Intelligent infusion adjusting system and method for infusion medicine in operation

Abstract

The invention discloses an intelligent infusion adjusting system and method for infusion medicine in an operation, and relates to the technical field of intelligent medical treatment. Comprising the following steps: generating corresponding medicine information, breathing state information, hemoglobin information and blood pressure information through a signal acquisition module, obtaining a medical history of a user by utilizing a cloud platform module, preprocessing collected data, eliminating error data, judging the medicine information as a first parameter, and outputting the first parameter. Judging the anesthesia degree of the patient according to the breathing state information of the patient as a second parameter, constructing a feature calculation model, judging bleeding information according to hemoglobin information and the medical history of the user as a third parameter, and generating a blood pressure signal according to a blood pressure standard threshold value and the blood pressure information of the user as a fourth parameter; the medicine infusion condition is comprehensively judged according to the first parameter, the second parameter, the third parameter and the fourth parameter, an infusion signal is formed, and the intelligent infusion module adjusts the medicine infusion rate of a patient according to the infusion signal and adjusts the intraoperative vasoactive medicine. Accurate infusion adjustment of the vasoactive medicine in the operation is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent medical treatment, and particularly relates to an intelligent infusion regulation system and method for infusing drugs during surgery. Background Art

[0002] When injecting drugs, the requirements for drug injection accuracy vary according to different drug types and patient conditions. Sometimes, the requirements for injection accuracy are very high. For example, the booster drugs or cardiac stimulants used to regulate blood pressure in shock therapy must be precisely controlled. Therefore, when infusing or injecting drugs to patients, an infusion pump for drugs can be used to execute the infusion doctor's order for the patient to achieve automatic drug infusion. When the infusion pump is working, medical staff need to manually check the working condition of the infusion pump to determine whether the infusion pump is working properly and adjust the infusion parameters according to the actual infusion situation. However, this manual analysis method is prone to errors in drug infusion analysis and cannot identify risks in a timely manner, thus bringing drug use risks to patients.

[0003] Therefore, how to provide an intelligent infusion regulation system and method for infusing drugs during surgery to solve the difficulties existing in the prior art is an urgent problem for those skilled in the art to solve. Summary of the Invention

[0004] In view of this, the present invention provides an intelligent infusion regulation system and method for infusing drugs during surgery, which realizes precise infusion regulation of vasoactive drugs during surgery, improves the safety and success rate of surgery, and provides a more convenient and efficient technical means for medical staff.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] An intelligent infusion regulation system for infusing drugs during surgery includes a signal acquisition module, a cloud platform module, a data processing module, and an intelligent infusion module.

[0007] The signal acquisition module is used to acquire drug information, respiratory state information, and bleeding information.

[0008] The cloud platform module is connected to the second input end of the data processing module and is used to obtain the patient's medical history.

[0009] The data processing module has its first input end connected to the output end of the signal acquisition module and is used to receive the acquired information and the patient's medical history to generate a corresponding infusion signal.

[0010] The intelligent infusion module has its input end connected to the output end of the data processing module and is used to adjust the liquid medicine infusion situation according to the infusion signal.

[0011] Optionally, it further includes a drug pump, an anesthesia module, a blood pressure acquisition module, and a heart rate acquisition module, and the drug pump, the anesthesia module, the blood pressure acquisition module, and the heart rate acquisition module are connected in parallel to the signal acquisition module.

[0012] Optionally, the drug pump includes a drug storage unit and an infusion unit.

[0013] The drug storage unit is provided with a drug inlet and a drug outlet for accommodating the drug to be injected.

[0014] The infusion unit includes an infusion tube and a control module for controlling drug infusion and realizing drug injection.

[0015] The anesthesia module includes an oxygen cylinder, a pressure pump, an atomization device, and a gas supply device for atomizing the anesthetic and adjusting the anesthetic concentration.

[0016] The input end of the control module and the input end of the gas supply device are connected in parallel to the output end of the intelligent infusion module.

[0017] An intelligent infusion regulation method for infusing drugs during surgery, which is applied to the intelligent infusion regulation system for infusing drugs during surgery described in any one of the above, includes the following steps:

[0018] S1. Collect drug information, respiratory state information, and hemoglobin content through the signal acquisition module, generate corresponding drug information, respiratory state information, and hemoglobin information, and obtain the user's medical history using the cloud platform module.

[0019] S2. Preprocess the drug information, respiratory state information, hemoglobin information, blood pressure information, and user's medical history, and eliminate error data.

