Comprehensive diagnosis and treatment system for neurosurgery patients

Abstract

The invention relates to the technical field of medical informatics, in particular to a neurosurgery patient comprehensive diagnosis and treatment system which comprises a multi-mode state monitoring module, a dynamic trend evaluation module, a consciousness function analysis module, an optimization nursing intervention module and a nursing risk early warning management module. According to the method, key features are extracted in combination with image information, health indexes and behavior changes, serialized monitoring of intracranial lesions, physiological fluctuations and behavior modes is achieved, vital signs and behavior change trends are fused, continuity and objectivity of patient state evaluation are improved, the accuracy of risk identification is enhanced, and the risk identification efficiency is improved. According to the method, a health state change rate evaluation mode is introduced, the prediction capability of function recovery potential is improved, an unstable region is dynamically identified and potential risks are pre-judged in combination with an original state trajectory and intervention response difference, continuous optimization of an intervention path and active avoidance of nursing risks are realized, and the collaboration and continuity of comprehensive management are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical informatics, and in particular to a comprehensive diagnosis and treatment system for neurosurgery patients. Background Art

[0002] The technical field of medical informatics includes information technology, data analysis and its application in medical and health management. This field mainly involves the collection, storage, management, analysis and sharing of health data to promote the quality improvement and efficiency optimization of medical services. The core content includes electronic health record systems (EHR), medical data processing and analysis technologies, artificial intelligence-assisted decision-making systems and the application of big data technology in medicine. Medical informatics not only focuses on the management of patient data, but also involves the circulation and use of medical information to ensure that various medical resources can provide services to patients efficiently and safely.

[0003] Among them, the traditional comprehensive diagnosis and treatment system for neurosurgery patients refers to comprehensive patient management through the integration of multiple diagnosis and treatment links, including the patient's medical history records, imaging data, clinical symptoms and other information. In the traditional model, the system relies on a single information source or technical means to collect and analyze data, and there are problems such as information islands and low collaboration efficiency. Traditional methods mainly rely on separate diagnosis and treatment links to operate, and fail to form a closed loop of diagnosis, treatment and rehabilitation management, making the overall patient management process lack of coherence and systematicness. The comprehensive management of neurosurgery patients fails to fully meet the needs of efficient and personalized services.

[0004] Traditional technologies rely on a single data source and collection method, which makes it difficult to accurately reflect the evolution of the patient's condition under multivariate interference scenarios. Information isolation makes it difficult to share data between diagnosis and treatment nodes, which in turn leads to delayed risk identification and disconnection from the response mechanism. When the condition is complex and fluctuating, diagnostic information is difficult to support the dynamic adjustment of the intervention path. For example, when changes in behavioral patterns and abnormal physiological indicators are not synchronously correlated, the rising trend of risk cannot be warned in time. Traditional recording methods rely on static data to form a basis for judgment and lack continuous monitoring of the state evolution process, resulting in increased lag in clinical judgment. Changes in patient status are often identified only after symptoms appear, and it is easy to miss the key window period for intervention, affecting overall management efficiency. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, the embodiment of the present invention provides a comprehensive diagnosis and treatment system for neurosurgery patients. The technical solution is as follows:

[0006] In one aspect, a comprehensive diagnosis and treatment system for neurosurgery patients is provided, the system comprising:

[0007] The multi-modal state monitoring module extracts intracranial lesion region distribution, vital sign fluctuation range and behavior pattern change based on patient image data, basic health indicators and real-time behavior feedback, stores and analyzes image abnormal region expansion trend in time sequence, judges the cumulative influence of vital sign fluctuation, identifies the stability distribution of behavior pattern, and obtains patient state stability;

[0008] The dynamic trend evaluation module analyzes the change trend of physiological indicator fluctuation range based on the patient state stability, judges the cumulative change of behavior pattern abnormality, counts the fluctuation frequency of short-term physiological compensation capacity, identifies the change range of external environmental factors, and obtains the patient risk condition;

[0009] The consciousness function analysis module analyzes the change trend of brain function compensation capacity based on the patient risk condition, identifies the consciousness recovery rate, judges the function recovery potential, and generates the patient consciousness function health degree;

[0010] The optimized nursing intervention module extracts patient original state record, external influencing factor and nursing stability indicator based on the patient consciousness function health degree, identifies the state stability change interval, analyzes the external influence degree, and obtains the improved nursing intervention list.

[0011] As a further scheme of the application, the patient state stability includes intracranial lesion expansion rate, vital sign fluctuation distribution, behavior pattern stability and external environment consistency, the patient risk condition includes physiological fluctuation amplitude, behavior abnormality cumulative influence, compensation capacity change frequency and external environment fluctuation range, the patient consciousness function health degree includes brain function compensation capacity, consciousness recovery rate and function recovery potential, and the improved nursing intervention list includes state stability interval, external influence degree and nursing implementation risk.

[0012] As a further scheme of the application, the multi-modal state monitoring module includes:

[0013] The image abnormality analysis submodule extracts intracranial lesion region distribution and expansion trend based on patient image data, basic health indicators and real-time behavior feedback, calculates lesion region volume change and collects it to the corresponding time point, arranges lesion expansion values in time sequence, judges the fluctuation of lesion expansion, and obtains the intracranial lesion expansion rate;

[0014] The vital sign fluctuation distribution submodule calls the intracranial lesion expansion rate screening time point, extracts vital sign fluctuation data, counts fluctuation categories and proportion, analyzes fluctuation category proportion change, and generates vital sign fluctuation category proportion change value;

[0015] The behavior pattern monitoring submodule calls the vital sign fluctuation category proportion change value, compares behavior pattern standard, counts behavior abnormality non-compliance time point proportion, and obtains the patient state stability.

[0016] As a further solution of the present invention, the dynamic trend assessment module includes:

[0017] The physiological fluctuation analysis submodule extracts the fluctuation range of physiological indicators based on the patient's state stability, analyzes the fluctuation amplitude of each indicator within the continuous time window, screens indicators whose fluctuations exceed the physiological stability threshold, determines the trend of physiological fluctuations, and obtains the physiological fluctuation coefficient;

[0018] The behavior pattern abnormality monitoring submodule calls the physiological fluctuation coefficient, extracts behavior pattern abnormality records, identifies the number and proportion of abnormal records, determines the abnormal change trend, and obtains the cumulative change rate of behavior pattern abnormality;

[0019] The external environment impact assessment submodule calls the abnormal cumulative change rate of the behavioral pattern, extracts the external environment factor data, and calculates the numerical interval and variation range of the differentiation factor to obtain the patient's risk status.

