A medical device performance assessment system and method

Abstract

The application discloses a kind of medical equipment efficiency evaluation system and method, the system includes the hardware terminal of mounting type and evaluation device, and the hardware terminal of mounting type is used to obtain the log data and operating state data of equipment;Evaluation device includes data integration module and evaluation model;Data integration module receives log data, operating state data, the business data of hospital electronic information system and artificial input data, and with equipment asset coding is associated multi-source data;Evaluation model is configured to: obtain and medical equipment associated multi-source data, calculate the basic score under each evaluation dimension, cross-check multi-source data based on preset constraint rules, judge whether the corresponding evaluation dimension is abnormal;If abnormal, generate correction factor to calibrate basic score as effective score, based on the effective score of evaluation dimension, preset dimension weight is calculated to obtain equipment comprehensive efficiency score, based on equipment comprehensive efficiency score generates efficiency rating and procurement decision result.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a medical device performance evaluation system and method. Background Technology

[0002] While existing technologies for benefit analysis and operational monitoring of medical equipment have achieved the collection and basic analysis of some data, they still suffer from numerous technical shortcomings and application pain points, failing to meet the needs of refined management across the entire lifecycle and multiple dimensions of medical equipment. Specifically, existing technologies mainly have the following deficiencies: The evaluation dimensions are relatively singular: Existing technologies mostly focus on the single-dimensional analysis of equipment economic benefits or operating status, lacking comprehensive consideration of multiple dimensions, resulting in incomplete evaluation results that cannot provide a comprehensive basis for decisions such as equipment procurement and discipline development.

[0003] Data acquisition suffers from silos and insufficient accuracy and comprehensiveness: Existing equipment relies heavily on operational data from hospital HIS (Hospital Information System) / PACS (Picture Archiving and Communication System) systems or single sensor operational data, failing to achieve integrated acquisition of underlying hardware data and hospital operational data; furthermore, there is a lack of universal acquisition terminals adapted to large, medium, small, and mobile medical devices. Some devices (such as portable ultrasound and monitors) struggle to achieve real-time data acquisition, resulting in poor data integrity and traceability.

[0004] The quantification and weighting of indicators lack scientific rigor: existing equipment evaluation indicators are mostly qualitative descriptions or simple quantitative calculations, and a standardized indicator quantification system has not been established.

[0005] Visualization is disconnected from actual decision-making: Existing visualization technologies mostly consist of single reports or basic charts, failing to effectively establish a seamless process connecting "data-information-decision-execution".

[0006] Therefore, there is an urgent need to build a hardware and software integrated (i.e., "hardware acquisition + software evaluation") medical equipment performance evaluation system that can achieve accurate and universal acquisition of all-source data of the equipment, establish a scientific multi-dimensional quantitative evaluation model, and provide a comprehensive, accurate and operable basis for medical equipment management and procurement decisions through visualization.

[0007] The statements herein provide only background information in relation to this invention and do not necessarily constitute prior art. Summary of the Invention

[0008] The purpose of this invention is to provide a medical equipment performance evaluation system and method that overcomes the technical shortcomings of existing medical equipment performance evaluation methods, such as single-dimensionality evaluation, fragmented data collection, insufficient scientific rigor, distorted evaluation results, and disconnect between data governance and decision-making. The system provides closed-loop management throughout the entire process, from data collection and quantitative evaluation to deviation calibration and decision output, significantly improving the objectivity, accuracy, and comprehensiveness of medical equipment performance evaluation. This provides a scientific and reliable quantitative basis for medical equipment operation and maintenance management, upgrade procurement, and discipline development.

