Postoperative delirium prediction system and method based on electroencephalogram signals

Abstract

The invention discloses a postoperative delirium prediction system and method based on electroencephalogram signals, and relates to the technical field of biomedical engineering.The system uses EEG equipment and a heart rate monitor to obtain brain wave signals and heart rate data, the signals are processed through filtering and FFT conversion, and brain wave power data are generated; calculating a delirium risk assessment index ZWF by obtaining a heart rate variability index HRV and brain wave power data through calculation, and performing preliminary assessment; when it is preliminarily assessed that the patient does not have the delirium risk, the medication history of the patient is obtained through a hospital information system (HIS), and the answer and performance of the patient are recorded according to a short mental state examination scale (MMSE) to calculate a cognitive function score (RZ); and comprehensively calculating a comprehensive delirium risk index ZFX based on the data, and performing secondary evaluation. The system finally provides targeted postoperative intervention suggestions for patients through two times of risk assessment in combination with drug history and cognitive functions, and aims to effectively reduce the risk of postoperative delirium.

Description

Technical Field

[0001] The present invention relates to the technical field of biomedical engineering, and in particular to a postoperative delirium prediction system and method based on electroencephalogram signals. Background Art

[0002] Postoperative delirium is a common postoperative complication, which manifests as confusion, cognitive impairment and behavioral disorders, seriously affecting the patient's recovery and quality of life. With the aging of the population, the number of elderly patients undergoing surgery is increasing worldwide, and the incidence of postoperative delirium is rising accordingly. The shortage of medical resources and medical staff makes timely and effective delirium prediction and intervention more important. Traditional delirium monitoring methods often rely on the subjective judgment of medical staff, with large errors and lags. With the development of artificial intelligence and biomedical technology, objective monitoring and prediction systems using physiological data such as EEG and heart rate variability have gradually become a new technical means, which is expected to play an important role in the early prediction and prevention of postoperative delirium, improve the quality of postoperative care for patients, reduce the incidence of complications, and reduce the burden on the medical system.

[0003] Existing postoperative delirium risk prediction mostly relies on the experience of clinicians and the patient's preoperative health status. This method has the problems of strong subjectivity and low accuracy. It is usually difficult for doctors to track the changes in patients' physiological signals in real time before, during and after surgery, and it is not easy to accurately capture the early warning signs of postoperative delirium. In addition, the causes of postoperative delirium are complex and changeable, and a single physiological parameter is not easy to provide a comprehensive basis for judgment. Existing methods are often not easy to fully consider the individual differences of patients, resulting in inaccurate diagnosis and even misjudgment. Traditional evaluation methods are limited to surface symptom analysis and fail to deeply analyze important physiological indicators such as patients' EEG activity and heart rate variability, which can easily lead to some high-risk patients not being identified in time, thereby increasing the risk of postoperative complications. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a postoperative delirium prediction system and method based on electroencephalogram signals, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a postoperative delirium prediction system based on EEG signals, comprising an EEG signal acquisition module, a central processing module, a delirium analysis module, a deep data acquisition module and a deep analysis module;

[0006] The EEG signal acquisition module is used to use an EEG device and a heart rate monitor to monitor the patient's EEG activity and heart rate changes in real time, obtain the EEG signal set and the patient's heart rate HR, and transmit the EEG signal set and the patient's heart rate HR to the central processing module via a wireless network;

[0007] The central processing module is used to receive the brain wave signal set and the patient's heart rate HR in real time, pre-process the brain wave signal set, obtain the brain wave power data set, and then store the brain wave power data set and the patient's heart rate HR in the time series database InfluxDB;

[0008] The delirium analysis module is used to perform summary calculation based on the acquired patient heart rate HR, obtain the heart rate variability index HRV, and summarize and calculate with the brain wave power data group to obtain the delirium risk assessment index ZWF, and then perform a preliminary assessment with the preset delirium risk threshold A, and generate a secondary assessment based on the assessment results to deeply predict the delirium risk;

[0009] The deep data acquisition module is used to log in to the hospital information system HIS with authorization credentials to query the patient's medication history data when initially assessing that the patient does not have a risk of delirium, and then record the patient's answers and performance based on the MMSE cognitive function assessment tool to calculate the cognitive function score RZ;

[0010] The in-depth analysis module is used to perform summary calculations based on the medication history data to obtain the drug impact risk index Yfx, and to perform summary calculations with the obtained delirium risk assessment index ZWF and cognitive function score RZ to obtain the comprehensive delirium risk index ZFX, and then perform a secondary assessment with the preset delirium risk threshold A, and intervene and guide the patient based on the assessment results.

[0011] Preferably, the EEG signal acquisition module includes a signal acquisition unit, a data synchronization unit and a data transmission unit;

[0012] The signal acquisition unit is used to monitor the patient's brain electrical activity using an EEG device, place electrode patches on the patient's scalp in the main brain area according to the international 10-20 system standard, record brain wave activities in different frequency bands in real time, obtain brain wave signal sets, and then monitor heart rate changes in real time through a heart rate monitor to obtain the patient's heart rate HR;

[0013] The data transmission unit is used to transmit the acquired brain wave signal set and the patient's heart rate HR to the central processing module via a wireless network.

