A data visualization method and system for influenza vaccine clinical trials

Abstract

The present invention relates to data analysis technology and discloses a data visualization method and system for influenza vaccine clinical trials, including: obtaining preset normal vital sign data of vaccinated personnel, first vital sign data after vaccination with a first preset dose of vaccine, and second vital sign data after vaccination with a second preset dose of vaccine, identifying a dose-sensitive factor based on the normal vital sign data, the first vital sign data, and the second vital sign data, predicting a third antibody level prediction curve of the vaccinated personnel after vaccination with a preset third dose of vaccine based on the dose-sensitive factor, confirming the dose-sensitive factor by performing an accuracy check on the third antibody level prediction curve, constructing a multidimensional dose antibody level attenuation visualization curve based on the dose-sensitive factor, and identifying a compliant dose based on the multidimensional dose antibody level attenuation visualization curve. The present invention can improve the accuracy of identifying compliant doses in influenza vaccine clinical trials.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a data visualization method and system in influenza vaccine clinical trials. Background Art

[0002] In the field of influenza vaccine development, clinical trials are a critical step in evaluating a vaccine's safety, efficacy, and immunogenicity. This process generates massive amounts of complex data, encompassing subjects' basic information, pre- and post-vaccination physical data, antibody titer changes, adverse reaction data, and more. Efficiently processing, analyzing, and presenting this data has become a critical challenge.

[0003] Traditional methods of processing vaccine clinical trial data, such as simply presenting data in tabular form, can provide detailed information, but they have many drawbacks. On the one hand, the data is too complex, making it difficult for people to quickly and intuitively grasp the key features and internal connections in the data, resulting in inefficient information acquisition. For example, when analyzing the differences in immune responses to influenza vaccines among subjects of different age groups and genders, screening and comparing relevant information from a large amount of tabular data is not only time-consuming and labor-intensive, but also prone to human omissions. On the other hand, traditional tables are unable to present data trends and relationships. Important information such as the dynamic change trend of antibody levels over time after vaccination, and the relationship between different vaccine doses and immune effects, are difficult to clearly display through tables, which is not conducive to scientific researchers and relevant decision makers quickly gaining insight into the laws behind the data, thereby affecting key decision-making in the vaccine development process. Summary of the Invention

[0004] The present invention provides a data visualization method and system for influenza vaccine clinical trials, the main purpose of which is to solve the problem that existing vaccine clinical trial data visualization methods cannot accurately identify compliant doses through visualization processing.

[0005] To achieve the above objectives, the present invention provides a method for visualizing data in influenza vaccine clinical trials, comprising:

[0006] Obtaining preset normal vital sign data of the vaccinated person, obtaining first vital sign data of the vaccinated person after receiving the first preset dose of vaccine and second vital sign data of the vaccinated person after receiving the second preset dose of vaccine;

[0007] An immune response analysis is performed by comparing the normal physical sign data with the first physical sign data to obtain a first immune response intensity curve. An immune response analysis is performed by comparing the normal physical sign data with the second physical sign data to obtain a second immune response intensity curve. A first antibody level attenuation curve is constructed according to the antibody titer contained in the first physical sign data. A second antibody level attenuation curve is constructed according to the antibody titer contained in the second physical sign data. The first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve are normalized to obtain a normalized first intensity curve. a normalized second intensity curve, a normalized first attenuation curve, and a normalized second attenuation curve; calculating a dose-response gain ratio according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating a time synergy coefficient according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating an absolute value of a difference between the first preset dose and the second preset dose to obtain a dose difference; multiplying the dose difference by the dose-response gain ratio and then dividing the result by the time synergy coefficient to obtain a dose sensitivity factor;

[0008] Predicting a third antibody level prediction curve of the vaccinated person after receiving a preset third dose of vaccine based on the dose-sensitive factor;

[0009] Confirming the dose sensitivity factor by performing accuracy verification on the third antibody level prediction curve;

[0010] Based on the dose-sensitive factor, the data on the decay of antibody levels corresponding to different doses over time are integrated to obtain a multi-dimensional dose antibody level decay curve. The multi-dimensional dose antibody level decay curve is visualized using data visualization technology to obtain a multi-dimensional dose antibody level decay visualization curve. The compliant dose is identified based on the multi-dimensional dose antibody level decay visualization curve.

[0011] Optionally, performing immune response analysis by comparing the normal vital sign data and the first vital sign data to obtain a first immune response intensity curve includes:

[0012] Performing time series alignment on the normal vital sign data and the first vital sign data to obtain aligned normal vital sign data and aligned first vital sign data;

[0013] Calculating the dynamic difference between the aligned normal vital sign data and the aligned first vital sign data at each time point to obtain a difference sequence;

[0014] identifying the normal vital sign data and peak vital sign data in the first vital sign data;

[0015] performing normalization processing on the difference sequence based on the peak vital sign data to obtain a normalized difference sequence;

[0016] Performing weighted fusion on the body temperature, blood pressure, and heart rate corresponding to each difference group in the normalized difference sequence to obtain a quantitative indicator sequence;

[0017] A first immune response intensity curve is constructed according to the quantitative index sequence.

[0018] Optionally, calculating the dose-response gain ratio according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve includes:

[0019] Obtaining a first intensity peak value in the normalized first intensity curve, and obtaining a second intensity peak value in the normalized second intensity curve;

[0020] Calculating the areas under the normalized first intensity curve and the normalized second intensity curve to obtain a first total intensity and a second total intensity;

[0021] Identifying half-life durations of the normalized first attenuation curve and the normalized second attenuation curve to obtain a first duration and a second duration;

[0022] identifying the steady-state concentration of the antibody according to the normalized first decay curve and the normalized second decay curve to obtain a first concentration and a second concentration;

[0023] Calculating a ratio of the second intensity peak to the first intensity peak to obtain a peak ratio;

[0024] calculating a ratio of the second total intensity to the first total intensity to obtain a total intensity ratio;

[0025] Calculating a ratio of the second duration to the first duration to obtain a duration ratio;

[0026] calculating a ratio of the second concentration to the first concentration to obtain a concentration ratio;

[0027] Multiplying the peak value ratio and the total intensity ratio by a preset first weight parameter and a preset second weight parameter respectively and then adding the results to obtain a numerator term;

[0028] Multiplying the duration ratio and the concentration ratio by the preset first weight parameter and the second weight parameter respectively and then adding them together to obtain a denominator;

[0029] The ratio of the numerator term to the denominator term is calculated to obtain the dose-response gain ratio.

