A method and related device for dynamically evaluating early cardiopulmonary rehabilitation risk of ICU patients

Abstract

The application provides an ICU patient early cardiopulmonary rehabilitation risk dynamic evaluation method and related equipment, belongs to the technical field of rehabilitation risk evaluation, compares the vital sign data with the absolute safety threshold, and if it exceeds, it is determined that there is a risk, and a rehabilitation action restriction instruction is output. After the stress cycle ends, the actual recovery time length of the heart rate from the peak value to the resting level and the actual rising amplitude of the blood pressure peak value relative to the resting baseline are determined according to the identified heart rate peak value and blood pressure peak value. Based on the historical recovery time length and blood pressure rising amplitude of the patient in the same stress cycle, the expected recovery time length and the expected rising amplitude are determined, and then the stress risk level is determined. According to the stress risk level, the rehabilitation action intensity and the rest time of the next cycle of the patient are adjusted. The scheme of the application can realize individualized risk dynamic evaluation in the rehabilitation process.

Description

Technical Field

[0001] This application relates to the field of rehabilitation risk assessment technology, and in particular to a method and related equipment for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients. Background Technology

[0002] Early cardiopulmonary rehabilitation for ICU patients has been proven to effectively shorten mechanical ventilation time and hospital stay. However, these patients have fragile cardiovascular reserve, and rehabilitation training may induce myocardial ischemia, arrhythmia, or even cardiac arrest.

[0003] Currently, ICU rehabilitation risk control generally uses fixed threshold alarms, such as setting the upper limit of heart rate to a uniform 130 beats / min or estimating it using 220 minus age. This approach has obvious flaws in real-world scenarios—the same patient at different stages of the disease, such as before and after reducing the dosage of vasoactive drugs, has significantly different cardiac reserve capacity. Fixed thresholds are either too conservative, preventing the intensity of rehabilitation from being increased, or too lenient, leading to missed risks. More importantly, existing monitoring systems only alarm and prompt to stop when the threshold is exceeded, failing to answer a question that clinicians are truly concerned about: to what extent has the patient's heart recovered after completing a set of exercises, and can the intensity of the next set of exercises be increased? Existing studies have shown that the rate of heart rate recovery and the magnitude of blood pressure response after exercise are effective indicators for assessing autonomic nervous function and cardiovascular reserve. However, these indicators are currently only used for retrospective prognostic assessment and have never been incorporated into the real-time rehabilitation decision-making loop in the ICU. Therefore, how to achieve individualized dynamic risk assessment during the rehabilitation process based on the actual physiological recovery capacity of ICU patients to stress load has become a challenge for the industry. Summary of the Invention

[0004] Based on this, this application provides a method and related equipment for dynamic risk assessment of early cardiopulmonary rehabilitation in ICU patients to achieve individualized dynamic risk assessment during the rehabilitation process.

[0005] Firstly, this application provides a method for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients, comprising the following steps: Acquire vital sign data of ICU patients at rest and while performing rehabilitation exercise segments, wherein the rehabilitation exercise segments contain at least one complete stress cycle; During the execution of the action, the vital signs data are compared with the preset absolute safety threshold. If the threshold is exceeded, it is determined that there is a risk, and then the rehabilitation action restriction instruction is output. After the stress cycle ends, the actual recovery time of heart rate from peak to resting level and the actual increase of blood pressure relative to resting baseline are determined based on the identified peak heart rate and peak blood pressure. Based on the patient's historical recovery time and blood pressure rise during similar stress cycles, the expected recovery time and expected rise are determined. Then, based on the comparison between the actual recovery time and the actual rise and the expected recovery time and expected rise, the stress risk level is determined. The intensity of rehabilitation exercises and rest duration for the next cycle will be adjusted based on the stress risk level.

[0006] In some embodiments, the vital signs data include at least continuous heart rate data and continuous blood pressure data.

[0007] In some embodiments, the preset absolute safety threshold is pre-configured by the attending physician based on the patient's age, primary diagnosis, level of vasoactive drug use, and state of consciousness, and remains constant throughout the current rehabilitation assessment period.

[0008] In some embodiments, the actual recovery time is determined as follows: starting from the peak heart rate, the time when the heart rate first drops to no higher than the resting heart rate plus a preset allowable offset is calculated along the time axis backward, and the time difference between the two is the actual recovery time.

[0009] In some embodiments, determining the expected recovery time and expected increase in blood pressure based on the patient's historical recovery time and blood pressure rise during similar stress cycles specifically includes: From the patient’s own historical assessment records, the actual recovery time and actual increase in the same type of previous stress cycle as the current stress cycle were selected to obtain a historical recovery time sample sequence and a historical increase sample sequence. Based on the historical recovery duration sample sequence and the historical increase amplitude sample sequence, the expected recovery duration and the expected increase amplitude are determined respectively.

