Intelligent infusion monitoring management system

Abstract

The invention discloses an intelligent infusion monitoring management system, and relates to the technical field of medical equipment, and the system comprises the steps: collecting patient data, synchronizing the patient data to a central monitoring system through a block chain technology, and generating a personalized infusion scheme; based on a personalized infusion scheme, a medical worker uses a mobile device to carry out identity verification on a patient and obtain medicine information, and a voice assistant function is integrated; the monitoring module is responsible for monitoring vital signs of a patient and the temperature of a ward by using wearable equipment and a temperature sensor, and adjusting a personalized infusion scheme and liquid temperature according to the vital signs and the temperature of the ward; the risk value prediction module is responsible for predicting risk values of blockage and leakage according to the adjusted personalized infusion scheme and the liquid temperature and setting a graded alarm mechanism; patients and family members receive the infusion progress through the intelligent infusion monitor. According to the invention, the block chain technology and the advanced artificial intelligence algorithm are integrated, so that the health data and medicine information of the patient can be efficiently managed and analyzed.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to an intelligent infusion monitoring and management system. Background Art

[0002] In modern medical practice, infusion therapy is an extremely common and crucial link in clinical nursing. With the development of technology, infusion monitoring systems have gradually evolved from traditional manual monitoring towards intelligence and automation. In the prior art, some systems have been able to achieve automatic monitoring and adjustment of infusion speed, as well as real-time feedback of infusion status through sensors. However, most of these systems lack in-depth consideration of individual patient differences and fail to fully combine the patient's health data and drug information to generate personalized solutions. In addition, the existing systems have deficiencies in risk warning, and fail to effectively utilize advanced technologies such as deep learning to accurately predict and classify potential risks (such as blockage and leakage) during the infusion process, resulting in a lag in the response of medical staff when dealing with emergencies and increasing the safety hazards for patients. Furthermore, there are also obvious shortcomings in the doctor-patient interaction of the existing infusion monitoring systems. Summary of the Invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides an intelligent infusion monitoring and management system to solve the problems of the existing infusion monitoring systems, such as the lack of personalized solution generation, insufficient accuracy of risk warning, and poor doctor-patient interaction experience.

[0005] To solve the above technical problems, the present invention provides the following technical solutions:

[0006] The present invention provides an intelligent infusion monitoring and management system, which includes a solution generation module responsible for collecting patient data, synchronizing it to the central monitoring system through blockchain technology, and generating a personalized infusion solution, where the patient data includes health data and drug information;

[0007] An identity verification module responsible for, based on the personalized infusion solution, medical staff using a mobile device to verify the patient's identity and obtain drug information, and integrating the voice assistant function;

[0008] An intelligent adjustment module responsible for using wearable devices and temperature sensors to monitor the patient's vital signs and the ward temperature, and adjusting the personalized infusion solution and the liquid temperature according to the vital signs and the ward temperature;

[0009] A risk prediction module responsible for predicting the risk values of blockage and leakage according to the adjusted personalized infusion solution and the liquid temperature, setting a grading alarm mechanism, and feeding it back to medical staff through a mobile device;

[0010] The doctor-patient interaction module is responsible for enabling patients and their families to receive infusion progress through the intelligent infusion monitor and providing interactive educational resources.

[0011] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: the health data includes age, gender, weight, height, medical history, allergy history, current condition, blood routine, and liver and kidney function;

[0012] The drug information includes drug type, drug dosage, drug interactions, and pharmacokinetics.

[0013] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: according to the patient data, a personalized infusion plan is generated, including the following steps,

[0014] Standardize the patient's health data and drug information, and construct a multi-modal data set containing temporal features;

[0015] Determine the key feature weights through SHAP value analysis, and establish an input feature importance model consistent with the clinical decision-making logic;

[0016] Construct an infusion decision-making environment based on the Markov decision process. The infusion decision-making environment includes a state space, an action space, a reward function, a state transition model, an initial state distribution, and a termination condition. Among them, the state space includes the patient's health data and drug information, the action space is the total infusion volume, infusion duration, and infusion speed of the drug, the reward function is the weighted sum of three parts: safety reward, economic reward, and consistency reward, the state transition model describes the dynamic law of the state changing with the action, the initial state distribution samples the patient's characteristics and initial vital signs from historical data, and the termination condition is to complete the total infusion volume and the vital signs are stable;

[0017] Adopt a policy-constrained Q-learning framework. When updating the Q value, introduce entropy regularization and log-sum-exp penalty terms, use the environment transition model to predict state transitions, combine the behavior prediction model to output the action probability distribution, and use the KL divergence to constrain the similarity between the proxy policy and the expert policy. Jointly optimize the policy network, Q value network, and constraint network in the Actor-Critic architecture to balance reward maximization and safety constraints;

[0018] Based on the trained PCQL model, output a personalized infusion plan including the total infusion volume, infusion duration, and infusion speed.

