Personalized parameter optimization system for transcranial magnetic stimulation therapy based on artificial intelligence

Abstract

The invention discloses a transcranial magnetic stimulation treatment individualized parameter optimization system based on artificial intelligence, and relates to the technical field of transcranial magnetic stimulation optimization systems. The transcranial magnetic stimulation treatment individualized parameter optimization system based on artificial intelligence comprises a data acquisition preprocessing module, a feature extraction module, a treatment parameter prediction module and a treatment effect evaluation module, and the data acquisition module is used for acquiring brain function data of a patient in real time; the feature extraction module is used for performing feature extraction on the preprocessed brain function data and clinical data; the treatment parameter prediction module is used for determining a treatment scheme suitable for the current condition of the patient according to the transcranial magnetic stimulation treatment parameter prediction result; the treatment effect evaluation module is used for continuously monitoring brain function data of the patient in the treatment process. The problems that in traditional transcranial magnetic stimulation treatment, parameter setting depends on experience and a general guide, individualized optimization and parameter adjustment are lacked, and consequently the treatment effect is inaccurate and the treatment time is long are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of transcranial magnetic stimulation optimization systems, and in particular to an artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system. Background Art

[0002] Transcranial magnetic stimulation is a non-invasive neuromodulation technique that uses magnetic fields to induce electric currents and activate neurons in specific areas of the brain. This technique is widely used to treat depression, anxiety, and other neuropsychiatric disorders. Although transcranial magnetic stimulation has achieved some success in clinical applications, its effectiveness depends largely on the precise setting of treatment parameters, such as the target, frequency, and intensity of stimulation. The optimization of these parameters is crucial, as improper parameter settings may lead to poor treatment effects or poor patient experience.

[0003] Traditional transcranial magnetic stimulation therapy parameter settings mostly rely on experience and generalized clinical guidelines, lacking customization for the specific needs of individual patients. In addition, the determination of parameters usually requires multiple trials and adjustments, which is not only time-consuming but also increases the treatment burden on patients. Therefore, it is particularly important to develop a system that can automatically and accurately predict and adjust treatment parameters.

[0004] In addition, although various biofeedback mechanisms are used in existing technologies to monitor treatment effects, such as electroencephalography and functional near-infrared spectroscopy, which provide valuable brain activity data, how to convert these data into specific and optimized adjustments of treatment parameters remains a technical challenge.

[0005] Therefore, in response to the above problems, there is an urgent need for an artificial intelligence-based individualized parameter optimization system for transcranial magnetic stimulation therapy. Summary of the invention

[0006] Technical issues solved

[0007] In view of the shortcomings of the prior art, the present invention provides an artificial intelligence-based individualized parameter optimization system for transcranial magnetic stimulation therapy, which solves the problems in traditional transcranial magnetic stimulation therapy that parameter setting relies on experience and generalized guidelines, lacks individualized optimization and parameter adjustment, and leads to inaccurate treatment effects and long treatment time.

[0008] Technical Solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: an artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system, comprising a data acquisition preprocessing module, a feature extraction module, a treatment parameter prediction module and a treatment effect evaluation module, wherein the data acquisition module is used to collect the patient's brain function data in real time, obtain target weights, stimulation frequency and stimulation intensity, obtain clinical data, and preprocess the brain function data and clinical data; the feature extraction module is used to extract features from the preprocessed brain function data and clinical data, and mark the extracted data as feature data; the treatment parameter prediction module is used to predict transcranial magnetic stimulation treatment parameters based on the feature data, and determine a treatment plan suitable for the patient's current condition according to the transcranial magnetic stimulation treatment parameter prediction results; the treatment effect evaluation module is used to continuously monitor the patient's brain function data during the treatment process, obtain brain function effects, evaluate treatment effects, and make corresponding optimization and adjustment measures according to the treatment effects.

[0010] Furthermore, the real-time collection of the patient's brain function data, acquisition of target weights, stimulation frequency and stimulation intensity, and acquisition of clinical data specifically involve the following process: the brain function data include brain wave data and brain region blood oxygen concentration change data, the EEG sensor is used to collect the brain wave data, the fNIRS sensor is used to collect the brain region blood oxygen concentration change data, the electroencephalogram and functional near-infrared spectroscopy are used to detect the activity of related brain regions, the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target and the medial prefrontal lobe stimulation target are selected, the appropriate stimulation frequency and stimulation intensity are selected based on the patient's electroencephalogram analysis results, and the clinical data are automatically collected through the user input system.

[0011] Furthermore, the specific process of preprocessing the brain function data and clinical data is: denoising and standardizing the brain function data and clinical data, merging the brain function data, clinical data and clinical data to generate the patient's brain function status characteristics.