[0020] S3. Judge the drug information as the first parameter, judge the patient's anesthesia level using the patient's respiratory state information as the second parameter, construct a feature calculation model to judge the bleeding information in combination with the hemoglobin information and the user's medical history, and use it as the third parameter. Generate a blood pressure signal based on the blood pressure standard threshold and the user's blood pressure information, and use it as the fourth parameter.

[0021] S4. Comprehensively judge the drug infusion situation based on the first, second, third, and fourth parameters to form an infusion signal.

[0022] S5. The intelligent infusion module adjusts the patient's drug injection rate according to the infusion signal and regulates the vasoactive drugs during the operation.

[0023] Optionally, in S1, the drug information includes infusion information, drug information, operator information, and operator permissions; the respiratory state information includes a heartbeat signal and a respiratory signal.

[0024] Optionally, the second parameter in S3 includes: obtaining a cardiopulmonary index and an injury irritation index by analyzing a heartbeat signal and a respiration signal, and determining an anesthesia state based on the cardiopulmonary index and the injury irritation index.

[0025] Optionally, the feature calculation model in S3 includes: using SHAP to combine with the lasso regression algorithm to screen data features, and using the ridge regression algorithm to calculate data feature coefficients, and finally obtaining the feature calculation model.

[0026] As can be seen from the above technical solutions, compared with the prior art, the present invention provides an intelligent infusion regulation system and method for intraoperative infusion of drugs, which has the following beneficial effects: 1) The present invention can obtain comprehensive infusion information through drug information and automatically analyze the infusion situation of drugs; 2) The present invention can meet the needs of intraoperative anesthesia, provide a reference for the infusion of anesthetic administration, and thus provide the most suitable anesthesia state for anesthetized patients; 3) The present invention realizes the precise infusion regulation of vasoactive drugs during surgery, improves the safety and success rate of surgery, and provides a more convenient and efficient technical means for medical staff. Description of the Drawings

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0028] Figure 1 It is a block diagram of an intelligent infusion regulation system for intraoperative infusion of drugs disclosed by the present invention;

[0029] Figure 2 It is a flowchart of an intelligent infusion regulation method for intraoperative infusion of drugs disclosed by the present invention. Detailed Embodiments

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0031] Refer to Figure 1 As shown, the present invention discloses an intelligent infusion regulation system for intraoperative infusion of drugs, including a signal acquisition module, a cloud platform module, a data processing module, and an intelligent infusion module.

[0032] The signal acquisition module is used to acquire drug information, respiratory status information, and bleeding information;

[0033] The cloud platform module is connected to the second input end of the data processing module and is used to obtain the user's medical history;

[0034] The data processing module, with its first input end connected to the output end of the signal acquisition module, is used to receive the acquired information and the user's medical history to generate corresponding infusion signals;

[0035] The intelligent infusion module, with its input end connected to the output end of the data processing module, is used to adjust the liquid medicine infusion situation according to the infusion signal.

[0036] Furthermore, it also includes a drug pump, an anesthesia module, a blood pressure acquisition module, and a heart rate acquisition module. The drug pump, anesthesia module, blood pressure acquisition module, and heart rate acquisition module are connected in parallel with the signal acquisition module.

[0037] Furthermore, the drug pump includes a medicine storage unit and an infusion unit.

[0038] The medicine storage unit is provided with a medicine inlet and a medicine outlet and is used to hold the medicine to be injected;

[0039] The infusion unit includes an infusion tube and a control module group and is used to control the drug infusion and realize drug injection;

[0040] The anesthesia module includes an oxygen cylinder, a pneumatic pump, an atomization device, and a gas supply device and is used to atomize the anesthetic and adjust the anesthetic concentration;

[0041] The input end of the control module group and the input end of the gas supply device are connected in parallel to the output end of the intelligent infusion module.

[0042] Specifically, the medicine storage unit, the control module group, and the infusion tube are connected in sequence, and the other end of the infusion tube is sent subcutaneously to realize drug infusion; the pneumatic pump is used to provide the carrying force of respiratory air and adjust the output oxygen concentration. The atomization device is used to mix the gas with a certain oxygen concentration into the anesthetic to form anesthetic liquid and vaporize the anesthetic liquid. The gas supply device is used to adjust the output of the anesthetic gas to realize the adjustment ability of the anesthetic inhaled by the patient.

