Intelligent operation and maintenance method and system of medical equipment, electronic equipment and storage medium

Abstract

The invention discloses an intelligent operation and maintenance method and system for medical equipment, electronic equipment and a storage medium, and relates to the technical field of medical equipment operation and maintenance. The method comprises the following steps: acquiring equipment operation parameters and historical use data of each medical equipment in a hospital, and constructing an equipment parameter diagram of the hospital based on each equipment operation parameter and historical use data; determining abnormal medical equipment in the equipment data graph in combination with the historical fault equipment graph of the hospital; determining an anomaly type and an anomaly level based on the anomaly parameters of the abnormal medical equipment; and determining an operation and maintenance strategy corresponding to the abnormal medical equipment in combination with the diagnosis time window of the abnormal medical equipment, the medical importance level, the abnormal type and the abnormal level. By implementing the technical scheme provided by the invention, the operation and maintenance efficiency of the medical equipment can be improved.

Description

Technical Field

[0001] This application relates to the technical field of medical device operation and maintenance, and particularly relates to an intelligent operation and maintenance method, system, electronic device, and storage medium for medical devices. Background Art

[0002] With the development of medical technology, the quantity and variety of various medical devices in hospitals are constantly increasing. The normal operation of medical devices is directly related to the quality of medical services and patient safety. Therefore, the operation and maintenance management of medical devices has become an important part of hospital management.

[0003] Currently, hospitals generally adopt a preventive maintenance operation and maintenance method, that is, according to the maintenance cycle specified in the device manual, the device is regularly inspected and maintained. Since device maintenance is only carried out according to a fixed cycle and cannot adjust the maintenance strategy in a timely manner according to the actual operation status of the device, some devices may have accidental failures within the maintenance cycle, while some other devices may have unnecessary maintenance, reducing the operation and maintenance efficiency of medical devices and increasing the risk of medical service interruption at the same time. Summary of the Invention

[0004] This application provides an intelligent operation and maintenance method, system, electronic device, and storage medium for medical devices, which can improve the operation and maintenance efficiency of medical devices.

[0005] In a first aspect, this application provides an intelligent operation and maintenance method for medical devices, and the method includes: Obtain the device operation parameters and historical usage data of each medical device in the hospital, and construct a device parameter map of the hospital based on each of the device operation parameters and historical usage data; Determine abnormal medical devices in the device data map in combination with the historical faulty device map of the hospital; Determine the abnormal type and abnormal level based on the abnormal parameters of the abnormal medical device; Determine the operation and maintenance strategy corresponding to the abnormal medical device in combination with the diagnosis time window, medical importance level, and the abnormal type and abnormal level of the abnormal medical device.

[0006] By adopting the above technical solution, by obtaining the operation parameters and historical usage data of medical devices to construct a device parameter map, and combining the historical faulty device map to determine abnormal medical devices, then determining the abnormal type and abnormal level based on the abnormal parameters, and finally determining the operation and maintenance strategy according to the diagnosis time window, medical importance level, and abnormal type and abnormal level, the real-time monitoring and abnormal warning of the operation status of medical devices are realized, enabling the device maintenance to be flexibly adjusted according to the actual operation status, avoiding the problems of untimely or excessive maintenance caused by the fixed-cycle maintenance method, thereby improving the operation and maintenance efficiency of medical devices and reducing the risk of medical service interruption.

[0007] In a second aspect of the present application, an intelligent operation and maintenance system for medical devices is provided. The system includes: A data acquisition module, configured to acquire the device operation parameters and historical usage data of each medical device in a hospital, and construct a device parameter map of the hospital based on the device operation parameters and historical usage data; An abnormal device determination module, configured to determine abnormal medical devices in the device data map by combining the historical fault device map of the hospital; An abnormal information determination module, configured to determine the abnormal type and abnormal level based on the abnormal parameters of the abnormal medical device; An operation and maintenance strategy determination module, configured to determine the operation and maintenance strategy corresponding to the abnormal medical device by combining the diagnosis time window, medical importance level of the abnormal medical device, and the abnormal type and abnormal level.

[0008] In a third aspect of the present application, a computer storage medium is provided. The computer storage medium stores multiple instructions, and the instructions are adapted to be loaded and executed by a processor to perform the above method steps.

[0009] In a fourth aspect of the present application, an electronic device is provided, including: a processor and a memory; wherein, the memory stores a computer program, and the computer program is adapted to be loaded and executed by the processor to perform the above method steps.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: The present application constructs a device parameter map by acquiring the operation parameters and historical usage data of medical devices, determines abnormal medical devices by combining the historical fault device map, then determines the abnormal type and abnormal level based on the abnormal parameters, and finally determines the operation and maintenance strategy according to the diagnosis time window, medical importance level, and abnormal type and abnormal level, realizing real-time monitoring of the operation status of medical devices and abnormal early warning, enabling device maintenance to be flexibly adjusted according to the actual operation status, avoiding problems of untimely maintenance or over-maintenance caused by the fixed-cycle maintenance method, thereby improving the operation and maintenance efficiency of medical devices and reducing the risk of medical service interruption. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a flowchart of an intelligent operation and maintenance method for medical devices provided by an embodiment of the present application; Figure 2 is a module diagram of an intelligent operation and maintenance system for medical devices provided by an embodiment of the present application; Figure 3 is a structural diagram of an electronic device provided by an embodiment of the present application.