[0012] Furthermore, the specific process of feature extraction of the preprocessed brain function data and clinical data is: extracting the alpha wave frequency of the occipital lobe from the EEG data, extracting the blood oxygen concentration of the left prefrontal lobe, the blood oxygen concentration of the right prefrontal lobe, the phase change of the left prefrontal cortex and the phase change of the right prefrontal cortex from the brain area blood oxygen concentration change data; obtaining the patient's clinical feedback and disease history information from the clinical data, and recording the treatment progress data from the clinic.

[0013] Furthermore, the specific process of predicting transcranial magnetic stimulation treatment parameters based on characteristic data and determining a treatment plan suitable for the patient's current condition according to the transcranial magnetic stimulation treatment parameter prediction results is as follows: obtaining the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, the medial prefrontal lobe stimulation target, the stimulation frequency, the stimulation intensity, the blood oxygen concentration of the left prefrontal lobe, the blood oxygen concentration of the right prefrontal lobe, the phase change of the left prefrontal cortex, and the phase change of the right prefrontal cortex, and obtaining the treatment parameter prediction values ​​by comprehensively calculating the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, the medial prefrontal lobe stimulation target, the stimulation frequency, the stimulation intensity, the blood oxygen concentration of the left prefrontal lobe, the blood oxygen concentration of the right prefrontal lobe, the phase change of the left prefrontal cortex, and the phase change of the right prefrontal cortex, and determining the treatment plan suitable for the patient's current condition according to the treatment parameter prediction values.

[0014] Furthermore, the specific process of determining a treatment plan suitable for the patient's current condition based on the predicted values ​​of the treatment parameters is: determining a treatment plan suitable for the patient's current condition based on the predicted values ​​of the treatment parameters, selecting a stimulation target suitable for the patient based on the predicted stimulation target, setting the frequency of the transcranial magnetic stimulation device based on the predicted stimulation frequency, and adjusting the intensity of the transcranial magnetic stimulation device based on the predicted stimulation intensity.

[0015] Furthermore, the specific calculation method of the predicted value of the treatment parameter is: Where T p represents the predicted value of the treatment parameter, represents the weighted sum of the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, and the medial prefrontal lobe stimulation target, w i represents the weight coefficient of the i-th target, α i represents the index of the i-th target, f represents the stimulation frequency, and w 4 represents the weight coefficient of the stimulation frequency, I represents the stimulation intensity, and w 5 Represents the weight coefficient of stimulus intensity, O left Indicates the blood oxygen concentration of the left frontal lobe, O right represents the blood oxygen concentration of the right frontal lobe, w 6 The weight coefficient representing the product of the cerebral blood oxygen concentration of the left and right prefrontal lobes, ΔO left represents the phase change of the left prefrontal cortex, ΔO right represents the phase change of the right prefrontal cortex, w 7 Represents the weight coefficient of the product of the time-phase changes in the left and right prefrontal cerebral blood oxygen concentrations.

[0016] Furthermore, the specific process of evaluating the treatment effect and making corresponding optimization and adjustment measures based on the treatment effect is: obtaining clinical feedback, disease history information, treatment progress data and brain function effects, obtaining a treatment effect evaluation value through comprehensive calculation of clinical feedback, disease history information, treatment progress data and brain function effects, and making corresponding optimization and adjustment measures based on the treatment effect evaluation value.

[0017] Furthermore, the specific process of making corresponding optimization and adjustment measures according to the treatment effect evaluation value is: real-time comparison of the treatment effect evaluation value and the threshold, when the treatment effect evaluation value is greater than the threshold, no adjustment is made; when the treatment effect evaluation value is less than or equal to the threshold, the specific position of the target is adjusted, the stimulation frequency is adjusted, and the stimulation intensity is adjusted until the treatment effect evaluation value is increased above the threshold.

[0018] Furthermore, the specific calculation method of the treatment effect evaluation value is: Where E t Represents the treatment effect evaluation value, R c Indicates clinical feedback, w c represents the weight coefficient of clinical feedback, R f Indicates disease history information, w f Represents the weight coefficient of disease history information, B e Indicates the effect of brain function, w b Represents the weight coefficient of brain function effect, T prog Indicates treatment progress data, w T Represents the weight coefficient of treatment progress data.

[0019] Beneficial Effects

[0020] The present invention has the following beneficial effects:

[0021] (1) The present invention realizes the accurate formulation of individualized treatment plans by collecting the patient's brain function data and clinical data in real time and combining the artificial intelligence model to predict the most suitable transcranial magnetic stimulation treatment parameters. It also achieves the effect of tailoring the treatment plan for each patient, effectively solving the problem of transcranial magnetic stimulation treatment relying on experience and lacking individualized adjustment in the prior art.

