Intelligent control system of tumor electric field treatment device

Abstract

The invention relates to the technical field of intelligent control systems, in particular to an intelligent control system of a tumor electric field treatment device, which comprises a resistivity acquisition module for measuring tumor electrical impedance under differentiated frequencies by using a four-electrode measuring instrument, recording resistivity data changing along with time, enhancing the signal-to-noise ratio of signals by using a differential amplification technology, and acquiring the tumor electrical impedance by using the resistivity acquisition module; and calibrating the reading of the instrument, and generating a calibrated resistivity parameter set. According to the method, by analyzing the correlation between tumor electrical impedance and gene expression data, accurate adjustment of treatment electric field parameters is achieved, the treatment pertinence and the treatment effect are improved, the method allows personalized adjustment of a treatment scheme according to specific biomarkers of tumors, optimal matching of the electric field parameters and specific tumor characteristics of patients is ensured, and the treatment effect is improved. The application of clustering analysis realizes fine group division in patients with different tumor types or stages, so that the electric field treatment can be optimized according to specific tumor biological behaviors, and the phenomenon of one-time cutting possibly occurring in traditional treatment is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control systems, and in particular to an intelligent control system for a tumor electric field treatment device. Background Art

[0002] The field of intelligent control system technology is an interdisciplinary field involving electronic engineering, computer science and cybernetics, focusing on the development of technical solutions that can automatically perform tasks and optimize performance. The core of this field is to create systems that can receive environmental input (through sensors), process this data (through computer programs) and perform corresponding actions (through actuators). Intelligent control systems are widely used in industrial automation, robotics, aerospace, vehicle power management systems, etc., continuously promoting technological innovation and efficiency improvement. By integrating artificial intelligence and machine learning technologies, these systems can learn from experience and improve their decision-making processes to adapt to changing operating conditions and environmental challenges.

[0003] Among them, the intelligent control system of the tumor electric field treatment device refers to a specific device used for cancer treatment, which is a system that inhibits the growth of tumor cells or induces cell death by exerting influence on them by using electric fields. The purpose of this technology is mainly to provide a non-invasive cancer treatment method, which can be used alone or in combination with traditional chemotherapy, radiotherapy and other methods. The role of the intelligent control system here is to accurately control the intensity, frequency and direction of the electric field to ensure the maximum effect of the treatment while reducing potential damage to healthy cells.

[0004] Existing technologies have obvious deficiencies in personalized treatment. The lack of in-depth understanding of tumor biological differences often leads to the generalization of treatment plans, which may not only affect the treatment effect, but also increase the risk of damage to non-target cells. In addition, due to the lack of real-time data processing and instant feedback capabilities, traditional technologies are unable to adjust treatment parameters based on the patient's current condition, limiting their ability to cope with complex and changing clinical situations. This technological lag often leads to inaccurate treatment, and may even aggravate the patient's condition due to inappropriate electric field settings, thereby affecting the overall treatment effectiveness. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent control system for a tumor electric field treatment device.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: An intelligent control system of a tumor electric field treatment device comprises:

[0007] The resistivity acquisition module uses a four-electrode measuring instrument to measure the electrical impedance of the tumor under differential frequencies, records the resistivity data that changes over time, uses differential amplification technology to enhance the signal-to-noise ratio of the signal, calibrates the instrument readings, and generates a calibrated resistivity parameter set;

[0008] The feature fusion module obtains gene expression data of tumor cells, including tumor suppressor gene expression, tumor promoter gene expression, cell cycle regulatory gene expression, and signal transduction pathway gene expression, and uses orthogonal signal processing technology to screen gene features associated with resistivity changes, and fuses the calibrated resistivity parameter set with the screened gene data to form a gene resistance feature set;

[0009] The sensitive clustering module uses the Euclidean distance to measure the fit between samples in the gene resistance feature set, divides the samples into similar groups based on the density peak method, determines the core samples of multiple groups through cluster analysis, and obtains sample clustering grouping;

[0010] The electric field adjustment module analyzes the resistivity change trends of multiple groups according to the sample clustering grouping, refers to the tumor type and biological response data, fine-tunes the electric field frequency and intensity, sends parameter adjustment commands, and generates individualized electric field configurations.