[0020] As a further solution of the present invention, the consciousness function analysis module includes:

[0021] The brain function compensation capacity assessment submodule extracts brain function compensation indicators and short-term compensation capacity amounts based on the patient's risk status, identifies the proportion of short-term compensation capacity to total compensation, screens the patient numbers whose short-term compensation ratio exceeds the benchmark value, summarizes the changes in brain function compensation capacity, and obtains the brain function compensation fluctuation rate;

[0022] The consciousness recovery rate analysis submodule calls the brain function compensation fluctuation rate, extracts consciousness recovery data, calculates the consciousness recovery cycle and average recovery days, analyzes the changes in consciousness recovery rate, and generates a consciousness recovery change rate;

[0023] The functional recovery potential calculation submodule calls the consciousness recovery change rate, evaluates the functional recovery data, identifies the functional recovery interval and recovery ratio, analyzes the functional recovery trend, and obtains the patient's consciousness function health.

[0024] As a further solution of the present invention, the consciousness recovery change rate adopts the formula:

[0025]

[0026] Among them, R represents the rate of change of consciousness recovery, C i represents the level of consciousness recovered from the i-th data sampling, C i-1 represents the level of consciousness of the i-1th data sampling recovery, n represents the total number of data sampling, V represents the volatility of the recovered data, and T represents the recovery period.

[0027] As a further solution of the present invention, the optimized nursing intervention module includes:

[0028] The consciousness function health assessment submodule extracts brain function compensation data, consciousness recovery data, and function recovery data based on the patient's consciousness function health, calculates the compensation ability index, recovery rate, and recovery potential, and obtains the patient's consciousness function health index;

[0029] The state stability analysis submodule extracts the patient's original state record based on the patient's consciousness function health index, determines whether the state deviation exceeds the state deviation threshold, analyzes the state change trend, and obtains the state stability change interval;

[0030] The nursing implementation risk judgment submodule captures external environment fluctuation data and nursing impact data according to the state stability change interval, calculates the external environment fluctuation rate, analyzes the nursing implementation stability, screens patients whose nursing risks exceed the benchmark threshold, and obtains a list of improved nursing interventions.

[0031] As a further solution of the present invention, the external environment volatility adopts the formula:

[0032]

[0033] Among them, E represents the volatility of the external environment, m represents the total number of samples, and P k Represents the external environment value of the kth sample, P avg Represents the average value of the external environment value.

[0034] As a further solution of the present invention, the system also includes a nursing risk early warning management module:

[0035] The nursing risk warning management module extracts the patient's current status dynamics based on the improved nursing intervention list, monitors the expansion of intracranial lesions, fluctuations in vital signs, and changes in behavioral patterns, analyzes the range of dynamic status fluctuations, identifies the amplitude of changes in patient status stability, determines abnormal changes in nursing care, and obtains nursing risk warning indicators;

[0036] The nursing risk warning indicators include the dynamic fluctuation range of the state, the variation range of the state stability, and abnormal changes in nursing.

[0037] As a further solution of the present invention, the nursing risk early warning management module includes:

[0038] The dynamic state monitoring submodule monitors the expansion of intracranial lesions, fluctuations in vital signs, and changes in behavioral patterns based on the improved nursing intervention list, identifies delayed lesion expansion, abnormal vital signs, and changes in behavioral patterns, and obtains the dynamic state fluctuation range;

[0039] The state fluctuation analysis submodule analyzes the patient's state change trend based on the dynamic state fluctuation range, screens patients with lesion expansion fluctuations, abnormal vital signs, and decreased behavioral patterns, determines the degree of state stability change, identifies state persistence and abnormal concentration intervals, and obtains the amplitude of the patient's state stability change;

[0040] The nursing abnormality judgment submodule detects the nursing change frequency, implementation deviation and patient records according to the fluctuation range of the patient's state stability, screens patients with unstable nursing implementation, and obtains nursing risk warning indicators.

[0041] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0042] By extracting key features from a combination of imaging information, health indicators, and behavioral changes, we can achieve serial monitoring of intracranial lesion expansion, physiological fluctuations, and behavioral stability. We can also overlay and analyze the joint changing trends of vital signs and behavioral patterns to enhance the continuity and objectivity of patient status assessment. By jointly judging short-term compensatory capacity, external interference, and the recovery of consciousness and function, we can strengthen the accuracy of risk identification. We can further introduce a comprehensive assessment method for the rate of change of health status, and enhance the ability to predict the potential for functional recovery. At the same time, by combining the patient's original state trajectory with the difference in intervention response, we can dynamically construct an intervention optimization path, identify unstable areas, and predict potential unstable links, achieve targeted and continuous iteration of the intervention mechanism, and actively avoid nursing risks, thereby ensuring coordination and continuity in the comprehensive management process. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 is a schematic diagram of a comprehensive diagnosis and treatment system for neurosurgery patients provided by an embodiment of the present invention;

[0045] Figure 2 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0047] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0048] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0049] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0050] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0051] The embodiment of the present invention provides a comprehensive diagnosis and treatment system for neurosurgery patients, such as Figure 1-2 The diagram of the comprehensive diagnosis and treatment system for neurosurgery patients shown in the figure includes:

[0052] The multimodal status monitoring module extracts the distribution of intracranial lesions, the range of vital sign fluctuations, and changes in behavioral patterns based on patient imaging data, basic health indicators, and real-time behavioral feedback. It stores and analyzes the expansion trend of abnormal imaging areas in time series, determines the cumulative impact of vital sign fluctuations, identifies the stability distribution of behavioral patterns, and determines the patient's status stability.

[0053] The dynamic trend assessment module analyzes the changing trend of the fluctuation range of physiological indicators based on the stability of the patient's condition, determines the cumulative changes in abnormal behavioral patterns, calculates the frequency of fluctuations in short-term physiological compensation ability, identifies the range of changes in external environmental factors, and obtains the patient's risk status;

[0054] The consciousness function analysis module analyzes the changing trend of brain function compensation ability based on the patient's risk status, identifies the consciousness recovery rate, determines the functional recovery potential, and generates the patient's consciousness function health status;

[0055] The optimized nursing intervention module is based on the patient's consciousness and functional health, extracts the patient's original status records, external influencing factors, and nursing stability indicators, identifies the interval of status stability changes, analyzes the degree of external influence, and obtains a list of improved nursing interventions;

[0056] The nursing risk warning management module is based on the improved nursing intervention list, extracts the patient's current status dynamics, monitors the expansion of intracranial lesions, fluctuations in vital signs, changes in behavioral patterns, analyzes the dynamic fluctuation range of the status, identifies the amplitude of changes in the patient's status stability, judges abnormal changes in nursing, and obtains nursing risk warning indicators.

[0057] The stability of the patient's condition includes the expansion rate of intracranial lesions, the distribution of vital sign fluctuations, the stability of behavioral patterns, and the consistency of the external environment. The patient's risk status includes the amplitude of physiological fluctuations, the cumulative impact of behavioral abnormalities, the frequency of changes in compensatory ability, and the range of external environment fluctuations. The health of the patient's consciousness function includes the brain function compensation ability, the rate of consciousness recovery, and the potential for functional recovery. The improved nursing intervention list includes the state stability range, the degree of external influence, and the risk of nursing implementation. The nursing risk warning indicators include the dynamic fluctuation range of the state, the amplitude of changes in state stability, and abnormal changes in nursing.

