Severe illness rehabilitation auxiliary system and method based on intelligent monitoring

Abstract

The invention discloses a severe illness rehabilitation assisting system and method based on intelligent monitoring, and relates to the technical field of severe illness monitoring, and the severe illness rehabilitation assisting system comprises a sensor module, a data transmission module, a state judgment module, a plan making module, a feedback and prompt module and a data storage module. The method has the advantages that the correction function obtained through training based on the deep learning algorithm is introduced through the state judgment module to calculate the data deviation value, and the correction function can further correct the calculation result of the current deviation value according to the actually corresponding deviation condition when similar parameter values appear in historical data; therefore, the change of the health state of the patient can be more accurately recognized, especially under the condition of complex individual differences of the patient, misjudgment can be effectively avoided, the safety of the patient is improved, meanwhile, based on accurate state judgment, the system can automatically adjust the rehabilitation plan according to the specific condition of the patient, and the effectiveness and pertinence of rehabilitation activities are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of critical illness monitoring, and in particular to a critical illness rehabilitation assistance system and method based on intelligent monitoring. Background Art

[0002] In the medical field, critical care monitoring and management are key to ensuring patient safety and improving treatment outcomes. Traditional critical care monitoring methods rely primarily on the experience of medical staff and regular physical examinations, such as monitoring vital signs and analyzing laboratory test results. These methods played an important role in early medical practice, helping doctors understand patients' health status in a timely manner and make treatment decisions.

[0003] However, traditional methods often make it difficult to collect and analyze these data in real time and accurately, resulting in a lack of scientific basis for the formulation and adjustment of rehabilitation plans, which in turn affects the rehabilitation effect. To this end, we propose a critical care rehabilitation assistance system and method based on intelligent monitoring. Summary of the Invention

[0004] The purpose of the present invention is to provide a critical illness rehabilitation assistance system and method based on intelligent monitoring.

[0005] To solve the problems raised in the above background technology, the present invention provides the following technical solutions: a critical illness rehabilitation assistance system based on intelligent monitoring, comprising the following modules:

[0006] Sensor module, which collects patient vital signs data, behavioral signs data, and environmental data;

[0007] The data transmission module is responsible for transmitting the data collected by the sensor to the cloud server;

[0008] The status judgment module compares the collected data with the standard data features, calculates the data deviation value, judges the patient's physical condition based on the size of the data deviation value, and optimizes the standard data features according to the differences in the patient's physical condition;

[0009] The plan making module makes a rehabilitation plan based on the results of the patient's physical condition;

[0010] The feedback and reminder module sets safety thresholds for patients' vital signs and rehabilitation indicators. When the monitoring data exceeds the normal range, the alarm mechanism is triggered, reminding patients and medical staff to implement the plan content according to the rehabilitation plan every day;

[0011] The data storage module stores all monitoring data generated by the patient since admission and encrypts the patient's privacy information.

[0012] As a further solution of the present invention: The sensor module includes a vital sign data acquisition unit, a behavioral sign data acquisition unit, an environmental data acquisition unit, and an actuator unit. The actuator unit is responsible for performing corresponding actions according to the collected data.

[0013] As a further solution of the present invention: The data transmission module includes a data classification unit and an anti-interference unit. The data classification unit is used to classify the collected data, and the anti-interference unit is used to ensure the reliable transmission of data in a complex interference environment. The anti-interference unit adopts a redundant data transmission mechanism and uses multiple channels to transmit data.