[0022] (2) The present invention combines brain wave data, brain region blood oxygen concentration change data and clinical feedback from patients, and the system can accurately predict and adjust transcranial magnetic stimulation treatment parameters, thereby achieving precise matching of treatment targets and stimulation frequencies. This improves treatment accuracy and effectively solves the problem that transcranial magnetic stimulation treatment in the prior art fails to fully consider individual differences among patients.

[0023] (3) The present invention automatically feeds back adjustment suggestions through the treatment effect evaluation module, thereby achieving the effect of real-time evaluation and dynamic feedback of treatment effect, and effectively solving the problem of delayed treatment effect evaluation and lack of timely adjustment mechanism in the prior art.

[0024] (4) The present invention combines brain wave data, brain region blood oxygen concentration change data and clinical feedback from patients, and the system can accurately predict and adjust transcranial magnetic stimulation treatment parameters, thereby achieving precise matching of treatment targets and stimulation frequencies. This improves treatment accuracy and effectively solves the problem that transcranial magnetic stimulation treatment in the prior art fails to fully consider individual differences among patients.

[0025] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a structural diagram of an individualized parameter optimization system for transcranial magnetic stimulation therapy based on artificial intelligence according to the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] See also Figure 1 The embodiment of the present invention provides a technical solution: an artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system, comprising a data acquisition preprocessing module, a feature extraction module, a treatment parameter prediction module and a treatment effect evaluation module, wherein the data acquisition module is used to collect the patient's brain function data in real time, obtain target weights, stimulation frequency and stimulation intensity, obtain clinical data, and preprocess the brain function data and clinical data; the feature extraction module is used to extract features from the preprocessed brain function data and clinical data, and mark the extracted data as feature data; the treatment parameter prediction module is used to predict the transcranial magnetic stimulation treatment parameters based on the feature data, and determine a treatment plan suitable for the patient's current condition according to the transcranial magnetic stimulation treatment parameter prediction results; the treatment effect evaluation module is used to continuously monitor the patient's brain function data during the treatment process, obtain brain function effects, evaluate the treatment effects, and make corresponding optimization and adjustment measures according to the treatment effects.

[0029] Specifically, the patient's brain function data is collected in real time, and the target weight, stimulation frequency and stimulation intensity are obtained. The specific process of obtaining clinical data is as follows: First, the brain function data consists of brain wave data and brain region blood oxygen concentration change data. Through the EEG sensor, the system can collect the patient's electric wave data in real time to reflect the brain's electrical activity, especially the brain wave changes in different brain regions, thereby providing basic information for treatment. At the same time, the fNIRS sensor is used to collect brain region blood oxygen concentration change data, which can monitor the fluctuation of cerebral blood oxygen level in real time and reflect the changes in local brain activity and oxygenation status. These data are used to monitor the activity of different brain regions of patients through EEG and functional near-infrared spectroscopy technology, providing a scientific basis for subsequent treatment target selection and treatment parameter setting. In terms of target selection, the system determines the most suitable stimulation target based on the collected EEG and blood oxygen concentration change data, usually including the three key brain regions of the left prefrontal lobe, right prefrontal lobe and medial prefrontal lobe, to ensure the accuracy and effectiveness of the treatment. The stimulation frequency and intensity are selected by in-depth interpretation of the patient's EEG analysis results, combined with their brain response characteristics, to select the most suitable parameters. In addition, the system automatically collects clinical data through user input, such as the patient's medical history, feedback information, and treatment progress. The comprehensive collection and analysis of these data provide a comprehensive and accurate basis for the subsequent optimization of individualized transcranial magnetic stimulation treatment parameters, thereby achieving a more refined and intelligent treatment plan design.

[0030] In this embodiment, by collecting the patient's brain function data and clinical data in real time, including brain wave data, brain area blood oxygen concentration change data and related clinical feedback information, this step can comprehensively and accurately evaluate the patient's brain function status. EEG and fNIRS sensors are used to collect brain wave and blood oxygen change data to provide a reliable basis for subsequent target selection and optimization of stimulation parameters. Through the interpretation of the EEG analysis results, the system can accurately select the stimulation target, and automatically determine the stimulation frequency and intensity according to the electrical activity characteristics of the brain to ensure the individualization and effectiveness of the treatment. At the same time, the system collects clinical data in real time through user input to further enrich the patient's treatment information. The realization of this process ensures the comprehensiveness and accuracy of data collection, and lays the foundation for the formulation of personalized transcranial magnetic stimulation treatment plans.