[0012] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0013] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0015] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0016] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0017] Please refer to Figure 1 , a flowchart of an intelligent operation and maintenance method for medical equipment is proposed. The method can be implemented by a computer program, can be implemented by a single-chip microcomputer, or can be run on an intelligent operation and maintenance system for medical equipment. The computer program can be integrated in a computer device or can be run as an independent tool application. Specifically, the method includes steps 10 to 40, and the steps are as follows: Step 10: Obtain the equipment operating parameters and historical usage data of each medical device in the hospital, and construct an equipment parameter map of the hospital based on the equipment operating parameters and historical usage data.

[0018] In the embodiments of the present application, medical devices refer to various devices used for medical services such as patient diagnosis, treatment, and monitoring in hospitals, including but not limited to medical imaging devices, life support devices, inspection devices, treatment devices, etc.

[0019] In the embodiments of the present application, device operation parameters refer to various index data reflecting the current working state of medical devices, including but not limited to physical parameters such as the operating temperature, voltage, current, vibration, noise, and pressure of the device, as well as the functional parameters and performance parameters of the device.

[0020] In the embodiments of the present application, historical usage data refers to the information related to the historical operation of devices recorded in the hospital device management system, including but not limited to historical fault records, historical usage frequencies, historical operation data, etc.

[0021] In the embodiments of the present application, a device parameter graph refers to an associated topological structure constructed by device nodes and parameter nodes, where the device nodes store the identification information of medical devices, and the parameter nodes store the corresponding device operation parameters and their normal operation ranges, which are used to characterize the operation states of various medical devices in the hospital.

[0022] Specifically, in order to ensure the effective monitoring of medical devices with different levels of importance, first, a medical importance level is set based on the impact of the device on medical services. Life support devices (such as ventilators and monitors) are set as the highest level A, emergency surgical devices (such as operating tables and anesthetic machines) are set as level B, and conventional diagnosis and treatment devices (such as DR and CT) are set as level C. Correspondingly, the acquisition frequency for level A devices is once per minute, the acquisition frequency for level B devices is once every 5 minutes, and the acquisition frequency for level C devices is once per hour.

[0023] According to the set acquisition frequency, the original operation data is obtained through the data acquisition module deployed on the medical device. Taking a ventilator as an example, key operation parameters such as airway pressure, inspiratory time, expiratory time, and tidal volume are acquired. At the same time, historical usage data such as the fault repair records, average daily usage duration, and historical operation parameters of the ventilator in the past year are extracted from the database of the hospital device management system. The acquired original operation data is preprocessed such as denoising and normalization to eliminate abnormal data fluctuations. Then, the processed data is aligned with the historical operation data according to the time stamp. For example, the real-time acquired airway pressure data is corresponding to the historical airway pressure data in the time dimension one by one. The device operation parameters obtained in this way not only contain the current state information of the device but also maintain the relevance with the historical data.

[0024] Furthermore, based on the processed data, group each medical device by functional category and department, extract the key operating parameter dimensions, determine the normal operating range, construct the associated topological structure between device nodes and parameter nodes, and form a complete device parameter map, thereby providing a data basis for subsequent anomaly detection.

[0025] Based on the above embodiments, as an alternative embodiment, the step of constructing a device parameter map of a hospital based on the operating parameters of each device and historical usage data may further include the following steps: Step 101: Group each medical device according to its functional category and the department it belongs to.

[0026] Specifically, to improve the efficiency of device management, it is necessary to scientifically group the medical devices in the hospital. First, divide them into four major functional categories according to the functional characteristics of the devices: diagnostic, therapeutic, monitoring, and auxiliary. Among them, the diagnostic category includes imaging devices such as CT, DR, and ultrasound; the therapeutic category includes treatment devices such as operating tables and ventilators; the monitoring category includes monitoring devices such as electrocardiogram monitors and blood pressure monitors; and the auxiliary category includes auxiliary devices such as infusion pumps and injection pumps. On the basis of functional classification, further perform secondary grouping according to the department to which the device belongs. For example, group the CT and DR in the radiology department into the radiology diagnosis group, and group the operating table and anesthesia machine in the operating room into the operating room treatment group. This two-level grouping method not only considers the functional similarity of the devices but also reflects the spatial distribution characteristics of the devices, facilitating the subsequent targeted analysis of the device operating status.

[0027] Step 102: For each group of medical devices, extract the key dimensions in the corresponding device operating parameters, and determine the normal operating range of each key dimension based on historical usage data.

[0028] Specifically, for each device group, it is necessary to determine the key parameter dimensions that can best reflect the device operating status. Taking the operating room treatment group as an example, the key dimensions of the operating table include mechanical parameters such as the bed board angle, lifting height, and load-bearing pressure, and the key dimensions of the anesthesia machine include physiological parameters such as oxygen concentration, respiratory rate, and tidal volume. By analyzing the operating records of the devices in the historical usage data, statistically analyze the numerical distribution of each parameter in the normal working state, and use the 3σ principle to determine the parameter fluctuation range, and set the mean ± 3 times the standard deviation as the normal operating range. For example, the normal range of the bed board angle of a certain model of operating table is 0° - 90°, and if it exceeds this range, there may be a mechanical failure. This method of defining the range based on historical data can accurately reflect the actual usage characteristics of the device.

[0029] Step 103: Construct the associated topological structure between each device node and parameter node, where the device node stores the medical device identification information, and the parameter node stores the corresponding device operating parameters and the normal operating range.

