Infusion pump calibration method based on data analysis

Through a linear regression model based on data analysis, the problem of infusion pump calibration error is solved, the accuracy and consistency of infusion is improved, the equipment life is extended, the calibration process is simplified, and the error and operation complexity in the existing technology are solved. The problem.

CN118983072APending Publication Date: 2024-11-19GUANGZHOU CTI TESTING & CERTIFICATION TECH CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411046026.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

There are errors in the calibration process of infusion pumps, especially when operating in solutions of specific chemical properties and are prone to waste and spillage or loopholes in water, and existing methods cannot guarantee consistency of the adhesion volume.

Method used

Using a data analysis-based approach, the flow rate of the infusion pump is calibrated by measurement and data analysis using a linear regression model, the calibration parameters of the pump are adjusted to reduce errors, and accuracy is ensured by correcting the flow rate and pressure.

Benefits of technology

Improves the accuracy and consistency of infusions, reduces dose errors due to inaccurate flow rates, extends the service life of the equipment, and simplifies the calibration process, saving resources and time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983072A_ABST
    Figure CN118983072A_ABST
Patent Text Reader

Abstract

The invention relates to the field of infusion pumps, and discloses an infusion pump calibration method based on data analysis, which comprises five steps of measurement preparation, data collection, data analysis, evaluation process and adjustment and calibration. According to the method, the linear regression model is used for assisting in correcting the flow speed of the infusion pump, dosage errors caused by the inaccurate flow speed of the infusion pump are reduced, and therefore the infusion accuracy is improved; moreover, the model can calibrate the flow rates of a plurality of pumps, so that the consistency among different devices is ensured, which is crucial for ensuring the continuity and quality control of treatment; and meanwhile, additional adjustment and monitoring caused by improper setting of the infusion pump can be reduced through accurate calibration, so that resources and time are saved. In addition, the infusion pump is calibrated regularly by using a linear regression method to help to monitor the equipment performance and prolong the service life of the equipment; in addition, although linear regression is a statistical technology, once a calibration model is established, the linear regression can be easily used by non-statistical professionals in daily work.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the field of infusion pumps, and in particular relates to an infusion pump calibration method based on data analysis. Background Art

[0002] An infusion pump is a medical device used to accurately control the drug infusion rate, infusion time, and total amount. In clinical medicine, it provides an important guarantee for accurate drug treatment. This device shows its important value in treatments that require long periods of time or that require strict control of drug delivery speed.

[0003] Infusion pumps are mainly divided into the following types:

[0004] Peristaltic pump: It promotes the flow of liquid by periodically squeezing the hose, and is suitable for infusing various types of drugs.

[0005] Piston pump: Uses a piston to drive the liquid in the syringe to achieve precise infusion control. It is often used in situations where small doses or high-precision infusion are required.

[0006] Titration pump: controls the infusion rate by controlling the volume of liquid. It is suitable for situations where precise control of infusion rate and total volume is required.

[0007] The calibration process for infusion pumps is an important step in ensuring that medical devices deliver medications and fluids correctly and accurately.

[0008] In terms of calibration, the weight of liquid delivered by the infusion pump in a specific time (usually water) is measured and compared with the theoretical weight to calculate the accuracy of the infusion pump. This method is the most common and accurate method for calibrating infusion pumps.

[0009] In some specific applications, calibration can be performed by chemical titration, especially when the infusion involves solutions with specific chemical properties. This method relies on the chemical properties of the solution and determines the volume delivered by the end point of the chemical reaction. The operation is complicated and only applies to solutions with specific chemical properties.

[0010] The volume method needs to deal directly with water. When water passes through the pump body and the pipe, it will have a certain degree of adhesion, which may lead to water waste, and overflow or leakage may occur during the measurement of water. Although the theoretical and actual measurement and comparison of the volume of transported water are carried out, both will adhere to the pump body and the pipe, but there is no guarantee that the volume of the two is the same. Summary of the invention

[0011] (I) Technical problem to be solved: How to reduce the error during infusion pump calibration.