[0014] Preferably, the central processing module includes a data processing unit and a data storage unit;

[0015] The data processing unit is used to receive a brain wave signal set and a patient's heart rate HR. The brain wave signal set is preprocessed by removing low-frequency and high-frequency noise in the EEG signal using a 0.5 Hz-45 Hz bandpass filter, and then the frequency domain signal obtained by the Fourier transform FFT is further calculated to obtain a power spectrum by using the fast Fourier transform FFT, and smoothing and standardization processing are performed to obtain a brain wave power data set;

[0016] The formula for obtaining the power spectrum is as follows;

[0017]

[0018] Where P(f) represents the power at frequency f, x n represents the nth EEG signal sample, N represents the total number of samples, n represents the sampling point number, and e represents the exponential function;

[0019] The brain wave power data set includes alpha waves, beta waves, theta waves and delta waves;

[0020] The band range of the brain wave power data set is: alpha wave is 8Hz-12 Hz, beta wave is 13Hz-30 Hz, theta wave is 4Hz-7 Hz, and delta wave is 0.5Hz-4 Hz;

[0021] The data storage unit is used to store the patient's heart rate HR and brain wave power data groups in the time series database InfluxDB. The time series database InfluxDB marks each data of the patient's heart rate HR and brain wave power data groups with a timestamp, a measurement value patient ID, a sensor type and an independent label, and optimizes storage through compression technology and partition indexing.

[0022] Preferably, the delirium analysis module includes a delirium risk analysis unit and a delirium risk assessment unit;

[0023] The delirium risk analysis unit includes a heart rate analysis unit and a delirium risk calculation unit;

[0024] The heart rate analysis unit is used to perform summary calculation based on the acquired patient heart rate HR to obtain the heart rate variability index HRV;

[0025] The heart rate variability index HRV is calculated by the following formula:

[0026]

[0027] Where M represents the number of measurements, HR i represents the heart rate measured at the i-th time, It represents the average value of M times of heart rate measurement;

[0028] The delirium risk calculation unit is used to perform summary calculation based on the acquired heart rate variability index HRV and brain wave power data group to obtain a delirium risk assessment index ZWF;

[0029]

[0030] Wherein, w0 represents the bias top constant, w1, w2, w3 and w4 represent the weight coefficients of α wave power, β wave power, θ wave power and heart rate variability index HRV respectively, and w1+w2+w3+w4=1, and its specific value is set by the user according to actual use, and e represents the exponential function.

[0031] Preferably, the delirium risk assessment unit analyzes the heart rate data and brain wave power data of each patient in the time series database InfluxDB, and screens out the historical heart rate data and brain wave power data of the same age group according to the data annotation label, and then calculates the average value of the delirium risk assessment index ZWF obtained according to the screened historical heart rate data and brain wave power data, performs a preset delirium risk threshold A, and then performs a preliminary assessment with the obtained delirium risk assessment index ZWF, and triggers a secondary assessment according to the assessment result. The specific assessment scheme is as follows;

[0032] When the delirium risk assessment index ZWF ≥ the preset delirium risk threshold A, it means that the patient is at risk of delirium. At this time, it is recommended that doctors and family members provide psychological counseling to the patient before surgery and pay attention to the depth of anesthesia control during surgery;

[0033] When the delirium risk assessment index ZWF is less than the preset delirium risk threshold A, it means that the patient is not at risk of delirium, and the secondary assessment mechanism is triggered.

[0034] Preferably, the deep data acquisition module includes a historical medication acquisition unit and a patient cognitive assessment unit;

[0035] The historical medication acquisition unit is used to log in to the hospital information system HIS using the authorization credentials when initially assessing that the patient does not have a risk of delirium, obtain the patient's detailed medical records, and query the patient's medication history data based on the patient's unique identifier, including the number of types of drugs used n, the dosage of drugs used jl, and the frequency of drug use pl;

[0036] The patient cognitive assessment unit is used to ask standardized questions and tasks to patients in a face-to-face manner based on the Mini-Mental State Examination (MMSE) cognitive function assessment tool, record the patient's answers and performance, give corresponding scores based on the patient's performance in each test, and calculate the final cognitive function score RZ.

[0037] Preferably, the in-depth analysis module includes a drug risk analysis unit and a comprehensive analysis unit;

[0038] The drug risk analysis unit is used to perform summary calculation based on the acquired medication history data to obtain the drug impact risk index Yfx;

[0039] The drug impact risk index Yfx is calculated and obtained by the following formula:

[0040]

[0041] In the formula, n represents the number of drug types, a i represents the influence coefficient of the i-th drug type, jl i represents the dosage of the i-th drug, pl i represents the frequency of use of the i-th drug.

[0042] Preferably, the comprehensive analysis unit includes a comprehensive delirium risk analysis unit and a comprehensive delirium risk assessment unit;

[0043] The comprehensive delirium risk analysis unit is used to perform summary calculation based on the acquired delirium risk assessment index ZWF, cognitive function score RZ and drug impact risk index Yfx to obtain a comprehensive delirium risk index ZFX;

[0044] The comprehensive delirium risk index ZFX is calculated by the following formula:

[0045]

[0046] Wherein, log represents the logarithmic function.