[0031] Specifically, the specific process of preprocessing brain function data and clinical data is as follows: First, brain function data, such as data collected by EEG and fNIRS, are often affected by various interferences and noises, such as interference from electronic devices or noise generated by physiological factors. The denoising step effectively removes these non-specific signals and improves the signal-to-noise ratio of the data by applying various digital filtering techniques. Subsequently, standardization is used to adjust brain function data and clinical data to a unified scale, which is crucial for comparing data at different time points or between different patients. Standardization ensures the consistency of the data, making data from different patients and under different conditions comparable. In addition, the preprocessing process also includes merging brain function data and clinical data, such as patient history information, treatment response, etc. This step is to generate a comprehensive patient brain function status feature by integrating information from multiple sources.

[0032] In this embodiment, in the step of preprocessing brain function data and clinical data, through denoising and standardization processing, the system significantly improves the data quality and ensures the reliability and consistency of the collected information. Denoising effectively removes interference signals and reduces errors, thereby improving the signal-to-noise ratio of brain wave and blood oxygen concentration change data, so that the data more accurately reflects the patient's true brain function state. Standardization processing enables data from different patients and different time points to be compared and analyzed under the same standard, which is particularly important for cross-patient analysis and evaluation of long-term treatment effects. By integrating and merging processed brain function data and clinical data, the system can generate comprehensive patient brain function state characteristics, providing a solid foundation for subsequent feature extraction and accurate prediction of treatment parameters. This step not only improves the efficiency of data processing, but also provides key support for the realization of personalized and precise treatment plans.

[0033] Specifically, the specific process of feature extraction of preprocessed brain function data and clinical data is as follows: In the process of feature extraction of preprocessed brain function data and clinical data, the system uses advanced data analysis technology to extract key information from brain wave data, such as the alpha wave frequency of the occipital lobe, which is usually associated with the relaxation and resting state of the brain and is extremely important for understanding the patient's neurophysiological state. In addition, the system also analyzes the changes in blood oxygen concentration in detail from functional near-infrared spectroscopy data, especially in the left and right prefrontal lobes, which play a key role in emotional regulation and cognitive function. By monitoring the blood oxygen concentration and its phase changes in the left and right prefrontal lobes, the system can accurately evaluate the activity changes of these brain regions during treatment, providing a scientific basis for the selection of treatment targets. At the same time, the feature extraction process also includes in-depth analysis of the patient's clinical data, such as the patient's clinical feedback and disease history information. This information is obtained directly from the patient or medical records and converted into useful treatment reference data through the intelligent analysis of the system. Treatment progress information in clinical data is also recorded and analyzed, which is crucial for evaluating treatment effects and further treatment decisions. This comprehensive feature extraction process not only optimizes the selection and adjustment of treatment parameters, but also greatly enhances the individualization and scientific nature of treatment plans by systematically analyzing and fusing multi-source data, ensuring that each patient receives the treatment most suitable for his or her specific condition.

[0034] In this embodiment, by performing feature extraction on the preprocessed brain function data and clinical data, the system can deeply analyze and mine the key brain functions and clinical characteristics of the patient, providing the necessary information for precise adjustment and personalized treatment. During the feature extraction process, the alpha wave frequency of the occipital lobe is extracted from the EEG data, which helps to assess the patient's relaxation state and baseline brain activity level. At the same time, by analyzing the blood oxygen concentration and phase changes of the left and right prefrontal lobes, the system can understand in detail the functional state of these key brain areas in cognitive and emotional regulation, which is essential for determining the most effective transcranial magnetic stimulation targets. In addition, the patient's clinical feedback and disease history information and treatment progress data extracted from the clinical data further enhance the clinical basis for treatment decisions and ensure that the treatment measures are closely aligned with the patient's specific needs and responses. This process significantly improves the scientificity and personalization of the treatment plan through systematic data analysis and feature recognition, thereby achieving more accurate and effective treatment interventions for patients.

[0035] Specifically, the transcranial magnetic stimulation treatment parameters are predicted based on the characteristic data, and the treatment plan suitable for the patient's current condition is determined according to the predicted results of the transcranial magnetic stimulation treatment parameters. The specific process is as follows: First, the key input data for the treatment is obtained: left prefrontal stimulation target, right prefrontal stimulation target, medial prefrontal stimulation target, stimulation frequency and stimulation intensity, as well as the blood oxygen concentration of the left and right prefrontal lobes and the phase changes of their cortex. These data not only reflect the physiological and functional state of the patient's brain, but also indicate the activity and responsiveness of potential treatment targets. The algorithm comprehensively considers these features, including the blood oxygen concentration of the left and right prefrontal lobes, phase changes, and brain wave activity characteristics related to the treatment targets, to calculate the predicted values ​​of the treatment parameters. This calculation process uses a machine learning model, combined with historical data and treatment responses of similar cases, to optimize and personalize treatment parameters. By comprehensively analyzing the data of left prefrontal stimulation targets, right prefrontal stimulation targets, medial prefrontal stimulation targets, stimulation frequency, stimulation intensity, blood oxygen concentration of the left prefrontal lobe, blood oxygen concentration of the right prefrontal lobe, phase changes of the left prefrontal cortex, and phase changes of the right prefrontal cortex, the system can accurately predict the most effective treatment parameters. Finally, based on these predicted values ​​of treatment parameters, a treatment plan suitable for the patient's current condition is determined.

