Psychological health assessment method and system for urinary surgery patient
By obtaining medical information data of urology patients, dividing the cognitive stage of the disease, combining anxiety assessment, emotion analysis and physiological monitoring, using EEG signal data for mental health assessment, solving the problem that existing tools cannot be evaluated in a personalized manner, and improving the The accuracy and reliability of the assessment achieve a comprehensive assessment and early warning of the mental health status of urology patients.
Patent Information
- Application Number
- CN202410922281.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-10
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing mental health assessment tools for urology patients cannot be evaluated for personalized situations, and the evaluation accuracy and reliability are low, making it impossible to fully consider the patient's anxiety, mood and physiological status.
A mental health assessment system for urology patients was designed. By obtaining medical information data, dividing the cognitive stages of the disease, anxiety assessment, emotion analysis and physiological monitoring were carried out, and anxiety values, mood fluctuations and site correlation index were integrated with EEG signal data. , generate a mental health assessment value and make early warnings based on preset thresholds.
It improves the accuracy and reliability of mental health assessment, can detect anxiety early, comprehensively evaluate mental health status, and provide personalized assessment and early warning mechanisms.
Smart Images

Figure CN118983085A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of mental health assessment, and in particular to a method and system for assessing mental health of patients in urology surgery. Background Art
[0002] In the early days, researchers began to try to apply commonly used mental health assessment tools such as anxiety scales and depression scales to urology patients to assess their mental state. However, these general assessment tools do not take into account the specific mental health issues of urology, so there are certain limitations. With a deeper understanding of the mental health needs of urology patients, researchers began to develop more targeted assessment tools. Combining the characteristics and needs of urology patients, they designed a series of special mental health assessment questionnaires and scales to more comprehensively assess the patient's mental state, such as anxiety before and after surgery, body image cognition after surgery, changes in sexual function, etc. With the development of information technology, the mental health assessment methods of urology patients have also begun to be digitized. Now, some applications and online platforms provide convenient mental health assessment tools for urology patients. Patients can be assessed at any time through mobile phones or computers and obtain relevant mental health support and advice. However, the current traditional mental health assessment still uses standardized assessment tools, which cannot be assessed for each patient's individual situation, and often only focuses on a single aspect, such as anxiety or emotions, resulting in low accuracy and reliability of the assessment. Summary of the invention
[0003] Based on this, it is necessary to provide a method and system for evaluating the psychological health of urology patients to solve at least one of the above technical problems.
[0004] To achieve the above purpose, a urology patient mental health assessment system is provided, the method comprising the following steps:
[0005] Anxiety assessment module, used to obtain medical information data of urinary shell patients; conduct disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; conduct patient anxiety assessment based on the first cognitive stage to obtain the anxiety value of the patient in the first stage;
[0006] The emotion fluctuation analysis module is used to perform cognitive behavior analysis on the patient based on the second cognitive stage to generate patient cognitive behavior data; perform patient emotion analysis on the patient cognitive behavior data to obtain patient emotion data; perform emotion fluctuation recognition on the patient cognitive behavior data through the patient emotion data to generate the second stage patient emotion fluctuation data;
[0007] The part association module is used to monitor the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's electroencephalogram signal; perform part association on the patient's physiological monitoring data to generate the patient's part association data; use the patient's electroencephalogram signal to calculate the part association index influence on the patient's part association data to obtain the third stage patient part association influence index;
[0008] The mental health assessment module is used to integrate the patient's anxiety value in the first stage, the patient's emotional fluctuation data in the second stage, and the patient's body part correlation impact index in the third stage to generate patient stage psychological impact data; conduct patient mental health assessment on the patient's stage psychological impact data to generate a patient mental health assessment value; compare the patient's mental health assessment value with a preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is issued.
[0009] The present invention can better understand the patient's disease cognition level and psychological state by analyzing the patient's medical information data and dividing the cognitive stages. By evaluating the patient's anxiety in the first cognitive stage, the patient's anxiety can be detected early and the patient's anxiety level can be reduced, thereby improving the accuracy of the anxiety assessment. By comprehensively considering the patient's cognitive behavioral data, emotional data, and physiological monitoring data, the patient's mental health condition can be more comprehensively assessed. Comprehensively considering the patient's psychological impact data helps to improve the accuracy of the patient's mental health assessment. Therefore, the present invention improves the accuracy and reliability of the assessment by performing detailed and personalized physiological and psychological comprehensive assessments based on different patient cognitive processes and combining patient physiological information monitoring and EEG signals.
[0010] In this specification, a method for evaluating the psychological health of patients in urology surgery is provided, which is used to implement the above-mentioned system for evaluating the psychological health of patients in urology surgery. The method for evaluating the psychological health of patients in urology surgery includes:
[0011] Step S1: Acquire medical information data of urinary shell patients; perform disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; perform patient anxiety assessment based on the first cognitive stage to obtain the first stage patient anxiety value;
[0012] Step S2: Based on the second cognitive stage, cognitive behavior analysis is performed on the patient to generate patient cognitive behavior data; patient emotion analysis is performed on the patient cognitive behavior data to obtain patient emotion data; emotion fluctuation recognition is performed on the patient cognitive behavior data through the patient emotion data to generate second stage patient emotion fluctuation data;
[0013] Step S3: monitoring the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's electroencephalogram signal; performing part association on the patient's physiological monitoring data to generate patient part association data; using the patient's electroencephalogram signal to calculate the part association index influence on the patient's part association data to obtain the third stage patient part association influence index;
[0014] Step S4: Integrate the anxiety value of the patient in the first stage, the emotional fluctuation data of the patient in the second stage, and the body part correlation impact index of the patient in the third stage to generate the patient's stage psychological impact data; conduct a patient mental health assessment on the patient's stage psychological impact data to generate a patient mental health assessment value; compare the patient's mental health assessment value with a preset standard psychological assessment threshold, and when the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, issue a corresponding mental health warning.
[0015] The beneficial effect of the present invention is that the medical information data of urology patients is obtained. Disease cognition data is generated by analyzing the medical information data. The cognitive data is divided into different cognitive stages to better understand the patient's cognitive level of the disease. Cognitive behavioral analysis is performed in the second cognitive stage to understand the patient's behavioral response and thinking process, and emotional analysis is performed on the cognitive behavioral data to understand the patient's emotional state. The patient's emotional fluctuations are identified through emotional data to help medical staff better understand the patient's emotional changes. Physiological monitoring is performed in the third cognitive stage to obtain the patient's physiological monitoring data and electroencephalogram signals. The physiological monitoring data is analyzed to determine the associated parts related to the disease, and the patient's part association impact index is calculated using the electroencephalogram signal to help evaluate the patient's part association impact degree. The data of different stages are integrated into the patient's stage psychological impact data. The patient's mental health assessment is performed based on the psychological impact data to obtain the patient's mental health assessment value. The assessment value is compared with the preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is performed. Therefore, the present invention improves the accuracy and reliability of the assessment by performing detailed and personalized physiological and psychological comprehensive assessments based on different patient cognitive processes and combining the patient's physiological information monitoring and electroencephalogram signals. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A schematic diagram of the module flow of a urology patient mental health assessment system;
[0017] Figure 2 for Figure 1 Schematic diagram of the functional flow of the emotion fluctuation analysis module;
[0018] Figure 3 for Figure 1Functional flow diagram of the middle position association module;
[0019] Figure 4 for Figure 3 A schematic diagram of the functional flow of performing part association on the patient's physiological monitoring data according to the overlapped spectrum diagram in the middle part association module and calculating the influence of the part association index on the patient's part association data using the patient's EEG signal;
[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0021] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.
[0022] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.