[0010] In some embodiments, determining the stress risk level based on comparisons between the actual recovery time and the actual increase in stress level and the expected recovery time and the expected increase in stress level specifically includes: The actual recovery time is compared with the upper and lower limits of the expected recovery time, and the actual increase is compared with the upper and lower limits of the expected increase to determine whether it exceeds the expected range. If neither of the two criteria exceeds the expected range, the stress risk level is assessed as low; if only one criterion exceeds the expected range, the stress risk level is assessed as medium; if both criteria exceed the expected range, the stress risk level is assessed as high.

[0011] In some embodiments, adjusting the intensity of rehabilitation activities and rest duration for the next cycle based on the stress risk level specifically includes: For low stress risk levels, the intensity of rehabilitation exercises will be increased by a preset step, while the rest time will be shortened by a preset step. For those at a medium stress risk level, maintain the current intensity of activity and rest duration. For high stress risk levels, the intensity of rehabilitation exercises will be reduced by a preset step, while the rest time will be extended by a preset step.

[0012] Secondly, this application provides a dynamic risk assessment system for early cardiopulmonary rehabilitation of ICU patients, including: The acquisition module is used to acquire vital sign data of ICU patients at rest and while performing rehabilitation exercise segments, wherein the rehabilitation exercise segments contain at least one complete stress cycle. The processing module is used to compare the vital sign data with a preset absolute safety threshold during the action execution period. If the threshold is exceeded, it is determined that there is a risk, and then the rehabilitation action restriction instruction is output. The processing module is also used to determine, after the stress cycle ends, the actual recovery time of the heart rate from the peak to the resting level, and the actual increase of the blood pressure peak relative to the resting baseline, based on the identified peak heart rate and peak blood pressure. The processing module is also used to determine the expected recovery time and expected increase based on the patient's historical recovery time and blood pressure rise in similar stress cycles, and then determine the stress risk level based on the comparison results of the actual recovery time and the actual increase with the expected recovery time and the expected increase. The execution module is used to adjust the intensity of the patient's rehabilitation movements and rest duration for the next cycle based on the stress risk level.

[0013] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described dynamic risk assessment method for early cardiopulmonary rehabilitation of ICU patients.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The method and related equipment for dynamic risk assessment of early cardiopulmonary rehabilitation in ICU patients provided in this application first acquire vital sign data of ICU patients at rest and during the execution of rehabilitation exercise segments. These rehabilitation exercise segments contain at least one complete stress cycle. This step provides a unified, complete, and traceable foundation of original physiological data, avoiding assessment bias caused by data fragmentation or missing baselines. Second, during the exercise execution period, the vital sign data are compared with preset absolute safety thresholds. If these thresholds are exceeded, a risk is identified, and a rehabilitation exercise restriction command is output. This step constructs an insurmountable physiological safety barrier during rehabilitation training. Once the heart rate or blood pressure exceeds the safety limit, a stop command is immediately output and an alarm is triggered, reducing the risk of serious adverse events such as myocardial ischemia and arrhythmia in ICU patients during early rehabilitation. Subsequently, after the stress cycle ends, the actual recovery time of the heart rate from the peak to the resting level is determined based on the identified peak heart rate and peak blood pressure. The step of determining the actual increase in blood pressure relative to the resting baseline transforms the patient's physiological response to stress load into a calculable objective indicator, providing standardized quantitative input for subsequent comparison with individualized expected ranges, thereby improving the objectivity of stress response assessment. Then, based on the patient's historical recovery time and blood pressure increase in similar stress cycles, the expected recovery time and expected increase are determined. Furthermore, based on the comparison results of the actual recovery time and actual increase with the expected recovery time and expected increase, respectively, the stress risk level is determined. This step dynamically generates an individualized expected range and compares it with the measured values ​​of the current cycle, allowing the risk assessment criteria to adaptively update as the patient's functional state changes. Finally, the intensity of rehabilitation activities and rest time for the next cycle are adjusted based on the stress risk level. In summary, the solution proposed in this application can achieve individualized dynamic risk assessment during the rehabilitation process based on the ICU patient's actual physiological recovery capacity to stress load. Attached Figure Description

[0016] Figure 1 This is an exemplary flowchart of a dynamic risk assessment method for early cardiopulmonary rehabilitation of ICU patients according to some embodiments of this application; Figure 2 This is a schematic diagram illustrating an application scenario of a dynamic evaluation data processing system according to some embodiments of this application; Figure 3 This is a schematic flowchart illustrating the process of determining stress risk level according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a dynamic risk assessment system for early cardiopulmonary rehabilitation of ICU patients, as shown in some embodiments of this application; Figure 5This is a schematic diagram of the structure of a computer device for implementing a method for dynamic risk assessment of early cardiopulmonary rehabilitation in ICU patients, according to some embodiments of this application. Detailed Implementation

[0017] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0018] refer to Figure 1 The figure is an exemplary flowchart of a dynamic risk assessment method for early cardiopulmonary rehabilitation of ICU patients according to some embodiments of this application. The dynamic risk assessment method for early cardiopulmonary rehabilitation of ICU patients mainly includes the following steps: In step 101, vital sign data of ICU patients are acquired during rest and while performing rehabilitation exercise segments, wherein the rehabilitation exercise segments contain at least one complete stress cycle.