[0014] As a further solution of the present invention: In the state judgment module, the method for obtaining the standard data characteristics is as follows: Collect the normal parameter data ranges of all patients of this type in this hospital, and divide them into four groups according to age: juvenile, young, middle-aged, and elderly. For each parameter of each group, use deep learning algorithms to train a large amount of historical data, construct a data distribution model, identify and remove outliers in the data through the model, take the average value of the remaining data as the normal parameter central value, and calculate the standard deviation according to the central value and the data distribution model to determine the normal parameter data range for each age group. In the state judgment module, the formula for calculating the data deviation value is:

[0015]

[0016] Where, Z represents the deviation value, X represents the current parameter value of the patient, P represents the normal parameter central value of this parameter, σ is the standard deviation, and y(x) represents the correction function, which is obtained by learning the deviation situation in the case of similar parameter values in historical data through deep learning algorithms. The value of y(x) belongs to 0.8 - 1.2. When 1 < Z ≤ 2, it is judged that the patient's state is slightly abnormal, and the detection frequency is increased to understand the patient's condition. When 2 < Z ≤ 3, it is judged that the patient's state is moderately abnormal, and the activities affecting the patient's parameters are stopped, and in-depth medical examinations are carried out. When Z > 3, it is judged that the patient's state is severely abnormal, the emergency room alarm is triggered, a text message is sent to notify the emergency doctor, and first aid measures are taken. If the patient's parameters are abnormal for 3 consecutive days and no abnormal vital signs of the patient are detected, calculate the average value of the patient's parameters within 3 days, and take the average value as the normal parameter central value of this patient.

[0017] As a further solution of the present invention: the plan formulation module includes a state analysis unit, a plan generation unit and a plan adjustment unit. The state analysis unit is used to receive the judgment result transmitted by the state judgment module, and analyze the patient's current rehabilitation stage. The patient's current rehabilitation stage is divided into early rehabilitation, middle rehabilitation and late rehabilitation. If the patient needs external force to assist in turning over limb activities, and the patient has more than 10 abnormal conditions in a week, the patient is judged to be in the early rehabilitation stage. If the patient can complete limb activities such as standing and waving hands, and the patient has less than 10 abnormal conditions in a week, the patient is judged to be in the middle rehabilitation stage. If the patient can independently complete daily activities such as dressing and washing, and the patient has less than 5 abnormal conditions in a week, the patient is judged to be in the late rehabilitation stage. The plan generation unit is used to formulate a rehabilitation plan according to the patient's rehabilitation stage, and the plan adjustment unit is used to adjust the patient's rehabilitation plan according to the patient's situation after executing the plan.

[0018] As a further solution of the present invention: in the plan generation unit, the rehabilitation plan is divided into an initial rehabilitation plan, a mid-term rehabilitation plan and a late rehabilitation plan. The initial rehabilitation plan is to detect vital signs every 15 minutes, and perform joint activities 3 times a day, each time for 10 times. The mid-term rehabilitation plan is to detect vital signs every 30 minutes, and perform standing activities 3 times a day, each time for 2 minutes. The late rehabilitation plan is to detect vital signs every 2 hours, and perform outdoor walking activities 3 times a day, each time for 10 minutes. In the plan adjustment unit, the specific method of adjusting the patient's rehabilitation plan is: if the patient has moderate abnormalities and severe abnormalities during the activity, stop the activity for that day and reduce the activity time for the next day by 50%; if the patient only has slight abnormalities during the activity, maintain the current rehabilitation activity; if the patient has no abnormalities during the activity and the deviation value shows a downward trend, the activity time is increased by 50%.

[0019] As a further solution of the present invention, the feedback and prompt module includes an alarm unit, a reminder unit, and a feedback unit. The alarm unit is used to monitor the patient's vital sign data and behavioral sign data. When the monitored data deviates from the set threshold, the alarm unit will trigger an alarm mechanism. The reminder unit is used to voice prompt the patient and the auxiliary personnel to execute the rehabilitation plan. The feedback unit is used to evaluate the patient's rehabilitation effect. The specific formula is as follows:

[0020] E=ω1·G1+ω2·G2+ω3·G3+ω4·F

[0021] Among them, E represents the comprehensive rehabilitation score, G1, G2 and G3 represent the vital signs improvement rate, behavioral signs improvement rate and rehabilitation plan completion rate respectively, F represents the patient's feedback evaluation, ω4 = 0.1, ω1, ω2 and ω3 represent the weight coefficients of the vital signs improvement rate, behavioral signs improvement rate and rehabilitation plan completion rate respectively, ω4 represents the weight coefficient of the patient's feedback evaluation, ω1+ω2+ω3+F=1, ω1:ω2:ω3=4:4:2, if 0.8≤E≤1, it means that the rehabilitation effect is excellent, and the above rehabilitation plan is continued; if 0.6≤E<0.8, it means that the rehabilitation effect is good; if E<0.6, it means that the rehabilitation effect is unsatisfactory, and a rehabilitation report is generated and sent to the plan formulation module to formulate a new rehabilitation plan.

[0022] As a further solution of the present invention: the data storage module includes a collaboration and evaluation unit, which stores the patient's current treatment progress. The collaboration and evaluation unit is used for different rehabilitation therapists to understand the patient's current treatment progress.

[0023] In addition, the present invention also provides a critical illness rehabilitation assisting method, comprising the following steps:

[0024] Step 1: The sensor module comprehensively collects the patient's vital signs, behavioral signs and environmental data;

[0025] Step 2: The data transmission module uploads the collected data to the cloud server safely and efficiently;

[0026] Step 3: The status judgment module compares the data, accurately determines the patient's status, and dynamically optimizes the standard data features;

[0027] Step 4: The planning module tailors the rehabilitation plan based on the patient's condition;

[0028] Step 5: The feedback and prompt module sets safety thresholds, issues timely alarms, and reminds users to implement rehabilitation plans;

[0029] Step 6: The data storage module stores system data, protects patient privacy, and records patient treatment progress.

[0030] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0031] 1. The present invention uses a correction function trained using a deep learning algorithm to calculate data deviation values ​​through a state judgment module. This correction function can further correct the calculated deviation value based on the actual deviation corresponding to the occurrence of similar parameter values ​​in historical data, thereby more accurately identifying changes in the patient's health status. This can effectively avoid misjudgments, especially in the case of complex individual patient differences, and improve patient safety. At the same time, based on accurate state judgment, the system can automatically adjust the rehabilitation plan according to the patient's specific situation, ensuring the effectiveness and pertinence of rehabilitation activities, thereby improving rehabilitation results.

[0032] 2. This invention analyzes the patient's monitoring data and uses it to identify deviations based on standard data features. It can dynamically formulate and adjust rehabilitation plans. Furthermore, the system can flexibly adjust the frequency and intensity of rehabilitation activities based on the patient's rehabilitation stage and condition, thereby further improving rehabilitation outcomes.

[0033] 3. The present invention uses a specific formula to comprehensively score the patient's rehabilitation effect. The formula not only takes into account the improvement rate of vital signs, behavioral signs and rehabilitation plan completion rate, but also incorporates the patient's feedback evaluation and assigns a reasonable weight coefficient, providing rehabilitation therapists with intuitive and multi-dimensional evaluation results. At the same time, a collaboration and evaluation unit is set up to facilitate different rehabilitation therapists to fully understand the patient's current rehabilitation progress, adjust the rehabilitation strategy in a timely manner, and improve the patient's rehabilitation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of the auxiliary system flow in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings shown in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] Example 1:

[0037] Please see the attached Figure 1 The present invention provides a critical illness rehabilitation assistance system based on intelligent monitoring, comprising the following modules:

[0038] Sensor module, which collects patient vital signs data, behavioral signs data, and environmental data;

[0039] The data transmission module is responsible for transmitting the data collected by the sensor to the cloud server;

[0040] The status judgment module compares the collected data with the standard data features, calculates the data deviation value, judges the patient's physical condition based on the size of the data deviation value, and optimizes the standard data features according to the differences in the patient's physical condition;

[0041] The plan making module makes a rehabilitation plan based on the results of the patient's physical condition;

[0042] The feedback and reminder module sets safety thresholds for patients' vital signs and rehabilitation indicators. When the monitoring data exceeds the normal range, the alarm mechanism is triggered, reminding patients and medical staff to implement the plan content according to the rehabilitation plan every day;