[0030] Specifically, when constructing the associated topological structure, first create device nodes, and each node contains identification information such as device ID, device model, and affiliated department. Then create multiple parameter nodes for each device to store the key dimension parameters determined in step 102 and their normal operating ranges. Taking a certain anesthesia machine as an example, create a device node to store information such as "device ID: AN001, model: XX-100, department: operating room", and at the same time create parameter nodes to store parameter information such as "oxygen concentration: 21%-100%, respiratory rate: 8-30 times / minute, tidal volume: 200-800 ml". The device node is connected to its corresponding parameter nodes through directed edges to form a star-shaped topological structure, which is convenient for quickly retrieving and updating the device operating status.

[0031] Step 104: According to the collaborative working relationship between medical devices, establish associated edges between device nodes, and the associated edges include weights reflecting the tightness of collaboration.

[0032] Specifically, there is a functional cooperation relationship between medical devices, and associated edges between device nodes need to be established. By analyzing historical data such as operation records and diagnosis and treatment processes, identify the collaborative working modes between devices. For example, during surgery, the anesthesia machine and the monitor are used in combination very frequently, and a high-weight associated edge (weight value 0.9) is established between them; while the operating table and the infusion pump are used in combination less frequently, and a low-weight associated edge (weight value 0.3) is established between them. The weight calculation formula is: the number of times two devices are used together / the total number of times the devices are used. This type of weighted associated edge can quantitatively reflect the strength of the collaborative relationship between devices.

[0033] Step 105: Integrate the associated topological structure and the associated edges between medical devices to obtain the device parameter graph of the hospital.

[0034] Specifically, integrate the constructed associated topological structure and the associated edges between devices to form a complete device parameter graph. Use a graph database to store this complex network structure, with device nodes and parameter nodes as the vertices of the graph, and the connections between devices and parameters as well as the collaborative relationships between devices as the edges. For example, connect the star-shaped topological structures of all devices in the operating room through collaborative relationship edges to form a local subgraph, and further connect the subgraphs of multiple departments to form the device parameter graph of the whole hospital. This graph structure not only preserves the parameter information of the devices but also reflects the associated relationships between the devices, providing a data basis for subsequent abnormal propagation analysis.

[0035] Step 20: Determine abnormal medical devices in the device data graph in combination with the historical fault device graph of the hospital.

[0036] In the embodiments of the present application, the historical fault equipment graph refers to a knowledge graph that records the historical fault information of medical equipment in a hospital, including but not limited to information such as the faulty equipment, fault parameters, fault types, and abnormal patterns of equipment operation parameters in each fault event, and is used to establish the corresponding relationship between equipment fault characteristics and fault types.

[0037] In the embodiments of the present application, an abnormal medical device refers to a medical device with potential risks in its current operating state, specifically manifested as: the operating parameters of the device show abnormal fluctuations and have a high similarity to the fault characteristics recorded in the historical fault equipment graph, or the abnormal score of the device exceeds a preset score threshold, and the device that requires timely fault diagnosis and maintenance.

[0038] Specifically, first, construct a historical fault equipment graph, and establish the corresponding relationship between the fault parameters and fault types in each fault event by analyzing the maintenance records. For example, when a certain type of ventilator shows a parameter combination of continuous airway pressure exceeding 40 cmH2O and tidal volume less than 200 ml, it usually shows a pipeline blockage fault. For each device node in the device data graph, extract the operating parameters in the current parameter node and calculate the deviation value from the normal operating range. Match these deviation values with the fault parameters of the same type of device in the historical fault graph to obtain the parameter abnormality similarity. When the parameter abnormality similarity of a certain ventilator exceeds 0.8, mark it as a high-risk device, and calculate the associated risk value of the device with an associated edge. Finally, comprehensively consider the parameter abnormality similarity and the associated risk value, calculate the abnormal score, and determine the device with a score exceeding the threshold as an abnormal medical device.

[0039] Based on the above embodiments, as an alternative embodiment, the step of determining abnormal medical devices in the device data graph in combination with the historical fault equipment graph of the hospital may further include the following steps: Step 201: Construct a historical fault equipment graph of the hospital, and the historical fault equipment graph includes the fault parameters and fault types of historical fault equipment.

[0040] Specifically, in order to effectively utilize historical fault experience, a systematic historical fault equipment map needs to be constructed. First, extract the fault repair records of the past three years from the maintenance record database of the hospital equipment management system, including data such as fault equipment information, abnormal parameter values at the time of fault occurrence, and fault type determination results. Classify and organize the fault cases of each type of equipment, and extract the combination of characteristic parameters at the time of fault occurrence. For example, when a certain type of CT has a tube fault, it is usually accompanied by abnormal fluctuations in high voltage value and unstable tube current; when a certain type of ventilator has a pipeline blockage, it has characteristic parameters such as increased airway pressure and decreased tidal volume. Establish a mapping relationship between these fault characteristic parameters and the corresponding fault types to form a complete fault equipment map, providing a reference benchmark for subsequent fault identification.

[0041] Step 202: For each equipment node in the equipment data graph, extract the deviation value between the equipment operation parameter in the current parameter node and the corresponding normal operation range.