[0019] In practice, obtaining vital sign data of ICU patients at rest and during rehabilitation exercise segments can be achieved as follows: First, before the patient performs any rehabilitation exercise, they are placed in a resting state as prescribed by the doctor, such as lying quietly supine for at least 5 minutes; heart rate and invasive arterial blood pressure signals are continuously collected using a bedside monitor to obtain continuous heart rate and blood pressure data. After excluding interference segments, the average value of all valid sampling points within a stable recording segment of no less than 3 minutes is taken as the resting baseline heart rate and resting baseline blood pressure values ​​for this assessment cycle; then, a standardized rehabilitation exercise segment is initiated by a rehabilitation therapist or programmed rehabilitation equipment. The rehabilitation exercise segment strictly includes a resting period, an exercise period, and a recovery period in sequence, forming a complete stress cycle. For example, the resting period involves maintaining a quiet supine position for 1 minute, the exercise period involves performing 2 minutes of active upper limb lifting exercises, and the recovery period involves maintaining a quiet supine position for 3 minutes. Throughout the entire segment, the bedside monitor continuously records heart rate and blood pressure data, and simultaneously records the timestamps of the start time, stop time, and end time of the recovery period. The collected continuous vital sign data with time stamps are output together with the resting baseline heart rate and resting baseline blood pressure values. The vital sign data includes at least continuous heart rate data and continuous blood pressure data.

[0020] The above steps can provide a unified, complete, and traceable original physiological data basis for subsequent individualized stress response quantification and risk level assessment, avoiding assessment bias caused by data fragmentation or missing baseline.

[0021] In some embodiments, reference Figure 2As shown in the figure, this figure is a schematic diagram of the application scenario of the dynamic assessment data processing system shown in some embodiments of this application. The figure includes three main components: acquisition device, server and data storage device. The acquisition device is responsible for collecting vital sign data of ICU patients at rest and when performing rehabilitation movements, and sending the collected vital sign data to the server through the communication network. The dynamic assessment data processing system runs in the server, and the server stores the processing results in the data storage device and visualizes them.

[0022] In step 102, during the action execution period, the vital signs data are compared with a preset absolute safety threshold. If the threshold is exceeded, it is determined that there is a risk, and then a rehabilitation action restriction instruction is output.

[0023] As a preferred embodiment, during the action execution period, the vital sign data is compared with a preset absolute safety threshold. If the threshold is exceeded, a risk is determined, and a rehabilitation action restriction instruction is output. This can be achieved through the following steps: Retrieve a preset absolute safety threshold that matches the patient's current condition. During the execution of the action, the continuous heart rate data and continuous blood pressure data in the vital signs data are compared with the absolute safety threshold in real time; If any parameter in the continuous heart rate data or the continuous blood pressure data exceeds the absolute safety threshold, a risk is determined, and a rehabilitation movement restriction instruction is output.

[0024] Preferably, retrieving the preset absolute safety threshold matching the patient's current condition can be achieved in the following way: During the initialization phase, the attending physician selects a set of inviolable physiological safety limits corresponding to the patient's current condition from the system's built-in threshold configuration table based on the patient's age, primary diagnosis, current level of vasoactive drug use, and level of consciousness. This set of physiological safety limits includes at least the absolute safety upper limit of heart rate, the absolute safety upper limit of systolic blood pressure, and the absolute safety lower limit of systolic blood pressure. For example, for a patient in the recovery period of acute myocardial infarction who is not using vasopressors, the absolute safety upper limit of heart rate can be set to 130 beats / min, the absolute safety upper limit of systolic blood pressure can be set to 180 mmHg, and the absolute safety lower limit of systolic blood pressure can be set to 90 mmHg. The preset absolute safety threshold remains constant throughout the current rehabilitation assessment cycle and is loaded into the module corresponding to real-time risk comparison for sequential retrieval. In other embodiments, other methods can also be used to preset the absolute safety threshold, which are not limited here.

