Intensive care unit informatization infection monitoring system and method

Abstract

The invention discloses an informatization infection monitoring system and method for an intensive care unit, and relates to the field of medical data monitoring, and the informatization infection monitoring system comprises a monitoring control module which is used as a monitoring personnel observation and interaction end and is used for editing and sending operation instructions of all function modules; the acquisition module is used for acquiring control permissions of a plurality of pre-deployed visual inspection devices with adjustable visual angles and acquiring wound images of different body positions of a patient in real time; the body position adjusting unit is used for constructing an adjusting model, generating a series of body position adjusting actions including a plurality of stages and submitting the series of body position adjusting actions to the monitoring control module based on the current wound state in combination with the patient medical record data and the wound state parameters, and monitoring the execution state; through medical records of the patient and real-time wound parameters, a body position adjusting scheme according with the specific condition of the patient is generated, the deterioration index of the wound is evaluated in real time, potential risks of the wound are actively recognized, an alarm is given out immediately when a deterioration sign appears, and manual intervention lag is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data monitoring, and in particular to an information-based infection monitoring system and method for an intensive care unit. Background Art

[0002] Patients in intensive care units are usually in critical condition and face a high risk of complications, especially infection, which directly affects the patient's recovery and survival rate. Therefore, the monitoring and management of infection has become particularly important. With the rapid development of information technology, especially the application of technologies such as artificial intelligence, the Internet of Things and big data analysis, real-time monitoring and analysis of medical data have become possible, which provides technical support for the development of intensive care units. In addition, modern medicine is turning to personalized medicine, and the care of critically ill patients requires refined management based on the specific conditions of the patients. In the field of trauma intensive care, monitoring of patient wounds is particularly important. Existing technologies rely on manual observation or traditional visual monitoring technology, which can easily lead to recognition errors when the wound status distribution is inconsistent or the patient's body position changes. Changes in the patient's body position or even slight movements may cause the monitoring equipment to be unable to accurately capture changes in the wound status, thereby causing misjudgment. It is difficult to actively provide a body position adjustment path to identify potential risks. There is a lack of real-time dynamic analysis capabilities, and it is impossible to respond quickly when the wound worsens, delaying the treatment opportunity. The ability to perform trend analysis and recovery prediction on changes in wound status is insufficient. Summary of the invention

[0003] 1. Technical issues to be resolved In view of the above-mentioned shortcomings of the prior art, the present invention provides an information-based infection monitoring system and method for an intensive care unit, which can effectively solve the problems of the prior art.

[0004] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention discloses an information-based infection monitoring system for an intensive care unit, comprising: The monitoring control module, as the monitoring personnel's observation and interaction terminal, edits and sends the operating instructions of each functional module; The acquisition module is used to obtain the control authority of several pre-deployed visual detection devices with adjustable viewing angles, and to collect wound images of patients in different body positions in real time; The state recognition module is used to extract the location, area, color and exudate state characteristics of the wound, and integrate and output them as standardized wound state parameters; The body position adjustment unit is used to construct an adjustment model, based on the current wound state, combined with the patient's medical record data and wound state parameters, to generate a series of body position adjustment actions containing several stages and submit them to the monitoring control module, and monitor the execution status; The deterioration analysis module is used to collect wound data again through the acquisition module after each stage of the body position adjustment of the body position adjustment unit, compare the data with the state before the adjustment, calculate the deterioration index, and evaluate the deterioration index risk through threshold judgment and trend analysis processing; Dynamic control module, used to immediately terminate the current series of adjustment actions when the deterioration index exceeds the preset safety threshold, save the current state snapshot and generate a termination report; The coefficient prediction module is used to build a prediction model. By integrating the wound data before and after adjustment, the prediction model is input to calculate the recovery coefficient in the next few cycles and trigger a graded alarm according to the coefficient interval; The strategy optimization module is used to trigger when the current series of posture adjustment actions are all completed and the recovery coefficient is higher than the preset standard, send an adjustment strategy with increased adjustment intensity to the posture adjustment unit, and replace the original series of posture adjustment actions after confirmation by the monitoring control module.