[0019] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: the identity verification and obtaining drug information include the following steps,

[0020] Medical staff use the AR device to scan the QR code on the patient's bracelet, verify their identity through the fingerprint module of the AR device, compare the scanned patient information with the patient information in the central monitoring system, and confirm whether the patient is correct;

[0021] Similarly, use the AR device to scan the QR code on the medicine package to obtain medicine information and confirm whether the medicine is correct.

[0022] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: the integrated voice assistant function means that medical staff can query more information and adjust the display content through voice commands, and the voice assistant will parse the voice commands and display the corresponding information on the screen.

[0023] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: the vital signs include blood pressure and heart rate.

[0024] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: adjusting the personalized infusion plan and liquid temperature according to the vital signs and environmental data includes the following steps,

[0025] Based on historical patient data, set the normal ranges of the patient's vital signs and the environmental data of the ward, and use a chart to record the long-term trends of blood pressure and heart rate;

[0026] Automatically adjust the infusion rate according to the real-time data of blood pressure and heart rate;

[0027] Automatically adjust the total infusion volume according to the long-term trends of blood pressure and heart rate;

[0028] Automatically adjust the temperature of the infusion liquid according to the environmental temperature and the patient's body temperature status.

[0029] As a preferred embodiment of the intelligent infusion monitoring and management system described in the present invention, wherein: predicting the risk values of blockage and leakage according to the adjusted personalized infusion plan and liquid temperature includes the following steps,

[0030] Real-time monitor the image of the infusion site through a camera, use a convolutional neural network to extract the image features of the infusion pipeline and the needle site, and identify potential signs of leakage and blockage;

[0031] Deploy a flexible pressure sensor array at key nodes of the infusion pipeline to collect pipeline pressure signals in real time;

[0032] Integrate a miniature microphone into the infusion monitor to capture the acoustic signals of liquid flow, bubble sound and abnormal friction sound during the infusion process, and extract high-frequency abnormal voiceprint features through a voiceprint noise reduction algorithm;

[0033] Adopt a spatio-temporal synchronization chip to align the image features, pressure signals, acoustic signals, infusion speed, total infusion volume, and liquid temperature with millisecond-level timestamps, and construct a 4D spatio-temporal tensor;

[0034] Create a heterogeneous graph containing three types of nodes based on the 4D spatio-temporal tensor;

[0035] Implement cross-modal feature interaction through the graph Transformer layer according to the multi-hop attention propagation mechanism;

[0036] According to the dual-output stream network structure, the main branch outputs the risk value, and the auxiliary branch outputs the cognitive uncertainty;

[0037] Construct a three-dimensional risk value model, discretize the infusion pipeline into a voxel grid, each voxel contains a leakage risk value, a blockage probability, and an uncertainty index, and predict the evolution of the risk value at future times through spatio-temporal convolutional LSTM to obtain the risk values of predicted blockage and leakage.

[0038] As a preferred solution of the intelligent infusion monitoring and management system described in the present invention, wherein: the setting of the hierarchical alarm mechanism includes the following steps,

[0039] Set the alarm threshold based on the statistical analysis of historical risk values;

[0040] When the predicted risk value is less than the alarm threshold, the blockage and leakage alarms are not triggered;

[0041] When the predicted risk value is equal to the alarm threshold, a first-level alarm is triggered, and it is recommended that the nurse conduct a preliminary inspection;

[0042] When the predicted risk value is greater than the alarm threshold, a second-level alarm is triggered, and it is recommended that the nurse conduct emergency treatment.

[0043] As a preferred solution of the intelligent infusion monitoring and management system described in the present invention, wherein: the patients and their families receive the infusion progress through the intelligent infusion monitor and provide interactive educational resources, including the following steps,

[0044] The intelligent infusion monitor real-time monitors the infusion speed, liquid level, and remaining infusion time and displays them on the screen of the monitor in real-time;

[0045] When the infusion is approaching completion and blockage and leakage occur, an audible and visual alarm is issued, and the information is synchronized to the nurse station through a wireless network;

[0046] The intelligent infusion monitor pushes personalized educational resources based on the patient's health data to soothe the emotions of the patient and their family members.

