An intelligent inventory management system for anesthesia consumables

Abstract

The present invention discloses an intelligent inventory management system for anesthesia consumables, which relates to the technical field of intelligent inventory management of anesthesia consumables, including an anesthesia consumables data collection module, a real-time consumables surplus calculation module, a consumables surplus analysis and classification module, a surgery complexity assessment module, and an inventory update strategy adjustment module; the anesthesia consumables data collection module collects anesthesia consumables information of all ongoing anesthesia surgeries during each anesthesia surgery, including the expected usage and actual take-up of all anesthesia surgeries. The present invention optimizes inventory management, reduces unnecessary replenishment, and improves resource utilization efficiency by calculating the consumables surplus in real time and analyzing the complexity of the surgery through machine learning; based on complexity assessment, the update strategy is dynamically adjusted, especially in scenarios with high surplus consumables, the update frequency is lowered to reduce fluctuations and waste, enhance system flexibility and emergency response capabilities, and ensure the stability of consumables supply.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent inventory management of anesthesia consumables, and in particular to an intelligent inventory management system for anesthesia consumables. Background Art

[0002] The intelligent inventory management system for anesthesia consumables is a comprehensive solution based on IoT technology and data analysis, which aims to optimize the inventory management of anesthesia consumables in hospitals. The system monitors the usage of consumables in real time, automatically records inventory changes, and uses intelligent algorithms to predict future consumables demand by combining historical usage data and surgical scheduling information. At the same time, the system can automatically trigger replenishment orders to avoid insufficient or excessive inventory reserves, ensure the continuous supply of anesthesia consumables, improve hospital operating efficiency and reduce inventory management costs.

[0003] The inventory of anesthesia consumables in the prior art is usually updated in real time. Modern intelligent inventory management systems rely on Internet of Things technology, which monitors the use and inventory status of each consumable in real time through RFID tags, sensors, etc., and can achieve instant updates after the consumables are used, ensuring that the inventory data is real-time and accurate.

[0004] The prior art has the following deficiencies:

[0005] Although real-time updates can ensure the immediate accuracy of inventory data, in actual operations, since consumables are always kept on hand during anesthesia surgery to deal with emergencies, real-time updates may misjudge consumable consumption, causing the system to trigger unnecessary replenishment needs, resulting in confusion in inventory management and waste of resources.

[0006] For example:

[0007] In a complex heart surgery, the anesthesia team will prepare multiple sets of endotracheal tubes, anesthesia masks, and other related consumables to deal with possible emergencies, even if only one set is expected to be used. In modern intelligent inventory management systems, these spare consumables may be identified as consumed by the system at the beginning of the operation. However, after the operation, the spare consumables are not actually used, so the real-time update of the system misjudges the actual inventory consumption, which may cause the hospital to restock consumables when they are not needed. This not only increases the complexity of inventory management, but also may cause waste of resources, affecting the accuracy of the overall inventory and the operating costs of the hospital.

[0008] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0009] The purpose of the present invention is to provide an intelligent inventory management system for anesthesia consumables. By calculating the surplus consumables of anesthesia surgery in real time, the difference between actual demand and spare consumables can be accurately identified, and the complexity of the surgery can be analyzed through a machine learning model to optimize inventory management, reduce unnecessary replenishment needs, and improve resource utilization efficiency. At the same time, based on the complexity assessment results, the inventory update strategy is dynamically adjusted, especially in scenarios with high surplus consumables, the update frequency is lowered, inventory fluctuations and resource waste are reduced, the flexibility and emergency response capabilities of the system are enhanced, and the stability and adequacy of consumables supply are ensured to solve the problems in the above-mentioned background technology.

[0010] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an intelligent inventory management system for anesthesia consumables, comprising an anesthesia consumables data collection module, a real-time consumables surplus calculation module, a consumables surplus analysis and classification module, a surgery complexity assessment module and an inventory update strategy adjustment module;

[0011] Anesthesia consumables data collection module collects information on anesthesia consumables for all ongoing anesthesia surgeries, including the expected usage and actual consumption of all anesthesia surgeries;

[0012] The real-time consumable surplus calculation module performs real-time analysis on the consumables of all anesthesia surgeries and calculates the real-time consumable surplus based on the expected usage and actual amount of anesthesia consumables taken.

[0013] The consumables surplus analysis and classification module analyzes the consumables surplus and divides the ongoing anesthesia surgery into high surplus consumables inventory and normal surplus consumables inventory according to the anesthesia consumables situation;

[0014] The surgery complexity assessment module uses a pre-trained machine learning model to conduct a comprehensive analysis of all anesthesia surgeries performed simultaneously to assess the complexity of anesthesia surgeries in scenarios with high surplus consumables inventory.

[0015] The inventory update strategy adjustment module adjusts the actual inventory update strategy based on the surgical complexity assessment results and reduces the actual inventory update frequency through the real-time inventory update frequency.

[0016] Preferably, when each anesthesia operation is performed, the expected usage of all ongoing anesthesia operations, that is, the expected amount of anesthesia consumables, is collected. The specific steps are as follows:

[0017] Obtain the scheduling information of all ongoing anesthesia surgeries through the hospital's surgical scheduling system;

[0018] Match each surgery with a pre-set anesthesia consumables list template based on the surgery type information obtained from the scheduling system;

[0019] Personalize the generated list of anesthesia consumables through anesthesiologists;

[0020] After the personalized adjustment is completed, the consumables list for each operation is summarized and calculated to obtain the expected usage of each anesthesia consumable;

[0021] The calculated expected usage data of anesthesia consumables are recorded in the central database and bound to the real-time data of actual surgical anesthesia consumable usage.