[0005] Furthermore, the posture adjustment unit is provided with submodules at the lower level, and the submodules include: a strategy generation module, an interactive prompt module and an execution monitoring module, the strategy generation module is interactively connected with the interactive prompt module via a wireless network, and the interactive prompt module is interactively connected with the execution monitoring module via a wireless network, wherein: A strategy generation module is used to train the adjustment module based on historical patient wound information, healing stages, and adjusted positions as samples, obtain the current patient wound information and healing stage input adjustment model, and output several verified direction and amplitude position adjustment actions to form an action series; The interactive prompt module is used to push the generated posture adjustment actions to the monitoring control module in the form of visual instructions, support confirmation of execution or manual correction, record operation feedback, and trigger another reminder if there is no response within the timeout period; The execution monitoring module is used to track the patient's position changes in real time through the acquisition module and verify whether the action execution accuracy meets the preset threshold.

[0006] Furthermore, during the verification phase, the execution monitoring module triggers the module to jump. If no execution deviation is detected, the dynamic control module is adjusted to further run. If an execution deviation is detected, the strategy generation module is automatically triggered to issue correction instructions or suspend adjustment actions for the posture amplitude, direction, priority and timestamp.

[0007] Furthermore, the process of the deterioration analysis module evaluating the deterioration index risk is as follows: After each stage of adjustment, the wound redness and swelling saturation and exudate contour area were extracted, and the local temperature gradient was quantified by combining the wound infrared thermal imaging data to form a three-channel physiological index; A sliding window algorithm is used, with a window length greater than three consecutive adjustment cycles, to calculate the dynamic change rate of each indicator; By presetting the dynamic weights of each indicator, a comprehensive deterioration index is generated, and the change trend is analyzed by combining the data adjusted in several stages; Automatically match the preset wound severity grading standards according to the patient's wound deterioration trend, and adjust the safety threshold range in real time; When a single detection is affected by body position occlusion, a body position adjustment instruction is generated to the body position adjustment unit as a reference.

[0008] Furthermore, the dynamic control module and the coefficient prediction module are interactively connected to a graded warning module through a wireless network. The graded warning module is used to provide a graded alarm strategy to the monitoring control module, which is triggered when the deterioration index of the dynamic control module exceeds a preset safety threshold, and is triggered when the corresponding grade of the recovery coefficient obtained by the coefficient prediction module reaches a preset alarm standard, and provides several intensity alarm strategies according to the trigger level.

[0009] Furthermore, the monitoring control module is interactively connected to a knowledge base module via a wireless network, and the knowledge base module is used to store adjustment records, deterioration indexes and recovery coefficients of all patients, build an infection monitoring knowledge base, and mine potential rules between specific body position adjustments and wound healing speeds through association rules, and submit them to the body position adjustment unit as a reference for strategy generation.

[0010] Furthermore, the monitoring control module is interactively connected to the acquisition module through a wireless network, the acquisition module is interactively connected to the state recognition module through a wireless network, the state recognition module is interactively connected to the position adjustment unit through a wireless network, the position adjustment unit is interactively connected to the deterioration analysis module through a wireless network, the deterioration analysis module is interactively connected to the dynamic control module through a wireless network, the dynamic control module is interactively connected to the coefficient prediction module through a wireless network, and the coefficient prediction module is interactively connected to the strategy optimization module through a wireless network.