[0042] Specifically, in order to detect equipment anomalies in a timely manner, it is necessary to monitor the equipment operation parameters in real time. The system reads the equipment node information one by one from the equipment data graph, and obtains the current operation parameter value stored in the parameter node connected to the equipment and the preset normal operation range. Calculate the deviation degree between each parameter value and the mean value of its normal range, and use standardization processing to unify the parameter deviations of different dimensions to the same scale. Taking a ventilator as an example, if the airway pressure is 45 cmH2O at a certain moment and its normal range is 15 - 35 cmH2O, then calculate the standardized pressure deviation value; similarly, calculate the deviation values of other parameters such as tidal volume and respiratory rate. This standardized deviation value calculation method makes the abnormal degrees of different parameters comparable.

[0043] Step 203: Match and calculate the deviation value with the fault parameters of the same type of fault equipment in the historical fault equipment map to obtain the parameter anomaly similarity.

[0044] Specifically, in order to compare the current abnormal state of the equipment with historical fault experience, it is necessary to calculate the parameter anomaly similarity. Using the vector cosine similarity method, combine the parameter deviation values of the current equipment as a feature vector, and match and calculate it with the fault parameter vector of the same type of equipment in the historical fault map. For example, calculate the cosine similarity between the feature vector composed of the current airway pressure deviation, tidal volume deviation and other parameters of a ventilator and the feature vector of the pipeline blockage fault recorded in the historical fault map to obtain the parameter anomaly similarity value. The similarity value ranges from 0 to 1, and the larger the value, the more similar the current abnormal state is to the historical fault characteristics.

[0045] Step 204: Obtain high-risk devices with a parameter anomaly similarity higher than the similarity threshold, and determine the associated risk values of associated devices related to the high-risk devices according to the associated edges of the high-risk devices in the device data graph.

[0046] Specifically, the purpose of determining high-risk devices and their influence scope is to evaluate the diffusion risk of device anomalies. First, set a similarity threshold (such as 0.8), and mark devices with a parameter anomaly similarity exceeding the threshold as high-risk devices. Then, traverse along the associated edges of the high-risk devices in the device data graph, and calculate the risk exposure degree of the associated devices according to the weights of the associated edges. The specific calculation method is: associated risk value = anomaly similarity of the high-risk device × weight of the associated edge × attenuation coefficient. The attenuation coefficient decreases with the increase of the associated path, indicating the attenuation effect of risk propagation. This calculation method not only considers the intensity of the collaborative relationship between devices but also reflects the distance attenuation characteristics of risk propagation.

[0047] Step 205: Calculate the anomaly scores of each medical device by comprehensively considering the parameter anomaly similarity and the associated risk value, and determine the devices with anomaly scores exceeding the score threshold as abnormal medical devices.

[0048] Specifically, in order to comprehensively evaluate the abnormal state of the device, it is necessary to consider both the abnormal degree of the device itself and the associated risk. The weighted summation method is used to calculate the anomaly score: score = w1×parameter anomaly similarity + w2×associated risk value. The weights w1 and w2 are determined according to the key points of hospital device management. For example, when focusing on the anomaly of the device itself, w1 = 0.7 and w2 = 0.3. Set a score threshold (such as 0.75), and determine the devices with anomaly scores exceeding the threshold as abnormal medical devices that need to be processed preferentially. This scoring mechanism can not only identify devices with serious parameter anomalies but also discover potential risk devices with slightly abnormal parameters that may affect other important devices, which helps to formulate a reasonable maintenance priority.

[0049] Step 30: Determine the anomaly type and anomaly level based on the abnormal parameters of the abnormal medical device.

[0050] Specifically, to accurately determine the nature of the equipment failure, first, extract the set of abnormal parameters from the parameter nodes of the abnormal medical equipment, record the chronological order of the occurrence of each abnormal parameter, and form a parameter abnormality sequence. For example, for a certain ventilator, the airway pressure first increases, then the tidal volume decreases, and finally the pressure alarm is triggered. This sequence of abnormal parameter changes is matched with the preset fault feature sequence library. The abnormal type is determined as a pipeline blockage fault through sequence matching. Then, calculate the proportion of the abnormal parameters in the total parameters of the equipment (for example, there are 3 abnormal parameters and 10 total parameters, with a proportion of 30%), and combine it with the abnormal score of the equipment (such as 0.85). According to the preset grading standard, calculate the abnormal severity index of 0.75, which is correspondingly determined as a Class B abnormality. This analysis method based on the evolution of the parameter sequence can more accurately identify the fault type and evaluate the fault severity.

[0051] Based on the above embodiments, as another alternative embodiment, for the step of determining the abnormal type and abnormal level based on the abnormal parameters of the abnormal medical equipment, the following steps may further be included: Step 301: Extract the set of abnormal parameters of the abnormal medical equipment, form a parameter abnormality sequence according to the chronological order of the occurrence of each abnormal parameter in the set of abnormal parameters, and perform a similarity match between the parameter abnormality sequence and the preset fault feature sequence to determine the abnormal type.