[0011] As a further solution of the present invention, the steps of obtaining the calibrated resistivity parameter set are specifically as follows:

[0012] Configure the differentiated frequencies of the four-electrode measuring instrument, set the measurement parameters to match multiple frequency ranges, start the device to collect the original resistance values ​​under multiple frequencies, and obtain the original resistance data set;

[0013] Synchronously record the measurement time of each resistance value, construct a time series database, arrange the original resistance data set in chronological order, and generate a time-varying resistivity data set;

[0014] The differential amplification technique was applied to enhance the signal of the time-varying resistivity data set, the amplification factor was adjusted and the noise suppression algorithm was applied to optimize the signal clarity, using the formula:

[0015]

[0016] Calculate the enhanced signal strength and generate an enhanced signal data set;

[0017] Among them, R enhanced Indicates the enhanced signal strength, V input Represents the input voltage, which is related to the original reading of the device, G represents the amplification factor of the signal, N is the noise voltage, and S is the signal voltage;

[0018] The instrument reading error is adjusted using the calibration parameters, and data calibration is performed according to the enhanced signal data set to obtain a calibrated resistivity parameter set.

[0019] As a further solution of the present invention, the steps of obtaining the genetic resistance feature set are specifically as follows:

[0020] Extract RNA from tumor cells, sequence them using high-throughput sequencing technology, extract gene expression information including tumor suppression, promotion, cell cycle regulation and signal transduction from the sequencing data, and generate a gene expression data set;

[0021] Analyzing the gene expression data set, applying orthogonal signal processing technology to identify gene features significantly associated with resistivity changes, screening key gene expression patterns, and generating a key gene feature data set;

[0022] The calibrated resistivity parameter set and the key gene feature data set were integrated, and multivariate statistical methods were used to ensure data consistency and integrity, using the formula:

[0023]

[0024] Among them, G res represents the gene resistance feature set, E i is the multi-parameter value in the resistivity parameter set, D j is the multi-feature value in the key gene feature dataset, α i and β j is the weight coefficient for adjusting the proportion of resistance parameters and gene features in the integration, N is the normalization factor of the weight, and the gene resistance feature set is generated.

[0025] As a further solution of the present invention, the steps of obtaining the sample clustering groups are specifically as follows:

[0026] Calculating the Euclidean distances between multiple samples in the genetic resistance feature set, establishing a distance matrix to evaluate the fit between samples, and generating a distance matrix between samples;

[0027] Applying the density peak method to the distance matrix between the samples, classifying the samples into similar groups according to local density and distance parameters, and generating preliminary sample clustering data;

[0028] By identifying clustering information from the preliminary sample clustering data, the core samples of each group are determined, and cluster analysis is performed to refine the identification of the core samples, using the Gaussian kernel weighted formula:

[0029]

[0030] Determine sample clustering grouping;

[0031] Among them, C core represents the core sample set, d iis the distance from sample i to the nearest high-density point determined from the distance matrix, μ is the mean of the sample distances, σ is the standard deviation of the distances, and w i is the density-based sample weight.

[0032] As a further solution of the present invention, the steps of obtaining the individualized electric field configuration are specifically:

[0033] Analyzing the sample clustering groups, monitoring the resistivity change trends within the multiple groups, and subdividing the resistivity response of each tumor type according to the trend analysis results to generate trend analysis results;

[0034] combining the trend analysis results with tumor type and biological response data to evaluate the need for adjustment of electric field frequency and intensity and propose electric field adjustment plans for each tumor type;

[0035] According to the electric field adjustment scheme, the current electric field frequency and intensity parameters are calculated and optimized using the formula:

[0036]

[0037] Adjusting electric field parameters based on tumor response data to generate individualized electric field configurations;

[0038] Among them, P new is the individualized electric field configuration, P current is the current parameter, α is the coefficient adjusted based on tumor response sensitivity, ΔR is the recommended resistivity change, and R base is the baseline resistivity.