[0036] In this embodiment, by comprehensively utilizing key features extracted from the patient's brain function data and clinical data, the system can accurately predict the transcranial magnetic stimulation treatment parameters suitable for the patient's current condition. The system-integrated machine learning model uses the blood oxygen concentration, phase changes, and brain wave activity data of the left and right prefrontal lobes to calculate the treatment parameters. This method allows the system to not only consider the selection of targets, but also adjust the stimulation frequency and intensity according to the actual response of the patient's brain to ensure the personalization and optimization of treatment measures. Through this process, the system can customize a treatment plan for the patient that accurately matches his pathological state and brain function characteristics, greatly improving the pertinence and efficiency of the treatment. This not only improves the clinical effect of the treatment, but also reduces the time delays and additional costs that may be caused by the trial and error process, and effectively solves the shortcomings of individualized treatment parameter setting in traditional methods.

[0037] Specifically, the specific process of determining a treatment plan suitable for the patient's current condition based on the predicted values ​​of the treatment parameters is as follows: First, the treatment plan is based on the predicted values ​​of the treatment parameters generated by the machine learning model, which integrates the patient's brain function and clinical data to provide personalized treatment input. Based on these predicted values, the system selects the stimulation target that best suits the patient's current neurophysiological state. For example, if the prediction results show that the left prefrontal lobe is more suitable for the patient as a target, the system will automatically adjust the positioning of the transcranial magnetic stimulation device to accurately target the area. At the same time, the system adjusts the frequency setting of the transcranial magnetic stimulation device according to the predicted stimulation frequency. Different stimulation frequencies have significant differences in their effects on the brain, and the correct frequency setting can enhance the treatment effect or alleviate symptoms. For example, high-frequency stimulation is usually used to activate brain function, while low-frequency stimulation is used to inhibit overactive brain areas. In addition, the adjustment of the stimulation intensity is also based on the predicted values ​​to ensure that the intensity of the stimulation can achieve both therapeutic effects and discomfort to the patient. Through meticulous parameter adjustments, the system ensures that each setting can meet the specific needs of the patient to the greatest extent, thereby improving the safety and effectiveness of the treatment. The implementation of this process makes transcranial magnetic stimulation therapy more precise and can provide effective treatment solutions for patients' specific conditions.

[0038] In this embodiment, by determining the treatment plan suitable for the patient's current condition based on the predicted values ​​of the treatment parameters, this step significantly improves the personalization and accuracy of transcranial magnetic stimulation treatment. The system uses the results of the machine learning model analysis to accurately adjust the stimulation target, frequency, and intensity, thereby ensuring that each setting is specifically targeted at the patient's specific neurophysiological condition and treatment needs. For example, by selecting the best stimulation target, the system can more effectively reach the treatment target area, thereby improving the treatment effect. At the same time, precise frequency adjustment helps to optimize the brain's response, and the appropriate stimulation intensity ensures that the treatment is both effective and safe. These fine adjustments enable transcranial magnetic stimulation treatment to respond to various neurological diseases more accurately, maximize the treatment effect, and reduce unnecessary side effects, providing patients with a safer and more effective treatment option.

[0039] Specifically, the specific calculation method of the predicted value of the treatment parameter is: Where T p represents the predicted value of the treatment parameter, represents the weighted sum of the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, and the medial prefrontal lobe stimulation target, w i Represents the weight coefficient of the i-th target, usually ranging from 0 to 1, and the specific value is optimized according to historical data and treatment effects. i represents the index of the i-th target, which is adjusted according to the influence of different targets. It can be positive or negative to adjust the influence of different targets. f represents the stimulation frequency, and w4 It represents the weight coefficient of the stimulation frequency, which is adjusted according to the contribution of the stimulation frequency to the treatment effect. It is usually selected between 0 and 1. I represents the stimulation intensity, and w 5 The weight coefficient representing the intensity of stimulation is also set based on the impact on the therapeutic effect. left Indicates the blood oxygen concentration of the left frontal lobe, O right represents the blood oxygen concentration of the right frontal lobe, w 6 The weight coefficient representing the product of the cerebral blood oxygen concentration of the left and right prefrontal lobes is used to evaluate the synergistic effect of blood oxygen concentration in the two cerebral hemispheres, ΔO left represents the phase change of the left prefrontal cortex, ΔO right represents the phase change of the right prefrontal cortex, w 7 The weight coefficient representing the product of the time-phase changes in the left and right prefrontal cerebral blood oxygen concentrations is used to evaluate the impact of time changes on the treatment effect. The weight coefficient is set based on historical data, stored in the database, and dynamically adjusted according to real-time changes.