[0030] Optionally, calculating a time coordination coefficient according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve includes:

[0031] identifying an intersection point between the normalized first intensity curve and the normalized second intensity curve to obtain a first intersection time;

[0032] identifying an intersection point of the normalized first attenuation curve and the normalized second attenuation curve to obtain a second intersection time;

[0033] Identifying peak time points of the normalized first intensity curve and the normalized second intensity curve to obtain a first intensity peak time point and a second intensity peak time point;

[0034] Identifying the peak time points of the normalized first attenuation curve and the normalized second attenuation curve to obtain a first concentration peak time point and a second concentration peak time point;

[0035] Calculate the absolute time difference between the first intersection time and the first intensity peak time point and the second intensity peak time point respectively to obtain a first intensity curve time difference and a second intensity curve time difference;

[0036] Calculate the absolute time difference between the second intersection time and the first concentration peak time, and the second concentration peak time to obtain a first attenuation curve time difference and a second attenuation curve time difference;

[0037] A time coordination coefficient is calculated according to the first intensity curve time difference, the second intensity curve time difference, the first attenuation curve time difference, and the second attenuation curve time difference.

[0038] Optionally, calculating a time coordination coefficient based on the time difference of the first attenuation curve and the time difference of the second attenuation curve includes:

[0039] Multiplying the first intensity curve time difference by a preset intensity sensitivity coefficient to obtain a first intensity product term;

[0040] performing an exponential operation on the inverse of the first intensity product term using a preset exponential function to obtain a first intensity exponential term;

[0041] multiplying the second intensity curve time difference by a preset intensity sensitivity coefficient to obtain a second intensity product term;

[0042] performing an exponential operation on the inverse of the second intensity product term using a preset exponential function to obtain a second intensity exponential term;

[0043] Multiplying the first attenuation curve time difference by a preset attenuation sensitivity coefficient to obtain a first attenuation product term;

[0044] Performing an exponential operation on the inverse of the first attenuation product term using a preset exponential function to obtain a first attenuation exponential term;

[0045] Multiplying the second attenuation curve time difference by a preset attenuation sensitivity coefficient to obtain a second attenuation product term;

[0046] performing an exponential operation on the inverse of the second attenuation product term using a preset exponential function to obtain a second attenuation exponential term;

[0047] Calculating a mean of the first intensity index term and the second intensity product term and multiplying the result by a preset intensity weight coefficient to obtain an intensity weight term;

[0048] Calculating the mean of the first attenuation exponent term and the second attenuation exponent term and multiplying the calculated mean by a preset attenuation weight coefficient to obtain an attenuation weight term;

[0049] The intensity weight term and the attenuation weight term are summed to obtain the time coordination coefficient.

[0050] Optionally, confirming the dose sensitivity factor by performing an accuracy check on the third antibody level prediction curve includes:

[0051] Obtaining the third vital sign data of the vaccinated person after receiving the preset third dose of vaccine;

[0052] constructing a third antibody level true curve according to the third physical sign data;

[0053] Calculating a curve fit coefficient between the true curve of the third antibody level and the predicted curve of the third antibody level;

[0054] Determining whether the curve fitting coefficient is greater than a preset coefficient threshold;

[0055] If the curve fitting coefficient is greater than the coefficient threshold, the dose sensitivity factor is confirmed to be valid;

[0056] If the curve fitting coefficient is less than or equal to the coefficient threshold, the dose-sensitive factor is fine-tuned and the third antibody level prediction curve of the vaccinated person after receiving the preset third dose of vaccine is re-predicted based on the dose-sensitive factor to obtain a fine-tuned third antibody level prediction curve;

[0057] The dose-sensitive factor was confirmed by performing an accuracy check on the fine-tuned third antibody level prediction curve.

[0058] Optionally, calculating the curve fitting coefficient between the true curve of the third antibody level and the predicted curve of the third antibody level includes:

[0059] calculating a difference signal between the true curve of the third antibody level and the predicted curve of the third antibody level;

[0060] Performing a fast Fourier transform on the difference signal to obtain a power spectrum distribution of the difference signal;

[0061] Calculating the Shannon entropy of the power spectrum distribution of the difference signal;

[0062] Calculating the fractal dimensions of the true curve of the third antibody level and the predicted curve of the third antibody level using a preset algorithm to obtain the fractal dimension of the predicted curve and the fractal dimension of the true curve;

[0063] Calculating a multifractal cross-correlation index between the fractal dimension of the predicted curve and the fractal dimension of the true curve;

[0064] Performing continuous wavelet transform on the true curve of the third antibody level and the predicted curve of the third antibody level to obtain a wavelet coefficient matrix of the predicted curve and a wavelet coefficient matrix of the true curve;

[0065] Extracting the instantaneous phases of the predicted curve wavelet coefficient matrix and the true curve wavelet coefficient matrix and calculating the phase difference;

[0066] The Shannon entropy, the multifractal cross-correlation index and the phase difference are weightedly fused to obtain a curve fitting coefficient.

