A method and system for remote intraoperative neurophysiological monitoring

Abstract

The application provides a remote intraoperative neurophysiological monitoring method and system, first, a set of continuous neuroelectrophysiological waveform signals of a patient in an operation recorded synchronously through multiple monitoring leads is collected, then feature extraction is performed on the signal set to obtain a nerve function state feature containing waveform features and rhythm features, then remote real-time analysis is carried out on the nerve function state feature to generate an intraoperative nerve function monitoring result containing function stability information and abnormal fluctuation information, and the intraoperative nerve function monitoring result is transmitted to a remote monitoring terminal for dynamic display, finally, an intraoperative intervention prompt operation is triggered based on the abnormal fluctuation information to assist the operator to adjust the operation, thereby breaking through the spatial limitation of traditional intraoperative neuroelectrophysiological monitoring, fully utilizing high-quality medical resources, providing decision support for the operator in time, and reducing the risk of surgical nerve injury.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring technology, and more specifically, to a remote intraoperative neurophysiological monitoring method and system. Background Technology

[0002] During surgery, real-time and accurate monitoring of the patient's neurological function is crucial for ensuring surgical success and postoperative neurological recovery. Traditional intraoperative neurophysiological monitoring methods typically involve using specialized monitoring equipment and personnel at the surgical site to collect and analyze the patient's neurophysiological signals. However, this approach has several limitations. On the one hand, the limited space at the surgical site means that additional monitoring equipment and personnel may interfere with the surgical procedure, affecting its smoothness and efficiency. On the other hand, in some complex or large surgeries, on-site monitoring may not be able to fully utilize broader medical resources, such as the lack of real-time consultation and comprehensive judgment from multidisciplinary experts.

[0003] Furthermore, existing neurophysiological monitoring technologies have shortcomings in signal processing and analysis. They can usually only obtain basic information about neurophysiological signals, and the assessment of neurological function is not comprehensive or in-depth enough. They are unable to accurately capture subtle changes in neurological function and potential risks, and cannot provide timely and effective decision support for surgeons, thus increasing the risk of nerve damage during surgery. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for remote intraoperative neurophysiological monitoring, the method comprising:

[0005] The patient's neurophysiological signals were collected during the operation, and the neurophysiological signals included continuous neurophysiological waveform signals recorded synchronously through multiple monitoring leads.

[0006] The neural electrophysiological signal set is subjected to feature extraction processing to obtain the neural functional state features of the neural electrophysiological waveform signals, wherein the neural functional state features include waveform features and rhythm features;

[0007] The neurological function state characteristics are remotely analyzed and processed in real time to generate intraoperative neurological function monitoring results, which include functional stability information and abnormal fluctuation information.

[0008] The intraoperative neurological function monitoring results are transmitted to a remote monitoring terminal, which is used to dynamically display the functional stability information and abnormal fluctuation information.

[0009] Based on the abnormal fluctuation information in the intraoperative neurological function monitoring results, an intraoperative intervention prompt operation is triggered, which is used to assist the surgeon in adjusting the surgical procedure.

[0010] In another aspect, embodiments of the present invention also provide a remote intraoperative neurophysiological monitoring system, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0011] Based on the above, this embodiment of the invention first collects a set of continuous neurophysiological waveform signals synchronously recorded by multiple monitoring leads. Feature extraction processing is then performed on this set of signals to obtain neurofunctional state features containing waveform and rhythm characteristics. This allows for deeper exploration of the intrinsic information of the neurophysiological signals, more accurately reflecting the neurofunctional state. Remote real-time analysis of the neurofunctional state features generates intraoperative neurofunctional monitoring results containing functional stability and abnormal fluctuation information. This breaks spatial limitations, enabling experts to participate remotely in monitoring and diagnosis, fully utilizing high-quality medical resources. The monitoring results are transmitted to a remote monitoring terminal for dynamic display, facilitating real-time monitoring of the patient's neurofunctional status by relevant personnel. Intraoperative intervention prompts are triggered based on abnormal fluctuation information, providing timely decision-making support for the surgeon, assisting in adjusting surgical procedures, and effectively reducing the risk of intraoperative nerve damage. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the execution flow of the remote intraoperative neurophysiological monitoring method provided in this embodiment of the invention.

[0013] Figure 2 This is a schematic diagram of exemplary hardware and software components of the remote intraoperative neurophysiological monitoring system provided in an embodiment of the present invention. Detailed Implementation

[0014] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a remote intraoperative neurophysiological monitoring method according to an embodiment of the present invention. The following is a detailed description of the remote intraoperative neurophysiological monitoring method.

[0015] Step S110: Acquire a set of neurophysiological signals from the patient during the operation, the set of neurophysiological signals including continuous neurophysiological waveform signals recorded synchronously through multiple monitoring leads.

[0016] In neurosurgical procedures involving clipping cerebral aneurysms, it is essential to collect a dataset of neurophysiological signals to monitor the patient's neurological function in real time and comprehensively during surgery. The operating room is equipped with a neurophysiological monitoring system featuring multiple monitoring leads. These leads are positioned on specific areas of the patient's scalp based on the location of the aneurysm and the distribution of surrounding nerves.

[0017] For example, if a cerebral aneurysm is located near the left temporal lobe of the brain, monitoring leads will be densely arranged on the corresponding scalp area to focus on capturing the electrophysiological activity of neurons in that region. Simultaneously, a certain number of monitoring leads will be strategically distributed in other relevant brain regions to ensure the recording of broad and comprehensive neurophysiological information. Each monitoring lead continuously records neurophysiological waveform signals. Furthermore, all monitoring leads operate strictly synchronously, meaning they begin recording signals at the same time to ensure that the recorded neurophysiological signals are continuous and synchronized, forming a complete set of neurophysiological signals. The signals in this set of neurophysiological signals reflect the real-time activity of neurons in different brain regions during the surgical procedure.

[0018] Step S120: Perform feature extraction processing on the set of neurophysiological signals to obtain the neurofunctional state features of the neurophysiological waveform signals, wherein the neurofunctional state features include waveform features and rhythm features.

[0019] After acquiring the set of neurophysiological signals, feature extraction processing is required to extract key information reflecting the state of nerve function. Waveform and rhythm features are important indicators in neurophysiological signals, reflecting the activity patterns and functional states of the nerves. By extracting and analyzing waveform and rhythm features from neurophysiological signals, we can more accurately understand the changes in the patient's nerve function during surgery.

[0020] Step S121: Perform signal preprocessing on the continuous electrophysiological waveform signals in the set of neurophysiological signals to obtain interference-free electrophysiological waveform signals.

[0021] In actual signal acquisition, due to the complexity of the surgical environment and the patient's own physiological activities, the acquired continuous electrophysiological waveform signals are inevitably subject to various interferences. These interferences affect the accurate extraction of signal features, so signal preprocessing is required to remove these interferences in order to obtain pure electrophysiological waveform signals that can truly reflect neural activity.

[0022] Step S1211: Perform power frequency interference suppression processing on the continuous electrophysiological waveform signal, and use notch filtering to filter out the fixed frequency interference components in the continuous electrophysiological waveform signal, while retaining the effective frequency components of the neurophysiological signal.

[0023] In the environment of cerebral aneurysm clipping surgery, various electrical devices in the operating room generate power frequency interference. This power frequency interference typically manifests as a fixed-frequency electrical signal that superimposes on the neurophysiological waveform signal, affecting signal quality. To remove this power frequency interference, a notch filter can be used. The notch filter's parameters are precisely set according to the common power frequency interference frequencies in the surgical environment. When a continuous electrophysiological waveform signal passes through the notch filter, the filter identifies the fixed-frequency interference components and filters them out. The effective frequency components of the neurophysiological signal can then pass through the filter smoothly, resulting in a pre-purified signal. This ensures that the signal analyzed subsequently is not affected by power frequency interference, more accurately reflecting the true electrophysiological activity of the nerve.

[0024] Step S1212: Perform baseline drift correction processing on the continuous electrophysiological waveform signal, and eliminate slow baseline fluctuations in the continuous electrophysiological waveform signal by using a moving average filtering method, so that the waveform baseline is kept at a preset stable level.

[0025] During data acquisition, continuous electrophysiological waveform signals may exhibit slow baseline fluctuations. These baseline drifts can be caused by factors such as slight patient movements or minor changes in electrode-skin contact. Baseline drift leads to an overall signal shift, affecting the accurate interpretation of waveform characteristics. To eliminate this baseline drift, a moving average filtering method can be used. Specifically, a fixed-length time window is set, and the signal is averaged within this window. As time progresses, this time window slides along the signal's time axis, continuously performing averaging calculations. This process yields a smooth baseline estimate. Subtracting this baseline estimate from the original signal eliminates the slow baseline fluctuations, maintaining the waveform baseline at a preset stable level. Consequently, subsequent analysis of the signal's waveform characteristics is free from baseline drift interference, enabling more accurate identification of waveform morphology and changes.

