Intelligent monitoring system and method for nursing of critically ill patients

Abstract

The present invention discloses an intelligent monitoring system and method for the care of critically ill patients, and relates to the field of intelligent monitoring technology; a multi-sensor system is used to collect the patient's physiological data and activity data in real time, and an initial health record of the patient is established; based on the collected physiological data and activity data, the patient's daily activities and behavior patterns are analyzed to establish an individualized health baseline; the patient's physiological data and activity data are monitored in real time, abnormal trends are identified, and early warning signals are generated; nursing measures are preferentially allocated according to the patient's status; the effectiveness of nursing measures is evaluated, and the monitoring strategy is readjusted if the expected nursing effect is not achieved; the present invention conducts comprehensive and real-time monitoring and accurate analysis of the patient's health status, so as to timely discover and intervene when abnormalities occur, ensure that the patient can receive timely care and treatment, reduce the waste of nursing resources and nursing errors, and improve the treatment effect and nursing quality of critically ill patients.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, in particular to an intelligent monitoring system and method for critically ill patient care. Background Art

[0002] In recent years, with the rapid development of medical technology, the field of critical care has gradually shifted from traditional manual monitoring and nursing models to intelligent and automated directions; traditional critical care relies on the experience and real-time monitoring of nursing staff, but with the increase in the number of patients and the shortage of medical resources, the traditional model has many limitations; existing monitoring equipment can usually only provide monitoring within a specific parameter range, and cannot comprehensively evaluate the patient's multi-dimensional health status in real time; moreover, most systems can only monitor the patient's physiological data (such as heart rate, blood pressure, body temperature, etc.), but lack effective collection and analysis of the patient's behavioral data (such as activity frequency, rest status, etc.).

[0003] Despite this, the existing technology still has some shortcomings in the intelligent monitoring of critically ill patients' care; first, the abnormal detection mechanism of most intelligent monitoring systems is mainly based on physiological data, and lacks sufficient consideration of patients' behavior patterns, resulting in insufficient comprehensiveness of monitoring; second, the existing system still lags behind in the dynamic adjustment of personalized care plans, and is unable to optimize care measures in real time according to changes in patient status, making it difficult to cope with complex and changeable clinical situations; in addition, the existing technology's evaluation of the effectiveness of nursing measures is also relatively simple, and lacks a comprehensive feedback mechanism based on multi-dimensional data (such as physiological data, behavioral data, etc.), resulting in inaccurate evaluation of nursing effectiveness, which affects the improvement of nursing quality. Summary of the invention

[0004] In view of the problems existing in the above-mentioned background technology, the present invention proposes an intelligent monitoring system and method for the care of critically ill patients.

[0005] Therefore, the problem to be solved by the present invention is how to solve the problems in the prior art of incomplete nursing monitoring, unintelligent allocation of nursing resources, and delayed evaluation of nursing effects.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent monitoring method for critically ill patient care, which comprises: step S1: using a multi-sensor system to collect the patient's physiological data and activity data in real time, and establishing the patient's initial health record;

[0008] Step S2: Based on the collected physiological data and activity data, the dynamic time warping algorithm is used to extract the patient's behavioral characteristics, and the patient's activity pattern characteristics are grouped through the K-means clustering algorithm. The health baseline categories are divided according to the patient's physiological state and behavioral characteristics. For each category, the patient's daily activities and behavior patterns are analyzed to establish an individualized health baseline;

[0009] Step S3: Monitor the patient's physiological data and activity data in real time, use time series analysis methods to identify deviations from abnormal trends in physiological parameters, calculate the degree of deviation from the baseline, generate early warning signals, and prioritize nursing measures based on the patient's status;

[0010] Step S4: Evaluate the effectiveness of nursing measures to determine whether the expected nursing effect is achieved. If the expected nursing effect is not achieved, readjust the monitoring strategy.

[0011] As a preferred solution of the intelligent monitoring method for critically ill patient care described in the present invention, the specific implementation process of step S1 includes: starting the patient monitoring equipment to collect health data of critically ill patients in real time, the health data including physiological data and activity data, the patient monitoring equipment including an electrocardiogram sensor, a body temperature sensor, a respiratory monitoring sensor and a blood oxygen sensor, these data cover the patient's vital signs and basic behaviors (such as turning over, body movement frequency, etc.), ensuring that the patient's health status is fully captured.

[0012] Based on the physiological data and the activity data collected in real time, an individualized initial health record is established for the patient, and the individualized initial health record records the patient's current physiological parameter baseline and behavioral pattern characteristics; according to the patient's health record, the monitoring thresholds of various physiological indicators (such as the upper and lower limits of heart rate, blood oxygen saturation warning value, etc.) are preliminarily set to provide a reference standard for subsequent dynamic monitoring.