[0011] The information-based infection monitoring method for the intensive care unit includes the following steps: Step 1: Use pre-deployed visual inspection equipment with adjustable viewing angle to collect real-time wound images and infrared thermal imaging data of patients in different body positions, extract the morphological features of the wound location, area, color and exudate contour, combine infrared thermal imaging data to quantify the temperature gradient around the wound, generate morphological, exudate and temperature physiological indicators, integrate all features, and output standardized wound status parameters; Step 2: Based on the historical patient data, the adjustment model is trained and combined with the wound status parameters and medical record data of the current patient to generate a series of posture adjustment actions including direction, amplitude and priority, and the action series is pushed to the monitoring personnel interaction terminal in the form of visual instructions; Step 3: Use visual inspection equipment to monitor the patient's position changes in real time to verify whether the action execution reaches the preset direction and amplitude accuracy thresholds. If an execution deviation is detected, it will automatically trigger a correction instruction or pause the adjustment action; Step 4: After each stage of adjustment, the wound data was recollected to extract the dynamic change rate of redness and swelling saturation, exudate area, and local temperature gradient, and the weighted comprehensive deterioration index of each index was calculated using a sliding window algorithm; Step 5: Dynamically adjust the safety threshold interval based on individual differences and historical data of patients. If body position occlusion is detected, resulting in data abnormality, trigger a readjustment instruction; Step 6: If the deterioration index exceeds the safety threshold, immediately terminate the current adjustment action, save the current status snapshot and generate a termination report including the cause analysis, integrate the data before and after the adjustment, calculate the recovery coefficient in the future cycle through the prediction model, trigger a graded alarm according to the recovery coefficient interval, and push it to the medical staff terminal; Step 7: When the series of adjustment actions are completed and the recovery coefficient is higher than the preset standard, the current strategy is determined to be effective, and a new strategy corresponding to the adjustment amplitude and frequency is automatically generated according to the preset standard. After confirmation by the supervisor, the original action series is replaced.

[0012] Furthermore, the calculation formula of the coefficient of restitution in step 6 is: ; In the above formula, Representative n Cycle recovery coefficient, represents the baseline recovery coefficient, represents the dynamic weight coefficient of the seepage area, Representative k The reduction in the exudate area predicted by the cycle, Represents the initial seepage area benchmark value, represents the dynamic weight coefficient of temperature gradient, Representative k The temperature gradient drop value predicted by the cycle, Represents the initial temperature gradient baseline value around the wound, Represents the dynamic weight coefficient of redness and saturation, Representative k The periodic predicted decrease in redness and swelling saturation, Represents the initial redness and swelling saturation baseline value, Represents the future cycle k As the value of the wound improvement effect increases, the contribution of the currently predicted wound improvement effect to the final recovery coefficient gradually decreases. represents the healing rate attenuation factor, Represents the number of cycles.

[0013] (III) Beneficial effects Compared with the known prior art, the technical solution provided by the present invention has the following beneficial effects: By collecting patient medical records and real-time wound parameters, the model is adjusted to dynamically generate a position adjustment plan that suits the patient's specific condition, and combined with real-time tracking execution accuracy to ensure the effectiveness of the adjustment action, the wound deterioration index is evaluated in real time, and its impact on wound healing is obtained at each adjustment stage. This allows the system to proactively provide different position adjustment plans to proactively identify potential wound risks, issue warnings immediately when signs of deterioration first appear, and dynamically terminate high-risk actions, thereby avoiding further deterioration of the condition and delays in manual intervention.

[0014] By retrieving wound data before and after adjustment, using machine learning algorithms to perform trend analysis and recovery coefficient prediction, the key features of the wound are automatically extracted, and the recovery coefficient is calculated through a predictive model. Combined with a graded alarm strategy, early warning of wound recovery status is provided to facilitate medical staff to take targeted intervention measures. When the recovery coefficient is high, the adjustment strategy can also be optimized to increase the wound healing speed, reduce the subjective errors of manual observation, and enhance the comparability of data and analysis efficiency.

[0015] By real-time monitoring of execution deviations of position adjustment movements and dynamically correcting the direction, amplitude, priority and timestamp of the position adjustment, the execution accuracy of the adjustment movements is greatly improved, ensuring the accurate execution of the adjustment movements and reducing the impact of deviations on monitoring and treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a schematic diagram of the framework of the information infection monitoring system of the intensive care unit in the present invention; Figure 2 It is a schematic diagram of the flow of the information-based infection monitoring method for the intensive care unit of the present invention.

[0018] The numbers in the figure represent, respectively, 1. monitoring control module; 2. acquisition module; 3. state recognition module; 4. posture adjustment unit; 41. strategy generation module; 42. interactive prompt module; 43. execution monitoring module; 5. deterioration analysis module; 6. dynamic control module; 7. coefficient prediction module; 8. strategy optimization module; 9. graded warning module; 10. knowledge base module. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] The present invention will be further described below in conjunction with the embodiments.