[0039] Compared with the prior art, the advantages and positive effects of the present invention are:

[0040] In the present invention, by carefully analyzing the correlation between tumor electrical impedance and gene expression data, precise adjustment of the therapeutic electric field parameters is achieved, thereby improving the pertinence and effectiveness of the treatment. This method allows the treatment plan to be personalized according to the specific biomarkers of the tumor, ensuring the best match between the electric field parameters and the patient's specific tumor characteristics. The application of cluster analysis achieves a fine group division among patients with different tumor types or stages, allowing electric field therapy to be optimized according to the specific biological behavior of the tumor. This method reduces potential damage to healthy cells and significantly improves the safety and effectiveness of the treatment, avoiding the one-size-fits-all phenomenon that may occur in traditional treatments. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a system flow chart of the present invention;

[0042] Figure 2 A flow chart of the steps for obtaining the calibrated resistivity parameter set of the present invention;

[0043] Figure 3 A flowchart of the steps for obtaining the gene resistance feature set of the present invention;

[0044] Figure 4 A flow chart of the steps for obtaining sample clustering groups of the present invention;

[0045] Figure 5 Flow chart of the steps for obtaining individualized electric field configuration of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. 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.

[0047] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0048] Embodiment 1

[0049] See also Figure 1 , an intelligent control system of a tumor electric field treatment device comprises:

[0050] The resistivity acquisition module uses a four-electrode measuring instrument to measure the electrical impedance of the tumor under differential frequencies, records the resistivity data that changes over time, uses differential amplification technology to enhance the signal-to-noise ratio of the signal, calibrates the instrument readings, and generates a calibrated resistivity parameter set;

[0051] The feature fusion module obtains the gene expression data of tumor cells, including tumor suppressor gene expression, tumor promoter gene expression, cell cycle regulatory gene expression, and signal transduction pathway gene expression, and uses orthogonal signal processing technology to screen gene features associated with resistivity changes, and fuses the calibrated resistivity parameter set with the screened gene data to form a gene resistance feature set;

[0052] The sensitive clustering module uses the Euclidean distance to measure the fit between samples in the gene resistance feature set, divides the samples into similar groups based on the density peak method, determines the core samples of multiple groups through cluster analysis, and obtains sample clustering grouping;

[0053] The electric field adjustment module analyzes the resistivity change trends of multiple groups according to sample clustering and grouping, refers to tumor type and biological response data, fine-tunes the electric field frequency and intensity, sends parameter adjustment commands, and generates individualized electric field configurations.

[0054] The calibrated resistivity parameter set specifically includes tumor electrical impedance, resistivity time series, and signal-to-noise ratio. The gene impedance feature set specifically includes tumor suppressor gene features, tumor promoting gene features, cell cycle regulatory gene features, and signal transduction gene features. The sample clustering grouping specifically includes the Euclidean distance between samples, density peak classification, and core sample identification. The individualized electric field configuration includes adjusted electric field frequency, electric field strength, and biological response parameters.

[0055] See also Figure 2 , the specific steps for obtaining the calibrated resistivity parameter set are:

[0056] Configure the differentiated frequencies of the four-electrode measuring instrument, set the measurement parameters to match multiple frequency ranges, start the device to collect the original resistance values ​​under multiple frequencies, and obtain the original resistance data set;

[0057] Begin by configuring the frequency settings of the four-electrode measuring instrument. First, adjust the equipment parameters to match the differentiated test frequency, including the adjustment of the current intensity and the fine-tuning of the electrode position, to ensure that the current is evenly distributed on the test sample at the differentiated frequency, thereby ensuring the accuracy and consistency of the measurement data. Next, start the equipment and monitor the data output in real time to ensure that data collection at all frequencies is within the control range, optimize the data collection process, and obtain the original resistance data set through adjustments.

