Cardiothoracic surgery postoperative multi-device collaborative management system and method based on Internet of Things

Abstract

The invention relates to the technical field of health monitoring, in particular to a cardiothoracic surgery postoperative multi-device collaborative management system and method based on the Internet of Things. The system comprises a data monitoring module, a priority alarm module, a central processing module and a noise evaluation module. Real-time data of various medical devices are collected, abnormity in the data is recognized through threshold comparison, comprehensiveness of the data is ensured, alarms in target data are classified and broadcasted through the priority alarm module according to preset priorities, emergency situations are ensured to be processed preferentially, a large amount of data are processed through the central processing module, and the data processing efficiency is improved. According to the method, the correlation is identified, false alarms in the associated data are identified and eliminated, high-accuracy target data are obtained, the false alarms are effectively reduced, unnecessary interference is avoided, the system credibility is improved, the alarm modes are adaptively switched through the noise evaluation module according to the environmental noise, the alarm effectiveness is improved, and secondary false alarms caused by the noise are reduced.

Description

Technical Field

[0001] The present invention relates to the field of health monitoring technology, and in particular to an Internet of Things-based multi-device collaborative management system and method for cardiothoracic surgery. Background Art

[0002] While the success rate of cardiothoracic surgery has significantly increased with advances in medical technology, postoperative patient management still faces numerous challenges, particularly for the elderly or those with serious medical conditions, who are at higher risk for postoperative complications and require close monitoring and timely intervention. Traditional postoperative monitoring models typically rely on data collection and manual analysis from a single device, resulting in information silos, inaccurate data, and inefficient management. These models struggle to meet the demands of modern healthcare for precise and intelligent management.

[0003] The Internet of Things (IoT), through the integration of sensors, communications, and data processing technologies, enables interconnected devices and information sharing. In the medical field, the application of IoT technology has already seen initial success, such as in the development of remote medical monitoring and smart medical devices. However, its application in high-risk patient populations, such as those undergoing cardiothoracic surgery, is still in its infancy. A management system that enables multi-device collaboration, real-time monitoring, and intelligent analysis is urgently needed. By integrating multiple medical devices, such as electrocardiograms, blood pressure monitors, and oximeters, it enables real-time data collection, transmission, and sharing. Leveraging IoT technology, this system transcends limitations imposed by device vendors and protocols, enabling interoperability and data integration across different devices, ensuring comprehensive and consistent medical data. Furthermore, the system utilizes edge computing and cloud computing technologies to process and analyze massive amounts of real-time data. Combined with artificial intelligence algorithms, it enables prediction of patient status and early warning, assisting physicians in timely decision-making and improving the efficiency and effectiveness of postoperative care.

[0004] A Chinese patent document with publication number CN115274137A discloses an active health management system and method for multi-device collaboration, including: multiple health devices; a health management collaborative system for users to configure collaborative monitoring strategies under required monitoring scenarios, each collaborative monitoring strategy including device information, collaborative execution sequence and corresponding associated collaborative trigger conditions of at least two health devices; the collaborative monitoring strategy is then executed to actively control the corresponding health devices according to the device information and collaborative execution sequence to work collaboratively to collect corresponding health data and store it when the associated collaborative trigger conditions are met, for evaluation of the user's health status under the required monitoring scenario; it can be seen that the existing multi-device collaborative management technology lacks the integration of real-time data of all devices and the combination of environmental factors for multi-parameter comprehensive analysis, making it difficult to identify real abnormal situations, resulting in frequent alarms and a high proportion of false alarms on single devices, resulting in low alarm effectiveness of postoperative monitoring equipment. Summary of the Invention

[0005] To this end, the present invention provides an Internet of Things-based multi-device collaborative management system and method for post-operative cardiothoracic surgery, which is used to overcome the problems in the prior art of lacking collaborative management of multiple monitoring devices for post-operative cardiothoracic surgery patients, failing to identify true abnormal situations and timely adjust the alarm frequency, resulting in a high false alarm rate and low post-operative management quality.