[0047] Preferably, the comprehensive delirium risk assessment unit is used to perform a secondary assessment based on the obtained comprehensive delirium risk index ZFX and a preset delirium risk threshold A. The specific assessment scheme is as follows;

[0048] When the comprehensive delirium risk index ZFX is less than the preset delirium risk threshold A, it means that the patient's historical medication and cognitive behavior have no effect on postoperative delirium, and normal monitoring should be maintained at this time;

[0049] When the comprehensive delirium risk index ZFX ≥ the preset delirium risk threshold A, it means that the patient's historical medication and cognitive behavior have an impact on postoperative delirium. At this time, the system generates an adjustment plan, including changing the patient's medication, adjusting the patient's daily routine and living environment, providing cognitive stimulation, and iteratively evaluating the adjustment plan through the delirium analysis module until the patient's postoperative delirium prediction reaches a safe level.

[0050] A method for predicting postoperative delirium based on electroencephalogram signals comprises the following steps:

[0051] S1, using EEG equipment and heart rate monitor to monitor the patient's brain electrical activity and heart rate changes in real time, obtain brain wave signal set and patient's heart rate HR, and transmit the brain wave signal set and patient's heart rate HR to S2 via a wireless network;

[0052] S2, receiving the brain wave signal set and the patient's heart rate HR in real time, preprocessing the brain wave signal set, obtaining the brain wave power data set, and then storing the brain wave power data set and the patient's heart rate HR in the time series database InfluxDB;

[0053] S3. The heart rate variability index HRV is obtained by summarizing and calculating the patient's heart rate HR, and the delirium risk assessment index ZWF is obtained by summarizing and calculating the data with the brain wave power data group. Then, a preliminary assessment is performed with the preset delirium risk threshold A, and a secondary assessment is generated based on the assessment results to deeply predict the delirium risk;

[0054] S4. When the patient is initially assessed as not at risk of delirium, use the authorization credentials to log in to the hospital information system (HIS) to query the patient's medication history data, and then use the short mental state examination (MMSE) cognitive function assessment tool to record the patient's answers and performance and calculate the cognitive function score RZ;

[0055] S5. Summarize and calculate the medication history data to obtain the drug impact risk index Yfx, and summarize and calculate it with the obtained delirium risk assessment index ZWF and cognitive function score RZ to obtain the comprehensive delirium risk index ZFX, and then conduct a secondary assessment with the preset delirium risk threshold A, and intervene and guide the patient based on the assessment results.

[0056] The present invention provides a postoperative delirium prediction system and method based on EEG signals, which has the following beneficial effects:

[0057] (1) The system's EEG signal acquisition module combines EEG equipment and heart rate monitors to monitor the patient's EEG activity and heart rate changes in real time, generating a detailed set of EEG signals and the patient's heart rate HR. This real-time monitoring function not only improves the efficiency of data collection, but also provides accurate basic data for subsequent analysis, enabling the system to identify potential delirium risks earlier.

[0058] (2) The central processing module of the system uses a bandpass filter to remove low-frequency and high-frequency noise, and uses fast Fourier transform (FFT) to decompose the EEG signal. The system successfully generates multi-band EEG power data. After smoothing and standardization, these data are stored in the time series database InfluxDB, ensuring that each data is accompanied by a timestamp and patient ID for subsequent retrieval and analysis. The efficient storage and management of heart rate data and EEG power data enables the system to track data for a long time, supporting the subsequent delirium analysis module for in-depth evaluation.

[0059] (3) The delirium analysis module of the system combines heart rate variability HRV, brain wave power data, and the patient's medication history and cognitive function assessment to calculate the delirium risk assessment index ZWF. This module not only performs a preliminary assessment, but also compares with patients of the same age based on historical data to identify existing risk factors. At the same time, the deep data acquisition module further improves the accuracy of the prediction by querying the patient's medication history and cognitive assessment. Finally, the calculation of the comprehensive delirium risk index ZFX enables the system to provide patients with personalized intervention plans, thereby significantly reducing the incidence of postoperative delirium and improving patients' postoperative safety and quality of life. Through this series of technical means, the system effectively integrates physiological signal monitoring and deep analysis, achieves accurate prediction and timely intervention of postoperative delirium risk, and provides strong support for clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flow chart of a postoperative delirium prediction system based on EEG signals of the present invention;

[0061] Figure 2 This is a schematic diagram of the steps of a method for predicting postoperative delirium based on EEG signals of the present invention. DETAILED DESCRIPTION

[0062] 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.