[0058] The measurement time of each resistance value is recorded synchronously, a time series database is constructed, the original resistance data set is arranged in chronological order, and a time-varying resistivity data set is generated;

[0059] Based on the timestamps of the recorded resistance values, a time series database is organized and constructed. By sorting the time tags of the original resistance data set, the time series function in the database management system is used to ensure that the data can be stored and accessed in the order of the actual collection time, including data cleaning, removing data items with incorrect or duplicate time tags, and optimizing the query efficiency of the database, so as to respond to data call requests and generate a structured time-varying resistivity data set.

[0060] The differential amplification technique was applied to enhance the signal of the time-varying resistivity data set, the amplification factor was adjusted and the noise suppression algorithm was applied to optimize the signal clarity, using the formula:

[0061]

[0062] Calculate the enhanced signal strength and generate an enhanced signal data set;

[0063] Among them, R enhanced Indicates the enhanced signal strength, V input Represents the input voltage, which is related to the original reading of the device, G represents the amplification factor of the signal, N is the noise voltage, and S is the signal voltage;

[0064] formula:

[0065]

[0066] The benefit of the formula is that it optimizes signal clarity by integrating the signal and noise ratio, effectively enhancing the signal, making the resistance measurement more accurate and reflecting more subtle changes, which is extremely critical in medical and industrial applications.

[0067] Detailed explanation of the formula and the process of formula calculation and derivation:

[0068] In a measurement, the input voltage V input The voltage is 0.5 volts, the amplification factor G is set to 10 times, the noise voltage N is 0.05 volts, and the signal voltage S is 0.45 volts. Substitute the formula to calculate the enhanced signal strength:

[0069]

[0070] R enhanced =4.969

[0071] The results show that the use of the formula can effectively improve the quality of the measurement signal and obtain clearer and more accurate resistance measurement results, which is of key significance for diagnosis and monitoring.

[0072] The instrument reading error is adjusted using the calibration parameters, and data calibration is performed based on the enhanced signal data set to obtain the calibrated resistivity parameter set.

[0073] In the process of applying calibration parameters for data calibration, we first conduct error analysis based on the enhanced signal data set obtained in the previous step, including statistically analyzing the deviation and fluctuation range of each data point, and using the calibration algorithm to correct each measurement value. Through this series of operations, the measurement error is reduced, the accuracy and reliability of the data are improved, and it is ensured that the calibrated resistivity parameter set can reflect the actual physical properties, providing a solid data foundation for subsequent applications and research.

[0074] See also Figure 3 , the specific steps for obtaining the gene resistance feature set are:

[0075] Extract RNA from tumor cells, sequence them using high-throughput sequencing technology, extract gene expression information including tumor suppression, promotion, cell cycle regulation and signal transduction from the sequencing data, and generate a gene expression data set;

[0076] After extracting RNA from tumor cells and performing high-throughput sequencing, expression data of multiple types of tumor-associated genes were obtained. These data were initially screened to eliminate sequences that did not meet quality standards, ensuring the quality and reliability of the data set and laying the foundation for the next step of analysis. Some sequences were verified by quantitative PCR to verify the authenticity and consistency of the data. This process ensured the scientific nature of the data and provided basic information for subsequent gene expression pattern analysis.

[0077] Analyze gene expression data sets, apply orthogonal signal processing techniques to identify gene features significantly associated with resistivity changes, screen key gene expression patterns, and generate key gene feature data sets;

[0078] To analyze the gene expression data set, orthogonal signal processing technology was used to preprocess the data first, including standardization, denoising and outlier processing. This step improved the accuracy of data analysis. Statistical methods and machine learning algorithms were then used to identify gene features that were significantly associated with resistivity changes. The identification of key genes relied on mathematical models and algorithms to ensure the accuracy and repeatability of the screening process. The generated key gene feature data set provided the core input for the next step of data fusion and analysis.

[0079] The calibrated resistivity parameter set and key gene feature data set were integrated, and multivariate statistical methods were used to ensure data consistency and integrity. The formula was used:

[0080]

[0081] Among them, G res represents the gene resistance feature set, E i is the multi-parameter value in the resistivity parameter set, D j is the multi-feature value in the key gene feature dataset, α i and β j is the weight coefficient for adjusting the proportion of resistance parameters and gene features in the integration, N is the normalization factor of the weight, and the gene resistance feature set is generated.