[0040] In this embodiment, the optimal treatment parameters based on real-time data are calculated. This includes integrating the blood oxygen concentration and phase change information of the left and right prefrontal lobes using the weights and indexes of the target location, as well as the weights of the stimulation frequency and stimulation intensity. This method not only optimizes the target selection and stimulation intensity of the treatment, but also takes into account the interaction between brain regions, thereby greatly improving the accuracy and effectiveness of the treatment. This comprehensive calculation method makes the treatment plan more personalized, ensuring that each patient receives treatment customized to their specific brain physiological and functional conditions.

[0041] Specifically, the treatment effect is evaluated and corresponding optimization and adjustment measures are made according to the treatment effect. The specific process is as follows: First, the system obtains clinical feedback, disease history information, treatment progress data, and brain function effects. The integration of these data provides a multi-dimensional perspective for the comprehensive evaluation of treatment effects. Clinical feedback may include patients' self-reported symptoms, observations of medical professionals, and records of any side effects; disease history information provides patients' health background and response data from previous treatments; treatment progress data reflects the implementation of the current treatment plan and the patient's response trend; and brain function effects are measured by the latest electroencephalogram or functional near-infrared spectroscopy data, showing changes in brain activity and the direct impact of treatment. Through the fusion of this information, advanced data analysis technology is used to comprehensively calculate the treatment effect evaluation value. This evaluation value is based on preset algorithms and weight parameters, which can reflect the overall effectiveness of the treatment and any aspects that need to be adjusted. Then, based on this treatment effect evaluation value, the system will automatically propose optimization and adjustment measures, such as adjusting the stimulation intensity, frequency, or specific targets of the transcranial magnetic stimulation device.

[0042] In this implementation scheme, in the process of evaluating the treatment effect and optimizing the adjustment measures, the system comprehensively analyzes data from clinical feedback, disease history information, treatment progress data, and brain function effects, thereby generating a comprehensive treatment effect evaluation value. This comprehensive evaluation mechanism allows the system to accurately quantify the effectiveness of the treatment and adjust the treatment parameters in real time according to the specific evaluation results, such as adjusting the target, frequency, and intensity of transcranial magnetic stimulation. The implementation of this process significantly improves the adaptability and responsiveness of the treatment, allowing the treatment plan to flexibly respond to the patient's specific reactions and changes, ensuring that the treatment measures are both effective and safe. Through such dynamic adjustments, the system not only optimizes the treatment effect, but also enhances the patient's treatment experience, effectively solving the problem of lack of personalization and real-time feedback in traditional treatment plans.

[0043] Specifically, the specific process of making corresponding optimization and adjustment measures according to the treatment effect evaluation value is as follows: First, the system will compare the treatment effect evaluation value with the set threshold in real time. When the treatment effect evaluation value is greater than the threshold, this indicates that the current treatment plan is effective, so no adjustment is made and the existing treatment plan continues to be implemented. When the treatment effect evaluation value is less than or equal to the threshold, it means that the treatment effect has not met expectations and needs to be adjusted. In this case, the system will automatically make multiple key adjustments to optimize the treatment effect. Specifically, it includes adjusting the target location of transcranial magnetic stimulation treatment, which is to determine a more effective stimulation area by analyzing brain function data and clinical feedback; adjusting the stimulation frequency to treat at a frequency that is more suitable for the current patient's brain response; and adjusting the stimulation intensity to ensure that the stimulation can achieve sufficient therapeutic effects without causing discomfort to the patient. These adjustments are based on real-time data and advanced analysis algorithms to ensure that every adjustment is accurate and well-founded.

[0044] In this embodiment, the adaptability and effect of the treatment process are ensured to be maximized by real-time monitoring and dynamic adjustment of treatment parameters. In implementation, the system will compare the treatment effect evaluation value with the preset threshold in real time as a basis for adjustment. When the evaluation value is higher than the threshold, it indicates that the current treatment strategy is effective, so the status quo is maintained. If the evaluation value is lower than or equal to the threshold, the adjustment mechanism is triggered, including optimizing the specific location of the target, adjusting the stimulation frequency and stimulation intensity. These adjustments are based on precise data analysis and are intended to quickly improve the treatment effect to the ideal level. This responsive adjustment strategy not only improves the personalization and accuracy of the treatment, but also enhances the safety of the treatment process and the comfort of the patient, and effectively solves the shortcomings of traditional treatment methods, such as the lack of immediate feedback and adjustment capabilities. In this way, the system ensures that each patient can obtain effective treatment results under the appropriate treatment state.