[0026] Step S1213: Perform electromyographic interference removal processing on the continuous electrophysiological waveform signal, and use an adaptive filtering algorithm to identify and suppress high-frequency electromyographic interference pulses in the continuous electrophysiological waveform signal while retaining low-frequency neurophysiological signal components.

[0027] During cerebral aneurysm clipping surgery, the patient's muscle activity also generates electrical signals, which can interfere with the acquisition of neurophysiological waveform signals. Electromyographic (EMG) signals typically have high frequencies, while neurophysiological signals have relatively low frequencies. To remove EMG interference, an adaptive filtering algorithm can be used. An adaptive filter automatically adjusts its parameters based on the characteristics of the input signal to effectively identify and suppress EMG interference. It analyzes the frequency components of the signal, identifies high-frequency EMG interference pulses, and subtracts these interference pulses from the continuous electrophysiological waveform signal by adjusting the filter weights. This preserves the low-frequency neurophysiological signal components, making the signal purer and more accurately reflecting nerve activity.

[0028] Step S1214: Perform electrode noise filtering on the continuous electrophysiological waveform signal, and identify and remove sudden electrode noise spikes in the continuous electrophysiological waveform signal by using a threshold judgment method.

[0029] During signal acquisition, the contact between the electrodes and the skin may generate sudden noise spikes, which can severely affect signal quality. To remove these electrode noise spikes, a thresholding method can be used. First, a reasonable threshold can be set based on the amplitude range of normal neurophysiological signals. When the amplitude of a continuous electrophysiological waveform exceeds this threshold, the signal corresponding to that amplitude is considered a sudden electrode noise spike. Then, these noise spikes can be removed from the signal and replaced with a suitable substitute value. This substitute value can be calculated by interpolation based on the normal signals before and after the noise spike to ensure signal continuity and integrity. This method effectively filters out electrode noise spikes and improves signal quality.

[0030] Step S1215: Integrate the preprocessed signals to obtain a de-interferenced electrophysiological waveform signal that removes physiological interference and external environmental interference. The de-interferenced electrophysiological waveform signal retains the original characteristics of neurophysiological activity.

[0031] After completing preprocessing steps such as power frequency interference suppression, baseline drift correction, electromyography interference removal, and electrode noise filtering, the resulting processed signals need to be integrated. This integration process ensures that the results of each processing step are consistent and do not introduce new interference or errors. Specifically, the signals obtained from different processing steps can be matched and fused in time and amplitude to form a unified signal. The final interference-free electrophysiological waveform signal removes physiological and environmental interference while preserving the original characteristics of neurophysiological activity.

[0032] Step S122: Perform time-division processing on the interference-free electrophysiological waveform signal, and divide the interference-free electrophysiological waveform signal into multiple continuous waveform time segments according to a preset time interval, with each waveform time segment having a continuous time sequence relationship.

[0033] After obtaining the interference-free electrophysiological waveform signal, it needs to be segmented in the time dimension for more detailed analysis of its characteristics. In cerebral aneurysm clipping surgery, a suitable time interval can be preset based on the progress of the surgery and the characteristics of the neurophysiological signals. For example, this time interval can be determined based on the time cycle of key operations during the surgery; if clipping the aneurysm may require a certain amount of time, the time interval can be set to match that operation time. Then, according to the preset time interval, the interference-free electrophysiological waveform signal is divided into multiple continuous waveform time segments. Each waveform time segment is continuous in time and has a clear sequence. Through the above segmentation process, a long signal can be decomposed into multiple shorter, easier-to-analyze segments, facilitating subsequent in-depth study of the waveform and rhythmic characteristics of each segment. Each waveform time segment contains detailed information about the neurophysiological signals within that time period.

[0034] Step S123: Extract waveform features for each waveform time segment, identify the characteristic waveform morphology in the waveform time segment, the characteristic waveform morphology includes the waveform fluctuation pattern and the connection relationship between waveforms, and obtain the waveform features of each waveform time segment based on the characteristic waveform morphology.

[0035] After completing the time-dimension segmentation, waveform feature extraction is required for each waveform time segment. Waveform features can reflect the waveform change characteristics of neural electrophysiological signals within a specific time segment.

[0036] Step S1231: Perform waveform morphology recognition on each waveform time segment, and compare the waveform time segment with a preset standard neurophysiological waveform template using a template matching method to identify the characteristic waveforms in the waveform time segment that conform to the standard template.

[0037] In cerebral aneurysm clipping surgery, a series of standard neurophysiological waveform templates can be pre-established. These templates are derived from the analysis and summarization of a large number of normal neurophysiological signals, representing typical waveform morphologies under different neurological functional states. For each waveform time segment, a template matching method can be used to compare it with the pre-set standard templates. Specifically, the waveform time segment is slid along the time axis and compared with each standard template one by one. By calculating the similarity index between the two, such as the correlation coefficient, it is determined whether there is a characteristic waveform in the waveform time segment that conforms to the standard template. If the similarity index exceeds a preset threshold, it is considered that there is a corresponding characteristic waveform in the waveform time segment. In this way, representative characteristic waveforms can be identified from complex waveform time segments.

[0038] Step S1232: Extract the fluctuation pattern of the feature waveform, analyze the rising segment change trend and falling segment change trend of the feature waveform, and determine the overall morphological characteristics of the feature waveform.

[0039] After identifying the characteristic waveform, it is necessary to further extract its fluctuation patterns. This includes a detailed analysis of the rising and falling segments of the characteristic waveform. The rising segment refers to the part of the waveform that rises from a lower amplitude to a higher amplitude, while the falling segment is the part that falls from a higher amplitude to a lower amplitude. For the rising segment, the trend of its rising speed, slope, and other changes can be analyzed. For example, a faster rising speed may indicate a higher level of nerve excitation, while a slower rising speed may indicate a slower nerve response. Similarly, for the falling segment, the characteristics such as the falling speed and slope are analyzed. By comprehensively analyzing the changing trends of the rising and falling segments, the overall morphological characteristics of the characteristic waveform can be determined. These overall morphological characteristics can reflect the activity pattern and functional state of the nerve within that time period.

[0040] Step S1233: Analyze the connection relationship between adjacent feature waveforms in the waveform time segment, identify the interval pattern and superposition pattern between feature waveforms, and determine the structural features of the waveform sequence.

[0041] In addition to analyzing the morphological characteristics of individual feature waveforms, it is also necessary to analyze the connectivity between adjacent feature waveforms within a waveform time segment. Different interval patterns and superposition patterns may exist between adjacent feature waveforms. An interval pattern refers to the time interval between adjacent feature waveforms; for example, a longer interval may indicate a slower rhythm of neural activity, while a shorter interval may indicate more frequent neural activity. A superposition pattern refers to whether adjacent feature waveforms overlap; the degree and manner of superposition can also reflect the complexity of neural activity. By analyzing these interval and superposition patterns, the structural characteristics of the waveform sequence can be determined. The structural characteristics of the waveform sequence reflect the organization and arrangement of neurophysiological signals in the time dimension.

[0042] Step S1234: Construct a waveform feature descriptor based on the overall morphological features and structural features. The waveform feature descriptor includes the morphological parameters of the feature waveform and the structural parameters of the waveform sequence.

[0043] After determining the overall morphological characteristics of the characteristic waveform and the structural characteristics of the waveform sequence, these characteristics need to be integrated to construct a waveform feature descriptor. The waveform feature descriptor is a comprehensive feature representation that includes the morphological parameters of the characteristic waveform and the structural parameters of the waveform sequence. Morphological parameters may include the rise rate, fall rate, and amplitude of the characteristic waveform, while structural parameters may include the time interval between adjacent characteristic waveforms and the degree of superposition. By combining these parameters, a multi-dimensional feature vector is formed, i.e., the waveform feature descriptor. This waveform feature descriptor can comprehensively describe the waveform characteristics of a waveform time segment.

[0044] Step S1235: Use the waveform feature descriptor as the waveform feature of each waveform time segment, the waveform feature being used to characterize the waveform change characteristics of the neurophysiological signal within the time segment.