[0023] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0024] To achieve this, please refer to Figures 1 to 4 , a urology patient mental health assessment system, the system comprising:
[0025] Anxiety assessment module, used to obtain medical information data of urinary shell patients; conduct disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; conduct patient anxiety assessment based on the first cognitive stage to obtain the anxiety value of the patient in the first stage;
[0026] The emotion fluctuation analysis module is used to perform cognitive behavior analysis on the patient based on the second cognitive stage to generate patient cognitive behavior data; perform patient emotion analysis on the patient cognitive behavior data to obtain patient emotion data; perform emotion fluctuation recognition on the patient cognitive behavior data through the patient emotion data to generate the second stage patient emotion fluctuation data;
[0027] The part association module is used to monitor the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's electroencephalogram signal; perform part association on the patient's physiological monitoring data to generate the patient's part association data; use the patient's electroencephalogram signal to calculate the part association index influence on the patient's part association data to obtain the third stage patient part association influence index;
[0028] The mental health assessment module is used to integrate the patient's anxiety value in the first stage, the patient's emotional fluctuation data in the second stage, and the patient's body part correlation impact index in the third stage to generate patient stage psychological impact data; conduct patient mental health assessment on the patient's stage psychological impact data to generate a patient mental health assessment value; compare the patient's mental health assessment value with a preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is issued.
[0029] The present invention can better understand the patient's disease cognition level and psychological state by analyzing the patient's medical information data and dividing the cognitive stages. By evaluating the patient's anxiety in the first cognitive stage, the patient's anxiety can be detected early and the patient's anxiety level can be reduced, thereby improving the accuracy of the anxiety assessment. By comprehensively considering the patient's cognitive behavioral data, emotional data, and physiological monitoring data, the patient's mental health condition can be more comprehensively assessed. Comprehensively considering the patient's psychological impact data helps to improve the accuracy of the patient's mental health assessment. Therefore, the present invention improves the accuracy and reliability of the assessment by performing detailed and personalized physiological and psychological comprehensive assessments based on different patient cognitive processes and combining patient physiological information monitoring and EEG signals.
[0030] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the module flow of a urology patient psychological health assessment system of the present invention. In this example, the urology patient psychological health assessment system includes:
[0031] Anxiety assessment module, used to obtain medical information data of urinary shell patients; conduct disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; conduct patient anxiety assessment based on the first cognitive stage to obtain the anxiety value of the patient in the first stage;
[0032] The present invention collects medical information data of urology patients, including medical records, diagnostic reports, imaging examination results, etc., and data acquisition can be queried through hospital information systems and electronic medical record systems. Natural language processing (NLP) technology is used to perform text analysis on the patient's medical information to identify keywords, phrases and sentences related to urology diseases. Machine learning algorithms, such as text classification or clustering, are used to analyze and mine medical information to understand the patient's degree of cognition and attitude towards the disease. According to the analysis results, the patient's disease cognition is divided into different stages, such as the first cognitive stage (understanding the disease), the second cognitive stage (accepting the treatment plan), and the third cognitive stage (coping with and managing the disease). Expert knowledge can be used to divide the stages, or the patient's cognitive data can be automatically classified by a machine learning algorithm. For patients in the first cognitive stage, anxiety assessment tools (such as the Self-Assessment Anxiety Scale SAS) are used to conduct anxiety assessment. Through a questionnaire survey or an online assessment system, patients are asked to fill in the relevant anxiety assessment form to obtain the anxiety value of patients in the first stage.
[0033] The emotion fluctuation analysis module is used to perform cognitive behavior analysis on the patient based on the second cognitive stage to generate patient cognitive behavior data; perform patient emotion analysis on the patient cognitive behavior data to obtain patient emotion data; perform emotion fluctuation recognition on the patient cognitive behavior data through the patient emotion data to generate the second stage patient emotion fluctuation data;
[0034] In an embodiment of the present invention, based on the data of the second cognitive stage, which includes the patient's questionnaire answers, interview records, behavioral observation reports, etc., the data collection involves the communication records between the patient and the medical team, the implementation of the treatment plan, the patient's behavioral changes, etc. The text data is processed using natural language processing (NLP) technology to identify behavioral patterns and cognitive patterns. A text classification algorithm can be used to classify the data into different cognitive behavior categories, such as "active response", "indecision", "negative emotions", etc. Extract features related to cognitive behavior, such as the patient's attitude towards the disease, the patient's compliance with the doctor's advice, etc. This can be achieved by keyword extraction, sentiment dictionary analysis, etc. Using sentiment analysis technology, emotional information is extracted from the patient's cognitive behavior data. A pre-trained sentiment analysis model can be used to determine the emotional state in the text, such as "positive", "negative" or "neutral". Use a specific sentiment dictionary to match the words in the text and calculate the sentiment polarity and intensity. This can help identify the patient's emotional response in different situations. In order to intuitively understand the patient's emotional trend, emotional changes can be displayed using charts and other methods. Extract the characteristics of emotional fluctuations from the patient's emotional data, including the frequency and amplitude of emotional polarity changes, or the conversion speed of positive and negative emotions. Use time series analysis methods to monitor changes in emotions over time and identify patterns and trends in emotional fluctuations. ARIMA models, smoothing filters and other methods can be used to extract emotional fluctuation signals. Apply anomaly detection technology to identify abnormal points in emotional fluctuations, which reflect unstable or drastic changes in patients' emotions.
[0035] The part association module is used to monitor the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's electroencephalogram signal; perform part association on the patient's physiological monitoring data to generate the patient's part association data; use the patient's electroencephalogram signal to calculate the part association index influence on the patient's part association data to obtain the third stage patient part association influence index;
[0036] In an embodiment of the present invention, the physiological parameters of the patient are monitored in real time by using biosensors or medical devices, such as heart rate monitors, sphygmomanometers, thermometers, etc. These devices can record changes in physiological signals and transmit data to a computer system for analysis. Electroencephalogram (EEG) equipment is used to record the patient's brain electrical signals by placing electrodes on the patient's scalp. EEG can provide information about the patient's brain activity, including neural activity related to the site. Combined with medical imaging, such as MRI, CT, etc., the patient's disease-related sites are located and analyzed. These imaging data can help determine the specific location of the disease-related site. Using data mining technology or machine learning algorithms, the association between physiological monitoring data and disease-related sites is modeled and analyzed to determine the correlation between different physiological parameters and disease sites. The collected EEG signals are preprocessed and feature extracted to obtain neural activity features related to site association, including frequency domain analysis, time domain analysis, spatial domain analysis, etc. Using machine learning algorithms or pattern recognition techniques, the relationship between EEG signal features and the degree of site association influence is modeled and predicted.
[0037] The mental health assessment module is used to integrate the patient's anxiety value in the first stage, the patient's emotional fluctuation data in the second stage, and the patient's body part correlation impact index in the third stage to generate patient stage psychological impact data; conduct patient mental health assessment on the patient's stage psychological impact data to generate a patient mental health assessment value; compare the patient's mental health assessment value with a preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is issued.
[0038] In an embodiment of the present invention, the patient anxiety values collected in the first stage are incorporated into the data integration process. These data are obtained through questionnaires, psychological tests or clinical assessments. The emotional fluctuation data of patients in the second stage are integrated into the data set. These data come from emotional monitoring devices, diary records or sentiment analysis tools. The patient's part association impact index in the third stage is integrated into the data set. These indexes are obtained through neuroimaging, physiological monitoring or part association assessment tools. The integrated data is analyzed and modeled using statistical analysis or machine learning algorithms, involving steps such as feature extraction, data standardization, and model training. A variety of models, such as regression models, classification models, etc., can be used to predict the patient's mental health assessment value. According to the established model, the patient's data is evaluated to generate a mental health assessment value. This value can represent the patient's overall mental health status. A preset psychological assessment threshold is set as a basis for judging whether the patient needs preoperative mental health counseling. The patient's mental health assessment value is compared with a preset standard psychological assessment threshold. If the patient's assessment value is greater than or equal to the threshold, the patient's mental health is judged to be unqualified and a corresponding warning is issued.