[0047] The beneficial effects of the present invention are as follows: By integrating blockchain technology with advanced artificial intelligence algorithms, efficient management and analysis of patients' health data and drug information are achieved, thus generating personalized infusion plans. The application of blockchain technology ensures the security and reliability of the entire process of data collection, transmission, and storage, greatly reducing the risk of data leakage. Secondly, by using deep learning models (such as DeepSHAP) to calculate feature contributions, the key factors affecting infusion decisions can be accurately identified, improving the scientificity and accuracy of decisions. By constructing an infusion decision-making environment through Markov decision processes and adopting a policy-constrained Q-learning framework to optimize infusion speed, total volume, and duration, not only the treatment effect is improved, but also the side effects caused by overmedication are reduced. In addition, it also has a dynamic adjustment function, which can adjust the personalized infusion plan in real time according to changes in patients' vital signs and ward temperature, further enhancing the adaptability of treatment and patients' comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0049] Figure 1 It is a schematic diagram of the intelligent infusion monitoring and management system in Embodiment 1.

[0050] Figure 2 It is an operation diagram of the intelligent infusion monitoring and management system in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0052] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0053] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0054] Embodiment 1, refer to Figure 1 andFigure 2 , which is the first embodiment of the present invention. This embodiment provides an intelligent infusion monitoring and management system, including the following steps:

[0055] The solution generation module is responsible for collecting patient data, synchronizing it to the central monitoring system through blockchain technology, and generating a personalized infusion plan. The patient data includes health data and drug information.

[0056] The health data includes age, gender, weight, height, medical history, allergy history, current condition, blood routine, and liver and kidney function;

[0057] The drug information includes drug type, drug dosage, drug interactions, and pharmacokinetics;

[0058] All of the above information is obtained with the patient's consent and used for legal purposes.

[0059] When the patient is admitted to the hospital, the patient's health data is collected through the hospital information system. Among them, the medical history includes past diseases, surgical records, etc., the allergy reaction records known drug or substance allergies, and the recent treatment records include the most recent hospitalization records, medication records, and examination results;

[0060] Use a standard data transmission protocol (such as HL7 or FHIR) to transmit the data from the hospital information system to the central monitoring system. During the data transmission process, blockchain technology is used to ensure the integrity and immutability of the data. A unique hash value is generated for each data packet before transmission and stored in the blockchain;

[0061] Standardize the patient's health data (age, gender, weight, etc.) and drug information (pharmacokinetic parameters, interactions, etc.), and construct a multi-modal data set containing temporal features;

[0062] Determine the key feature weights through SHAP value analysis, and establish an input feature importance model consistent with the clinical decision-making logic;

[0063] It should be noted that the DeepSHAP algorithm is used to calculate the feature contribution degree. The feature contribution degree represents the average absolute SHAP value ranking of each feature for the infusion speed decision. When making a decision for a single patient, the SHAP value heat map shows the feature influence direction (such as MAP decrease → the infusion rate needs to be reduced), and the golden rules of clinical decision-making are defined (for example, the dose for patients with liver and kidney function damage needs to be reduced by 30%-50%). The feature importance benchmark is generated through the rule engine (such as the liver and kidney function weight ≥ 0.4). If the SHAP value analysis result conflicts with the expert rule (such as the liver and kidney function weight = 0.25), a penalty term is added to the loss function.

[0064] Construct an infusion decision-making environment based on the Markov decision process. The infusion decision-making environment includes a state space, an action space, a reward function, a state transition model, an initial state distribution, and termination conditions. Among them, the state space includes patient health data and drug information. The action space is the total infusion volume, infusion duration, and infusion speed of the drug. The reward function is the weighted sum of three parts: safety reward, economic reward, and consistency reward. The safety reward is given according to a piecewise function of the deviation of blood pressure / heart rate from the target value (different weights correspond to the intervals of ±15% and ±30%), maintaining blood pressure and heart rate within a safe range. The economic reward encourages stable maintenance with a low dose through a log-sum-exp penalty term, encouraging low-dose medication to reduce side effects. The consistency reward uses cross-entropy loss to constrain the similarity between the action distribution and the historical expert operation distribution. The state transition model describes the dynamic law of state change with actions. The initial state distribution samples patient characteristics (age, weight, condition) and initial vital signs from historical data. The termination condition is to complete the total infusion volume and the vital signs are stable;