[0067] In order to solve the above problems, the present invention also provides a data visualization system for influenza vaccine clinical trials, the system comprising:

[0068] A data acquisition module is used to obtain the preset normal vital sign data of the vaccinated person, obtain the first vital sign data of the vaccinated person after receiving the first preset dose of vaccine, and obtain the second vital sign data of the vaccinated person after receiving the second preset dose of vaccine;

[0069] A data identification module is used to perform immune response analysis by comparing the normal physical sign data with the first physical sign data to obtain a first immune response intensity curve, perform immune response analysis by comparing the normal physical sign data with the second physical sign data to obtain a second immune response intensity curve, construct a first antibody level attenuation curve according to the antibody titer contained in the first physical sign data, construct a second antibody level attenuation curve according to the antibody titer contained in the second physical sign data, and normalize the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve to obtain a normalized a first intensity curve, a normalized second intensity curve, a normalized first attenuation curve, and a normalized second attenuation curve; calculating a dose-response gain ratio based on the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating a time synergy coefficient based on the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating an absolute value of a difference between the first preset dose and the second preset dose to obtain a dose difference; multiplying the dose difference by the dose-response gain ratio and then dividing the result by the time synergy coefficient to obtain a dose sensitivity factor;

[0070] A curve prediction module, configured to predict a third antibody level prediction curve of the vaccinated person after receiving a preset third dose of vaccine based on the dose-sensitive factor;

[0071] a data confirmation module, configured to confirm the dose sensitivity factor by performing an accuracy check on the third antibody level prediction curve;

[0072] The curve visualization module is used to integrate the data of antibody level decay over time corresponding to different doses based on the dose-sensitive factor to obtain a multi-dimensional dose antibody level decay curve, and use data visualization technology to visualize the multi-dimensional dose antibody level decay curve to obtain a multi-dimensional dose antibody level decay visualization curve, and identify the compliant dose based on the multi-dimensional dose antibody level decay visualization curve.

[0073] The embodiment of the present invention obtains the normal vital sign data of the preset vaccination personnel, obtains the first vital sign data of the vaccination personnel after vaccination with the first preset dose of vaccine and the second vital sign data after vaccination with the second preset dose of vaccine, identifies the dose-sensitive factor according to the normal vital sign data, the first vital sign data, and the second vital sign data, predicts the third antibody level prediction curve of the vaccination personnel after vaccination with the preset third dose of vaccine based on the dose-sensitive factor, confirms the dose-sensitive factor by performing an accuracy check on the third antibody level prediction curve, integrates the data of the antibody levels corresponding to different doses that decay over time based on the dose-sensitive factor, obtains a multi-dimensional dose antibody level decay curve, uses data visualization technology to visualize the multi-dimensional dose antibody level decay curve, obtains a multi-dimensional dose antibody level decay visualization curve, and identifies the compliant dose according to the multi-dimensional dose antibody level decay visualization curve. Therefore, the data visualization method and system for influenza vaccine clinical trials proposed by the present invention can solve the problem that the existing vaccine clinical trial data visualization method cannot accurately identify the compliant dose through visualization. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of a process for visualizing data in a clinical trial of an influenza vaccine according to an embodiment of the present invention;

[0075] Figure 2 This is a functional module diagram of a data visualization system for influenza vaccine clinical trials provided by one embodiment of the present invention.

[0076] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0077] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0078] The embodiment of the present application provides a data visualization method in a flu vaccine clinical trial. The execution subject of the data visualization method in the flu vaccine clinical trial includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the data visualization method in the flu vaccine clinical trial can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0079] Reference Figure 1 FIG. 1 is a flow chart of a method for visualizing data in a clinical trial of an influenza vaccine according to an embodiment of the present invention. In this embodiment, the method for visualizing data in a clinical trial of an influenza vaccine includes:

[0080] S1. Obtain the preset normal vital sign data of the vaccinated person, obtain the first vital sign data of the vaccinated person after receiving the first preset dose of vaccine and the second vital sign data of the vaccinated person after receiving the second preset dose of vaccine.

[0081] In the embodiment of the present invention, obtaining the preset normal vital signs data of the vaccinated person refers to obtaining the vital signs data of the vaccinated person before vaccination.

[0082] In an embodiment of the present invention, the vital sign data may include body temperature, blood pressure, and heart rate.

[0083] In an embodiment of the present invention, the first vital sign data and the second vital sign data may include body temperature, blood pressure, heart rate and antibody titer.

[0084] In detail, antibody titer is an indicator to measure antibody activity, indicating the ability of the antibody to bind to the antigen, and is usually expressed by measuring the antibody concentration by a serial dilution method or the highest dilution of the antibody's ability to bind to the antigen.

[0085] S2. Identify a dose-sensitive factor based on the normal vital sign data, the first vital sign data, and the second vital sign data.

[0086] In an embodiment of the present invention, the dose-sensitive factor is identified based on the normal vital sign data, the first vital sign data, and the second vital sign data. This is done by comparing the normal vital sign data of the vaccinated person with the vital sign data after the first and second doses of the vaccine, and generating two immune response intensity curves (reflecting short-term physiological responses) and two antibody level attenuation curves (reflecting long-term immune protection), respectively. The four curves are then normalized, and two key parameters are calculated based on the normalized curves: the dose-response gain ratio (quantifying the immune benefit of the dose increase) and the time synergy coefficient (evaluating the temporal matching of the immune dynamics). Finally, the dose difference between the two doses of the vaccine is combined, and the result is output according to the formula: dose-sensitive factor = |dose difference| × dose-response gain ratio / time synergy coefficient, thereby quantitatively evaluating the effect of the vaccination dose on the sensitivity of the individual's immune system in a data-driven manner.

[0087] In an embodiment of the present invention, identifying a dose-sensitive factor based on the normal vital sign data, the first vital sign data, and the second vital sign data includes:

[0088] Performing immune response analysis by comparing the normal physical sign data with the first physical sign data to obtain a first immune response intensity curve;

[0089] Performing immune response analysis by comparing the normal physical sign data and the second physical sign data to obtain a second immune response intensity curve;

[0090] constructing a first antibody level decay curve according to the antibody titer included in the first physical sign data;

[0091] constructing a second antibody level decay curve according to the antibody titer included in the second physical sign data;

[0092] The dose sensitivity factor is calculated according to the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve.

[0093] Specifically, the immune response analysis performed by comparing the normal vital sign data with the first vital sign data yields a first immune response intensity curve. This curve is constructed by calculating the dynamic deviation between the vital sign data (temperature, blood pressure, heart rate) after the first dose of the vaccine and the normal vital sign data (pre-vaccination baseline). This curve, with time as the horizontal axis and the magnitude of change in physiological indicators as the vertical axis, quantifies the intensity of the immune system's acute response to the first dose of the vaccine (e.g., peak body temperature reflects the level of inflammatory response).