[0039] Preferably, the anxiety assessment module includes:
[0040] Obtain medical information data of urology patients;
[0041] Perform data preprocessing on the medical information data of urology patients to generate standard patient medical information data, where data preprocessing includes data denoising, data missing value filling, data outlier detection and data standardization;
[0042] Perform disease cognition analysis through standard patient medical information data to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage;
[0043] The patient's anxiety is assessed based on the patient's first cognitive stage, and the patient's first stage anxiety assessment data is generated.
[0044] The present invention can improve the accuracy and reliability of medical information data of urology patients through data preprocessing, including denoising, missing value filling, outlier detection and data standardization, and provide a more reliable data basis for subsequent analysis. By performing disease cognition analysis and cognitive stage division on standard patient medical information data, the patient's disease cognition level can be better understood. Patient anxiety assessment can be carried out in the patient's first cognitive stage, which helps to detect the patient's anxiety in time, so as to take corresponding intervention measures to reduce the patient's anxiety level. Through comprehensive processing and analysis of medical information data, the patient's condition and needs can be more comprehensively understood, which helps medical staff to provide more accurate and personalized medical services, improve medical quality and patient satisfaction.
[0045] In an embodiment of the present invention, medical information data of urology patients is obtained. Usually, these data come from the hospital's electronic medical record system, doctor's records or other medical information management systems. The data include basic information of the patient (such as age, gender), symptom description, diagnosis results, treatment plan, etc. The data is obtained through data extraction tools, APIs or directly exported from the medical information system. Use data cleaning technology to identify and delete outliers, erroneous values or inconsistent values in the data to ensure data quality. Use filling algorithms (such as mean and median filling) or predictive filling based on machine learning models to process missing values in the data. Use statistical methods (such as box plots, Z-scores), clustering algorithms or deep learning-based anomaly detection methods to identify and process outliers. Use standardization methods (such as Min-Max standardization and Z-score standardization) to convert data into a standard form with a unified scale and distribution for subsequent analysis. Use data mining, machine learning or deep learning technology to analyze the patient's medical information to identify the patient's disease cognition level, involving text analysis, pattern recognition and other technologies. According to the disease cognition level, patients are divided into different cognitive stages (such as the first cognitive stage, the second cognitive stage, and the third cognitive stage). For the first cognitive stage of patients, conduct anxiety assessment on patients and use standardized anxiety assessment tools (such as the Self-Rating Anxiety Scale, the Hospital Anxiety and Depression Scale, etc.) to assess the anxiety level of patients. Based on the assessment results, generate anxiety assessment data for patients in the first cognitive stage to help doctors understand the patient's psychological state.
[0046] Preferably, the anxiety assessment of the patient based on the patient's first cognitive stage includes:
[0047] An electronic anxiety scale was designed for patients based on the first cognitive stage of the patients to obtain the electronic anxiety scale for the patients;
[0048] Conducting an electronic anxiety questionnaire assessment on the patient through the patient electronic anxiety scale to obtain the patient electronic anxiety assessment scale; calculating the questionnaire option scores on the patient electronic anxiety assessment scale to obtain the initial score data of the patient anxiety assessment;
[0049] Analyze the time spent on the questions of the patient's electronic anxiety assessment scale to generate the time spent on the questions of the patient's electronic anxiety assessment scale; screen the key assessment questions of the patient's electronic anxiety assessment scale based on the time spent on the questions of the patient's electronic anxiety assessment scale to generate the key anxiety assessment question data;
[0050] The number of option selections for the key questions of the anxiety assessment was analyzed to obtain the number of anxiety assessment option selections; the initial score data of the patient's anxiety assessment was averaged according to the number of anxiety assessment option selections to generate the patient's first-stage anxiety assessment data.
[0051] The present invention can objectively evaluate the patient's anxiety level through the design of an electronic anxiety scale and the evaluation of an electronic anxiety questionnaire, avoid the errors caused by subjective evaluation, and provide accurate feedback on the patient's emotional state. By analyzing the patient's electronic anxiety assessment scale, including question time analysis, key assessment question screening, and option selection frequency analysis, the specific manifestations and causes of the patient's anxiety can be understood more finely, thereby formulating a personalized anxiety management plan. The use of electronic questionnaire evaluation and data analysis can greatly improve the efficiency of the evaluation process, reduce the time cost of traditional manual evaluation, and enable medical staff to focus more on dealing with other aspects of the patient's needs. By generating the patient's first-stage anxiety assessment data, a continuous monitoring and adjustment mechanism can be established to track the patient's anxiety in a timely manner and make necessary interventions and adjustments.
[0052] In the embodiment of the present invention, by selecting a suitable anxiety assessment scale according to the purpose of anxiety assessment and patient characteristics, or designing a customized anxiety scale according to clinical experience, psychological knowledge and clinical experience are involved. The designed anxiety scale can be digitized, and an online survey platform, professional medical software or self-developed application can be used so that patients can conveniently conduct evaluation. The patient completes the anxiety scale through an electronic device (such as a tablet computer, a smart phone). The filling process can be carried out through a specially designed application. According to the patient's filling results, a predefined algorithm or a standard scoring method is used to calculate the patient's initial anxiety assessment score, which involves the calculation of the score for each question and the summary of the total score. The time taken by the patient to complete each question is recorded to analyze the patient's reaction speed and attention distribution on different questions. According to the patient's question time data and clinical experience, the most representative and sensitive key assessment questions for assessing anxiety levels are selected. The number of times the patient chooses each option is counted to understand the patient's preference and tendency for different options. According to the number of option selections, the initial score data of the patient's anxiety assessment is averaged by swinging the option score, that is, the score is adjusted according to the selection of the option to reduce the score deviation caused by the imbalance of the option.
[0053] Preferably, the emotion fluctuation analysis module includes:
[0054] Based on the second cognitive stage, the patient's cognitive behavior analysis is performed to generate the patient's cognitive behavior data, wherein the patient's cognitive behavior analysis includes speech expression analysis, behavior analysis and social interaction analysis;
[0055] Describe the patient's condition through the patient's cognitive behavior data and generate the patient's self-reported condition data;
[0056] Use natural language technology to analyze the patient's self-reported data to obtain patient emotion data; use the patient emotion data to classify the patient's cognitive behavior data to generate patient emotion classification data;
[0057] The emotion fluctuation quantification formula is used to quantify the emotion fluctuations of the patient's emotion classification data to generate the emotion fluctuation quantification value; the emotion fluctuations of the patient's emotional data are identified according to the emotion fluctuation quantification value to generate the second-stage patient emotion fluctuation data.
[0058] Through patient cognitive behavior analysis and emotion analysis, the present invention can fully understand the patient's verbal expression, behavior and social interaction, and then obtain the patient's emotional data and emotion classification, which helps medical staff to have a deep understanding of the patient's emotional state and psychological needs. Through the generation of condition description and emotion fluctuation data, it can help medical staff to formulate more personalized treatment plans. Through emotion fluctuation quantification and emotion fluctuation identification, it is possible to monitor and identify the patient's emotion fluctuations, timely discover the changing trends and abnormal fluctuations of the patient's emotions, provide medical staff with the opportunity to intervene in time, and help the patient's emotions stabilize and recover.