[0058] Specifically, if Figure 2 As shown, the multimodal condition monitoring module includes:

[0059] The imaging abnormality analysis submodule extracts the distribution and expansion trend of intracranial lesions based on patient imaging data, basic health indicators, and real-time behavioral feedback. It calculates the volume change of the lesion area and aggregates it to the corresponding time point. It arranges the lesion expansion values ​​in chronological order, determines the fluctuation of lesion expansion, and obtains the intracranial lesion expansion rate.

[0060] Based on patient image data, basic health indicators, and real-time behavior feedback, the patient's brain CT or MRI image is obtained, for example, when patient A is admitted to the hospital, his T1 weighted magnetic resonance image is obtained, and image preprocessing is performed to remove noise and artifacts, and through a deep learning model such as the U-Net model, the preprocessed image data is semantically segmented to identify abnormal regions such as tumors, edema, or hemorrhage, for example, in patient A's T1 weighted image, the model accurately segments the glioma region in the left frontal lobe, with an initial volume of 10.5 cubic centimeters, the patient's basic health indicators are extracted, including age, gender, medical history, blood pressure, blood sugar, etc., for example, patient A, male, 65 years old, with a history of hypertension, blood pressure maintained at 140 / 90 mmHg, and real-time daily behavior feedback data is received, such as sleep time, activity level, language clarity, etc. obtained through wearable devices or sensors, for example, patient A's smartwatch records his daily sleep duration as 6-7 hours, and his average activity level is 3000 steps / day, by comparing multiple consecutive days of image data, for example, patient A's MRI re-examination on the 7th, 14th, and 21st day after admission, the morphological changes of the intracranial lesion region are extracted and tracked, the displacement of the boundary and the distortion of the shape are calculated, for example, the Hausdorff distance or Dice similarity coefficient is calculated to quantify the extent of lesion expansion, and according to the image data of each review, the precise volume of the lesion region is calculated using a three-dimensional reconstruction algorithm, for example, patient A's glioma volume increased to 11.2 cubic centimeters on the 7th day, 12.1 cubic centimeters on the 14th day, and 13.5 cubic centimeters on the 21st day, the volume values are accurately associated with the corresponding image acquisition time points to form time series data, for example, (D1: 10.5 cubic centimeters, D7: 11.2 cubic centimeters, D14: 12.1 cubic centimeters, D21: 13.5 cubic centimeters), then arrange the lesion expansion values in chronological order, for example, for patient A's lesion volume sequence (10.5, 11.2, 12.1, 13.5), calculate the volume change rate between adjacent time points to determine the fluctuation of lesion expansion, for example, the first fluctuation rate is (11.2-10.5) / 10.5=0.066, the second fluctuation rate is (12.1-11.2) / 11.2=0.080, and the third fluctuation rate is (13.5-12.1) / 12.1=0.116, the fluctuation of lesion expansion is quantified by statistical variance or standard deviation, for example, the standard deviation of the above fluctuation rate sequence is calculated to evaluate its stability, finally, the intracranial lesion expansion rate is obtained according to the above calculation results, which reflects the overall growth trend and fluctuation amplitude of the lesion within a certain time period, for example, patient A's intracranial lesion expansion rate is 0.087 (taking the average of the three fluctuation rates), indicating that his intracranial lesion grows an average of 8.7% per week during the observation period.

[0061] The vital signs fluctuation distribution submodule calls the intracranial lesion expansion rate screening time point, extracts vital signs fluctuation data, counts fluctuation categories and proportions, analyzes changes in fluctuation category proportions, and generates vital signs fluctuation category proportion change values;

[0062] Call the intracranial lesion expansion rate to filter time points. For example, the intracranial lesion expansion rate of patient A is 0.087, and specific time points with higher lesion expansion volatility are filtered out based on the expansion rate. For example, the fluctuation threshold of the intracranial lesion expansion rate is set to 0.05. When the volatility exceeds the threshold, the corresponding date is marked as a key time point. The volatility of patient A from D14 to D21 is 0.116, which exceeds 0.05. Therefore, D21 is marked as a key time point. Based on the filtered time points, the patient's corresponding vital sign fluctuation data, including heart rate and respiratory rate, are extracted. , body temperature, blood pressure, blood oxygen saturation, etc. For example, on D21, patient A's heart rate is 95 beats / min, respiratory rate is 22 times / min, body temperature is 38.1℃, blood pressure is 150 / 95mmHg, and blood oxygen saturation is 92%. The vital sign fluctuation data are classified into different fluctuation categories, such as tachycardia (heart rate>100 beats / min), tachypnea (respiratory rate>20 times / min), fever (body temperature>37.5℃), hypertension (systolic blood pressure>140mmHg or diastolic blood pressure>90mmHg), hypoxemia (blood oxygen saturation<95%), and each fluctuation is statistically analyzed. The proportion of fluctuation categories at the screening time point. For example, on D21, patient A showed tachycardia (95 beats / min, although not exceeding 100, but significantly higher than the baseline of 80 beats / min, which was determined to be abnormal), tachypnea, fever and hypertension. If there are a total of 5 vital sign indicators, the proportion of fluctuation categories is: tachycardia 1 / 5 (20%), tachypnea 1 / 5 (20%), fever 1 / 5 (20%), hypertension 1 / 5 (20%), hypoxemia 0 / 5 (0%). Analyze the changing trend of the proportion of fluctuation categories of vital signs at different time points. For example, compare D7 and D1. The proportion of fluctuation categories on D4 and D21, no obvious fluctuation on D7, only a slight increase in blood pressure on D14, and fluctuations in multiple indicators on D21. The change is quantified by calculating the difference in the proportions of different categories. For example, the proportion of fever and shortness of breath increased by 20% on D21 compared with D14. Finally, the change value of the proportion of vital signs fluctuation categories is generated, which reflects the dynamic changes in the patient's vital signs fluctuations. For example, the change value of the vital signs fluctuation category proportion of patient A from D14 to D21 is 0.6 (obtained by weighted summation of the proportions of newly added fluctuation categories).

[0063] The behavior pattern monitoring submodule calls the change value of the vital sign fluctuation category, compares it with the behavior pattern standard, and calculates the proportion of time points when the behavior is abnormal and does not meet the standard to obtain the patient's state stability;

[0064] Call the change value of the proportion of vital sign fluctuation categories. For example, the change value of the proportion of vital sign fluctuation categories received from patient A is 0.6. Based on this change value, compare it with the preset behavioral pattern standard. The standard is formulated by expert consensus and includes quantitative indicators of normal work and rest, language communication, cognitive response, emotional stability, etc. For example, the normal work and rest standard stipulates 7-9 hours of sleep per day, the language communication standard stipulates a speaking speed of 200 words / minute and a vocabulary of 3000, the cognitive response standard stipulates that the reaction time to simple instructions is less than 2 seconds, and the emotional stability standard stipulates that the number of emotional fluctuations per day is less than 3 times. Count the proportion of time points when the patient's abnormal behavior does not meet the standard within a specific time period. For example, if patient A has a total of 10 behaviors during a certain observation period For monitoring points, there are 3 time points with non-standard behaviors such as insufficient sleep (6 hours), slow speech (speech speed 150 words / minute) and slow reaction (reaction time 3 seconds), then the non-standard time points account for 3 / 10 (30%), and the non-standard time points are cumulatively counted and their percentage in the total monitoring time is calculated. For example, if the total monitoring time is 24 hours, of which the abnormal behavior lasts for 8 hours, then the non-standard time points account for 8 / 24 (33.3%). Through the statistical results, the patient's state stability is finally obtained. This stability is a measure of the degree to which the patient's behavior pattern deviates from the normal standard. For example, the state stability of patient A is 0.7 (calculated as 1-the proportion of non-standard time points, that is, 1-0.3=0.7).