[0043] The data storage module stores all monitoring data generated by the patient since admission and encrypts the patient's privacy information;

[0044] The sensor module includes a vital sign data acquisition unit, a behavioral sign data acquisition unit, an environmental data acquisition unit, and an actuator unit. The actuator unit is responsible for performing corresponding actions based on the collected data;

[0045] The data transmission module includes a data classification unit and an anti-interference unit. The data classification unit is used to classify the collected data, and the anti-interference unit is used to ensure reliable data transmission in a complex interference environment. The anti-interference unit adopts a redundant data transmission mechanism and uses multiple channels to transmit data.

[0046] In the status judgment module, the method for obtaining standard data features is to collect the normal parameter data range of all patients of this type in the hospital and divide them into four groups according to age: young, young, middle-aged and elderly. For each parameter in each group, a deep learning algorithm is used to train massive historical data to build a data distribution model. The model is used to identify and remove outliers in the data, and the average value of the remaining data is used as the normal parameter center value. The standard deviation is calculated based on the center value combined with the data distribution model to determine the normal parameter data range for each age group. In the status judgment module, the formula for calculating the data deviation value is as follows:

[0047]

[0048] Among them, Z represents the deviation value, X represents the current parameter value of the patient, P represents the normal parameter central value of this parameter, σ is the standard deviation, and y(x) represents the correction function, which is obtained by learning the deviation situation in the case of similar parameter values in historical data through a deep learning algorithm. The value of y(x) belongs to 0.8 - 1.2. When 1 < Z ≤ 2, it is judged that the patient's state is slightly abnormal, and the detection frequency is increased to understand the patient's situation. When 2 < Z ≤ 3, it is judged that the patient's state is moderately abnormal, and the activities affecting the patient's parameters are stopped, and in-depth medical examinations are carried out. When Z > 3, it is judged that the patient's state is severely abnormal, the emergency room alarm is triggered, a text message is sent to notify the emergency doctor, and first aid measures are taken. If the patient's parameters are abnormal for 3 consecutive days and no abnormal vital signs of the patient are detected, the average value of the patient's parameters within 3 days is calculated, and the average value is used as the normal parameter central value of this patient.

[0049] Specific work process: In actual intensive care rehabilitation treatment, take the intensive care rehabilitation ward of a certain hospital as an example. The vital sign data acquisition unit (such as a heart rate monitor, a sphygmomanometer, etc.), the behavioral sign data acquisition unit (such as a limb movement sensor), and the environmental data acquisition unit (such as a ward temperature and humidity sensor) in the sensor module continuously collect data;

[0050] There is a 65-year-old patient with severe heart disease in intensive care rehabilitation. The heart rate data is transmitted through the sensor. In the state judgment module, a data distribution model constructed by a deep learning algorithm is used to train a large amount of historical data of similar elderly heart disease patients. Suppose the current heart rate value X of this patient is 80 beats per minute, the normal parameter central value P obtained through the model is 70 beats per minute, the standard deviation is 5, and the correction function y(x) is obtained by learning the deviation situation of historical similar heart rate values and the value is 1.1. Calculate the deviation value Z = |80 - 70|×1.1 / 5 = 2.2. Since 2 < Z ≤ 3, it is judged as moderately abnormal. The system automatically increases the detection frequency and stops the rehabilitation activities that may affect the heart rate, such as temporarily stopping the intensive limb movement training. Based on this, the medical staff adjusts the rehabilitation plan. The original mild limb movement of 3 times a day and 10 minutes each time is changed to 2 times a day and 8 minutes each time. Continuous monitoring is carried out subsequently. This adjustment method based on innovative state judgment can respond more accurately to the changes in the patient's state compared with the traditional method. In the statistics of 50 similar patients, the situation of the deterioration of the condition caused by misjudgment of the state has been reduced by 30%, effectively improving the safety and effect of rehabilitation.