[0059] As an example of the present invention, refer to Figure 2 As shown, in this example, the emotion fluctuation analysis module includes:
[0060] Based on the second cognitive stage, the patient's cognitive behavior analysis is performed to generate the patient's cognitive behavior data, wherein the patient's cognitive behavior analysis includes speech expression analysis, behavior analysis and social interaction analysis;
[0061] In the embodiment of the present invention, the text data of the patient's verbal expression is analyzed by using natural language processing technology, involving sentiment analysis, word frequency statistics, topic extraction and other technologies. The sentiment analysis algorithm is used to identify the emotions and emotional tendencies contained in the text. This can help determine whether the patient has psychological problems such as anxiety and depression. Through the topic extraction technology, the key topics or concerns in the patient's verbal expression are determined to understand the content of their thinking and areas of concern. Recording the patient's behavior through video monitoring, behavior records or observer reports requires the use of professional observation tools and well-trained observers. Using pattern recognition technology, the patient's behavior pattern is analyzed, including activity frequency, posture, and movement coherence. This can help discover cognitive problems or abnormal behavior in patients. By analyzing the patient's interaction on social networks, including speech, interaction frequency, relationship network, etc. on social platforms, their social activity patterns and communication behaviors are understood. According to the actual conversation with others, the patient's language expression, conversation fluency, speech speed, intonation and other factors are analyzed to infer their cognitive level and social ability. By simulating social situations or role-playing, the patient's performance and reaction in different social scenarios are observed to understand their social adaptability and communication skills.
[0062] Describe the patient's condition through the patient's cognitive behavior data and generate the patient's self-reported condition data;
[0063] In an embodiment of the present invention, the previously collected patient cognitive behavioral data, including the results of speech expression analysis, behavior analysis, and social interaction analysis, are integrated. Key features are extracted from the integrated data, such as emotional tendencies in speech expression, pattern recognition results in behavior, and communication methods in social interaction. Natural language generation technology is used to convert the extracted features into natural language descriptions, involving technologies such as text generation models and template filling. According to the individual differences and disease characteristics of the patients, personalized self-description content is customized to meet the needs and preferences of the patients. Through communication with the patients or review by professionals, it is verified whether the generated self-description data accurately reflects the patient's cognitive behavioral characteristics and disease description. The verified self-description data is fed back to the patient for review and confirmation. At the same time, necessary explanations and supplementary instructions are provided to ensure that the patient understands and accepts the self-description content.
[0064] Use natural language technology to analyze the patient's self-reported data to obtain patient emotion data; use the patient emotion data to classify the patient's cognitive behavior data to generate patient emotion classification data;
[0065] In an embodiment of the present invention, by using sentiment analysis technology, the emotional tendencies expressed in the text are identified, including positive, negative or neutral, etc., involving a sentiment classification model based on machine learning or deep learning. The intensity and degree of emotions are analyzed to understand the patient's emotional state. This can be achieved by calculating the weights of the sentiment words in the text or analyzing the context. According to the results of the sentiment analysis, the patient's emotions are divided into different emotion categories, such as happiness, depression, anxiety, etc. This can be achieved using a sentiment dictionary or a trained sentiment classifier. The intensity and degree of each emotion is analyzed to understand the patient's response to different emotions. This can be measured by the score or weight in the sentiment analysis, and the sentiment classification results are integrated with the patient's cognitive behavior data to form a complete patient emotion classification data set.
[0066] The emotion fluctuation quantification formula is used to quantify the emotion fluctuations of the patient's emotion classification data to generate the emotion fluctuation quantification value; the emotion fluctuations of the patient's emotional data are identified according to the emotion fluctuation quantification value to generate the second-stage patient emotion fluctuation data.
[0067] In an embodiment of the present invention, a suitable emotion fluctuation quantification formula is formulated or selected to convert emotion classification data into specific fluctuation quantification values, which involves the design of a statistical method or a mathematical model. According to the selected emotion fluctuation quantification formula, the patient's emotion classification data is calculated to obtain the emotion fluctuation quantification value in each time period. According to the distribution of the fluctuation quantification value and the characteristics of the emotion data, a suitable emotion fluctuation threshold is set to judge the critical point of the emotion fluctuation. According to the comparison between the emotion fluctuation quantification value and the set threshold, the emotion fluctuation in the emotion data is identified. When the fluctuation quantification value exceeds the threshold, it is considered that an emotion fluctuation has occurred. According to the fluctuation identification result, the second stage of the patient's emotion fluctuation data is generated, including the time point when the fluctuation occurs, the duration of the fluctuation, the type of fluctuation (such as emotion rise and fall, fluctuation amplitude, etc.) and other information.
[0068] Preferably, using natural language technology to perform patient emotion analysis on the patient's self-reported condition data and using the patient's emotion data to perform patient emotion classification on the patient's cognitive behavior data includes:
[0069] The patient's self-reported condition data is converted into text format using natural language technology to generate the patient's self-reported condition text data; the patient's self-reported condition text data is symbol-removed to generate the patient's self-reported condition text-removed data;
[0070] Performing text segmentation on the excluded data of the patient's self-report text to generate the patient's self-report text segmentation data; performing sentiment word matching on the patient's self-report text segmentation data based on a preset sentiment dictionary to generate the patient's self-report sentiment word matching data;
[0071] By matching the patient's self-reported condition sentiment words with the patient's self-reported condition text data, the patient's sentiment polarity is identified to generate the patient's sentiment data;
[0072] The patient's emotion data is used to classify the patient's cognitive behavior data to generate patient emotion classification data.
[0073] The present invention converts the text format of the patient's self-described condition data through natural language technology to generate the patient's self-described condition text data, and removes symbols to generate the patient's self-described condition text removal data. This can help convert the patient's condition description provided by the patient from different formats (such as voice records or handwritten notes) into text data that is easy to process, and remove irrelevant symbols, so as to improve the accuracy and efficiency of the subsequent text processing steps. The patient's self-described condition text removal data is segmented to generate the patient's self-described condition text segmentation data, and the patient's self-described condition text segmentation data is matched with emotion words based on a preset emotion dictionary to generate the patient's self-described condition emotion word matching data. This step segmentes the patient's condition description, splits the text into meaningful words, and then uses the emotion dictionary to identify the emotion words therein, and performs emotion matching to improve the accuracy of the subsequent emotion analysis. The patient's self-described condition text data is identified by the patient's condition emotion word matching data to generate the patient's emotion data. This step is intended to identify the emotion polarity in the patient's condition description, such as positive, negative or neutral, to help medical staff better understand the patient's emotions and psychological state. The patient's emotion classification data is generated by combining the patient's emotion data with the patient's cognitive behavior data to classify the patient's emotions, such as anxiety, depression, calmness, etc., so as to better understand the patient's mental health status.
[0074] In an embodiment of the present invention, by utilizing natural language processing (NLP) technology, methods such as text parsing and lexical analysis are used to convert the self-report data of the patient's condition provided into a text format that can be processed by a computer, for example, using the NLTK or spaCy library in Python. Then, for the generated self-report text data of the patient's condition, symbols such as punctuation marks, special characters, etc. are removed by regular expressions or string processing methods to obtain clean self-report text removal data of the patient's condition. Text segmentation is performed on the self-report text removal data of the patient's condition, and a segmentation tool or algorithm is usually used, such as the segmenter in the jieba Chinese segmentation library or NLTK, to divide the text into meaningful words or phrases, and form the self-report text segmentation data of the patient's condition. Then, using a pre-constructed emotional dictionary, such as the emotional dictionary Afinn or NRC, the text is matched with emotional words, the emotional words therein are identified, and the emotional words are associated with the corresponding emotional values to generate the patient's condition self-report emotional word matching data. Using the patient's self-reported emotional word matching data, sentiment analysis techniques such as rule-based methods or machine learning algorithms (e.g., sentiment classifiers) are used to identify the sentiment polarity of the patient's self-reported text data. By calculating the weights and scores of sentiment words and sentiment conversion rules, the sentiment polarity of the text (such as positive, negative, or neutral) is determined to generate patient sentiment data. Using the patient's emotional data, combined with cognitive behavioral theory or emotion classification models, the patient's emotions are classified. This can be achieved through methods such as rule engines, decision trees, support vector machines (SVMs), or deep learning models. According to the characteristics of the patient's emotional data, it is classified into different emotion types, such as anxiety, depression, calmness, etc., to generate patient emotion classification data.