[0021] Example 1: The information infection monitoring system of the intensive care unit of this embodiment is as follows: Figure 1 As shown, including: The monitoring control module 1, as the monitoring personnel observation and interaction terminal, edits and sends the operation instructions of each functional module; the monitoring control module 1 is interactively connected to the knowledge base module 10 through a wireless network, and the knowledge base module 10 is used to store the adjustment records, deterioration index and recovery coefficient of all patients, build an infection monitoring knowledge base, and mine the potential rules of specific body position adjustment and wound healing speed through association rules, and submit them to the body position adjustment unit 4 as a reference for strategy generation; Acquisition module 2 is used to obtain control authority for several pre-deployed visual detection devices with adjustable viewing angles, and to collect wound images of patients in different body positions in real time; The state recognition module 3 is used to extract the location, area, color and exudate state characteristics of the wound, and integrate and output them as standardized wound state parameters; The body position adjustment unit 4 is used to construct an adjustment model, based on the current wound state, combined with the patient's medical record data and wound state parameters, generate a series of body position adjustment actions including several stages, submit them to the monitoring control module 1, and monitor the execution status; The posture adjustment unit 4 is deployed with submodules at the lower level, including: a strategy generation module 41, an interactive prompt module 42 and an execution monitoring module 43. The strategy generation module 41 is interactively connected with the interactive prompt module 42 through a wireless network, and the interactive prompt module 42 is interactively connected with the execution monitoring module 43 through a wireless network, wherein: A strategy generation module 41 is used to train an adjustment module based on historical patient wound information, healing stages and adjusted body positions as samples, obtain current patient wound information and healing stages to input an adjustment model, and output several verified body position adjustment actions of directions and amplitudes to form an action series; The interactive prompt module 42 is used to push the generated posture adjustment action to the monitoring control module 1 in the form of visual instructions, support confirmation execution or manual correction, record operation feedback, and trigger another reminder if there is no response within a timeout period; The execution monitoring module 43 is used to track the patient's body position changes in real time through the acquisition module 2 to verify whether the action execution accuracy meets the preset threshold; the execution monitoring module 43 triggers the module jump in the verification stage. If no execution deviation is detected, it is adjusted to the dynamic control module 6 for further operation. If an execution deviation is detected, the strategy generation module 41 is automatically triggered to correct the body position amplitude, direction, priority and timestamp or suspend the adjustment action; The deterioration analysis module 5 is used to collect wound data again through the collection module 2 after each stage of body position adjustment by the body position adjustment unit 4, and compare the data with the state before adjustment, calculate the deterioration index, and evaluate the deterioration index risk through threshold judgment and trend analysis processing; the process of evaluating the deterioration index risk is as follows: After each stage of adjustment, the wound redness and swelling saturation and exudate contour area were extracted, and the local temperature gradient was quantified by combining the wound infrared thermal imaging data to form a three-channel physiological index; A sliding window algorithm is used, with a window length greater than three consecutive adjustment cycles, to calculate the dynamic change rate of each indicator; By presetting the dynamic weights of each indicator, a comprehensive deterioration index is generated, and the change trend is analyzed by combining the data adjusted in several stages; Automatically match the preset wound severity grading standards according to the patient's wound deterioration trend, and adjust the safety threshold range in real time; When a single detection is affected by body position occlusion, a body position adjustment instruction is generated to the body position adjustment unit 4 as a reference; Dynamic control module 6, used to immediately terminate the current series of adjustment actions when the deterioration index exceeds a preset safety threshold, save the current state snapshot and generate a termination report; The coefficient prediction module 7 is used to construct a prediction model, integrate the wound data before and after the adjustment, input the prediction model, calculate the recovery coefficient in the next several cycles, and trigger a graded alarm according to the coefficient interval; The dynamic control module 6 and the coefficient prediction module 7 are interactively connected to a graded warning module 9 through a wireless network. The graded warning module 9 is used to provide a graded alarm strategy to the monitoring control module 1. It is triggered when the deterioration index of the dynamic control module 6 exceeds the preset safety threshold, and when the corresponding grade of the recovery coefficient obtained by the coefficient prediction module 7 reaches the preset alarm standard, and provides several intensity alarm strategies according to the trigger level; The strategy optimization module 8 is used to trigger when the current series of posture adjustment actions are all completed and the recovery coefficient is higher than the preset standard, and send an adjustment strategy of increasing adjustment intensity to the posture adjustment unit 4, which replaces the original series of posture adjustment actions after confirmation by the monitoring control module 1; like Figure 1-2As shown, the monitoring control module 1 is interactively connected to the acquisition module 2 through a wireless network, the acquisition module 2 is interactively connected to the state recognition module 3 through a wireless network, the state recognition module 3 is interactively connected to the body position adjustment unit 4 through a wireless network, the body position adjustment unit 4 is interactively connected to the deterioration analysis module 5 through a wireless network, the deterioration analysis module 5 is interactively connected to the dynamic control module 6 through a wireless network, the dynamic control module 6 is interactively connected to the coefficient prediction module 7 through a wireless network, and the coefficient prediction module 7 is interactively connected to the strategy optimization module 8 through a wireless network.