[0009] To achieve the above objectives, the present invention provides a medical device performance evaluation system, comprising: a mounted hardware terminal and an evaluation device; The mounted hardware terminal includes a log acquisition sensor, a non-contact current sensing sensor, and an RFID tag; the log acquisition sensor is used to collect log data of the medical device, the non-contact current sensing sensor is used to collect operating status data of the medical device, and the RFID tag stores an asset code that uniquely identifies the medical device. The evaluation device includes: a data integration module and an evaluation model; The data integration module is configured to receive multi-source data, including log data, operational status data, business data from the hospital's electronic information system, and manually entered data. The evaluation model includes: a basic score calculation unit, a correction factor calibration unit, and a scoring and rating and procurement decision unit; The basic score calculation unit is configured to: establish a mapping relationship between the multi-source data using the asset code as an index; Based on the aforementioned association mapping, the multi-source data associated with the medical device is obtained, and a basic score for the medical device under the corresponding evaluation dimension is calculated. The correction factor calibration unit is configured to: perform reliability cross-validation on the multi-source data associated with the medical device based on preset constraint rules, generate a correction factor for the corresponding basic score based on the validation result, and correct the basic score based on the correction factor to obtain the corresponding effective score. The scoring and procurement decision unit is configured to: calculate and generate a comprehensive performance score for medical equipment based on the effective scores of each evaluation dimension and the preset dimension weights, and generate a comprehensive performance rating and procurement decision based on the comprehensive performance score.

[0010] Optionally, each evaluation dimension includes multiple indicators; the basic score calculation unit is configured as follows: Data associated with the indicator is selected from the multi-source data received by the data integration module to generate the original value of the indicator; The original values ​​of the indicators are standardized based on the indicator type to generate standardized values ​​for the indicators. Calculate the final weight within the dimension for each indicator under the evaluation dimension; Based on the evaluation dimension, the standardized values ​​of each indicator and the final weights within the dimension are used to calculate the basic score of the evaluation dimension.

[0011] Optionally, the hospital electronic information system includes at least one of the following: HIS system, PACS system, RIS system, financial system, and equipment management system; The multiple evaluation dimensions include economic benefits, equipment operation, clinical diagnosis and treatment, discipline development, and comprehensive value. The preset constraint rules include: economic benefit dimension constraint rules, equipment operation dimension constraint rules, clinical diagnosis and treatment dimension constraint rules, discipline development dimension constraint rules, and comprehensive value dimension constraint rules; The economic benefit dimension constraint rules include: ;and ; , , , These are the total revenue from equipment-based medical services, the compliant fee per equipment session, the number of valid medical services provided by the equipment, and revenue from consumables, respectively, within the business data. This is a preset percentage threshold; The device operation dimension constraint rules include: ;in, , , These are the total device power-on time in the operating status data, the power-on time in the log data, and the effective working time of the device in the operating status data, respectively. The constraints on the clinical diagnosis and treatment dimensions include: ,and ; , These are the longest average treatment time per case and the longest total effective treatment time in the business data. This represents the industry's lowest time consumption for examination items corresponding to a single case of diagnosis and treatment; This refers to the effective operating time of the device in the log data; The constraints on the discipline development dimension include: The number of key disease cases diagnosed clinically is greater than the number of key cases treated using equipment. The comprehensive value dimension constraint rules include: The equipment reliability score, Equipment failure rate This is a score for the linkage between reagents and consumables. The percentage of reagent and consumable costs in total equipment revenue; This characterizes the degree of dependence on equipment consumables and the difficulty in controlling consumable costs; , Scoring is done by experts, while data is entered manually. .

[0012] Optionally, if the economic benefit dimension constraint rules are not met, the correction factor calibration unit is configured to generate an anomaly score D1 under the economic benefit dimension based on the deviation between the total equipment revenue and the revenue due calculated based on the number of outpatient visits, and the deviation between the proportion of consumable revenue in the total equipment revenue and the preset proportion threshold. If the device operation dimension constraint rules are not met, the correction factor calibration unit is configured to, based on , Calculate the anomaly score D2 under the equipment operation dimension; If the clinical diagnosis and treatment dimension constraint rules are not met, the correction factor calibration unit is configured to, based on , Calculate the abnormality score D3 under the clinical diagnosis and treatment dimension; If the constraint rules of the discipline development dimension are not met, the correction factor calibration unit is configured to set the abnormality score D4 under the discipline development dimension to a predetermined score. If the comprehensive value dimension constraint rules are not met, the correction factor calibration unit is configured to, based on , Calculate the anomaly score D5 under the comprehensive value dimension; The correction factors under the dimensions of economic benefits, equipment operation, clinical diagnosis and treatment, discipline development, and comprehensive value are denoted as K1, K2, K3, K4, and K5, respectively.