[0012] (II) Technical solution: The present invention provides an infusion pump calibration method based on data analysis, comprising the following steps:

[0013] 1. Measurement preparation:

[0014] a. Select a reasonable flow rate range according to the technical specifications of the infusion pump;

[0015] b. Calibrate the measuring cylinder or bottle used to ensure accurate readings;

[0016] c. Keep the temperature and humidity in the calibration environment stable to avoid affecting the results;

[0017] 2. Data Collection:

[0018] a. Starting from the lowest flow rate, set the infusion pump to the first flow rate in the designed experiment;

[0019] b. Allow the infusion pump to run at the selected flow rate for a certain period of time, then measure the volume of infusion, and repeat the measurement more than three times to obtain reliable data;

[0020] c. Record the average infusion volume at each flow rate;

[0021] 3. Data Analysis:

[0022] a. Draw a data graph on a coordinate paper with the x-axis representing the pump speed and the y-axis representing the actual measured infusion volume;

[0023] b. Use statistical software or manual calculation to find the best fitting line, that is, the linear regression line, and obtain the correlation coefficient, which includes the slope m and the intercept b;

[0024] 4. Evaluation process:

[0025] a. Calculate the confirmation coefficient R 2 , in R 2 When it is close to the value of 1, it indicates a high degree of fit, which can be used to evaluate how well the linear regression model fits the infusion pump calibration data;

[0026] b. Use the regression equation to predict the infusion volume for flow rates not in the original data and compare it with the actual value to verify the accuracy;

[0027] 5. Adjustment and calibration:

[0028] a. If significant deviations are found, adjust the calibration parameters of the infusion pump based on the linear regression model results;

[0029] b. When using an infusion pump, adjust the actual set flow rate according to the regression model to compensate for possible reading errors on the display.

[0030] Furthermore, the linear regression equation is calculated as:

[0031] y=mx+b

[0032] Where y is the response variable, volume, representing the predicted or estimated value; x is the independent variable, pump rate, representing the value used to make the prediction; m is the slope; and b is the intercept.

[0033] Furthermore, the coefficient R 2 The calculation steps are as follows:

[0034] a. Calculate the total sum of squares SST: The total sum of squares represents the sum of the squares of the deviations of all data points about their mean, and the calculation formula is:

[0035]

[0036] Among them, y i is the actual observation value of the ith is the mean of all observations, and n is the total number of observations;

[0037] b. Calculate the regression sum of squares SSR: The regression sum of squares represents the variation explained by the regression model, and the calculation formula is:

[0038]

[0039] in, is the model’s predicted value for the i-th data point;

[0040] c. Calculate the error sum of squares SSE: The error sum of squares represents the variation that the model cannot explain, that is, the sum of squares of all residuals, and the calculation formula is:

[0041]

[0042] d. Calculate the coefficient R 2 : R 2 It indicates the proportion of the variation explained by the regression model to the total variation. The calculation formula is:

[0043]

[0044] Among them, R 2 The values ​​range from 0 to 1, with 0 indicating that the model does not explain any variation and 1 indicating that the model perfectly explains all variation.

[0045] Furthermore, the calculation steps of the slope m are as follows:

[0046] a. Calculate the average value of pump speed x and infusion volume y:

[0047]

[0048] Where n is the total number of data points, x i and i is the coordinate value of each data point;

[0049] b. Calculate the slope m:

[0050]

[0051] The above is the calculation formula for the slope m.

[0052] Furthermore, the calculation formula of the intercept b is as follows:

[0053]

[0054] This is the calculation formula for the intercept b.

[0055] Furthermore, in step five, if the actual slope is less than the theoretical slope, it means that the actual flow rate delivered by the pump is less than expected, and the pump speed setting needs to be increased to compensate for the gap; if the intercept is significantly not 0, the minimum operating pressure or start-up threshold of the pump needs to be adjusted to ensure that there is no excessive infusion at a low flow rate.

[0056] Further, in step 5, the specific steps of adjusting the actually set flow rate according to the regression model to compensate for the possible reading error on the display screen are:

[0057] First, calculate the actual measured infusion volume y 真实 The difference from the model's predicted output is calculated as:

[0058] Difference = y 真实 -(mx+b)

[0059] Next, calculate the corrected flow rate using the formula:

[0060]

[0061] The obtained x ′ That is the corrected flow rate setting value;

[0062] Finally, the new flow rate x ′ Set it on the instrument and then observe whether the reading on the display is close to the ideal infusion volume. 真实 , repeat this calibration process until the reading error drops to an acceptable range.