[0065] Specifically, if Figure 2 As shown, the dynamic trend evaluation module includes:

[0066] The physiological fluctuation analysis submodule extracts the fluctuation range of physiological indicators based on the stability of the patient's state, analyzes the fluctuation amplitude of each indicator within the continuous time window, screens indicators whose fluctuations exceed the physiological stability threshold, determines the trend of physiological fluctuations, and obtains the physiological fluctuation coefficient;

[0067] Based on the patient's state stability, for example, the state stability of patient A is received as 0.7. According to this stability, the fluctuation range of various physiological indicators of the patient is extracted, including blood sugar, blood lipids, electrolytes, renal function indicators, etc. For example, the fasting blood sugar range of patient A is 5.0-7.0mmol / L, and the total cholesterol range is 3.0-5.2mmol / L. The fluctuation range of each indicator in the continuous time window is analyzed. For example, with 24 hours as the time window, the difference between the maximum and minimum values ​​of patient A's daily fasting blood sugar and the difference between the maximum and minimum values ​​of total cholesterol are calculated. If the fasting blood sugar of patient A fluctuates from 5.5mmol / L to 6.8mmol / L within 24 hours, the fluctuation range is 1.3mmol / L. Then, the indicators whose fluctuations exceed the physiological stability threshold are screened. The physiological stability threshold is set according to clinical guidelines and individual differences. The sugar fluctuation threshold is set at 1.0mmol / L, and the total cholesterol fluctuation threshold is set at 0.5mmol / L. If the fasting blood glucose fluctuation amplitude of patient A is 1.3mmol / L, which exceeds the threshold of 1.0mmol / L, the fasting blood glucose is marked as an abnormal fluctuation indicator. At the same time, the changing trend of the physiological fluctuation is judged. For example, linear regression analysis or moving average method is used to judge whether the blood glucose fluctuation amplitude continues to increase, decrease or remain stable. For example, if the blood glucose fluctuation amplitude is 1.3mmol / L, 1.5mmol / L, and 1.7mmol / L for three consecutive days, it is judged that the fluctuation amplitude is increasing. Finally, the physiological fluctuation coefficient is obtained, which comprehensively reflects the overall fluctuation degree and trend of the patient's physiological indicators. For example, the physiological fluctuation coefficient of patient A is 0.85 (calculated by taking the weighted average of the number of indicators exceeding the threshold and the fluctuation amplitude).

[0068] The behavioral pattern abnormality monitoring submodule calls the physiological fluctuation coefficient, extracts behavioral pattern abnormality records, identifies the number and proportion of abnormal records, determines the abnormal change trend, and obtains the cumulative change rate of behavioral pattern abnormality;

[0069] Call the physiological fluctuation coefficient. For example, if the physiological fluctuation coefficient of patient A is 0.85, based on this coefficient, extract the patient's behavioral pattern abnormality records. The records come from sensor data, medical staff observation records and patient self-reports, including specific events such as abnormal emotions, cognitive impairment, sleep disorders, and reduced activity. For example, the abnormal records of patient A include: D15 irritability 1 time, D16 slow response to commands 2 times, D17 awakening at night 3 times, D18 increased bed rest time 4 hours, identify the number and proportion of abnormal records. For example, in a 24-hour observation period, patient A has a total of 10 behavioral records, of which 4 are abnormal records, then the abnormal records The number of records is 4, accounting for 4 / 10 (40%). The trend of abnormal changes is further judged. For example, by analyzing the changes in the number and proportion of abnormal records in consecutive time periods, if the number of abnormal records in D15 is 1, D16 is 2, D17 is 3, and D18 is 4, it is judged that the number of abnormal records is increasing. The exponential smoothing method can be used to predict the changing trend of abnormal records. Finally, the cumulative change rate of behavioral pattern abnormalities is obtained. This change rate measures the cumulative degree and development trend of the patient's behavioral pattern abnormalities. For example, the cumulative change rate of patient A's behavioral pattern abnormalities is 0.05 (obtained through comprehensive calculation of the changing trend of the number of abnormal records and the proportion).

[0070] The external environmental impact assessment submodule calls the abnormal cumulative change rate of behavioral patterns, extracts external environmental factor data, and calculates the numerical interval and variation range of differentiation factors to obtain the patient's risk status;

[0071] Call the abnormal cumulative change rate of behavioral patterns. For example, if the abnormal cumulative change rate of patient A's behavioral patterns is 0.05, extract the external environmental factor data based on this change rate. The factors include the noise level in the ward, light intensity, number of visitors, changes in nursing staff schedules, medication adjustments, etc. For example, in patient A's ward, the D19 noise level is 60 decibels, the light intensity is 500 lux, there are 2 visitors, and the nursing staff schedule is adjusted. Statistically calculate the numerical range and variation range of the differentiation factor. For example, the normal range of noise level is set at 30-50 decibels. The noise level of 60 decibels in patient A's ward exceeds the normal range, and the variation range is 10 decibels. Bei, the normal range of light intensity is 300-600 lux, and the light intensity of 500 lux in patient A's ward is within the normal range. The impact of each external environmental factor is evaluated by calculating its deviation or volatility. For example, the deviation of the noise level is (60-50) / 50=0.2. Finally, the patient's risk status is obtained, which comprehensively reflects the potential impact of external environmental factors on the patient's condition. For example, the risk status of patient A is 0.6 (obtained by taking a weighted sum of the deviations of various external environmental factors, and the weights are set according to clinical experience, for example, the noise weight is 0.4, the number of visitors weight is 0.3, and the nursing schedule weight is 0.3).

