The algorithm logic is clear, easy to implement and standardized, and does not require complex and expensive detection equipment or special operating conditions. It can be applied in various clinical scenarios such as general wards and intensive care environments, demonstrating good scalability and practical value. In summary, this invention, through the joint analysis of spatial temperature distribution and temporal evolution characteristics, achieves early, continuous, and objective determination of the risk of extravasation during infusion, effectively overcoming the shortcomings of prior art, such as delayed extravasation detection, high false alarm rate, and insufficient clinical applicability. It can significantly improve the safety of infusion therapy and reduce the risk of serious medical harm.

[0027] In one feasible implementation, the formation of a local spatial temperature gradient distribution within the preset monitoring area around the infusion puncture site includes: Skin temperature data were acquired at multiple locations within a pre-defined monitoring area around the infusion puncture site; The skin temperature at the location corresponding to the above-mentioned infusion puncture point is used as the reference temperature; The temperature difference between the above-mentioned reference temperature and the skin temperature at multiple differential locations in the surrounding area is calculated to form a local spatial temperature gradient distribution.

[0028] For example, in this embodiment, the system first delineates a preset monitoring area around the infusion puncture site. This preset monitoring area is used to cover the subcutaneous tissue area near the infusion puncture site where extravasation may occur. This monitoring area can be set according to the type of puncture site, skin thickness, and common clinical extravasation diffusion ranges, and is used to limit the spatial range of temperature acquisition, so as to ensure that the acquired data can reflect the tissue status around the puncture site, while avoiding excessive noise interference caused by an excessively large monitoring range.

[0029] After setting the monitoring area, the system acquires skin temperature data at multiple locations within the preset monitoring area. Specifically, the system arranges temperature acquisition points at the location corresponding to the puncture point and at multiple differential locations around the puncture point. These differential locations can be distributed circumferentially, radially, or in combination around the puncture point to cover skin areas in different directions around the puncture point. The system synchronously acquires skin temperature data from each acquisition point during each monitoring cycle, thereby obtaining multi-point temperature sampling results reflecting the temperature distribution in that local area. Through multi-point sampling, the system can acquire information on spatial temperature differences, rather than just the absolute value change of a single point's temperature.

[0030] Subsequently, the system uses the skin temperature at the location corresponding to the infusion puncture point as the baseline temperature. This baseline temperature serves as a reference point for local temperature analysis, aiming to establish a relative temperature relationship between the "center" and the "periphery." Since different patients have varying basal body temperature, skin temperature, and ambient temperature, relying solely on the absolute change at a single peripheral temperature point for judgment is easily affected by individual differences and external disturbances. Therefore, this implementation introduces the location corresponding to the puncture point as the baseline temperature, allowing subsequent calculations to focus more on the relative changes within the same local area, thereby improving the stability and repeatability of the judgment.

[0031] After obtaining the reference temperature, the system calculates the temperature difference between the reference temperature and the skin temperatures at multiple differential locations to form a local spatial temperature gradient distribution. Specifically, the system calculates the temperature difference between the skin temperature at each differential location and the reference temperature. This temperature difference characterizes the degree of temperature deviation between the center of the puncture point and the surrounding skin in the corresponding orientation. The system further correlates the temperature differences at each differential location with their spatial position, for example, organizing them according to angular orientation, radial distance, or grid coordinates to form a local spatial temperature gradient distribution. This local spatial temperature gradient distribution reflects the spatial difference structure of skin temperature around the puncture point, enabling the system not only to identify whether the temperature is abnormal, but also to identify key information such as where the temperature abnormality is distributed, in which direction it is more obvious, and whether the abnormal range is expanding.

[0032] In this embodiment, the local spatial temperature gradient distribution formed around the infusion puncture point provides a basic input for subsequent spatial temperature distribution model construction and abnormal diffusion behavior analysis. Especially in the early stages of extravasation, the extravasated fluid entering the subcutaneous tissue usually causes non-uniform changes in the local temperature field around the puncture point, manifested as a continuous deviation of temperature differences from the baseline in certain directions and a gradual expansion. The spatial gradient distribution constructed by this embodiment using multi-point temperature differences can more sensitively capture such spatial non-uniform changes, thereby providing a reliable and quantifiable basis for the early identification of extravasation risk.