[0022] Compared with existing technologies, the system can collect wound images in different body positions in real time through visual detection equipment with adjustable viewing angles, and quickly analyze and process them. Compared with traditional methods, real-time monitoring improves the response speed to wound conditions, and medical staff can detect signs of wound deterioration earlier, so as to adjust the nursing plan in time. Based on historical patient data and current wound status, machine learning is used to optimize the body position adjustment model and automatically generate the most suitable body position adjustment instructions for patients, which reduces the workload of medical staff, improves the efficiency of personalized care, and ensures targetedness and effectiveness. Dynamically capture changes in wound conditions and calculate the deterioration index, providing a more accurate and sensitive way to monitor the condition. Compared with traditional scheduled inspections, dynamic assessment can detect problems in real time, thereby better ensuring the safety of patients. According to the changing trend of the wound, the system can automatically adjust the safety threshold to better adapt to the specific situation of each patient, increase the flexibility and adaptability of the system, and reduce the risk of false alarms or missed alarms. The built-in graded alarm strategy integrates real-time data analysis. When the deterioration index exceeds the preset safety range or the recovery coefficient decreases, the corresponding level of alarm will be immediately issued to the monitoring personnel, providing clear and graded alarm information to help medical staff take quick action and reduce potential risks.

[0023] Embodiment 2: In other aspects, this embodiment provides another optimization strategy based on Embodiment 1, specifically: an information-based infection monitoring method for an intensive care unit, comprising the following steps: Step 1: Use pre-deployed visual inspection equipment with adjustable viewing angle to collect real-time wound images and infrared thermal imaging data of patients in different body positions, extract the morphological features of the wound location, area, color and exudate contour, combine infrared thermal imaging data to quantify the temperature gradient around the wound, generate morphological, exudate and temperature physiological indicators, integrate all features, and output standardized wound status parameters; Step 2: Based on the historical patient data, the adjustment model is trained and combined with the wound status parameters and medical record data of the current patient to generate a series of posture adjustment actions including direction, amplitude and priority, and the action series is pushed to the monitoring personnel interaction terminal in the form of visual instructions; Step 3: Use visual inspection equipment to monitor the patient's position changes in real time to verify whether the action execution reaches the preset direction and amplitude accuracy thresholds. If an execution deviation is detected, it will automatically trigger a correction instruction or pause the adjustment action; Step 4: After each stage of adjustment, the wound data was recollected to extract the dynamic change rate of redness and swelling saturation, exudate area, and local temperature gradient, and the weighted comprehensive deterioration index of each index was calculated using a sliding window algorithm; Step 5: Dynamically adjust the safety threshold interval based on individual differences and historical data of patients. If body position occlusion is detected, resulting in data abnormality, trigger a readjustment instruction; Step 6: If the deterioration index exceeds the safety threshold, immediately terminate the current adjustment action, save the current status snapshot and generate a termination report including the cause analysis, integrate the data before and after the adjustment, calculate the recovery coefficient in the future cycle through the prediction model, trigger a graded alarm according to the recovery coefficient interval, and push it to the medical staff terminal; Step 7: When the series of adjustment actions are completed and the recovery coefficient is higher than the preset standard, the current strategy is determined to be effective, and a new strategy with high adjustment amplitude and high frequency is automatically generated according to the preset standard. After confirmation by the supervisor, the original action series is replaced.