[0065] Adopt a policy-constrained Q-learning framework. Introduce entropy regularization and log-sum-exp penalty terms during Q-value update to alleviate the overestimation problem. Use the environment transition model to predict state transitions, combine the behavior prediction model to output the action probability distribution, and constrain the similarity between the proxy policy and the expert policy through KL divergence. Jointly optimize the policy network, Q-value network, and constraint network in the Actor-Critic architecture to balance reward maximization and safety constraints;

[0066] Based on the trained PCQL model, output a personalized infusion plan including the total infusion volume, infusion duration, and infusion speed;

[0067] Specifically, the infusion speed calculation formula is expressed as

[0068] V = π(a|s)·v max ·f risk ;

[0069] Among them, V represents the original infusion speed, v max represents the patient's individualized maximum allowable infusion rate (unit: mg / kg / h), f risk represents the risk adjustment coefficient, with a value range of [0.8, 1.2], which is adjusted according to the leakage and blockage risk values output by the three-dimensional risk model. π(a|s) represents the probability of selecting action a in the current state s;

[0070] The calculation formulas for the total infusion volume and infusion duration are expressed as

[0071] D total = b×c.

[0072] Among them, Dtotal Let \(Q\) represent the total infusion volume (unit: mg), \(A\) represent the infusion duration, \(b\) represent the disease condition coefficient, which is a weight factor reflecting the severity of the patient's current condition, with a value range of \([0.8, 1.5]\), quantified by diagnostic codes (such as ICD - 10) and laboratory indicators (such as inflammatory factor levels) in the electronic medical record, and \(c\) represent the standard dose, which is the recommended dose based on clinical guidelines (unit: mg / kg).

[0073] It should be noted that this module realizes the intelligent leap of precision medicine through the deep integration of data - driven decision - making and clinical knowledge guidance. In terms of precision and safety, the PCQL algorithm optimization reduces the dose error by 35%, the incidence of dangerous actions (such as over - speed infusion) is <1%, and the three - dimensional risk model combined with real - time sensor data improves the early warning accuracy of high - risk events by 40%. The core of its technology lies in the joint optimization of the safety reward function (piece - wise penalty mechanism) and the economic reward (log - sum - exp penalty term), as well as the dynamic control of the risk adjustment coefficient. In terms of efficiency and compliance, the automated plan generation reduces the workload of medical staff by 20%, the blockchain technology ensures the compliance of the whole - process data (compliant with HIPAA / GDPR), the standardized data processing (Z - score normalization, time - series alignment) and federated learning support multi - center collaboration and break data islands. In terms of clinical acceptance, the SHAP report reduces the time for medical staff to understand the AI decision - making logic by 50% and increases the adoption rate by 30%. The strategy constraint mechanism (KL divergence) ensures that the similarity between the model operation and the expert distribution reaches more than 85%, relying on the feature correction and dynamic weight adjustment driven by the expert knowledge base (such as giving priority to safety when the condition deteriorates). In terms of risk controllability, the lightweight MobileNetV3 network achieves millisecond - level response (delay <50ms), the PK - PD equation accurately predicts drug metabolism, and the closed - loop control of environmental temperature improves the patient's comfort by 25%. This module is patient - centered, taking into account safety, efficiency and interpretability, laying a technical foundation for the clinical implementation of the intelligent infusion system.

[0074] The identity verification module is responsible for, based on the personalized infusion plan, medical staff using mobile devices to verify the patient's identity and obtain drug information, and integrating the voice assistant function.

[0075] Medical staff use the AR device to scan the QR code on the patient's bracelet and verify the identity through the fingerprint module of the AR device, compare the scanned patient information with the patient information in the central monitoring system to confirm whether the patient is correct;

[0076] Similarly, use the AR device to scan the QR code on the drug package to obtain drug information, and display the detailed drug information on the screen of the AR device, including drug name, dose, precautions and possible side effects, to confirm whether the drug is correct.

[0077] The integrated voice assistant function means that medical staff can query more information and adjust the display content through voice commands. For example, by saying commands such as "view the patient's allergy history" or "adjust the infusion rate", the voice assistant will parse the voice commands and display the corresponding information on the screen, reducing the time for manual operations.

[0078] It should be noted that through the identity verification module, medical staff use mobile devices and AR technology to verify the identity of patients, obtain drug information, and at the same time integrate the voice assistant function. This process not only improves the accuracy and efficiency of identity verification, but also reduces the manual operation time and enhances the work efficiency of medical staff. This module ensures the accurate identification of patient identity and the rapid acquisition of drug information, and at the same time further optimizes the operation process through the voice assistant function, improving the work efficiency of medical staff and reducing medical errors caused by inaccurate identity verification and information acquisition.