[0006] To achieve the above objectives, on the one hand, the present invention provides a multi-device collaborative management system for cardiothoracic surgery based on the Internet of Things, comprising: A data monitoring module, comprising various monitoring devices, any one of which is used to collect real-time postoperative monitoring data of the patient, and the data monitoring module is used to identify suspected postoperative risk data in the real-time postoperative monitoring data; A priority alarm module, connected to the data monitoring module, for issuing an alarm at a preset alarm frequency for the suspected risk data after surgery according to a preset priority; a central processing module, which is connected to the data monitoring module and the priority alarm module respectively, and is used to analyze the suspected risk data, filter out false reporting monitoring data, and reduce the corresponding preset alarm frequency according to the false reporting type of the false reporting monitoring data; The noise assessment module is connected to the priority alarm module and the central processing module respectively, and is used to analyze the impact of the alarm on the environmental noise and trigger the alarm mode switching strategy according to the impact.

[0007] Furthermore, the central processing module includes a data analysis unit, a false alarm filtering unit and an alarm frequency tuning unit, wherein: The data analysis unit is used to integrate the real-time postoperative monitoring data of each monitoring device and perform multi-parameter comprehensive analysis to obtain correlated postoperative monitoring data and postoperative false reporting risk data; The false alarm filtering unit performs root cause analysis on the false reporting risk data after surgery to determine the false reporting type of the false reporting risk data; The alarm frequency tuning unit executes a corresponding alarm frequency adjustment strategy according to the false alarm type.

[0008] Furthermore, the data analysis unit includes an association rule base, an association degree calculation subunit and a marking subunit, wherein: The association rule library is used to store physiological coupling rules and temporal association rules; A correlation calculation subunit, used to calculate the real-time correlation based on the patient's postoperative type, correlation coefficient and event interval attenuation factor; The marking subunit determines the associated postoperative suspected risk data according to the physiological coupling rules and the temporal association rules, and marks the associated postoperative suspected risk data according to the real-time correlation degree, marking it as postoperative false risk data.

[0009] Furthermore, the real-time correlation is calculated based on the patient's postoperative type, correlation coefficient and event interval attenuation factor, including: Determine weight distribution based on the patient's postoperative type; The real-time correlation is calculated based on the weight, correlation coefficient and event interval decay factor.

[0010] Furthermore, the real-time correlation degree is the sum of the first correlation degree and the second correlation degree; The first correlation is the product of the correlation coefficient and the corresponding weight; The second correlation degree is the product of the event interval attenuation factor and the corresponding weight.

[0011] Furthermore, false alarm types include interference false alarms and equipment failure false alarms; The false alarm filtering unit includes an interference false alarm subunit and a displacement false alarm subunit, wherein, Interference false alarm subunit, determines the false alarm type as interference false alarm or equipment failure false alarm based on signal spectrum characteristics; The displacement false alarm subunit, combined with the bedside camera posture recognition, determines that the false alarm type is a false alarm of equipment failure and switches the current low-priority alarm to a high-priority alarm.

[0012] Furthermore, the noise assessment module includes a noise impact index calculation unit and an adaptive noise reduction unit, wherein: The noise impact index calculation unit is used to calculate the noise impact index according to the ambient noise decibel and the patient distance coefficient; The adaptive noise reduction unit triggers the alarm mode switching strategy according to the noise impact index, and executes the corresponding noise reduction strategy according to the current noise environment.

[0013] Furthermore, the noise impact index calculation unit calculates the noise impact index using the following formula: Noise impact index = alarm volume / (ambient noise decibels × patient distance factor).

[0014] Furthermore, the adaptive noise reduction unit includes a first noise reduction strategy subunit, a second noise reduction strategy subunit and a third noise reduction strategy subunit, wherein: The first noise reduction strategy subunit switches the current alarm mode to a vibration alarm; The second noise reduction strategy subunit performs a delayed alarm according to the sudden noise; The third noise reduction strategy subunit determines whether to reduce the volume according to the current alarm period.

[0015] On the other hand, the present invention also provides a method for coordinating and managing multiple devices after cardiothoracic surgery based on the Internet of Things, which is applied to the above-mentioned coordinating and managing multiple devices after cardiothoracic surgery based on the Internet of Things, comprising: Identify suspected postoperative risk data from real-time postoperative monitoring data; Alarming the suspected risk data after surgery at a preset alarm frequency according to a preset priority; Analyze suspected risk data, filter out false monitoring data, and reduce the corresponding preset alarm frequency based on the false reporting type of the false monitoring data; Analyze the impact of the alarm on environmental noise and trigger the alarm mode switching strategy based on the impact level.