[0063] Furthermore, the method for calibrating the correct reading of the measuring cylinder or measuring bottle is as follows: place the measuring cylinder on a stable table, ensure that the measuring cylinder is flat before reading, and keep the line of sight level with the lowest point of the concave liquid surface in the measuring cylinder.

[0064] Furthermore, if the slope deviates from the theoretical value, corrections can be made by adjusting the flow rate setting parameters of the pump, including the following: first, if the actual slope is less than the theoretical slope, it means that the actual flow rate delivered by the pump is less than expected, and the pump speed setting needs to be increased to compensate for the difference; second, if the intercept is significantly not 0, the minimum operating pressure or start-up threshold of the pump needs to be adjusted to ensure that there is no excessive infusion at low flow rates.

[0065] (III) Technical Effects:

[0066] 1. The present invention uses a linear regression model to help correct the flow rate of an infusion pump, reducing the dosage error caused by an inaccurate flow rate of the infusion pump, thereby improving the accuracy of the infusion; moreover, the model can calibrate the flow rates of multiple pumps to ensure consistency between different devices, which is crucial for ensuring the continuity and quality control of treatment; at the same time, accurate calibration can reduce additional adjustments and monitoring caused by improper settings of the infusion pump, thereby saving resources and time.

[0067] 2. In the method provided by the present invention, the regular use of the linear regression method to calibrate the infusion pump can help monitor the performance of the equipment, timely discover and correct problems, and extend the service life of the equipment; in addition, although linear regression is a statistical technique, once the calibration model is established, it can be easily used by non-statistical professionals in daily work. In summary, the use of the linear regression model to calibrate the infusion pump in a medical environment is a simple, economical and effective method that can improve the quality and efficiency of clinical treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0069] Figure 1 It is a schematic diagram of the steps of the present invention;

[0070] Figure 2 It is a schematic diagram of the coefficient calculation steps of the present invention;

[0071] Figure 3 It is a schematic diagram of the display screen reading correction steps of the present invention. DETAILED DESCRIPTION

[0072] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0073] The infusion pump calibration method based on data analysis provided in this specific embodiment is as follows: Figure 1 , Figure 2 and Figure 3 As shown, the following steps are included:

[0074] 1. Measurement preparation:

[0075] a. Select a reasonable flow rate range according to the technical specifications of the infusion pump;

[0076] b. Calibrate the measuring cylinder or bottle used to ensure accurate readings;

[0077] c. Keep the temperature and humidity in the calibration environment stable to avoid affecting the results.

[0078] 2. Data Collection:

[0079] a. Starting from the lowest flow rate, set the infusion pump to the first flow rate in the designed experiment;

[0080] b. Allow the infusion pump to run at the selected flow rate for a certain period of time, then measure the volume of infusion, and repeat the measurement more than three times to obtain reliable data;

[0081] c. Record the average infusion volume at each flow rate.

[0082] 3. Data Analysis:

[0083] a. Draw a data graph on a coordinate paper with the x-axis representing the pump speed and the y-axis representing the actual measured infusion volume;

[0084] b. Use statistical software or manual calculation to find the best fitting line, that is, the linear regression line, and obtain the correlation coefficient, which includes the slope m and the intercept b.

[0085] 4. Evaluation process:

[0086] a. Calculate the confirmation coefficient R 2 , in R 2 When it is close to the value of 1, it indicates a high degree of fit, which can be used to evaluate how well the linear regression model fits the infusion pump calibration data;

[0087] Coefficient R 2 The calculation steps are as follows:

[0088] a. Calculate the total sum of squares SST: The total sum of squares represents the sum of the squares of the deviations of all data points about their mean, and the calculation formula is:

[0089]

[0090] Among them, y i is the actual observation value of the ith is the mean of all observations, and n is the total number of observations;

[0091] b. Calculate the regression sum of squares SSR: The regression sum of squares represents the variation explained by the regression model, and the calculation formula is:

[0092]

[0093] in, is the model’s predicted value for the i-th data point;

[0094] c. Calculate the error sum of squares SSE: The error sum of squares represents the variation that the model cannot explain, that is, the sum of squares of all residuals, and the calculation formula is:

[0095]

[0096] d. Calculate the coefficient R 2 : R 2 It indicates the proportion of the variation explained by the regression model to the total variation. The calculation formula is:

[0097]

[0098] Among them, R 2 The value of ranges from 0 to 1, where 0 means that the model does not explain any variation and 1 means that the model perfectly explains all variation;

[0099] b. Use the regression equation to predict the infusion volume for flow rates not in the original data and compare it with the actual value to verify the accuracy;

[0100] The linear regression equation is calculated as:

[0101] y=mx+b

[0102] Where y is the response variable, volume, representing the predicted or estimated value; x is the independent variable, pump speed, representing the value used for prediction; m is the slope; and b is the intercept. The calculation steps for the slope m are as follows:

[0103] a. Calculate the average value of pump speed x and infusion volume y:

[0104]

[0105] Where n is the total number of data points, x i and i is the coordinate value of each data point;

[0106] b. Calculate the slope m:

[0107]

[0108] The above is the calculation formula for slope m;

[0109] The calculation formula for intercept b is as follows:

[0110]

[0111] This is the calculation formula for the intercept b.

[0112] 5. Adjustment and calibration:

[0113] a. If significant deviations are found, adjust the calibration parameters of the infusion pump according to the results of the linear regression model; if the slope deviates from the theoretical value, it can be corrected by adjusting the flow rate setting parameters of the pump. For example, if the actual slope is less than the theoretical slope, it means that the actual flow rate delivered by the pump is less than expected, and the pump speed setting needs to be increased to compensate for the difference; if the intercept is significantly different from 0 (especially a positive value), it may be necessary to adjust the minimum operating pressure or start threshold of the pump to ensure that there is no excessive infusion at low flow rates; if the adjusted model is still not ideal, it may be necessary to repeat the above steps until the calibration parameters make the model's R 2 The value is close to 1, and the slope and intercept are close to the theoretical values;

[0114] b. When using the infusion pump, adjust the actual set flow rate according to the regression model to compensate for possible reading errors on the display screen; the specific steps for adjusting the actual set flow rate according to the regression model to compensate for possible reading errors on the display screen are:

[0115] First, calculate the actual measured infusion volume y 真实 The difference from the model's predicted output is calculated as:

[0116] Difference = y 真实 -(mx+b)

[0117] Next, calculate the corrected flow rate using the formula:

[0118]

[0119] The obtained x ′ That is the corrected flow rate setting value;

[0120] Finally, the new flow rate x ′ Set it on the instrument and then observe whether the reading on the display is close to the ideal infusion volume. 真实 , repeat this calibration process until the reading error drops to an acceptable range.

[0121] The present invention uses a linear regression model to help correct the flow rate of an infusion pump, reducing the dosage error caused by an inaccurate flow rate of an infusion pump, thereby improving the accuracy of infusion; and the model can calibrate the flow rates of multiple pumps to ensure consistency between different devices, which is essential for ensuring the continuity and quality control of treatment; at the same time, accurate calibration can reduce additional adjustments and monitoring caused by improper settings of the infusion pump, thereby saving resources and time. Moreover, regular use of the linear regression method to calibrate the infusion pump can help monitor equipment performance, promptly discover and correct problems, and extend the service life of the equipment; in addition, although linear regression is a statistical technique, once a calibration model is established, it can be easily used by non-statistical professionals in daily work. In summary, using a linear regression model to calibrate an infusion pump in a medical environment is a simple, economical and effective method that can improve the quality and efficiency of clinical treatment.

[0122] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0123] 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 method for calibrating an infusion pump based on data analysis, characterized in that: The following steps are involved:

1. Measurement preparation: a. Select a reasonable flow rate range according to the technical specifications of the infusion pump; b. Calibrate the measuring cylinder or bottle used to ensure accurate readings; c. Keep the temperature and humidity in the calibration environment stable to avoid affecting the results; 2. Data Collection: a. Starting from the lowest flow rate, set the infusion pump to the first flow rate in the designed experiment; b. Allow the infusion pump to run at the selected flow rate for a certain period of time, then measure the volume of infusion, and repeat the measurement more than three times to obtain reliable data; c. Record the average infusion volume at each flow rate; 3. Data Analysis: a. Draw a data graph on a coordinate paper with the x-axis representing the pump speed and the y-axis representing the actual measured infusion volume; b. Use statistical software or manual calculation to find the best fitting line, that is, the linear regression line, and obtain the correlation coefficient, which includes the slope m and the intercept b; IV. Evaluation process: a. Calculate the confirmation coefficient R 2 , in R 2 When it is close to the value of 1, it indicates a high degree of fit, which can be used to evaluate how well the linear regression model fits the infusion pump calibration data; b. Use the regression equation to predict the infusion volume for flow rates not in the original data and compare it with the actual value to verify the accuracy; 5. Adjustment and calibration: a. If significant deviations are found, adjust the calibration parameters of the infusion pump based on the linear regression model results; b. When using an infusion pump, adjust the actual set flow rate according to the regression model to compensate for possible reading errors on the display.

2. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: The linear regression equation is calculated as: y=mx+b Where y is the response variable, volume, representing the predicted or estimated value; x is the independent variable, pump rate, representing the value used to make the prediction; m is the slope; and b is the intercept.

3. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: Coefficient R 2 The calculation steps are as follows: a. Calculate the total sum of squares SST: The total sum of squares represents the sum of the squares of the deviations of all data points about their mean, and the calculation formula is: Among them, y i is the actual observation value of the ith is the mean of all observations, and n is the total number of observations; b. Calculate the regression sum of squares SSR: The regression sum of squares represents the variation explained by the regression model, and the calculation formula is: in, is the model’s predicted value for the i-th data point; c. Calculate the error sum of squares SSE: The error sum of squares represents the variation that the model cannot explain, that is, the sum of squares of all residuals, and the calculation formula is: d. Calculate the coefficient R 2 : R 2 It indicates the proportion of the variation explained by the regression model to the total variation. The calculation formula is: Among them, R 2 The values ​​range from 0 to 1, with 0 indicating that the model does not explain any variation and 1 indicating that the model perfectly explains all variation.

4. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: The calculation steps of slope m are as follows: a. Calculate the average value of pump speed x and infusion volume y: Where n is the total number of data points, x i and i is the coordinate value of each data point; b. Calculate the slope m: The above is the calculation formula for the slope m.

5. The infusion pump calibration method based on data analysis according to claim 4, characterized in that: The calculation formula for intercept b is as follows: This is the calculation formula for the intercept b.

6. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: In step five, if the actual slope is less than the theoretical slope, it means that the actual flow rate delivered by the pump is less than expected, and the pump speed setting needs to be increased to compensate for the gap; if the intercept is significantly not 0, the minimum operating pressure or start-up threshold of the pump needs to be adjusted to ensure that there is no excessive infusion at a low flow rate.

7. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: In step 5, the specific steps for adjusting the actual set flow rate according to the regression model to compensate for possible reading errors on the display are: First, calculate the actual measured infusion volume y 真实 The difference from the model's predicted output is calculated as: Difference = y 真实 -(mx+b) Next, calculate the corrected flow rate using the formula: The obtained x ′ That is the corrected flow rate setting value; Finally, the new flow rate x ′ Set it on the instrument and then observe whether the reading on the display is close to the ideal infusion volume. 真实 , repeat this calibration process until the reading error drops to an acceptable range.

8. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: The method to calibrate the correct reading of a measuring cylinder or a measuring bottle is as follows: Place the measuring cylinder on a stable table, make sure it is flat before taking the reading, and keep your line of sight level with the lowest point of the concave liquid surface in the measuring cylinder.

9. The infusion pump calibration method based on data analysis according to claim 1, characterized in that: If the slope deviates from the theoretical value, corrections can be made by adjusting the flow rate setting parameters of the pump, including the following: First, if the actual slope is less than the theoretical slope, it means that the actual flow rate delivered by the pump is less than expected, and the pump speed setting needs to be increased to compensate for the difference; second, if the intercept is significantly not 0, the minimum operating pressure or start-up threshold of the pump needs to be adjusted to ensure that there is no excessive infusion at low flow rates.

Citation Information

Patent Citations

  • Method for calibrating output accuracy of transfusion controller

    CN103212130A

  • Infusion precision automatic calibration control system and control method of infusion pump

    CN112089924A

  • Test calibration method and device for peristaltic pump

    CN113007086A

  • Calibration method and device of infusion pump and infusion pump

    CN114441094A

  • Secondary instrument calibration method

    CN117235511A