Intelligent pain relieving pump dosage adjusting system driven by pain feedback

Abstract

The invention provides a pain feedback driven intelligent analgesic pump dosage adjusting system. The intelligent pain relieving pump dosage adjusting system driven by pain feedback comprises a pain sensor module, a control unit, a medicine pump and a feedback adjusting unit, and the pain sensor module is based on the multi-mode sensing technology and can collect various biological signals such as skin resistance, electromyographic signals, heart rate variability and skin temperature at the same time; the pain degree of the patient is calculated through a fusion algorithm, and comprehensive assessment of pain feedback is achieved. According to the intelligent pain relieving pump dosage adjusting system driven by pain feedback, accurate assessment of pain degrees of different patients is achieved through multi-mode sensor fusion and an individualized pain sensing model. According to the system, a fusion algorithm of multiple biological signals is adopted, and data are collected through a multi-mode sensor of skin resistance, electromyographic signals, heart rate variability and skin temperature.

Description

Technical Field

[0001] The present invention relates to the technical field of dosage adjustment of intelligent analgesic pumps, and in particular to an intelligent analgesic pump dosage adjustment system driven by pain feedback. Background Art

[0002] A pain feedback-driven intelligent analgesic pump dosage adjustment system consists of a pain sensor module, a control unit, a drug pump, and a feedback adjustment unit. The system monitors the patient's pain level in real time through the pain sensor and transmits the data to the control unit. The control unit determines the patient's pain level based on the preset pain threshold and algorithm, and automatically adjusts the infusion rate of the drug pump to ensure that the patient receives a timely and appropriate analgesic dose. In addition, the feedback adjustment unit dynamically adjusts the dose in response to the patient's pain changes, achieving personalized dosage management and avoiding the problem of inflexible dosage in traditional analgesic pumps.

[0003] The defects of this system are mainly reflected in the accuracy and adaptability of sensors and algorithms. The pain sensor may not be fully applicable to the pain feedback of different patients, resulting in deviations in the detection results of pain levels and affecting the accuracy of dose adjustment. The algorithm is not sensitive enough to sudden severe pain or chronic pain, which may lead to delayed drug infusion and failure to relieve pain in time. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a pain feedback-driven intelligent analgesic pump dosage adjustment system, which solves the problem that the pain sensor may not be fully applicable to the pain feedback of different patients, resulting in deviations in the detection results of the pain degree; the algorithm is not sensitive enough to sudden severe pain or chronic pain, which may lead to delayed drug infusion and failure to relieve pain in time.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a pain feedback driven intelligent analgesic pump dosage adjustment system, comprising:

[0006] A pain sensor module, a control unit, a drug pump and a feedback adjustment unit. The pain sensor module is based on multimodal sensing technology and can simultaneously collect multiple biological signals such as skin resistance, electromyographic signals, heart rate variability and skin temperature, calculate the patient's pain level through a fusion algorithm, and achieve a comprehensive evaluation of pain feedback;

[0007] The control unit has multiple algorithm models embedded in it, including an individualized pain perception model and a pain fluctuation response algorithm, which can update algorithm parameters based on patient historical data and real-time feedback to improve the applicability of pain detection for different patients, and includes a multi-level response mechanism to control the output of the drug pump according to the pain level;

[0008] The drug pump adopts a precision control structure driven by a micro-stepping motor, which can achieve micro-level drug infusion adjustment to achieve accurate dosage control for different pain levels;

[0009] The feedback adjustment unit is based on a feedback optimization algorithm, and performs secondary detection of the patient's pain feedback signal after the drug pump is injected, and adjusts the algorithm parameters of the control unit to achieve adaptive optimization of pain detection and dosage adjustment, so as to reduce dosage deviation caused by sensing errors;

[0010] The system further comprises:

[0011] Adaptive pain recognition module, which uses machine learning algorithms to generate individualized pain perception models and dynamically adjusts algorithm weights based on individual patient characteristics to improve the accuracy of pain recognition;

[0012] The sudden and chronic pain graded regulation module includes a sudden pain response model and a chronic pain relief model. Different analgesic doses are calculated based on the characteristics of each type of pain, and the dynamic controller is used to achieve refined control of the dose output.

[0013] The remote monitoring module allows medical staff to view the patient's pain data and dosage adjustment status in real time through a remote connection, and to make parameter adjustments or manual interventions when necessary.

[0014] Preferably, the pain sensor module performs weighted processing on skin resistance, electromyographic signals, heart rate variability, and skin temperature signals based on a multimodal sensor fusion algorithm to achieve a refined assessment of the pain level. The adaptive pain recognition module uses a gradient enhanced decision tree model in machine learning to perform multi-parameter input training on the patient's pain data to improve the accuracy of the pain feedback model.