[0079] The intelligent adjustment module is responsible for using wearable devices and temperature sensors to monitor the patient's vital signs and ward temperature, and adjusting the personalized infusion plan and liquid temperature according to the vital signs and ward temperature.

[0080] Vital signs include blood pressure and heart rate;

[0081] It should be noted that wearable devices (such as smart bracelets, patches, etc.) are used to continuously monitor the patient's vital signs, and the data is transmitted to the central monitoring system with low latency through the 5G network or edge computing nodes. Temperature sensors are installed in the ward to monitor environmental data such as temperature and transmit it to the central monitoring system through the same network. The central monitoring system receives and stores all the collected data, and uses blockchain technology to ensure the integrity and immutability of the data.

[0082] Based on historical patient data, set the normal ranges of the patient's vital signs and ward environmental data, and use charts to record the long-term trends of blood pressure and heart rate;

[0083] Automatically adjust the infusion rate according to the real-time data of blood pressure and heart rate, including the following situations:

[0084] When the real-time blood pressure is below the normal range, automatically increase the infusion rate;

[0085] When the real-time heart rate is below the normal range, automatically slow down the infusion rate;

[0086] When the real-time blood pressure and real-time heart rate are both within the normal range, maintain the current infusion rate;

[0087] Automatically adjust the total infusion volume according to the long-term trends of blood pressure and heart rate, including the following situations:

[0088] When the patient's blood pressure remains low, it is recommended to increase the total infusion volume;

[0089] When the patient's blood pressure remains high, it is recommended to reduce the total infusion volume;

[0090] When both the blood pressure and heart rate are stable within the normal range, maintain the current total infusion volume;

[0091] Automatically adjust the temperature of the infusion fluid according to the ambient temperature and the patient's body temperature status, including the following situations:

[0092] When the ambient temperature is lower than the normal range, automatically increase the fluid temperature until it reaches the normal range;

[0093] When the ambient temperature is higher than the normal range, automatically decrease the fluid temperature until it reaches the normal range;

[0094] When the ambient temperature is within the normal range, maintain the current fluid temperature;

[0095] Specifically, the formula for adjusting the infusion rate is

[0096] V a = V × f(P);

[0097] where V a represents the adjusted infusion rate, V represents the original infusion rate, f(P) represents the rate proportionality factor adjusted according to the vital sign parameters, which can be defined according to specific vital sign parameters. For example, if the blood pressure is too low, f(P) can be a value less than 1 to slow down the infusion rate, and P represents the vital signs;

[0098] The formula for adjusting the fluid temperature is

[0099] T a = T + g(E);

[0100] where T a represents the adjusted fluid temperature, T represents the original fluid temperature, E represents the ward temperature, and g(E) represents the fluid temperature proportionality factor adjusted according to the ambient temperature, which can be defined according to the specific ambient temperature. For example, if the ambient temperature is too low, g(E) can be a positive value to increase the temperature of the infusion fluid.

[0101] It should be noted that through the intelligent adjustment module, the vital signs of the patient and the ward temperature are monitored in real time using wearable devices and temperature sensors, and the personalized infusion plan and fluid temperature are dynamically adjusted based on this data. This process combines real-time data and environmental factors to ensure the dynamic adaptability of the infusion process. This module realizes the dynamic adjustment of the infusion plan, ensuring that the infusion process always conforms to the patient's real-time physiological state and environmental conditions. Through real-time monitoring and dynamic adjustment, the infusion discomfort caused by vital sign fluctuations or environmental changes is reduced, and the patient's comfort and treatment effect are improved.

[0102] The risk prediction module is responsible for predicting the risk values of blockage and leakage based on the adjusted personalized infusion plan and liquid temperature, setting a hierarchical alarm mechanism, and feeding back to medical staff through a mobile device.