[0024] Embodiment 3: In this embodiment, a calculation formula for the coefficient of restitution is provided, specifically: ; In the above formula, Representative n Cycle recovery coefficient, represents the baseline recovery coefficient, which is calculated from the initial wound state of the patient, i.e., the initial parameter of the state recognition module 3, represents the dynamic weight coefficient of the seepage area, Representative k The reduction in the exudate area predicted by the cycle, Represents the initial seepage area benchmark value, represents the dynamic weight coefficient of temperature gradient, Representative k The temperature gradient drop value predicted by the cycle, Represents the initial temperature gradient baseline value around the wound, Represents the dynamic weight coefficient of redness and saturation, Representative k The periodic predicted decrease in redness and swelling saturation, Represents the initial redness and swelling saturation baseline value, Represents the future cycle k As the value of the wound improvement effect increases, the contribution of the currently predicted wound improvement effect to the final recovery coefficient gradually decreases. represents the healing rate attenuation factor, represents the number of cycles; The working logic of the calculation formula of the restitution coefficient is: Input current wound status parameters, historical adjustment action execution effects and individual patient healing characteristics; Use the LSTM network to predict the reduction in exudate area, temperature gradient, and redness and swelling saturation in each future cycle, and assign weights based on infection types. If the patient is at risk of delayed healing, the attenuation factor is corrected to inhibit the growth of the long-term recovery coefficient.

[0025] Compared with existing technologies, the formula can reflect the patient's recovery in real time by combining the dynamic improvement of key physiological indicators in the wound healing process, such as exudate area, temperature gradient, and redness and swelling saturation. The setting of the dynamic weight coefficient and time decay factor in the formula can adapt to the individual differences and healing characteristics of different patients, providing a more personalized assessment. At the same time, the use of exponential decay to model the recovery trends connecting history and the future enhances the accuracy and operability of the prediction, thereby improving the pertinence and effectiveness of monitoring and intervention.

[0026] In summary: when the information infection monitoring system of the present invention is installed, the monitoring personnel operate through the monitoring control module 1, the collection module 2 collects data, the state recognition module 3 identifies and processes it into parameters, the posture adjustment unit 4 generates an adjustment action, and the model is trained through the strategy generation module 41 to generate a posture adjustment plan. The interactive prompt module 42 pushes the posture adjustment plan, and the execution monitoring module 43 verifies the execution. After the adjustment is executed, the deterioration analysis module 5 re-collects data and evaluates the deterioration index. If it exceeds the threshold, it is processed by the dynamic control module 6. The coefficient prediction module 7 predicts the recovery coefficient and triggers an alarm. The strategy optimization module 8 adjusts the strategy when the recovery coefficient is high, the graded warning module 9 processes the alarm, and the knowledge base module 10 stores data and optimizes the strategy; Through visual inspection equipment with adjustable viewing angle and infrared thermal imaging technology, the patient's wound status can be monitored in real time, abnormal changes can be discovered and feedback can be given in a timely manner. Combining historical patient data and the current patient's wound status, a more personalized posture adjustment strategy can be formulated to better meet the needs of different patients. A series of posture adjustment actions are generated according to the wound status parameters and pushed to the caregiver in a visual manner, simplifying the complex nursing decision-making process and improving nursing efficiency and accuracy. The effect of position adjustment is verified in real time. Once an error is found, the system will automatically trigger a correction instruction to ensure the accuracy and safety of the nursing process. The deterioration index is calculated, and the redness, swelling, saturation, exudate area, and local temperature gradient of the wound are dynamically monitored. This can achieve a more comprehensive assessment of the health status of the wound and help doctors better understand the changes in the patient's condition. The safety threshold interval is dynamically adjusted according to the individual differences and historical data of the patients, which further improves the sensitivity and accuracy of monitoring and can detect potential risks earlier. When the deterioration index exceeds the safety threshold, the system can quickly terminate the current improper position adjustment and generate a detailed termination report, improving the emergency response capability for emergencies. After successfully adjusting the position, the system can automatically generate new nursing strategies with high adjustment range and high frequency to ensure that patients receive optimized nursing support during the recovery process without having to rely on manual evaluation within the traditional time frame.