[0045] Finally, the constructed waveform feature descriptor is used as the waveform feature for each waveform time segment. This waveform feature can accurately characterize the waveform changes of the neurophysiological signal within that time segment. By analyzing and comparing the waveform features of each waveform time segment, the waveform changes of the neurophysiological signal in different time periods can be determined, thereby inferring whether the functional state of the nerve has changed. For example, if the waveform features in a certain time period differ significantly from normal, it may indicate that the nerve has been affected by surgical procedures during that time period, resulting in functional abnormalities.

[0046] Step S124: Extract rhythm features from the interference-free electrophysiological waveform signal, analyze the repetitive change pattern of the interference-free electrophysiological waveform signal in a continuous time interval, identify rhythmic patterns with periodic occurrence characteristics, and obtain the rhythm features of the interference-free electrophysiological waveform signal based on the rhythmic patterns.

[0047] Besides waveform characteristics, rhythmic characteristics are also important features in neurophysiological signals. Rhythmic characteristics reflect the periodicity and regularity of neural activity. In cerebral aneurysm clipping surgery, rhythmic characteristics need to be extracted from the interference-free electrophysiological waveform signals.

[0048] First, the interference-free electrophysiological waveform signal can be analyzed over a continuous time interval to find recurring patterns. This can be achieved through methods such as spectral analysis. Spectral analysis converts the signal from the time domain to the frequency domain, allowing for clearer observation of the signal's frequency components. In the frequency domain, periodic signals exhibit peaks at specific frequencies. By identifying these peaks, the rhythmic patterns present in the signal can be determined. For example, if a significant peak is found at a certain frequency in the spectrum, and this peak persists over a continuous time interval, then the signal corresponding to that frequency can be considered periodic, i.e., a corresponding rhythmic pattern exists.

[0049] After identifying the rhythmic pattern, features associated with that pattern can be further extracted. These features can include the rhythm's frequency, amplitude, and phase. Frequency indicates the speed of the rhythm, amplitude indicates its intensity, and phase indicates its relative position in time. By comprehensively analyzing these features, the rhythmic characteristics of the interference-free electrophysiological waveform signal can be obtained. Rhythmic characteristics reflect the rhythm and stability of nerve activity over a period of time and are of significant reference value for judging changes in nerve function. For example, if the rhythmic characteristics change significantly, such as changes in rhythm frequency or fluctuations in amplitude, it may indicate that the nerve's functional state has been affected, requiring further attention and analysis.

[0050] Step S125: Perform time axis association processing on the waveform features and the rhythm features to establish the correspondence between waveform features and rhythm features within the same time interval, and generate a set of associated features containing time markers.

[0051] After extracting waveform and rhythm features separately, in order to gain a more comprehensive understanding of the characteristics of neurophysiological signals and the functional state of the nerves, it is necessary to perform time-axis correlation processing on these two features. In the context of cerebral aneurysm clipping surgery, since waveform features are extracted based on waveform time segments, while rhythm features are extracted based on continuous time intervals, it is necessary to correlate and associate them on the time axis.

[0052] The specific operation involves arranging waveform and rhythm features in chronological order and then establishing their correspondences within the same time interval. For example, for a specific time interval, the corresponding waveform and rhythm features within that interval are identified and associated. To facilitate subsequent analysis and processing, time stamps can be added to each associated waveform and rhythm feature, recording their corresponding time intervals. This process generates a set of associated features containing time stamps. This set integrates waveform and rhythm features along the time dimension, allowing for simultaneous analysis of neurophysiological signals at different time points from both waveform and rhythm perspectives, providing a more comprehensive understanding of the neuronal functional state. For instance, within the time interval of a critical surgical procedure, changes in waveform and rhythm features can be observed simultaneously, leading to a more accurate assessment of the surgical procedure's impact on neuronal function.

[0053] Step S126: Based on the set of associated features, the neural functional state features of the neural electrophysiological waveform signal are integrated to obtain the neural functional state features, which include combinations of waveform features and rhythm features corresponding to different time intervals.

[0054] After generating a set of associated features containing time stamps, it is necessary to integrate these features to obtain the neural functional state features of the neurophysiological waveform signals. The neural functional state features are a combination of waveform features and rhythmic features corresponding to different time intervals.

[0055] In cerebral aneurysm clipping surgery, waveform and rhythmic features from the associated feature set can be grouped and integrated according to time intervals. For each time interval, the corresponding waveform and rhythmic features within that interval are combined to form a multidimensional feature vector, which represents the functional state of the nerve within that time interval. By analyzing and comparing the feature vectors from different time intervals, the changes in nerve function over time can be determined. For example, the characteristics of nerve function may change differently at different stages of the surgery. During aneurysm clipping, waveform and rhythmic features may fluctuate significantly; analyzing these changes allows for timely detection of whether nerve function has been affected. Finally, the feature vectors from all time intervals are integrated to form the neurofunctional state characteristics of the neurophysiological waveform signal. These characteristics comprehensively and accurately reflect the functional state of the nerve throughout the entire surgical process.

[0056] Step S130: Perform remote real-time analysis and processing on the neural function state characteristics to generate intraoperative neural function monitoring results, which include functional stability information and abnormal fluctuation information.

[0057] After obtaining the characteristics of the neurological function status, in order to know the patient's neurological function status during the operation in a timely manner, it is necessary to perform remote real-time analysis and processing on these characteristics to generate intraoperative neurological function monitoring results.

[0058] Step S131: The neural function state features are sent to the remote analysis system so that the remote analysis system performs time series modeling on the neural function state features and constructs a dynamic model of the neural function state features changing with monitoring time. The dynamic model is used to describe the continuous change process of waveform features and rhythm features.

[0059] In a cerebral aneurysm clipping surgery scenario, neurological functional status characteristics are transmitted from the surgical site to a remote analysis system. Upon receiving these characteristics, the remote analysis system can perform time-series modeling. Time-series modeling is a method for analyzing data that changes over time, capturing features such as trends, periodicity, and seasonality.

[0060] For neural functional state characteristics, the remote analysis system arranges waveform features and rhythmic features separately according to monitoring time, forming two time series. Then, using appropriate time series modeling methods, such as the Autoregressive Integrated Moving Average (ARIMA) model or Long Short-Term Memory (LSTM) network, these two time series are modeled. These models can predict future data based on historical data, thus constructing a dynamic model of how neural functional state characteristics change over monitoring time. This dynamic model can describe the changes in waveform and rhythmic features over continuous monitoring time, including their rising and falling trends, and periodic changes. Through this dynamic model, a deeper understanding of the dynamic patterns of neural functional state changes can be obtained.

[0061] Step S132: Analyze the changing trend of the neural functional state characteristics based on the dynamic model, extract the changing patterns of the waveform characteristics and the changing patterns of the rhythm characteristics, and obtain the overall trend change information of the neural functional state characteristics.

[0062] After constructing the dynamic model, it is necessary to analyze the changing trends of neural functional state characteristics based on the dynamic model.

[0063] Step S1321: Based on the waveform feature time series output by the dynamic model, analyze the amplitude and direction of change of the waveform features within the continuous monitoring time, and determine the short-term and long-term change patterns of the waveform features.

[0064] In cerebral aneurysm clipping surgery, dynamic models output a time series of waveform characteristics changing over monitoring time. For amplitude analysis of waveform characteristics, the focus is on the differences in amplitude within different short time intervals. For example, within a short time segment, it's observed whether the waveform amplitude increases or decreases, and to what extent. The direction of change refers to whether the waveform characteristic shows an upward or downward trend. Through continuous observation and analysis of these amplitude and direction changes, short-term change patterns of the waveform characteristics can be determined. For instance, if the waveform amplitude continuously increases and the magnitude of the increase gradually increases within several adjacent short time segments, it can be determined that the waveform characteristic exhibits an upward and strengthening change pattern within that short period.

[0065] To determine long-term change patterns, the observation timeframe is expanded to a longer period. By combining the changes in multiple short time segments, the overall trend of waveform characteristics over a longer time period is analyzed. For example, during the first half of the operation, the waveform characteristics generally show a fluctuating upward trend, but the magnitude of the increase is not uniform, sometimes large and sometimes small. This allows us to determine the long-term change pattern of the waveform characteristics within this longer time period.

[0066] Step S1322: Based on the time series of rhythmic features output by the dynamic model, analyze the frequency and intensity changes of the rhythmic features during continuous monitoring time, and determine the short-term and long-term change patterns of the rhythmic features.