[0016] Compared with the prior art, the beneficial effect of the present invention is that, since multiple devices are required to monitor the patient's heart rate, heart rhythm, pulse, blood pressure, respiration, blood oxygen saturation and other physiological parameters, prompt the patient's condition changes and issue relevant alarms, however, the devices will cause frequent clinical alarms and a high proportion of false alarms, thereby causing medical staff to be overloaded or less sensitive to alarms, that is, alarm fatigue, and distrust of the alarm system, thereby delaying responses, ignoring, silencing or turning off alarms, resulting in missed critical alarms, delaying patient treatment, and threatening the patient's life safety, that is, the effective alarm efficiency of the equipment is low, and equipment alarm management is particularly important. Through alarm classification and hierarchical management, the different priority levels of specialized disease alarms or alarm combinations are clarified, and the noise pollution caused by too many false alarms is considered to achieve accurate identification of critical alarms. By analyzing related monitoring data, homologous false reports are processed and the alarm efficiency is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the structure of a multi-device collaborative management system for cardiothoracic surgery based on the Internet of Things according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the central processing module according to an embodiment of the present invention; Figure 3 Schematic diagram of the structure of a data analysis unit according to an embodiment of the present invention; Figure 4 Schematic diagram of the process of multi-device collaborative management method after cardiothoracic surgery based on the Internet of Things according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0019] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0020] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0021] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0022] See also Figure 1 As shown, it is a structural diagram of a multi-device collaborative management system for cardiothoracic surgery based on the Internet of Things according to an embodiment of the present invention. The present invention provides a multi-device collaborative management system for cardiothoracic surgery based on the Internet of Things, comprising: A data monitoring module, comprising various monitoring devices, any one of which is used to collect real-time postoperative monitoring data of the patient, and the data monitoring module is used to identify suspected postoperative risk data in the real-time postoperative monitoring data; A priority alarm module, connected to the data monitoring module, for issuing an alarm at a preset alarm frequency for the suspected risk data after surgery according to a preset priority; a central processing module, which is connected to the data monitoring module and the priority alarm module respectively, and is used to analyze the suspected risk data, filter out false reporting monitoring data, and reduce the corresponding preset alarm frequency according to the false reporting type of the false reporting monitoring data; The noise assessment module is connected to the priority alarm module and the central processing module respectively, and is used to analyze the impact of the alarm on the environmental noise and trigger the alarm mode switching strategy according to the impact.

[0023] The monitoring equipment in this embodiment includes an electrocardiogram (ECG), a sphygmomanometer, a ventilator, a thermometer, and a hemodynamic monitor. Real-time postoperative monitoring data includes physiological parameters such as blood pressure and temperature. Multiple devices are required to monitor the patient's heart rate, rhythm, pulse, blood pressure, respiration, and blood oxygen saturation, indicating changes in the patient's condition and issuing relevant alarms. However, the large number of devices can cause frequent clinical alarms and a high rate of false alarms, resulting in sensory overload or reduced sensitivity to alarms for medical staff, i.e., alarm fatigue. This leads to a lack of trust in the alarm system, which can lead to delayed responses, ignoring, silencing, or shutting off alarms. This can lead to missed critical alarms, delayed patient care, and threats to the patient's life. This results in low effective alarm efficiency for the equipment. Therefore, equipment alarm management is particularly important. Through alarm classification and hierarchical management, the different priorities of specialized disease alarms or alarm combinations are clearly defined, and noise pollution caused by excessive false alarms is considered to achieve accurate identification of critical alarms. By analyzing correlated monitoring data, false alarms from the same source are processed to improve alarm efficiency.

[0024] Clinical alarms are divided into three priority levels: high, medium, and low. High-priority alarms are life-threatening and require immediate response from medical personnel. They are mainly concentrated in arrhythmia alarms, including cardiac arrest, ventricular fibrillation, ventricular tachycardia, etc. Priority alarms include heart rate, blood pressure, respiration, blood oxygen saturation, ventricular premature beats, etc. Low-priority alarms include low battery, poor wire connection, etc. Through priority grading, critical alarms such as cardiac arrest and ventricular fibrillation are ensured to receive priority response, thereby improving alarm management capabilities.

[0025] The data monitoring module collects real-time data from various medical devices such as heart rate, blood pressure, and respiratory rate, and identifies suspected postoperative risk data through threshold comparison, so as to identify anomalies in a timely manner and ensure the comprehensiveness of the data. The priority alarm module classifies and broadcasts alarms in the target data according to the preset priority to ensure that emergency situations are handled first. The central processing module processes large amounts of data, identifies correlations, identifies and eliminates false alarms in related data, and obtains highly accurate target data to effectively reduce false alarms, avoid unnecessary interference, and improve system credibility. The noise assessment module adaptively switches the alarm mode according to the environmental noise, thereby improving the effectiveness of the alarm and reducing secondary false alarms caused by noise.