[0043] Furthermore, the drug pump can be used to automatically infuse drugs for the patient and monitor the patient's condition. A pre - established drug library can be burned into the drug pump. The drug library is a configuration file of the threshold values or default values of the infusion parameters of different drugs determined by medical staff and related to the department or the patient. The infusion parameters can include drug name, infusion speed, infusion volume, infusion time, etc. For example, the drugs to be infused and the preset infusion speed threshold values can be set in the drug library. The drug pump can automatically carry out the infusion work through the drug library. And the drug pump can record its own infusion situation in real time and generate an infusion log according to its own infusion situation.

[0044] An intelligent infusion regulation method for intraoperative drug infusion, which is applied to the intelligent infusion regulation system for intraoperative drug infusion described in any one of the above, with reference to Figure 2 as shown, includes the following steps:

[0045] S1. Collect drug information, respiratory status information, and hemoglobin content through the signal acquisition module, generate corresponding drug information, respiratory status information, and hemoglobin information, and obtain the user's medical history using the cloud platform module;

[0046] S2. Preprocess the drug information, respiratory status information, hemoglobin information, blood pressure information, and user's medical history, and eliminate error data.

[0047] S3. Judge the drug information as the first parameter, judge the patient's anesthesia level using the patient's respiratory status information as the second parameter, construct a feature calculation model to judge the bleeding information in combination with the hemoglobin information and the user's medical history, and use it as the third parameter. Generate a blood pressure signal based on the blood pressure standard threshold and the user's blood pressure information, and use it as the fourth parameter;

[0048] S4. Comprehensively judge the drug infusion situation for the first, second, third, and fourth parameters to form an infusion signal;

[0049] S5. The intelligent infusion module adjusts the patient's drug injection rate according to the infusion signal and regulates the vasoactive drugs during the operation.

[0050] Furthermore, in S1, the drug information includes infusion information, drug information, operator information, and operator permissions; the respiratory status information includes heartbeat signals and respiratory signals.

[0051] Specifically, the drug information can be obtained from the infusion log. The infusion information represents the corresponding infusion parameters and their corresponding values. For example, it can include one or more of the actual infusion speed, infusion volume, infusion duration, and infusion time, etc.; the drug information can include the drug type and drug amount, etc.; the operator type can be medical staff, for example, it can be a doctor or a nurse, etc.; the operator permissions are the permissions set in advance for various operators.

[0052] The respiratory status information is obtained from the thoracic impedance signal. Obtaining the heartbeat signal includes preprocessing the collected thoracic impedance signal, such as removing noise and normalizing it; then setting a time period as a time window to divide the thoracic impedance signal into several signal segments, and then performing forward difference operations on each signal segment one by one to obtain a difference array. Determine the position of the thoracic impedance signal with the smallest value in the difference array in each signal segment. Using 0.05s as a time window, find the wave peaks respectively forward and backward, which are the heartbeat signals.

[0053] Further, in the data preprocessing, the preprocessing of drug information includes verifying the accuracy of drug information by corroborating the content of the infusion log before and after.

[0054] Further, in S3, the first parameter includes infusion abnormalities and device abnormalities, and the second parameter includes: obtaining a cardiopulmonary index and an injury irritation index by analyzing the heartbeat signal and the respiratory signal, and determining the anesthesia state based on the cardiopulmonary index and the injury irritation index.

[0055] Further, in S3, infusion abnormalities include infusion blockage and approaching completion of infusion, etc. For example, device abnormalities include abnormal pusher head, etc.;

[0056] The cardiopulmonary index is obtained by performing similarity analysis on the heartbeat signal and the respiratory signal. For example, the wavelet coherence function is used to complete the similarity analysis; the injury irritation index is obtained by extracting the RR sequence from the heartbeat signal and then calculating the area under the curve formed by the RR sequence.

[0057] Specifically, similarity analysis refers to performing correlation analysis on the time-synchronized respiratory signal and heartbeat signal to evaluate the similarity degree of the two signals. Since the directly collected respiratory signal and heartbeat signal are discrete time series, only the real part of the wavelet transform is considered. First, the respiratory and heartbeat signals in the time domain are transformed into frequency domain signals through wavelet transform, and then the coherence analysis of the respiratory signal and the heartbeat signal is performed in the time-frequency domain to obtain the coherence coefficient. The patient's anesthesia level is obtained by synthesizing the injury irritation index and the cardiopulmonary index, that is, the second parameter is obtained.