[0052] Specifically, to accurately identify the equipment fault type, it is necessary to analyze the evolution process of the abnormal parameters. First, extract all the parameters that exceed the normal operating range from the parameter nodes of the abnormal medical equipment to form a set of abnormal parameters. Taking a ventilator as an example, extract abnormal parameters such as airway pressure, tidal volume, and respiratory rate. According to the timestamp information of the parameter abnormality, sort these parameters in chronological order of the occurrence of the abnormality to construct a parameter abnormality sequence. For example, the sequence "Airway pressure increase (t1)->Tidal volume decrease (t2)->Pressure alarm trigger (t3)". The system pre-stores the characteristic sequence templates of various faults. For example, the characteristic sequence of the pipeline blockage fault is "Airway pressure increase->Tidal volume decrease->Pressure alarm". Use the sequence edit distance algorithm to calculate the similarity between the current abnormal sequence and each fault characteristic sequence. The fault type with the highest similarity is the abnormal type of the equipment. This analysis method based on the time series evolution can more accurately reflect the fault development process.

[0053] Step 302: Calculate the abnormal severity index according to the abnormal score of the abnormal medical equipment and the proportion of the number of abnormal parameters in the total parameters of the abnormal medical equipment.

[0054] Specifically, to quantitatively evaluate the severity of a fault, it is necessary to comprehensively consider the abnormal range and degree. First, calculate the ratio of the number of abnormal parameters of the abnormal medical device to the total number of device parameters to obtain the proportion of parameter abnormalities. For example, if a CT scanner monitors a total of 20 operating parameters and currently has 5 abnormal parameters, the proportion of parameter abnormalities is 25%. Combining the abnormal score calculated in step 205 (reflecting the degree of parameter abnormality), use the weighted calculation formula: Abnormal severity index = 0.6 × Abnormal score + 0.4 × Proportion of parameter abnormalities. If the abnormal score is 0.85 and the proportion of parameter abnormalities is 0.25, the calculated abnormal severity index is 0.61. This calculation method considers both the breadth of the abnormality (the range of parameters involved) and reflects the depth of the abnormality (the degree of parameter deviation).

[0055] Step 303: Determine the abnormal level in combination with the abnormal severity index.

[0056] Specifically, determine the abnormal level according to the abnormal severity index to guide subsequent maintenance decisions. Set the grading criteria: a severity index greater than 0.8 is grade A (severe abnormality), and immediate shutdown for repair is required; an index between 0.5 - 0.8 is grade B (moderate abnormality), and maintenance needs to be arranged in a timely manner; an index between 0.3 - 0.5 is grade C (mild abnormality), and it can be maintained within the plan. Taking the abnormal severity index of 0.61 calculated in step 302 as an example, it is determined as a grade B abnormality. In addition, for devices with a higher medical importance level, the grading threshold is appropriately reduced to improve the warning sensitivity. For example, for life support devices, the determination threshold for grade B is adjusted to 0.4 - 0.7. This grading mechanism can allocate maintenance resources differently according to the importance of the device.

[0057] Step 40: Determine the corresponding operation and maintenance strategy for the abnormal medical device in combination with the diagnostic time window, medical importance level, abnormal type, and abnormal level of the abnormal medical device.

[0058] In the embodiments of the present application, the diagnostic time window refers to the available time period during which a medical device allows for fault diagnosis and repair, including but not limited to the idle period of the device, the planned maintenance period, the non-emergency period at night, etc. The length of this time window is affected by factors such as the device usage arrangement and the patient visit plan, and is used to evaluate the time constraint for device repair.

[0059] In the embodiments of the present application, the medical importance level refers to the importance level determined according to the impact degree of a medical device on medical services, and is divided into three levels: A / B / C. Among them, level A is life support devices (such as ventilators, monitors, etc.), which directly affect the life safety of patients; level B is emergency surgery devices (such as operating tables, anesthesia machines, etc.), which affect the normal development of emergency medical services; level C is conventional diagnosis and treatment devices (such as DR, CT, etc.), which have a relatively small impact on medical services.

[0060] In the embodiments of the present application, the operation and maintenance strategy refers to a maintenance plan formulated according to the specific conditions of abnormal medical devices, including but not limited to the determination of repair priorities, technical requirements for maintenance personnel, repair time arrangements, spare part preparation plans, etc., and is used to guide the specific implementation of equipment maintenance work. This strategy needs to comprehensively consider multiple factors such as the type of equipment abnormality, the level of abnormality, the diagnostic time window, and the medical importance level.

[0061] Specifically, the operation and maintenance strategy is formulated by analyzing the various indicators of abnormal medical devices. First, the repair technical requirements are evaluated. For example, for a failure in the signal acquisition of a monitor (Class C abnormality), an electronic maintenance engineer is required to handle it, with a repair duration of 1 hour and the replacement of the signal acquisition board. The urgency of the repair is evaluated based on the medical importance level (Class B) of the equipment and the available repair time (16:00 - 18:00 after the outpatient service ends). The repair complexity is calculated as 0.4, and the delay risk index is 0.5, and the repair priority is determined as "scheduled processing". Based on this, the operation and maintenance strategy is generated: arrange the repair task at 16:30 on the same day, to be executed by an electronic maintenance engineer, and transfer the patient to a standby monitor before the repair. This strategy not only ensures the repair quality but also reduces the impact on medical services.

[0062] Based on the above embodiments, as another alternative embodiment, for the step of determining the operation and maintenance strategy corresponding to the abnormal medical device by combining the diagnostic time window, medical importance level, and type and level of abnormality of the abnormal medical device, the following steps may further be included: Step 401: Determine the repair complexity according to the type and level of abnormality. The repair complexity is determined by the level of technical personnel required, the repair duration, and the spare part requirement list.