[0082] formula:

[0083]

[0084] The benefit of the formula is that by combining the weight coefficients of resistivity parameters and gene expression data, the correlation between resistance changes and gene expression of tumor cells can be evaluated, which can enhance the explanatory power and prediction accuracy of the model. The detailed explanation of the formula and the derivation process of the formula calculation are as follows:

[0085] There are three resistivity parameters E1, E2, and E3 set to 100, 150, and 200 respectively, and two gene expression features D1 and D2 set to 0.8 and 0.6 respectively, and the weight coefficient α i and β j According to previous bioinformatics studies, the values ​​were set to 1.2 and 0.9, and the normalization factor N was set to 5. The calculation process is as follows:

[0086]

[0087] The results showed that the value of the gene resistance feature set was 108.252, which means that after comprehensive reference to resistivity parameters and gene expression features, the resistance characteristic expression value of tumor cells was 108.252, which can be used in biomedical research and clinical applications to predict tumor behavior and its response to treatment.

[0088] See also Figure 4 , the specific steps for obtaining sample clustering groups are:

[0089] Calculate the Euclidean distance between multiple samples in the gene resistance feature set, establish a distance matrix to evaluate the fit between samples, and generate a distance matrix between samples;

[0090] By measuring the distance between samples in the gene resistance feature set, the Euclidean distance is calculated to generate a distance matrix. Based on the distance matrix, the density peak method is used to perform preliminary sample classification processing, so as to evaluate the fit between each other according to the Euclidean distance between samples. This step is completed by measuring and recording the straight-line distance of the feature differences between multiple samples. Each sample is represented by its multidimensional data point of gene expression, and the distance calculation formula between each point is where x i1 and x i2 are the expression values ​​of the two samples in the i-th dimension respectively. Such processing is not only to divide the samples, but also to determine the fit and difference between the samples. Cluster analysis will identify potential similar patterns based on the differences and generate a distance matrix between the samples.

[0091] Apply the density peak method to the distance matrix between samples, classify the samples into similar groups by local density and distance parameters, and generate preliminary sample clustering data;

[0092] By applying the density peak method to analyze the generated distance matrix, the samples are classified according to their local density and relative distance to samples with higher density, generating preliminary sample clustering data. In this step, the local density of each sample is first calculated, and how many samples around it are within a certain radius. Then, the distance from each sample to the nearest sample with higher density is calculated. These distances and density information are used together to determine the classification of the sample. For example, a sample is a boundary point if it is densely surrounded but far from high-density samples. This method assists in identifying cluster centers and isolated points, providing an effective means to divide sample groups with similar gene expression characteristics.

[0093] By identifying clustering information from preliminary sample clustering data, the core samples of each group are determined, and cluster analysis is performed to refine the identification of core samples. The Gaussian kernel weighted formula is used:

[0094]

[0095] Determine sample clustering grouping;

[0096] Among them, C core represents the core sample set, d i is the distance from sample i to the nearest high-density point determined from the distance matrix, μ is the mean of the sample distances, σ is the standard deviation of the distances, and w i is the density-based sample weight.

[0097] formula:

[0098]

[0099] The benefit of the formula is that by combining the weight of each sample with a Gaussian function of its distance to the nearest high-density sample, the core samples in the cluster are identified, which increases the flexibility and accuracy of the clustering algorithm when dealing with data sets with distributions.

[0100] Detailed explanation of the formula and the process of formula calculation and derivation:

[0101] Suppose there is a data set, which includes samples S1, S2, S3, whose corresponding distances are d1=0.5, d2=1.5, d3=0.2, average distance μ=0.73, standard deviation σ=0.65, and weights w1=0.9, w2=0.5, w3=1.0. Calculate the value of the core sample set:

[0102]

[0103] C core =0.9·exp(-0.126)+0.5·exp(-1.414)+1.0·exp(-0.421)

[0104] C core =0.9·0.881+0.5·0.243+1.0·0.657

[0105] C core =0.793+0.1215+0.657

[0106] C core =1.5715

[0107] The results show that the weighted sum of the core sample set is 1.5715, which reflects the importance of the samples after weighting according to density and distance.