[0075] Preferably, the emotion fluctuation quantification formula used to quantify the emotion fluctuation of the patient's emotion classification data is as follows:
[0076]
[0077] Among them, V(t) represents the quantitative value of emotional fluctuation at time t, α represents the amplitude of control fluctuation, β represents the attenuation rate of control fluctuation, γ represents the coefficient of change of control fluctuation amplitude, ω represents the periodic coefficient of control fluctuation, E(τ) represents the emotional value at time t, and τ represents the time within the integration range.
[0078] The present invention analyzes and integrates a formula for quantifying emotion fluctuations. V(t) in the formula represents the quantified value of emotion fluctuations at time t, which is the final desired result, that is, the specific quantified value of the degree of emotion fluctuation at different time points. α, β, γ, ω are parameters for controlling emotion fluctuations, which correspond to the amplitude, attenuation rate, coefficient of variation of amplitude, and periodicity coefficient, respectively. By adjusting these parameters, the characteristics of emotion fluctuations can be adjusted to meet the needs. E(τ) represents the emotion value at time τ, and the result V(t) of the emotion fluctuation quantification formula is calculated based on the emotion value at time t and the emotion change rate within the time range. is the derivative of the emotion value E with respect to time τ, indicating the rate of change of emotion over time. This part reveals how emotions change over time and is the basis for quantifying emotion fluctuations. ―β(t―τ) . is a wave function that describes the form of emotional fluctuations. ―β(t―τ) It represents the attenuation of emotional fluctuations, which weakens over time; (1+γ·sin(ω(t-τ))) describes the amplitude of the fluctuation, where γ controls the change in amplitude, and sin(ω(t-τ)) represents periodic fluctuations. When using the conventional emotional fluctuation quantification formula in the field, the emotional fluctuation quantification value at time t can be obtained. By applying the emotional fluctuation quantification formula provided by the present invention, the emotional fluctuation quantification value at time t can be calculated more accurately. Through the combination of these parameters and formulas, the emotional fluctuations can be quantified, and the form and characteristics of the fluctuations can also be controlled. For example, the amplitude of the fluctuation can be controlled by adjusting α, the attenuation speed of the fluctuation can be controlled by adjusting β, and the periodicity and amplitude changes of the fluctuation can be controlled by adjusting γ and ω. This can more accurately understand and describe the emotional fluctuations, thereby providing more targeted information and tools for emotional management and prediction.
[0079] Preferably, the part association module includes:
[0080] According to the third cognitive stage, the patient's physiological information is monitored using physiological monitoring equipment to obtain the patient's physiological monitoring data; the patient's electroencephalogram (EEG) signal is collected based on the electroencephalogram (EEG) to obtain the patient's electroencephalogram (EEG) signal data;
[0081] Perform abnormal physiological parameter fluctuation analysis on the patient's physiological monitoring data to generate abnormal physiological fluctuation data of the patient; perform spectrum analysis on the patient's abnormal physiological fluctuation data to generate a spectrum diagram of the patient's abnormal physiological fluctuation;
[0082] Performing EEG signal fluctuation analysis on the patient's EEG signal data to generate the patient's EEG signal fluctuation data; performing spectrum analysis on the patient's EEG signal fluctuation data to generate the patient's EEG signal spectrum graph; overlapping the patient's abnormal physiological fluctuation spectrum graph and the patient's EEG signal spectrum graph to obtain an overlapped spectrum graph;
[0083] The patient's physiological monitoring data is partly associated with each other according to the overlapped spectrum diagram to generate patient part-associated data; the patient's EEG signal is used to calculate the influence of the part-associated index on the patient's part-associated data to obtain the third-stage patient part-associated influence index.
[0084] The present invention can monitor the patient's physiological information and EEG signals in real time through the combination of physiological monitoring equipment and EEG, and achieve a comprehensive understanding of the patient's condition. By performing abnormal physiological parameter fluctuation analysis and spectrum analysis on physiological monitoring data, the patient's physiological abnormalities can be identified in time, providing important reference for doctors and helping to adjust the treatment plan in time. Fluctuation analysis and spectrum analysis of EEG signals can reveal the patient's EEG activity characteristics, such as the frequency and amplitude of brain waves, which helps to identify abnormal patterns and regularities of EEG signals. Based on the overlapping spectrum graph, the disease-related parts related to the EEG signals in the patient's physiological monitoring data can be determined, and then the patient's part association influence index can be calculated.
[0085] As an example of the present invention, refer to Figure 3 As shown, in this example, the part association module includes:
[0086] According to the third cognitive stage, the patient's physiological information is monitored using physiological monitoring equipment to obtain the patient's physiological monitoring data; the patient's electroencephalogram (EEG) signal is collected based on the electroencephalogram (EEG) to obtain the patient's electroencephalogram (EEG) signal data;
[0087] In an embodiment of the present invention, a set of devices capable of monitoring multiple physiological indicators is selected. These devices include electrocardiogram (ECG) devices, sphygmomanometers, oximeters, and thermometers. Modern monitoring devices are usually wearable and can continuously monitor and transmit data via wireless communication. Electrocardiogram electrodes are attached to specific locations on the patient's chest to ensure accurate measurement of cardiac electrical signals. Other devices are installed, such as placing an oximeter on the patient's finger, tying a sphygmomanometer on the arm, and using a forehead or ear thermometer. All equipment needs to be calibrated to ensure accuracy. Start the device and ensure that data collection is performed normally. Data is transmitted to a central monitoring system or the patient's electronic health record via wireless communication. Data collection is usually performed in real time, but sampling intervals can also be set as needed. Data from different devices are integrated into the patient's physiological monitoring data. Using an electroencephalogram device, select a system with multiple electrode channels to ensure that sufficient brain areas are covered. Modern electroencephalogram devices are usually portable and have wireless transmission capabilities. According to the international 10-20 system, an electrode cap or electrode patch is installed on the patient's scalp. To ensure good contact between the electrode and the scalp, conductive paste or conductive liquid is required to reduce impedance. Start the EEG device and start collecting EEG signals. The signal contains a lot of noise, so it is necessary to apply filters to remove myoelectric interference and environmental noise. The EEG signal data is transmitted to a central monitoring system or database via wireless or wired communication. The data is usually processed in segments to ensure that the EEG activity of each time period is accurately recorded.
[0088] Perform abnormal physiological parameter fluctuation analysis on the patient's physiological monitoring data to generate abnormal physiological fluctuation data of the patient; perform spectrum analysis on the patient's abnormal physiological fluctuation data to generate a spectrum diagram of the patient's abnormal physiological fluctuation;
[0089] In an embodiment of the present invention, the physiological monitoring data is analyzed by using a signal processing algorithm to detect abnormal fluctuations in physiological parameters. Abnormal fluctuations are identified using techniques such as statistical methods, machine learning or deep learning models. The physiological monitoring data is preprocessed, including steps such as noise removal, filtering and data normalization to ensure data quality. An appropriate anomaly detection algorithm, such as a threshold-based method, a time series model or a machine learning method, is applied to detect abnormal fluctuations in physiological parameters. The time point and amplitude of the abnormal fluctuation are identified and recorded to generate abnormal physiological fluctuation data of the patient. The abnormal physiological fluctuation data generated in the previous step is used as input. Spectral analysis techniques such as Fourier transform or wavelet transform are applied to convert the abnormal fluctuation data in the time domain into the frequency domain. Using the spectrum analysis results, a spectrum diagram of the patient's abnormal physiological fluctuations is drawn. The spectrum diagram usually includes frequency (horizontal axis) and amplitude or power (vertical axis).
