Method for generating personalized nerve regulation and control stimulation scheme

Abstract

The invention provides a method for generating a personalized nerve regulation and control stimulation scheme, and aims to generate a precise nerve regulation and control stimulation scheme for an individual through an electroencephalogram evaluation result. The method comprises the following steps: firstly, constructing a scheme library containing a plurality of transcranial electrical stimulation basic schemes; secondly, collecting resting-state electroencephalogram signals of a user, extracting electroencephalogram characteristic indexes related to emotion, cognition and sleep, and comparing the electroencephalogram characteristic indexes with a norm database to judge cognition risks; generating a primary stimulation scheme according to an evaluation result, and if a cognitive risk exists, further detecting that a feature index is abnormal and generating a targeted correction scheme; all the schemes are subjected to priority ranking, and the sequence is determined according to the abnormal severity degree and the clinical weight; and finally, outputting a personalized treatment scheme sequence of one week. According to the method, the accuracy and effectiveness of treatment are improved, high individuation, systematicness, practicability and dynamic optimization potential are achieved, and powerful support is provided for nerve regulation and control treatment.

Description

Technical Field

[0001] This invention relates to the field of neuromodulation and cognitive intervention, and in particular to a method for generating personalized neuromodulation stimulation programs, which can formulate dynamically adjusted electrical stimulation treatment plans based on an individual's emotional, cognitive, and sleep states. Background Technology

[0002] Transcranial electrical stimulation (tES) techniques, such as transcranial direct current stimulation (tDCS), transcranial alternating current stimulation (tACS), transcranial random noise stimulation (tRNS), and transcranial pulsed electrical stimulation (tPCS), are non-invasive neuromodulation methods. With their advantages of high safety, ease of operation, and relatively low cost, they have shown great potential in improving mood disorders, sleep problems, cognitive enhancement, and neurorehabilitation. Numerous studies have shown that tES can positively modulate brain function through mechanisms such as adjusting neuronal membrane potential, altering cortical excitability, and regulating brain network oscillation synchrony. Electroencephalography (EEG), as a non-invasive, high-temporal-resolution technique for recording the electrophysiological activity of the cerebral cortex, serves as a "window" into an individual's brain functional state. It can provide multi-dimensional quantitative indicators, including power spectrum characteristics, brain rhythm characteristics, functional connectivity (such as phase lock value and weighted phase lag index), and signal complexity (such as sample entropy and fractal dimension), providing important references for understanding an individual's brain functional state and guiding neuromodulation.

[0003] Despite its promising future, current clinical applications of tES (thermoelectric electroencephalography) still face a significant bottleneck: treatment protocols generally employ standardized, one-size-fits-all approaches. Key parameters such as stimulation targets, current / voltage intensity, and frequency are often based on population averages, neglecting individual differences in anatomical structure, baseline EEG patterns, and pathophysiological states. This leads to deviations in current distribution or mismatches between frequency and individual intrinsic rhythms, resulting in significant differences in efficacy, low response efficiency, and even negative effects. Furthermore, EEG assessment and protocol development remain fragmented processes, relying on experience and intuition, lacking systematic and automated decision support, and struggling to quickly find the optimal match from a vast array of parameter combinations.

[0004] Therefore, there is an urgent need in this field for an EEG-based personalized assessment method that can effectively convert multidimensional EEG features into specific and executable tES parameters and automatically generate highly personalized and adaptive stimulation protocols to improve the effectiveness and precision of neuromodulation therapy. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide a method for generating personalized neuromodulation stimulation programs. This method, through systematic evaluation and decision-making logic, can dynamically combine or generate entirely new stimulation programs from a pre-set program library based on an individual's current brain function state, and prioritize treatment, thereby achieving truly personalized and precise intervention.

[0006] This invention provides a method for generating personalized neuromodulation stimulation protocols, characterized by comprising the following steps:

[0007] Step 1: Construct a stimulation protocol library. A stimulation protocol library is pre-constructed, containing multiple basic transcranial electrical stimulation protocols, including but not limited to transcranial direct current stimulation (tDCS), transcranial alternating current stimulation (tACS), transcranial random noise stimulation (tRNS), transcranial pulsed current stimulation (tPCS), and microcurrent stimulation. Each protocol in this library defines detailed stimulation parameters, including stimulation type, stimulation site, current intensity, stimulation frequency, and stimulation duration.