[0013] As a preferred solution of the intelligent monitoring method for critically ill patient care described in the present invention, the specific implementation process of step S2 includes: based on the physiological data and the activity data collected in real time, a dynamic time warping algorithm is used to extract the patient's behavioral characteristics, such as activity pattern changes, frequency, duration, etc., to form a basic feature set of behavioral data.

[0014] The K-means clustering algorithm is used to group the activity pattern characteristics of patients and divide them into multiple health benchmark categories based on their physiological status and behavioral characteristics. For each category, an individualized health baseline is established, including the normal fluctuation range of physiological data and typical activity behavior patterns. This baseline can reflect the patient's long-term health trends and normal behaviors.

[0015] Based on the patient's daily behavior and physiological data, time series analysis methods (such as hidden Markov model, HMM) are used to model the evolution of the patient's behavior pattern and automatically identify the changing trend of the behavior pattern; for example, identify the patient's transition from normal activity mode to rest state, or sudden abnormal behavior pattern; by comparing historical data with current data, update the health baseline, and monitor in real time whether there is a significant deviation.

[0016] As a preferred solution of the intelligent monitoring method for critically ill patients' care of the present invention, the specific implementation process of step S2 also includes: combining the patient's historical health records and the dynamic behavior pattern evolution results, intelligently adjusting the parameters and thresholds of the individualized health baseline, as follows: ;in, represents the health baseline after the i-th adjustment, represents the i-1th adjusted health baseline, Indicates the latest health data, Indicates the preset adjustment factor; ;in, represents the health threshold after the i-th adjustment, represents the initial health threshold, Indicates the change in health status, Represents preset influencing factors; for example, dynamically adjusts the monitoring thresholds of activity frequency, heart rate or respiratory rate based on changes in patient behavior patterns; continuously optimizes the anomaly detection model through machine learning algorithms such as random forests or support vector machines to more accurately identify individualized abnormal trends.

[0017] After successfully building an individualized health baseline, the baseline will be applied to daily patient monitoring and prepared to provide a reference for subsequent abnormality detection. At this time, the system will monitor the patient's physiological data and behavioral patterns based on the new health baseline, generate early warning signals when significant deviations occur, and automatically allocate nursing resources.

[0018] As a preferred solution of the intelligent monitoring method for critically ill patient care described in the present invention, the specific implementation process of step S3 includes: based on the individualized health baseline established above, real-time collection of the patient's physiological data (such as heart rate, blood pressure, body temperature, etc.) and activity data (such as activity frequency, limb movements, etc.); through the data transmission and processing system, ensuring that the collected data is synchronized with the baseline data in real time, providing instant data support for abnormality identification.

[0019] The real-time collected patient data is compared with the individual health baseline, and time series analysis methods (such as sliding windows) are used to identify deviations from abnormal trends in physiological parameters; for short-term physiological fluctuations (such as rapid changes in heart rate or abnormal breathing rate), the system will calculate the degree of deviation from the baseline and mark it as a potential abnormality when the deviation exceeds the preset threshold, as follows: ;in, represents the abnormal trend value at time point t, w represents the window size, represents the physiological data collected at time point a, and T represents the current time point;

[0020] Preset abnormal trend threshold , if the abnormal trend value at time point t , it is determined that an abnormality has occurred.

[0021] The degree of deviation is calculated as follows: ;in, represents the deviation measure at time t, Indicates the physiological data monitored in real time. represents the baseline value at time t, that is, the normal range or expected value calculated based on the patient's historical data and health records.

[0022] As a preferred solution of the intelligent monitoring method for critically ill patient care described in the present invention, the specific implementation process of step S3 also includes: when the system detects that the real-time data deviates significantly from the healthy baseline, especially the sudden changes in physiological data or behavioral patterns (such as a sharp increase in heart rate or a sudden cessation of activity by the patient), the system will automatically trigger an early warning signal; the early warning level is automatically adjusted according to the degree of deviation (such as a slight deviation is a low-level warning, and a sharp fluctuation is a high-risk warning), and is displayed in real time on the nursing staff terminal.

[0023] When the warning signal is triggered, nursing resources and nursing measures are automatically allocated according to the warning level, as follows:

[0024] Construct the warning level formula, the formula is as follows: ;in, represents the warning level at time t, It is a weighting factor based on deviation and abnormal trend.

[0025] when When the emergency occurs, it is recorded as a low-level warning, regular nursing staff are assigned, no additional equipment is required, and the nursing measures are routine care.

[0026] when It is recorded as an intermediate warning, and nursing staff is increased and monitoring equipment is activated. The nursing measures are close observation and collaboration with doctors.

[0027] when When an emergency occurs, it is recorded as a high-level warning, a large amount of nursing resources are allocated, emergency equipment is activated, and the nursing measures are emergency intervention, immediate response, and real-time communication.