[0063] Example 1

[0064] See also Figure 1 , the present invention provides a postoperative delirium prediction system based on EEG signals. To achieve the above purpose, the present invention is implemented through the following technical scheme: including an EEG signal acquisition module, a central processing module, a delirium analysis module, a deep data acquisition module and a deep analysis module;

[0065] The EEG signal acquisition module is used to use an EEG device and a heart rate monitor to monitor the patient's EEG activity and heart rate changes in real time, obtain the EEG signal set and the patient's heart rate HR, and transmit the EEG signal set and the patient's heart rate HR to the central processing module via a wireless network;

[0066] The central processing module is used to receive the brain wave signal set and the patient's heart rate HR in real time, pre-process the brain wave signal set, obtain the brain wave power data set, and then store the brain wave power data set and the patient's heart rate HR in the time series database InfluxDB;

[0067] The delirium analysis module is used to perform summary calculation based on the acquired patient heart rate HR, obtain the heart rate variability index HRV, and summarize and calculate with the brain wave power data group to obtain the delirium risk assessment index ZWF, and then perform a preliminary assessment with the preset delirium risk threshold A, and generate a secondary assessment based on the assessment results to deeply predict the delirium risk;

[0068] The deep data acquisition module is used to log in to the hospital information system HIS with authorization credentials to query the patient's medication history data when initially assessing that the patient does not have a risk of delirium, and then record the patient's answers and performance based on the MMSE cognitive function assessment tool to calculate the cognitive function score RZ;

[0069] The in-depth analysis module is used to perform summary calculations based on the medication history data to obtain the drug impact risk index Yfx, and to perform summary calculations with the obtained delirium risk assessment index ZWF and cognitive function score RZ to obtain the comprehensive delirium risk index ZFX, and then perform a secondary assessment with the preset delirium risk threshold A, and intervene and guide the patient based on the assessment results.

[0070] In this embodiment, the EEG signal acquisition module combines EEG equipment and heart rate monitor to capture the patient's EEG activity and heart rate changes in real time. The design of this module effectively improves the efficiency of physiological signal acquisition, making the basic data for subsequent analysis more reliable, and thus provides strong support for the timely identification of delirium risk. The central processing module removes noise through a bandpass filter, and decomposes the signal using fast Fourier transform FFT to generate multi-band brain wave power data. Compared with traditional methods, this module realizes the automation and efficiency of data processing, which not only enhances the accuracy of data analysis, but also manages data efficiently through the time series database InfluxDB, making the analysis and comparison of historical data possible. By storing and processing brain wave power data groups and patient heart rate HR, the system can better grasp the patient's physiological state and ensure the scientificity and systematicness of delirium risk assessment. Under the joint action of the delirium analysis module and the deep data acquisition module, not only can the delirium risk assessment index ZWF be calculated based on real-time data, but also the comprehensive delirium risk index ZFX can be calculated using the patient's medication history and cognitive function assessment. Compared with the traditional single indicator evaluation, this multi-dimensional evaluation method significantly improves the accuracy and timeliness of risk prediction. In addition, it can also provide personalized intervention plans based on the evaluation results, thereby effectively reducing the incidence of postoperative delirium and improving the patient's postoperative safety and quality of life. Through the improvement of these technical means, the system has achieved comprehensive monitoring and intervention of postoperative delirium risks, improving the efficiency and effectiveness of clinical care.

[0071] Example 2

[0072] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the EEG signal acquisition module includes a signal acquisition unit, a data synchronization unit and a data transmission unit;

[0073] The signal acquisition unit is used to monitor the patient's brain electrical activity using an EEG device, place electrode patches on the patient's scalp in the main brain area, record brain wave activities in different frequency bands in real time, obtain a brain wave signal set, and then monitor heart rate changes in real time through a heart rate monitor to obtain the patient's heart rate HR;

[0074] The data transmission unit is used to transmit the acquired brain wave signal set and the patient's heart rate HR to the central processing module via a wireless network.

[0075] In this embodiment, the design of the EEG signal acquisition module realizes accurate monitoring and data processing of the patient's EEG activity and heart rate changes through the effective collaboration of the signal acquisition unit, the data synchronization unit and the data transmission unit. The signal acquisition unit is equipped with standard electrodes to ensure the accurate recording of brain wave activity and to capture brain wave signals of different frequency bands in real time. At the same time, the heart rate data is obtained in real time through the heart rate monitor, which enhances the comprehensiveness of physiological signals. The data synchronization unit assigns accurate timestamps to each physiological signal, and synchronizes the heart rate data with the EEG signal through the interpolation algorithm, so that different signals have a high degree of consistency within the time window, ensuring the reliability of data analysis. The data transmission unit efficiently transmits the collected data to the central processing module through a wireless network, greatly improving the efficiency of data processing. This series of optimization measures not only improves the accuracy and real-time performance of data acquisition, but also provides a high-quality data basis for subsequent delirium risk assessment, and ultimately effectively improves the scientificity and effectiveness of clinical monitoring.

[0076] Example 3

[0077] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the central processing module includes a data processing unit and a data storage unit;

[0078] The data processing unit is used to receive a brain wave signal set and a patient's heart rate HR. The brain wave signal set is preprocessed by removing low-frequency and high-frequency noise in the EEG signal using a 0.5 Hz-45 Hz bandpass filter, and then the frequency domain signal obtained by the Fourier transform FFT is further calculated to obtain a power spectrum by using the fast Fourier transform FFT, and smoothing and standardization processing are performed to obtain a brain wave power data set;

[0079] The brain wave power data set includes alpha wave, beta wave, theta wave and delta wave,

[0080] The band range of the brain wave power data set is: alpha wave is 8Hz-12 Hz, beta wave is 13Hz-30 Hz, theta wave is 4Hz-7 Hz, and delta wave is 0.5Hz-4 Hz;

[0081] The data storage unit is used to store the patient's heart rate HR and brain wave power data groups in the time series database InfluxDB. The time series database InfluxDB marks each data of the patient's heart rate HR and brain wave power data groups with a timestamp, a measurement value patient ID, a sensor type and an independent label, and optimizes storage through compression technology and partition indexing.