[0063] Specifically, query the fault repair knowledge base and match the repair requirements corresponding to the type of abnormality. Taking the failure of the ventilator pipeline blockage (Class B abnormality) as an example, three repair elements need to be determined: the requirement for the level of technical personnel is a senior maintenance engineer (coefficient 0.8), the estimated repair duration is 2 hours (coefficient 0.6), and the spare part requirements include air circuit components and sealing rings (coefficient 0.5). Using the weighted calculation formula: repair complexity = 0.4×technical personnel level coefficient + 0.35×repair duration coefficient + 0.25×spare part requirement coefficient, the repair complexity of this fault is obtained as 0.65. This multi-dimensional complexity evaluation method can comprehensively reflect the difficulty and resource requirements of the repair task.

[0064] Step 402: Calculate the repair delay risk index based on the diagnostic time window and medical importance level. The repair delay risk index reflects the degree of impact on medical services caused by the postponement of equipment repair.

[0065] Specifically, to evaluate the rationality of the maintenance time arrangement, it is necessary to calculate the impact that maintenance delays may cause. First, determine the basic risk value according to the medical importance level. For example, the basic risk value of Class A equipment is 0.9, Class B is 0.6, and Class C is 0.3. Then analyze the limiting factors of the diagnostic time window, including the equipment's daily usage plan, patient visit arrangements, etc. Calculate the time urgency: Urgency = 1 - (Available maintenance time / 24 hours). For example, for a certain ventilator (Class A equipment), the available maintenance time is from 23:00 at night to 5:00 the next day, and the time urgency is 0.75. Finally, calculate the maintenance delay risk index: Risk index = Basic risk value × Time urgency, and the maintenance delay risk index of this equipment is obtained as 0.675. This calculation method takes into account both the importance of the equipment and the impact of time constraints.

[0066] Step 403: Determine the maintenance priority based on the maintenance complexity and the maintenance delay risk index, and determine the corresponding operation and maintenance strategy for the abnormal medical equipment based on the maintenance priority.

[0067] Specifically, determine the maintenance priority and formulate the corresponding operation and maintenance strategy based on the urgency of the maintenance task. First, perform a weighted calculation of the maintenance complexity and the maintenance delay risk index: Priority index = 0.45 × Maintenance complexity + 0.55 × Maintenance delay risk index. When the priority index is greater than 0.8, it is determined as the "Handle immediately" level; when it is between 0.5 - 0.8, it is the "Handle with priority" level; when it is less than 0.5, it is the "Plan to handle" level. Taking the above ventilator as an example, with a maintenance complexity of 0.65 and a delay risk index of 0.675, the calculated priority index is 0.664, which is determined as the "Handle with priority" level. Accordingly, generate the operation and maintenance strategy: Arrange senior maintenance engineers to perform maintenance at 23:00 on the same day, prepare the gas path components and sealing rings 2 hours in advance, and at the same time allocate a backup ventilator to ensure the continuity of medical services. This method of formulating strategies based on multiple factors not only ensures the maintenance efficiency but also ensures the continuity of medical services.

[0068] Based on the above embodiments, as an optional embodiment, an intelligent operation and maintenance method for medical equipment may further include the following process: Specifically, to master the abnormal distribution law of medical devices, the system counts the abnormal conditions of various devices every month. First, the devices are classified according to functional categories and departments. For example, the anesthesia machines and monitors in the operating room are grouped together. The number of abnormalities occurring in each group of devices within a unit of time (such as monthly) is counted, and the abnormal occurrence frequency is calculated. At the same time, the level distribution of each abnormality is recorded. For example, the proportion of Class A abnormalities is 20%, Class B is 50%, and Class C is 30%. These data are plotted into a risk heat map according to device categories and department locations. The horizontal axis represents device categories, the vertical axis represents the departments to which they belong, and the shade of color represents the risk level (calculated by weighting the abnormal frequency and abnormal level). For example, the monthly abnormal frequency of the anesthesia machine group in the operating room is 3 times, which is displayed in red; the monthly abnormal frequency of the infusion pump group in the general ward is 1 time, which is displayed in yellow. This visual display method intuitively reflects the spatial distribution characteristics of device abnormalities.

[0069] Based on the risk heat map, select the device groups with the top 20% abnormal frequencies as high-frequency abnormal device groups. For example, it is found that the anesthesia machine group and the monitor group in the operating room both belong to high-frequency abnormal devices. Analyze the abnormal occurrence times of these devices, and use the time series correlation algorithm to calculate the degree of abnormal correlation between devices. The specific calculation method is as follows: within a 30-day observation window, count the distribution of the time intervals between the occurrences of abnormalities of two devices. If 90% of the abnormal time intervals are less than 2 hours, it is considered that these two devices have a high degree of correlation (correlation coefficient 0.8). This analysis method can discover the potential propagation law between device abnormalities.

[0070] Furthermore, to improve the prediction accuracy of abnormal propagation risks, it is necessary to dynamically adjust the association weights in the device parameter map according to device correlations. For device pairs with high calculated correlations, increase the weight values of the association edges between them. Use the adaptive adjustment formula: new weight = original weight + α × correlation coefficient, where α is the learning rate (taking a value of 0.1). For example, the original association weight between a certain anesthesia machine and a monitor is 0.6, and the correlation coefficient is 0.8, then the adjusted weight is 0.68. At the same time, regularly (such as monthly) re-evaluate device correlations and dynamically update the weight values. This adaptive weight adjustment mechanism can make the device parameter map more accurately reflect the actual association relationship between devices and improve the accuracy of abnormal propagation risk assessment.