[0028] As a preferred solution of the intelligent monitoring method for critically ill patients' care of the present invention, the specific implementation process of step S4 includes: the system will track the implementation effect of the nursing measures in real time, and evaluate the effectiveness of the nursing measures by comparing the changes in the patient's physiological data (such as heart rate, blood pressure, oxygen saturation, etc.) and activity data (such as activity frequency, limb activity, etc.) before and after receiving care, as follows:

[0029] Calculate the changes in physiological data using the following formula: ;in, Indicates the change value of physiological data before and after care, and Represent the physiological data before and after care, respectively.

[0030] Calculate the activity data change, the calculation formula is: ;in, Indicates the change value of activity data before and after care, and Represents the activity data after and before care, respectively.

[0031] Based on the change value of physiological data before and after care Changes in activity data before and after care , calculate the comprehensive evaluation index, the calculation formula is as follows: ;in, represents the comprehensive evaluation index, and Respectively represent the change values ​​of physiological data before and after care Changes in activity data before and after care The weight coefficient of .

[0032] Based on the automatic evaluation results of nursing effectiveness, the system will adjust the nursing strategy according to data feedback; if the effect of a certain nursing measure does not meet expectations (such as body temperature cannot be effectively controlled or blood oxygen level fails to recover), the system will automatically recommend or adjust the nursing measures, such as adjusting drug dosage, changing nursing methods or adjusting monitoring frequency.

[0033] Through continuous monitoring and care feedback, the system will optimize individualized care plans based on the latest patient data and care measure evaluation results; data feedback after each care will update the patient's health record, forming a continuously improving care cycle and providing an optimization basis for the next monitoring and care.

[0034] In the second aspect, the present invention provides an intelligent monitoring system for critically ill patient care, which includes a multi-sensor data acquisition module for real-time acquisition of patient physiological data and activity data, and establishment of the patient's initial health record; an individualized health baseline generation module, which analyzes the patient's daily activities and behavior patterns based on the collected multi-dimensional data, establishes an individualized health baseline, and provides a reference for subsequent abnormality detection; a real-time abnormality monitoring module, which monitors the patient's physiological data and behavioral data in real time, identifies abnormal trends through baseline comparison, and instantly generates early warning signals; in the case of early warning, nursing resources are preferentially allocated according to the patient's status, the required nursing measures are implemented, and the nursing operations are fed back to the system in real time for tracking; a nursing effect evaluation module, in which the system automatically evaluates the effectiveness of nursing measures, determines whether the expected nursing effect is achieved through data change trends, and readjusts the monitoring strategy if the effect is not ideal; according to the feedback evaluation results, the monitoring parameters and nursing plans are automatically adjusted to optimize individualized nursing, and the monitoring and nursing plans are gradually improved in the next monitoring cycle.

[0035] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the intelligent monitoring method for critically ill patient care as described in the first aspect of the present invention are implemented.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the intelligent monitoring method for critically ill patient care as described in the first aspect of the present invention are implemented.

[0037] The beneficial effects of the present invention are as follows: by integrating multi-sensor data collection, personalized health record establishment, real-time monitoring and early warning system, nursing effect evaluation and adjustment and other links, a highly intelligent, personalized, dynamically optimized critically ill patient care monitoring system is formed; this system can conduct comprehensive and real-time monitoring and accurate analysis of the patient's health status, so as to promptly detect and intervene when abnormalities occur, ensure that patients can receive timely care and treatment, reduce the waste of nursing resources and nursing errors, and improve the treatment effect and nursing quality of critically ill patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of 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.

[0039] Figure 1 A schematic diagram of the steps of the intelligent monitoring method for critically ill patient care of the present invention.

[0040] Figure 2 It is a structural schematic diagram of the intelligent monitoring system for critically ill patient care of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Example 1: Reference Figure 1~Figure 2 , which is the first embodiment of the present invention, and provides an intelligent monitoring method for critically ill patients' care, comprising:

[0045] Step S1: Use a multi-sensor system to collect the patient's physiological data (such as electrocardiogram, body temperature, respiration, etc.) and activity data in real time, and establish the patient's initial health record.

[0046] Specifically, the patient monitoring equipment is started to collect the health data of critically ill patients in real time. The health data includes physiological data and activity data. The patient monitoring equipment includes an electrocardiogram sensor, a body temperature sensor, a respiratory monitoring sensor, and a blood oxygen sensor. These data cover the patient's vital signs and basic behaviors (such as turning over, body movement frequency, etc.) to ensure that the patient's health status is fully captured.

[0047] Furthermore, based on the physiological data and the activity data collected in real time, an individualized initial health record is established for the patient, and the individualized initial health record records the patient's current physiological parameter baseline and behavioral pattern characteristics; according to the patient's health record, the monitoring thresholds of various physiological indicators (such as the upper and lower limits of heart rate, blood oxygen saturation warning value, etc.) are preliminarily set to provide a reference standard for subsequent dynamic monitoring.