[0094] In detail, the first antibody level attenuation curve is constructed according to the antibody titer contained in the first vital sign data, and the curve is constructed by fitting the antibody attenuation function based on the antibody titer time series data after the first dose of vaccination.

[0095] In an embodiment of the present invention, performing immune response analysis by comparing the normal vital sign data and the first vital sign data to obtain a first immune response intensity curve includes:

[0096] Performing time series alignment on the normal vital sign data and the first vital sign data to obtain aligned normal vital sign data and aligned first vital sign data;

[0097] Calculating the dynamic difference between the aligned normal vital sign data and the aligned first vital sign data at each time point to obtain a difference sequence;

[0098] identifying the normal vital sign data and peak vital sign data in the first vital sign data;

[0099] performing normalization processing on the difference sequence based on the peak vital sign data to obtain a normalized difference sequence;

[0100] Performing weighted fusion on the body temperature, blood pressure, and heart rate corresponding to each difference group in the normalized difference sequence to obtain a quantitative indicator sequence;

[0101] A first immune response intensity curve is constructed according to the quantitative index sequence.

[0102] In detail, the body temperature, blood pressure, and heart rate corresponding to each difference group in the normalized difference sequence are weightedly fused, and a weight of 0.5 is assigned to the body temperature, a weight of 0.2 is assigned to the blood pressure, and a weight of 0.3 is assigned to the heart rate for weighted fusion.

[0103] In an embodiment of the present invention, calculating the dose sensitivity factor according to the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve includes:

[0104] Normalizing the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve to obtain a normalized first intensity curve, a normalized second intensity curve, a normalized first attenuation curve, and a normalized second attenuation curve;

[0105] calculating a dose-response gain ratio according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve;

[0106] Calculating a time cooperation coefficient according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve;

[0107] calculating an absolute value of a difference between the first preset dose and the second preset dose to obtain a dose difference;

[0108] The dose difference is multiplied by the dose-response gain ratio and then divided by the time synergy coefficient to obtain a dose sensitivity factor.

[0109] In detail, the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve and the second antibody level attenuation curve are normalized to obtain a normalized first intensity curve, a normalized second intensity curve, a normalized first attenuation curve and a normalized second attenuation curve. The normalization method is piecewise adaptive normalization, which uses minimum-maximum scaling (retaining relative fluctuations) for the intensity curve and Z-score normalization (adapting to exponential attenuation characteristics) after logarithmic transformation for the antibody attenuation curve.

[0110] In an embodiment of the present invention, the calculating of the dose-response gain ratio according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve includes:

[0111] Obtaining a first intensity peak value in the normalized first intensity curve, and obtaining a second intensity peak value in the normalized second intensity curve;

[0112] Calculating the areas under the normalized first intensity curve and the normalized second intensity curve to obtain a first total intensity and a second total intensity;

[0113] Identifying half-life durations of the normalized first attenuation curve and the normalized second attenuation curve to obtain a first duration and a second duration;

[0114] identifying the steady-state concentration of the antibody according to the normalized first decay curve and the normalized second decay curve to obtain a first concentration and a second concentration;

[0115] Calculating a ratio of the second intensity peak to the first intensity peak to obtain a peak ratio;

[0116] calculating a ratio of the second total intensity to the first total intensity to obtain a total intensity ratio;

[0117] Calculating a ratio of the second duration to the first duration to obtain a duration ratio;

[0118] calculating a ratio of the second concentration to the first concentration to obtain a concentration ratio;

[0119] Multiplying the peak value ratio and the total intensity ratio by a preset first weight parameter and a preset second weight parameter respectively and then adding the results to obtain a numerator term;

[0120] Multiplying the duration ratio and the concentration ratio by the preset first weight parameter and the second weight parameter respectively and then adding them together to obtain a denominator;

[0121] The ratio of the numerator term to the denominator term is calculated to obtain the dose-response gain ratio.

[0122] In detail, the half-life refers to the time required for the antibody concentration to decrease by 50%.

[0123] In detail, the steady-state antibody concentration refers to the stable antibody concentration level in the late decay stage.

[0124] In detail, the first weight parameter and the second weight parameter may both be 0.5.

[0125] In an embodiment of the present invention, calculating a time coordination coefficient according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve includes:

[0126] identifying an intersection point between the normalized first intensity curve and the normalized second intensity curve to obtain a first intersection time;

[0127] identifying an intersection point of the normalized first attenuation curve and the normalized second attenuation curve to obtain a second intersection time;

[0128] Identifying peak time points of the normalized first intensity curve and the normalized second intensity curve to obtain a first intensity peak time point and a second intensity peak time point;

[0129] Identifying the peak time points of the normalized first attenuation curve and the normalized second attenuation curve to obtain a first concentration peak time point and a second concentration peak time point;

[0130] Calculate the absolute time difference between the first intersection time and the first intensity peak time point and the second intensity peak time point respectively to obtain a first intensity curve time difference and a second intensity curve time difference;

[0131] Calculate the absolute time difference between the second intersection time and the first concentration peak time, and the second concentration peak time to obtain a first attenuation curve time difference and a second attenuation curve time difference;

[0132] A time coordination coefficient is calculated according to the first intensity curve time difference, the second intensity curve time difference, the first attenuation curve time difference, and the second attenuation curve time difference.

[0133] Specifically, the peak time points represent the moments when the immune response intensity reaches its maximum value during the course of each curve. Determining these two time points clearly identifies the specific times when the immune response intensity, as reflected by the two intensity curves, reaches its peak, providing a key reference for subsequent analysis of the temporal relationship between intensity changes.

[0134] In this embodiment of the present invention, the absolute time difference between the first intersection time and the peak time points of the two intensity curves is calculated to quantify the interval between the first intersection time and the peak times of the two intensity curves. These two time differences reflect the difference in the time course from the intersection of the two intensity curves to the peak intensity of each curve, and are important indicators for measuring the temporal coordination of their intensity changes.