[0025] In addition, during the execution period of the action, the real-time comparison of continuous heart rate data and continuous blood pressure data in the vital signs data with the absolute safety thresholds can be achieved in the following way: starting from the start of the action period of the rehabilitation action segment, the module corresponding to the real-time risk comparison immediately compares each frame of heart rate and blood pressure value transmitted from the bedside monitor after artifact filtering with the preset absolute safety thresholds for the upper limit of absolute safety of heart rate, the upper limit of absolute safety of systolic blood pressure, and the lower limit of absolute safety of systolic blood pressure, to determine whether the current heart rate value is higher than the upper limit of absolute safety of heart rate and whether the current systolic blood pressure value is higher than the upper limit of absolute safety of systolic blood pressure or lower than the lower limit of absolute safety of systolic blood pressure. This comparison process continues during the execution period of the action until the action stops.

[0026] Furthermore, if any parameter in the continuous heart rate data or the continuous blood pressure data exceeds the absolute safety threshold, a risk is determined, and a rehabilitation movement restriction instruction is output. This can be achieved in the following way: During real-time comparison, once any of the following situations is detected—the current heart rate value being higher than the absolute safety upper limit, the current systolic blood pressure value being higher than the absolute safety upper limit, or the current systolic blood pressure value being lower than the absolute safety lower limit—the risk flag is immediately set to valid, an unacceptably high risk is determined in the current stress cycle, and a rehabilitation movement restriction instruction is generated. The semantics of this rehabilitation movement restriction instruction are to immediately stop the current rehabilitation movement and return to the resting position. Simultaneously, the bedside monitor is activated to issue an audible and visual alarm, and the specific parameter type, the value exceeding the limit, and the precise time of the exceeding the limit that triggered the preset absolute safety threshold are recorded as a high-risk event marker within the stress cycle for subsequent review and analysis. Other methods can also be used in other embodiments, which are not limited here.

[0027] It should be noted that the above steps can build an insurmountable physiological safety barrier during rehabilitation training. Once the heart rate or blood pressure exceeds the safety limit, a stop command will be immediately output and an alarm will be triggered, reducing the risk of serious adverse events such as myocardial ischemia and arrhythmia in ICU patients during early rehabilitation.

[0028] In step 103, after the stress cycle ends, the actual recovery time of the heart rate from the peak to the resting level and the actual increase of the blood pressure peak relative to the resting baseline are determined based on the identified peak heart rate and peak blood pressure.

[0029] In some embodiments, after the stress cycle ends, determining the actual recovery time of heart rate from peak to resting level and the actual increase in blood pressure relative to resting baseline, based on the identified peak heart rate and peak blood pressure, can be achieved through the following steps: After the stress cycle ends, the peak heart rate and peak blood pressure are identified from the vital signs data stream; Starting from the peak heart rate moment, the time difference between the moment when the heart rate first drops to no higher than the resting heart rate plus a preset allowable offset is calculated along the time axis backwards, and the actual recovery time is the actual recovery time. Determine the actual increase in blood pressure peak relative to the resting baseline blood pressure value.

[0030] The identification of the peak heart rate and peak blood pressure from the vital signs data stream after the stress cycle ends can be achieved in the following way: After the stress cycle ends, review all continuous heart rate and blood pressure data within the range from the start of the action to 30 seconds after the action stops during the stress cycle, and use a sliding window extreme value search algorithm to find the maximum value in the heart rate data. Record the time point corresponding to the maximum value as the peak heart rate moment. At the same time, find the maximum value in the blood pressure data and record the maximum blood pressure as the peak blood pressure moment.

[0031] Preferably, the actual recovery time can be calculated by counting the moment when the heart rate first drops to no higher than the resting heart rate plus a preset allowable offset, starting from the peak heart rate. This can be achieved by scanning the heart rate data point by point along the time axis from the peak heart rate, finding the moment when the heart rate value drops to no higher than the resting baseline heart rate value plus a preset allowable offset. The preset allowable offset is used to define the acceptable fluctuation range of the heart rate recovering from the peak to near the resting level, and its value is determined based on the physiological coefficient of variation of the heart rate signal. By default, this allowable offset is set to 5% of the resting heart rate value. For example, if a patient's resting heart rate is 80 beats / min, the allowable deviation is 80 × 5% = 4 beats / min. That is, a heart rate recovery to no more than 84 beats / min is considered to have met the recovery standard. This percentage coefficient can be adjusted in the configuration interface according to the monitoring device's sampling accuracy and clinical experience. The recommended adjustment range is 3% to 8%. The time difference between this moment and the peak heart rate moment is taken as the actual recovery time of this stress cycle. If, within the preset recovery observation window, for example, within 5 minutes from the peak heart rate moment, all values ​​in the heart rate data fail to meet the condition, the actual recovery time is recorded as the maximum duration of the recovery observation window, with an incomplete recovery marker attached.