[0067] Similarly, dynamic models also output time series of rhythmic features. For frequency variation analysis of rhythmic features, the number of times the rhythm occurs within a continuous monitoring period is counted. If the frequency of a rhythm suddenly increases or decreases within a short period, this frequency change can be captured. For example, if a rhythm that initially occurs stably at a certain frequency within a short time segment suddenly experiences a significant increase in frequency in the following short period, this is a short-term manifestation of frequency variation. Intensity variation refers to changes in the amplitude of the rhythm. By observing the increase or decrease in rhythm amplitude within a short period, the short-term intensity variation pattern of the rhythmic features can be determined.

[0068] Regarding long-term change patterns, the frequency and intensity changes of rhythmic features over a longer period can be considered. For example, during the entire surgical procedure, the frequency of the rhythmic features may gradually decrease first, and then slowly increase again at a certain stage, while the intensity may also fluctuate accordingly. Based on these combined factors, the long-term change pattern of the rhythmic features can be determined.

[0069] Step S1323: The short-term and long-term change patterns of the waveform features are fused to obtain a comprehensive change pattern of the waveform features, which reflects the overall evolution law of the waveform features over time.

[0070] After identifying the short-term and long-term variation patterns of the waveform characteristics, they need to be fused to gain a more comprehensive understanding of the changes in the waveform characteristics. The fusion process considers both the rapid fluctuations in the short-term variation pattern and the overall trend in the long-term variation pattern. For example, there may be some local fluctuations in the short-term variation pattern, but the long-term variation pattern shows an overall upward or downward trend; these information will be combined during fusion. Through this fusion, a comprehensive variation pattern of the waveform characteristics can be obtained, reflecting how the waveform characteristics evolve throughout the monitoring period, such as whether it gradually stabilizes, changes gradually, or exhibits complex fluctuations.

[0071] Step S1324: The short-term and long-term change patterns of the rhythmic features are fused to obtain a comprehensive change pattern of the rhythmic features, which reflects the overall evolution of the rhythmic features over time.

[0072] For rhythmic features, their short-term and long-term variation patterns must also be fused. During the fusion process, the different manifestations of the frequency and intensity of the rhythmic features in the short and long term will be considered. For example, there may be rapid fluctuations in frequency in the short term, but a slow downward trend in frequency in the long term; this information will be integrated during the fusion process. Therefore, the final comprehensive variation pattern of the rhythmic features can clearly show the overall evolution of the rhythmic features throughout the monitoring period, indicating whether they become more regular, more disordered, or exhibit other changes.

[0073] Step S1325: Integrate the comprehensive change pattern of the waveform features and the comprehensive change pattern of the rhythm features to generate overall trend change information of the neural functional state features. The overall trend change information is used to describe the continuous change process of the neural functional state over the monitoring time.

[0074] Finally, the combined change patterns of waveform and rhythm features are integrated, taking into account their temporal synchronicity and interrelationship. For example, waveform and rhythm features may change simultaneously at certain time intervals, or a change in one feature may trigger a change in the other. By integrating these two combined change patterns, overall trend information on the neural functional state features is generated. This overall trend information can comprehensively and in detail describe how the neural functional state changes continuously throughout the monitoring period.

[0075] Step S133: Compare the trend change information with a preset neural function safety reference range, which includes the waveform feature range and rhythm feature range under normal physiological conditions, and identify the feature change interval that exceeds the neural function safety reference range.

[0076] After obtaining information on the overall trend changes in neural function characteristics, it is necessary to compare it with the preset neural function safety reference range. The neural function safety reference range is obtained based on the analysis of a large number of neurophysiological signals under normal physiological conditions, and it includes the waveform characteristic range and rhythm characteristic range under normal conditions.

[0077] In cerebral aneurysm clipping surgery, the waveform and rhythm characteristics in the overall trend information are compared with their corresponding safety reference ranges. For waveform characteristics, it is checked whether the trend of change is within the normal waveform characteristic range, such as whether the waveform amplitude and frequency are within a reasonable range. For rhythm characteristics, it is checked whether the frequency, amplitude, phase, and other characteristics are within the normal rhythm characteristic range.

[0078] If waveform or rhythmic characteristics within a certain time interval are found to exceed the safe reference range, that time interval is considered a characteristic change interval. Through the above comparison and identification, potential abnormalities in neurological function can be detected promptly. For example, if during surgery, a sudden increase in waveform amplitude exceeding the normal range is observed, or a significant change in rhythmic frequency occurs outside the normal range, it can be determined that neurological function may have been affected during that time period, requiring further monitoring and analysis.

[0079] Step S134: Continuously verify the feature change interval, determine whether the waveform features and rhythm features within the feature change interval continuously exceed the neural function safety reference range, and if they continuously exceed the range, determine it as an abnormal fluctuation interval, and generate abnormal fluctuation information based on the abnormal fluctuation interval.

[0080] After identifying the characteristic variation intervals, continuous verification of these intervals is necessary to avoid misjudgment. In the context of cerebral aneurysm clipping surgery, characteristic variation intervals may appear due to transient interference or accidental factors, but these changes do not necessarily indicate a true abnormality in neurological function. Therefore, it is necessary to determine whether the waveform and rhythmic characteristics within the characteristic variation intervals consistently exceed the safe reference range for neurological function.

[0081] The specific operation involves setting a time threshold. If the waveform and rhythm characteristics within the characteristic change interval consistently exceed the safe reference range within this time threshold, then the characteristic change interval is determined to be an abnormal fluctuation interval. For example, if the time threshold is specified as a specific duration, and within this duration, the amplitude of the waveform characteristics is consistently higher than the normal range, and the frequency of the rhythm characteristics consistently deviates from the normal range, then this time period can be considered an abnormal fluctuation interval.

[0082] After determining the abnormal fluctuation range, abnormal fluctuation information can be generated based on this range. This information can include the start and end times of the abnormal fluctuation, the type of abnormal fluctuation (such as abnormal waveform characteristics, abnormal rhythm characteristics, etc.), and the degree of the abnormal fluctuation. This abnormal fluctuation information can accurately describe the abnormalities occurring in the neurological functional state.

[0083] Step S135: Integrate the trend change information and the abnormal fluctuation information to generate intraoperative neurological function monitoring results that include functional stability information and abnormal fluctuation information. The functional stability information is used to describe the overall stability of the neurological function state, and the abnormal fluctuation information is used to mark the abnormal change range of the neurological function state.

[0084] After completing the continuous verification of characteristic change ranges and generating abnormal fluctuation information, it is necessary to integrate trend change information and abnormal fluctuation information to generate intraoperative neurological function monitoring results. In cerebral aneurysm clipping surgery, functional stability information can be determined by analyzing trend change information. If the trend change information shows that the waveform and rhythm characteristics fluctuate within the normal range for most of the time and the change trend is relatively stable, then the overall stability of the neurological function can be considered high; conversely, if the trend change information shows that the characteristic changes are relatively drastic and frequently exceed the normal range, then the overall stability of the neurological function is low.

[0085] Abnormal fluctuation information is identified by marking abnormal changes in neurological function. Integrating this abnormal fluctuation information with functional stability information forms a complete intraoperative neurological function monitoring result. This result reflects both the overall stability of neurological function and clearly identifies the time periods and types of abnormalities. For example, the monitoring result may clearly show that neurological function is relatively stable at one stage of the surgery, while abnormal fluctuations occur at another stage, and the specific details of these fluctuations, such as their onset time, duration, and type, can be identified. Therefore, the surgical team can promptly understand changes in neurological function based on the intraoperative neurological function monitoring results and take appropriate measures to ensure the safety of the surgery.

[0086] Step S140: Transmit the intraoperative neurological function monitoring results to a remote monitoring terminal, which is used to dynamically display the functional stability information and abnormal fluctuation information.

[0087] After generating intraoperative neurological function monitoring results, these results need to be transmitted to a remote monitoring terminal so that the surgical team can have a real-time and intuitive understanding of the neurological function status. The remote monitoring terminal is typically located in the operating room or other relevant monitoring locations for easy access by the surgical team.

[0088] In cerebral aneurysm clipping surgery, intraoperative neurological function monitoring results are transmitted from a remote analysis system to a remote monitoring terminal via a high-speed and stable network. Upon receiving the intraoperative neurological function monitoring results, the remote monitoring terminal can analyze and process them to dynamically display information on functional stability and abnormal fluctuations.

[0089] Step S141: The remote monitoring terminal receives the intraoperative neurological function monitoring results and analyzes the functional stability information and abnormal fluctuation information in the intraoperative neurological function monitoring results.

[0090] After receiving the intraoperative neurological function monitoring results, the remote monitoring terminal first parses them. The monitoring results are usually transmitted in a set data format, and the remote monitoring terminal needs to decode and analyze them according to the corresponding protocols and rules.