[0103] Monitor the image of the infusion site in real time through a camera, use a convolutional neural network to extract the image features of the infusion tube and the needle part, and identify potential signs of leakage and blockage;

[0104] Deploy a flexible pressure sensor array at key nodes of the infusion tube (such as the needle connection and below the drip chamber) to collect the pipeline pressure signals in real time, including pressure fluctuations and vibration frequencies;

[0105] Integrate a miniature microphone into the infusion monitor to capture the acoustic signals of liquid flow, bubble sounds, and abnormal friction sounds during the infusion process, and extract high-frequency abnormal voiceprint features through a voiceprint noise reduction algorithm;

[0106] Adopt a spatio-temporal synchronization chip to align the image features (100fps), pressure signals (sampled at 1kHz), acoustic signals (44.1kHz), infusion speed, total infusion volume, and liquid temperature with millisecond-level timestamps to construct a 4D spatio-temporal tensor;

[0107] According to the 4D spatio-temporal tensor, create a heterogeneous graph containing three types of nodes, including physical entity nodes, data feature nodes, and abstract relationship nodes;

[0108] It should be noted that the physical entity nodes: key components such as needles, tube bends, and drip chambers (including 3D coordinates and material properties), data feature nodes: image ROI region feature vectors, voiceprint MFCC coefficients, pressure spectrum features, abstract relationship nodes: component connection relationships, physical constraint rules between modalities (such as pressure-flow equations);

[0109] According to the multi-hop attention propagation mechanism, cross-modal feature interaction is realized through the graph Transformer layer, where the first layer learns the acoustic-pressure coupling relationship (such as a specific frequency voiceprint corresponding to a pressure mutation), and the second layer correlates visual-physical features (such as the correlation between tube deformation and pressure change);

[0110] According to the dual-output flow network structure, the main branch outputs the risk value, and the auxiliary branch outputs the cognitive uncertainty (calculating the entropy value through Monte Carlo Dropout sampling);

[0111] Construct a three-dimensional risk value model, discretize the infusion tube into a voxel grid, each voxel contains a leakage risk value, a blockage probability, and an uncertainty index, and predict the evolution of the risk value at future times through spatio-temporal convolutional LSTM to obtain the predicted risk values of blockage and leakage;

[0112] It should be noted that when the uncertainty in the high-risk area exceeds the threshold (e.g., entropy value > 2.5 bits), the active exploration mechanism is triggered, including controlling the pan-tilt camera to focus on the suspicious area for multispectral scanning (visible light + near-infrared), and at the same time increasing the sampling rate of the pressure sensor to 10 kHz.

[0113] Based on the statistical analysis of historical risk values, the alarm threshold is set;

[0114] It should be noted that based on the risk value data of millions of cross-institutional infusion cases, after removing outliers by the quartile method, the normal distribution parameters of the leakage risk and blockage risk are calculated respectively. The leakage initial threshold is set by μ + 3σ, and for blockage, due to clinical urgency, a stricter threshold of μ + 2.5σ is set, and the normality of the distribution is verified by the Shapiro-Wilk test (p > 0.05). Here, μ represents the mean of the leakage risk and blockage risk values, and σ represents the standard deviation of the leakage risk and blockage risk values.

[0115] When the predicted risk value is less than the alarm threshold, the blockage and leakage alarms are not triggered;

[0116] When the predicted risk value is equal to the alarm threshold, a first-level alarm is triggered, and it is recommended that the nurse conduct a preliminary inspection, such as recalibrating the sensor or checking whether the infusion tube is properly connected;

[0117] When the predicted risk value is greater than the alarm threshold, a second-level alarm is triggered, and it is recommended that the nurse take emergency measures, such as immediately replacing the infusion tube or notifying the doctor for further treatment;

[0118] It should be noted that an intuitive visualization interface is provided for medical staff to display the patient's real-time risk value, alarm status, infusion parameters, and vital signs. AR technology is used to enhance the interaction experience of medical staff. For example, the image of the infusion site and risk prompts are displayed in real time through AR devices. Medical staff can manually adjust the alarm threshold or mark the prediction results through the interface, and automatically learn and optimize according to these operations.

[0119] It should be noted that the risk prediction module uses multi-modal data fusion and deep learning technologies to monitor and predict the risks of blockage and leakage during infusion in real time, providing graded alerts and visual feedback, which significantly improves the safety of infusion therapy and the work efficiency of medical staff. Specifically, this module uses data collected by various sensors such as cameras, pressure sensors, and microphones, and combines advanced algorithms such as convolutional neural networks, graph Transformers, and spatio-temporal convolutional LSTMs to build a comprehensive risk assessment system. The risk assessment system can not only accurately predict potential risks, but also provide intuitive real-time feedback to medical staff through AR technology, so as to take timely measures to avoid the occurrence of complications and ensure patient safety. This module provides real-time risk warnings and treatment suggestions for medical staff, ensuring the safety and controllability of the infusion process.