[0032] The actual increase in blood pressure relative to the resting baseline blood pressure value can be determined as follows: First, identify the peak systolic blood pressure during the stress cycle; if the peak systolic blood pressure is greater than or equal to the resting baseline systolic blood pressure, then the actual increase = peak systolic blood pressure - resting baseline systolic blood pressure; if the peak systolic blood pressure is less than the resting baseline systolic blood pressure, it indicates that the patient has a blood pressure drop response after stress, and the actual increase is recorded as a negative value, and an additional blood pressure drop warning sign is generated. This negative value itself will be used in subsequent comparisons with the lower limit of the expected increase (i.e., a negative value) to identify the risk of excessive blood pressure response.

[0033] The above steps can transform the patient's physiological response to stress load into calculable objective indicators, providing standardized quantitative input for subsequent comparison and judgment with individualized expected ranges, thereby improving the objectivity of stress response assessment.

[0034] In step 104, based on the patient's historical recovery time and blood pressure rise in similar stress cycles, the expected recovery time and expected rise are determined. Then, based on the comparison between the actual recovery time and the actual rise and the expected recovery time and expected rise, the stress risk level is determined.

[0035] In some embodiments, determining the expected recovery time and expected increase in blood pressure based on the patient's historical recovery time and blood pressure rise during similar stress cycles can be achieved through the following steps: From the patient’s own historical assessment records, the actual recovery time and actual increase in the same type of previous stress cycle as the current stress cycle were selected to obtain a historical recovery time sample sequence and a historical increase sample sequence. Based on the historical recovery duration sample sequence and the historical increase amplitude sample sequence, the expected recovery duration and the expected increase amplitude are determined respectively.

[0036] As a preferred embodiment, the so-called similar past stress cycles refer to rehabilitation movement segments performed in past historical cycles that have the same movement pattern classification as rehabilitation movement segments in the current stress cycle. The movement pattern classification includes at least: passive joint range of motion training, active antigravity training (such as arm and leg raises in bed), seated balance training, bedside standing training, etc. Only when the movement pattern classification of the historical cycle and the current cycle are completely consistent are they identified as similar stress cycles. For example, if the current cycle is performed with active upper limb lifting training, only cycles that are also performed with active upper limb lifting training will be selected from the historical records, and the cycle data of passive ankle pump training or bedside sitting training will not be included in the calculation.

[0037] In practice, the actual recovery time and actual increase in intensity from previous stress cycles of the same type as the current stress cycle are selected from the patient's own historical assessment records. This results in a historical recovery time sample sequence and a historical increase in intensity sample sequence. This can be achieved as follows: A historical assessment record chain is maintained for each patient. Each record in this chain is accompanied by an action type label and a timestamp. The action type label identifies the type of rehabilitation action segment performed in each stress cycle, such as passive ankle pumps, active upper limb lifting, or bedside sitting. When it is necessary to perform individualized expectation calculations for the current stress cycle, the patient's own historical assessment records are queried. The system retrieves all historical cycle records within the past 48 hours that have the same action type label as the current stress cycle and have been fully completed. It then extracts the actual recovery time and actual increase rate corresponding to each historical cycle to form a historical recovery time sample sequence and a historical increase rate sample sequence. If the number of historical cycle records that meet the above conditions is less than the preset minimum number of cases, for example, less than 3 times, the query time window is automatically expanded to the past 72 hours. If it is still insufficient, reference distribution data of the same type of action and the same disease group as the patient is called as a cold start supplement. The reference distribution data comes from the 25th to 75th percentile interval of similar patient samples in the historical desensitization database.

[0038] In a preferred embodiment, determining the expected recovery duration and expected increase based on the historical recovery duration sample sequence and the historical increase amplitude sample sequence can be achieved through the following steps: The historical recovery duration sample sequence and the historical increase amplitude sample sequence are sorted respectively; Based on the sorting results, a specified quantile interval of the historical recovery duration sample sequence is taken as the expected recovery duration, and a specified quantile interval of the historical rise amplitude sample sequence is taken as the expected rise amplitude.

[0039] The sorting of the historical recovery duration sample sequence and the historical rise amplitude sample sequence can be achieved in the following way: after obtaining the historical recovery duration sample sequence and the historical rise amplitude sample sequence, the values ​​of each sample point in the two sample sequences are sorted in ascending order from smallest to largest to obtain an ordered historical recovery duration sample sequence and an ordered historical rise amplitude sample sequence.

[0040] In addition, based on the sorting results, the specified quantile interval of the historical recovery duration sample sequence is taken as the expected recovery duration, and the specified quantile interval of the historical rise amplitude sample sequence is taken as the expected rise amplitude. This can be achieved in the following way: the 25th percentile of the historical recovery duration sample sequence is taken as the lower limit and the 75th percentile as the upper limit to form the expected recovery duration; the 25th percentile of the historical rise amplitude sample sequence is taken as the lower limit and the 75th percentile as the upper limit to form the expected rise amplitude. The specified quantile interval is the 25th percentile as the lower limit and the 75th percentile as the upper limit. In other embodiments, the specified quantile interval can also be set by other methods, which are not limited here.