[0091] For functional stability information, descriptions and related data regarding the overall stability of neural function can be extracted, such as stability scores and stable time periods. For abnormal fluctuation information, key information such as the start time, end time, and type of abnormal fluctuations can be extracted. Through analysis, functional stability information and abnormal fluctuation information are separated from the monitoring results.

[0092] Step S142: Generate a dynamic trend graph of functional stability based on the functional stability information. The dynamic trend graph of functional stability plots the stability change curve of neural functional state in real time with the monitoring time as the horizontal axis and the degree of functional stability as the vertical axis.

[0093] After parsing the functional stability information, the remote monitoring terminal generates a dynamic trend chart of functional stability based on this information. A coordinate system is established with monitoring time on the horizontal axis and the degree of functional stability on the vertical axis. The degree of functional stability can be represented by a quantifiable indicator, such as a stability score.

[0094] During cerebral aneurysm clipping surgery, the remote monitoring terminal updates data on functional stability in real time as monitoring progresses, plotting corresponding points on a coordinate system. These points are then connected to form a stability change curve. This curve visually displays the stability changes of neurological function throughout the surgical process. For example, a relatively smooth curve indicates that neurological function is stable for most of the time; large fluctuations suggest that neurological function may have been affected by surgical procedures or other factors, leading to instability. By observing this dynamic trend graph, the surgical team can promptly identify changes in neurological stability and take appropriate measures.

[0095] Step S143: Based on the abnormal fluctuation information, mark the abnormality on the functional stability dynamic trend chart, and add a visual identifier at the time axis position of the abnormal change interval corresponding to the abnormal fluctuation information. The visual identifier is used to distinguish different types of abnormal fluctuations.

[0096] After generating the dynamic trend map of functional stability, in order for the surgical team to more intuitively identify abnormal fluctuations in the neurological functional state, it is necessary to mark abnormalities based on the abnormal fluctuation information.

[0097] Step S1431: Analyze the abnormal fluctuation type in the abnormal fluctuation information and determine the visual identifier style corresponding to each abnormal fluctuation type. The visual identifier style includes color, shape and fill pattern.

[0098] During cerebral aneurysm clipping surgery, the remote monitoring terminal receives abnormal fluctuation information and first analyzes it. This abnormal fluctuation information includes different types of abnormal fluctuations, such as waveform feature abnormalities and rhythm feature abnormalities. For each type of abnormal fluctuation, a corresponding visual identifier style needs to be determined. In terms of color, waveform feature abnormalities can be set to red, as red usually indicates danger and abnormality, attracting the surgical team's attention; rhythm feature abnormalities can be set to blue, as blue is relatively milder and represents a different type of abnormality. In terms of shape, waveform feature abnormalities can be represented by rectangles, which give a sense of regularity and clarity; rhythm feature abnormalities can be represented by triangles, which have a certain uniqueness. The filling pattern can also differ; for example, rectangles for waveform feature abnormalities can be filled solidly, while triangles for rhythm feature abnormalities can be filled hollowly. Through these settings, the surgical team can quickly distinguish different types of abnormal fluctuations using the visual identifier style.

[0099] Step S1432: Locate the start and end time points of the abnormal change interval corresponding to the abnormal fluctuation information on the time axis of the functional stability dynamic trend graph, and determine the time range of the abnormal marker.

[0100] After determining the visual identifier style, it is necessary to accurately locate the abnormal change intervals corresponding to the abnormal fluctuation information on the time axis of the functional stability dynamic trend graph. This is done by analyzing the start and end times of the abnormal fluctuation information and precisely marking these points on the time axis. For example, if the abnormal fluctuation starts at a specific moment after the surgery begins and ends at another moment, the corresponding positions on the time axis will be found. Once these two positions are determined, the time range for anomaly marking is clarified, that is, the time period from the start time point to the end time point.

[0101] Step S1433: Based on the time range of the anomaly marker and the style of the visual identifier, draw the visual identifier at the corresponding time axis position of the functional stability dynamic trend chart. The length of the visual identifier is proportional to the duration of the anomaly change interval.

[0102] Based on the determined time range of the anomaly markers and the style of the visual identifiers, visual identifiers are plotted at the corresponding time axis positions on the functional stability dynamic trend graph. The length of the visual identifiers is adjusted according to the duration of the anomaly range; the longer the duration, the longer the visual identifier. For example, if an anomaly lasts for a long time, the corresponding visual identifier (such as a rectangle or triangle) will be longer on the time axis. This allows the surgical team to intuitively understand the duration of the anomaly from the length of the visual identifiers. Accurate plotting ensures that the visual identifiers are clearly displayed on the functional stability dynamic trend graph, facilitating observation by the surgical team.

[0103] Step S1434: Perform hierarchical processing on the visual identifiers corresponding to the overlapping abnormal change intervals, determine the display level of the visual identifiers according to the priority of the abnormal fluctuation type, and display the visual identifiers with higher priority at the top.

[0104] In practice, overlapping abnormal fluctuation ranges may occur, meaning different types of abnormal fluctuations may appear within the same time period. In such cases, it's necessary to hierarchically process the visual identifiers corresponding to the overlapping abnormal fluctuation ranges. First, priorities are determined based on the importance of the abnormal fluctuation type and its impact on neurological function. For example, waveform feature abnormalities may have a more direct and severe impact on neurological function, so their priority might be higher than rhythm feature abnormalities. Following this priority order, higher-priority visual identifiers are displayed at the top. This way, when the surgical team reviews the functional stability dynamic trend chart, they can see the higher-priority abnormal fluctuations first, allowing them to focus on and address abnormalities with a greater impact on neurological function.

[0105] Step S1435: Add an interactive prompt function to the visual identifier. When the surgeon clicks or hovers over the visual identifier, the detailed information of the abnormal fluctuation is displayed. The detailed information includes the abnormal start time, the abnormal duration, and the abnormal fluctuation type.

[0106] To enable the surgical team to gain a deeper understanding of anomalous fluctuations, interactive prompts will be added to the visual identifiers. When the surgeon clicks or hovers over the visual identifier, a pop-up window will display detailed information about the anomalous fluctuation. This information includes the onset time of the anomaly, letting the surgical team know when the anomaly began; the duration of the anomaly, indicating how long it has lasted; and the type of anomalous fluctuation, specifying whether it is an abnormal waveform or a rhythmic feature. Through this interactive prompt feature, the surgical team can obtain detailed information about the anomalous fluctuations when needed.

[0107] Step S144: Extract the waveform features and rhythm features corresponding to the abnormal fluctuation range from the intraoperative neurological function monitoring results, and display the waveform features and rhythm features in the associated area of ​​the functional stability dynamic trend map in the form of a waveform diagram to realize the linkage display of abnormal fluctuations and corresponding waveform and rhythm features.

[0108] After marking the abnormalities, in order to give the surgical team a more comprehensive understanding of the abnormal fluctuations, it is necessary to extract the waveform and rhythm features corresponding to the abnormal fluctuation ranges from the intraoperative neurological function monitoring results and display them in the relevant area of ​​the functional stability dynamic trend map in the form of waveform graphs.

[0109] In cerebral aneurysm clipping surgery, for each abnormal fluctuation range, the corresponding waveform and rhythm characteristics within that range are identified from the monitoring results. These data are then processed and transformed to generate corresponding waveform diagrams. These waveform diagrams can visually display the waveform and rhythm changes of neurophysiological signals within the abnormal fluctuation range.

[0110] The generated waveform is displayed in the relevant area of ​​the functional stability dynamic trend chart, such as next to or below the visual identifier of the abnormality. Thus, when the surgical team views the functional stability dynamic trend chart, they can simultaneously observe the specific waveform and rhythmic characteristics corresponding to the abnormal fluctuations, achieving a linked display of abnormal fluctuations and their corresponding waveforms and rhythmic features. Through this linked display, the surgical team can analyze the causes and effects of abnormal fluctuations in greater depth.

[0111] Step S145: The remote monitoring terminal updates the dynamic trend graph of functional stability and the associated waveform graph in real time to ensure that the displayed content is synchronized with the latest intraoperative neurological function monitoring results.

[0112] During surgery, neurological function changes continuously, and intraoperative neurological function monitoring results are updated in real time. To ensure the timeliness and accuracy of the information displayed on the remote monitoring terminal, it is necessary to update the dynamic trend chart of functional stability and the associated waveform diagrams in real time.

[0113] The remote monitoring terminal periodically retrieves the latest intraoperative neurological function monitoring results from the remote analysis system. Upon receiving new results, it can re-analyze the functional stability and abnormal fluctuation information. For the functional stability dynamic trend graph, the stability change curve can be updated based on the new functional stability data. For the associated waveform graphs, if new abnormal fluctuation ranges appear or the characteristics of the original abnormal fluctuation ranges change, the corresponding waveform graphs can be regenerated and displayed.