[0033] In one feasible implementation, the characteristic is that, The aforementioned differential positions are distributed circumferentially or radially along the aforementioned infusion puncture point, and the distance between the aforementioned differential positions and the aforementioned infusion puncture point is within a preset range.

[0034] For example, the following describes in detail the setting principle and function of "multiple differential positions are distributed circumferentially or radially along the infusion puncture point, and the distance between the differential positions and the infusion puncture point is within a preset range" in this embodiment.

[0035] In this embodiment, to enable the system to stably and comprehensively acquire the spatial temperature variation characteristics of the tissue surrounding the infusion puncture site, multiple differential locations are set up within a preset monitoring area. These differential locations are used to arrange temperature acquisition points and collect skin temperature data at the corresponding locations. Unlike setting up single-point temperature acquisition only near the puncture site, this embodiment arranges the differential locations circumferentially or radially, allowing the temperature acquisition to reflect not only the local temperature state at the center of the puncture site but also the temperature differences at different locations and distances around the puncture site. This provides a reliable spatial sampling basis for subsequently forming a local spatial temperature gradient distribution and identifying abnormal temperature diffusion behavior.

[0036] Specifically, when the differential positions are distributed circumferentially along the infusion puncture point, the system sets multiple differential positions at different angles around the puncture point, allowing the temperature acquisition points to cover multiple directional areas around the puncture point. Since the diffusion of extravasated fluid in subcutaneous tissue is not necessarily perfectly symmetrical, its diffusion direction may be affected by factors such as blood vessel orientation, subcutaneous tissue interstitial structure, the direction of pressure from the adhesive tape, and the patient's position. Therefore, circumferential distribution enhances the system's ability to detect "directional abnormalities." When extravasation occurs first on one side and diffuses along a certain direction, the temperature shift of the corresponding differential position relative to the reference temperature will be manifested earlier and more significantly, enabling the system to capture non-uniform changes in the temperature gradient distribution at an early stage.

[0037] When the differential positions are radially distributed along the infusion puncture point, the system sets multiple differential positions at different distances outward from the puncture point, allowing the temperature acquisition points to cover the temperature change gradient from the center outward. The advantage of radial distribution is that it can more directly describe the "diffusion distance" and "diffusion rate" of the abnormal temperature region. That is, when extravasated fluid enters the subcutaneous tissue, the abnormal temperature often gradually expands from the vicinity of the puncture point to more distant surrounding tissues. Radial arrangement enables the system to identify whether the area affected by the temperature anomaly is expanding, whether the outer boundary is advancing, and the rate of advancement during continuous monitoring, thereby providing more reliable data support for subsequent calculation of the spatial diffusion rate of the abnormal temperature region.

[0038] In this embodiment, the distance between the differential location and the infusion puncture point is limited to a preset range, which is used to balance "monitoring sensitivity" and "interference resistance". If the differential location is too close to the puncture point, the collection point may be affected by the dressing material, local pressure, or minor physiological fluctuations around the puncture, leading to increased temperature difference fluctuations. If the differential location is too far from the puncture point, the temperature change may reflect more the ambient temperature or the overall temperature change of the limb, thus weakening the sensitivity to early local abnormalities of extravasation. Therefore, by limiting the distance between the differential location and the puncture point to a preset range, the system can ensure that the collected temperature difference mainly reflects the local temperature field changes caused by the infusion fluid infiltration and diffusion around the puncture point, improving the effectiveness and stability of the formed local spatial temperature gradient distribution.

[0039] Specifically, the temperature acquisition elements set at the differential location can be distributed in a fan shape around the puncture point, with a fan-shaped coverage area of ​​approximately 120°. The distance between the differential temperature acquisition elements and the puncture point can be set to 3 cm. Multiple temperature acquisition elements are arranged at preset angle intervals within the fan-shaped area to ensure spatial sampling density of local tissue temperature changes.