[0048] It should be noted that by activating multi-sensor equipment (such as electrocardiogram sensors, body temperature sensors, respiratory monitoring sensors, etc.) to collect physiological data and activity data of critically ill patients in real time, an individualized health record is established for the patient; this preliminary health record records the patient's baseline physiological parameters (such as heart rate, blood oxygen level) and basic behavior patterns (such as turning over, activity frequency, etc.); this personalized health record provides an accurate reference standard for subsequent monitoring, early warning and nursing decisions, making subsequent health data comparisons and abnormality detection more accurate, avoiding errors in nursing decisions based on general standards; this step establishes a detailed health record for the patient by ensuring comprehensive and personalized data collection, providing data support for subsequent abnormality detection and nursing resource allocation, and effectively reducing the risk of misdiagnosis and missed diagnosis during the nursing process.

[0049] Step S2: Based on the collected multi-dimensional data, analyze the patient's daily activities and behavior patterns to establish an individualized health baseline to provide a reference for subsequent abnormality detection.

[0050] Specifically, based on the physiological data and the activity data collected in real time, a dynamic time warping algorithm is used to extract the patient's behavioral characteristics, such as activity pattern changes, frequency, duration, etc., to form a basic feature set of the behavioral data.

[0051] Furthermore, the K-means clustering algorithm is used to group the activity pattern characteristics of patients and divide them into multiple health benchmark categories according to their physiological status and behavioral characteristics. For each category, an individualized health baseline is established, including the normal fluctuation range of physiological data and typical activity behavior patterns. This baseline can reflect the patient's long-term health trends and normal behaviors.

[0052] Based on the patient's daily behavior and physiological data, time series analysis methods (such as hidden Markov model HMM) are used to model the evolution of the patient's behavior pattern and automatically identify the changing trend of the behavior pattern; for example, identify the patient's transition from normal activity mode to rest state, or sudden abnormal behavior pattern; by comparing historical data with current data, update the health baseline, and monitor in real time whether there is a significant deviation.

[0053] Furthermore, the parameters and thresholds of the individualized health baseline are intelligently adjusted based on the patient's historical health records and the dynamic behavior pattern evolution results, as follows: ;in, represents the health baseline after the i-th adjustment, represents the i-1th adjusted health baseline, Indicates the latest health data, Indicates the preset adjustment factor. ;in, represents the health threshold after the i-th adjustment, represents the initial health threshold, Indicates the amount of change in health status, based on the patient's historical data and current status assessment, Represents preset influencing factors; for example, dynamically adjusts the monitoring thresholds of activity frequency, heart rate or respiratory rate based on changes in patient behavior patterns; continuously optimizes the anomaly detection model through machine learning algorithms such as random forest or support vector machine (SVM) to more accurately identify individual abnormal trends.

[0054] Furthermore, after successfully building an individualized health baseline, the baseline will be applied to daily patient monitoring and prepared to provide a reference for subsequent abnormality detection; at this time, the system will monitor the patient's physiological data and behavioral patterns based on the new health baseline, generate early warning signals when significant deviations occur, and automatically allocate nursing resources.

[0055] It should be noted that the patient's activity patterns are analyzed through the dynamic time warping algorithm and the K-means clustering algorithm, and combined with physiological data to establish an individualized health baseline. This baseline reflects the patient's health status and normal behavior patterns, and can identify changes in behavior patterns in real time. This step is particularly important for critically ill patients because their conditions may fluctuate rapidly. Time series analysis methods (such as hidden Markov models) enable the evolution trend of behavior patterns to be dynamically captured and predicted, so as to promptly detect sudden abnormal behaviors. By establishing an individualized health baseline, the system can monitor and identify the patient's abnormal behavior and physiological status in real time based on the patient's historical and current data. This method can accurately track the patient's long-term health trends, adjust nursing measures in a timely manner, and ensure that the patient's health problems can be discovered and dealt with as early as possible.

[0056] Step S3: Monitor the patient's physiological and behavioral data in real time, identify abnormal trends or sudden changes through baseline comparison, and generate early warning signals immediately; in the case of early warning, prioritize the allocation of nursing resources according to the patient's status, implement the required nursing measures, and feed back the nursing operations to the system in real time for tracking.

[0057] Specifically, based on the individualized health baseline established above, the patient's physiological data (such as heart rate, blood pressure, body temperature, etc.) and activity data (such as activity frequency, limb movements, etc.) are collected in real time; through the data transmission and processing system, the collected data is ensured to be synchronized with the baseline data in real time, providing instant data support for abnormality identification.

[0058] Furthermore, the real-time collected patient data is compared with the individualized health baseline, and time series analysis methods (such as sliding windows) are used to identify deviations from abnormal trends in physiological parameters; for short-term physiological fluctuations (such as rapid changes in heart rate or abnormal breathing rate), the system will calculate the degree of deviation from the baseline and mark it as a potential abnormality when the deviation exceeds the preset threshold, as follows: ;in, represents the abnormal trend value at time point t, w represents the window size, represents the physiological data collected at time point a, and T represents the current time point.