[0026] See Figure 2 As shown, it is a structural diagram of the central processing module according to an embodiment of the present invention; Specifically, the central processing module includes a data analysis unit, a false alarm filtering unit, and an alarm frequency tuning unit, wherein: The data analysis unit is used to integrate the real-time postoperative monitoring data of each monitoring device and perform multi-parameter comprehensive analysis to obtain correlated postoperative monitoring data and postoperative false reporting risk data; The false alarm filtering unit performs root cause analysis on the false reporting risk data after surgery to determine the false reporting type of the false reporting risk data; The alarm frequency tuning unit executes a corresponding alarm frequency adjustment strategy according to the false alarm type.

[0027] Multi-parameter comprehensive analysis includes triggering matching rules based on real-time postoperative monitoring data, calling physiological coupling rules and time series association rules to perform multi-parameter coupling analysis and time series modeling, and identifying associated data and false reporting risk data in the monitoring data; Among them, when it is detected that the real-time postoperative monitoring data is greater than the corresponding alarm threshold, the rule matching is triggered, and the associated postoperative suspected risk data and postoperative false reporting risk data are determined based on the matching results; When it is detected that each real-time postoperative monitoring data is less than or equal to the corresponding alarm threshold, rule matching is not triggered.

[0028] In this embodiment, the alarm threshold corresponding to each real-time postoperative monitoring data is the critical value for determining whether the physiological parameter is abnormal. The threshold is customized according to the pathological mechanism. At the same time, the setting of the alarm threshold needs to be adapted to the patient's baseline. The alarm threshold = standard threshold × (patient preoperative value / population average) k k is the disease severity coefficient, which is related to the patient's compensatory ability and tolerance to changes in the parameter and is negatively correlated with tolerance. Generally, k is set to 0.8 for mild disease, 1.0 for moderate disease, and 1.2-1.5 for severe disease. For example, for patients with severe heart failure, the tolerance to parameter deviation is even worse, so k is set to 1.5. If the patient's preoperative blood oxygen level is 82%, the postoperative alarm threshold is set to 89% × (82 / 95) 1.5 ≈71.3%; while for patients with chronic hypoxia, preoperative Sp The baseline is 82%, k is set to 1.0, and the standard threshold is 89%. The postoperative alarm threshold is set to 89% × (82 / 95) 1 ≈77%, corresponding to blood oxygen saturation (Sp ) has a lower limit of 71.3% and a lower limit of 77%, indicating that the lower limit of blood oxygen saturation in the real-time postoperative monitoring data shall not be lower than 71.3% and 77%; the alarm thresholds for heart rate (HR) are 50 beats / min and 130 beats / min. When the real-time monitored heart rate is lower than 50 beats / min or higher than 130 beats / min, it is judged to be abnormal; the alarm threshold for systolic blood pressure (ART-S) is a lower limit of 90 mmHg. If the real-time monitored systolic blood pressure exceeds the lower limit, it is judged to be abnormal. For example, if the real-time monitored systolic blood pressure is 85 mmHg, it is judged to be abnormal.

[0029] By determining the alarm threshold based on the disease severity coefficient, the alarm threshold for patients with severe heart failure is optimized from 89% to 71.3%, avoiding frequent false alarms caused by basic hypoxia; by effectively distinguishing real pathological events from isolated abnormalities based on the correlation between various monitoring parameters, the interference of false alarms is reduced, the accuracy of alarm recognition is improved, and the specificity of critical alarms is improved by converting discrete alarms into chains of pathological events; by conducting root cause analysis on postoperative false alarm risk data, targeted strategies are implemented to ensure priority response to critical alarms and reduce the number of unnecessary alarms.

[0030] See Figure 3 , which is a schematic structural diagram of a data analysis unit according to an embodiment of the present invention; Specifically, the data analysis unit includes an association rule base, an association degree calculation subunit and a marking subunit, wherein: The association rule library is used to store physiological coupling rules and temporal association rules; A correlation calculation subunit, used to calculate the real-time correlation based on the patient's postoperative type, correlation coefficient and event interval attenuation factor; A marking subunit determines associated postoperative suspected risk data according to physiological coupling rules and temporal association rules, and marks the associated postoperative suspected risk data according to real-time correlation, marking them as postoperative false risk data; Among them, the event interval attenuation factor T is calculated based on the time difference. ; i is the attenuation coefficient, i=0.5; t is the time difference between the start time of the two matched associated postoperative suspected risk data; When the real-time correlation degree is greater than or equal to the standard correlation degree, the associated postoperative suspected risk data will not be marked and the alarm will be retained; When the real-time correlation degree is less than the standard correlation degree, the associated postoperative suspected risk data is marked as postoperative false risk data.