[0051] Furthermore, a correction function obtained through deep learning algorithm training is introduced through the state judgment module to calculate the data deviation value. This correction function can further correct the calculation result of the current deviation value according to the actual corresponding deviation when similar parameter values ​​appear in the historical data, thereby more accurately identifying changes in the patient's health status. Especially in the case of complex individual differences among patients, it can effectively avoid misjudgment and improve the safety of patients. At the same time, based on accurate state judgment, the system can automatically adjust the rehabilitation plan according to the patient's specific situation to ensure the effectiveness and pertinence of rehabilitation activities, thereby improving the rehabilitation effect.

[0052] Example 2:

[0053] Based on the first embodiment, the plan formulation module includes a state analysis unit, a plan generation unit and a plan adjustment unit. The state analysis unit is used to receive the judgment result transmitted by the state judgment module, analyze the patient's current rehabilitation stage, and the patient's current rehabilitation stage is divided into early rehabilitation, middle rehabilitation and late rehabilitation. If the patient needs external force to assist in turning over limb activities, and the patient has more than 10 abnormal conditions in a week, it is judged that the patient is in the early rehabilitation stage. If the patient can complete the limb activities of standing and waving hands, and the patient has less than 10 abnormal conditions in a week, it is judged that the patient is in the middle rehabilitation stage. If the patient can independently complete daily activities such as dressing and washing, and the patient has less than 5 abnormal conditions in a week, it is judged that the patient is in the late rehabilitation stage. The plan generation unit is used to formulate a rehabilitation plan according to the patient's rehabilitation stage, and the plan adjustment unit is used to adjust the patient's rehabilitation plan according to the patient's situation after executing the plan;

[0054] In the plan generation unit, the rehabilitation plan is divided into initial rehabilitation plan, mid-term rehabilitation plan and late rehabilitation plan. The initial rehabilitation plan is to check vital signs every 15 minutes, and perform joint activities 3 times a day, each time for 10 times. The mid-term rehabilitation plan is to check vital signs every 30 minutes, and perform standing activities 3 times a day, each time for 2 minutes. The late rehabilitation plan is to check vital signs every 2 hours, and perform outdoor walking activities 3 times a day, each time for 10 minutes. In the plan adjustment unit, the specific way to adjust the patient's rehabilitation plan is: if the patient has moderate and severe abnormalities during the activity, stop the activity for that day and reduce the activity time for the next day by 50%. If the patient only has slight abnormalities during the activity, maintain the current rehabilitation activity. If the patient has no abnormalities during the activity and the deviation value shows a downward trend, the activity time will increase by 50%.

[0055] Specific workflow: In a rehabilitation hospital, a 45-year-old stroke patient is recovering. Sensors continuously collect patient data, and the data transmission module transmits the data to the cloud server. The status judgment module processes the data. For example, the patient's blood pressure data fluctuates several times within a week, with the systolic pressure reaching a maximum of 160 mmHg and the diastolic pressure reaching a maximum of 100 mmHg. The normal blood pressure parameters of the middle-aged group are 130 mmHg for systolic pressure and 85 mmHg for diastolic pressure, with standard deviations of 10 mmHg and 5 mmHg, respectively. The calculated systolic pressure deviation value Z = (160-130) / 10 = 3 and the diastolic pressure deviation value Z = (100-85) / 5 = 3, indicating that the patient's physical condition is moderately abnormal. At the same time, when the patient performs simple hand grasping training, his strength and coordination are reduced compared to before, and his behavioral sign data are abnormal.