[0071] Please refer to Figure 2 , which is a schematic diagram of the modules of an intelligent operation and maintenance system for medical devices provided by an embodiment of the present application. Among them, the system includes: A data acquisition module, configured to acquire the device operation parameters and historical usage data of each medical device in the hospital, and construct a device parameter map of the hospital based on each of the device operation parameters and historical usage data; An abnormal device determination module, configured to determine abnormal medical devices in the device data graph by combining the historical faulty device map of the hospital; An abnormal information determination module, configured to determine the abnormal type and abnormal level based on the abnormal parameters of the abnormal medical devices; An operation and maintenance strategy determination module, configured to determine the operation and maintenance strategy corresponding to the abnormal medical devices by combining the diagnosis time window, medical importance level, and the abnormal type and abnormal level of the abnormal medical devices.

[0072] Optionally, the data acquisition module is further configured to determine the corresponding acquisition frequency according to the medical importance level of each medical device; Obtain the original operation data of each medical device according to the acquisition frequency; Use the historical fault records, historical usage frequencies, and historical operation data corresponding to each medical device extracted from the hospital device management system as historical usage data; Preprocess the original operation data and perform time series alignment with the historical operation data to obtain device operation parameters.

[0073] Optionally, the data acquisition module is further configured to group each medical device according to the functional category and the department to which it belongs; For each group of medical devices, extract the key dimensions in the corresponding device operation parameters, and determine the normal operation range of each key dimension based on the historical usage data; Construct an association topology structure between each device node and parameter node, where the device node stores medical device identification information, and the parameter node stores the corresponding device operation parameters and the normal operation range; According to the collaborative working relationship between medical devices, establish association edges between device nodes, and the association edges include weights reflecting the collaborative tightness; Integrate the association topology structure and the association edges between medical devices to obtain the device parameter graph of the hospital.

[0074] Optionally, the abnormal device determination module is further configured to construct a historical faulty device map of the hospital, and the historical faulty device map includes the fault parameters and fault types of historical faulty devices; For each device node in the device data graph, extract the deviation value between the device operation parameters in the current parameter node and the corresponding normal operation range; Perform a matching calculation on the deviation value and the fault parameters of faulty devices of the same type in the historical faulty device map to obtain the parameter anomaly similarity; Obtain high-risk devices with the parameter anomaly similarity higher than the similarity threshold, and determine the association risk value of the associated devices related to the high-risk devices according to the association edges of the high-risk devices in the device data graph; Based on the above-mentioned parameter anomaly similarity and the associated risk value, calculate the anomaly score for each medical device, and determine the devices with the anomaly score exceeding the score threshold as abnormal medical devices.

[0075] Optionally, the anomaly information determination module is further configured to extract the set of anomaly parameters of the abnormal medical device, form a parameter anomaly sequence according to the order of occurrence of each anomaly parameter in the set of anomaly parameters, and perform similarity matching between the parameter anomaly sequence and a preset fault feature sequence to determine the anomaly type. Calculate the anomaly severity index based on the anomaly score of the abnormal medical device and the proportion of the number of anomaly parameters in the total parameters of the abnormal medical device. Determine the anomaly level in combination with the anomaly severity index.

[0076] Optionally, the operation and maintenance strategy determination module is further configured to determine the maintenance complexity according to the anomaly type and anomaly level, and the maintenance complexity is determined by the level of technical personnel required, the maintenance duration, and the spare part requirement list. Calculate the maintenance delay risk index based on the diagnosis time window and the medical importance level, and the maintenance delay risk index reflects the degree of impact on medical services caused by the postponement of equipment maintenance. Determine the maintenance priority based on the maintenance complexity and the maintenance delay risk index, and determine the operation and maintenance strategy corresponding to the abnormal medical device based on the maintenance priority.

[0077] Optionally, the operation and maintenance strategy determination module is further configured to count the anomaly occurrence frequency and anomaly level of different types of medical devices, and generate a device risk heat map. Determine a high-frequency anomaly device group according to the heat map, and calculate the correlation between medical devices in the high-frequency anomaly device group. Dynamically adjust the weights of the associated edges in the device parameter graph according to the correlation.

[0078] It should be noted that when the system provided in the above embodiment realizes its functions, only the division of the above-mentioned functional modules is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0079] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded and executed by a processor to implement the intelligent operation and maintenance method of a medical device in the above embodiment. The specific execution process can refer to the specific description in the above embodiment and will not be elaborated here.

[0080] Please refer to Figure 3 The present application also discloses an electronic device. Figure 3 FIG. is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0081] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0082] Among them, the user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0083] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0084] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305, the processor 301 executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0085] Among them, the memory 305 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 In the memory 305, as a computer storage medium, an operating system, a network communication module, a user interface module, and an application program of an intelligent operation and maintenance method for a medical device may be included.

[0086] In Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 301 can be used to call the application program of the intelligent operation and maintenance method for a medical device stored in the memory 305. When executed by one or more processors 301, the electronic device 300 is caused to execute the method of one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0087] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0088] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some service interfaces. The indirect coupling or communication connection of devices or units can be in electrical or other forms.

[0089] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0091] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0092] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will easily think of other implementation schemes of the present disclosure after considering the specification and the disclosure of the practical truth.