[0022] Preferably, the actual amount of anesthesia taken in all ongoing anesthesia surgeries is collected in the following manner:

[0023] Use RFID tags, barcodes or QR codes on each consumable. When anesthesiologists extract anesthesia consumables, they automatically record the type and quantity of anesthesia consumables through scanning equipment, upload the recorded data to the central inventory management system in real time, and associate it with the anesthesia surgery scheduling information to ensure that the actual amount of anesthesia consumables extracted for each anesthesia surgery is accurately recorded, thereby collecting the actual amount taken for each anesthesia surgery, and then collecting the actual amount taken for all ongoing anesthesia surgeries.

[0024] Preferably, the consumables of all anesthesia surgeries are analyzed in real time, and the expected usage and actual amount of anesthesia consumables are analyzed in real time to calculate the real-time surplus of consumables. The specific steps are as follows:

[0025] The expected consumption of consumables for each anesthesia operation is set to The actual amount taken is , where i represents different surgeries and the types of consumables are represented by j, then the expected usage of each consumable is The actual amount taken is ;

[0026] Calculate the difference in volume of each consumable per surgery , the calculation expression is: , where represents the difference in the jth consumables for the i-th surgery, Indicates a dynamic adjustment item, which is used to make real-time corrections to the difference amount according to actual usage;

[0027] Based on the difference in volume for each consumable , calculate the real-time margin of each operation, the calculation expression is: ,in, is the consumable importance coefficient of the jth consumable in the i-th surgery, indicating the importance weight of each consumable to the surgery. is the usage frequency of the jth consumable in the i-th surgery, and n represents the total number of consumable types;

[0028] Calculate the real-time surplus of consumables for all anesthesia surgeries. The calculation expression is: , where It represents the real-time surplus of consumables for all anesthesia surgeries, and d represents the total number of all ongoing anesthesia surgeries.

[0029] Preferably, the real-time surplus consumables generated by real-time analysis of the consumables of all anesthesia surgeries are compared with a preset real-time surplus consumables reference value, and the ongoing anesthesia surgeries are divided according to the anesthesia consumables conditions. The specific division steps are as follows:

[0030] If the real-time surplus of consumables is greater than or equal to the real-time surplus reference value of consumables, the ongoing anesthesia surgery is classified as high surplus consumables inventory;

[0031] If the real-time surplus consumables quantity is less than the real-time surplus consumables quantity reference value, the ongoing anesthesia surgery will be classified as normal surplus consumables inventory.

[0032] Preferably, in a scenario with high surplus consumables inventory, the probability of emergency occurrence and the estimated duration of all simultaneously performed anesthesia surgeries are obtained, and after analyzing the probability of emergency occurrence and the estimated duration of surgery, an expected intraoperative emergency index and an estimated uncertainty index for surgery duration are generated, respectively. The expected intraoperative emergency index and the estimated uncertainty index for surgery duration are input into a pre-trained machine learning model to generate a comprehensive complexity coefficient for anesthesia surgery, and the complexity of anesthesia surgery is evaluated by the comprehensive complexity coefficient for anesthesia surgery.

[0033] Preferably, the specific steps of analyzing the probability of emergencies in all the anesthesia surgeries performed simultaneously to generate an expected index of emergencies during surgery are as follows:

[0034] Collect relevant data of all ongoing anesthesia surgeries and set the number of historical emergencies for each surgery i to , the patient's pathological complexity parameter is , the surgery type parameters are The risk factor of anesthetic drugs is , is the number of historical emergencies in the i-th surgery, is the pathological complexity parameter of the i-th surgical patient, is the surgical type parameter of the i-th surgery, is the risk coefficient of anesthesia drugs for the i-th surgery;

[0035] According to the collected parameters, the probability of emergency occurrence in each operation is calculated, and the calculation expression is: , where represents the probability of an emergency occurring in the i-th operation;

[0036] According to the probability of emergencies in all surgeries , calculate the expected index of intraoperative emergencies, and the calculation expression is: , is the surgery importance index, which reflects the contribution weight of the surgery to the overall risk of emergencies. Represents the expected index of intraoperative emergencies.

[0037] Preferably, the specific steps of generating the uncertainty index of surgery duration estimation after analyzing the estimated surgery duration of all anesthesia surgeries performed simultaneously are as follows:

[0038] Collect the estimated duration of each ongoing anesthesia surgery and set the estimated duration of each surgery as ,in, represents the estimated duration of the i-th operation;

[0039] Calculate the uncertainty factor of the duration of each operation, and the calculation expression is: , where represents the uncertainty factor of the estimated duration of the i-th operation, represents the pth influencing factor related to the duration of the i-th operation, is the weight of the pth influencing factor, indicating the contribution of each influencing factor to the duration uncertainty, is the volatility coefficient of the pth influencing factor in the i-th operation, is the inherent complexity adjustment coefficient of the i-th surgery, which is used to balance the complexity differences between surgeries, and N represents the total number of influencing factors;

[0040] After calculating the uncertainty factor for the duration of all surgeries, Finally, the uncertainty factor of the duration is combined to calculate the uncertainty index of the overall surgery duration estimate. The calculation expression is: , where represents the uncertainty index of the estimated operation duration, It represents the priority weight of the i-th surgery, indicating the importance of the surgery in uncertainty assessment.