[0059] Preset abnormal trend threshold , if the abnormal trend value at time point t , it is determined that an abnormality has occurred.

[0060] The degree of deviation is calculated as follows: ;in, represents the deviation measure at time t, Indicates the physiological data monitored in real time. represents the baseline value at time t, that is, the normal range or expected value calculated based on the patient's historical data and health records.

[0061] When the system detects that real-time data deviates significantly from the healthy baseline, especially sudden changes in physiological data or behavioral patterns (such as a sharp increase in heart rate or a sudden cessation of activity by the patient), the system will automatically trigger an early warning signal; the warning level will be automatically adjusted according to the degree of deviation (such as a slight deviation is a low-level warning, and a sharp fluctuation is a high-risk warning), and will be displayed in real time on the nursing staff terminal.

[0062] When the warning signal is triggered, nursing resources and nursing measures are automatically allocated according to the warning level, as follows:

[0063] Construct the warning level formula, the formula is as follows: ;in, represents the warning level at time t, It is a weighting factor based on deviation and abnormal trend.

[0064] when When the emergency occurs, it is recorded as a low-level warning, regular nursing staff are assigned, no additional equipment is required, and the nursing measures are routine care.

[0065] when It is recorded as an intermediate warning, and nursing staff is increased and monitoring equipment is activated. The nursing measures are close observation and collaboration with doctors.

[0066] when When an emergency occurs, it is recorded as a high-level warning, a large amount of nursing resources are allocated, emergency equipment is activated, and the nursing measures are emergency intervention, immediate response, and real-time communication.

[0067] It should be noted that, based on the patient's health baseline, the patient's physiological and behavioral data are monitored in real time and compared with the health baseline to automatically identify abnormal trends or sudden changes; through the sliding window method and deviation measurement, the system can sensitively capture physiological fluctuations (such as sudden changes in heart rate or abnormal breathing) or sudden changes in behavioral patterns (such as cessation of activity); this process automatically generates early warning signals, and allocates nursing resources and takes nursing measures according to the warning level; this step can promptly issue early warning signals and allocate nursing resources when abnormalities occur in the patient's health data, greatly improving the efficiency of nursing care for critically ill patients; through the real-time feedback mechanism, nursing staff can respond quickly to the patient's sudden condition, reduce the probability of potential crises, and ensure that patients can receive the most timely and appropriate care.

[0068] Step S4: The system automatically evaluates the effectiveness of nursing measures and determines whether the expected nursing effect is achieved through data change trends. If the effect is not ideal, the monitoring strategy is readjusted. Based on the feedback evaluation results, the monitoring parameters and nursing plans are automatically adjusted to optimize individualized care, and the monitoring and nursing plans are gradually improved in the next monitoring cycle.

[0069] The system will track the implementation effect of nursing measures in real time, and evaluate the effectiveness of nursing measures by comparing the changes in physiological data (such as heart rate, blood pressure, oxygen saturation, etc.) and activity data (such as activity frequency, limb activity, etc.) of patients before and after receiving care, as follows:

[0070] Calculate the changes in physiological data using the following formula: ;in, Indicates the change value of physiological data before and after care, and Represent the physiological data before and after care, respectively.

[0071] Calculate the activity data change, the calculation formula is: ;in, Indicates the change value of activity data before and after care, and Represents the activity data after and before care, respectively.

[0072] Based on the change value of physiological data before and after care Changes in activity data before and after care , calculate the comprehensive evaluation index, the calculation formula is as follows: ;in, represents the comprehensive evaluation index, and Respectively represent the change values ​​of physiological data before and after care Changes in activity data before and after care The weight coefficient of .

[0073] Based on the comprehensive evaluation index, the system will adjust the nursing strategy according to data feedback; if the effect of a certain nursing measure does not meet expectations (such as body temperature cannot be effectively controlled or blood oxygen level fails to recover), the system will automatically recommend or adjust the nursing measures, such as adjusting the drug dosage, changing the nursing method or adjusting the monitoring frequency.

[0074] Through continuous monitoring and care feedback, the system will optimize individualized care plans based on the latest patient data and care measure evaluation results; data feedback after each care will update the patient's health record, forming a continuously improving care cycle and providing an optimization basis for the next monitoring and care.

[0075] It should be noted that the effectiveness of nursing measures is evaluated by comparing the physiological data and activity data of patients before and after nursing; a comprehensive evaluation index is obtained by calculating the changes in physiological data and activity data, which will provide a basis for the optimization of nursing plans; if the nursing effect does not meet expectations, the system will automatically adjust the nursing strategy and optimize subsequent nursing plans; based on the continuous updating of patient data and nursing feedback, the nursing plan can be continuously optimized; this step enables dynamic adjustment of nursing measures through continuous monitoring and nursing feedback, ensuring that the effect after each nursing can be evaluated and continuously optimized; for critically ill patients, the effect of nursing is directly related to life and death, so this step can effectively ensure the quality of nursing and improve the patient's cure rate and quality of life.