[0040] By employing the aforementioned differential position arrangement in the circumferential or radial directions, this embodiment enables the system to characterize the temperature distribution features around the puncture point with a more reasonable spatial sampling structure. This allows the system to capture potential directional abnormal changes in the early stages of extravasation and to track the evolution of abnormal temperature zones from the center outwards. Consequently, it provides high-quality input for subsequent updates to the spatial temperature distribution model and extraction of time-series feature parameters, thereby improving the accuracy and reliability of early detection of extravasation during infusion.

[0041] In one feasible implementation, the characteristic is that, The above-mentioned anomaly determination conditions include the above-mentioned temperature gradient change continuing or increasing over multiple consecutive monitoring periods, or the above-mentioned spatial diffusion rate continuing or increasing over multiple consecutive monitoring periods.

[0042] For example, the system's early risk assessment of extravasation is not based solely on a single temperature deviation or instantaneous change in spatial diffusion, but rather on an analysis of the changing trends over multiple continuous monitoring periods to ensure accurate identification of early signs of extravasation and avoid false alarms and missed alarms.

[0043] The system calculates the temperature difference between the puncture site center and multiple differential locations around it within each monitoring cycle, obtaining a local temperature gradient. By analyzing temperature data from multiple consecutive monitoring cycles, the system examines whether this local temperature gradient exhibits persistent changes. If the temperature gradient change persists and increases over multiple cycles, it indicates an intensifying abnormal temperature trend, potentially a sign of extravasation. This judgment of "persistence or increasing trend" can more effectively avoid misjudgments caused by instantaneous local temperature fluctuations (such as short-term changes in body position or environmental temperature fluctuations), thereby improving the accuracy of the assessment.

[0044] For spatial diffusion of abnormal temperature areas, the system not only examines the diffusion rate within the current cycle but also analyzes the expansion over multiple consecutive monitoring cycles. If the abnormal temperature area shows a continuous expansion trend over time, or if the diffusion rate gradually increases over multiple cycles, this abnormal diffusion trend can be further confirmed as the expansion of extravasated fluid. Through time series analysis, the system can capture temperature fluctuation patterns expanding outward from the puncture point; the persistence and intensification of this trend indicate that fluid may be spreading to a wider area of ​​subcutaneous tissue.

[0045] The advantage of this method lies in its ability to avoid overly sensitive judgments at a single point in time through continuous monitoring data analysis. It provides a reasonable time window to suppress false alarms, particularly regarding temperature fluctuations caused by body positioning or external environmental influences. Simultaneously, it enables the system to identify the dynamic characteristics of fluid diffusion in the early stages of extravasation, providing early risk warnings and ensuring timely intervention to reduce potential harm to patients. Through this multi-cycle continuous assessment, this implementation significantly improves the accuracy and reliability of extravasation detection and provides a more robust basis for subsequent warning signal output, effectively reducing false alarms and missed alarms and improving clinical safety.

[0046] In one feasible implementation, the process of comparing the above-mentioned feature parameters with a preset judgment threshold and continuously making a judgment includes: In each monitoring cycle, the currently acquired feature parameters are compared with the corresponding preset judgment thresholds to determine whether the feature parameters meet the abnormal judgment conditions. When any of the above-mentioned characteristic parameters meets the above-mentioned anomaly determination conditions within a single monitoring period, the monitoring period is marked as an anomaly candidate period, and continuous monitoring timing is started. In multiple consecutive monitoring periods, it is continuously determined whether the above-mentioned characteristic parameters continuously meet the above-mentioned anomaly determination conditions, and the duration of the above-mentioned anomaly candidate periods is accumulated. When the cumulative duration of the above-mentioned abnormal candidate cycles exceeds the preset time threshold, the current state is determined to be an early risk state of infusion extravasation. After determining that the above-mentioned early risk state of extravasation of infusion is identified, a corresponding warning signal is output.

[0047] For example, the system reliably assesses early risks of extravasation by comparing characteristic parameters with preset thresholds and employing a continuous assessment strategy. This process, through dynamic data analysis over a continuous monitoring period, ensures that false alarms caused by transient changes in body position or environmental disturbances are filtered out when identifying extravasation risks.