[0072] Specifically, if Figure 2 As shown, the consciousness function analysis module includes:

[0073] The brain function compensation capacity assessment submodule extracts brain function compensation indicators and short-term compensation capacity amounts based on the patient's risk status, identifies the proportion of short-term compensation capacity to total compensation capacity, screens the patient numbers whose short-term compensation ratio exceeds the benchmark value, summarizes the changes in brain function compensation capacity, and obtains the brain function compensation fluctuation rate;

[0074] Based on the patient's risk status, for example, the risk status of patient A is 0.6. Based on this status, brain function compensation indicators and short-term compensation capacity amounts are extracted. Brain function compensation indicators include cognitive reserve, brain network remodeling ability, neural plasticity, etc. The short-term compensation capacity amount is a quantitative value obtained based on the patient's recent cognitive test performance, neuroimaging evidence (such as functional magnetic resonance imaging fMRI) and electroencephalogram (EEG) activity assessment. For example, patient A's cognitive reserve score is 85 points (out of 100 points), fMRI shows that the degree of default mode network remodeling is moderate, and EEG shows that the power of its alpha band has a slight decrease. According to the data, the short-term compensation capacity amount is calculated as 300 units, identifying the proportion of short-term compensation capacity to total compensation. The total compensation capacity is the maximum compensation capacity estimated based on factors such as the patient's age, education level, and baseline cognitive function. For example, patient A The total compensatory capacity is set to 500 units, and the ratio of short-term compensatory capacity to total compensation is 300 / 500=0.6. Patient numbers whose short-term compensatory ratio exceeds the benchmark value are screened. The benchmark value is a normal range derived from statistical analysis of a large amount of clinical data. For example, the benchmark value of the short-term compensatory ratio is set to 0.5. If patient A's short-term compensatory ratio of 0.6 exceeds the benchmark value of 0.5, patient A is marked as having high short-term compensatory capacity. Changes in brain function compensatory capacity are collected. For example, by regularly monitoring and recording the amount and ratio of the patient's short-term compensatory capacity to form time series data, for example, the short-term compensatory capacity amounts of patient A on D7, D14, and D21 after admission are 300, 280, and 260, respectively, and the corresponding ratios are 0.6, 0.56, and 0.52, respectively. The fluctuation rate of brain function compensation is obtained, which reflects the degree of dynamic changes in the patient's brain function compensatory capacity.

[0075] The consciousness recovery rate analysis submodule calls the brain function compensation fluctuation rate, extracts consciousness recovery data, calculates the consciousness recovery cycle and average recovery days, analyzes the changes in consciousness recovery rate, and generates the consciousness recovery change rate;

[0076] The rate of change of consciousness recovery is calculated using the formula:

[0077]

[0078] Among them, R represents the rate of change of consciousness recovery, C i represents the level of consciousness recovered from the i-th data sampling, C i-1 represents the level of consciousness of the i-1th data sampling recovery, n represents the total number of data sampling, V represents the volatility of the recovered data, and T represents the recovery period;

[0079] The brain function compensation fluctuation rate is called. For example, the brain function compensation fluctuation rate of patient A is 0.08. Based on this fluctuation rate, the consciousness recovery data is extracted. The data includes the Glasgow Coma Scale (GCS) score, the Mini-Mental State Examination (MMSE) score, the pupil light reflex, the limb movement reaction, etc. For example, the consciousness recovery data of patient A in three consecutive samplings are as follows: the GCS score increased from 10 points to 12 points, the MMSE score increased from 18 points to 22 points, and the pupil light reflex changed from dull to sensitive. The system calculates the consciousness recovery cycle and the average recovery days, the consciousness recovery cycle It is the length of time from the onset of consciousness disorder to the recovery of consciousness to the baseline level or a preset level. The average number of recovery days is calculated based on historical data and the patient's specific situation. For example, the consciousness recovery period of patient A is 21 days, and the average number of recovery days is 18 days. The changes in the consciousness recovery rate are analyzed and the recovery rate is judged by comparing the change in the consciousness level at different time points. For example, patient A's GCS score increased by 2 points from D7 to D14, and the GCS score increased by 2 points from D14 to D21. The consciousness recovery change rate is generated, which quantifies the volatility and instability of the consciousness recovery process.

[0080] The calculation formula for the consciousness recovery change rate R is:

[0081] Among them, R represents the rate of change of consciousness recovery, which is an indicator to measure the volatility of the patient's consciousness recovery process;

[0082] C i represents the level of consciousness recovered at the i-th data sampling, such as the Glasgow Coma Scale (GCS) score;

[0083] C i-1 represents the level of consciousness recovered from the i-1th data sampling;

[0084] n represents the total number of data sampling times, indicating the total number of times the level of consciousness sampling was performed;

[0085] V represents the volatility of the recovery data, which is used to measure the degree of dispersion of the consciousness recovery data itself. For example, it can be obtained by calculating the average of the squared differences between each consciousness level sampling value and the average value;

[0086] T stands for recovery period, which is the total time it takes for consciousness to recover;

[0087] The operational logic of this formula is to first calculate the sum of the absolute values ​​of the changes in the level of consciousness within each sampling interval, and then divide it by the total number of sampling times to obtain the average change in the level of consciousness per sampling, which partially reflects the average degree of change in consciousness recovery; then, The correction term adjusts the average change, where V represents the volatility of the recovery data, calculated as the square of the standard deviation of the consciousness level sampling values. For example, if Patient A's GCS scores in three samplings were 10, 12, and 14, respectively, the average GCS score was 12, the differences between each sampling value and the average were -2, 0, and 2, and the squared differences were 4, 0, and 4, respectively. Then V = (4 + 0 + 4) / 3 = 8 / 3 ≈ 2.67; T represents the recovery period. For example, Patient A's recovery period was 21 days. The +1 in the correction term is to avoid a denominator of zero or too small, resulting in meaningless results, and to ensure that the correction term is always greater than 1, thereby increasing the R value when the recovery data fluctuates greatly or the recovery period is short, and decreasing the R value otherwise. The purpose of this correction term is to combine the change in consciousness level with the volatility and time factors in the recovery process, so that the final consciousness recovery change rate can more comprehensively reflect the complexity of consciousness recovery.

[0088] The benefit of this formula is that, by introducing the volatility of recovery data and the recovery period as correction factors, the assessment of the rate of consciousness recovery is no longer limited to simple changes in the level of consciousness, but more comprehensively considers the instability and time-consuming nature of the recovery process, thereby enabling a more accurate assessment of the patient's consciousness function health within the overall system.

[0089] Now, let's use the actual data of patient A for calculation. Assume that patient A's level of consciousness (GCS score) in three data samplings is C1 = 10, C2 = 12, C3 = 14, and the total number of data samplings is n = 3. The volatility V of the recovered data is: First, calculate the average GCS score:

[0090] (10+12+14) / 3=12;

[0091]

[0092] Recovery period T = 21 days, substitute into the formula for calculation:

[0093]

[0094] The results show that the consciousness recovery change rate of patient A is 1.41, which is a relatively high change rate, indicating that there is a certain degree of volatility or instability in the patient's consciousness recovery process. This numerical result will be used as an input parameter of the subsequent functional recovery potential calculation submodule to comprehensively evaluate the patient's consciousness function health.