[0031] The physiological coupling rules and temporal association rules in this embodiment are rules pre-defined in the association rule library and are used to describe the physiological mechanism correlation and temporal continuity between multiple physiological parameters. The temporal association rule indicates that two associated events overlap or are closely connected in time. The degree of closeness is quantified by the event interval attenuation factor. The larger the time interval Δt, the lower the correlation. The physiological coupling rule indicates that multiple physiological parameters change synergistically due to the same pathology, reflecting the parameter linkage directly affected by the body disease. Therefore, by analyzing each parameter and quantifying this relationship based on the real-time correlation metric, events in which multiple physiological parameters change synergistically due to the same pathological mechanism are accurately identified. The corresponding data is marked as associated postoperative suspected risk data. The associated postoperative suspected risk data is analyzed for false reporting and any false reporting is marked as postoperative false reporting risk data, effectively reducing the number of alarms while achieving accurate identification of critical alarms. The real-time correlation degree is a value calculated by a formula that quantifies whether the current monitoring data meets a certain rule, that is, the possibility of an event occurring. The value is between 0 and 1. The standard correlation degree is set to 0.75. The data monitoring module monitors various parameters in real time. When a parameter exceeds the threshold, that is, once a parameter is found to be abnormal, the central processing module rule matching is triggered. The data analysis unit calls and matches the rules related to the parameter in the association rule library, and then calculates the real-time correlation of these rules. If the correlation exceeds the threshold, the association event is triggered. That is, if the blood oxygen saturation is detected to be decreased, the triggered rules include the "hypoxia-related event" rule. In this case, it is necessary to check whether the heart rate has increased. By taking the data of the most recent period of time, the correlation coefficient between the current abnormal parameter and other related parameters, such as the heart rate, is calculated. The time difference between the abnormal occurrence of the current abnormal parameter and other related parameters, and the correlation coefficient between the current abnormal parameter and other related parameters are calculated. If the correlation calculated based on the postoperative stage of the patient is greater than 0.75, the rule is considered to be established, triggering the association event, that is, the hypoxia event. If the correlation is less than 0.3, it is considered to be an isolated false report. For example, a patient in the acute phase after cardiac surgery ( =0.6, =0.4) real-time postoperative monitoring data, if the following occurs at a certain moment: Blood oxygen saturation dropped from 98% to 85% in 10 seconds (a 13% drop, exceeding the 10% threshold in the regulations).

[0032] Heart rate increased from 80 to 110 beats per minute over the same time period (a 37.5% increase, exceeding the 30% threshold in the regulations); In this case, a sudden drop in blood oxygen and an increase in heart rate are detected, matching the physiological coupling rules in the rule base: Sp If the decrease is greater than 10% and the HR increases by more than 30%, calculate the blood oxygen saturation and heart rate over a period of time to calculate the correlation: The corresponding blood oxygen saturation is 95, 93, 88, 85, 82; Corresponding heart rates: 80, 85, 92, 105, 120; The correlation coefficient = -0.98, indicating that decreased blood oxygen and increased heart rate are significantly negatively correlated, consistent with the hypoxia compensation mechanism; The time difference between the start time of blood oxygen saturation and heart rate is 0.2 minutes, and the event interval attenuation factor = =0.9; Real-time relevance = -0.98 ×0.6+0.9×0.4=0.948; The real-time correlation is greater than the standard correlation, which corresponds to a real hypoxia event, and no suspected risk data after surgery will be marked; When the patient turned over and the ECG leads became loose, the heart rate would rise to 150 beats / min, the oxygen saturation would be stable at 98%, and the time difference between the start time of oxygen saturation and heart rate was 0 minutes. Normal) = -0.05 (no correlation), event interval decay factor: 1. Real-time correlation = 0.05×0.6+1×0.4=0.43. At this time, the real-time correlation is less than the standard correlation. The associated postoperative suspected risk data is marked as postoperative false risk data.