[0108] See also Figure 5 , the specific steps for obtaining the individualized electric field configuration are:

[0109] Analyze sample clustering and grouping, monitor resistivity change trends within multiple groups, and subdivide the resistivity response of each tumor type based on trend analysis results to generate trend analysis results;

[0110] By analyzing the resistivity change trend, the tumor type data of each cluster group is combined with the time series resistivity data, and the response characteristics of each tumor are analyzed. In this way, the tumor type that is most sensitive to the target electric field change is identified. In this analysis process, the key relies on time series data and statistical analysis. By normalizing the data, calculating the standard deviation and mean, analyzing the resistivity fluctuation pattern, and its correlation with tumor biomarkers, not only the accuracy of diagnosis is improved, but also a scientific basis is provided for the subsequent adjustment of the electric field strength, so that each tumor type can obtain the treatment parameters that best suit its characteristics.

[0111] Combine trend analysis results with tumor type and biological response data to assess the need for adjustment of electric field frequency and intensity and propose electric field adjustment plans for each tumor type;

[0112] Based on the results of the resistivity change trend analysis, combined with tumor type and biological response data, the responses of differentiated tumors to electric field adjustment were systematically evaluated. By adjusting the electric field parameters, it was ensured that each tumor type could be treated in the optimal electric field environment. During this process, the biological characteristics of the tumor and the resistivity data were compared, and multivariate analysis technology was used to calculate the predictive model for electric field frequency and intensity adjustment. Multiple factors, including tumor growth rate, location, and treatment response data, were considered to design personalized treatment plans for each tumor, increasing the targetedness and effectiveness of the treatment.

[0113] According to the electric field adjustment plan, calculate the current electric field frequency and intensity parameters, and use the formula for optimization:

[0114]

[0115] Adjusting electric field parameters based on tumor response data to generate individualized electric field configurations;

[0116] Among them, P new is the individualized electric field configuration, P current is the current parameter, α is the coefficient adjusted based on tumor response sensitivity, ΔR is the recommended resistivity change, and R base is the baseline resistivity.

[0117] formula:

[0118]

[0119] The formula is useful in that by adjusting the coefficient α and the resistivity change ratio ΔR / R base Control parameters are adjusted so that each tumor type receives personalized treatment based on its differentiated sensitivity to electric fields, thereby enhancing the therapeutic effect.

[0120] Detailed explanation of the formula and the process of formula calculation and derivation:

[0121] Set the initial electric field parameter P current =100Hz, ΔR=0.05 (5% resistivity increase), R base =1.00, referring to the fact that some tumors are particularly sensitive to electric fields, α is set to 0.2. Substitute the values ​​into the formula for calculation:

[0122]

[0123] P new =100·(1+0.2·0.05)

[0124] P new =100·1.01=101Hz

[0125] The results suggest that the electric field frequency should be adjusted from 100 Hz to 101 Hz to provide a therapeutic setting for the tumor type.

[0126] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent control system for a tumor electric field treatment device, characterized in that: The system comprises: The resistivity acquisition module uses a four-electrode measuring instrument to measure the electrical impedance of the tumor under differential frequencies, records the resistivity data that changes over time, uses differential amplification technology to enhance the signal-to-noise ratio of the signal, calibrates the instrument readings, and generates a calibrated resistivity parameter set; The feature fusion module obtains gene expression data of tumor cells, including tumor suppressor gene expression, tumor promoter gene expression, cell cycle regulatory gene expression, and signal transduction pathway gene expression, and uses orthogonal signal processing technology to screen gene features associated with resistivity changes, and fuses the calibrated resistivity parameter set with the screened gene data to form a gene resistance feature set; The sensitive clustering module uses the Euclidean distance to measure the fit between samples in the gene resistance feature set, divides the samples into similar groups based on the density peak method, determines the core samples of multiple groups through cluster analysis, and obtains sample clustering grouping; The electric field adjustment module analyzes the resistivity change trends of multiple groups according to the sample clustering grouping, refers to the tumor type and biological response data, fine-tunes the electric field frequency and intensity, sends parameter adjustment commands, and generates individualized electric field configurations.