[0041] Preferably, based on the surgical complexity assessment results, the actual inventory update strategy is adjusted, and the specific steps are as follows:

[0042] The comprehensive complexity coefficient of anesthesia surgery is compared with the preset reference value of the comprehensive complexity coefficient of anesthesia surgery, and the deviation of the complexity coefficient is calculated. The calculation expression is: , where represents the complexity coefficient deviation, represents the comprehensive complexity coefficient of anesthesia surgery, It represents the reference value of the comprehensive complexity coefficient of anesthesia surgery;

[0043] According to the complexity coefficient deviation The size of , calculate the real-time inventory update frequency adjustment factor, the calculation expression is: , where It represents the real-time inventory update frequency adjustment factor, which determines the adjustment range of inventory update frequency. e is the base of the natural index.

[0044] Leverage real-time inventory update frequency adjustment factors Calculate the new actual inventory update frequency. The calculation expression is: , where Indicates the actual inventory update frequency, Indicates the current real-time inventory update frequency.

[0045] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0046] The present invention can accurately identify the difference between actual consumables demand and spare consumables by collecting the expected usage and actual amount taken for each anesthesia operation and calculating the surplus of consumables in real time. By dividing the surgical consumables into high surplus consumables inventory and normal surplus consumables inventory, it can accurately identify possible inventory misjudgments, especially in the scenario of high surplus consumables inventory. The complexity of the operation is comprehensively analyzed through the pre-trained machine learning model, so that inventory management not only relies on simple consumables consumption data, but also takes into account the actual complexity of the operation, greatly reducing unnecessary replenishment needs, avoiding inventory management chaos caused by real-time updates, and improving the accuracy of inventory management and the utilization efficiency of hospital resources.

[0047] Based on the surgical complexity assessment results, the present invention can dynamically adjust the actual inventory update strategy. Especially in the scenario of high surplus consumables inventory, by lowering the real-time inventory update frequency, the system effectively reduces frequent inventory fluctuations and prevents waste of resources. At the same time, after monitoring the inventory and real-time data during the operation, it can quickly adjust according to the actual situation to ensure that the inventory update frequency matches the actual surgical complexity. This flexible adjustment mechanism enables the system to better cope with unforeseen emergencies during the operation and ensure the stability and adequacy of the consumables supply, thereby improving the hospital's overall management capabilities and emergency response speed in complex surgical environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0049] Figure 1 The present invention is a module schematic diagram of an intelligent inventory management system for anesthesia consumables. DETAILED DESCRIPTION

[0050] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0051] The present invention provides Figure 1 An intelligent inventory management system for anesthesia consumables shown includes an anesthesia consumables data collection module, a real-time consumables surplus calculation module, a consumables surplus analysis and classification module, a surgery complexity assessment module, and an inventory update strategy adjustment module;

[0052] Anesthesia consumables data collection module, when each anesthesia surgery is performed, collects the anesthesia consumables information of all the anesthesia surgeries being performed, including the expected usage of all anesthesia surgeries (i.e., the usage of anesthesia consumables predicted based on the type of surgery and experience) and the actual amount taken (i.e., the amount of anesthesia consumables actually taken from the inventory by the anesthesiologist);

[0053] When each anesthesia operation is performed, the expected usage of all ongoing anesthesia operations, that is, the expected amount of anesthesia consumables, is collected. The specific steps are as follows:

[0054] Obtain the scheduling information of all ongoing anesthesia surgeries through the hospital's surgical scheduling system;

[0055] This information usually includes the type of surgery, time, surgeon, anesthesiologist, basic patient information, and estimated duration of surgery. Through seamless integration with the scheduling system, the system can obtain and update surgery information in real time, ensuring that the basic data for the expected usage calculation is up-to-date and accurate.

[0056] Each surgery is matched with a pre-set anesthesia consumables list template based on the surgery type information obtained from the scheduling system;

[0057] These templates are pre-defined based on historical data, surgical guidelines, and physician experience, and contain all the anesthesia consumables and corresponding quantities that are typically required for this type of surgery. For example, for cardiac surgery, the consumables list may include a specific type of endotracheal tube, anesthesia mask, monitoring electrodes, etc. After matching is completed, the system generates a preliminary consumables list for each operation as the basis for subsequent calculations of expected usage.

[0058] The specific needs of each surgery may vary depending on the patient's condition and the complexity of the surgery, so the system will personalize the generated anesthesia consumables list through the anesthesiologist;

[0059] Anesthesiologists can increase or decrease the types and quantities of consumables based on factors such as the patient's body size, medical history, special needs (such as allergies or device contraindications). For example, for a patient with respiratory problems, the physician may add a spare type of endotracheal tube. The adjusted list will be submitted to the system and compared with the original template list to generate the final expected usage data.