[0033] Specifically, the real-time correlation is calculated based on the patient's postoperative type, correlation coefficient, and event interval attenuation factor, including: Determine weight distribution based on the patient's postoperative type; If the patient's postoperative type is acute postoperative period, the weight corresponding to the correlation coefficient is 0.6, and the weight corresponding to the event interval attenuation factor is 0.4; If the patient's postoperative type is postoperative recovery period, the weight corresponding to the correlation coefficient is 0.4, and the weight corresponding to the event interval attenuation factor is 0.6; The real-time correlation is calculated based on the weight, correlation coefficient and event interval decay factor.

[0034] The postoperative types in this embodiment include the postoperative acute phase and the postoperative recovery phase, which are determined according to the number of days after surgery. Generally, the postoperative acute phase is less than or equal to three days after surgery, and the postoperative recovery phase is more than three days after surgery.

[0035] Specifically, the real-time correlation degree is the sum of the first correlation degree and the second correlation degree; The first correlation is the product of the correlation coefficient and the corresponding weight; The second correlation degree is the product of the event interval attenuation factor and the corresponding weight.

[0036] In this embodiment, by integrating multi-device monitoring data, including heart rate, blood pressure, blood oxygen saturation, etc., the physiological coupling rules are used, such as a sudden drop in blood oxygen accompanied by an increase in heart rate → marked as an "hypoxia-related event", and the temporal association rules, such as abnormal blood pressure + abnormal breathing within 5 minutes → marked as a "circulatory and respiratory-related event" are used to calculate the correlation degree, so as to effectively distinguish real pathological events, thereby reducing false reporting interference. By dynamically adjusting the weight according to the patient's postoperative type, that is, focusing on physiological coupling in the acute postoperative period and focusing on temporal continuity in the postoperative recovery period, the risk characteristics of patients at different stages are adapted.

[0037] Specifically, false alarm types include interference false alarms and equipment failure false alarms; The false alarm filtering unit includes an interference false alarm subunit and a displacement false alarm subunit, wherein, Interference false alarm subunit, determines the false alarm type as interference false alarm or equipment failure false alarm based on signal spectrum characteristics; The displacement false alarm subunit, combined with the bedside camera posture recognition, determines that the false alarm type is a false alarm of equipment failure and switches the current low-priority alarm to a high-priority alarm.

[0038] Signal spectrum analysis of postoperative false reporting risk data: If 50Hz power frequency interference is detected, the corresponding false alarm type is interference false alarm; If the physiological frequency band disappears and high-frequency clutter appears, it means that there is a device failure, and the corresponding false alarm type is a false alarm of equipment failure; Among them, the physiological frequency band is the frequency band corresponding to an amplitude equal to 0.2, and the high-frequency clutter is the frequency band corresponding to noise greater than 100Hz; If no power frequency interference is detected, the physiological frequency band disappears, or high-frequency clutter appears, posture recognition is performed in conjunction with the bedside camera. Through torso stability analysis, arm movement analysis, and movement trajectory analysis, it is determined that the false alarm type is a false alarm of equipment failure: The patient area is scanned in real time, the coordinates of the human body joints are extracted and numbered: left wrist number 1, right wrist number 2, left elbow number 3, right elbow number 4, and torso midpoint number 5. To perform a trunk stability analysis: Calculate the angle between the trunk baseline and the horizontal frame line to get the real-time trunk angle, and compare it with the standard angle of 10° for lying posture. If the real-time torso angle is greater than the standard angle for lying down, it is marked as a turning action and the arm movement analysis is performed; If the real-time torso angle is less than or equal to the standard angle of the lying posture, it is not marked as a turning action; Perform arm movement analysis: Calculate the angle between the arm action line and the trunk baseline to obtain the arm expansion angle; Calculate the real-time Euclidean distance between the wrist joint and the device wire to obtain the displacement distance; Compare the arm extension angle with the standard arm angle. If the arm extension angle is smaller than the standard arm angle, it is determined that there is no dangerous action; If the arm extension angle is greater than or equal to the standard arm angle of 45°, compare the displacement distance with the wire distance threshold: If the displacement distance is greater than or equal to the wire distance threshold, it is determined to be a suspected dangerous action and the action trajectory analysis is performed. This is done by obtaining the motion path of the wrist joint to analyze whether there is a risk of equipment failure caused by the dangerous trajectory action and to determine whether the corresponding false alarm type is a false alarm of equipment failure. If the displacement distance is less than the wire distance threshold, it is determined that there is no dangerous action; The wire distance threshold is the product of the device wire length and the relaxation factor, and the relaxation factor is 30%; Motion trajectory analysis: Capture the motion path of the wrist joint with continuous video frames and generate a real-time trajectory route; The standard dangerous action library contains standard trajectories of dangerous actions such as waving and quick grasping. The real-time trajectory is compared with the standard dangerous action library using the Jaccard coefficient to calculate the similarity between the real-time trajectory and the standard trajectory: If the similarity is greater than or equal to 70%, it is marked as a high-risk action and the trajectory frequency is obtained. If the trajectory frequency is greater than the standard frequency of 3, the corresponding false alarm type is determined to be a false alarm of equipment failure, and the equipment inspection command is triggered; If the trajectory frequency is less than or equal to the standard frequency 3, the current alarm mode is switched to vibrating the bed and the nurse station is notified; If the similarity is greater than or equal to 70% and the trajectory frequency is greater than the standard frequency of 3, there may be movements such as reaching for something or unconscious twitching. In this case, the risk of unnecessary movement causing the device wire to disconnect is high, and the corresponding false alarm type is determined to be a false alarm of equipment failure. Actions with a similarity of less than 70% are marked as low-risk, such as slight posture adjustments. The risk of unnecessary movement causing device wire disconnection is low. Through posture recognition, it analyzes whether the patient has made unnecessary movements that may cause the device wires to disconnect, and distinguishes unnecessary movements, such as turning over, stretching or moving arms, to analyze whether unnecessary movements may cause the device wires to disconnect. When there are high-frequency dangerous trajectory movements, the risk of device wire disconnection is very high. The corresponding false alarm type is determined to be a false alarm of equipment failure, and the equipment inspection instruction is triggered, and the current low-priority alarm is switched to a high-priority alarm, so that the equipment can be inspected in time.