[0082] In this embodiment, the central processing module realizes efficient management and analysis of EEG signals and heart rate data through close cooperation between the data processing unit and the data storage unit. The data processing unit uses a 0.5Hz-45Hz bandpass filter to effectively remove the noise in the EEG signal, and uses the fast Fourier transform FFT to accurately extract the power spectrum of α wave, β wave, θ wave and δ wave. This multi-band analysis not only improves the resolution of brain wave data, but also provides an important basis for in-depth understanding of the patient's neurological state. At the same time, the data storage unit stores all data in the time series database InfluxDB to ensure that each data is accompanied by an accurate timestamp and patient information for subsequent tracking and analysis. Through compression technology and partition index optimization storage, the data retrieval efficiency is significantly improved, and the management and analysis of long-term data is supported. This comprehensive and sophisticated data processing and storage mechanism not only improves the accuracy and timeliness of postoperative delirium risk assessment, but also provides valuable real-time data support for clinicians, thereby effectively improving the quality and safety of patient care.

[0083] Example 4

[0084] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the delirium analysis module includes a delirium risk analysis unit and a delirium risk assessment unit;

[0085] The delirium risk analysis unit includes a heart rate analysis unit and a delirium risk calculation unit;

[0086] The heart rate analysis unit is used to perform summary calculation based on the acquired patient heart rate HR to obtain the heart rate variability index HRV;

[0087] The heart rate variability index HRV is calculated by the following formula:

[0088]

[0089] Where M represents the number of measurements, HR i represents the heart rate measured at the i-th time, It represents the average value of M times of heart rate measurement;

[0090] The delirium risk calculation unit is used to perform summary calculation based on the acquired heart rate variability index HRV and brain wave power data group to obtain a delirium risk assessment index ZWF;

[0091]

[0092] Wherein, w0 represents the bias top constant, w1, w2, w3 and w4 represent the weight coefficients of α wave power, β wave power, θ wave power and heart rate variability index HRV respectively, and w1+w2+w3+w4=1, and its specific value is set by the user according to actual use, and e represents the exponential function.

[0093] The delirium risk assessment unit analyzes the heart rate data and brain wave power data of each patient in the time series database InfluxDB, and screens out the historical heart rate data and brain wave power data of the same age group according to the data annotation label, and then calculates the average value of the delirium risk assessment index ZWF obtained according to the screened historical heart rate data and brain wave power data, performs a preset delirium risk threshold A, and then performs a preliminary assessment with the obtained delirium risk assessment index ZWF, and triggers a secondary assessment according to the assessment result. The specific assessment plan is as follows;

[0094] When the delirium risk assessment index ZWF ≥ the preset delirium risk threshold A, it means that the patient is at risk of delirium. At this time, it is recommended that doctors and family members provide psychological counseling to the patient before surgery and pay attention to the depth of anesthesia control during surgery;

[0095] When the delirium risk assessment index ZWF is less than the preset delirium risk threshold A, it means that the patient is not at risk of delirium, and the secondary assessment mechanism is triggered.

[0096] In this embodiment, the delirium analysis module combines the heart rate variability index HRV with the brain wave power data to achieve an accurate assessment of the patient's delirium risk. First, the heart rate analysis unit obtains the heart rate variability index HRV based on the patient's heart rate HR summary calculation, providing an important physiological indicator reflecting the function of the autonomic nervous system, while the delirium risk calculation unit comprehensively considers the multi-band power of brain waves and the heart rate variability index HRV to calculate the delirium risk assessment index ZWF. This multi-dimensional assessment method not only improves the sensitivity of risk identification, but also ensures the relativity and scientificity of the assessment results based on historical data and comparison with patients of the same age group. In addition, by presetting the delirium risk threshold A, clear intervention guidance is provided for doctors and patients; when the risk of delirium is identified, psychological counseling and control of anesthesia depth are recommended, so as to take preventive measures in advance, reduce the incidence of postoperative delirium, and ultimately improve the overall postoperative recovery quality and quality of life of patients. This innovative assessment mechanism makes clinical care more refined and personalized, and provides a strong guarantee for the safety and health of patients.

[0097] Example 5

[0098] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the deep data acquisition module includes a historical medication acquisition unit and a patient cognitive assessment unit;

[0099] The historical medication acquisition unit is used to log in to the hospital information system HIS using the authorization credentials when initially assessing that the patient does not have a risk of delirium, obtain the patient's detailed medical records, and query the patient's medication history data based on the patient's unique identifier, including the number of types of drugs used n, the dosage of drugs used jl, and the frequency of drug use pl;

[0100] The patient cognitive assessment unit is used to ask standardized questions and tasks to patients in a face-to-face manner based on the Mini-Mental State Examination (MMSE) cognitive function assessment tool, record the patient's answers and performance, give corresponding scores based on the patient's performance in each test, and calculate the final cognitive function score RZ.