[0090] Performing EEG signal fluctuation analysis on the patient's EEG signal data to generate the patient's EEG signal fluctuation data; performing spectrum analysis on the patient's EEG signal fluctuation data to generate the patient's EEG signal spectrum graph; overlapping the patient's abnormal physiological fluctuation spectrum graph and the patient's EEG signal spectrum graph to obtain an overlapped spectrum graph;
[0091] In an embodiment of the present invention, various waveforms in the EEG signal, such as α, β, θ and δ waves, are identified and extracted by applying a waveform analysis algorithm. According to the waveform analysis results, the patient's EEG signal fluctuation data is generated, including information such as waveform type, amplitude, frequency, etc. The EEG signal fluctuation data generated in the previous step is used as input. Apply spectrum analysis techniques such as Fourier transform or wavelet transform to convert the EEG signal fluctuation data in the time domain into the frequency domain. Using the spectrum analysis results, draw the patient's EEG signal spectrum. The spectrum diagram usually includes frequency (horizontal axis) and power or amplitude (vertical axis). Obtain the patient's abnormal physiological fluctuation spectrum diagram and the EEG signal spectrum diagram. The two spectrum diagrams are overlapped, usually drawn in the same coordinate system, ensuring that the horizontal axis (frequency) is the same and the vertical axis (amplitude or power) is superimposed and displayed. Draw the overlapped spectrum diagram to show the overlap of the patient's abnormal physiological fluctuation spectrum and the EEG signal spectrum in frequency and amplitude.
[0092] The patient's physiological monitoring data is partly associated with each other according to the overlapped spectrum diagram to generate patient part-associated data; the patient's EEG signal is used to calculate the influence of the part-associated index on the patient's part-associated data to obtain the third-stage patient part-associated influence index.
[0093] In an embodiment of the present invention, the overlapped spectrum graph is preprocessed, including denoising, contrast enhancement, etc., to prepare for the identification of disease-associated parts. Features such as shape, texture, color, etc. are extracted from the preprocessed overlapped spectrum graph. A pattern recognition algorithm is applied to train a classifier to identify disease-associated parts. According to the results of pattern recognition, patient part association data is generated, including information such as the type, location, and size of the disease part. Features related to part association, such as frequency spectrum, spectrum power, etc., are extracted from the patient's EEG signal. The features of the EEG signal are matched with the part association data to determine the EEG signal features related to the disease-associated part. The degree of association between the EEG signal and the disease-associated part is calculated using a statistical analysis method, and the degree of influence of the part association index is calculated accordingly. According to the calculation results, the third-stage patient part association influence index is obtained, which is used to evaluate the patient's part association degree, for example, features related to part association are extracted from the EEG signal of patient A, such as the power of a specific frequency spectrum band, frequency change, etc. The features of the EEG signal are matched with the part association data to find out the EEG signal features related to the disease part area. Assume that through data association, it is determined that the left temporal lobe area of patient A is related to the changes in EEG signals in a specific frequency band. Using the regression analysis method, calculate the degree of association between these EEG signal features and the region, that is, the degree of influence of the region on the part association index. According to the regression analysis results, the part association influence index of patient A is obtained. For example, the results show that the left temporal lobe has a greater influence on the part association of patient A, and a quantitative value of the part association index is given.
[0094] Preferably, performing part association on the physiological monitoring data of the patient according to the overlapped frequency spectrum and performing part association index influence calculation on the part association data of the patient using the EEG signal of the patient include:
[0095] Perform overlapping frequency range analysis on the overlapping spectrum diagram to obtain overlapping frequency range data; perform same-frequency amplitude analysis on the overlapping spectrum diagram based on the overlapping frequency range data based on the positive feedback effect to generate same-frequency amplitude data;
[0096] Based on the coincident frequency range data, the same frequency amplitude data and the patient's physiological monitoring data, the physiological location of the disease is associated.
[0097] The patient's EEG signal is used to analyze the patient's EEG activity intensity on the patient's part-related data to generate the patient's EEG activity intensity data; the patient's part-related index influence is calculated using the patient's EEG activity intensity data to obtain the third-stage patient part-related influence index.
[0098] The present invention can determine the frequency-coincident areas in the patient's brain and their amplitudes through overlapping frequency range analysis and same-frequency amplitude analysis. This information helps to understand the brain's activity patterns within a specific frequency range and is related to site-association perception. By correlating overlapping frequency range data, same-frequency amplitude data, and the patient's physiological monitoring data, the physiological sites associated with the disease can be more accurately determined. This helps to link the site association index calculation with the patient's physiological state and disease-related information. Using the patient's EEG signal to perform EEG activity intensity analysis on the patient's site association data further provides information about the activity of the brain areas associated with the site association. This can provide a more direct biomarker for the calculation of the site association index.
[0099] As an example of the present invention, refer to Figure 4 As shown, in this example, the part association of the patient's physiological monitoring data according to the overlapped spectrum diagram and the part association index influence calculation of the patient's part association data using the patient's EEG signal include:
[0100] Perform overlapping frequency range analysis on the overlapping spectrum diagram to obtain overlapping frequency range data; perform same-frequency amplitude analysis on the overlapping spectrum diagram based on the overlapping frequency range data based on the positive feedback effect to generate same-frequency amplitude data;
[0101] In an embodiment of the present invention, by extracting the overlapping frequency range from the overlapping spectrum diagram, it involves using a spectrum analysis method in signal processing technology, such as Fourier transform. The extracted frequency range data is further analyzed, including statistical analysis, spectrum shape fitting, etc., to obtain more information about the overlapping frequency range, such as the average frequency, the standard deviation of the frequency range, etc. In the overlapping spectrum diagram, the amplitude data of the same frequency is extracted for the frequencies within the overlapping frequency range. This can be achieved by measuring the amplitude within the frequency range. Based on the positive feedback effect, the amplitude data of the same frequency is further analyzed. The positive feedback effect refers to the enhancement effect of certain systems on the input signal, which can be used to enhance or weaken the signal of a specific frequency. The extracted amplitude data of the same frequency is analyzed, including statistical analysis, amplitude change trend analysis, etc., to obtain information about the amplitude of the same frequency, such as the average amplitude, the degree of fluctuation of the amplitude, etc.
[0102] Correlation of disease physiological sites is performed based on overlapping frequency range data, same frequency amplitude data and patient physiological monitoring data to generate patient site correlation data;
[0103] In an embodiment of the present invention, a suitable feature extraction method is selected for the overlapping frequency range data and the same-frequency amplitude data, such as statistical features (mean value, standard deviation, etc.), spectral features (frequency components, spectral morphology, etc.). Feature selection is performed based on the importance and relevance of the features to screen out features that have an impact on the association with the physiological site of the disease, so as to reduce the computational complexity of subsequent analysis and improve the interpretability of the model. The patient's physiological monitoring data is integrated with the previously extracted overlapping frequency range data and the same-frequency amplitude data to form a complete data set. Association analysis methods such as correlation analysis, regression analysis, machine learning models, etc. are used to analyze the degree of association between the physiological monitoring data and the frequency range data and amplitude data to determine the association relationship between the physiological site of the disease. If a machine learning model is used, the model is trained and verified to ensure that the model can accurately predict the association relationship between the physiological site of the disease.
[0104] The patient's EEG signal is used to analyze the patient's EEG activity intensity on the patient's part-related data to generate the patient's EEG activity intensity data; the patient's part-related index influence is calculated using the patient's EEG activity intensity data to obtain the third-stage patient part-related influence index.
[0105] In an embodiment of the present invention, the characteristics of EEG signals in the time and frequency domains are explored by utilizing time-frequency analysis techniques, such as wavelet transform or time-frequency analysis. This can reveal the activity intensity of different frequency bands, such as delta waves (0.5-4Hz), theta waves (4-8Hz), alpha waves (8-13Hz), beta waves (13-30Hz) and gamma waves (30-100Hz). The spatial distribution of EEG signals is determined by spatial filtering techniques (such as independent component analysis) or source localization techniques (such as inverse problem solving), that is, the activity level of different brain regions is determined. Combined with the time-frequency characteristics and spatial distribution of EEG signals, the patient's EEG activity intensity data is generated. This can be a matrix containing the activity levels of each brain region, or the activity level for a specific frequency band. Combining the patient's EEG activity intensity data with the previously obtained site association data involves modeling the correlation between the disease-related site and different brain regions, and determining the relationship between the patient's EEG activity level and the site association index. According to the established model, the patient's site association index influence is calculated, which is a quantitative indicator that reflects the degree of correlation between the patient's EEG activity level and the site association level.