[0015] Preferably, the sudden pain response model adopts formula D t =α×ΔP t +β×R t , where D t Indicates the drug adjustment amount of breakthrough pain, P t is the pain feedback signal value, R t is the rate of change of pain level, α and β are adjustment coefficients, and the weights of α and β are adjusted through the secondary detection data to adapt to the patient's pain response.

[0016] Preferably, the chronic pain relief model smoothes the pain feedback signal by a moving average algorithm, and its chronic pain dose adjustment amount D c The calculation formula is Wherein γ is the adjustment coefficient, and pain relief is achieved by weighting historical pain data. The dynamic controller adopts a fuzzy control algorithm to adjust the frequency and rate of drug infusion according to the fluctuation and uncertainty of the pain feedback signal to achieve sensitive response.

[0017] Preferably, the feedback adjustment unit performs error analysis on the pain feedback signal through a feedback optimization algorithm, adjusts the weight parameters in the control unit, and continuously optimizes the pain recognition accuracy.

[0018] Preferably, the control unit includes a sudden pain prediction module, which predicts the trend of sudden pain based on a time series algorithm to provide early warning and initiate drug adjustment. The sudden pain prediction module uses an autoregressive moving average model to predict pain signal fluctuations and establishes a pain trend prediction model in combination with the patient's individualized data.

[0019] Preferably, the system has a built-in data recording module that can store patient pain feedback data, analgesic dosage adjustment process and other information to facilitate subsequent personalized program adjustment and data analysis. The remote monitoring module provides doctors with patient pain curves and dosage change trends in real time, and has an abnormal reminder function, which sends out a reminder signal when sudden pain fluctuations are detected.

[0020] Preferably, the pain feedback-driven intelligent analgesic pump dosage adjustment system supports flexible switching between manual and automatic modes. In manual mode, the doctor adjusts the drug infusion rate and parameters according to the patient's actual situation. The individualized pain perception model is dynamically adjusted based on the patient's previous pain records, and the pain model is automatically optimized in combination with the patient's physiological data.

[0021] The present invention provides a pain feedback-driven intelligent analgesic pump dosage adjustment system. It has the following beneficial effects: through multimodal sensor fusion and individualized pain perception model, accurate assessment of the pain levels of different patients is achieved. The system adopts a fusion algorithm of multiple biological signals, collects data through multimodal sensors of skin resistance, electromyography, heart rate variability and skin temperature, and generates a personalized pain model through a machine learning algorithm. It can dynamically adjust the algorithm parameters in real time to adapt the system to the pain feedback characteristics of different patients, thereby effectively solving the problem of insufficient adaptability of pain sensors in the prior art leading to deviations in detection results. In addition, the system also includes hierarchical adjustment modules for sudden and chronic pain, which respectively respond to the characteristics of severe pain and slow pain, provide refined dosage control, and greatly improve the immediacy and stability of drug infusion.

[0022] The feedback adjustment unit realizes adaptive optimization of pain detection and dosage adjustment through secondary detection and optimization algorithm, combined with adaptive control and fuzzy control, and has built-in remote monitoring and data recording functions, so that medical staff can monitor the patient's pain curve and dosage change trend in real time, and make parameter adjustments or manual interventions when necessary, which significantly improves the safety and effectiveness of the system. The system further supports the switching between manual and automatic modes, as well as the prediction and early warning functions of sudden pain, effectively solving the problem of the existing algorithm's insensitivity to sudden severe pain and chronic pain, and realizing fine management and personalized treatment of pain. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Embodiment 1

[0026] like Figure 1 As shown, an embodiment of the present invention provides a pain feedback driven intelligent analgesic pump dosage adjustment system, including a pain sensor module, a control unit, a drug pump and a feedback adjustment unit. The pain sensor module is based on multimodal sensing technology and can simultaneously collect multiple biological signals such as skin resistance, electromyographic signals, heart rate variability and skin temperature, calculate the patient's pain level through a fusion algorithm, and achieve a comprehensive evaluation of pain feedback. The pain sensor module performs weighted processing on skin resistance, electromyographic signals, heart rate variability and skin temperature signals based on a multimodal sensor fusion algorithm to achieve a refined evaluation of the pain level. The adaptive pain recognition module adopts a gradient enhancement decision tree model in machine learning to perform multi-parameter input training on the patient's pain data to improve the accuracy of the pain feedback model. The feedback adjustment unit performs error analysis on the pain feedback signal through a feedback optimization algorithm, adjusts the weight parameters in the control unit, and continuously optimizes the pain recognition accuracy.