[0101] In this embodiment, the historical medication acquisition unit systematically collects the patient's medication history, including important information such as drug type, dosage and frequency of use, by accessing the hospital information system HIS. This process ensures a comprehensive understanding of the patient's medication situation, so that risk assessment can be based on real medical data, thereby effectively identifying drug factors that may cause delirium. At the same time, the patient cognitive assessment unit uses the brief mental state examination scale MMSE for standardized assessment, which can timely understand the patient's cognitive function status. Through face-to-face questioning and performance records, the unit provides each patient with a personalized cognitive function score RZ, further enriching the dimension of risk assessment. This multi-dimensional data integration makes the assessment not only based on physiological signals, but also covers drug effects and cognitive status, providing a scientific basis for formulating more targeted intervention plans. In summary, the special benefit of the deep data acquisition module to the system is that it provides a more accurate and personalized delirium risk assessment, which significantly improves the quality and safety of postoperative care for patients.

[0102] Example 6

[0103] This embodiment is explained in Example 5. Please refer to Figure 1 ,Specifically: the in-depth analysis module includes a drug risk analysis unit and a comprehensive analysis unit;

[0104] The drug risk analysis unit is used to perform summary calculation based on the acquired medication history data to obtain the drug impact risk index Yfx;

[0105] The drug impact risk index Yfx is calculated and obtained by the following formula:

[0106]

[0107] In the formula, n represents the number of drug types, a i represents the influence coefficient of the i-th drug type, jl i represents the dosage of the i-th drug, pl i represents the frequency of use of the i-th drug.

[0108] The comprehensive analysis unit includes a comprehensive delirium risk analysis unit and a comprehensive delirium risk assessment unit;

[0109] The comprehensive delirium risk analysis unit is used to perform summary calculation based on the acquired delirium risk assessment index ZWF, cognitive function score RZ and drug impact risk index Yfx to obtain a comprehensive delirium risk index ZFX;

[0110] The comprehensive delirium risk index ZFX is calculated by the following formula:

[0111]

[0112] Wherein, log represents the logarithmic function.

[0113] The comprehensive delirium risk assessment unit is used to perform a secondary assessment based on the obtained comprehensive delirium risk index ZFX and the preset delirium risk threshold A. The specific assessment scheme is as follows;

[0114] When the comprehensive delirium risk index ZFX is less than the preset delirium risk threshold A, it means that the patient's historical medication and cognitive behavior have no effect on postoperative delirium, and normal monitoring should be maintained at this time;

[0115] When the comprehensive delirium risk index ZFX ≥ the preset delirium risk threshold A, it means that the patient's historical medication and cognitive behavior have an impact on postoperative delirium. At this time, the system generates an adjustment plan and iteratively evaluates the adjustment plan through the delirium analysis module until the patient's postoperative delirium prediction reaches a safe level.

[0116] In this embodiment, through the drug risk analysis unit and comprehensive analysis unit of the deep analysis module, a comprehensive evaluation and intervention of the patient's medication and cognitive behavior are achieved, which significantly improves the accuracy and effectiveness of postoperative care. The calculation of the drug impact risk index Yfx provides a scientific basis for evaluating the potential impact of drugs on delirium risk, and the derivation of the comprehensive delirium risk index ZFX integrates multi-dimensional physiological data, cognitive scores and medication history to form a comprehensive risk assessment system. This system can not only identify high-risk patients in a timely manner and take targeted intervention measures, thereby reducing the incidence of postoperative delirium. In addition, through continuous monitoring and iterative evaluation, personalized care plans can be provided to patients to ensure that patients maintain a good cognitive state during the postoperative rehabilitation process, thereby improving the overall quality of life and safety of patients. This comprehensive and dynamic risk management strategy not only improves the effectiveness of clinical care, but also creates more favorable conditions for patients' postoperative recovery.

[0117] Example 7

[0118] See also Figure 1 and Figure 2 , a method for predicting postoperative delirium based on electroencephalogram signals, comprising the following steps:

[0119] S1, using EEG equipment and heart rate monitor to monitor the patient's brain electrical activity and heart rate changes in real time, obtain brain wave signal set and patient's heart rate HR, and transmit the brain wave signal set and patient's heart rate HR to S2 via a wireless network;

[0120] S2, receiving the brain wave signal set and the patient's heart rate HR in real time, preprocessing the brain wave signal set, obtaining the brain wave power data set, and then storing the brain wave power data set and the patient's heart rate HR in the time series database InfluxDB;

[0121] S3. The heart rate variability index HRV is obtained by summarizing and calculating the patient's heart rate HR, and the delirium risk assessment index ZWF is obtained by summarizing and calculating the data with the brain wave power data group. Then, a preliminary assessment is performed with the preset delirium risk threshold A, and a secondary assessment is generated based on the assessment results to deeply predict the delirium risk;

[0122] S4. When the patient is initially assessed as not at risk of delirium, use the authorization credentials to log in to the hospital information system (HIS) to query the patient's medication history data, and then use the short mental state examination (MMSE) cognitive function assessment tool to record the patient's answers and performance and calculate the cognitive function score RZ;

[0123] S5. Summarize and calculate the medication history data to obtain the drug impact risk index Yfx, and summarize and calculate it with the obtained delirium risk assessment index ZWF and cognitive function score RZ to obtain the comprehensive delirium risk index ZFX, and then conduct a secondary assessment with the preset delirium risk threshold A, and intervene and guide the patient based on the assessment results.