[0060] After the personalized adjustment is completed, the consumables list for each operation is summarized and calculated to obtain the expected usage of each anesthesia consumable;

[0061] This process involves matching each consumable in the list with the corresponding item in the inventory system to confirm the quantity and specifications of the required consumables. The system will calculate an accurate expected usage data set based on the type of surgery, list adjustments, and analysis of historical data, and use it as the basis for subsequent inventory management and monitoring. The key to this step is to ensure the accuracy and comprehensiveness of the calculation in order to provide an accurate forecast of consumable demand.

[0062] The calculated expected usage data of anesthesia consumables is recorded in the central database and linked with the real-time data of actual usage of anesthesia consumables during surgery;

[0063] The expected usage for each surgery will serve as a benchmark, and any subsequent extraction, use or adjustment of consumables will be compared with this benchmark. The system will continuously update the database to ensure that the difference between the expected usage and actual usage of all surgeries can be monitored and analyzed in a timely manner, providing data support for the update and management of post-operative inventory. This step of real-time data recording and updating ensures the transparency and traceability of the entire system, allowing hospital management to understand the consumables needs and usage of each surgery at any time.

[0064] Collect actual take volumes (i.e., the amount of supplies actually taken from inventory by the anesthesiologist) for all anesthesia procedures being performed by:

[0065] Use RFID tags, barcodes or QR codes on each consumable. When anesthesiologists extract anesthesia consumables, they automatically record the type and quantity of anesthesia consumables through scanning equipment, upload the recorded data to the central inventory management system in real time, and associate it with the anesthesia surgery scheduling information to ensure that the actual amount of anesthesia consumables extracted for each anesthesia surgery is accurately recorded, thereby collecting the actual amount taken for each anesthesia surgery, and then collecting the actual amount taken for all ongoing anesthesia surgeries.

[0066] The real-time consumable surplus calculation module performs real-time analysis on the consumables of all anesthesia surgeries and calculates the real-time consumable surplus based on the expected usage and actual amount of anesthesia consumables taken.

[0067] Real-time analysis of the consumables of all anesthesia surgeries is performed. The expected usage and actual amount of anesthesia consumables are analyzed in real time to calculate the real-time surplus of consumables. The specific steps are as follows:

[0068] The expected consumption of consumables for each anesthesia operation is set to The actual amount taken is , where i represents different surgeries and the types of consumables are represented by j, then the expected usage of each consumable is The actual amount taken is ;

[0069] Calculate the difference in volume of each consumable per surgery , the calculation expression is: , where represents the difference in the jth consumables for the i-th surgery, Indicates a dynamic adjustment item, which is used to make real-time corrections to the difference amount according to actual usage;

[0070] Specifically, Real-time calculations can be performed based on factors such as the actual consumption rate of consumables, unexpected situations during surgery (such as the need for additional consumables or unexpected reductions in consumable usage), etc. For example, if consumable usage is found to deviate significantly from expectations during surgery (such as a sudden increase or decrease in usage), the system will adjust based on these changes. to more accurately reflect the actual demand for consumables during surgery. The value of can be updated in real time through machine learning algorithms or rules based on historical data to ensure the accuracy and flexibility of the difference calculation.

[0071] Based on the difference in volume for each consumable , calculate the real-time margin of each operation, the calculation expression is: ,in, is the consumable importance coefficient of the jth consumable in the i-th surgery, indicating the importance weight of each consumable to the surgery. is the usage frequency of the jth consumable in the i-th surgery, and n represents the total number of consumable types;

[0072] Consumables Importance Coefficient Indicates the criticality and necessity of each consumable in the operation, that is, the weight of the consumable's impact on the success of the operation and the safety of the patient. Specifically, different anesthesia consumables play different roles in the operation. Some consumables, such as endotracheal tubes and anesthesia masks, are crucial to maintaining the patient's vital signs and the smooth progress of the operation, while others, such as monitoring electrodes and disinfection supplies, are also important, but their importance is relatively low. By assigning different weights to different consumables, it reflects the importance that needs to be given priority in consumable management and inventory updates. For example, consumables with high importance weights will be given priority in surplus calculations to ensure sufficient supply and reasonable use of these key consumables.

[0073] Calculate the real-time surplus of consumables for all anesthesia surgeries. The calculation expression is: , where It represents the real-time surplus of consumables for all anesthesia surgeries, and d represents the total number of all anesthesia surgeries in progress.

[0074] The larger the real-time surplus of consumables for all anesthesia surgeries, the greater the risk of misjudging consumable consumption by updating consumables in real time. Specifically, a larger surplus means that the actual consumables taken are far more than the expected usage, which may be due to the fact that a large number of spare consumables are reserved for surgery. If the system performs real-time inventory updates without considering this backup situation, it may erroneously trigger a replenishment request, resulting in confusion in inventory management and possible waste of resources. Therefore, when the real-time surplus is large, the system needs to handle it with caution to avoid frequent and unnecessary replenishment operations.

[0075] The consumables surplus analysis and classification module analyzes the consumables surplus and divides the ongoing anesthesia surgery into high surplus consumables inventory and normal surplus consumables inventory according to the anesthesia consumables situation;

[0076] The real-time surplus of consumables generated by real-time analysis of the consumables of all anesthesia surgeries is compared with the preset reference value of real-time surplus of consumables, and the ongoing anesthesia surgeries are divided according to the anesthesia consumables. The specific division steps are as follows:

[0077] If the real-time surplus of consumables is greater than or equal to the real-time surplus reference value of consumables, the ongoing anesthesia surgery is classified as high surplus consumables inventory;

[0078] If the real-time surplus consumables quantity is less than the real-time surplus consumables quantity reference value, the ongoing anesthesia surgery will be classified as normal surplus consumables inventory.