[0135] In this embodiment of the present invention, the absolute time difference between the second intersection time and the peak time points of the two decay curves can be calculated to quantify the interval between the second intersection time and the peak times of the two decay curves. These two time differences reflect the difference in the time course from the intersection of the two decay curves to the peak value of the key characteristic change during the decay process, and are used to measure their temporal coordination during the decay process.

[0136] In the embodiment of the present invention, calculating the time coordination coefficient according to the first intensity curve time difference, the second intensity curve time difference, the first attenuation curve time difference, and the second attenuation curve time difference includes:

[0137] Multiplying the first intensity curve time difference by a preset intensity sensitivity coefficient to obtain a first intensity product term;

[0138] performing an exponential operation on the inverse of the first intensity product term using a preset exponential function to obtain a first intensity exponential term;

[0139] multiplying the second intensity curve time difference by a preset intensity sensitivity coefficient to obtain a second intensity product term;

[0140] performing an exponential operation on the inverse of the second intensity product term using a preset exponential function to obtain a second intensity index term;

[0141] Multiplying the first attenuation curve time difference by a preset attenuation sensitivity coefficient to obtain a first attenuation product term;

[0142] performing an exponential operation on the inverse of the first attenuation product term using a preset exponential function to obtain a first attenuation exponential term;

[0143] Multiplying the second attenuation curve time difference by a preset attenuation sensitivity coefficient to obtain a second attenuation product term;

[0144] performing an exponential operation on the inverse of the second attenuation product term using a preset exponential function to obtain a second attenuation exponential term;

[0145] Calculating a mean of the first intensity index term and the second intensity product term and multiplying the result by a preset intensity weight coefficient to obtain an intensity weight term;

[0146] Calculating the mean of the first attenuation exponent term and the second attenuation exponent term and multiplying the calculated mean by a preset attenuation weight coefficient to obtain an attenuation weight term;

[0147] The intensity weight term and the attenuation weight term are summed to obtain the time coordination coefficient.

[0148] S3. Predicting the third antibody level prediction curve of the vaccinated person after receiving the preset third dose of vaccine based on the dose-sensitive factor.

[0149] In the embodiments of the present invention, the dose-sensitive factor quantifies the relationship between the immune response intensity curve and the antibody level decay curve after two doses of vaccination, revealing the inherent connection between dose variation and immune efficacy. This relationship can be used to establish a dose-antibody response model. Specifically, by analyzing the known antibody decay curves after the first and second doses of vaccination, combined with the dose-response gain ratio and time synergy coefficient in the dose-sensitive factor, the patterns of antibody production and decay can be inferred. For example, the dose-response gain ratio reflects the impact of dose escalation on immune benefit and can be used to predict the magnitude of the peak antibody increase that a third dose may bring. The time synergy coefficient reflects the temporal matching of immune dynamics and helps determine the time points when antibodies reach peak and decay. Then, based on the preset proportional relationship between the third dose and the first two doses, the model parameters are adjusted, using the dose-sensitive factor as a key input parameter to simulate the antibody production and decay process after the third dose of vaccination. Ultimately, a third antibody level prediction curve is generated. This curve can reflect the expected antibody peak, the time to peak, and the subsequent decay trend, providing data support for the development of personalized vaccination plans.

[0150] S4. Confirm the dose sensitivity factor by performing accuracy verification on the third antibody level prediction curve.

[0151] In an embodiment of the present invention, the step of confirming the dose-sensitive factor by performing an accuracy check on the third antibody level prediction curve includes:

[0152] Obtaining the third vital sign data of the vaccinated person after receiving the preset third dose of vaccine;

[0153] constructing a third antibody level true curve according to the third physical sign data;

[0154] Calculating a curve fit coefficient between the true curve of the third antibody level and the predicted curve of the third antibody level;

[0155] Determining whether the curve fitting coefficient is greater than a preset coefficient threshold;

[0156] If the curve fitting coefficient is greater than the coefficient threshold, the dose sensitivity factor is confirmed to be valid;

[0157] If the curve fitting coefficient is less than or equal to the coefficient threshold, the dose-sensitive factor is fine-tuned and the third antibody level prediction curve of the vaccinated person after receiving the preset third dose of vaccine is re-predicted based on the dose-sensitive factor to obtain a fine-tuned third antibody level prediction curve;

[0158] The dose-sensitive factor was confirmed by performing an accuracy check on the fine-tuned third antibody level prediction curve.

[0159] Specifically, the third antibody level curve constructed based on the third vital sign data is based on the collected information about antibody titers over time. Using data processing and curve fitting methods, a curve is constructed that truly reflects the dynamic changes in antibody levels after the third dose of the vaccine. This curve, with time as the horizontal axis and antibody titer as the vertical axis, intuitively presents the generation, change, and decay trends of antibody levels after actual vaccination.

[0160] In detail, the confirmation of the dose-sensitive factor by performing accuracy verification on the fine-tuned third antibody level prediction curve refers to repeating the above-mentioned verification process from obtaining real physical sign data to judging the curve fitting coefficient for the newly generated fine-tuned third antibody level prediction curve, and recalculating the degree of fit with the actual third antibody level true curve, and judging whether the adjusted dose-sensitive factor is valid based on the comparison result of the fitting coefficient and the threshold value. If it still does not meet the requirements, continue to fine-tune and optimize until a valid dose-sensitive factor is obtained to ensure that it can accurately reflect the relationship between the vaccination dose and the immune response, and provide a reliable basis for the formulation of vaccination plans.