[0114] By updating in real time, the content displayed on the remote monitoring terminal is kept synchronized with the latest intraoperative neurological function monitoring results. This allows the surgical team to obtain the latest information on neurological function status at any time, enabling timely decisions and adjustments, and ensuring the safety and success of the surgery.

[0115] Step S150: Trigger an intraoperative intervention prompt based on the abnormal fluctuation information in the intraoperative neurological function monitoring results. The intraoperative intervention prompt is used to assist the surgeon in adjusting the surgical procedure.

[0116] After displaying the intraoperative neurological function monitoring results and marking abnormal fluctuation information on the remote monitoring terminal, it is necessary to trigger intraoperative intervention prompts based on the abnormal fluctuation information in order to respond promptly to abnormal changes in neurological function status.

[0117] Step S151: Analyze the abnormal fluctuation information, extract the abnormal start time, abnormal duration and abnormal fluctuation type from the abnormal fluctuation information, and the abnormal fluctuation type is determined based on the abnormal pattern of waveform features and rhythm features.

[0118] During cerebral aneurysm clipping surgery, the remote monitoring terminal receives abnormal fluctuation information and first analyzes it. This abnormal fluctuation information typically includes key information such as the onset time, duration, and type of abnormal fluctuation. The type of abnormal fluctuation is determined based on abnormal patterns in waveform and rhythm characteristics. For example, if waveform characteristics exhibit abnormal patterns such as a sudden increase in amplitude or a change in frequency, or if rhythm characteristics show abnormal changes in frequency, amplitude, or phase, the corresponding abnormal fluctuation type can be determined based on these abnormal patterns, such as abnormal waveform characteristics or abnormal rhythm characteristics.

[0119] Step S152: Assess the severity of the abnormal fluctuation based on the abnormal duration and the type of abnormal fluctuation, the severity being determined based on the length of the abnormal duration and the potential impact of the abnormal pattern on neural function.

[0120] After extracting key information from the abnormal fluctuations, the severity of the abnormal fluctuations needs to be assessed based on their duration and type. The duration of the abnormal fluctuation is a crucial factor in assessing severity. Generally, the longer the abnormal fluctuation lasts, the longer the neurological function is affected, and the greater the potential harm.

[0121] The type of abnormal fluctuation also affects the assessment of severity. Different types of abnormal fluctuations have different potential impacts on neurological function. For example, abnormal waveform characteristics may affect the transmission and processing of neural signals, while abnormal rhythm characteristics may affect the synchronicity and coordination of nerves. Based on the degree of potential impact of the abnormal pattern on neurological function, abnormal fluctuation types can be classified into different levels, such as mild, moderate, and severe abnormalities.

[0122] The severity of an anomaly is determined by comprehensively considering both its duration and type. For example, if the anomaly lasts for a long time and is classified as a severe anomaly, its severity is considered high; conversely, if the anomaly lasts for a short time and is classified as a mild anomaly, its severity is relatively low.

[0123] Step S153: Based on the severity, match the corresponding intervention prompt rule from the preset intervention rule base. The intervention prompt rule includes the prompt method and the prompt content. The prompt method is positively correlated with the severity.

[0124] After assessing the severity of the abnormal fluctuations, corresponding intervention prompt rules need to be matched from a pre-built intervention rule base. This rule base contains intervention prompt rules corresponding to different levels of severity.

[0125] Intervention prompting rules include the prompting method and the prompting content. The prompting method is positively correlated with the severity; that is, the higher the severity, the more obvious and intense the prompting method. For example, for mild anomalies, the prompting method might be a slight flashing on the display interface of the remote monitoring terminal; for moderate anomalies, the prompting method might be a large pop-up prompt window on the display interface, accompanied by a slight prompting sound; for severe anomalies, the prompting method might be a prominent red pop-up prompt window on the display interface, accompanied by a strong prompting sound.

[0126] The message is customized based on the type and severity of the abnormal fluctuation, and may include a brief description of the abnormality, possible cause analysis, and preliminary suggestions. For example, for a mild abnormality in waveform characteristics, the message might be "A slight abnormality in waveform characteristics has been detected, which may be a temporary effect of the surgical procedure. Please monitor closely." For a severe abnormality in rhythm characteristics, the message might be "A serious abnormality in rhythm characteristics has occurred, which may affect neurological function. It is recommended to adjust the surgical procedure immediately."

[0127] By matching the corresponding intervention prompt rules from the intervention rule base, it is possible to ensure that appropriate prompts and prompts are provided according to the severity of abnormal fluctuations, and to promptly remind the surgical team to pay attention to abnormal changes in neurological function.

[0128] Step S154: Trigger the multimodal prompting operation of the remote monitoring terminal based on the prompting method. The multimodal prompting operation includes visual prompting operation and auditory prompting operation. The visual prompting operation generates an abnormal prompting window on the display interface, and the auditory prompting operation plays a prompting sound through the audio output module.

[0129] After matching the corresponding intervention prompt rule, the remote monitoring terminal is triggered with multimodal prompts based on the prompt method. These multimodal prompts include visual and auditory prompts, simultaneously alerting the surgical team through multiple methods.

[0130] For visual cues, an anomaly alert window is generated on the remote monitoring terminal's display interface according to the required cues method. The size, color, and content of the alert window are adjusted based on the severity of the anomaly. For example, for mild anomalies, the alert window can be smaller and lighter in color; for severe anomalies, the alert window will be larger and a bright red. The alert window will display the alert content, allowing the surgical team to intuitively understand the anomaly and receive recommendations.

[0131] For auditory prompts, a prompt tone is played via the audio output module of the remote monitoring terminal. The intensity and frequency of the prompt tone are adjusted according to the severity of the anomaly. For example, for a mild anomaly, the prompt tone may be a soft ticking sound; for a severe anomaly, the prompt tone may be a loud alarm.

[0132] Multimodal prompts ensure that the surgical team receives timely alerts about abnormal fluctuations under any circumstances, increasing their awareness of abnormal changes in neurological function.

[0133] Step S155: Generate surgical operation adjustment suggestions based on the prompt content and abnormal fluctuation type. The surgical operation adjustment suggestions include surgical operation steps and adjustment directions related to the abnormal fluctuation type. The adjustment direction is determined based on the changing trend of the abnormal fluctuation.

[0134] After triggering a multimodal prompt, in order to help the surgeon adjust the surgical procedure in a timely manner to cope with abnormal fluctuations in neurological function, it is necessary to generate surgical procedure adjustment suggestions based on the prompt content and the type of abnormal fluctuation.

[0135] Step S1551: Analyze the prompt content and extract the neurofunctional influencing factors related to the abnormal fluctuation type. The neurofunctional influencing factors include the mechanical and electrical stimulation of nerve tissue by the surgical operation.

[0136] In cerebral aneurysm clipping surgery, the prompts displayed on the remote monitoring terminal contain important information related to the type of abnormal fluctuations. By analyzing these prompts, neurological function influencing factors related to the type of abnormal fluctuations can be extracted. For example, if the abnormal fluctuation type is characterized by waveform abnormalities, the prompt might mention that it is caused by excessive mechanical stimulation of the nerve tissue by the surgical instruments; if it is characterized by rhythm abnormalities, it may be that electrical stimulation during the surgical procedure interfered with the normal rhythm of the nerve. This clarifies the specific factors affecting neurological function.

[0137] Step S1552: Based on the neurofunctional influencing factors, query the corresponding surgical operation steps from the preset operation step association library. The surgical operation steps include instrument operation area, operation force control, and operation speed adjustment.

[0138] The pre-built surgical procedure association database is a pre-established database that records surgical procedure steps corresponding to different factors influencing neurological function. Once the influencing factor is identified, the corresponding surgical procedure steps can be retrieved from the database based on this factor. For example, if the influencing factor is mechanical stimulation, the database will show that the corresponding surgical procedure steps may include instrument operation area, control of operating force, and adjustment of operating speed. The instrument operation area may need adjustment to avoid the instrument getting too close to or compressing the nerve tissue; regarding operating force control, the force may need to be reduced to lessen mechanical stimulation of the nerve; regarding operating speed adjustment, the operating speed may need to be reduced to allow sufficient recovery time for the nerve tissue. By querying the surgical procedure association database, the specific surgical procedure steps that may need adjustment are identified.