[0124] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A postoperative delirium prediction system based on electroencephalogram signals, characterized in that: It includes an EEG signal acquisition module, a central processing module, a delirium analysis module, a deep data acquisition module and a deep analysis module; The EEG signal acquisition module is used to use an EEG device and a heart rate monitor to monitor the patient's EEG activity and heart rate changes in real time, obtain the EEG signal set and the patient's heart rate HR, and transmit the EEG signal set and the patient's heart rate HR to the central processing module via a wireless network; The central processing module is used to receive the brain wave signal set and the patient's heart rate HR in real time, pre-process the brain wave signal set, obtain the brain wave power data set, and then store the brain wave power data set and the patient's heart rate HR in the time series database InfluxDB; The delirium analysis module is used to perform summary calculation based on the acquired patient heart rate HR, obtain the heart rate variability index HRV, and summarize and calculate with the brain wave power data group to obtain the delirium risk assessment index ZWF, and then perform a preliminary assessment with the preset delirium risk threshold A, and generate a secondary assessment based on the assessment results to deeply predict the delirium risk; The deep data acquisition module is used to log in to the hospital information system HIS with authorization credentials to query the patient's medication history data when initially assessing that the patient does not have a risk of delirium, and then record the patient's answers and performance based on the MMSE cognitive function assessment tool to calculate the cognitive function score RZ; The in-depth analysis module is used to perform summary calculations based on the medication history data to obtain the drug impact risk index Yfx, and to perform summary calculations with the obtained delirium risk assessment index ZWF and cognitive function score RZ to obtain the comprehensive delirium risk index ZFX, and then perform a secondary assessment with the preset delirium risk threshold A, and intervene and guide the patient based on the assessment results.

2. The postoperative delirium prediction system based on EEG signals according to claim 1, characterized in that: The EEG signal acquisition module includes a signal acquisition unit, a data synchronization unit and a data transmission unit; The signal acquisition unit is used to monitor the patient's brain electrical activity using an EEG device, place electrode patches on the patient's scalp in the main brain area, record brain wave activities in different frequency bands in real time, obtain a brain wave signal set, and then monitor heart rate changes in real time through a heart rate monitor to obtain the patient's heart rate HR; The data transmission unit is used to transmit the acquired brain wave signal set and the patient's heart rate HR to the central processing module via a wireless network.

3. The postoperative delirium prediction system based on EEG signals according to claim 2, characterized in that: The central processing module includes a data processing unit and a data storage unit; The data processing unit is used to receive a brain wave signal set and a patient's heart rate HR. The brain wave signal set is preprocessed by removing low-frequency and high-frequency noise in the EEG signal using a 0.5 Hz-45 Hz bandpass filter, and then the frequency domain signal obtained by the Fourier transform FFT is further calculated to obtain a power spectrum by using the fast Fourier transform FFT, and smoothing and standardization processing are performed to obtain a brain wave power data set; The brain wave power data set includes alpha waves, beta waves, theta waves and delta waves; The band range of the brain wave power data set is: alpha wave is 8Hz-12 Hz, beta wave is 13Hz-30 Hz, theta wave is 4Hz-7Hz, and delta wave is 0.5Hz-4 Hz; The data storage unit is used to store the patient's heart rate HR and brain wave power data groups in the time series database InfluxDB. The time series database InfluxDB marks each data of the patient's heart rate HR and brain wave power data groups with the measurement value patient ID, sensor type and independent label, and optimizes storage through compression technology and partition indexing.

4. The postoperative delirium prediction system based on EEG signals according to claim 3, characterized in that: The delirium analysis module includes a delirium risk analysis unit and a delirium risk assessment unit; The delirium risk analysis unit includes a heart rate analysis unit and a delirium risk calculation unit; The heart rate analysis unit is used to perform summary calculation based on the acquired patient heart rate HR to obtain the heart rate variability index HRV; The heart rate variability index HRV is calculated by the following formula: Where M represents the number of measurements, HR i represents the heart rate measured at the i-th time, It represents the average value of M heart rate measurements; The delirium risk calculation unit is used to perform summary calculation based on the acquired heart rate variability index HRV and brain wave power data group to obtain a delirium risk assessment index ZWF; Wherein, w0 represents the bias top constant, w1, w2, w3 and w4 represent the weight coefficients of α wave power, β wave power, θ wave power and heart rate variability index HRV respectively, and w1+w2+w3+w4=1, and its specific value is set by the user according to actual use, and e represents the exponential function.