[0161] In an embodiment of the present invention, the step of calculating the curve fit coefficient between the actual curve of the third antibody level and the predicted curve of the third antibody level includes:

[0162] calculating a difference signal between the true curve of the third antibody level and the predicted curve of the third antibody level;

[0163] Performing a fast Fourier transform on the difference signal to obtain a power spectrum distribution of the difference signal;

[0164] Calculating the Shannon entropy of the power spectrum distribution of the difference signal;

[0165] Calculating the fractal dimensions of the true curve of the third antibody level and the predicted curve of the third antibody level using a preset algorithm to obtain the fractal dimension of the predicted curve and the fractal dimension of the true curve;

[0166] Calculating a multifractal cross-correlation index between the fractal dimension of the predicted curve and the fractal dimension of the true curve;

[0167] Performing continuous wavelet transform on the true curve of the third antibody level and the predicted curve of the third antibody level to obtain a wavelet coefficient matrix of the predicted curve and a wavelet coefficient matrix of the true curve;

[0168] Extracting the instantaneous phases of the predicted curve wavelet coefficient matrix and the true curve wavelet coefficient matrix and calculating the phase difference;

[0169] The Shannon entropy, the multifractal cross-correlation index and the phase difference are weightedly fused to obtain a curve fitting coefficient.

[0170] In detail, the difference signal between the true curve of the third antibody level and the predicted curve of the third antibody level is calculated by calculating the algebraic difference between the true curve of the third antibody level and the predicted curve point by point to generate a residual signal sequence, which is essentially a time domain expression of the prediction error.

[0171] Specifically, performing a fast Fourier transform on the difference signal converts the time-domain error into a frequency-domain energy distribution. The squared amplitude of each frequency component in the power spectrum represents the energy contribution of the error in that frequency band. High-frequency components reflect short-term fluctuations, while low-frequency components reveal systematic deviations.

[0172] In detail, the Shannon entropy is a core concept in information theory, which is used to quantify the uncertainty or randomness of information. The larger the entropy value, the more uniform the error energy is distributed in the frequency domain; the smaller the entropy value, the more concentrated the energy is in a specific frequency band.

[0173] In detail, the fractal dimension of the third antibody level true curve and the third antibody level prediction curve is calculated using a preset algorithm. The box counting method or the Higuchi algorithm can be used to calculate the fractal dimension of the two curves. The fractal dimension is used to describe the geometric complexity of the curve.

[0174] In detail, the multifractal cross-correlation index between the fractal dimension of the predicted curve and the fractal dimension of the true curve can be calculated by detrending the two curves, calculating the fluctuation function at multiple scales, and finally fitting the scaling index.

[0175] In detail, the continuous wavelet transform is performed on the true curve of the third antibody level and the predicted curve of the third antibody level, and a time-frequency decomposition is performed on the two curves using a Morlet wavelet basis to generate a time-varying wavelet coefficient matrix.

[0176] Specifically, the instantaneous phase is used in wavelet transform to represent the phase information of a signal at different scales (frequencies) and positions. It is an important feature extracted from complex wavelet coefficients and can reflect the instantaneous variation characteristics of the signal.

[0177] In detail, the Shannon entropy, the multifractal cross-correlation index and the phase difference are weightedly fused to obtain the curve fitting coefficient, and weights of 0.4, 0.3 and 0.3 are assigned to the weighted fusion respectively.

[0178] S5. Based on the dose-sensitive factor, the data on the decay of antibody levels corresponding to different doses over time are integrated to obtain a multi-dimensional dose antibody level decay curve. The multi-dimensional dose antibody level decay curve is visualized using data visualization technology to obtain a multi-dimensional dose antibody level decay visualization curve. The compliant dose is identified based on the multi-dimensional dose antibody level decay visualization curve.

[0179] In an embodiment of the present invention, the data on the decay of antibody levels corresponding to different doses over time are integrated based on the dose-sensitive factor to obtain a multi-dimensional dose antibody level decay curve, and the multi-dimensional dose antibody level decay curve is visualized using data visualization technology to obtain a multi-dimensional dose antibody level decay visualization curve. After completing the accuracy verification of the dose-sensitive factor and confirming its effectiveness, the antibody level decay curves corresponding to different doses (including the first and second dose real curves and the verified effective third dose prediction curve, etc.) are integrated with dose as one dimension. Through data visualization technology, data in multiple dimensions such as time, antibody level, and dose are presented in a graphical manner to construct a multi-dimensional dose antibody level decay visualization curve, such as using a three-dimensional coordinate system, with the horizontal axis representing time, the vertical axis representing antibody level, and the vertical axis representing vaccine dose, or a dynamic interactive chart is used to display the decay changes of antibody levels over time at different doses.

[0180] In an embodiment of the present invention, the compliant dose is identified based on the multi-dimensional dose antibody level attenuation visualization curve. In this visualization curve, by setting medical standards and clinical goals, such as meeting the duration of the minimum effective antibody concentration, the antibody decay rate threshold and other conditions, the dosage range that meets the requirements is identified. The dose within this range is the compliant dose, providing an intuitive and scientific decision-making basis for personalized vaccination plans.

[0181] like Figure 2, which is a functional module diagram of a data visualization system for influenza vaccine clinical trials provided by one embodiment of the present invention.

[0182] The data visualization system 100 for influenza vaccine clinical trials described herein can be installed in an electronic device. Depending on the functionality implemented, the data visualization system 100 can include a data acquisition module 101, a data identification module 102, a curve prediction module 103, a data confirmation module 104, and a curve visualization module 105. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0183] In this embodiment, the functions of each module / unit are as follows:

[0184] The data acquisition module 101 is used to obtain the preset normal vital sign data of the vaccinated person, and obtain the first vital sign data of the vaccinated person after receiving the first preset dose of vaccine and the second vital sign data of the vaccinated person after receiving the second preset dose of vaccine;

[0185] The data identification module 102 is configured to perform immune response analysis by comparing the normal vital sign data with the first vital sign data to obtain a first immune response intensity curve, perform immune response analysis by comparing the normal vital sign data with the second vital sign data to obtain a second immune response intensity curve, construct a first antibody level attenuation curve based on the antibody titer included in the first vital sign data, construct a second antibody level attenuation curve based on the antibody titer included in the second vital sign data, and perform normalization processing on the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve to obtain a normalized curve. normalizing a first intensity curve, a normalized second intensity curve, a normalized first attenuation curve, and a normalized second attenuation curve, calculating a dose-response gain ratio based on the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve, calculating a time synergy coefficient based on the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve, calculating an absolute value of a difference between the first preset dose and the second preset dose to obtain a dose difference, multiplying the dose difference by the dose-response gain ratio and dividing the result by the time synergy coefficient to obtain a dose sensitivity factor;

[0186] The curve prediction module 103 is used to predict the third antibody level prediction curve of the vaccine recipient after receiving the preset third dose of vaccine based on the dose-sensitive factor;

[0187] The data confirmation module 104 is configured to confirm the dose sensitivity factor by performing an accuracy check on the third antibody level prediction curve;

[0188] The curve visualization module 105 is used to integrate the data on the decay of antibody levels corresponding to different doses over time based on the dose sensitivity factor to obtain a multi-dimensional dose antibody level decay curve, use data visualization technology to visualize the multi-dimensional dose antibody level decay curve to obtain a multi-dimensional dose antibody level decay visualization curve, and identify the compliant dose based on the multi-dimensional dose antibody level decay visualization curve.