[0079] The surgery complexity assessment module uses a pre-trained machine learning model to conduct a comprehensive analysis of all anesthesia surgeries performed simultaneously to assess the complexity of anesthesia surgeries in scenarios with high surplus consumables inventory.

[0080] In the scenario of high surplus consumables inventory, the probability of emergency occurrence and the estimated duration of all anesthesia operations performed simultaneously are obtained. After analyzing the probability of emergency occurrence and the estimated duration of operations, an expected intraoperative emergency index and an estimated uncertainty index for operation duration are generated respectively. The expected intraoperative emergency index and the estimated uncertainty index for operation duration are input into the pre-trained machine learning model to generate a comprehensive complexity coefficient of anesthesia operations, and the complexity of anesthesia operations is evaluated by the comprehensive complexity coefficient of anesthesia operations.

[0081] A pre-trained machine learning model refers to an algorithm model that has been trained and optimized with a large amount of historical data, and can predict or calculate the target value (such as the comprehensive complexity coefficient of anesthesia surgery) based on specific input parameters (such as the expected index of intraoperative emergencies and the uncertainty index of surgery duration estimation). In this scenario, the model may use a supervised learning method to adjust the weights and parameters of the model by learning the relationship between emergencies, duration uncertainty, and actual complexity of past surgeries. After training, the model can quickly and accurately generate an assessment of the complexity of anesthesia surgery after inputting new surgical data, providing support for clinical decision-making. This model can be based on a variety of algorithms, such as neural networks, support vector machines, random forests, etc. The specific choice depends on the characteristics of the data and application requirements.

[0082] When the probability of emergencies in all anesthesia surgeries performed simultaneously is high, it usually indicates that the overall situation of these surgeries is more complicated. A higher probability of emergencies means that more unforeseen problems may occur during surgery, such as abnormal physiological reactions of patients, unexpected events during surgery, or the need to temporarily adjust the anesthesia plan. These situations increase the risk and difficulty of surgery. Therefore, surgeries with a higher probability of emergencies usually mean that the anesthesia team needs to be more cautious and flexible in dealing with complex surgical environments, reflecting the higher overall complexity of the surgery.

[0083] The specific steps for generating the intraoperative emergency expectation index after analyzing the probability of emergencies in all simultaneously performed anesthesia surgeries are as follows:

[0084] Collect relevant data of all ongoing anesthesia surgeries and set the number of historical emergencies for each surgery i to , the patient's pathological complexity parameter is , the surgery type parameters are The risk factor of anesthetic drugs is , is the number of historical emergencies in the i-th surgery, reflecting the frequency of emergencies in similar surgeries in the past. is the pathological complexity parameter of the i-th surgical patient, indicating the impact of the patient’s health status on the emergency event. is the surgical type parameter of the i-th surgery. The complexity of different types of surgeries may lead to different probabilities of emergencies. is the anesthetic risk coefficient for the i-th surgery, indicating the potential risk impact of the anesthetic used on the emergency;

[0085] Patient pathology complexity parameters It is usually determined through a comprehensive analysis of the patient's medical history, diagnostic records, and current health conditions. This data can be obtained from the hospital's electronic health record (EHR) system, covering the patient's past illnesses, complications, allergies, organ function, etc. Based on this information, the medical team can use a pre-set scoring system (such as the Charlson Comorbidity Index, etc.) to quantify the patient's pathological complexity and ultimately derive pathological complexity parameters suitable for surgery.

[0086] Surgery type parameters It is determined based on the specific nature and complexity of the surgery. The type of surgery information can be obtained from the OR Scheduling System, which records the classification of each surgery in detail, such as cardiac surgery, neurosurgery or general surgery. The medical team will set a corresponding complexity parameter for each type of surgery, which is usually evaluated by experts based on multiple dimensions such as the technical requirements of the surgery, the operation time, and risk factors.

[0087] Anesthetic drug risk factors It is determined based on the type and dose of anesthetic drugs used in the operation. Anesthesiologists will choose different anesthetic drugs according to the needs of the operation, such as general anesthesia, local anesthesia or sedatives, and this information can be obtained through the Anesthesia Information Management System (AIMS). Each drug has its own specific risk factor, which is usually provided by drug experts or clinical guidelines based on factors such as the side effects of the drug, the impact on the patient's physiology, and the interaction with other drugs. By combining these factors, a corresponding anesthetic drug risk factor can be set for each operation.

[0088] According to the collected parameters, the probability of emergency occurrence in each operation is calculated, and the calculation expression is: , where represents the probability of an emergency occurring in the i-th operation;

[0089] Among them, the number of historical emergencies The complexity of the patient's pathology Together they determine the basic risk of an emergency, and the type of surgery As the denominator, the risk weights of different surgical types were adjusted. The overall risk probability is further adjusted so that the final It can more accurately reflect the probability of surgical emergencies.

[0090] According to the probability of emergencies in all surgeries , calculate the expected index of intraoperative emergencies, and the calculation expression is: , is the surgery importance index, which reflects the contribution weight of surgery to the overall risk of emergencies. A value of 0 means that the surgery has a greater impact on the overall risk. It represents the expected index of intraoperative emergencies, reflecting the comprehensive risk of emergencies in all surgeries.