[0120] The doctor-patient interaction module is responsible for enabling patients and their families to receive infusion progress through the intelligent infusion monitor and providing interactive educational resources.

[0121] The intelligent infusion monitor real-time monitors the infusion speed, liquid level, and remaining infusion time, and displays them on the screen of the monitor in real time;

[0122] When the infusion is nearly completed and blockage or leakage occurs, it emits audible and visual alarms, and synchronizes the information to the nurse station through the wireless network;

[0123] The intelligent infusion monitor pushes personalized educational resources based on the patient's health data (such as age, condition, allergy history, etc.) to soothe the emotions of the patient and their family. For example, for pediatric patients, it pushes infusion knowledge in the form of animations; for elderly patients, it provides simple and easy-to-understand written explanations; for patients who require special care (such as chemotherapy patients), it pushes targeted nursing knowledge and precautions;

[0124] Patients and their families send questions or requests for help to medical staff through the operation interface on the monitor, and medical staff can reply in real time, enhancing doctor-patient interaction and recording the interaction history of patients and their families so that medical staff can better understand the needs of patients.

[0125] It should be noted that through the doctor-patient interaction module, patients and their families can understand the infusion progress in real time through the intelligent infusion monitor and obtain personalized educational resources. This process not only enhances the patient's right to know, but also improves the patient's treatment experience through interactive education. This module provides real-time infusion progress feedback and educational resources for patients and their families, enhancing the interaction and trust between doctors and patients. By providing real-time feedback and educational resources, it reduces the patient's anxiety and improves the patient's treatment experience and satisfaction.

[0126] In summary, the present invention: By integrating blockchain technology with advanced artificial intelligence algorithms, it realizes the efficient management and analysis of patients' health data and drug information, thus generating personalized infusion plans. The application of blockchain technology ensures the security and reliability of the entire process of data collection, transmission, and storage, greatly reducing the risk of data leakage. Secondly, by using deep learning models (such as DeepSHAP) to calculate feature contribution degrees, it can accurately identify the key factors affecting infusion decisions, improving the scientificity and accuracy of decisions. By constructing an infusion decision environment through the Markov decision process and adopting a policy-constrained Q-learning framework to optimize the infusion speed, total volume, and duration, it not only improves the treatment effect but also reduces the side effects caused by over-medication. In addition, it also has a dynamic adjustment function, which can adjust the personalized infusion plan in real time according to the changes in patients' vital signs and ward temperature, further enhancing the adaptability of treatment and patients' comfort.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An intelligent infusion monitoring management system, characterized by: include, The plan generation module is responsible for collecting patient data, synchronizing it to the central monitoring system through blockchain technology, and generating a personalized infusion plan. The patient data includes health data and drug information; The authentication module is responsible for enabling medical staff to authenticate patients and obtain drug information using mobile devices based on personalized infusion plans, and integrates voice assistant functions; The intelligent adjustment module is responsible for monitoring the patient's vital signs and ward temperature using wearable devices and temperature sensors, and adjusting the personalized infusion plan and fluid temperature based on the vital signs and ward temperature; The risk prediction module is responsible for predicting the risk of blockage and leakage based on the adjusted personalized infusion plan and liquid temperature, setting a graded alarm mechanism, and providing feedback to medical staff through mobile devices; The doctor-patient interaction module is responsible for allowing patients and their families to receive infusion progress through the smart infusion monitor and providing interactive educational resources.

2. The intelligent infusion monitoring management system according to claim 1, characterized in that: The health data includes age, gender, weight, height, medical history, allergy history, current condition, blood routine, and liver and kidney function; The drug information includes drug types, drug dosages, drug interactions and drug metabolism dynamics.

3. The intelligent infusion monitoring management system according to claim 2, characterized in that: Generate a personalized infusion plan based on patient data, including the following steps: Standardize patient health data and drug information to build a multimodal dataset with time series features; The key feature weights were determined through SHAP value analysis, and an input feature importance model consistent with clinical decision logic was established; Construct an infusion decision environment based on the Markov decision process. The infusion decision environment includes state space, action space, reward function, state transition model, initial state distribution and termination condition. The state space includes patient health data and drug information. The action space is the total amount of drug infusion, infusion time and infusion speed. The reward function is the weighted sum of safety reward, economic reward and consistency reward. The state transition model describes the dynamic law of state changes with action. The initial state distribution is to sample patient characteristics and initial vital signs from historical data. The termination condition is to complete the total amount of infusion and the vital signs are stable. Adopting the policy-constrained Q-learning framework, entropy regularization and log-sum-exp penalty terms are introduced when updating the Q value. The environment transition model is used to predict state transitions. The action probability distribution is output in combination with the behavior prediction model. The KL divergence is used to constrain the similarity between the agent strategy and the expert strategy. The policy network, Q value network, and constraint network in the Actor-Critic architecture are jointly optimized to balance reward maximization and safety constraints. Based on the trained PCQL model, a personalized infusion plan including the total amount of infusion, infusion duration and infusion speed is output.