[0008] Step 2: EEG Assessment and Risk Determination. Resting-state EEG signals are collected from the user and preprocessed. N EEG feature indicators related to emotion, cognition, and sleep state are extracted from the preprocessed signals. These N feature indicators include, but are not limited to, power spectral density, sample entropy, individualized alpha peak frequency, alpha / β power ratio, phase lock value, and fractal dimension. These feature indicators are compared with a norm database, and their Z-scores are calculated for standardization correction. Thresholds are set based on the Z-scores; for example, |Z|<1 is normal, 1≤|Z|<2 is mildly abnormal, and |Z|≥2 is abnormal, to determine whether the user's overall cognitive function is at risk.

[0009] Step 3: Primary Stimulation Protocol Generation. A primary stimulation protocol is generated based on the EEG assessment results from Step 2:

[0010] If the user's cognitive function is at no risk, a treatment plan that can guarantee the user a week of treatment will be directly selected from the stimulation plan library;

[0011] If there is a risk to the user's cognitive function, a basic stimulus scheme 1 is generated to address the cognitive risk.

[0012] Step 4: Multi-dimensional feature anomaly detection and targeted solution generation. Anomaly detection is performed on the N feature indicators mentioned in Step 2: if M feature indicators are abnormal (M is an integer, and 1≤M≤N), a feature correction scheme is generated for each abnormal feature indicator; the final scheme set consists of the stimulus scheme 1 and the M feature correction schemes.

[0013] Step 5: Prioritize Stimulation Treatment Protocols. Prioritize all protocols in the final protocol set. The priority is based on the severity of the abnormality of the corresponding feature indicators and their preset clinical weights. Protocols with higher abnormality severity and greater clinical weights have higher priority. Supplementary protocols randomly selected from the protocol library have the lowest priority.

[0014] Step 6: Output Personalized Treatment Plan. Based on the personalized treatment plan generated in the above steps, output a one-week treatment plan sequence.

[0015] The beneficial effects of this invention are as follows:

[0016] By deeply integrating EEG assessment results, highly precise stimulation protocols are achieved from group-based to individualized approaches; an intelligent decision-making process of "assessment-judgment-generation-supplementation-ranking" is constructed to improve the efficiency and reliability of protocol generation; relying on a protocol library, a complete and feasible treatment plan can be output under any circumstances, with good practicality and robustness; and it supports dynamic optimization by combining periodic EEG reassessment, providing a guarantee for long-term adaptive neuromodulation. Attached Figure Description

[0018] Figure 1 This is an overall flowchart of the personalized stimulation scheme generation method described in this invention. Detailed Implementation

[0019] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be understood that the embodiments described are for illustrative purposes only and are not intended to limit the scope of the invention.

[0020] like Figure 1 As shown in the figure, this embodiment provides a method for generating personalized neuromodulation stimulation schemes. The implementation process of this method is as follows:

[0021] Step 1: Acquire the user's resting-state EEG signals

[0022] Using multi-lead (usually 8 or more leads) EEG acquisition equipment that meets medical or research standards, and following international 10-20 system or denser electrode placement standards, the user should wear an EEG cap to ensure spatial resolution and positioning accuracy of the signal acquisition. During signal acquisition, the environment should be kept quiet and the lighting soft, and the user should be asked to remain relaxed and minimize limb movement and eye movement to obtain high-quality, low-noise resting-state EEG data.

[0023] Step 2: Preprocessing and Feature Extraction

[0024] The system preprocesses the acquired EEG signals (including filtering, artifact removal, etc.) and extracts N feature indicators (e.g., power spectral density, sample entropy, individualized α peak frequency, α / β power ratio, phase lock value, fractal dimension).

[0025] Step 3: Risk assessment.

[0026] The system uses machine learning or threshold discrimination methods, combined with a norm database, to comprehensively evaluate whether there is risk in the user's perception (e.g., the overall Z-score exceeds a threshold). If it is determined to be risk-free, it randomly selects 5 solutions from the solution library and outputs them, and the process ends.

[0027] Step 4: Generate the basic stimulus protocol.

[0028] If a risk is identified, a general "cognitive enhancement program" is generated as stimulation program 1 (e.g., a tDCS program targeting the dorsolateral prefrontal cortex, with a current intensity of 1.5 mA and a duration of 20 minutes).

[0029] Step 5: Anomaly detection of feature indicators.