[0106] Preferably, the mental health assessment module includes:
[0107] The anxiety values of patients in the first stage, the emotional fluctuation data of patients in the second stage, and the body part association impact index of patients in the third stage are integrated to generate the psychological impact data of the patients;
[0108] The patient's psychological impact data at each stage is divided into a data set to obtain a model training set and a model test set; the model training set is trained using a support vector machine algorithm to generate a patient mental health assessment training model;
[0109] Iteratively optimize the patient mental health assessment training model according to the model test set to generate a patient mental health assessment model; import the patient's stage psychological impact data into the patient mental health assessment model to conduct a patient mental health assessment and generate a patient mental health assessment value;
[0110] The patient's mental health assessment value is compared with the preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is issued.
[0111] The present invention obtains the psychological impact data of patients at different stages by integrating the data of the first, second and third stages. Such integration helps to comprehensively consider the patient's anxiety level, mood swings and part-related impact index, and provides more comprehensive psychological state information. The integrated data set is divided into a training set and a test set, and the training set is trained using a support vector machine algorithm to generate a patient psychological health assessment training model. This model can help identify the patterns and trends of the patient's mental health status. Through model iterative optimization, a more accurate patient psychological health assessment model is generated. This model can more accurately predict the patient's mental health status and provide more targeted suggestions for subsequent psychological support. The patient's mental health assessment value is compared with a preset standard psychological assessment threshold, and when the assessment value is higher than or equal to the threshold, the patient is provided with preoperative psychological health counseling. Such counseling measures can help patients cope with anxiety and tension before surgery, improve the success rate of surgery and the patient's mental health level.
[0112] In an embodiment of the present invention, the anxiety value of the first-stage patient, the mood swing data of the second-stage patient, and the position-related impact index of the third-stage patient are obtained from different sources (such as questionnaires, sensor data, etc.). These data are preprocessed, including data cleaning, missing value processing, and data standardization, etc., to ensure the quality and consistency of the data. The preprocessed data are integrated into a data set, each row represents a patient, and each column represents a feature (such as anxiety value, mood swings, etc.) to form patient stage psychological impact data. The patient stage psychological impact data is divided into a model training set and a model test set, usually by cross-validation or random division. The model training set is trained using a support vector machine (SVM) algorithm. SVM is a supervised learning algorithm that performs classification or regression tasks by finding the best hyperplane. The patient's mental health assessment training model is verified and optimized using the model test set, and the hyperparameters of the SVM algorithm are adjusted by methods such as cross-validation or grid search to improve the performance of the model. Feature selection, data enhancement, or ensemble learning can be used to further optimize the model to improve its generalization ability and robustness. The patient's psychological impact data at this stage is imported into the trained mental health assessment model, and the patient's mental health assessment value is obtained through the model. The patient's mental health assessment value is compared with the preset standard psychological assessment threshold. If the assessment value is higher than or equal to the threshold, it means that the patient has mental health problems and needs preoperative mental health counseling.
[0113] In this specification, a method for evaluating the psychological health of patients in urology surgery is provided, which is used to implement the above-mentioned system for evaluating the psychological health of patients in urology surgery. The method for evaluating the psychological health of patients in urology surgery includes:
[0114] Step S1: Acquire medical information data of urinary shell patients; perform disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; perform patient anxiety assessment based on the first cognitive stage to obtain the first stage patient anxiety value;
[0115] Step S2: Based on the second cognitive stage, cognitive behavior analysis is performed on the patient to generate patient cognitive behavior data; patient emotion analysis is performed on the patient cognitive behavior data to obtain patient emotion data; emotion fluctuation recognition is performed on the patient cognitive behavior data through the patient emotion data to generate second stage patient emotion fluctuation data;
[0116] Step S3: monitoring the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's electroencephalogram signal; performing part association on the patient's physiological monitoring data to generate patient part association data; using the patient's electroencephalogram signal to calculate the part association index influence on the patient's part association data to obtain the third stage patient part association influence index;
[0117] Step S4: Integrate the anxiety value of the patient in the first stage, the emotional fluctuation data of the patient in the second stage, and the body part correlation impact index of the patient in the third stage to generate the patient's stage psychological impact data; conduct a patient mental health assessment on the patient's stage psychological impact data to generate a patient mental health assessment value; compare the patient's mental health assessment value with a preset standard psychological assessment threshold, and when the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, issue a corresponding mental health warning.
[0118] The beneficial effect of the present invention is that the medical information data of urology patients is obtained. Disease cognition data is generated by analyzing the medical information data. The cognitive data is divided into different cognitive stages to better understand the patient's cognitive level of the disease. Cognitive behavioral analysis is performed in the second cognitive stage to understand the patient's behavioral response and thinking process, and emotional analysis is performed on the cognitive behavioral data to understand the patient's emotional state. The patient's emotional fluctuations are identified through emotional data to help medical staff better understand the patient's emotional changes. Physiological monitoring is performed in the third cognitive stage to obtain the patient's physiological monitoring data and electroencephalogram signals. The physiological monitoring data is analyzed to determine the associated parts related to the disease, and the patient's part association impact index is calculated using the electroencephalogram signal to help evaluate the patient's part association impact degree. The data of different stages are integrated into the patient's stage psychological impact data. The patient's mental health assessment is performed based on the psychological impact data to obtain the patient's mental health assessment value. The assessment value is compared with the preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is performed. Therefore, the present invention improves the accuracy and reliability of the assessment by performing detailed and personalized physiological and psychological comprehensive assessments based on different patient cognitive processes and combining the patient's physiological information monitoring and electroencephalogram signals.
[0119] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0120] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A method for evaluating the psychological health of urology patients, characterized in that: The following steps are involved: Anxiety assessment module, used to obtain medical information data of urinary shell patients; conduct disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; conduct patient anxiety assessment based on the first cognitive stage to obtain the anxiety value of the patient in the first stage; The emotion fluctuation analysis module is used to conduct cognitive behavior analysis on the patient based on the second cognitive stage and generate cognitive behavior data of the patient; Performing patient emotion analysis on the patient cognitive behavior data to obtain patient emotion data; The emotional fluctuations of patients are identified through the emotional data of patients and the emotional fluctuation data of patients in the second stage are generated; The part association module is used to monitor the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's EEG signal; Performing part association on the patient's physiological monitoring data to generate patient part association data; using the patient's EEG signal to calculate the impact of the part association index on the patient's part association data to obtain the third-stage patient part association impact index; The mental health assessment module is used to integrate the anxiety value of patients in the first stage, the emotional fluctuation data of patients in the second stage, and the body part correlation impact index of patients in the third stage to generate the psychological impact data of the patients; Conduct a mental health assessment on the patient's psychological impact data at each stage to generate a mental health assessment value for the patient; The patient's mental health assessment value is compared with the preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is issued.
2. The urology patient psychological health assessment system according to claim 1, characterized in that: The anxiety assessment module includes: Obtain medical information data of urology patients; Perform data preprocessing on the medical information data of urology patients to generate standard patient medical information data, where data preprocessing includes data denoising, data missing value filling, data outlier detection and data standardization; Perform disease cognition analysis through standard patient medical information data to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; The patient's anxiety is assessed based on the patient's first cognitive stage, and the patient's first stage anxiety assessment data is generated.