[0013] m is a positive integer. A and B are correction parameters. .

[0014] Optionally, the medical device performance evaluation system further includes: the evaluation device further includes a storage module and a visualization module; The storage module is primarily used to store the multi-source data; The visualization module is used to display the multi-source data in a visualization interface, including at least one of the following under each evaluation dimension: base score, correction factor, effective score, comprehensive performance score, comprehensive performance rating, and procurement decision.

[0015] This invention also provides a method for evaluating the effectiveness of medical devices, implemented using the medical device effectiveness evaluation system described in this invention, comprising the following steps: S1. Acquire multi-source data, including medical equipment log data and operating status data collected by the onboard hardware terminal, business data of the hospital's electronic information system, and manually entered data; S2. Using the asset code of the medical equipment as an index, establish a correlation mapping between multi-source data; based on the correlation mapping, obtain the multi-source data associated with the medical equipment, and calculate multiple basic scores for the medical equipment under multiple evaluation dimensions respectively; S3. Based on preset constraint rules, perform reliability cross-validation on the multi-source data associated with medical devices to determine whether there are any abnormalities in each evaluation dimension; if there are abnormalities, generate a correction factor for the corresponding basic score, and correct the basic score based on the correction factor to obtain the corresponding effective score. S4. Based on the effective scores of each evaluation dimension and the preset dimension weights, generate a comprehensive performance score for the medical equipment, and generate a comprehensive performance rating and procurement decision based on the comprehensive performance score.

[0016] Optionally, each evaluation dimension includes multiple indicators; in step S2, the basic score for each evaluation dimension for the medical device is calculated, including: S21. From the multi-source data associated with the medical device, select the data associated with the indicator, and calculate and generate the original value of the indicator according to the preset calculation formula. S22. Based on the indicator type, perform a standardization operation on the original value of the indicator to generate a standardized value of the indicator; The indicators include positive and negative indicators; the original values ​​of the positive and negative indicators are positively and negatively correlated with the effectiveness of medical equipment, respectively. Let the original value of the j-th indicator in the m-th evaluation dimension be denoted as The minimum and maximum original values ​​of the corresponding indicators for the same type of medical equipment are respectively denoted as: , ; If the j-th indicator of the m-th evaluation dimension is a positive indicator. ; If the j-th indicator of the m-th evaluation dimension is a negative indicator. ; S23. The multiple evaluation dimensions include the Mth evaluation dimension of the first evaluation dimension; calculate the final weight within the dimension for each indicator under the mth evaluation dimension, and calculate the basic score of the mth evaluation dimension based on the standardized value of the indicator and the final weight within the dimension. ; ; n m This represents the total number of indicators corresponding to the m-th evaluation dimension. ; This represents the standardized value of the j-th indicator in the m-th evaluation dimension, and the final weight within the dimension.

[0017] Optional, let This represents the correction factor for the m-th evaluation dimension. This represents the effective score of the m-th evaluation dimension. ; make , Represent the overall performance score and the preset dimension weights for the m-th evaluation dimension, respectively. .

[0018] Optionally, in step S23, calculating the final weights within each indicator of the m-th evaluation dimension includes the following steps: S231. Calculate the coefficient of variation of the j-th indicator in the m-th evaluation dimension. ,in ; , They represent the m-th evaluation dimension and the th evaluation dimension, respectively. Standard deviation and mean of each indicator; S232. Perform Pearson correlation analysis on the standardized values ​​of all indicators in the m-th evaluation dimension to establish a correlation coefficient matrix. ; For the m-th evaluation dimension, the first... The first indicator, the first The correlation coefficient of each indicator ; This represents the number of all indicators under the m-th dimension; S233. Calculate the conflict coefficient of the j-th indicator in the m-th evaluation dimension. , ; S234. Calculate the information content of the j-th indicator in the m-th evaluation dimension. , ; S235. Calculate the base weight of the j-th indicator of the m-th evaluation dimension ,