[0048] Within each monitoring cycle, the system acquires and calculates the characteristic parameters, which typically include the temperature gradient change and the spatial diffusion rate of the abnormal temperature region. The system then compares the characteristic parameters for the current cycle with preset threshold values ​​to determine if they meet preset anomaly criteria. If the change in a particular characteristic parameter exceeds the preset threshold range, the system considers that the cycle to have a potential risk of extravasation, triggers an anomaly candidate cycle marker, and begins continuous monitoring. At this point, the system enters the continuous tracking phase of the anomaly signal.

[0049] When any characteristic parameter in a monitoring cycle meets the anomaly determination criteria, the system marks this cycle as an "anomaly candidate cycle" and initiates a timing mechanism to record the duration of this anomaly candidate cycle. This timing process provides data support for subsequent time-duration analysis, ensuring that the system can capture the trend of continuous temperature anomalies. The purpose of this is to ensure that the system only determines a true risk state after an abnormal state has accumulated for a certain period of time, avoiding misjudgments caused by instantaneous disturbances (such as local pressure, changes in body position, changes in ambient temperature, etc.).

[0050] Over several consecutive monitoring periods, the system continuously assesses whether each feature parameter consistently meets the anomaly criteria. If an anomaly persists and exceeds a preset threshold range in each period, the system accumulates the duration of these candidate anomaly periods. This accumulation process provides temporal support for subsequent risk assessment, ensuring the system can identify whether the anomaly exhibits a persistent or intensifying trend.

[0051] Once the cumulative duration of the aforementioned abnormal candidate cycles exceeds a preset time threshold, the system will determine the current state as an "early risk state of intravenous extravasation." This determination is based on the fact that only when the abnormal temperature signal persists for multiple cycles and its intensity continuously increases can intravenous extravasation be considered to have occurred and pose a risk of further expansion. At this time, the system will output a corresponding warning signal, prompting nursing staff to take timely measures, such as adjusting the infusion rate, checking the puncture site, assessing swelling, or changing the puncture route, to avoid more serious complications caused by extravasation.

[0052] Through this continuous assessment mechanism, this implementation method effectively suppresses false alarms caused by transient interference factors, while also ensuring the accuracy of early detection and warning of extravasation. This method enables risk assessment in the initial stages of extravasation and allows for preventative intervention, significantly improving safety during clinical treatment and reducing the risk of serious medical harm to patients.

[0053] In one feasible implementation, the aforementioned preset judgment threshold is an individualized adaptive threshold, and its determination process includes: During the baseline establishment phase after the infusion begins, spatial temperature distribution data of the skin area around the infusion puncture site are collected. Based on the above spatial temperature distribution data, the baseline statistical values ​​corresponding to the above characteristic parameters are calculated; Based on the baseline statistics mentioned above, an individualized judgment threshold corresponding to the current patient is determined, which is then used to compare the aforementioned feature parameters with the aforementioned preset judgment threshold.

[0054] For example, the system uses an individualized adaptive threshold, rather than a uniform standard threshold, to determine the risk of extravasation. This approach allows the system to more accurately adapt to the physiological differences and environmental changes of different patients, avoiding errors caused by a uniform threshold, especially considering individual differences in body size, skin temperature, or external environmental conditions.

[0055] During the baseline establishment phase after the infusion begins, the system starts collecting individualized baseline data for each patient. The purpose of this phase is to obtain "benchmark" spatial temperature distribution data for the patient under normal infusion conditions, serving as a reference standard for subsequent assessments. During this process, the system collects temperature data of the skin area surrounding the infusion puncture site, forming a spatial temperature distribution reflecting the temperature characteristics of the puncture site and its surroundings. This dataset represents the normal temperature distribution for the patient in the absence of extravasation or other abnormalities, and forms the basis for the system to assess the risk of extravasation based on the actual situation.

[0056] Based on the collected spatial temperature distribution data, the system calculates baseline statistics for the corresponding characteristic parameters. These parameters typically include the temperature gradient between the puncture site center and surrounding areas, the magnitude of temperature change, and the range of temperature fluctuations in the local area. Through statistical analysis of this data, the system can derive a baseline statistical value that reflects the characteristics of skin temperature changes under normal conditions. This baseline statistical value provides a personalized reference standard for subsequent risk assessment.