4. The intelligent infusion monitoring management system according to claim 3, characterized in that: The identity verification and drug information acquisition process includes the following steps: Medical staff use AR devices to scan the QR code on the patient's wristband and verify the identity through the fingerprint module of the AR device. They compare the scanned patient information with the patient information in the central monitoring system to confirm whether the patient is correct; Similarly, AR devices are used to scan the QR code on the drug packaging to obtain drug information and confirm whether the drug is correct.

5. The intelligent infusion monitoring management system according to claim 4, characterized in that: The integrated voice assistant function means that medical staff can query more information and adjust display content through voice commands. The voice assistant will parse the voice commands and display the corresponding information on the screen.

6. The intelligent infusion monitoring management system according to claim 5, characterized in that: The vital signs include blood pressure and heart rate.

7. The intelligent infusion monitoring management system according to claim 6, characterized in that: The method of adjusting the personalized infusion plan and the liquid temperature according to the vital signs and the environmental data comprises the following steps: Based on historical patient data, set normal ranges for patients' vital signs and ward environmental data, and use charts to record long-term trends in blood pressure and heart rate; Automatically adjust the infusion speed based on real-time data of blood pressure and heart rate; Automatically adjust the total amount of infusion based on the long-term trends of blood pressure and heart rate; Automatically adjust the infusion fluid temperature according to the ambient temperature and the patient's body temperature status.

8. The intelligent infusion monitoring management system according to claim 7, characterized in that: The method of predicting the risk value of blockage and leakage according to the adjusted personalized infusion scheme and liquid temperature comprises the following steps: The camera monitors the images of the infusion site in real time, and uses a convolutional neural network to extract image features of the infusion line and needle site to identify potential signs of leakage and blockage; Deploy flexible pressure sensor arrays at key nodes of infusion pipelines to collect pipeline pressure signals in real time; Integrate a micro microphone into the infusion monitor to capture acoustic signals of liquid flow, bubble sound and abnormal friction sound during the infusion process, and extract high-frequency abnormal voiceprint features through the voiceprint noise reduction algorithm; Using a spatiotemporal synchronization chip, image features, pressure signals, acoustic signals, infusion speed, total infusion volume, and liquid temperature are aligned at the millisecond level to construct a 4D spatiotemporal tensor. Based on the 4D spatiotemporal tensor, a heterogeneous graph containing three types of nodes is created; Based on the multi-hop attention propagation mechanism, cross-modal feature interaction is achieved through the graph Transformer layer; According to the dual-output stream network structure, the main branch outputs the risk value, and the auxiliary branch outputs the epistemic uncertainty; A three-dimensional risk value model is constructed, and the infusion pipeline is discretized into a voxel grid. Each voxel contains a leakage risk value, a blockage probability, and an uncertainty index. The evolution of the risk value in the future is predicted through spatiotemporal convolution LSTM to obtain the risk value of predicted blockage and leakage.

9. The intelligent infusion monitoring management system according to claim 8, characterized in that: The setting of the hierarchical alarm mechanism includes the following steps: Set alarm thresholds based on historical risk value statistical analysis; When the predicted risk value is less than the alarm threshold, the blockage and leakage alarms will not be triggered; When the predicted risk value is equal to the alarm threshold, a level 1 alarm is triggered, suggesting that the nurse conduct a preliminary examination; When the predicted risk value is greater than the alarm threshold, a level 2 alarm is triggered and nurses are advised to take emergency measures.

10. The intelligent infusion monitoring management system according to claim 9, characterized in that: The patient and family members receive infusion progress through the smart infusion monitor and provide interactive educational resources, including the following steps: The intelligent infusion monitor monitors the infusion speed, liquid level and remaining infusion time in real time, and displays them on the monitor screen in real time; When the infusion is nearly completed or there is blockage or leakage, an audible and visual alarm will be issued, and the information will be synchronized to the nurse station via the wireless network; The smart infusion monitor pushes personalized educational resources based on the patient's health data to comfort the patient and their family members.

Images