2. The intelligent control system of the tumor electric field treatment device according to claim 1, characterized in that: The steps for obtaining the calibrated resistivity parameter set are specifically as follows: Configure the differentiated frequencies of the four-electrode measuring instrument, set the measurement parameters to match multiple frequency ranges, start the device to collect the original resistance values ​​under multiple frequencies, and obtain the original resistance data set; Synchronously record the measurement time of each resistance value, construct a time series database, arrange the original resistance data set in chronological order, and generate a time-varying resistivity data set; The differential amplification technique was applied to enhance the signal of the time-varying resistivity data set, the amplification factor was adjusted and the noise suppression algorithm was applied to optimize the signal clarity, using the formula: Calculate the enhanced signal strength and generate an enhanced signal data set; Among them, R enhanced Indicates the enhanced signal strength, V input Represents the input voltage, which is related to the original reading of the device, G represents the amplification factor of the signal, N is the noise voltage, and S is the signal voltage; The instrument reading error is adjusted using the calibration parameters, and data calibration is performed according to the enhanced signal data set to obtain a calibrated resistivity parameter set.

3. The intelligent control system of the tumor electric field treatment device according to claim 2, characterized in that: The steps for obtaining the gene resistance feature set are specifically as follows: Extract RNA from tumor cells, sequence them using high-throughput sequencing technology, extract gene expression information including tumor suppression, promotion, cell cycle regulation and signal transduction from the sequencing data, and generate a gene expression data set; Analyzing the gene expression data set, applying orthogonal signal processing technology to identify gene features significantly associated with resistivity changes, screening key gene expression patterns, and generating a key gene feature data set; The calibrated resistivity parameter set and the key gene feature data set were integrated, and multivariate statistical methods were used to ensure data consistency and integrity, using the formula: Among them, G res represents the gene resistance feature set, E i is the multi-parameter value in the resistivity parameter set, D j is the multi-feature value in the key gene feature dataset, α i and β j is the weight coefficient for adjusting the proportion of resistance parameters and gene features in the integration, N is the normalization factor of the weight, and the gene resistance feature set is generated.

4. The intelligent control system of the tumor electric field treatment device according to claim 3, characterized in that: The steps of obtaining the sample clustering grouping are specifically as follows: Calculating the Euclidean distances between multiple samples in the genetic resistance feature set, establishing a distance matrix to evaluate the fit between samples, and generating a distance matrix between samples; Applying the density peak method to the distance matrix between the samples, classifying the samples into similar groups according to local density and distance parameters, and generating preliminary sample clustering data; By identifying clustering information from the preliminary sample clustering data, the core samples of each group are determined, and cluster analysis is performed to refine the identification of the core samples, using the Gaussian kernel weighted formula: Determine sample clustering grouping; Among them, C core represents the core sample set, d i is the distance from sample i to the nearest high-density point determined from the distance matrix, μ is the mean of the sample distances, σ is the standard deviation of the distances, and w i is the density-based sample weight.

5. The intelligent control system of the tumor electric field treatment device according to claim 4, characterized in that: The steps of obtaining the individualized electric field configuration are specifically as follows: Analyzing the sample clustering groups, monitoring the resistivity change trends within the multiple groups, and subdividing the resistivity response of each tumor type according to the trend analysis results to generate trend analysis results; combining the trend analysis results with tumor type and biological response data to evaluate the need for adjustment of electric field frequency and intensity and propose electric field adjustment plans for each tumor type; According to the electric field adjustment scheme, the current electric field frequency and intensity parameters are calculated and optimized using the formula: Adjusting electric field parameters based on tumor response data to generate individualized electric field configurations; Among them, P new is the individualized electric field configuration, P current is the current parameter, α is the coefficient adjusted based on tumor response sensitivity, ΔR is the recommended resistivity change, and R base is the baseline resistivity.

Images