[0027] The control unit has multiple built-in algorithm models, including individualized pain perception model and pain fluctuation response algorithm. It can update algorithm parameters according to patient historical data and real-time feedback to improve the applicability of pain detection for different patients. It also includes a multi-level response mechanism to control the output of the drug pump according to the pain level. The sudden pain response model adopts formula D t =α×ΔP t+β×R t , where D t Indicates the drug adjustment amount of breakthrough pain, P t is the pain feedback signal value, R t is the rate of change of pain level, α and β are adjustment coefficients, and the weights of α and β are adjusted through secondary detection data to adapt to the patient's pain response. The control unit includes a sudden pain prediction module, which predicts the trend of sudden pain based on the time series algorithm to give early warning and start drug adjustment. The sudden pain prediction module uses an autoregressive moving average model to predict the fluctuation of pain signals, and establishes a pain trend prediction model in combination with the patient's individualized data;

[0028] The drug pump adopts a precision control structure driven by a micro-stepping motor, which can achieve micro-level drug infusion adjustment to achieve accurate dosage control for different pain levels;

[0029] The feedback adjustment unit is based on the feedback optimization algorithm. It performs secondary detection on the patient's pain feedback signal after the drug pump is injected and adjusts the algorithm parameters of the control unit to achieve adaptive optimization of pain detection and dosage adjustment, so as to reduce the dosage deviation caused by the sensor error.

[0030] The system also includes:

[0031] Adaptive pain recognition module, which uses machine learning algorithms to generate individualized pain perception models and dynamically adjusts algorithm weights based on individual patient characteristics to improve the accuracy of pain recognition;

[0032] The sudden and chronic pain graded regulation module includes a sudden pain response model and a chronic pain relief model. Different analgesic doses are calculated based on the characteristics of each type of pain, and the dose output is finely controlled through a dynamic controller. The chronic pain relief model smoothes the pain feedback signal through a moving average algorithm, and its chronic pain dose adjustment amount D c The calculation formula is Where γ is the adjustment coefficient, pain relief is achieved by weighting historical pain data, and the dynamic controller uses a fuzzy control algorithm to adjust the frequency and rate of drug infusion according to the fluctuation and uncertainty of the pain feedback signal to achieve sensitive response;

[0033] The remote monitoring module allows medical staff to view the patient's pain data and dosage adjustment in real time through a remote connection, and can adjust parameters or intervene manually when necessary. The system has a built-in data recording module that can store patient pain feedback data, analgesic dosage adjustment process and other information to facilitate subsequent personalized program adjustment and data analysis. The remote monitoring module provides doctors with patients' pain curves and dosage change trends in real time, and has an abnormal reminder function, which sends a reminder signal when sudden pain fluctuations are detected. The pain feedback-driven intelligent analgesic pump dosage adjustment system supports flexible switching between manual and automatic modes. Doctors adjust the drug infusion rate and parameters according to the actual situation of the patient in manual mode. The individualized pain perception model is dynamically adjusted based on the patient's previous pain records, and the pain model is automatically optimized in combination with the patient's physiological data. The system remote monitoring module supports two-way data transmission. The doctor can transmit adjustment suggestions in real time based on the patient's feedback information and provide personalized parameter recommendation solutions. The patient can receive and present the doctor's feedback and adjustment information, and patients and medical staff can interact in real time. This module integrates distributed data storage technology based on blockchain to ensure the security of patient privacy data while improving the stability of the system and the integrity of data records.

[0034] Embodiment 2:

[0035] In this embodiment, the intelligent analgesic pump dosage adjustment system driven by pain feedback further introduces an environmental factor impact module to comprehensively analyze the impact of the patient's environmental factors on pain perception, thereby improving the accuracy of pain identification and system adaptability.

[0036] This embodiment adds an environmental factor sensing module to the original system structure. The module includes environmental sensors such as air pressure, temperature, humidity, and noise, and transmits environmental data to the control unit in real time through the wireless communication module.

[0037] Environmental factors collection and analysis:

[0038] The environmental factor sensing module collects data such as air pressure, temperature, humidity and noise of the patient's environment in real time through multiple sensors.

[0039] The environmental factor assessment algorithm in the control unit analyzes the collected environmental data and evaluates its impact on the patient's pain perception through a statistical model. The patient's pain feedback data is weighted according to the environmental data to calibrate the pain fluctuations caused by environmental changes and further refine the pain assessment.

[0040] Environmental factors adjustment plan:

[0041] When the system detects significant changes in environmental factors, it automatically activates the environmental adjustment reminder function to prompt medical staff or patients to adjust environmental parameters to reduce interference with pain perception.

[0042] If the impact of environmental changes on pain levels reaches a preset threshold, the system automatically and dynamically corrects the pain feedback signal and adjusts the infusion frequency and dosage of the drug pump to ensure the stability and continuity of pain management.