[0041] In some embodiments, reference Figure 3 As shown in the figure, this is a flowchart illustrating the process of determining the stress risk level in some embodiments of this application. In this embodiment, the stress risk level is determined by comparing the actual recovery time and the actual increase with the expected recovery time and the expected increase, respectively. This can be achieved through the following steps: In step 1041, the actual recovery time is compared with the upper and lower limits of the expected recovery time, and the actual increase is compared with the upper and lower limits of the expected increase to determine whether it exceeds the expected range. In step 1042, if neither of the two conditions exceeds the expected range, the stress risk level is assessed as low; if only one condition exceeds the expected range, the stress risk level is assessed as medium; if both conditions exceed the expected range, the stress risk level is assessed as high.

[0042] Preferably, comparing the actual recovery time with the upper and lower limits of the expected recovery time, and comparing the actual increase with the upper and lower limits of the expected increase, to determine whether it exceeds the expected range can be achieved in the following way: Read the lower and upper limits of the expected recovery time, and compare the actual recovery time of the current stress cycle with the lower and upper limits respectively: if the actual recovery time is less than the lower limit or greater than the upper limit, it is determined that the actual recovery time has exceeded the expected range; otherwise, it is determined that it is within the expected range. Read the lower and upper limits of the expected increase, and compare the actual increase of the current stress cycle with the lower and upper limits respectively: if the actual increase is less than the lower limit or greater than the upper limit, it is determined that the actual increase has exceeded the expected range; otherwise, it is determined that it is within the expected range.

[0043] In practice, if neither of the two parameters exceeds the expected range, the stress risk level is assessed as low; if only one parameter exceeds the expected range, the stress risk level is assessed as medium; and if both parameters exceed the expected range, the stress risk level is assessed as high. This can be achieved by comparing the actual recovery time and the actual increase in stress with the expected range, and then using a predetermined rating rule for comprehensive determination. The rating rule is as follows: if both the actual recovery time and the actual increase in stress are within their expected range, the current stress cycle is assessed as low stress risk; if only one of the actual recovery time and the actual increase in stress exceeds its corresponding range, the stress risk level is assessed as high. If the actual recovery time and the actual increase both exceed their respective expected ranges, the current stress cycle is assessed as a medium stress risk level. If both the actual recovery time and the actual increase exceed their respective expected ranges, the current stress cycle is assessed as a high stress risk level. Furthermore, for the medium stress risk level, the degree of risk can be distinguished based on the specific extent to which the actual recovery time exceeds the upper limit of its expected range. For example, if the actual recovery time under the medium stress risk level exceeds the upper limit of its expected range by more than 30%, the stress risk level is raised by one level. In other embodiments, other methods can also be used to assess the stress risk level of the current stress cycle, which are not limited here.

[0044] The above steps can dynamically generate an individualized expected range and compare it with the measured value of the current cycle, thereby automatically assessing the risk level of the current stress cycle and making the risk assessment criteria adaptively updated as the patient's functional state changes.

[0045] In step 105, the intensity of the patient's rehabilitation activities and the duration of rest are adjusted according to the stress risk level for the next cycle.

[0046] As a preferred embodiment, a rehabilitation intensity adjustment mapping table can be pre-constructed. This mapping table binds the stress risk level with specific rehabilitation action intensity adjustment strategies and rest duration adjustment strategies. For example, for a low stress risk level, the rehabilitation action intensity adjustment strategy is preset to increase the current action intensity by a preset step, and the rest duration adjustment strategy is preset to shorten the rest duration by a preset step. For a medium stress risk level, the rehabilitation action intensity adjustment strategy is preset to maintain the current action intensity, and the rest duration adjustment strategy is preset to maintain the current rest duration. For a high stress risk level, the rehabilitation action intensity adjustment strategy is preset to decrease the current action intensity by a preset step, and the rest duration adjustment strategy is preset to extend the rest duration by a preset step. In other embodiments, other methods can be used to set the rehabilitation action intensity adjustment strategy and rest duration adjustment strategy, which are not limited here.

[0047] In practice, the intensity of rehabilitation movements and the duration of rest are adjusted for the next cycle based on the stress risk level-matched rehabilitation movement intensity adjustment strategy and rest duration adjustment strategy.

[0048] The intensity of rehabilitation exercises is defined using a step-by-step quantitative model. Taking active upper limb lifting training as an example, the preset intensity steps are divided into 5 levels from low to high: Level 1 (5 times / set, lifting angle 30°), Level 2 (10 times / set, lifting angle 45°), Level 3 (15 times / set, lifting angle 60°), Level 4 (20 times / set, lifting angle 75°), and Level 5 (25 times / set, lifting angle 90°). The preset rest time is based on a 30-second interval.