[0056] Based on these data, the rehabilitation plan formulation module adjusted the rehabilitation plan. The intensity of hand grip training in the original rehabilitation plan was reduced from 3 sets of exercises using a 3-pound grip ball per day, 15 times per set, to 3 sets of exercises using a 2-pound grip ball, 10 times per set. At the same time, the number of hand joint movement training was increased from 2 times a day to 3 times, and the frequency of vital sign monitoring was increased from once an hour to once every 30 minutes. As the patient's blood pressure gradually stabilized within the normal range, the hand grip ability also began to gradually improve. The system adjusted the plan again according to the patient's improvement. Three months later, the patient's limb strength and mobility were significantly improved, his blood pressure was normal, and he was able to complete simple daily activities, proving that dynamically adjusting the plan based on data deviation can improve the rehabilitation effect.

[0057] Furthermore, by analyzing the patient's monitoring data and combining it with standard data characteristics to make deviation judgments, the rehabilitation plan can be dynamically formulated and adjusted. According to the patient's rehabilitation stage and status changes, the system can flexibly adjust the frequency and intensity of rehabilitation activities, thereby further improving the rehabilitation effect.

[0058] Example 3:

[0059] Based on the second embodiment, the feedback and prompt module includes an alarm unit, a reminder unit, and a feedback unit. The alarm unit is used to monitor the patient's vital signs and behavioral signs data. When the monitored data deviates from the set threshold, the alarm unit will trigger the alarm mechanism. The reminder unit is used to voice prompt the patient and the auxiliary personnel to execute the rehabilitation plan. The feedback unit is used to evaluate the patient's rehabilitation effect. The specific formula is as follows:

[0060] E=ω1·G1+ω2·G2+ω3·G3+ω4·F

[0061] Wherein, E represents the comprehensive rehabilitation score, G1, G2 and G3 represent the improvement rate of vital signs, the improvement rate of behavioral signs and the completion rate of rehabilitation plan respectively, F represents the patient's feedback evaluation, ω4 = 0.1, ω1, ω2 and ω3 represent the weight coefficients of the improvement rate of vital signs, the improvement rate of behavioral signs and the completion rate of rehabilitation plan respectively, ω4 represents the weight coefficient of the patient's feedback evaluation, ω1 + ω2 + ω3 + F = 1, ω1: ω2: ω3 = 4:4:2, if 0.8 ≤ E ≤ 1, it means that the rehabilitation effect is excellent and the above rehabilitation plan is continued; if 0.6 ≤ E < 0.8, it means that the rehabilitation effect is good; if E < 0.6, it means that the rehabilitation effect is unsatisfactory and a rehabilitation report is generated and sent to the plan formulation module to formulate a new rehabilitation plan;

[0062] The data storage module includes a collaboration and evaluation unit, which stores the patient's current treatment progress. The collaboration and evaluation unit is used by different rehabilitation therapists to understand the patient's current treatment progress.

[0063] Specific workflow: In another rehabilitation scenario, a group of 20 stroke rehabilitation patients were evaluated by the feedback and prompt module. For example, one of the patients, Mr. Li, showed a 70% improvement in vital signs (such as blood pressure and blood oxygen levels), a 60% improvement in behavioral signs (enhanced limb mobility), and an 80% completion rate for the rehabilitation plan. Mr. Li reported feeling well recovered, with an evaluation score of 8 out of 10.

[0064] According to the comprehensive rehabilitation scoring formula E = (0.7×0.4+0.6×0.4+0.8×0.2)×0.9+8×0.1=0.744, since 0.6≤E<0.8, it means that the rehabilitation effect is good. Based on this result, the rehabilitation therapist decided to maintain the current rehabilitation plan, but appropriately add some targeted rehabilitation training, such as adding fine motor training of the hands. In the long-term observation of this group of patients, it was found that through this comprehensive scoring and corresponding rehabilitation strategy adjustment, the rehabilitation cycle was shortened by an average of about 15% compared with patients who did not use the system for evaluation. At the same time, the collaboration and evaluation unit allows rehabilitation therapists on different shifts to clearly understand the patient's treatment progress. For example, when a therapist takes leave, other therapists can quickly continue to provide appropriate rehabilitation treatment for the patient based on the stored information, ensuring rehabilitation efficiency.