[0027] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An information-based infection monitoring system for intensive care units, characterized in that: include: The monitoring control module, as the monitoring personnel's observation and interaction terminal, edits and sends the operating instructions of each functional module; The acquisition module is used to obtain the control authority of several pre-deployed visual detection devices with adjustable viewing angles, and to collect wound images of patients in different body positions in real time; The state recognition module is used to extract the location, area, color and exudate state characteristics of the wound, and integrate and output them as standardized wound state parameters; The body position adjustment unit is used to construct an adjustment model, based on the current wound state, combined with the patient's medical record data and wound state parameters, to generate a series of body position adjustment actions containing several stages and submit them to the monitoring control module, and monitor the execution status; The deterioration analysis module is used to collect wound data again through the acquisition module after each stage of the body position adjustment of the body position adjustment unit, compare the data with the state before the adjustment, calculate the deterioration index, and evaluate the deterioration index risk through threshold judgment and trend analysis processing; Dynamic control module, used to immediately terminate the current series of adjustment actions when the deterioration index exceeds the preset safety threshold, save the current state snapshot and generate a termination report; The coefficient prediction module is used to build a prediction model. By integrating the wound data before and after adjustment, the prediction model is input to calculate the recovery coefficient in the next few cycles and trigger a graded alarm according to the coefficient interval; The strategy optimization module is used to trigger when the current series of posture adjustment actions are all completed and the recovery coefficient is higher than the preset standard, send an adjustment strategy with increased adjustment intensity to the posture adjustment unit, and replace the original series of posture adjustment actions after confirmation by the monitoring control module.

2. The information infection monitoring system for the intensive care unit according to claim 1, characterized in that: The posture adjustment unit is provided with submodules at the lower level, including: a strategy generation module, an interactive prompt module and an execution monitoring module. The strategy generation module is interactively connected with the interactive prompt module via a wireless network, and the interactive prompt module is interactively connected with the execution monitoring module via a wireless network, wherein: A strategy generation module is used to train the adjustment module based on historical patient wound information, healing stages, and adjusted positions as samples, obtain the current patient wound information and healing stage input adjustment model, and output several verified direction and amplitude position adjustment actions to form an action series; The interactive prompt module is used to push the generated posture adjustment actions to the monitoring control module in the form of visual instructions, support confirmation of execution or manual correction, record operation feedback, and trigger another reminder if there is no response within the timeout period; The execution monitoring module is used to track the patient's position changes in real time through the acquisition module and verify whether the action execution accuracy meets the preset threshold.

3. The information infection monitoring system for the intensive care unit according to claim 2, characterized in that: During the verification phase, the execution monitoring module triggers the module to jump. If no execution deviation is detected, the module is adjusted to the dynamic control module for further operation. If an execution deviation is detected, the strategy generation module is automatically triggered to issue correction instructions or suspend adjustment actions for the posture amplitude, direction, priority and timestamp.

4. The information infection monitoring system for the intensive care unit according to claim 1, characterized in that: The process of evaluating the deterioration index risk by the deterioration analysis module is as follows: After each stage of adjustment, the wound redness and swelling saturation and exudate contour area were extracted, and the local temperature gradient was quantified by combining the wound infrared thermal imaging data to form a three-channel physiological index; A sliding window algorithm is used, with a window length greater than three consecutive adjustment cycles, to calculate the dynamic change rate of each indicator; By presetting the dynamic weights of each indicator, a comprehensive deterioration index is generated, and the change trend is analyzed by combining the data adjusted in several stages; Automatically match the preset wound severity grading standards according to the patient's wound deterioration trend, and adjust the safety threshold range in real time; When a single detection is affected by body position occlusion, a body position adjustment instruction is generated to the body position adjustment unit as a reference.

5. The information infection monitoring system for the intensive care unit according to claim 1, characterized in that: The dynamic control module and the coefficient prediction module are interactively connected to a graded warning module through a wireless network. The graded warning module is used to provide a graded alarm strategy to the monitoring control module. It is triggered when the deterioration index of the dynamic control module exceeds a preset safety threshold, and is triggered when the corresponding grade of the recovery coefficient obtained by the coefficient prediction module reaches a preset alarm standard, and provides several intensity alarm strategies according to the trigger level.