[0139] Step S1553: Analyze the changing trend in the abnormal fluctuation information to determine whether the abnormal fluctuation is an aggravating trend or a decelerating trend. The aggravating trend indicates that the degree of abnormality increases over time, and the decelerating trend indicates that the degree of abnormality decreases over time.

[0140] After determining the surgical procedure, it's necessary to analyze the trends in abnormal fluctuation information. By comparing and analyzing abnormal data at different time points, it's possible to determine whether the abnormal fluctuations are intensifying or decreasing. For example, if the amplitude and frequency of abnormal fluctuations continuously increase over several consecutive time points, it indicates an intensifying trend; conversely, if these indicators gradually decrease, it indicates a decreasing trend. Clearly identifying the trend of abnormal fluctuations is crucial for determining the direction of adjustments.

[0141] Step S1554: Determine the adjustment direction based on the surgical operation steps and the changing trend of abnormal fluctuations. If the abnormal fluctuations show an aggravating trend, the adjustment direction is to reduce the stimulation intensity on the nerve tissue. If the abnormal fluctuations show a slowing trend, the adjustment direction is to maintain the current operation or moderately adjust the stimulation intensity.

[0142] The direction of adjustment is determined based on the surgical procedure and the trend of abnormal fluctuations. If the abnormal fluctuations are intensifying, it indicates that the current surgical procedure is stimulating the nerve tissue excessively, and measures need to be taken to reduce the intensity of stimulation. For example, for the instrument operation area, the instrument can be moved further away from the nerve tissue; for the control of the operating force, the operating force can be further reduced; for the adjustment of the operating speed, the operating speed can be reduced. If the abnormal fluctuations are slowing down, it indicates that the current operation may be effective, and the current operation can be maintained, or the intensity of stimulation can be adjusted appropriately as needed, such as fine-tuning the operating force or speed, to ensure that nerve function can continue to recover steadily.

[0143] Step S1555: Combine the surgical operation steps and corresponding adjustment directions into surgical operation adjustment suggestions. The surgical operation adjustment suggestions are displayed in the prompt window of the remote monitoring terminal in the form of text descriptions to assist the surgeon in adjusting the surgical operation.

[0144] Finally, the surgical procedure steps and their corresponding adjustment directions are combined into surgical procedure adjustment suggestions. For example, each surgical procedure step (such as instrument operation area, control of operating force, and adjustment of operating speed) and its corresponding adjustment direction (such as reducing stimulation intensity, maintaining or moderately adjusting stimulation intensity) are described clearly and explicitly in text. For example, "The current waveform characteristics are abnormally aggravated; it is recommended to adjust the instrument operation area away from the nerve tissue, while reducing the operating force and decreasing the operating speed." The surgical procedure adjustment suggestions are displayed in text description form in the prompt window of the remote monitoring terminal. The surgeon can directly see the specific adjustment suggestions in the prompt window and adjust the surgical procedure in a timely manner according to these suggestions to ensure the patient's neurological function safety.

[0145] Figure 2 Schematic diagrams are shown of exemplary hardware and software components of a remote intraoperative neurophysiological monitoring system 100 that can implement the ideas of this application, according to some embodiments of this application. For example, a processor 120 may be used on the remote intraoperative neurophysiological monitoring system 100 and to perform the functions described in this application.

[0146] The remote intraoperative neurophysiological monitoring system 100 can be a general-purpose server or a special-purpose server, both of which can be used to implement the remote intraoperative neurophysiological monitoring method of this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the load.

[0147] For example, the remote intraoperative neurophysiological monitoring system 100 may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the remote intraoperative neurophysiological monitoring system 100 may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to these program instructions. The remote intraoperative neurophysiological monitoring system 100 also includes an I / O interface 150 between the computer and other input / output devices.

[0148] For ease of illustration, only one processor is described in the remote intraoperative neurophysiological monitoring system 100. However, it should be noted that the remote intraoperative neurophysiological monitoring system 100 of this application may also include multiple processors, and therefore the steps performed by one processor described in this application may also be performed jointly by multiple processors or individually. For example, if the processor of the remote intraoperative neurophysiological monitoring system 100 performs steps A and B, it should be understood that steps A and B may also be performed jointly by two different processors or individually by one processor. For example, the first processor performs step A, the second processor performs step B, or the first processor and the second processor jointly perform steps A and B.

[0149] Furthermore, this embodiment of the invention also provides a readable storage medium, wherein computer-executable instructions are preset in the readable storage medium, and when the processor executes the computer-executable instructions, the above-mentioned remote intraoperative neurophysiological monitoring method is implemented.

[0150] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A remote intraoperative neurophysiological monitoring system, characterized in that, The system includes a processor and a memory connected to each other. The memory stores programs, instructions, or code, and the processor executes the programs, instructions, or code stored in the memory to implement the following remote intraoperative neurophysiological monitoring method: The patient's neurophysiological signals were collected during the operation, and the neurophysiological signals included continuous neurophysiological waveform signals recorded synchronously through multiple monitoring leads. The neural electrophysiological signal set is subjected to feature extraction processing to obtain the neural functional state features of the neural electrophysiological waveform signals, wherein the neural functional state features include waveform features and rhythm features; The neurological function state characteristics are remotely analyzed and processed in real time to generate intraoperative neurological function monitoring results, which include functional stability information and abnormal fluctuation information. The intraoperative neurological function monitoring results are transmitted to a remote monitoring terminal, which is used to dynamically display the functional stability information and abnormal fluctuation information. Based on the abnormal fluctuation information in the intraoperative neurological function monitoring results, an intraoperative intervention prompt operation is triggered, which is used to assist the surgeon in adjusting the surgical procedure. The remote real-time analysis and processing of the neurological functional state characteristics to generate intraoperative neurological function monitoring results includes: The neural functional state features are sent to a remote analysis system so that the remote analysis system can perform time series modeling on the neural functional state features and construct a dynamic model of the neural functional state features changing with monitoring time. The dynamic model is used to describe the continuous change process of waveform features and rhythm features. Based on the dynamic model, the changing trend of the neural functional state characteristics is analyzed, the changing patterns of the waveform characteristics and the changing patterns of the rhythm characteristics are extracted, and the overall trend information of the neural functional state characteristics is obtained. The trend change information is compared with a preset neural function safety reference range, which includes the waveform feature range and rhythm feature range under normal physiological conditions, and the feature change intervals that exceed the neural function safety reference range are identified. The feature change interval is continuously verified to determine whether the waveform features and rhythm features within the feature change interval continuously exceed the neural function safety reference range. If they continuously exceed the range, they are identified as abnormal fluctuation intervals, and abnormal fluctuation information is generated based on the abnormal fluctuation intervals. By integrating the trend change information and the abnormal fluctuation information, an intraoperative neurological function monitoring result containing functional stability information and abnormal fluctuation information is generated. The functional stability information is used to describe the overall stability of the neurological function state, and the abnormal fluctuation information is used to mark the abnormal change range of the neurological function state. The process involves analyzing the changing trends of the neural functional state characteristics based on the dynamic model, extracting the changing patterns of the waveform features and the changing patterns of the rhythm features, and obtaining overall trend information on the neural functional state characteristics, including: Based on the waveform feature time series output by the dynamic model, the amplitude and direction of change of the waveform features within the continuous monitoring time are analyzed to determine the short-term and long-term change patterns of the waveform features. Based on the time series of rhythmic features output by the dynamic model, the frequency and intensity changes of the rhythmic features during continuous monitoring are analyzed to determine the short-term and long-term change patterns of the rhythmic features. By fusing the short-term and long-term change patterns of the waveform features, a comprehensive change pattern of the waveform features is obtained, which reflects the overall evolution law of the waveform features over time. By fusing the short-term and long-term change patterns of the rhythmic features, a comprehensive change pattern of the rhythmic features is obtained, which reflects the overall evolution of the rhythmic features over time. By integrating the comprehensive change patterns of the waveform features and the comprehensive change patterns of the rhythm features, overall trend change information of the neural functional state features is generated. This overall trend change information is used to describe the continuous change process of the neural functional state over the monitoring time. The intraoperative intervention prompt operation triggered based on abnormal fluctuation information in the intraoperative neurological function monitoring results includes: The abnormal fluctuation information is analyzed to extract the abnormal start time, abnormal duration, and abnormal fluctuation type. The abnormal fluctuation type is determined based on the abnormal pattern of waveform features and rhythm features. The severity of the abnormal fluctuations is assessed based on the duration and type of the abnormal fluctuations, the severity of which is determined based on the duration of the abnormal fluctuations and the potential impact of the abnormal patterns on neural function. Based on the severity, a corresponding intervention prompt rule is matched from a preset intervention rule base. The intervention prompt rule includes a prompt method and a prompt content, and the prompt method is positively correlated with the severity. The remote monitoring terminal is triggered to perform a multimodal prompting operation based on the aforementioned prompting method. The multimodal prompting operation includes a visual prompting operation and an auditory prompting operation. The visual prompting operation generates an abnormal prompting window on the display interface, and the auditory prompting operation plays a prompting sound through the audio output module. Based on the prompts and the type of abnormal fluctuations, surgical operation adjustment suggestions are generated. The surgical operation adjustment suggestions include surgical operation steps and adjustment directions related to the type of abnormal fluctuations. The adjustment direction is determined based on the changing trend of the abnormal fluctuations. The process of generating surgical operation adjustment suggestions based on the prompt content and abnormal fluctuation type includes: The prompt content was analyzed, and the neurofunctional influencing factors related to the abnormal fluctuation type were extracted. These neurofunctional influencing factors include the mechanical and electrical stimulation of nerve tissue by the surgical operation. Based on the neurofunctional influencing factors, the corresponding surgical operation steps are queried from the preset operation step association library. The surgical operation steps include instrument operation area, operation force control and operation speed adjustment. Analyze the changing trends in the abnormal fluctuation information to determine whether the abnormal fluctuations are intensifying or slowing down. An intensifying trend indicates that the degree of abnormality is increasing over time, while a slowing down trend indicates that the degree of abnormality is decreasing over time. The adjustment direction is determined based on the surgical procedure and the changing trend of abnormal fluctuations. If the abnormal fluctuations are intensifying, the adjustment direction is to reduce the stimulation intensity on the nerve tissue. If the abnormal fluctuations are slowing down, the adjustment direction is to maintain the current operation or moderately adjust the stimulation intensity. The surgical procedure steps and corresponding adjustment directions are combined into surgical procedure adjustment suggestions, which are displayed in the prompt window of the remote monitoring terminal in the form of text descriptions to assist the surgeon in adjusting the surgical procedure.