[0019] Optionally, in step S23, calculating the intra-dimension final weight for each indicator under the m-th evaluation dimension includes the following steps: S236. Construct a judgment matrix , where is used to characterize the importance degree of the -th indicator relative to the -th indicator under the m-th evaluation dimension, and is marked manually;

[0020] S237. Calculate the product of each row of the judgment matrix: ; Calculate the -th root of : ; Perform normalization processing on to obtain a feature vector , that is, the initial industry weight value; Calculate the maximum eigenvalue ; S238. Calculate the consistency index ; Calculate the consistency ratio , is the average random consistency index obtained by looking up a table according to ; If CR < a, the judgment matrix meets the consistency requirement, and the industry weight of the -th indicator under the m-th evaluation dimension is equal to the j-th element in the feature vector ; ; If CR ≥ a, adjust the judgment matrix and repeat steps S236 to S238; S239. The intra-dimension final weight of the j-th indicator of the m-th evaluation dimension is obtained by the following formula: ; and are respectively preset weight coefficients.

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows: 1) The sources of evaluation data are diversified, and precise traceability can be realized, which ensures the completeness and authenticity of evaluation information from the data source.

[0022] This invention employs a framework of "multi-dimensional evaluation + correction factor calibration," ensuring comprehensive evaluation dimensions and objective, reliable results. Based on preset constraint rules, cross-validation of multi-source data effectively identifies anomalous data under each evaluation dimension. Correction factors are used to adjust the baseline scores of each evaluation dimension, preventing inflated or distorted evaluation results and thus accurately reflecting the overall equipment performance. This provides a reliable basis for equipment operation and maintenance and procurement decisions.

[0023] This application forms a complete closed loop of data collection, governance, evaluation, calibration, visualization and decision output, which solves the problem of the disconnect between traditional data and decision-making, and enables refined and standardized management of medical equipment throughout its entire life cycle.

[0024] 2) This invention employs a hardware-mountable terminal for data collection from medical devices, overcoming limitations imposed by the size and portability of the equipment. This solves the problems of difficult data collection and potential data omissions associated with some medical devices. Data collected via the hardware-mountable terminal can be provided to the evaluation system in real time, ensuring the timeliness and effectiveness of the evaluation results. Operational status data can serve as a hard anchor point to calibrate the authenticity of data from other data sources, significantly improving the issues of easily tampered medical device logs and distorted data sources.

[0025] 3) This invention solves the problem of different indicators having different dimensions, making direct weighted calculation impossible, by standardizing the original values ​​of the indicators. This invention uses the CRITIC objective weighting method to calculate the basic weights of the indicators (objective weighting), combines it with the AHP method to calculate the industry weights of the indicators (subjective correction), and uses the Delphi method to calibrate the proportion of basic and industry weights in conjunction with the application scenario to obtain the final weights within the dimension of the indicator (used to calculate the basic score of the corresponding evaluation dimension). This invention overcomes the shortcomings of traditional methods that use single weighting of indicators, leading to excessive subjectivity and fixed weights. It is adaptable to different scenarios such as equipment addition, updates, and discipline construction, making it more adaptable and practical. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of a medical device performance evaluation system in an embodiment of the present invention.

[0027] Figure 2 This is a flowchart of a medical device performance evaluation method in an embodiment of the present invention. Detailed Implementation

[0028] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. The advantages and features of the present invention will become clearer from the following description. It should be noted that the drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clearly illustrate the embodiments of the present invention. Please refer to the drawings to make the objectives, features, and advantages of the present invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the implementation conditions of the present invention. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in proportions, or adjustments to the size, without affecting the effects and objectives achieved by the present invention, should still fall within the scope of the technical content disclosed in the present invention.

[0029] Figure 1 This is a schematic diagram of the medical equipment performance evaluation system in an embodiment of the present invention. The system is used to evaluate the comprehensive performance of equipment across multiple evaluation dimensions, each of which includes multiple indicators. In this embodiment, the multiple evaluation dimensions include economic benefit, equipment operation, clinical diagnosis and treatment, discipline development, and comprehensive value. Specific dimensions can be set according to actual needs and are not limited in this invention.