[0065] Furthermore, a specific formula is used to comprehensively score the patient's rehabilitation effect. The formula not only takes into account the improvement rate of vital signs, behavioral signs and rehabilitation plan completion rate, but also incorporates the patient's feedback evaluation and assigns a reasonable weight coefficient, providing rehabilitation therapists with intuitive and multi-dimensional evaluation results. At the same time, a collaboration and evaluation unit is set up to facilitate different rehabilitation therapists to fully understand the patient's current rehabilitation progress, adjust the rehabilitation strategy in a timely manner, and improve the patient's rehabilitation efficiency.

[0066] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A critical illness rehabilitation assistance system based on intelligent monitoring, characterized in that: It includes the following modules: A sensor module that collects patients' vital sign data, behavioral sign data, and environmental data; A data transmission module that is responsible for transmitting the data collected by the sensors to the cloud server; A status judgment module that compares the collected data with the standard data features, calculates the data deviation value, judges the patient's physical status according to the magnitude of the data deviation value, and optimizes the standard data features according to the differences in the patient's physical conditions; A plan formulation module that formulates a rehabilitation plan according to the result of the judged patient's physical status; A feedback and reminder module that sets safety thresholds for patients' vital signs and rehabilitation indicators. When the monitored data exceeds the normal range, it triggers an alarm mechanism and reminds the patient and medical staff to execute the plan content daily according to the rehabilitation plan; A data storage module that stores all the monitored data generated by the patient since admission and encrypts the patient's privacy information.

2. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 1, characterized in that: The sensor module includes a vital sign data acquisition unit, a behavioral sign data acquisition unit, an environmental data acquisition unit, and an actuator unit. The actuator unit is responsible for performing corresponding actions according to the collected data.

3. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 1, characterized in that: The data transmission module includes a data classification unit and an anti-interference unit. The data classification unit is used to classify the collected data, and the anti-interference unit is used to ensure the reliable transmission of data in a complex interference environment. The anti-interference unit adopts a redundant data transmission mechanism and uses multiple channels to transmit data.

4. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 1, characterized in that: In the status judgment module, the way to obtain the standard data features is as follows: collect the normal parameter data ranges of all patients of this type in this hospital and divide them into four groups according to age: juvenile, young, middle-aged, and elderly. For each parameter in each group, use deep learning algorithms to train a large amount of historical data, construct a data distribution model, identify and remove outliers from the data through the model, take the average value of the remaining data as the normal parameter central value, and calculate the standard deviation according to the central value combined with the data distribution model to determine the normal parameter data range for each age group. In the status judgment module, the formula for calculating the data deviation value is: where Z represents the deviation value, X represents the patient's current parameter value, P represents the normal parameter central value of this parameter, σ is the standard deviation, and y(x) represents a correction function obtained by learning the deviation situation in the case of similar parameter values in historical data through deep learning algorithms. The value of y(x) belongs to 0.8 - 1.

2. When 1 < Z ≤ 2, it is judged that the patient's status is slightly abnormal, and the detection frequency is increased to understand the patient's situation. When 2 < Z ≤ 3, it is judged that the patient's status is moderately abnormal, and the activities that affect the patient's parameters are stopped for in-depth medical examinations. When Z > 3, it is judged that the patient's status is severely abnormal, the emergency room alarm is triggered, a text message is sent to notify the emergency doctor, and first aid measures are taken. If the patient's parameters are abnormal for 3 consecutive days and no abnormal vital signs of the patient are detected, calculate the average value of the patient's parameters within 3 days and take the average value as the normal parameter central value of this patient.

5. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 1, characterized in that: The plan formulation module includes a state analysis unit, a plan generation unit and a plan adjustment unit. The state analysis unit is used to receive the judgment result transmitted by the state judgment module and analyze the patient's current rehabilitation stage. The patient's current rehabilitation stage is divided into early rehabilitation, middle rehabilitation and late rehabilitation. If the patient needs external force to assist in turning over limb activities, and the patient has more than 10 abnormal conditions in a week, the patient is judged to be in the early rehabilitation stage. If the patient can complete the limb activities of standing and waving hands, and the patient has less than 10 abnormal conditions in a week, the patient is judged to be in the middle rehabilitation stage. If the patient can independently complete daily activities of dressing and washing, and the patient has less than 5 abnormal conditions in a week, the patient is judged to be in the late rehabilitation stage. The plan generation unit is used to formulate a rehabilitation plan according to the patient's rehabilitation stage, and the plan adjustment unit is used to adjust the patient's rehabilitation plan according to the patient's situation after executing the plan.

6. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 5, characterized in that: In the plan generation unit, the rehabilitation plan is divided into an initial rehabilitation plan, a mid-term rehabilitation plan and a late rehabilitation plan. The initial rehabilitation plan is to detect vital signs every 15 minutes, and perform joint activities 3 times a day, each activity 10 times. The mid-term rehabilitation plan is to detect vital signs every 30 minutes, and perform standing activities 3 times a day, each time for 2 minutes. The late rehabilitation plan is to detect vital signs every 2 hours, and perform outdoor walking activities 3 times a day, each time for 10 minutes. In the plan adjustment unit, the specific method of adjusting the patient's rehabilitation plan is: if the patient has moderate and severe abnormalities during the activity, stop the activity for that day and reduce the activity time for the next day by 50%. If the patient only has slight abnormalities during the activity, maintain the current rehabilitation activity. If the patient has no abnormalities during the activity and the deviation value shows a downward trend, the activity time is increased by 50%.

7. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 5, characterized in that: The feedback and prompt module includes an alarm unit, a reminder unit, and a feedback unit. The alarm unit is used to monitor the patient's vital signs and behavioral signs. When the monitored data deviates from the set threshold, the alarm unit will trigger the alarm mechanism. The reminder unit is used to voice prompt the patient and the auxiliary personnel to implement the rehabilitation plan. The feedback unit is used to evaluate the patient's rehabilitation effect. The specific formula is as follows: E=ω1·G1+ω2·G2+ω3·G3+ω4·F Among them, E represents the comprehensive rehabilitation score, G1, G2 and G3 represent the vital signs improvement rate, behavioral signs improvement rate and rehabilitation plan completion rate respectively, F represents the patient's feedback evaluation, ω4 = 0.1, ω1, ω2 and ω3 represent the weight coefficients of the vital signs improvement rate, behavioral signs improvement rate and rehabilitation plan completion rate respectively, ω4 represents the weight coefficient of the patient's feedback evaluation, ω1+ω2+ω3+F=1, ω1:ω2:ω3=4:4:2, if 0.8≤E≤1, it means that the rehabilitation effect is excellent, and the above rehabilitation plan is continued; if 0.6≤E<0.8, it means that the rehabilitation effect is good; if E<0.6, it means that the rehabilitation effect is unsatisfactory, and a rehabilitation report is generated and sent to the plan formulation module to formulate a new rehabilitation plan.

8. The critical illness rehabilitation assistance system based on intelligent monitoring according to claim 1, characterized in that: The data storage module includes a collaboration and evaluation unit, which stores the patient's current treatment progress. The collaboration and evaluation unit is used for different rehabilitation therapists to understand the patient's current treatment progress.

9. The critical illness rehabilitation assistance method based on the intelligent monitoring critical illness rehabilitation assistance system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: The sensor module comprehensively collects the patient's vital signs, behavioral signs and environmental data; Step 2: The data transmission module uploads the collected data to the cloud server safely and efficiently; Step 3: The status judgment module compares the data, accurately determines the patient's status, and dynamically optimizes the standard data features; Step 4: The planning module tailors the rehabilitation plan based on the patient's condition; Step 5: The feedback and prompt module sets safety thresholds, issues timely alarms, and reminds users to implement rehabilitation plans; Step 6: The data storage module stores system data, protects patient privacy, and records patient treatment progress.

Images