[0057] Based on the calculated baseline statistics, the system determines an individualized threshold for the current patient. This threshold is used in subsequent monitoring cycles to compare real-time temperature data with this threshold. Compared to a standard threshold, the individualized threshold more accurately reflects the patient's baseline temperature and determines whether abnormalities have occurred based on the actual temperature fluctuation range. Only when the characteristic parameters exceed the individualized threshold will the system consider extravasation risk present and issue a warning.

[0058] By employing this individualized adaptive threshold determination process, this implementation effectively overcomes the problem of poor adaptability of a single standard threshold to different patients, providing a more accurate and personalized assessment of extravasation risk. This method improves the sensitivity and accuracy of the assessment, enabling the identification of extravasation risk at an early stage and providing timely intervention recommendations for clinicians, significantly reducing the risk of medical malpractice and misdiagnosis.

[0059] In one feasible implementation, the determination of the above-mentioned characteristic parameters further includes verifying the spatial consistency of the abnormal temperature region, wherein the spatial consistency verification includes: Within multiple consecutive monitoring cycles, determine whether the above differential positions that meet the abnormality criteria are spatially adjacent or appear continuously in a direction away from the above infusion puncture point. Only when the aforementioned abnormal temperature regions meet the preset consistency conditions in space will the corresponding characteristic parameters be included in the process of determining the early risk status of infusion extravasation.

[0060] For example, in this embodiment, to improve the accuracy of early risk assessment of extravasation, the system not only performs a simple quantitative judgment on temperature anomalies but also incorporates a spatial consistency verification step. This process helps ensure that extravasation risk is only included in the assessment when the temperature anomaly area shows an actual trend of spatial diffusion, thereby avoiding false alarms and overreactions.

[0061] The system continuously tracks temperature changes at differential locations over multiple monitoring cycles and determines which locations meet anomaly criteria. Anomaly criteria refer to temperature differences at these locations exceeding preset thresholds, indicating a localized temperature anomaly. However, temperature changes within a single cycle are insufficient to definitively confirm the existence of extravasation risk, as external factors (such as changes in local body position or temporary environmental variations) can also cause temperature fluctuations. Therefore, the system continuously analyzes whether these differential locations remain abnormal over multiple cycles.

[0062] The system performs spatial consistency verification on differential locations that meet the anomaly detection criteria. The core of this verification is to check whether these differential locations exhibit a certain spatial regularity across multiple monitoring periods. Specifically, the system determines whether these differential locations are spatially adjacent or appear consecutively along a direction away from the infusion puncture point. In other words, the system focuses on the propagation pattern of temperature anomalies, judging whether the anomaly has a "spreading" trend. For example, if multiple adjacent locations or similar angles show abnormal temperature changes, and this abnormal distribution gradually intensifies along the direction of outward expansion from the puncture point, it indicates that extravasation may be spreading in a certain direction. This spatial consistency verification helps the system distinguish between "localized, sporadic anomalies" and "extravasation with a spreading trend."

[0063] Only when the aforementioned abnormal temperature regions spatially meet preset consistency conditions will the corresponding characteristic parameters be included in the process of determining the early risk status of extravasation. If the diffusion behavior of the abnormal temperature does not meet the spatial consistency requirements, the system will consider that the temperature anomaly may only be an accidental or temporary fluctuation and will not trigger an early warning signal for extravasation risk.

[0064] By incorporating spatial consistency verification, this implementation effectively filters out false alarms caused by localized atypical temperature fluctuations, enhancing the system's sensitivity and accuracy in assessing extravasation risk. The system judges extravasation risk not only based on the magnitude of temperature changes but also by considering the spatial expansion trend of temperature, thereby improving early warning capabilities for extravasation and avoiding false alarms caused by localized disturbances. This spatial consistency verification makes risk assessment more physically grounded, enabling more precise identification and tracking of the dynamic process of extravasation, ensuring timely intervention and reducing medical harm to patients caused by extravasation.