[0076] Furthermore, the present embodiment also provides an intelligent monitoring system for critically ill patient care, including a multi-sensor data acquisition module for real-time acquisition of physiological data and activity data of patients, and establishment of an initial health record for patients; an individualized health baseline generation module for analyzing daily activities and behavior patterns of patients based on the collected multi-dimensional data, establishing an individualized health baseline, and providing a reference for subsequent abnormality detection; a real-time abnormality monitoring module for real-time monitoring of physiological data and behavioral data of patients, identifying abnormal trends through baseline comparison, and generating early warning signals in real time; in the case of early warning, prioritizing allocation of nursing resources according to the patient's status, implementing required nursing measures, and feeding back nursing operations to the system in real time for tracking; a nursing effect evaluation module, in which the system automatically evaluates the effectiveness of nursing measures, determines whether the expected nursing effect is achieved through data change trends, and readjusts the monitoring strategy if the effect is not ideal; based on the feedback evaluation results, automatically adjusts monitoring parameters and nursing plans, optimizes individualized nursing, and gradually improves monitoring and nursing plans in the next monitoring cycle.

[0077] This embodiment also provides a computer device, which is suitable for the case of an intelligent monitoring method for critically ill patient care, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent monitoring method for critically ill patient care proposed in the above embodiment.

[0078] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0079] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent monitoring method for critically ill patient care proposed in the above embodiment is implemented.

[0080] In summary, by integrating multi-sensor data collection, personalized health record establishment, real-time monitoring and early warning system, nursing effect evaluation and adjustment, etc., a highly intelligent, personalized, dynamically optimized critical care monitoring system has been formed; this system can conduct comprehensive and real-time monitoring and accurate analysis of the patient's health status, so as to promptly detect and intervene when abnormalities occur, ensure that patients can receive timely care and treatment, reduce the waste of nursing resources and nursing errors, and improve the treatment effect and nursing quality of critically ill patients.

[0081] Embodiment 2: In this embodiment 2, an intelligent monitoring method for critically ill patient care is provided. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0082] In order to verify the innovation and effectiveness of the health monitoring and nursing optimization method for critically ill patients based on a multi-sensor system, a simulation experiment was designed. The purpose of the experiment was to establish an individualized health file by collecting the patient's physiological data (such as electrocardiogram, body temperature, respiration, etc.) and activity data (such as turning over, body movement frequency, etc.) in real time, and to monitor the changes in the patient's health status based on this file, so as to optimize the allocation of nursing resources.

[0083] During the experiment, a variety of sensor devices were used, including electrocardiogram sensors, body temperature sensors, respiratory monitoring sensors, and blood oxygen sensors. These devices were deployed on simulated critically ill patients, and the patient monitoring equipment collected physiological data in real time and simultaneously recorded the patient's behavior patterns, such as turning over and body movement frequency. In addition, all sensors were connected to the central data processing system through wireless transmission modules to ensure real-time update and synchronization of data.

[0084] Experimental implementation steps:

[0085] 1. Start the patient monitoring equipment to collect health data in real time, including physiological parameters such as heart rate, blood pressure, body temperature, respiratory rate and blood oxygen saturation, as well as the patient's activity data (such as turning over frequency, number of body movements, etc.); the experiment is set for 24 hours, and data is collected every 5 minutes to ensure that the patient's health changes within 24 hours are covered.

[0086] 2. Based on real-time collected data, an individualized health record is established for each patient; the record records the patient's physiological data baseline values ​​and behavioral pattern characteristics; by analyzing health data, the monitoring thresholds of physiological parameters such as heart rate and blood oxygen are preliminarily set as the benchmark for subsequent abnormality detection.

[0087] 3. Use the dynamic time warping (DTW) algorithm to extract the patient's activity behavior characteristics, such as activity pattern changes, frequency, duration, etc., to establish an individualized health baseline; at the same time, use the K-means clustering algorithm to group the patient's activity patterns, determine multiple health benchmark categories, and establish an individualized health baseline for each category; the health baseline includes the patient's physiological parameter fluctuation range and typical activity behavior patterns.

[0088] 4. After establishing a health baseline, the system monitors the patient's physiological data and activity data in real time, and identifies abnormal trends or sudden changes by comparing them with the health baseline; for example, when the heart rate rises sharply or the patient's activity pattern changes drastically, the system will automatically trigger an early warning signal and automatically allocate nursing resources according to the early warning level; if the deviation of the patient's physiological data or behavior pattern exceeds the set threshold, the system will immediately remind the nursing staff to intervene.

[0089] 5. The system will track the effectiveness of nursing measures in real time and evaluate the nursing effect by comparing the changes in physiological data and activity data before and after nursing. If a nursing measure fails to achieve the expected effect, the system will automatically adjust the nursing plan to optimize the nursing strategy in the next monitoring cycle.