[0189] In detail, each module in the data visualization system 100 for the influenza vaccine clinical trial according to the embodiment of the present invention is used in the same manner as described above. Figure 1 The data visualization method in the influenza vaccine clinical trial described in

[15] is a similar technical method and can produce the same technical effect, so it will not be repeated here.

[0190] In the embodiments provided herein, it should be understood that the disclosed devices, systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical functional division, and actual implementation may employ other division methods.

[0191] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0192] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0193] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0194] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0195] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0196] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems recited in a system claim may also be implemented by a single unit or system through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0197] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A data visualization method for influenza vaccine clinical trials, characterized in that: The method comprises: Obtaining preset normal vital sign data of the vaccinated person, obtaining first vital sign data of the vaccinated person after receiving the first preset dose of vaccine and second vital sign data of the vaccinated person after receiving the second preset dose of vaccine; An immune response analysis is performed by comparing the normal physical sign data with the first physical sign data to obtain a first immune response intensity curve. An immune response analysis is performed by comparing the normal physical sign data with the second physical sign data to obtain a second immune response intensity curve. A first antibody level attenuation curve is constructed according to the antibody titer contained in the first physical sign data. A second antibody level attenuation curve is constructed according to the antibody titer contained in the second physical sign data. The first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve are normalized to obtain a normalized first intensity curve. a normalized second intensity curve, a normalized first attenuation curve, and a normalized second attenuation curve; calculating a dose-response gain ratio according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating a time synergy coefficient according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating an absolute value of a difference between the first preset dose and the second preset dose to obtain a dose difference; multiplying the dose difference by the dose-response gain ratio and then dividing the result by the time synergy coefficient to obtain a dose sensitivity factor; Predicting a third antibody level prediction curve of the vaccinated person after receiving a preset third dose of vaccine based on the dose-sensitive factor; Confirming the dose sensitivity factor by performing accuracy verification on the third antibody level prediction curve; Based on the dose-sensitive factor, the data on the decay of antibody levels corresponding to different doses over time are integrated to obtain a multi-dimensional dose antibody level decay curve. The multi-dimensional dose antibody level decay curve is visualized using data visualization technology to obtain a multi-dimensional dose antibody level decay visualization curve. The compliant dose is identified based on the multi-dimensional dose antibody level decay visualization curve.

2. The data visualization method for influenza vaccine clinical trials according to claim 1, characterized in that: The step of performing immune response analysis by comparing the normal vital sign data with the first vital sign data to obtain a first immune response intensity curve includes: Performing time series alignment on the normal vital sign data and the first vital sign data to obtain aligned normal vital sign data and aligned first vital sign data; Calculating the dynamic difference between the aligned normal vital sign data and the aligned first vital sign data at each time point to obtain a difference sequence; identifying the normal vital sign data and peak vital sign data in the first vital sign data; performing normalization processing on the difference sequence based on the peak vital sign data to obtain a normalized difference sequence; Performing weighted fusion on the body temperature, blood pressure, and heart rate corresponding to each difference group in the normalized difference sequence to obtain a quantitative indicator sequence; A first immune response intensity curve is constructed according to the quantitative index sequence.

3. The data visualization method for influenza vaccine clinical trials according to claim 1, characterized in that: Calculating the dose-response gain ratio according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve includes: Obtaining a first intensity peak value in the normalized first intensity curve, and obtaining a second intensity peak value in the normalized second intensity curve; Calculating the areas under the normalized first intensity curve and the normalized second intensity curve to obtain a first total intensity and a second total intensity; Identifying half-life durations of the normalized first attenuation curve and the normalized second attenuation curve to obtain a first duration and a second duration; identifying the steady-state concentration of the antibody according to the normalized first decay curve and the normalized second decay curve to obtain a first concentration and a second concentration; Calculating a ratio of the second intensity peak to the first intensity peak to obtain a peak ratio; calculating a ratio of the second total intensity to the first total intensity to obtain a total intensity ratio; Calculating a ratio of the second duration to the first duration to obtain a duration ratio; calculating a ratio of the second concentration to the first concentration to obtain a concentration ratio; Multiplying the peak value ratio and the total intensity ratio by a preset first weight parameter and a preset second weight parameter respectively and then adding the results to obtain a numerator term; Multiplying the duration ratio and the concentration ratio by the preset first weight parameter and the second weight parameter respectively and then adding them together to obtain a denominator; The ratio of the numerator term to the denominator term is calculated to obtain the dose-response gain ratio.

4. The data visualization method for influenza vaccine clinical trials according to claim 1, wherein: Calculating a time coordination coefficient according to the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve includes: identifying an intersection point between the normalized first intensity curve and the normalized second intensity curve to obtain a first intersection time; identifying an intersection point of the normalized first attenuation curve and the normalized second attenuation curve to obtain a second intersection time; Identifying peak time points of the normalized first intensity curve and the normalized second intensity curve to obtain a first intensity peak time point and a second intensity peak time point; Identifying the peak time points of the normalized first attenuation curve and the normalized second attenuation curve to obtain a first concentration peak time point and a second concentration peak time point; Calculate the absolute time difference between the first intersection time and the first intensity peak time point and the second intensity peak time point respectively to obtain a first intensity curve time difference and a second intensity curve time difference; Calculate the absolute time difference between the second intersection time and the first concentration peak time, and the second concentration peak time to obtain a first attenuation curve time difference and a second attenuation curve time difference; A time coordination coefficient is calculated according to the first intensity curve time difference, the second intensity curve time difference, the first attenuation curve time difference, and the second attenuation curve time difference.