[0065] In one feasible implementation, such as Figure 2 As shown in the diagram, this embodiment provides a scenario where a flexible temperature sensor array is attached around an infusion puncture point. This structure, centered on the infusion puncture point, performs multi-point, distributed temperature acquisition on the surrounding skin area to enable early monitoring and assessment of the risk of extravasation.

[0066] In this embodiment, a central reference temperature acquisition point T0 is set at the infusion puncture site. T0 is located above or immediately adjacent to the point where the puncture needle or indwelling needle enters the skin. It is used to collect skin temperature information closest to the infusion inlet, serving as a reference point for local temperature analysis. The temperature data collected by T0 reflects the temperature status of the core area of ​​the puncture site.

[0067] Around the central reference temperature acquisition point T0, multiple differential temperature acquisition points T1 to T12 are set up. These differential temperature acquisition points are distributed in a fan shape along the circumference of the puncture point, covering the subcutaneous tissue area around the infusion puncture point where fluid leakage and diffusion may occur. As can be seen from the figure, the differential temperature acquisition points are evenly distributed at different angles and positions, enabling the system to simultaneously acquire skin temperature data from multiple directions around the puncture point, thus forming a temperature sampling array with spatial resolution.

[0068] The flexible temperature sensor array employs a flexible substrate structure, allowing it to conform to the surface of the patient's limb. This adapts to different limb curvatures and puncture site shapes, reducing measurement errors caused by poor adhesion. The multiple sampling locations shown as dots in the figure represent multiple temperature sensing units within the flexible sensor array. These units are connected to an external acquisition and processing module via wires or flexible circuits to transmit the acquired temperature signals to the backend analysis system.

[0069] In actual operation, the system simultaneously collects skin temperature data from the central reference temperature acquisition point T0 and each differential temperature acquisition point T1 to T12. Using T0 as the reference temperature, the system calculates the temperature difference between each differential temperature acquisition point and T0. By correlating these temperature differences with their corresponding spatial locations, the system can construct a local spatial temperature gradient distribution that reflects the characteristics of skin temperature changes around the puncture point.

[0070] When intravenous infusion is in a normal state, the temperature difference between each differential temperature acquisition point and the central reference temperature acquisition point usually remains within a relatively stable range. However, when extravasation occurs, the extravasated fluid enters the subcutaneous tissue and gradually diffuses, causing abnormal changes in skin temperature in certain directions or areas around the puncture point, spatially exhibiting a trend of expansion outward from the puncture point. This flexible temperature sensor array structure can sensitively capture these changes in spatial temperature distribution, providing a reliable data foundation for subsequent spatial temperature distribution model construction, time series analysis, and early risk assessment of extravasation.

[0071] Secondly, this invention also proposes an early detection system for intravenous extravasation, such as... Figure 3 As shown, the method for early detection of extravasation during infusion as described in any one of the first aspects of claim includes: The flexible temperature acquisition unit 21 is used to collect skin temperature data in real time within a preset monitoring area around the infusion puncture point, forming a local spatial temperature gradient distribution. The spatial modeling unit 22 is used to construct a spatial temperature distribution model based on the above-mentioned local spatial temperature gradient distribution, and to track the temperature change trend to determine the spatial expansion of the abnormal temperature region. The time analysis unit 23 is used to perform time series analysis on the above-mentioned spatial temperature distribution model, extract characteristic parameters including at least the temperature gradient change and spatial diffusion rate, and perform time persistence analysis on it. The judgment and warning unit 24 is used to compare the above-mentioned characteristic parameters with the preset threshold to determine whether the abnormal judgment conditions are met, and to output a warning signal when the preset time threshold is continuously exceeded. Display / alarm terminal 25 is used to receive the above-mentioned warning signals and display them in real time or issue alarm prompts.

[0072] For example, the system includes a flexible temperature acquisition unit 21. The flexible temperature acquisition unit 21 is disposed within a preset monitoring area around the infusion puncture point, and uses a flexible attachment structure to adhere to the patient's skin surface. It is used to collect skin temperature data in real time at the puncture point and multiple surrounding locations. Through multi-point synchronous acquisition, the flexible temperature acquisition unit 21 can form a local spatial temperature gradient distribution reflecting the temperature differences around the puncture point, providing basic input data for subsequent spatial modeling and anomaly analysis. Due to its flexible structure, this unit can adapt to different limb curvatures, reducing measurement errors caused by poor adhesion, and is suitable for various clinical infusion scenarios.