[0090] Table 1 Patient health monitoring data table

[0091] Test subjects Heart rate blood pressure body temperature Blood oxygen saturation Body movement frequency Turning frequency Patient A (before care) 80 120 / 80 36.5 97 15 5 Patient A (after care) 78 118 / 78 36.4 98 18 6 Patient B (before care) 92 130 / 85 37.2 94 12 4 Patient B (after care) 90 128 / 84 37.1 96 14 5 Patient C (before care) 85 125 / 80 36.8 95 16 5 Patient C (after care) 83 123 / 79 36.7 96 17 6

[0092] As can be seen from Table 1, the patient's health data has changed significantly after nursing intervention, reflecting the innovation and effectiveness of the health monitoring and nursing optimization method based on the multi-sensor system. The following is a detailed data analysis:

[0093] 1. Changes in heart rate: For patients A and B, their heart rates decreased slightly after nursing (reduced by 2 bpm and 2 bpm respectively). This change shows that after nursing intervention, the patient's heart rate tended to stabilize, especially for patients with higher heart rates (such as patient B, whose heart rate was 92 bpm before nursing). Nursing effectively reduced the heart rate and helped the patient maintain it within the normal range.

[0094] 2. Improvement in blood pressure: The blood pressure of patients A and B improved slightly. Patient A's systolic blood pressure dropped from 120 to 118 mmHg, and diastolic blood pressure dropped from 80 to 78 mmHg; patient B's systolic blood pressure dropped from 130 to 128 mmHg, and diastolic blood pressure dropped from 85 to 84 mmHg. This shows that the nursing measures have achieved initial results in controlling blood pressure, especially for patients with hypertension. The nursing measures have successfully reduced blood pressure levels by optimizing health management.

[0095] 3. Improvement in body temperature and blood oxygen level: The body temperature of patients A and B changed slightly, but the body temperature was controlled within the normal range, indicating that the nursing measures played a role in regulating the patient's body temperature. Especially in terms of blood oxygen saturation, the blood oxygen levels of all patients increased (by 1-2 percentage points respectively). For example, the blood oxygen saturation of patient A increased from 97% to 98%, indicating that the nursing measures can effectively improve the patient's blood oxygen level and reduce the risk of hypoxia caused by respiratory problems.

[0096] 4. Changes in body movement and turning frequency: After nursing intervention, the body movement frequency and turning frequency of patients A, B, and C increased, indicating that nursing intervention helped patients increase their activity. Especially for patients with less mobility (such as patient B), the increase in body movement frequency and turning frequency can help avoid complications caused by long-term bed rest, such as lung infection or bedsores.

[0097] 5. Nursing effectiveness evaluation: Through comprehensive evaluation of changes in patients' physiological data and activity data, the comprehensive evaluation index of nursing effectiveness has been improved, indicating that nursing measures have played a positive role in patient health management.

[0098] Through data analysis, it can be seen that the health monitoring method based on a multi-sensor system provided by the present invention can realize accurate individualized care plans and real-time feedback mechanisms, and provides more creative and novel advantages than existing technologies in terms of monitoring, early warning, and nursing effect evaluation, and significantly improves the nursing effect and the patient's health management level.

[0099] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent monitoring method for critically ill patient care, characterized in that: include: Step S1: using a multi-sensor system to collect the patient's physiological data and activity data in real time, and establish the patient's initial health record; Step S2: Based on the collected physiological data and activity data, the dynamic time warping algorithm is used to extract the patient's behavioral characteristics, and the patient's activity pattern characteristics are grouped through the K-means clustering algorithm. The health baseline categories are divided according to the patient's physiological state and behavioral characteristics. For each category, the patient's daily activities and behavior patterns are analyzed to establish an individualized health baseline; Step S3: Monitor the patient's physiological data and activity data in real time, use time series analysis methods to identify deviations from abnormal trends in physiological parameters, calculate the degree of deviation from the baseline, generate early warning signals, and prioritize nursing measures based on the patient's status; Step S4: Evaluate the effect of nursing measures to determine whether the expected nursing effect is achieved. If the expected nursing effect is not achieved, readjust the monitoring strategy; The specific implementation process of step S2 includes: Based on the physiological data and the activity data collected in real time, a dynamic time warping algorithm is used to extract the patient's behavioral characteristics to form a basic feature set of behavioral data; The K-means clustering algorithm is used to group the activity pattern characteristics of patients, and the health baseline categories are divided according to the physiological status and behavioral characteristics of patients. For each category, an individualized health baseline is established, including the normal fluctuation range of physiological data and typical activity behavior patterns. Based on the patient's daily behavior and physiological data, the evolution of the patient's behavior pattern is modeled using a time series analysis method, and the changing trend of the behavior pattern is automatically identified. By comparing historical data with current data, the health baseline is updated, and real-time monitoring is performed to determine whether significant deviations occur. The specific implementation process of step S2 also includes: Combined with the patient's historical health records and dynamic behavior pattern evolution results, the parameters and thresholds of the individualized health baseline are intelligently adjusted as follows: ； in, represents the health baseline after the i-th adjustment, represents the health baseline after the i-1th adjustment, Indicates the latest health data, Indicates the preset adjustment factor; ； in, represents the health threshold after the i-th adjustment, represents the initial health threshold, Indicates the change in health status, Represents the preset influencing factors and continuously optimizes the anomaly detection model through machine learning algorithms.