3. The urology patient psychological health assessment system according to claim 2, characterized in that: The anxiety assessment of the patient based on the first cognitive stage of the patient includes: An electronic anxiety scale was designed for patients based on the first cognitive stage of the patients to obtain the electronic anxiety scale for the patients; Conducting an electronic anxiety questionnaire assessment on the patient through the patient electronic anxiety scale to obtain the patient electronic anxiety assessment scale; calculating the questionnaire option scores on the patient electronic anxiety assessment scale to obtain the initial score data of the patient anxiety assessment; Analyze the time spent on the questions of the patient's electronic anxiety assessment scale to generate the time spent on the questions of the patient's electronic anxiety assessment scale; screen the key assessment questions of the patient's electronic anxiety assessment scale based on the time spent on the questions of the patient's electronic anxiety assessment scale to generate the key anxiety assessment question data; The number of option selections for the key questions of the anxiety assessment was analyzed to obtain the number of anxiety assessment option selections; the initial score data of the patient's anxiety assessment was averaged according to the number of anxiety assessment option selections to generate the patient's first-stage anxiety assessment data.
4. The urology patient psychological health assessment system according to claim 1, characterized in that: The emotion fluctuation analysis module includes: Based on the second cognitive stage, the patient's cognitive behavior analysis is performed to generate the patient's cognitive behavior data, wherein the patient's cognitive behavior analysis includes speech expression analysis, behavior analysis and social interaction analysis; Describe the patient's condition through the patient's cognitive behavior data and generate the patient's self-reported condition data; Use natural language technology to analyze the patient's self-reported data to obtain patient emotion data; use the patient emotion data to classify the patient's cognitive behavior data to generate patient emotion classification data; The emotion fluctuation quantification formula is used to quantify the emotion fluctuations of the patient's emotion classification data to generate the emotion fluctuation quantification value; the emotion fluctuations of the patient's emotional data are identified according to the emotion fluctuation quantification value to generate the second-stage patient emotion fluctuation data.
5. The urology patient psychological health assessment system according to claim 4, characterized in that: The use of natural language technology to analyze patient sentiment on patient self-reported data and the use of patient sentiment data to classify patient sentiment on patient cognitive behavior data include: The patient's self-reported condition data is converted into text format using natural language technology to generate the patient's self-reported condition text data; the patient's self-reported condition text data is symbol-removed to generate the patient's self-reported condition text-removed data; Performing text segmentation on the excluded data of the patient's self-report text to generate the patient's self-report text segmentation data; performing sentiment word matching on the patient's self-report text segmentation data based on a preset sentiment dictionary to generate the patient's self-report sentiment word matching data; By matching the patient's self-reported condition sentiment words with the patient's self-reported condition text data, the patient's sentiment polarity is identified to generate the patient's sentiment data; The patient's emotion data is used to classify the patient's cognitive behavior data to generate patient emotion classification data.
6. The urology patient psychological health assessment system according to claim 4, characterized in that: The emotion fluctuation quantification formula in the emotion fluctuation quantification of the patient emotion classification data using the emotion fluctuation quantification formula is as follows: Among them, V(t) represents the quantitative value of emotional fluctuation at time t, α represents the amplitude of control fluctuation, β represents the attenuation rate of control fluctuation, γ represents the coefficient of change of control fluctuation amplitude, ω represents the periodic coefficient of control fluctuation, E(τ) represents the emotional value at time t, and τ represents the time within the integration range.
7. The urology patient psychological health assessment system according to claim 1, characterized in that: The part association module includes: According to the third cognitive stage, the patient's physiological information is monitored using physiological monitoring equipment to obtain the patient's physiological monitoring data; the patient's electroencephalogram (EEG) signal is collected based on the electroencephalogram (EEG) to obtain the patient's electroencephalogram (EEG) signal data; Perform abnormal physiological parameter fluctuation analysis on the patient's physiological monitoring data to generate abnormal physiological fluctuation data of the patient; perform spectrum analysis on the patient's abnormal physiological fluctuation data to generate a spectrum diagram of the patient's abnormal physiological fluctuation; Performing EEG signal fluctuation analysis on the patient's EEG signal data to generate the patient's EEG signal fluctuation data; performing spectrum analysis on the patient's EEG signal fluctuation data to generate the patient's EEG signal spectrum graph; overlapping the patient's abnormal physiological fluctuation spectrum graph and the patient's EEG signal spectrum graph to obtain an overlapped spectrum graph; The patient's physiological monitoring data is partly associated with each other according to the overlapped spectrum diagram to generate patient part-associated data; the patient's EEG signal is used to calculate the influence of the part-associated index on the patient's part-associated data to obtain the third-stage patient part-associated influence index.
8. The urology patient psychological health assessment system according to claim 7, characterized in that: The method of performing part association on the physiological monitoring data of the patient according to the overlapped spectrum diagram and performing part association index influence calculation on the part association data of the patient using the EEG signal of the patient includes: Perform overlapping frequency range analysis on the overlapping spectrum diagram to obtain overlapping frequency range data; perform same-frequency amplitude analysis on the overlapping spectrum diagram based on the overlapping frequency range data based on the positive feedback effect to generate same-frequency amplitude data; Correlation of disease physiological sites is performed based on overlapping frequency range data, same frequency amplitude data and patient physiological monitoring data to generate patient site correlation data; The patient's EEG signal is used to analyze the patient's EEG activity intensity on the patient's part-related data to generate the patient's EEG activity intensity data; the patient's part-related index influence is calculated using the patient's EEG activity intensity data to obtain the third-stage patient part-related influence index.
9. The urology patient psychological health assessment system according to claim 1, characterized in that: The mental health assessment module includes: The anxiety values of patients in the first stage, the emotional fluctuation data of patients in the second stage, and the body part association impact index of patients in the third stage are integrated to generate the psychological impact data of the patients; The patient's psychological impact data at each stage is divided into a data set to obtain a model training set and a model test set; the model training set is trained using a support vector machine algorithm to generate a patient mental health assessment training model; Iteratively optimize the patient mental health assessment training model according to the model test set to generate a patient mental health assessment model; import the patient's stage psychological impact data into the patient mental health assessment model to conduct a patient mental health assessment and generate a patient mental health assessment value; The patient's mental health assessment value is compared with the preset standard psychological assessment threshold. When the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, a corresponding mental health warning is issued.
10. A method for evaluating the psychological health of urology patients, characterized in that: Used to implement the urology patient psychological health assessment system as claimed in claim 1, the urology patient psychological health assessment method comprises: Step S1: Acquire medical information data of urinary shell patients; perform disease cognition analysis on patients according to the medical information data of urinary shell patients to generate disease cognition data; divide the disease cognition data into cognitive stages to generate the first cognitive stage, the second cognitive stage and the third cognitive stage; perform patient anxiety assessment based on the first cognitive stage to obtain the first stage patient anxiety value; Step S2: Based on the second cognitive stage, cognitive behavior analysis is performed on the patient to generate patient cognitive behavior data; patient emotion analysis is performed on the patient cognitive behavior data to obtain patient emotion data; emotion fluctuation recognition is performed on the patient cognitive behavior data through the patient emotion data to generate second stage patient emotion fluctuation data; Step S3: monitoring the patient's physiological information according to the third cognitive stage to obtain the patient's physiological monitoring data and the patient's electroencephalogram signal; performing part association on the patient's physiological monitoring data to generate patient part association data; using the patient's electroencephalogram signal to calculate the part association index influence on the patient's part association data to obtain the third stage patient part association influence index; Step S4: Integrate the anxiety value of the patient in the first stage, the emotional fluctuation data of the patient in the second stage, and the body part correlation impact index of the patient in the third stage to generate the patient's stage psychological impact data; conduct a patient mental health assessment on the patient's stage psychological impact data to generate a patient mental health assessment value; compare the patient's mental health assessment value with a preset standard psychological assessment threshold, and when the patient's mental health assessment value is greater than or equal to the preset standard psychological assessment threshold, issue a corresponding mental health warning.
Citation Information
Cited By
Multi-mode psychological disease risk screening robot, equipment and storage medium
CN119293739A
Cognitive state evaluation method in closed environment
CN119745319A