[0073] The collected local spatial temperature gradient distribution data is transmitted to the spatial modeling unit 22. Based on the aforementioned local spatial temperature gradient distribution, the spatial modeling unit 22 constructs a spatial temperature distribution model centered on the infusion puncture point and continuously updates this model during the infusion process. By modeling and comparing the temperature distribution at different time points, the spatial modeling unit 22 can identify the location changes of abnormal temperature areas within the monitoring area and track whether the abnormal temperature exhibits a spatial trend of expansion from the puncture point to surrounding tissues, thereby reflecting potential extravasation and diffusion behavior.

[0074] Subsequently, the constructed and continuously updated spatial temperature distribution model is input into the time analysis unit 23. The time analysis unit 23 performs time series analysis on the spatial temperature distribution model, extracting characteristic parameters for risk assessment within a preset time window. These characteristic parameters include at least the temperature gradient change between the puncture point center and the surrounding area, and the spatial diffusion rate of the abnormal temperature region. By performing time persistence analysis on the above characteristic parameters, the time analysis unit 23 can determine whether the temperature anomaly has a persistent or intensifying trend, thereby distinguishing between sporadic temperature fluctuations and anomalies with a developing trend.

[0075] After obtaining the characteristic parameters and their time-varying characteristics, the relevant data is sent to the judgment and early warning unit 24. The judgment and early warning unit 24 compares the characteristic parameters with a preset judgment threshold and makes a comprehensive judgment based on the duration condition. When at least one characteristic parameter meets the abnormal judgment condition, and the abnormal state continues for more than the preset time threshold, the judgment and early warning unit 24 determines the current state as an early risk state of intravenous extravasation and generates a corresponding early warning signal. By introducing a continuous judgment mechanism, this unit can effectively suppress instantaneous false alarms caused by changes in body position, short-term obstruction, or environmental changes, improving the reliability of the overall judgment result.

[0076] Finally, the warning signal is transmitted to the display / alarm terminal 25. The display / alarm terminal 25 is used to receive the warning signal output by the judgment and warning unit 24, and to display or alarm in real time in the form of graphics, text, sound and light or mobile terminal prompts, so that nursing staff can be informed of the early risk information of infusion extravasation in a timely manner and take corresponding clinical intervention measures.

[0077] Through the coordinated operation of the above-mentioned functional units, the infusion extravasation early detection system described in this embodiment can continuously and objectively monitor and analyze the temperature changes around the infusion puncture site without relying on patient complaints and frequent manual inspections. This enables early identification and graded warning of infusion extravasation risks, thereby improving the safety of the infusion treatment process and reducing the risk of serious medical damage.

[0078] In one feasible implementation, an early detection system for infusion extravasation can also perform any step of the method proposed in the first aspect.

[0079] Thirdly, the present invention also proposes an electronic device 300, such as... Figure 4 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the early determination method for extravasation of infusion as described in any of the first aspects.

[0080] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the early determination method for extravasation of infusion as described in any one of the first aspects.

[0081] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0082] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0084] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform the steps of the early determination method for extravasation in the corresponding embodiment.

[0087] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0088] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0093] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for early detection of intravenous extravasation, characterized in that, Includes the following steps: A local spatial temperature gradient distribution is formed within a pre-defined monitoring area around the infusion puncture site; Centered on the infusion puncture point, a spatial temperature distribution model is constructed based on the local spatial temperature gradient distribution, and the spatial temperature distribution model is updated at multiple consecutive time points to obtain the spatial changes of abnormal temperature areas within the monitoring area. Within a preset time window, a time series analysis is performed on the spatial temperature distribution model to extract characteristic parameters, including at least the temperature gradient change between the puncture point center and the surrounding area, and the spatial diffusion rate of the abnormal temperature area. The feature parameters are compared with preset judgment thresholds. When at least one of the feature parameters meets the abnormal judgment condition and continues to exceed the preset time threshold, it is judged as an early risk state of infusion extravasation, and an early warning signal is output.