2. The remote intraoperative neurophysiological monitoring system according to claim 1, characterized in that, The step of performing feature extraction processing on the set of neurophysiological signals to obtain the neurofunctional state features of the neurophysiological waveform signals includes: The continuous electrophysiological waveform signals in the set of neurophysiological signals are preprocessed to obtain interference-free electrophysiological waveform signals. The interference-free electrophysiological waveform signal is segmented into time dimensions. The interference-free electrophysiological waveform signal is divided into multiple continuous waveform time segments according to a preset time interval. Each waveform time segment has a continuous time sequence relationship. Waveform features are extracted for each waveform time segment to identify the characteristic waveform morphology in the waveform time segment. The characteristic waveform morphology includes the waveform fluctuation pattern and the connection relationship between waveforms. Based on the characteristic waveform morphology, the waveform features of each waveform time segment are obtained. The rhythm features of the interference-free electrophysiological waveform signal are extracted, the repetitive change pattern of the interference-free electrophysiological waveform signal in the continuous time interval is analyzed, the rhythm pattern with periodic occurrence is identified, and the rhythm features of the interference-free electrophysiological waveform signal are obtained based on the rhythm pattern. The waveform features and rhythm features are correlated on a time axis to establish a correspondence between waveform features and rhythm features within the same time interval, generating a set of correlated features containing time markers; The neural functional state features of the neurophysiological waveform signals are obtained by integrating the associated feature set. The neural functional state features include combinations of waveform features and rhythm features corresponding to different time intervals.

3. The remote intraoperative neurophysiological monitoring system according to claim 2, characterized in that, The step of preprocessing the continuous electrophysiological waveform signals in the set of neurophysiological signals to obtain interference-free electrophysiological waveform signals includes: The continuous electrophysiological waveform signal is subjected to power frequency interference suppression processing. The fixed frequency interference component in the continuous electrophysiological waveform signal is filtered out by notch filtering, while retaining the effective frequency component of the neurophysiological signal. The continuous electrophysiological waveform signal is subjected to baseline drift correction processing, and the slow baseline fluctuations in the continuous electrophysiological waveform signal are eliminated by the moving average filtering method, so that the waveform baseline is kept at a preset stable level. The continuous electrophysiological waveform signal is subjected to electromyographic interference removal processing. An adaptive filtering algorithm is used to identify and suppress high-frequency electromyographic interference pulses in the continuous electrophysiological waveform signal while retaining low-frequency neurophysiological signal components. Electrode noise filtering is performed on the continuous electrophysiological waveform signal, and sudden electrode noise spikes in the continuous electrophysiological waveform signal are identified and removed by a threshold judgment method. By integrating the preprocessed signals described above, a de-interference electrophysiological waveform signal is obtained, which removes physiological and environmental interferences. The de-interference electrophysiological waveform signal retains the original characteristics of neurophysiological activity.

4. The remote intraoperative neurophysiological monitoring system according to claim 2, characterized in that, The step of extracting waveform features for each waveform time segment and identifying characteristic waveform morphologies within the waveform time segment includes: For each waveform time segment, waveform morphology recognition is performed. The waveform time segment is compared with a preset standard neurophysiological waveform template using a template matching method to identify characteristic waveforms in the waveform time segment that conform to the standard template. Extract the fluctuation pattern of the characteristic waveform, analyze the rising and falling trends of the characteristic waveform, and determine the overall morphological characteristics of the characteristic waveform; Analyze the connection relationship between adjacent feature waveforms in the waveform time segment, identify the interval pattern and superposition pattern between feature waveforms, and determine the structural features of the waveform sequence; A waveform feature descriptor is constructed based on the overall morphological and structural features. The waveform feature descriptor includes the morphological parameters of the feature waveform and the structural parameters of the waveform sequence. The waveform feature descriptor is used as the waveform feature for each waveform time segment, and the waveform feature is used to characterize the waveform change characteristics of the neurophysiological signal within the time segment.

5. The remote intraoperative neurophysiological monitoring system according to claim 1, characterized in that, The transmission of the intraoperative neurological function monitoring results to a remote monitoring terminal, wherein the remote monitoring terminal is used to dynamically display the functional stability information and abnormal fluctuation information, includes: The remote monitoring terminal receives the intraoperative neurological function monitoring results and analyzes the functional stability information and abnormal fluctuation information in the intraoperative neurological function monitoring results. Based on the functional stability information, a dynamic trend graph of functional stability is generated. The dynamic trend graph of functional stability plots the stability change curve of the neural functional state in real time with the monitoring time as the horizontal axis and the degree of functional stability as the vertical axis. Based on the abnormal fluctuation information, anomalies are marked on the functional stability dynamic trend chart, and visual identifiers are added to the time axis positions of the abnormal change intervals corresponding to the abnormal fluctuation information. The visual identifiers are used to distinguish different types of abnormal fluctuations. The waveform and rhythm features corresponding to the abnormal fluctuation range are extracted from the intraoperative neurological function monitoring results. The waveform and rhythm features are displayed in the associated area of ​​the functional stability dynamic trend map in the form of waveform graphs, so as to realize the linkage display of abnormal fluctuations and corresponding waveform and rhythm features. The remote monitoring terminal updates the dynamic trend graph of functional stability and the associated waveform graph in real time to ensure that the displayed content is synchronized with the latest intraoperative neurological function monitoring results.

6. The remote intraoperative neurophysiological monitoring system according to claim 5, characterized in that, The step of marking anomalies on the functional stability dynamic trend chart based on the abnormal fluctuation information, and adding visual identifiers at the time axis positions of the abnormal change intervals corresponding to the abnormal fluctuation information, includes: The abnormal fluctuation type in the abnormal fluctuation information is analyzed, and the visual identifier style corresponding to each abnormal fluctuation type is determined. The visual identifier style includes color, shape and fill pattern. Locate the start and end time points of the abnormal change interval corresponding to the abnormal fluctuation information on the time axis of the functional stability dynamic trend graph, and determine the time range of the abnormal marker. Based on the time range of the anomaly marker and the style of the visual identifier, a visual identifier is drawn at the corresponding time axis position of the functional stability dynamic trend chart, and the length of the visual identifier is proportional to the duration of the anomaly change interval. The visual identifiers corresponding to overlapping abnormal change intervals are processed hierarchically. The display level of the visual identifiers is determined according to the priority of the abnormal fluctuation type, and the visual identifiers with higher priority are displayed at the top. An interactive prompt function is added to the visual identifier. When the surgeon clicks or hovers over the visual identifier, detailed information about the abnormal fluctuation is displayed, including the start time of the abnormality, the duration of the abnormality, and the type of abnormal fluctuation.

Images