[0049] Therefore, adjusting the intensity of rehabilitation activities and rest duration for the next cycle based on the aforementioned stress risk level can be achieved through the following steps: For low stress risk levels, increase the intensity of rehabilitation exercises by a preset step, such as from level 2 to level 3, while shortening the rest time by a preset step, such as from 180 seconds to 150 seconds. For those at a medium stress risk level, maintain the current intensity of activity and rest duration. For high stress risk levels, reduce the intensity of rehabilitation exercises by a preset step, for example, from level 3 to level 2, while extending the rest time by a preset step, for example, from 150 seconds to 180 seconds.

[0050] In addition, for different types of rehabilitation movements, such as passive exercise and bedside sitting training, the specific parameters of their intensity steps, such as number of repetitions, angle, resistance, and duration, can be preset with corresponding grading tables. However, all step adjustments should follow the principle of gradual increase and gradual decrease.

[0051] It also includes using the adjusted intensity and rest duration of rehabilitation movements to guide the execution of rehabilitation movements in the next cycle. Specifically, the adjusted intensity and rest duration of rehabilitation movements are encapsulated into a structured execution instruction for the next cycle. This instruction explicitly includes the specific movement name or movement code to be performed in the next stress cycle, the movement intensity parameters, and the rest duration during the recovery period. This execution instruction is sent to the terminal device responsible for controlling the rehabilitation process or displayed to the medical staff performing the treatment, so that the next stress cycle is executed with the adjusted intensity and rest duration of rehabilitation movements. Only after the execution instruction for the next cycle is loaded and used as the operational basis for the start of the next stress cycle is the next assessment cycle allowed, thus forming a closed loop from stress risk level assessment to adaptive adjustment of rehabilitation movements.

[0052] It should be noted that the solution provided in this application is based on computer program execution, and its purpose is to process and analyze vital sign data to generate risk assessment results and intensity adjustment suggestions for guiding rehabilitation training, and is not directly aimed at the diagnosis or treatment of diseases. The rehabilitation movements are performed by rehabilitation equipment or guided by medical personnel based on the assessment results. This solution does not contain any interventional procedures performed on the human body.

[0053] Furthermore, it should be noted that this application constructs a two-layer risk control architecture: the first layer is an absolute safety threshold, serving as an inviolable physiological red line to prevent immediately occurring high-risk events, such as exercise-induced severe hypertension; the second layer is an individualized dynamic assessment model, which assesses the relative stress load based on the patient's own historical recovery ability data, for fine-tuning the rehabilitation plan. The absolute safety threshold remains constant because its role is to define absolute no-go zones, while the adaptive updating of the dynamic assessment model is responsible for finding the optimal rehabilitation intensity within the safe zone. The functional levels and update mechanisms of the two are completely different, solving the technical challenge that a single fixed threshold cannot adapt to the dynamic changes in the patient's recovery ability.

[0054] In another aspect, in some embodiments, this application provides a dynamic risk assessment system for early cardiopulmonary rehabilitation of ICU patients, with reference to... Figure 4 The figure is a schematic diagram of the structure of a dynamic risk assessment system for early cardiopulmonary rehabilitation of ICU patients according to some embodiments of this application. The dynamic risk assessment system for early cardiopulmonary rehabilitation of ICU patients includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire vital sign data of ICU patients at rest and when performing rehabilitation exercise segments, wherein the rehabilitation exercise segments contain at least one complete stress cycle. Processing module 402, in this application, is mainly used to compare the vital sign data with a preset absolute safety threshold during the action execution period. If the threshold is exceeded, it is determined that there is a risk, and then a rehabilitation action restriction instruction is output. The processing module 402 described in this application is also used to determine, after the stress cycle ends, the actual recovery time of the heart rate from the peak to the resting level, and the actual increase of the blood pressure peak relative to the resting baseline, based on the identified heart rate peak and blood pressure peak. The processing module 402 described in this application is further configured to determine the expected recovery time and expected increase based on the patient's historical recovery time and blood pressure rise in similar stress cycles, and then determine the stress risk level based on the comparison results of the actual recovery time and the actual increase with the expected recovery time and the expected increase. The execution module 403 in this application is mainly used to adjust the intensity of the patient's rehabilitation movements and rest duration in the next cycle according to the stress risk level.

[0055] The modules in the aforementioned dynamic risk assessment system for early cardiopulmonary rehabilitation of ICU patients can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0056] In another embodiment, this application provides a computer device, which may be a server, and its internal structure diagram may be as follows. Figure 5 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores dynamic risk assessment data for early cardiopulmonary rehabilitation of ICU patients. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for dynamic risk assessment of early cardiopulmonary rehabilitation of ICU patients.