[0095] The functional recovery potential calculation submodule calls the consciousness recovery change rate, evaluates the functional recovery data, identifies the functional recovery interval and recovery ratio, analyzes the functional recovery trend, and obtains the patient's consciousness function health;

[0096] Call the consciousness recovery change rate. For example, if the consciousness recovery change rate of patient A is 1.41, evaluate the functional recovery data based on this change rate. The data include muscle strength recovery, limb mobility, daily living activities (ADL) ability score, cognitive function (such as memory, attention) test results, etc. For example, the muscle strength score of patient A is level 4 for the left limb and level 3 for the right limb. The ADL score increases from 30 to 50 points, and the memory test score increases from 60 to 75 points. Identify the functional recovery interval and recovery ratio. The functional recovery interval is set according to the patient's baseline level and the expected optimal recovery state. The recovery ratio is the ratio between the current recovery level and the maximum recovery potential. For example, if the maximum recovery potential of patient A is 1 00 points, and currently recovered to 50 points, then the recovery ratio is 50 / 100=0.5. Analyze the functional recovery trend. By comparing the functional recovery data at consecutive time points, determine whether it is showing a trend of continuous improvement, stagnation or deterioration. For example, if patient A's ADL score is 30, 40, and 50 for three consecutive weeks, it is judged to be a trend of continuous improvement. Time series analysis methods, such as the ARIMA model, can be used to predict the functional recovery trend. Finally, the patient's consciousness function health is obtained, which comprehensively reflects the patient's current overall level of consciousness and functional recovery as well as future recovery potential. For example, patient A's consciousness function health is 0.75 (calculated by taking the weighted average of the functional recovery ratio, trend, and consciousness recovery change rate).

[0097] Specifically, if Figure 2 As shown, the optimized nursing intervention module includes:

[0098] The consciousness function health assessment submodule extracts brain function compensation data, consciousness recovery data, and function recovery data based on the patient's consciousness function health, calculates the compensation ability index, recovery rate, and recovery potential, and obtains the patient's consciousness function health index;

[0099] Based on the patient's consciousness function health, for example, the consciousness function health of patient A is received as 0.75. Based on this health, brain function compensation data, consciousness recovery data and functional recovery data are extracted. For example, the brain function compensation data shows that the short-term compensation ratio of patient A is 0.6, the consciousness recovery data shows that the GCS score of patient A is 14 points at D21, and the functional recovery data shows that the ADL score of patient A is 50 points. The compensation ability index, recovery rate and recovery potential are calculated. The compensation ability index is a quantitative indicator calculated based on the brain function compensation data. For example, the compensation ability index The recovery rate is 0.8 (the weighted value of the short-term compensation ratio), the recovery rate is calculated based on the consciousness recovery data, for example, the recovery rate is an increase of 2 points in the GCS score every 7 days, and the recovery potential is calculated based on the functional recovery data, for example, the recovery potential is an increase in the ADL score to 80 points. The patient's consciousness function health index is obtained, which comprehensively evaluates the patient's comprehensive health level in consciousness, brain function compensation and functional recovery. For example, the consciousness function health index of patient A is 0.78 (calculated by taking the weighted average of the compensation ability index, recovery rate and recovery potential).

[0100] The state stability analysis submodule extracts the patient's original state record based on the patient's consciousness function health index, determines whether the state deviation exceeds the state deviation threshold, analyzes the state change trend, and obtains the state stability change range;

[0101] Based on the patient's consciousness function health index, for example, the consciousness function health index of patient A is received as 0.78. Based on this index, the patient's original status record is extracted, which includes daily vital signs, imaging examination results, behavioral observations, medication status, etc. For example, the original status record of patient A shows that his blood pressure fluctuation range is 130-150 / 85-95 mmHg, the monthly growth rate of intracranial lesion volume is 8.7%, and the daily sleep duration is 6-7 hours. It is judged whether the state deviation exceeds the state deviation threshold. The state deviation threshold is set according to clinical standards and individual baselines. For example, the blood pressure fluctuation threshold is 20 mmHg systolic pressure and 10 mmHg diastolic pressure, the monthly growth rate threshold of intracranial lesions is 10%, and the daily sleep duration threshold is less than 6 hours or more than 9 hours. If patient A's blood pressure fluctuation range is 130-150 / 85-95 mmHg, the systolic blood pressure fluctuation of 20 mmHg reaches the threshold, the monthly growth rate of intracranial lesions is 8.7% which does not exceed the threshold of 10%, and the daily sleep duration is 6-7 hours which does not exceed the threshold, then only the blood pressure is marked as having a state deviation, and the state change trend is analyzed by evaluating the accumulation and change direction of the state deviation in consecutive time periods. For example, if patient A's blood pressure deviation persists for three consecutive days, it is judged that the blood pressure fluctuation persists, and the state stability change interval is obtained. This interval describes the range and stability level of the patient's state fluctuation. For example, the state stability change interval of patient A is [0.70, 0.80], indicating that his state fluctuates within a certain range, but remains relatively stable overall.

[0102] The nursing implementation risk judgment submodule captures external environment fluctuation data and nursing impact data based on the state stability change interval, calculates the external environment fluctuation rate, analyzes the nursing implementation stability, screens patients whose nursing risks exceed the benchmark threshold, and obtains a list of improved nursing interventions;

[0103] The external environment volatility adopts the formula:

[0104]

[0105] Among them, E represents the volatility of the external environment, m represents the total number of samples, and P k Represents the external environment value of the kth sample, P avg Represents the average value of the external environment;

[0106] According to the state stability change interval, for example, the state stability change interval of patient A is received as [0.70, 0.80]. Based on this interval, the external environment fluctuation data and nursing impact data are captured. The external environment fluctuation data includes ward temperature, humidity, noise, light, etc. For example, the ward temperature is 25℃, the humidity is 60%, the noise is 50 decibels, and the light is 400 lux. The nursing impact data includes the frequency of nursing staff handover, nursing operation standardization, medication compliance, patient satisfaction, etc. For example, the nursing staff hands over twice a day, and the nursing operation standardization score is 95 points. The external environment fluctuation rate is calculated. The calculation formula of the external environment fluctuation rate E is: Where E represents the external environment volatility, which quantifies the degree of dispersion of external environmental factors; m represents the total number of samples, that is, the total number of monitored external environment data points; P k represents the external environment value of the kth sample, such as the noise decibel number at a certain moment; P avg Represents the average value of the external environment;

[0107] The operational logic of this formula is to first calculate the difference between the sample value and the average value of each external environmental factor and square it, in order to eliminate the positive and negative influences and highlight the larger deviations; then sum all the square differences to obtain the total degree of dispersion; finally divide it by the total number of samples and take the square root to obtain the standard deviation, thereby quantifying the degree of fluctuation of the external environment. This formula is essentially calculating the standard deviation of the external environmental data. The larger the standard deviation, the greater the environmental fluctuation and the greater the potential impact on the status. The benefit of the formula is that by quantitatively evaluating the fluctuations of external environmental factors, it can accurately identify environmental factors that have a negative impact on patient care, thereby guiding the adjustment of nursing interventions in the overall system and improving the accuracy and safety of nursing implementation;

[0108] Now, let's use the noise data from the patient's ward environment for calculation. Suppose that in one day, the noise in Patient A's ward is sampled five times, and the measured noise values ​​(in decibels) are P1 = 50, P2 = 55, P3 = 45, P4 = 60, and P5 = 50. The total number of samples, m, is 5.