[0043] Dynamic adjustment of individualized pain response:

[0044] The individualized pain perception model in the control unit further integrates the environmental factor data processing mechanism in this embodiment. When environmental factors change, the system adjusts the relevant parameters in the pain perception model according to the patient's historical data and real-time feedback to ensure that the patient's pain recognition is dynamically adapted to the environment.

[0045] Data recording and analysis:

[0046] The system has added the collection and recording of environmental factors to the built-in data recording module. By comparing pain feedback data and environmental factor data, it forms a personalized environmental response file for the patient, providing support for subsequent personalized adjustment plans.

[0047] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A pain feedback driven intelligent analgesic pump dosage adjustment system, characterized in that: include: A pain sensor module, a control unit, a drug pump and a feedback adjustment unit. The pain sensor module is based on multimodal sensing technology and can simultaneously collect multiple biological signals such as skin resistance, electromyographic signals, heart rate variability and skin temperature, calculate the patient's pain level through a fusion algorithm, and achieve a comprehensive evaluation of pain feedback; The control unit has multiple algorithm models embedded in it, including an individualized pain perception model and a pain fluctuation response algorithm, which can update algorithm parameters based on patient historical data and real-time feedback to improve the applicability of pain detection for different patients, and includes a multi-level response mechanism to control the output of the drug pump according to the pain level; The drug pump adopts a precision control structure driven by a micro-stepping motor, which can achieve micro-level drug infusion adjustment to achieve accurate dosage control for different pain levels; The feedback adjustment unit is based on a feedback optimization algorithm, and performs secondary detection of the patient's pain feedback signal after the drug pump is injected, and adjusts the algorithm parameters of the control unit to achieve adaptive optimization of pain detection and dosage adjustment, so as to reduce dosage deviation caused by sensing errors; The system further comprises: Adaptive pain recognition module, which uses machine learning algorithms to generate individualized pain perception models and dynamically adjusts algorithm weights based on individual patient characteristics to improve the accuracy of pain recognition; The sudden and chronic pain graded regulation module includes a sudden pain response model and a chronic pain relief model. Different analgesic doses are calculated based on the characteristics of each type of pain, and the dynamic controller is used to achieve refined control of the dose output. The remote monitoring module allows medical staff to view the patient's pain data and dosage adjustment status in real time through a remote connection, and to make parameter adjustments or manual interventions when necessary.

2. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The pain sensor module performs weighted processing on skin resistance, electromyographic signals, heart rate variability, and skin temperature signals based on a multimodal sensor fusion algorithm to achieve a refined assessment of the pain level. The adaptive pain recognition module uses a gradient enhancement decision tree model in machine learning to perform multi-parameter input training on the patient's pain data to improve the accuracy of the pain feedback model.

3. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The sudden pain response model uses the formula D t =α×ΔP t +β×R t , where D t Indicates the drug adjustment amount of breakthrough pain, P t is the pain feedback signal value, R t is the rate of change of pain level, α and β are adjustment coefficients, and the weights of α and β are adjusted through the secondary detection data to adapt to the patient's pain response.

4. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The chronic pain relief model smoothes the pain feedback signal by a moving average algorithm, and its chronic pain dose adjustment amount D c The calculation formula is Wherein γ is the adjustment coefficient, and pain relief is achieved by weighting historical pain data. The dynamic controller adopts a fuzzy control algorithm to adjust the frequency and rate of drug infusion according to the fluctuation and uncertainty of the pain feedback signal to achieve sensitive response.

5. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The feedback adjustment unit performs error analysis on the pain feedback signal through a feedback optimization algorithm, adjusts the weight parameters in the control unit, and continuously optimizes the pain recognition accuracy.

6. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The control unit includes a sudden pain prediction module, which predicts the trend of sudden pain based on a time series algorithm to provide early warning and initiate drug adjustment. The sudden pain prediction module uses an autoregressive moving average model to predict pain signal fluctuations and establishes a pain trend prediction model in combination with patient individualized data.

7. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The system has a built-in data recording module that can store patient pain feedback data, analgesic dosage adjustment process and other information to facilitate subsequent personalized program adjustment and data analysis. The remote monitoring module provides doctors with patient pain curves and dosage change trends in real time, and has an abnormal reminder function, which sends out a reminder signal when sudden pain fluctuations are detected.

8. The pain feedback driven intelligent analgesic pump dosage adjustment system according to claim 1, characterized in that: The pain feedback-driven intelligent analgesic pump dosage adjustment system supports flexible switching between manual and automatic modes. In manual mode, doctors adjust the drug infusion rate and parameters according to the actual conditions of the patient. The individualized pain perception model is dynamically adjusted based on the patient's previous pain records, and the pain model is automatically optimized in combination with the patient's physiological data.

Images