[0091] The greater the performance value of the intraoperative emergency expectation index generated by analyzing the probability of emergencies in all simultaneously performed anesthesia surgeries, the more complex the overall situation of all simultaneously performed anesthesia surgeries. A larger intraoperative emergency expectation index means a higher risk of emergencies during surgery, which may involve more unforeseen problems, the complexity of the patient's condition, higher technical requirements, and the need for flexible response of anesthesia plans. Therefore, the increase in the intraoperative emergency expectation index directly reflects the increase in the overall complexity of the surgery, requiring the anesthesia team to conduct closer monitoring and more detailed management during the operation to ensure the safety of the patient and the success of the operation.

[0092] When the estimated uncertainty of the operation time of all anesthesia surgeries performed simultaneously is large, it usually indicates that the overall situation of these surgeries is relatively complex. The uncertainty of the operation time reflects the multiple variables and unforeseen factors that may exist during the operation, such as the high difficulty of the operation, the complexity of the patient's condition, and possible emergencies during the operation. These factors will increase the unpredictability of the operation time, making anesthesia management and resource allocation more complicated. Therefore, large uncertainty in the estimated time is usually an important feature of complex surgery.

[0093] The specific steps for generating the uncertainty index of surgical duration estimation after analyzing the estimated duration of all anesthesia surgeries performed simultaneously are as follows:

[0094] Collect the estimated duration of each ongoing anesthesia surgery and set the estimated duration of each surgery as ,in, represents the estimated duration of the i-th operation;

[0095] Calculate the uncertainty factor of the duration of each operation, and the calculation expression is: , where represents the uncertainty factor of the estimated duration of the i-th operation, represents the pth influencing factor related to the duration of the i-th operation (such as the complexity of the patient's condition, the type of operation, historical data, etc.), is the weight of the pth influencing factor, indicating the contribution of each influencing factor to the duration uncertainty, is the volatility coefficient of the pth influencing factor in the i-th operation, indicating the degree of volatility of the factor, is the inherent complexity adjustment coefficient of the i-th surgery, which is used to balance the complexity differences between surgeries, and N represents the total number of influencing factors;

[0096] It should be noted that the volatility coefficient The acquisition of is usually based on the analysis of historical data and real-time monitoring data. Specifically, by retrospectively analyzing a large number of historical records of similar operations, the range and frequency of changes in each influencing factor in these operations can be calculated, thereby obtaining the volatility of the factor. For example, if the patient's blood pressure fluctuates greatly in a certain type of operation, then the influencing factors related to blood pressure will have a higher volatility coefficient. In addition, real-time monitoring data (such as real-time vital signs during surgery, drug reactions, etc.) can also be used to dynamically adjust the volatility coefficient to make it more accurately reflect the actual complexity and uncertainty of the operation. By combining historical and real-time data, the volatility coefficient can accurately capture the changes in various influencing factors during surgery.

[0097] After calculating the uncertainty factor for the duration of all surgeries, Finally, the uncertainty factor of the duration is combined to calculate the uncertainty index of the overall surgery duration estimate. The calculation expression is: , where represents the uncertainty index of the estimated operation duration, It represents the priority weight of the i-th surgery, indicating the importance of the surgery in uncertainty assessment.

[0098] The larger the performance value of the uncertainty index of surgical duration estimation generated by analyzing the estimated duration of all anesthesia surgeries performed simultaneously, the more complex the overall situation of all anesthesia surgeries performed simultaneously. A larger uncertainty index reflects that the estimation of surgical duration is more variable, which means that a variety of unpredictable factors may occur during the operation, such as fluctuations in patient status, increased surgical difficulty, and response to emergencies. These factors together increase the complexity of the operation, making anesthesia management and resource allocation more difficult. Therefore, a higher uncertainty index often means that the overall complexity of these surgeries is higher, requiring more careful management and decision-making.

[0099] The machine learning model is not specifically limited here, and can achieve the expected index of intraoperative emergencies and uncertainty index of surgery duration estimation Conduct comprehensive analysis to generate the comprehensive complexity coefficient of anesthesia surgery In order to realize the technical solution of the present invention, the present invention provides a specific implementation method;

[0100] Anesthesia surgery comprehensive complexity coefficient The resulting calculation formula is: , where , Intraoperative emergency expectancy index and uncertainty index of surgery duration estimation The preset scaling factor of , Both are greater than 0.

[0101] It can be seen from the comprehensive complexity coefficient of anesthesia surgery that the greater the performance value of the expected intraoperative emergency index generated after analyzing the probability of emergency occurrence of all simultaneously performed anesthesia surgeries, the greater the performance value of the surgery duration estimation uncertainty index generated after analyzing the estimated surgery duration of all simultaneously performed anesthesia surgeries, that is, the greater the performance value of the generated comprehensive complexity coefficient of anesthesia surgery, indicating that the comprehensive situation of all simultaneously performed anesthesia surgeries is more complex, and vice versa, indicating that the comprehensive situation of all simultaneously performed anesthesia surgeries is less complex.