2. The intelligent monitoring method for critically ill patient care according to claim 1, characterized in that: The specific implementation process of step S1 includes: Starting a patient monitoring device to collect health data of critically ill patients in real time, wherein the health data includes physiological data and activity data, and the patient monitoring device includes an electrocardiogram sensor, a body temperature sensor, a respiratory monitoring sensor, and a blood oxygen sensor; Based on the physiological data and the activity data collected in real time, an individualized initial health record is established for the patient, in which the patient's current physiological parameter baseline and behavioral pattern characteristics are recorded; based on the patient's health record, the monitoring thresholds of various physiological indicators are preliminarily set.

3. The intelligent monitoring method for critically ill patient care according to claim 2 is characterized in that: The specific implementation process of step S3 includes: The real-time collected patient data is compared with the individual health baseline, and the deviation of abnormal trends of physiological parameters is identified using time series analysis methods. The degree of deviation from the baseline is calculated and marked as a potential abnormality when the deviation exceeds the preset threshold, as follows: ； in, represents the abnormal trend value at time point t, w represents the window size, represents the physiological data collected at time point a, and T represents the current time point; Preset abnormal trend threshold , if the abnormal trend value at time point t , it is determined that an abnormality has occurred; The degree of deviation is calculated as follows: ； in, represents the deviation measure at time t, Indicates the physiological data monitored in real time. Represents the baseline value at time t.

4. The intelligent monitoring method for critically ill patient care according to claim 3 is characterized in that: The specific implementation process of step S3 also includes: When it is detected that the real-time data deviates significantly from the health baseline, an early warning signal is automatically triggered; the warning level is automatically adjusted according to the degree of deviation and displayed in real time on the nursing staff terminal; When the warning signal is triggered, nursing resources and nursing measures are automatically allocated according to the warning level: Construct the warning level formula, the formula is as follows: ； in, represents the warning level at time t, It is a weighting factor based on deviation and abnormal trend; when When the alarm is low, it is recorded as a low-level warning, and routine nursing staff are assigned, no additional equipment is required, and the nursing measure is routine care; when When the alarm is detected, it is recorded as an intermediate warning, and nursing staff is increased and monitoring equipment is activated. The nursing measures include close observation and collaboration with doctors. when When an emergency occurs, it is recorded as a high-level warning, a large amount of nursing resources are allocated, emergency equipment is activated, and the nursing measures are emergency intervention, immediate response, and real-time communication.

5. The intelligent monitoring method for critically ill patient care according to claim 4 is characterized in that: The specific implementation process of step S4 includes: Track the implementation effect of nursing measures in real time, and evaluate the effectiveness of nursing measures by comparing the changes in the patient's physiological data and activity data before and after receiving care: Calculate the changes in physiological data using the following formula: ； in, Indicates the change value of physiological data before and after care, and Represent the physiological data after and before nursing care respectively; Calculate the activity data change, the calculation formula is: ； in, Indicates the change value of activity data before and after care, and represent activity data after and before care, respectively; Based on the change value of physiological data before and after care Changes in activity data before and after care , calculate the comprehensive evaluation index, the calculation formula is as follows: ； in, represents the comprehensive evaluation index, and Respectively represent the change values ​​of physiological data before and after care Changes in activity data before and after care The weight coefficient of .

6. An intelligent monitoring system for critically ill patients' care, based on the intelligent monitoring method for critically ill patients' care according to any one of claims 1 to 5, characterized in that: Also includes: Multi-sensor data acquisition module, used to collect the patient's physiological data and activity data in real time and establish the patient's initial health record; The personalized health baseline generation module analyzes the patient's daily activities and behavior patterns based on the collected multi-dimensional data to establish a personalized health baseline; Real-time abnormality monitoring module, which monitors the patient's physiological and behavioral data in real time, identifies abnormal trends through baseline comparison, and generates early warning signals immediately; In the event of an early warning, nursing resources are allocated in priority according to the patient's status, the required nursing measures are implemented, and the nursing operations are fed back to the system in real time for tracking; The nursing effectiveness evaluation module evaluates the effectiveness of nursing measures and determines whether the expected nursing effect has been achieved through data change trends. If the expected nursing effect has not been achieved, the monitoring strategy will be readjusted.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent monitoring method for critically ill patient care described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent monitoring method for critically ill patient care described in any one of claims 1 to 5 are implemented.

Images