[0109] First calculate the average value P of the noise value avg :P avg =(50+55+45+60+50) / 5=52dB, substitute into the formula for calculation:

[0110]

[0111] The results show that the external environment (noise) fluctuation rate of patient A's ward is 5.10 decibels, which means that there is a certain fluctuation in the noise level, which affects the patient. Based on this external environment fluctuation rate, for example, if the noise fluctuation rate is higher than 5 decibels, it is judged to be a high-fluctuation environment. The stability of nursing implementation is analyzed by evaluating the standardization, timeliness and patient compliance of nursing operations. For example, if the nursing operation standardization score is continuously lower than 90 points and the medication compliance is lower than 80%, the nursing implementation stability is judged to be low. Patients whose nursing risks exceed the benchmark threshold are screened. The nursing risk benchmark threshold is set based on clinical experience and safety standards. For example, when the external environment fluctuation rate is higher than 5 decibels and the nursing implementation stability is lower than 85%, the patient is marked as having a high nursing risk, and a list of improved nursing interventions is obtained. The list lists the patients who need targeted nursing intervention adjustments. For example, patient A is included in the improved nursing intervention list and needs to strengthen environmental noise control and optimize medication management.

[0112] Specifically, if Figure 2 As shown, the nursing risk early warning management module includes:

[0113] The dynamic status monitoring submodule monitors the expansion of intracranial lesions, fluctuations in vital signs, and changes in behavioral patterns based on the improved nursing intervention list. It identifies delayed lesion expansion, abnormal vital signs, and changes in behavioral patterns, and determines the dynamic status fluctuation range.

[0114] Based on the improved nursing intervention list, for example, patient A is identified as being included in the improved nursing intervention list. Based on this list, the expansion of intracranial lesions, fluctuations in vital signs, and changes in behavioral patterns are continuously monitored. For example, brain imaging data of patient A is automatically obtained every 24 hours, and vital signs such as heart rate, blood pressure, and body temperature are monitored every hour. In addition, behavioral data such as sleep, activity, and communication are collected in real time to identify delayed lesion expansion, abnormal vital signs, and changes in behavioral patterns. For example, by comparing with historical data, it was found that the expansion of patient A's intracranial lesions decreased from 0.087 to 0.035 in the past week. , the frequency of vital sign fluctuations is reduced from 10 abnormal events per day to 2 abnormal events per day, and the number of night awakenings in behavioral patterns is reduced from 3 times per day to 1 time per day. Trend analysis algorithms, such as Kalman filtering, can be used to track and predict dynamic changes in real time. Finally, the dynamic fluctuation range of the state is obtained, which describes the fluctuation amplitude and stability of the patient's current state. For example, the dynamic fluctuation range of the state of patient A is: intracranial lesion expansion rate [0.03, 0.04], abnormal vital sign events [1, 3] times / day, and behavioral pattern changes (night awakenings) [0, 1] times / day.

[0115] The state fluctuation analysis submodule analyzes the patient's state change trend based on the dynamic state fluctuation range, screens patients with lesion expansion fluctuations, abnormal vital signs, and decreased behavioral patterns, determines the degree of state stability change, identifies state persistence and abnormal concentration intervals, and obtains the amplitude of the patient's state stability change;

[0116] Based on the dynamic fluctuation range of the state, for example, the dynamic fluctuation range of the state of patient A is received as the intracranial lesion expansion rate [0.03, 0.04], abnormal vital sign events [1, 3] times / day, and behavioral pattern changes (night awakenings) [0, 1] times / day. According to this fluctuation range, the patient's state change trend is analyzed, and the direction and amplitude of the change of each indicator in the continuous time window are evaluated. For example, if the intracranial lesion expansion rate of patient A continues to be stable between 0.03-0.04, the frequency of abnormal vital sign events continues to decrease, and the number of night awakenings continues to decrease, the moving average method can be used to smooth the state change trend and screen patients with lesion expansion fluctuations, abnormal vital signs and decreased behavioral patterns. For example, if the intracranial lesion expansion rate of patient A exceeds the threshold of 0.05, or If abnormal vital sign events occur more than three times in three consecutive days, or the number of nighttime awakenings in the behavioral pattern exceeds one time for three consecutive days, the patient will be marked as a patient with state fluctuations. The degree of change in state stability is determined by calculating the deviation between the fluctuation amplitude of each indicator and the baseline level. For example, if the abnormal vital sign events of patient A drop from 5 times a day to 2 times a day, the degree of change is 3 times. The persistence of the state and the concentration interval of abnormalities are identified. For example, it is found that the abnormal vital sign events of patient A are more concentrated between 8 and 10 am every day and last for a week. Finally, the amplitude of the patient's state stability change is obtained, which quantifies the degree to which the patient's state deviates from the stable level. For example, the amplitude of the state stability change of patient A is 0.15 (calculated by taking the weighted average of the fluctuation amplitudes of various state indicators).

[0117] The nursing abnormality judgment submodule detects the frequency of nursing changes, implementation deviations, and patient records based on the fluctuation range of patient status stability, screens patients with unstable nursing implementation, and obtains nursing risk warning indicators;

[0118] According to the fluctuation range of patient status stability, for example, the fluctuation range of patient A's status stability is 0.15. Based on this range, the frequency of nursing changes, implementation deviations and patient records are detected. The frequency of nursing changes refers to the number of times the nursing plan or operation is adjusted. For example, the nursing plan of patient A has been adjusted twice in the past week. The implementation deviation refers to the degree of deviation of the nursing operation from the standard process. For example, the standardization score of a certain medication operation is 80 points (out of 100 points). The patient record includes the patient's satisfaction feedback on the nursing service, the occurrence of complications, etc. For example, the satisfaction score of patient A for the nursing service is 8 points (out of 10 points). Screen patients with unstable nursing implementation and unstable nursing implementation. The judgment criteria are set comprehensively based on factors such as the frequency of nursing changes, implementation deviations and patient records. For example, if the frequency of nursing changes exceeds 1 time per week, or the implementation deviation rate is lower than 90%, or the patient satisfaction score is lower than 7 points, the patient is marked as unstable nursing implementation. The decision tree algorithm can be used to classify nursing anomalies. Finally, a nursing risk warning index is obtained, which comprehensively reflects the potential risks in nursing implementation. For example, the nursing risk warning index of patient A is 0.4 (calculated by taking a weighted average of the frequency of nursing changes, implementation deviations and patient records, where the weight of implementation deviations is 0.5, the weight of nursing change frequency is 0.3, and the weight of patient records is 0.2).