[0057] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0058] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above embodiment of the dynamic assessment method for early cardiopulmonary rehabilitation risk of ICU patients.

[0059] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above embodiment of the method for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients.

[0060] In one embodiment, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps described in the embodiment of the dynamic risk assessment method for early cardiopulmonary rehabilitation of ICU patients.

[0061] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0062] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0063] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients, characterized in that, The steps include the following: Acquire vital sign data of ICU patients at rest and while performing rehabilitation exercise segments, wherein the rehabilitation exercise segments contain at least one complete stress cycle; During the execution of the action, the vital signs data are compared with the preset absolute safety threshold. If the threshold is exceeded, it is determined that there is a risk, and then the rehabilitation action restriction instruction is output. After the stress cycle ends, the actual recovery time of heart rate from peak to resting level and the actual increase of blood pressure relative to resting baseline are determined based on the identified peak heart rate and peak blood pressure. Based on the patient's historical recovery time and blood pressure rise during similar stress cycles, the expected recovery time and expected rise are determined. Then, based on the comparison between the actual recovery time and the actual rise and the expected recovery time and expected rise, the stress risk level is determined. The intensity of rehabilitation exercises and rest duration for the next cycle will be adjusted based on the stress risk level.

2. The method as described in claim 1, characterized in that, The vital signs data include at least continuous heart rate data and continuous blood pressure data.

3. The method as described in claim 1, characterized in that, The preset absolute safety threshold is pre-configured by the attending physician based on the patient's age, primary diagnosis, level of vasoactive drug use, and state of consciousness, and remains constant throughout the current rehabilitation assessment period.

4. The method as described in claim 1, characterized in that, The actual recovery time is determined as follows: starting from the peak heart rate, calculate the moment when the heart rate first drops to no higher than the resting heart rate plus a preset allowable offset along the time axis. The time difference between the two is the actual recovery time.

5. The method as described in claim 1, characterized in that, Based on the patient's historical recovery time and blood pressure rise during similar stress cycles, the expected recovery time and expected rise are determined specifically as follows: From the patient’s own historical assessment records, the actual recovery time and actual increase in the same type of previous stress cycle as the current stress cycle were selected to obtain a historical recovery time sample sequence and a historical increase sample sequence. Based on the historical recovery duration sample sequence and the historical increase amplitude sample sequence, the expected recovery duration and the expected increase amplitude are determined respectively.

6. The method as described in claim 1, characterized in that, The stress risk level is determined by comparing the actual recovery time and the actual increase with the expected recovery time and the expected increase, respectively. Specifically, this includes: The actual recovery time is compared with the upper and lower limits of the expected recovery time, and the actual increase is compared with the upper and lower limits of the expected increase to determine whether it exceeds the expected range. If neither of the two criteria exceeds the expected range, the stress risk level is assessed as low; if only one criterion exceeds the expected range, the stress risk level is assessed as medium; if both criteria exceed the expected range, the stress risk level is assessed as high.

7. The method as described in claim 1, characterized in that, Adjusting the intensity of rehabilitation exercises and rest duration for the next cycle based on the stated stress risk level specifically includes: For low stress risk levels, the intensity of rehabilitation exercises will be increased by a preset step, while the rest time will be shortened by a preset step. For those at a medium stress risk level, maintain the current intensity of activity and rest duration. For high stress risk levels, the intensity of rehabilitation exercises will be reduced by a preset step, while the rest time will be extended by a preset step.

8. A dynamic risk assessment system for early cardiopulmonary rehabilitation in ICU patients, characterized in that, include: The acquisition module is used to acquire vital sign data of ICU patients at rest and while performing rehabilitation exercise segments, wherein the rehabilitation exercise segments contain at least one complete stress cycle. The processing module is used to compare the vital sign data with a preset absolute safety threshold during the action execution period. If the threshold is exceeded, it is determined that there is a risk, and then the rehabilitation action restriction instruction is output. The processing module is also used to determine, after the stress cycle ends, the actual recovery time of the heart rate from the peak to the resting level, and the actual increase of the blood pressure peak relative to the resting baseline, based on the identified peak heart rate and peak blood pressure. The processing module is also used to determine the expected recovery time and expected increase based on the patient's historical recovery time and blood pressure rise in similar stress cycles, and then determine the stress risk level based on the comparison results of the actual recovery time and the actual increase with the expected recovery time and the expected increase. The execution module is used to adjust the intensity of the patient's rehabilitation movements and rest duration for the next cycle based on the stress risk level.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for dynamic assessment of early cardiopulmonary rehabilitation risk in ICU patients as described in any one of claims 1 to 7.

Images