[0058] The feature calculation model includes: letting SHAP combine with the lasso regression algorithm to screen data features, using the ridge regression algorithm to calculate the data feature coefficients, and finally obtaining the feature calculation model.

[0059] Specifically, use SHAP to screen features, rank the importance of input features, analyze the positive and negative impacts of features on the target value, adjust the number of unstructured features, and obtain the features after the first screening; then use the lasso regression algorithm to perform a second screening on the features after the first screening, obtain the parameters with zero lasso regression calculation feature coefficients, discard the features corresponding to the zero parameters, and include the features corresponding to the non-zero coefficients in the model. Screen the features again through the lasso regression algorithm to reduce the model complexity and prevent overfitting; then use the ridge regression algorithm to calculate the regression coefficients of each feature, and finally obtain the feature calculation model. Input the hemoglobin information and the user's medical history into the feature calculation model to obtain the third parameter.

[0060] Further, set thresholds for the first parameter, the second parameter, and the third parameter respectively. When any parameter exceeds the threshold range, use a warning light to remind the medical staff.

[0061] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent infusion regulation system for infusing drugs during surgery, characterized in that: It includes signal acquisition module, cloud platform module, data processing module and intelligent infusion module. A signal acquisition module is used to collect drug information, respiratory status information and bleeding information; A cloud platform module, connected to the second input terminal of the data processing module, for obtaining the user's medical history; A data processing module, a first input end of which is connected to an output end of the signal acquisition module, and is used to receive the acquisition information and the user's medical history to generate a corresponding infusion signal; The intelligent infusion module has an input end connected to the output end of the data processing module and is used to adjust the infusion of the drug solution according to the infusion signal.

2. The intelligent infusion regulation system for intraoperative drug infusion according to claim 1, characterized in that: It also includes a drug pump, an anesthesia module, a blood pressure collection module and a heart rate collection module, which are connected in parallel with the signal collection module.

3. The intelligent infusion regulation system for intraoperative drug infusion according to claim 2, characterized in that: The drug pump includes a drug storage unit and an infusion unit. The drug storage unit is provided with a drug inlet and a drug outlet for containing the drug to be injected; An infusion unit, including an infusion tube and a control module, is used to control drug infusion and realize drug injection; The anesthesia module includes an oxygen cylinder, an air pressure pump, an atomizing device and an air supply device, which are used to atomize the anesthetic and adjust the concentration of the anesthetic; The control module input terminal and the gas supply device input terminal are connected in parallel to the intelligent infusion module output terminal.

4. An intelligent infusion regulation method for intraoperative drug infusion, applied to an intelligent infusion regulation system for intraoperative drug infusion as claimed in any one of claims 1 to 3, characterized in that: The following steps are involved: S1. Collect drug information, respiratory status information, hemoglobin content and blood pressure through the signal acquisition module, generate corresponding drug information, respiratory status information, hemoglobin information and blood pressure information, and use the cloud platform module to obtain the user's medical history; S2, pre-process the drug information, respiratory status information, hemoglobin information, blood pressure information and user medical history, and remove error data. S3, determining drug information as the first parameter, using the patient's respiratory status information to determine the patient's anesthesia level, using it as the second parameter, constructing a feature calculation model to determine bleeding information in combination with hemoglobin information and the user's medical history, and using it as the third parameter, generating a blood pressure signal based on the blood pressure standard threshold combined with the user's blood pressure information, and using it as the fourth parameter; S4, comprehensively judging the drug infusion situation based on the first, second, third and fourth parameters to form an infusion signal; S5. The intelligent infusion module adjusts the patient's drug injection rate according to the infusion signal and regulates intraoperative vasoactive drugs.

5. The intelligent infusion regulation method for intraoperative drug infusion according to claim 4, characterized in that: The drug information in S1 includes infusion information, drug information, operator information and operator authority; the respiratory status information includes heartbeat signal and respiratory signal.

6. The intelligent infusion regulation method for intraoperative drug infusion according to claim 5, characterized in that: The second parameter in S3 includes: obtaining a cardiopulmonary index and a noxious irritation index by analyzing the heartbeat signal and the respiratory signal, and determining the anesthetic state based on the cardiopulmonary index and the noxious irritation index.

7. The intelligent infusion regulation method for intraoperative drug infusion according to claim 5, characterized in that: The feature calculation model in S3 includes: combining SHAP with the lasso regression algorithm to screen data features, using the ridge regression algorithm to calculate data feature coefficients, and finally obtaining the feature calculation model.

Images