6. The information infection monitoring system for the intensive care unit according to claim 1, characterized in that: The monitoring control module is interactively connected to a knowledge base module via a wireless network. The knowledge base module is used to store adjustment records, deterioration indexes and recovery coefficients of all patients, build an infection monitoring knowledge base, and mine potential rules between specific body position adjustment and wound healing speed through association rules, and submit them to the body position adjustment unit as a reference for strategy generation.

7. The information infection monitoring system for the intensive care unit according to claim 1, characterized in that: The monitoring control module is interactively connected to the acquisition module through a wireless network, the acquisition module is interactively connected to the state recognition module through a wireless network, the state recognition module is interactively connected to the body position adjustment unit through a wireless network, the body position adjustment unit is interactively connected to the deterioration analysis module through a wireless network, the deterioration analysis module is interactively connected to the dynamic control module through a wireless network, the dynamic control module is interactively connected to the coefficient prediction module through a wireless network, and the coefficient prediction module is interactively connected to the strategy optimization module through a wireless network.

8. An information-based infection monitoring method for an intensive care unit, the method being an implementation method of an information-based infection monitoring system for an intensive care unit according to any one of claims 1 to 7, characterized in that: The following steps are involved: Step 1: Use pre-deployed visual inspection equipment with adjustable viewing angle to collect real-time wound images and infrared thermal imaging data of patients in different body positions, extract the morphological features of the wound location, area, color and exudate contour, combine infrared thermal imaging data to quantify the temperature gradient around the wound, generate morphological, exudate and temperature physiological indicators, integrate all features, and output standardized wound status parameters; Step 2: Based on the historical patient data, the adjustment model is trained and combined with the wound status parameters and medical record data of the current patient to generate a series of posture adjustment actions including direction, amplitude and priority, and the action series is pushed to the monitoring personnel interaction terminal in the form of visual instructions; Step 3: Use visual inspection equipment to monitor the patient's position changes in real time to verify whether the action execution reaches the preset direction and amplitude accuracy thresholds. If an execution deviation is detected, it will automatically trigger a correction instruction or pause the adjustment action; Step 4: After each stage of adjustment, the wound data was recollected to extract the dynamic change rate of redness and swelling saturation, exudate area, and local temperature gradient, and the weighted comprehensive deterioration index of each index was calculated using a sliding window algorithm; Step 5: Dynamically adjust the safety threshold interval based on individual differences and historical data of patients. If body position occlusion is detected, resulting in data abnormality, trigger a readjustment instruction; Step 6: If the deterioration index exceeds the safety threshold, immediately terminate the current adjustment action, save the current status snapshot and generate a termination report including the cause analysis, integrate the data before and after the adjustment, calculate the recovery coefficient in the future cycle through the prediction model, trigger a graded alarm according to the recovery coefficient interval, and push it to the medical staff terminal; Step 7: When the series of adjustment actions are completed and the recovery coefficient is higher than the preset standard, the current strategy is determined to be effective, and a new strategy corresponding to the adjustment amplitude and frequency is automatically generated according to the preset standard. After confirmation by the supervisor, the original action series is replaced.

9. The information-based infection monitoring method for an intensive care unit according to claim 8, characterized in that: The calculation formula of the restitution coefficient in step 6 is: ； In the above formula, Representative n Cycle recovery coefficient, represents the baseline recovery coefficient, represents the dynamic weight coefficient of the seepage area, Representative k The reduction in the exudate area predicted by the cycle, Represents the initial seepage area benchmark value, represents the dynamic weight coefficient of temperature gradient, Representative k The temperature gradient drop value predicted by the cycle, Represents the initial temperature gradient baseline value around the wound, Represents the dynamic weight coefficient of redness and saturation, Representative k The periodic predicted decrease in redness and swelling saturation, Represents the initial redness and swelling saturation baseline value, Represents the future cycle k As the value of the wound improvement effect increases, the contribution of the currently predicted wound improvement effect to the final recovery coefficient gradually decreases. represents the healing rate attenuation factor, Represents the number of cycles.

Images