[0045] Specifically, the specific calculation method of the treatment effect evaluation value is: Where E t It represents the evaluation value of treatment effect, which is an indicator used to comprehensively consider the influence of various aspects. c represents clinical feedback, which includes the patient's direct feedback on the treatment effect and the therapist's evaluation, c The weight coefficient of clinical feedback is usually between 0.1 and 0.5. This range allows this parameter to have a moderate weight in the overall evaluation to ensure that other variables can also affect the overall evaluation results. f Represents disease history information, including the patient's previous treatment response and medical history details, w f Represents the weight coefficient of disease history information. It is usually set between 0.1 and 0.4, and is adjusted according to the impact of disease history on the expected effect of the current treatment plan. To adjust R f The nonlinear effect on the overall evaluation makes it possible to maintain the stability of the evaluation even at extreme or marginal values. e Indicates the effect of brain function, usually assessed by data obtained from electroencephalography or functional magnetic resonance imaging, w b Represents the weight coefficient of brain function effect, T prog Indicates treatment progress data, w T The weight coefficient representing the treatment progress data, that is, the weight coefficient of the brain function effect, is usually set between 0.2 and 0.5, because it directly reflects the impact of the treatment on the patient's brain activity. The weight coefficient is set based on historical data, stored in the database, and dynamically adjusted according to real-time changes.

[0046] In this implementation scheme, by applying complex calculation formulas to evaluate the treatment effect, the system can integrate various clinical and brain function data to generate an accurate treatment effect evaluation value. This evaluation includes clinical feedback, disease history, brain function effect and treatment progress data. Each type of data is appropriately weighted by a set weight factor to ensure the comprehensiveness and balance of the evaluation. Clinical feedback and disease history information provide direct insights into the patient's response to treatment and previous treatment experience, while brain function effect and treatment progress data directly reflect the actual impact of the treatment on the patient's health status. This comprehensive evaluation allows the treatment plan to be dynamically adjusted according to the specific effect value obtained in real time, improving the accuracy and personalization of the treatment and ensuring that the patient obtains appropriate treatment results.

[0047] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0048] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system, comprising a data acquisition preprocessing module, a feature extraction module, a treatment parameter prediction module and a treatment effect evaluation module, characterized in that: The data acquisition module is used to collect the patient's brain function data in real time, obtain target weights, stimulation frequency and stimulation intensity, obtain clinical data, and pre-process the brain function data and clinical data; The feature extraction module is used to extract features from the preprocessed brain function data and clinical data, and mark the extracted data as feature data; The treatment parameter prediction module is used to predict the transcranial magnetic stimulation treatment parameters based on the characteristic data, and determine a treatment plan suitable for the patient's current condition according to the transcranial magnetic stimulation treatment parameter prediction results; The treatment effect evaluation module is used to continuously monitor the patient's brain function data during the treatment process, obtain brain function effects, evaluate the treatment effects, and make corresponding optimization and adjustment measures based on the treatment effects.

2. The system for optimizing individualized parameters of transcranial magnetic stimulation therapy based on artificial intelligence according to claim 1, characterized in that: The specific process of real-time acquisition of the patient's brain function data, obtaining the target weight, stimulation frequency and stimulation intensity, and obtaining clinical data is as follows: Brain function data include brain wave data and brain area blood oxygen concentration change data. EEG sensors are used to collect brain wave data, fNIRS sensors are used to collect brain area blood oxygen concentration change data, and electroencephalogram and functional near-infrared spectroscopy are used to detect the activity of related brain areas. The left prefrontal lobe stimulation target, right prefrontal lobe stimulation target and medial prefrontal lobe stimulation target are selected. The appropriate stimulation frequency and stimulation intensity are selected based on the patient's electroencephalogram analysis results. Clinical data are automatically collected through the user input system.

3. The artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system according to claim 1, characterized in that: The specific process of preprocessing brain function data and clinical data is as follows: The brain function data and clinical data were denoised and standardized, and the brain function data, clinical data, and clinical data were merged to generate the patient's brain function status characteristics.