5. The data visualization method for influenza vaccine clinical trials according to claim 4, characterized in that: Calculating a time coordination coefficient by using the first attenuation curve time difference and the second attenuation curve time difference includes: Multiplying the first intensity curve time difference by a preset intensity sensitivity coefficient to obtain a first intensity product term; performing an exponential operation on the inverse of the first intensity product term using a preset exponential function to obtain a first intensity exponential term; multiplying the second intensity curve time difference by a preset intensity sensitivity coefficient to obtain a second intensity product term; performing an exponential operation on the inverse of the second intensity product term using a preset exponential function to obtain a second intensity index term; Multiplying the first attenuation curve time difference by a preset attenuation sensitivity coefficient to obtain a first attenuation product term; performing an exponential operation on the inverse of the first attenuation product term using a preset exponential function to obtain a first attenuation exponential term; Multiplying the second attenuation curve time difference by a preset attenuation sensitivity coefficient to obtain a second attenuation product term; performing an exponential operation on the inverse of the second attenuation product term using a preset exponential function to obtain a second attenuation exponential term; Calculating a mean of the first intensity index term and the second intensity product term and multiplying the result by a preset intensity weight coefficient to obtain an intensity weight term; Calculating the mean of the first attenuation exponent term and the second attenuation exponent term and multiplying the calculated mean by a preset attenuation weight coefficient to obtain an attenuation weight term; The intensity weight term and the attenuation weight term are summed to obtain the time coordination coefficient.

6. The data visualization method for influenza vaccine clinical trials according to claim 1, characterized in that: The confirming the dose sensitivity factor by performing accuracy verification on the third antibody level prediction curve includes: Obtaining the third vital sign data of the vaccinated person after receiving the preset third dose of vaccine; constructing a third antibody level true curve according to the third physical sign data; Calculating a curve fit coefficient between the true curve of the third antibody level and the predicted curve of the third antibody level; Determining whether the curve fitting coefficient is greater than a preset coefficient threshold; If the curve fitting coefficient is greater than the coefficient threshold, the dose sensitivity factor is confirmed to be valid; If the curve fitting coefficient is less than or equal to the coefficient threshold, the dose-sensitive factor is fine-tuned and the third antibody level prediction curve of the vaccinated person after receiving the preset third dose of vaccine is re-predicted based on the dose-sensitive factor to obtain a fine-tuned third antibody level prediction curve; The dose-sensitive factor was confirmed by performing an accuracy check on the fine-tuned third antibody level prediction curve.

7. The data visualization method for influenza vaccine clinical trials according to claim 6, characterized in that: Calculating the curve fitting coefficient between the true curve of the third antibody level and the predicted curve of the third antibody level includes: calculating a difference signal between the true curve of the third antibody level and the predicted curve of the third antibody level; Performing a fast Fourier transform on the difference signal to obtain a power spectrum distribution of the difference signal; Calculating the Shannon entropy of the power spectrum distribution of the difference signal; Calculating the fractal dimensions of the true curve of the third antibody level and the predicted curve of the third antibody level using a preset algorithm to obtain the fractal dimension of the predicted curve and the fractal dimension of the true curve; Calculating a multifractal cross-correlation index between the fractal dimension of the predicted curve and the fractal dimension of the true curve; Performing continuous wavelet transform on the true curve of the third antibody level and the predicted curve of the third antibody level to obtain a wavelet coefficient matrix of the predicted curve and a wavelet coefficient matrix of the true curve; Extracting the instantaneous phases of the predicted curve wavelet coefficient matrix and the true curve wavelet coefficient matrix and calculating the phase difference; The Shannon entropy, the multifractal cross-correlation index and the phase difference are weightedly fused to obtain a curve fitting coefficient.

8. A data visualization system for influenza vaccine clinical trials, characterized in that: The system comprises: A data acquisition module is used to obtain the preset normal vital sign data of the vaccinated person, obtain the first vital sign data of the vaccinated person after receiving the first preset dose of vaccine, and obtain the second vital sign data of the vaccinated person after receiving the second preset dose of vaccine; A data identification module is used to perform immune response analysis by comparing the normal physical sign data with the first physical sign data to obtain a first immune response intensity curve, perform immune response analysis by comparing the normal physical sign data with the second physical sign data to obtain a second immune response intensity curve, construct a first antibody level attenuation curve according to the antibody titer contained in the first physical sign data, construct a second antibody level attenuation curve according to the antibody titer contained in the second physical sign data, and normalize the first immune response intensity curve, the second immune response intensity curve, the first antibody level attenuation curve, and the second antibody level attenuation curve to obtain a normalized a first intensity curve, a normalized second intensity curve, a normalized first attenuation curve, and a normalized second attenuation curve; calculating a dose-response gain ratio based on the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating a time synergy coefficient based on the normalized first intensity curve, the normalized second intensity curve, the normalized first attenuation curve, and the normalized second attenuation curve; calculating an absolute value of a difference between the first preset dose and the second preset dose to obtain a dose difference; multiplying the dose difference by the dose-response gain ratio and then dividing the result by the time synergy coefficient to obtain a dose sensitivity factor; A curve prediction module, configured to predict a third antibody level prediction curve of the vaccinated person after receiving a preset third dose of vaccine based on the dose-sensitive factor; a data confirmation module, configured to confirm the dose sensitivity factor by performing an accuracy check on the third antibody level prediction curve; The curve visualization module is used to integrate the data of antibody level decay over time corresponding to different doses based on the dose-sensitive factor to obtain a multi-dimensional dose antibody level decay curve, and use data visualization technology to visualize the multi-dimensional dose antibody level decay curve to obtain a multi-dimensional dose antibody level decay visualization curve, and identify the compliant dose based on the multi-dimensional dose antibody level decay visualization curve.

Images