[0119] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A comprehensive diagnosis and treatment system for neurosurgery patients, characterized by: The system comprises: The multimodal status monitoring module extracts the distribution of intracranial lesions, the range of vital sign fluctuations, and changes in behavioral patterns based on patient imaging data, basic health indicators, and real-time behavioral feedback. It stores and analyzes the expansion trend of abnormal imaging areas in time series, determines the cumulative impact of vital sign fluctuations, identifies the stability distribution of behavioral patterns, and determines the patient's status stability. The dynamic trend assessment module analyzes the changing trend of the fluctuation range of physiological indicators based on the stability of the patient's state, determines the cumulative changes in abnormal behavioral patterns, counts the fluctuation frequency of short-term physiological compensation ability, identifies the range of changes in external environmental factors, and obtains the patient's risk status; The consciousness function analysis module analyzes the changing trend of brain function compensation ability based on the patient's risk status, identifies the consciousness recovery rate, determines the functional recovery potential, and generates the patient's consciousness function health status; The optimized nursing intervention module extracts the patient's original status record, external influencing factors, and nursing stability indicators based on the patient's consciousness function health, identifies the status stability change interval, analyzes the degree of external influence, and obtains an improved nursing intervention list.

2. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 1, characterized in that: The patient's state stability includes the expansion rate of intracranial lesions, the distribution of vital sign fluctuations, the stability of behavioral patterns, and the consistency of the external environment. The patient's risk status includes the amplitude of physiological fluctuations, the cumulative impact of behavioral abnormalities, the frequency of changes in compensatory ability, and the range of external environment fluctuations. The patient's consciousness function health includes brain function compensation ability, consciousness recovery rate, and functional recovery potential. The improved nursing intervention list includes the state stability range, the degree of external influence, and the risk of nursing implementation.

3. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 1, characterized in that: The multimodal status monitoring module includes: The imaging abnormality analysis submodule extracts the distribution and expansion trend of intracranial lesions based on patient imaging data, basic health indicators, and real-time behavioral feedback. It calculates the volume change of the lesion area and aggregates it to the corresponding time point. It arranges the lesion expansion values ​​in chronological order, determines the fluctuation of lesion expansion, and obtains the intracranial lesion expansion rate. The vital sign fluctuation distribution submodule calls the intracranial lesion expansion rate screening time point, extracts vital sign fluctuation data, counts fluctuation categories and proportions, analyzes changes in fluctuation category proportions, and generates vital sign fluctuation category proportion change values; The behavior pattern monitoring submodule calls the change value of the vital sign fluctuation category proportion, compares it with the behavior pattern standard, and calculates the proportion of time points when the behavior is abnormal and does not meet the standard to obtain the patient's state stability.

4. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 3, characterized in that: The dynamic trend assessment module includes: The physiological fluctuation analysis submodule extracts the fluctuation range of physiological indicators based on the patient's state stability, analyzes the fluctuation amplitude of each indicator within the continuous time window, screens indicators whose fluctuations exceed the physiological stability threshold, determines the trend of physiological fluctuations, and obtains the physiological fluctuation coefficient; The behavior pattern abnormality monitoring submodule calls the physiological fluctuation coefficient, extracts behavior pattern abnormality records, identifies the number and proportion of abnormal records, determines the abnormal change trend, and obtains the cumulative change rate of behavior pattern abnormality; The external environment impact assessment submodule calls the abnormal cumulative change rate of the behavioral pattern, extracts the external environment factor data, and calculates the numerical interval and variation range of the differentiation factor to obtain the patient's risk status.

5. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 4, characterized in that: The consciousness function analysis module includes: The brain function compensation capacity assessment submodule extracts brain function compensation indicators and short-term compensation capacity amounts based on the patient's risk status, identifies the proportion of short-term compensation capacity to total compensation, screens the patient numbers whose short-term compensation ratio exceeds the benchmark value, summarizes the changes in brain function compensation capacity, and obtains the brain function compensation fluctuation rate; The consciousness recovery rate analysis submodule calls the brain function compensation fluctuation rate, extracts consciousness recovery data, calculates the consciousness recovery cycle and average recovery days, analyzes the changes in consciousness recovery rate, and generates a consciousness recovery change rate; The functional recovery potential calculation submodule calls the consciousness recovery change rate, evaluates the functional recovery data, identifies the functional recovery interval and recovery ratio, analyzes the functional recovery trend, and obtains the patient's consciousness function health.

6. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 5, characterized in that: The consciousness recovery change rate adopts the formula: Among them, R represents the rate of change of consciousness recovery, C i represents the level of consciousness recovered from the i-th data sampling, C i-1 represents the level of consciousness of the i-1th data sampling recovery, n represents the total number of data sampling, V represents the volatility of the recovered data, and T represents the recovery period.

7. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 5, characterized in that: The optimized nursing intervention module includes: The consciousness function health assessment submodule extracts brain function compensation data, consciousness recovery data, and function recovery data based on the patient's consciousness function health, calculates the compensation ability index, recovery rate, and recovery potential, and obtains the patient's consciousness function health index; The state stability analysis submodule extracts the patient's original state record based on the patient's consciousness function health index, determines whether the state deviation exceeds the state deviation threshold, analyzes the state change trend, and obtains the state stability change interval; The nursing implementation risk judgment submodule captures external environment fluctuation data and nursing impact data according to the state stability change interval, calculates the external environment fluctuation rate, analyzes the nursing implementation stability, screens patients whose nursing risks exceed the benchmark threshold, and obtains a list of improved nursing interventions.

8. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 7, characterized in that: The external environment volatility is expressed as follows: Among them, E represents the volatility of the external environment, m represents the total number of samples, and P k Represents the external environment value of the kth sample, P avg Represents the average value of the external environment.

9. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 1, characterized in that: The system also includes a nursing risk early warning management module: The nursing risk warning management module extracts the patient's current status dynamics based on the improved nursing intervention list, monitors the expansion of intracranial lesions, fluctuations in vital signs, and changes in behavioral patterns, analyzes the range of dynamic status fluctuations, identifies the amplitude of changes in patient status stability, determines abnormal changes in nursing care, and obtains nursing risk warning indicators; The nursing risk warning indicators include the dynamic fluctuation range of the state, the variation range of the state stability, and abnormal changes in nursing.

10. The comprehensive diagnosis and treatment system for neurosurgery patients according to claim 9, characterized in that: The nursing risk early warning management module includes: The dynamic state monitoring submodule monitors the expansion of intracranial lesions, fluctuations in vital signs, and changes in behavioral patterns based on the improved nursing intervention list, identifies delayed lesion expansion, abnormal vital signs, and changes in behavioral patterns, and obtains the dynamic state fluctuation range; The state fluctuation analysis submodule analyzes the patient's state change trend based on the dynamic state fluctuation range, screens patients with lesion expansion fluctuations, abnormal vital signs, and decreased behavioral patterns, determines the degree of state stability change, identifies state persistence and abnormal concentration intervals, and obtains the amplitude of the patient's state stability change; The nursing abnormality judgment submodule detects the nursing change frequency, implementation deviation and patient records according to the fluctuation range of the patient's state stability, screens patients with unstable nursing implementation, and obtains nursing risk warning indicators.

Images