[0039] Specifically, the noise assessment module includes a noise impact index calculation unit and an adaptive noise reduction unit, wherein: The noise impact index calculation unit is used to calculate the noise impact index according to the ambient noise decibel and the patient distance coefficient; The adaptive noise reduction unit triggers the alarm mode switching strategy according to the noise impact index, and executes the corresponding noise reduction strategy according to the current noise environment.

[0040] Specifically, the noise impact index calculation unit calculates the noise impact index using the following formula: Noise impact index = alarm volume / (ambient noise decibels × patient distance factor).

[0041] Specifically, the adaptive noise reduction unit includes a first noise reduction strategy subunit, a second noise reduction strategy subunit and a third noise reduction strategy subunit, wherein: The first noise reduction strategy subunit switches the current alarm mode to a vibration alarm; The second noise reduction strategy subunit performs a delayed alarm according to the sudden noise; The third noise reduction strategy subunit determines whether to reduce the volume according to the current alarm period.

[0042] In this embodiment, the noise impact index is calculated and the alarm mode is switched dynamically. In an environment of continuous high-frequency noise, or when too many false alarms cause noise pollution, the vibration alarm is switched. When sudden noise is detected in the current environment, the alarm is delayed for 10 seconds. When the current alarm period is night mode, the volume is lowered and the alarm mode is switched to prioritize the flashing of the bedside lamp to avoid environmental noise masking critical alarms, ensure alarm accessibility, and avoid signal interference caused by sudden noise, thereby reducing secondary false alarms caused by noise; high-frequency noise is noise greater than 65dB, and sudden noise is noise of unit 80dB.

[0043] See Figure 4 As shown, it is a flowchart of a multi-device collaborative management method for cardiothoracic surgery based on the Internet of Things according to an embodiment of the present invention; The present invention also provides a method for coordinating and managing multiple devices after cardiothoracic surgery based on the Internet of Things, which is applied to the above-mentioned coordinating and managing multiple devices after cardiothoracic surgery based on the Internet of Things, comprising: Step S1, identifying postoperative suspected risk data in real-time postoperative monitoring data; Step S2, alarming the suspected risk data after surgery at a preset alarm frequency according to a preset priority; Step S3: Analyze the suspected risk data, filter out false monitoring data, and reduce the corresponding preset alarm frequency according to the false reporting type of the false monitoring data; Step S4: Analyze the impact of the alarm on the ambient noise, and trigger the alarm mode switching strategy according to the impact.