[0093] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An intelligent operation and maintenance method for a medical device, characterized in that, The method includes: Obtaining the device operation parameters and historical usage data of each medical device in the hospital, and constructing a device parameter graph of the hospital based on the device operation parameters and historical usage data; Determining abnormal medical devices in the device data graph by combining with the historical fault device graph of the hospital; Determining the abnormal type and abnormal level based on the abnormal parameters of the abnormal medical devices; Determining the corresponding operation and maintenance strategy for the abnormal medical devices by combining the diagnosis time window, medical importance level, abnormal type and abnormal level of the abnormal medical devices.

2. The intelligent operation and maintenance method of the medical device according to claim 1, characterized in that The obtaining the device operation parameters and historical usage data of each medical device in the hospital includes: Determining the corresponding acquisition frequency according to the medical importance level of each medical device; Obtaining the original operation data of each medical device according to the acquisition frequency; Taking the historical fault records, historical usage frequencies and historical operation data corresponding to each medical device extracted from the hospital device management system as historical usage data; Preprocessing the original operation data and performing time series alignment with the historical operation data to obtain device operation parameters.

3. The intelligent operation and maintenance method of the medical device according to claim 1, characterized in that The constructing the device parameter graph of the hospital based on the device operation parameters and historical usage data includes: Grouping each medical device according to the function category and the department to which it belongs; For each group of medical devices, extracting the key dimensions in the corresponding device operation parameters, and determining the normal operation range of each key dimension based on the historical usage data; Constructing an associated topological structure between each device node and parameter node, where the device node stores medical device identification information, and the parameter node stores the corresponding device operation parameters and normal operation range; According to the collaborative working relationship between medical devices, establishing an associated edge between device nodes, and the associated edge includes a weight reflecting the collaborative tightness; Integrating the associated topological structure and the associated edges between medical devices to obtain the device parameter graph of the hospital.

4. The intelligent operation and maintenance method of the medical device according to claim 1, characterized in that The determining abnormal medical devices in the device data graph by combining with the historical fault device graph of the hospital includes: Constructing a historical fault device graph of the hospital, and the historical fault device graph includes the fault parameters and fault types of historical fault devices; For each device node in the device data graph, extracting the deviation value between the device operation parameters in the current parameter node and the corresponding normal operation range; Performing a matching calculation on the deviation value and the fault parameters of the same type of fault devices in the historical fault device graph to obtain a parameter abnormality similarity; Obtaining high-risk devices with the parameter abnormality similarity higher than the similarity threshold, and determining the associated risk value of the associated devices related to the high-risk devices according to the associated edges of the high-risk devices in the device data graph; Calculating the abnormality score of each medical device by comprehensively considering the parameter abnormality similarity and the associated risk value, and determining the devices with the abnormality score exceeding the score threshold as abnormal medical devices.

5. The intelligent operation and maintenance method of the medical device according to claim 1, characterized in that The determining the abnormal type and abnormal level based on the abnormal parameters of the abnormal medical devices includes: Extract the set of abnormal parameters of the abnormal medical device, form a parameter anomaly sequence according to the order of occurrence of each abnormal parameter in the set of abnormal parameters, and perform similarity matching between the parameter anomaly sequence and a preset fault feature sequence to determine the anomaly type; Calculate the anomaly severity index according to the anomaly score of the abnormal medical device and the proportion of the number of abnormal parameters in the total parameters of the abnormal medical device; Determine the anomaly level in combination with the anomaly severity index.

6. The intelligent operation and maintenance method of the medical device according to claim 1, characterized in that, The determining the operation and maintenance strategy corresponding to the abnormal medical device in combination with the diagnosis time window, medical importance level, and the anomaly type and anomaly level of the abnormal medical device includes: Determine the maintenance complexity according to the anomaly type and anomaly level, and the maintenance complexity is determined by the level of technical personnel required, the maintenance duration, and the spare part requirement list; Calculate the maintenance delay risk index based on the diagnosis time window and medical importance level, and the maintenance delay risk index reflects the degree of impact on medical services caused by the postponement of equipment maintenance; Determine the maintenance priority based on the maintenance complexity and the maintenance delay risk index, and determine the operation and maintenance strategy corresponding to the abnormal medical device based on the maintenance priority.

7. The intelligent operation and maintenance method of the medical device according to claim 3, characterized in that The method further includes: Count the anomaly occurrence frequency and anomaly level of different types of medical devices, and generate a device risk heat map; Determine a high-frequency anomaly device group according to the heat map, and calculate the correlation between each medical device in the high-frequency anomaly device group; Dynamically adjust the weights of the associated edges in the device parameter graph according to the correlation.

8. An intelligent operation and maintenance system for a medical device, characterized in that, The system includes: A data acquisition module, configured to acquire the device operation parameters and historical usage data of each medical device in the hospital, and construct a device parameter graph of the hospital based on each device operation parameter and historical usage data; An abnormal device determination module, configured to determine an abnormal medical device in the device data graph in combination with the historical fault device map of the hospital; An abnormal information determination module, configured to determine the anomaly type and anomaly level based on the abnormal parameters of the abnormal medical device; An operation and maintenance strategy determination module, configured to determine the operation and maintenance strategy corresponding to the abnormal medical device in combination with the diagnosis time window, medical importance level, and the anomaly type and anomaly level of the abnormal medical device.

9. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the method according to any one of claims 1-7.

10. An electronic device, characterized in that, It includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method according to any one of claims 1-7.

Images