[0102] The inventory update strategy adjustment module adjusts the actual inventory update strategy based on the surgical complexity assessment results, and reduces the actual inventory update frequency through the real-time inventory update frequency;

[0103] Based on the results of the surgical complexity assessment, adjust the actual inventory update strategy. The specific steps are as follows:

[0104] The comprehensive complexity coefficient of anesthesia surgery is compared with the preset reference value of the comprehensive complexity coefficient of anesthesia surgery, and the deviation of the complexity coefficient is calculated. The calculation expression is: , where represents the complexity coefficient deviation, represents the comprehensive complexity coefficient of anesthesia surgery, It represents the reference value of the comprehensive complexity coefficient of anesthesia surgery;

[0105] According to the complexity coefficient deviation The size of , calculate the real-time inventory update frequency adjustment factor, the calculation expression is: , where It represents the real-time inventory update frequency adjustment factor, which determines the adjustment range of inventory update frequency. e is the base of the natural index.

[0106] The formula uses the Sigmoid function form, so that the adjustment factor The value of varies smoothly between 0 and 1. Complexity coefficient deviation The bigger, The closer it is to 1, the more significant the inventory update frequency needs to be adjusted.

[0107] Leverage real-time inventory update frequency adjustment factors Calculate the new actual inventory update frequency. The calculation expression is: , where Indicates the actual inventory update frequency, Indicates the current real-time inventory update frequency.

[0108] The present invention can accurately identify the difference between actual consumables demand and spare consumables by collecting the expected usage and actual amount taken for each anesthesia operation and calculating the surplus of consumables in real time. By dividing the surgical consumables into high surplus consumables inventory and normal surplus consumables inventory, it can accurately identify possible inventory misjudgments, especially in the scenario of high surplus consumables inventory. The complexity of the operation is comprehensively analyzed through the pre-trained machine learning model, so that inventory management not only relies on simple consumables consumption data, but also takes into account the actual complexity of the operation, greatly reducing unnecessary replenishment needs, avoiding inventory management chaos caused by real-time updates, and improving the accuracy of inventory management and the utilization efficiency of hospital resources.

[0109] Based on the surgical complexity assessment results, the present invention can dynamically adjust the actual inventory update strategy. Especially in the scenario of high surplus consumables inventory, by lowering the real-time inventory update frequency, the system effectively reduces frequent inventory fluctuations and prevents waste of resources. At the same time, after monitoring the inventory and real-time data during the operation, it can quickly adjust according to the actual situation to ensure that the inventory update frequency matches the actual surgical complexity. This flexible adjustment mechanism enables the system to better cope with unforeseen emergencies during the operation and ensure the stability and adequacy of the consumables supply, thereby improving the hospital's overall management capabilities and emergency response speed in complex surgical environments.

[0110] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0112] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An intelligent inventory management system for anesthesia consumables, characterized in that: It includes anesthesia consumables data collection module, real-time consumables surplus calculation module, consumables surplus analysis and classification module, surgery complexity assessment module and inventory update strategy adjustment module; Anesthesia consumables data collection module collects information on anesthesia consumables for all ongoing anesthesia surgeries, including the expected usage and actual consumption of all anesthesia surgeries; The real-time consumable surplus calculation module performs real-time analysis on the consumables of all anesthesia surgeries and calculates the real-time consumable surplus based on the expected usage and actual amount of anesthesia consumables taken. The consumables surplus analysis and classification module analyzes the consumables surplus and divides the ongoing anesthesia surgery into high surplus consumables inventory and normal surplus consumables inventory according to the anesthesia consumables situation; The surgery complexity assessment module uses a pre-trained machine learning model to conduct a comprehensive analysis of all anesthesia surgeries performed simultaneously to assess the complexity of anesthesia surgeries in scenarios with high surplus consumables inventory. In the scenario of high surplus consumables inventory, obtain the probability of emergencies and the estimated duration of all anesthesia surgeries performed simultaneously. After analyzing the probability of emergencies and the estimated duration of surgery, generate the expected index of intraoperative emergencies and the uncertainty index of surgery duration estimation respectively. Input the expected index of intraoperative emergencies and the uncertainty index of surgery duration estimation into the pre-trained machine learning model to generate the comprehensive complexity coefficient of anesthesia surgery, and evaluate the complexity of anesthesia surgery through the comprehensive complexity coefficient of anesthesia surgery. The specific steps for generating the intraoperative emergency expectation index after analyzing the probability of emergencies in all simultaneously performed anesthesia surgeries are as follows: Collect relevant data of all ongoing anesthesia surgeries and set up each surgery The number of historical emergencies is , the patient's pathological complexity parameter is , the surgery type parameters are The risk factor of anesthetic drugs is , For the The number of historical emergencies in each operation, For the Pathological complexity parameters of the patients undergoing surgery, For the The surgical type parameters of each operation, For the Risk factor of anesthetic drugs for each operation; According to the collected parameters, the probability of emergency occurrence in each operation is calculated, and the calculation expression is: , where Indicates The probability of emergencies during the operation; According to the probability of emergencies in all surgeries , calculate the expected index of intraoperative emergencies, and the calculation expression is: , is the surgery importance index, which reflects the contribution weight of the surgery to the overall risk of emergencies. It represents the expected index of intraoperative emergencies; The specific steps for generating the uncertainty index of surgical duration estimation after analyzing the estimated duration of all anesthesia surgeries performed simultaneously are as follows: Collect the estimated duration of each ongoing anesthesia surgery and set the estimated duration of each surgery as ,in, Indicates The estimated duration of the surgery; Calculate the uncertainty factor of the duration of each operation, and the calculation expression is: ； In the formula, Indicates The uncertainty factor for the estimated duration of each operation is Indicates The duration of the operation is related to the Impact factors, For the The weight of each influencing factor indicates the contribution of each influencing factor to the uncertainty of duration. For the The impact factor is The coefficient of volatility in each operation, For the The inherent complexity adjustment factor of each operation is used to balance the complexity differences between operations. N represents the total number of impact factors; After calculating the uncertainty factor for the duration of all surgeries, Finally, the uncertainty factor of the duration is combined to calculate the uncertainty index of the overall surgery duration estimate. The calculation expression is: ； In the formula, represents the uncertainty index of the estimated operation duration, Indicates The surgery priority weight of the platform indicates the importance of the surgery in the uncertainty assessment; The inventory update strategy adjustment module adjusts the actual inventory update strategy based on the surgical complexity assessment results, and reduces the actual inventory update frequency through the real-time inventory update frequency; Based on the results of the surgical complexity assessment, adjust the actual inventory update strategy. The specific steps are as follows: The comprehensive complexity coefficient of anesthesia surgery is compared with the preset reference value of the comprehensive complexity coefficient of anesthesia surgery, and the deviation of the complexity coefficient is calculated. The calculation expression is: , where represents the complexity coefficient deviation, represents the comprehensive complexity coefficient of anesthesia surgery, It represents the reference value of the comprehensive complexity coefficient of anesthesia surgery; According to the complexity coefficient deviation The size of , calculate the real-time inventory update frequency adjustment factor, the calculation expression is: ； In the formula, Indicates the real-time inventory update frequency adjustment factor, which determines the adjustment range of the inventory update frequency. is the base of the natural index; Leverage real-time inventory update frequency adjustment factors Calculate the new actual inventory update frequency. The calculation expression is: , where Indicates the actual inventory update frequency, Indicates the current real-time inventory update frequency.