[0044] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0045] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. An IoT-based multi-device collaborative management system for postoperative cardiothoracic surgery, characterized by: include, A data monitoring module, comprising various monitoring devices, any one of which is used to collect real-time postoperative monitoring data of the patient, and the data monitoring module is used to identify suspected postoperative risk data in the real-time postoperative monitoring data; A priority alarm module, connected to the data monitoring module, for issuing an alarm at a preset alarm frequency for the suspected risk data after surgery according to a preset priority; a central processing module, which is connected to the data monitoring module and the priority alarm module respectively, and is used to analyze the suspected risk data, filter out false reporting monitoring data, and reduce the corresponding preset alarm frequency according to the false reporting type of the false reporting monitoring data; The noise assessment module is connected to the priority alarm module and the central processing module respectively, and is used to analyze the impact of the alarm on the environmental noise and trigger the alarm mode switching strategy according to the impact.

2. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 1 is characterized in that: The central processing module includes a data analysis unit, a false alarm filtering unit and an alarm frequency tuning unit, wherein: The data analysis unit is used to integrate the real-time postoperative monitoring data of each monitoring device and perform multi-parameter comprehensive analysis to obtain correlated postoperative monitoring data and postoperative false reporting risk data; The false alarm filtering unit performs root cause analysis on the false reporting risk data after surgery to determine the false reporting type of the false reporting risk data; The alarm frequency tuning unit executes a corresponding alarm frequency adjustment strategy according to the false alarm type.

3. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 2 is characterized in that: The data analysis unit includes an association rule base, an association degree calculation subunit and a marking subunit, wherein: The association rule library is used to store physiological coupling rules and temporal association rules; A correlation calculation subunit, used to calculate the real-time correlation based on the patient's postoperative type, correlation coefficient and event interval attenuation factor; The marking subunit determines the associated postoperative suspected risk data according to the physiological coupling rules and the temporal association rules, and marks the associated postoperative suspected risk data according to the real-time correlation degree, marking it as postoperative false risk data.

4. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 3 is characterized in that: The real-time correlation is calculated based on the patient's postoperative type, correlation coefficient and event interval attenuation factor, including: Determine weight distribution based on the patient's postoperative type; The real-time correlation is calculated based on the weight, correlation coefficient and event interval decay factor.

5. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 4 is characterized in that: The real-time correlation degree is the sum of the first correlation degree and the second correlation degree; The first correlation is the product of the correlation coefficient and the corresponding weight; The second correlation degree is the product of the event interval attenuation factor and the corresponding weight.

6. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 2 is characterized in that: False alarm types include interference false alarms and equipment failure false alarms; The false alarm filtering unit includes an interference false alarm subunit and a displacement false alarm subunit, wherein, Interference false alarm subunit, determines the false alarm type as interference false alarm or equipment failure false alarm based on signal spectrum characteristics; The displacement false alarm subunit, combined with the bedside camera posture recognition, determines that the false alarm type is a false alarm of equipment failure and switches the current low-priority alarm to a high-priority alarm.

7. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 1 is characterized in that: The noise assessment module includes a noise impact index calculation unit and an adaptive noise reduction unit, wherein: The noise impact index calculation unit is used to calculate the noise impact index according to the ambient noise decibel and the patient distance coefficient; The adaptive noise reduction unit triggers the alarm mode switching strategy according to the noise impact index, and executes the corresponding noise reduction strategy according to the current noise environment.

8. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 7 is characterized in that: The noise impact index calculation unit calculates the noise impact index using the following formula: Noise impact index = alarm volume / (ambient noise decibels × patient distance factor).

9. The multi-device collaborative management system for postoperative cardiothoracic surgery based on the Internet of Things according to claim 7, characterized in that: The adaptive noise reduction unit includes a first noise reduction strategy subunit, a second noise reduction strategy subunit and a third noise reduction strategy subunit, wherein: The first noise reduction strategy subunit switches the current alarm mode to a vibration alarm; The second noise reduction strategy subunit performs a delayed alarm according to the sudden noise; The third noise reduction strategy subunit determines whether to reduce the volume according to the current alarm period.

10. A method for coordinating and managing multiple devices after cardiothoracic surgery based on the Internet of Things, applied to the multi-device coordinating and managing system after cardiothoracic surgery based on the Internet of Things according to any one of claims 1 to 9, characterized in that: include, Identify suspected postoperative risk data from real-time postoperative monitoring data; Alarming the suspected risk data after surgery at a preset alarm frequency according to a preset priority; Analyze suspected risk data, filter out false monitoring data, and reduce the corresponding preset alarm frequency based on the false reporting type of the false monitoring data; Analyze the impact of the alarm on environmental noise and trigger the alarm mode switching strategy based on the impact level.

Images