2. The method for early determination of extravasation during infusion according to claim 1, characterized in that, The formation of a local spatial temperature gradient distribution within a preset monitoring area around the infusion puncture site includes: Skin temperature data were acquired at multiple locations within a pre-defined monitoring area around the infusion puncture site; The skin temperature at the location corresponding to the infusion puncture point is used as the reference temperature; The temperature difference between the reference temperature and the skin temperature at multiple differential locations in the surrounding area is calculated to form a local spatial temperature gradient distribution.

3. The method for early determination of extravasation during infusion according to claim 2, characterized in that, The plurality of differential positions are distributed circumferentially or radially along the infusion puncture point, and the distance between the differential positions and the infusion puncture point is within a preset range.

4. The method for early determination of extravasation during infusion according to claim 1, characterized in that, The anomaly determination conditions include the temperature gradient change being persistent or increasing over multiple consecutive monitoring periods, or the spatial diffusion rate being persistent or increasing over multiple consecutive monitoring periods.

5. The method for early determination of extravasation during infusion according to claim 1, characterized in that, The process of comparing the feature parameters with a preset judgment threshold and continuously making judgments includes: In each monitoring cycle, the currently acquired feature parameters are compared with the corresponding preset judgment thresholds to determine whether the feature parameters meet the abnormal judgment conditions. When any of the aforementioned feature parameters meets the anomaly determination condition within a single monitoring period, the monitoring period is marked as an anomaly candidate period, and continuous monitoring timing is initiated. Within multiple consecutive monitoring periods, it is continuously determined whether the feature parameters continuously meet the anomaly determination conditions, and the duration of the anomaly candidate period is accumulated. When the cumulative duration of the abnormal candidate cycle exceeds a preset time threshold, the current state is determined to be an early risk state of infusion extravasation. After determining that the infusion is in an early risk state of extravasation, a corresponding warning signal is output.

6. The method for early determination of extravasation during infusion according to claim 1, characterized in that, The preset judgment threshold is an individualized adaptive threshold, and its determination process includes: During the baseline establishment phase after the infusion begins, spatial temperature distribution data of the skin area surrounding the infusion puncture point are collected. Based on the spatial temperature distribution data, calculate the baseline statistical values ​​corresponding to the characteristic parameters; Based on the baseline statistics, an individualized judgment threshold corresponding to the current patient is determined, which is then used to compare the feature parameters with the preset judgment threshold.

7. The method for early determination of extravasation during infusion according to claim 1, characterized in that, The determination of the characteristic parameters also includes verifying the spatial consistency of the abnormal temperature region, wherein the spatial consistency verification includes: Within multiple consecutive monitoring cycles, it is determined whether the differential positions that meet the abnormality criteria are spatially adjacent or appear continuously along a direction away from the infusion puncture point. The corresponding characteristic parameters will only be included in the determination process of early risk status of extravasation in infusion when the abnormal temperature region meets the preset consistency condition in space.

8. An early detection system for intravenous extravasation, used to implement the early detection method for intravenous extravasation according to any one of claims 1 to 7, comprising: The flexible temperature acquisition unit is used to collect skin temperature data in real time within a preset monitoring area around the infusion puncture point, forming a local spatial temperature gradient distribution. The spatial modeling unit is used to construct a spatial temperature distribution model based on the local spatial temperature gradient distribution and to track temperature change trends to determine the spatial expansion of abnormal temperature regions. The time analysis unit is used to perform time series analysis on the spatial temperature distribution model, extract feature parameters including at least the temperature gradient change and the spatial diffusion rate, and perform time persistence analysis on it. The judgment and warning unit is used to compare the feature parameters with a preset threshold to determine whether the abnormal judgment conditions are met, and to output a warning signal when the preset time threshold is continuously exceeded. The display / alarm terminal is used to receive the warning signal and display it in real time or issue an alarm prompt.

9. An electronic device, comprising: The memory and processor are characterized in that the processor is used to implement the steps of the early determination method for extravasation of infusion as described in any one of claims 1-7 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for early determination of extravasation of infusion as described in any one of claims 1-7.

Images