5. The postoperative delirium prediction system based on EEG signals according to claim 4, characterized in that: The delirium risk assessment unit analyzes the heart rate data and brain wave power data of each patient in the time series database InfluxDB, and screens out the historical heart rate data and brain wave power data of the same age group according to the data annotation label, and then calculates the average value of the delirium risk assessment index ZWF obtained according to the screened historical heart rate data and brain wave power data, performs a preset delirium risk threshold A, and then performs a preliminary assessment with the obtained delirium risk assessment index ZWF, and triggers a secondary assessment according to the assessment result. The specific assessment plan is as follows; When the delirium risk assessment index ZWF ≥ the preset delirium risk threshold A, it means that the patient is at risk of delirium. At this time, it is recommended that doctors and family members provide psychological counseling to the patient before surgery and pay attention to the depth of anesthesia control during surgery; When the delirium risk assessment index ZWF is less than the preset delirium risk threshold A, it means that the patient is not at risk of delirium, and the secondary assessment mechanism is triggered.

6. The postoperative delirium prediction system based on EEG signals according to claim 5, characterized in that: The deep data acquisition module includes a historical medication acquisition unit and a patient cognitive assessment unit; The historical medication acquisition unit is used to log in to the hospital information system HIS using the authorization credentials when initially assessing that the patient does not have a risk of delirium, obtain the patient's detailed medical records, and query the patient's medication history data based on the patient's unique identifier, including the number of types of drugs used n, the dosage of drugs used jl, and the frequency of drug use pl; The patient cognitive assessment unit is used to ask standardized questions and tasks to patients in a face-to-face manner based on the Mini-Mental State Examination (MMSE) cognitive function assessment tool, record the patient's answers and performance, give corresponding scores based on the patient's performance in each test, and calculate the final cognitive function score RZ.

7. The postoperative delirium prediction system based on EEG signals according to claim 6, characterized in that: The in-depth analysis module includes a drug risk analysis unit and a comprehensive analysis unit; The drug risk analysis unit is used to perform summary calculation based on the acquired medication history data to obtain the drug impact risk index Yfx; The drug impact risk index Yfx is calculated and obtained by the following formula: In the formula, n represents the number of drug types, a i represents the influence coefficient of the i-th drug type, jl i represents the dosage of the i-th drug, pl i represents the frequency of use of the i-th drug.

8. The postoperative delirium prediction system based on EEG signals according to claim 7, characterized in that: The comprehensive analysis unit includes a comprehensive delirium risk analysis unit and a comprehensive delirium risk assessment unit; The comprehensive delirium risk analysis unit is used to perform summary calculation based on the acquired delirium risk assessment index ZWF, cognitive function score RZ and drug impact risk index Yfx to obtain a comprehensive delirium risk index ZFX; The comprehensive delirium risk index ZFX is calculated by the following formula: Wherein, log represents the logarithmic function.

9. The postoperative delirium prediction system based on EEG signals according to claim 8, characterized in that: The comprehensive delirium risk assessment unit is used to perform a secondary assessment based on the obtained comprehensive delirium risk index ZFX and the preset delirium risk threshold A. The specific assessment scheme is as follows; When the comprehensive delirium risk index ZFX is less than the preset delirium risk threshold A, it means that the patient's historical medication and cognitive behavior have no effect on postoperative delirium, and normal monitoring should be maintained at this time; When the comprehensive delirium risk index ZFX ≥ the preset delirium risk threshold A, it means that the patient's historical medication and cognitive behavior have an impact on postoperative delirium. At this time, the system generates an adjustment plan and iteratively evaluates the adjustment plan through the delirium analysis module until the patient's postoperative delirium prediction reaches a safe level.

10. A method for predicting postoperative delirium based on electroencephalogram signals, applied to a system for predicting postoperative delirium based on electroencephalogram signals as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: S1, using EEG equipment and heart rate monitor to monitor the patient's brain electrical activity and heart rate changes in real time, obtain brain wave signal set and patient's heart rate HR, and transmit the brain wave signal set and patient's heart rate HR to S2 via a wireless network; S2, receiving the brain wave signal set and the patient's heart rate HR in real time, preprocessing the brain wave signal set, obtaining the brain wave power data set, and then storing the brain wave power data set and the patient's heart rate HR in the time series database InfluxDB; S3. The heart rate variability index HRV is obtained by summarizing and calculating the patient's heart rate HR, and the delirium risk assessment index ZWF is obtained by summarizing and calculating the data with the brain wave power data group. Then, a preliminary assessment is performed with the preset delirium risk threshold A, and a secondary assessment is generated based on the assessment results to deeply predict the delirium risk; S4. When the patient is initially assessed as not at risk of delirium, use the authorization credentials to log in to the hospital information system (HIS) to query the patient's medication history data, and then use the short mental state examination (MMSE) cognitive function assessment tool to record the patient's answers and performance and calculate the cognitive function score RZ; S5. Summarize and calculate the medication history data to obtain the drug impact risk index Yfx, and summarize and calculate it with the obtained delirium risk assessment index ZWF and cognitive function score RZ to obtain the comprehensive delirium risk index ZFX, and then conduct a secondary assessment with the preset delirium risk threshold A, and intervene and guide the patient based on the assessment results.

Images