2. An intelligent inventory management system for anesthesia consumables according to claim 1, characterized in that: When each anesthesia operation is performed, the expected usage of all ongoing anesthesia operations, that is, the expected amount of anesthesia consumables, is collected. The specific steps are as follows: Obtain the scheduling information of all ongoing anesthesia surgeries through the hospital's surgical scheduling system; Match each surgery with a pre-set anesthesia consumables list template based on the surgery type information obtained from the scheduling system; Personalize the generated list of anesthesia consumables through anesthesiologists; After the personalized adjustment is completed, the consumables list for each operation is summarized and calculated to obtain the expected usage of each anesthesia consumable; The calculated expected usage data of anesthesia consumables are recorded in the central database and bound to the real-time data of actual surgical anesthesia consumable usage.

3. The intelligent inventory management system for anesthesia consumables according to claim 1, characterized in that: Collect actual volumes of anesthetics taken for all ongoing procedures by: Use RFID tags, barcodes or QR codes on each consumable. When anesthesiologists extract anesthesia consumables, they automatically record the type and quantity of anesthesia consumables through scanning equipment, upload the recorded data to the central inventory management system in real time, and associate it with the anesthesia surgery scheduling information to ensure that the actual amount of anesthesia consumables extracted for each anesthesia surgery is accurately recorded, thereby collecting the actual amount taken for each anesthesia surgery, and then collecting the actual amount taken for all ongoing anesthesia surgeries.

4. The intelligent inventory management system for anesthesia consumables according to claim 1, characterized in that: Real-time analysis of the consumables of all anesthesia surgeries is performed. The expected usage and actual amount of anesthesia consumables are analyzed in real time to calculate the real-time surplus of consumables. The specific steps are as follows: The expected consumption of consumables for each anesthesia operation is set to The actual amount taken is ,in Representing different surgeries, consumables types are The expected usage of each consumable is The actual amount taken is ; Calculate the difference in volume of each consumable per surgery , the calculation expression is: , where Indicates The first surgery The difference in the amount of consumables, Indicates a dynamic adjustment item, which is used to make real-time corrections to the difference amount according to actual usage; Based on the difference in volume for each consumable , calculate the real-time margin of each operation, the calculation expression is: ,in, It is The first surgery The consumable importance coefficient of each consumable indicates the importance weight of each consumable to the surgery. It is The first surgery The frequency of use of the consumables, Indicates the total number of consumable types; Calculate the real-time surplus of consumables for all anesthesia surgeries. The calculation expression is: , where Indicates the real-time surplus of consumables for all anesthesia surgeries. Represents the total number of all anesthesia surgeries in progress.

5. The intelligent inventory management system for anesthesia consumables according to claim 4, characterized in that: The real-time surplus of consumables generated by real-time analysis of the consumables of all anesthesia surgeries is compared with the preset reference value of real-time surplus of consumables, and the ongoing anesthesia surgeries are divided according to the anesthesia consumables. The specific division steps are as follows: If the real-time surplus of consumables is greater than or equal to the real-time surplus reference value of consumables, the ongoing anesthesia surgery is classified as high surplus consumables inventory; If the real-time surplus consumables quantity is less than the real-time surplus consumables quantity reference value, the ongoing anesthesia surgery will be classified as normal surplus consumables inventory.

Images