4. The system for optimizing individualized parameters of transcranial magnetic stimulation therapy based on artificial intelligence according to claim 1, characterized in that: The specific process of extracting features from the preprocessed brain function data and clinical data is as follows: Extract the alpha wave frequency of the occipital lobe from the EEG data, and extract the blood oxygen concentration of the left prefrontal lobe, the blood oxygen concentration of the right prefrontal lobe, the phase change of the left prefrontal cortex, and the phase change of the right prefrontal cortex from the blood oxygen concentration change data of the brain regions; Obtain patients' clinical feedback and disease history information from clinical data, and record treatment progress data from the clinic.

5. The system for optimizing individualized parameters of transcranial magnetic stimulation therapy based on artificial intelligence according to claim 1, characterized in that: The specific process of predicting transcranial magnetic stimulation treatment parameters based on characteristic data and determining a treatment plan suitable for the patient's current condition according to the transcranial magnetic stimulation treatment parameter prediction results is as follows: The left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, the medial prefrontal lobe stimulation target, the stimulation frequency, the stimulation intensity, the blood oxygen concentration of the left prefrontal lobe, the blood oxygen concentration of the right prefrontal lobe, the phase change of the left prefrontal cortex, and the phase change of the right prefrontal cortex are obtained, and the treatment parameter prediction value is obtained by comprehensive calculation of the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, the medial prefrontal lobe stimulation target, the stimulation frequency, the stimulation intensity, the blood oxygen concentration of the left prefrontal lobe, the blood oxygen concentration of the right prefrontal lobe, the phase change of the left prefrontal cortex, and the phase change of the right prefrontal cortex, and the treatment parameter prediction value is determined according to the treatment parameter prediction value.

6. The system for optimizing individualized parameters of transcranial magnetic stimulation therapy based on artificial intelligence according to claim 5, characterized in that: The specific process of determining a treatment plan suitable for the patient's current condition based on the predicted value of the treatment parameter is as follows: Determine a treatment plan suitable for the patient's current condition based on the predicted values ​​of the treatment parameters, select stimulation targets suitable for the patient based on the predicted stimulation targets, set the frequency of the transcranial magnetic stimulation device based on the predicted stimulation frequency, and adjust the intensity of the transcranial magnetic stimulation device based on the predicted stimulation intensity.

7. The system for optimizing individualized parameters of transcranial magnetic stimulation therapy based on artificial intelligence according to claim 5, characterized in that: The specific calculation method of the predicted value of the treatment parameter is: Where T p represents the predicted value of the treatment parameter, represents the weighted sum of the left prefrontal lobe stimulation target, the right prefrontal lobe stimulation target, and the medial prefrontal lobe stimulation target, w i represents the weight coefficient of the i-th target, α i represents the index of the i-th target, f represents the stimulation frequency, w4 represents the weight coefficient of the stimulation frequency, I represents the stimulation intensity, w5 represents the weight coefficient of the stimulation intensity, O left Indicates the blood oxygen concentration of the left frontal lobe, O right represents the blood oxygen concentration of the right prefrontal lobe, w6 represents the weight coefficient of the product of the cerebral blood oxygen concentration of the left and right prefrontal lobes, ΔO left represents the phase change of the left prefrontal cortex, ΔO right represents the phase change of the right prefrontal cortex, and w7 represents the weight coefficient of the product of the phase change of the left and right prefrontal cerebral blood oxygen concentration.

8. The system for optimizing individualized parameters of transcranial magnetic stimulation therapy based on artificial intelligence according to claim 1, characterized in that: The specific process of evaluating the treatment effect and making corresponding optimization and adjustment measures according to the treatment effect is as follows: Obtain clinical feedback, disease history information, treatment progress data and brain function effects, obtain a treatment effect evaluation value through comprehensive calculation of clinical feedback, disease history information, treatment progress data and brain function effects, and make corresponding optimization and adjustment measures based on the treatment effect evaluation value.

9. The artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system according to claim 8, characterized in that: The specific process of making corresponding optimization and adjustment measures according to the treatment effect evaluation value is as follows: Compare the treatment effect evaluation value with the threshold in real time. When the treatment effect evaluation value is greater than the threshold, no adjustment is made. When the treatment effect evaluation value is less than or equal to the threshold, the specific position of the target, the stimulation frequency, and the stimulation intensity are adjusted until the treatment effect evaluation value rises above the threshold.

10. The artificial intelligence-based transcranial magnetic stimulation therapy individualized parameter optimization system according to claim 8, characterized in that: The specific calculation method of the treatment effect evaluation value is: Where E t Represents the treatment effect evaluation value, R c Indicates clinical feedback, w c represents the weight coefficient of clinical feedback, R f Indicates disease history information, w f Represents the weight coefficient of disease history information, B e Indicates the effect of brain function, w b Represents the weight coefficient of brain function effect, T prog Indicates treatment progress data, w T Represents the weight coefficient of treatment progress data.

Images