[0030] The system checks each of the N feature indicators for abnormalities (e.g., an absolute Z-score greater than 1.5 is considered abnormal). Suppose the detection finds that the user has 3 abnormal indicators (M=3), such as: excessively high theta wave power, excessively low alpha wave power, and low sample entropy.

[0031] Step 6: Generate a targeted correction plan.

[0032] To address the excessive theta wave, a tACS scheme (Scheme A: 4Hz frequency, phase reversal, frontal midline electrode) was developed with the goal of suppressing low-frequency oscillations.

[0033] To address the issue of excessively low alpha waves, a tACS scheme (Scheme B: 10Hz frequency, occipital electrode) was developed to enhance the alpha rhythm.

[0034] To address the sample entropy difference, a tDCS protocol (Program C: bilateral frontal poles, cross-stimulation) was generated to regulate the balance of the brain hemispheres.

[0035] Step 7: Supplementary Plan

[0036] Combine Plan 1 with the correction plan. If the overall plan is less than one week of treatment, then randomly select one or more plans from the plan library.

[0037] Step 8: Priority Sort

[0038] The system prioritizes the final set of solutions. Priority scores are calculated based on the Z-score (severity) of each anomaly indicator and preset weights (e.g., theta waves have a higher weight).

[0039] Step 9: Output the treatment plan.

[0040] The final output is a one-week treatment plan sequence.

[0041] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating personalized neural modulation stimulation protocols, characterized in that, Includes the following steps: Step 1: Construct a stimulation protocol library. A stimulation protocol library is pre-constructed, containing multiple basic transcranial electrical stimulation protocols, including but not limited to transcranial direct current stimulation (tDCS), transcranial alternating current stimulation (tACS), transcranial random noise stimulation (tRNS), transcranial pulsed current stimulation (tPCS), and microcurrent stimulation. Each protocol in this library defines detailed stimulation parameters, including stimulation type, stimulation site, current intensity, stimulation frequency, and stimulation duration. Step 2: EEG Assessment and Risk Determination. Resting-state EEG signals are collected from the user and preprocessed. N EEG feature indicators related to emotion, cognition, and sleep state are extracted from the preprocessed signals. These N feature indicators include, but are not limited to, power spectral density, sample entropy, individualized alpha peak frequency, alpha / β power ratio, phase lock value, and fractal dimension. These feature indicators are compared with a norm database, and their Z-scores are calculated for standardization correction. Thresholds are set based on the Z-scores; for example, |Z|<1 is normal, 1≤|Z|<2 is mildly abnormal, and |Z|≥2 is abnormal, to determine whether the user's overall cognitive function is at risk. Step 3: Primary Stimulation Protocol Generation. A primary stimulation protocol is generated based on the EEG assessment results from Step 2: If the user's cognitive function is at no risk, a treatment plan that can guarantee the user a week of treatment will be selected directly from the stimulation plan library; If there is a risk to the user's cognitive function, a basic stimulus scheme 1 is generated to address the cognitive risk. Step 4: Multi-dimensional feature anomaly detection and targeted solution generation. Anomaly detection is performed on the N feature indicators mentioned in Step 2: if M feature indicators are abnormal (M is an integer, and 1≤M≤N), a feature correction scheme is generated for each abnormal feature indicator; the final scheme set consists of the stimulus scheme 1 and the M feature correction schemes. Step 5: Prioritize Stimulation Treatment Plans. Prioritize all plans in the final plan set based on the severity of the abnormality of the corresponding feature indicators and their preset clinical weights. Plans corresponding to features with higher abnormality severity and greater clinical weights have higher priority. The supplementary solution randomly selected from the solution library is given the lowest priority. Step 6: Output Personalized Treatment Plan. Based on the personalized treatment plan generated in the above steps, output a one-week treatment plan sequence.

2. The method for generating personalized stimulation programs according to claim 1, characterized in that, The stimulus programs in the stimulus program library are beneficial to a person's mood, sleep, and cognitive function.

3. The method for generating personalized stimulation programs according to claim 1, characterized in that, The EEG assessment includes the detection of the patient's emotions, cognition, and sleep status, as well as the detection of characteristic indicators.

4. The method for generating personalized stimulation programs according to claim 1, characterized in that, The priority ranking is determined based on the degree of abnormality of the patient's EEG characteristics and the targeting of the stimulation program.

Images