[0030] like Figure 1 As shown, the medical device performance evaluation system includes: a mounted hardware terminal 1 and an evaluation device 2. The mounted hardware terminal 1 includes a log acquisition sensor 11, a non-contact current sensing sensor 12, and a radio frequency identification tag 13.

[0031] In this embodiment, the log acquisition sensor 11 is a high-precision data parsing sensor. It interfaces with the medical device host to directly decode the device's log data, including engineering logs, clinical process data, and clinical outcome data. The acquisition frequency is in real-time / second.

[0032] The non-contact current sensing sensor 12 is used to collect operational status data of the medical device. In this embodiment, the current sensing sensor utilizes the principle of electromagnetic induction, is attached to the device's power supply line, and monitors the current intensity and waveform changes flowing through the power line to collect operational status and availability data. The collection frequency is on the order of minutes. In this embodiment, log data and operational status data are also collectively referred to as hardware data. In this embodiment, the specific collection items of the current sensor and log acquisition sensor 11, and the evaluation indicators supported by each collection item, are shown in Table 1.

[0033] Table 1

[0034] like Figure 1 As shown, the mounted hardware terminal 1 also includes a data transmission module 14, which supports both wireless and wired transmission modes. The wireless transmission mode (WiFi / 5G) is used for daily real-time data transmission. The wired transmission mode is used for high-speed transmission of massive log data from large devices.

[0035] like Figure 1 As shown, the mounted hardware terminal 1 also includes a power supply module 15. Large medical devices can power the mounted hardware terminal 1 through their own power supply interface, while small and medium-sized mobile devices can be powered by the built-in lithium battery of the mounted hardware terminal 1, ensuring that the data acquisition process is not interrupted.

[0036] The RFID tag 13 stores an asset code that uniquely identifies the medical device. Each RFID tag 13 is individually bound to the mounted hardware terminal 1. The data collected by the mounted hardware terminal 1 is associated with the code on the RFID tag, ensuring a one-to-one correspondence between the device, terminal, and data, thus preventing data confusion.

[0037] In this embodiment, the mounted hardware terminal 1 achieves physical connection with the medical device through an adaptable interface (such as USB, Type-C, or a dedicated connector). The mounted hardware terminal 1 solves the problem of data silos between devices, providing accurate and real-time raw data for evaluating the performance of medical devices. Furthermore, it adapts to the installation requirements of medical devices (large, medium, and small), and is not limited by the size or portability of the device.

[0038] like Figure 1 As shown, the evaluation device 2 includes a data integration module 21 and an evaluation model 22.

[0039] The data integration module 21 is configured to receive multi-source data, including log data, operation status data, business data from the hospital's electronic information system, and manually entered data.

[0040] In this embodiment, the data integration module 21 establishes a long connection with the mountable hardware terminal 1 via the TCP / IP protocol, receives data uploaded by the terminal in real time, and uses a message queue (such as RabbitMQ) to cache peak data to ensure no data loss or delay, with an access latency of ≤1 second.

[0041] In this embodiment, the data integration module 21 periodically retrieves business data from the hospital's electronic information system via a standardized API interface or database view mode. The interface frequency is configurable (synchronization once per hour by default, and core business data synchronized once every 30 minutes). The hospital's electronic information system includes: HIS (Hospital Information System), PACS (Picture Archiving and Communication System), RIS (Radiology Information System), HRP (Hospital Resource Planning), financial system, and equipment management system.

[0042] The HIS system acquires data on patient visits, billing details, number of emergency cases, and core fields of electronic medical records (such as disease diagnosis) to provide indicators for clinical diagnosis and treatment, including the proportion of core disease treatments, participation rate of difficult cases, emergency treatment support rate, average daily patient visits, improvement rate of treatment capabilities, and number of new technology implementations. It also provides patient visit data for the average duration of a single treatment and revenue per patient visit.

[0043] Data on the number of examinations, images, and scan sequence details for core diseases were obtained through PACS and RIS systems. The proportion of core disease treatments was used for clinical diagnosis and treatment, and cross-validated with HIS data.

[0044] By acquiring equipment procurement costs, maintenance expenses, revenue data, and depreciation information through HRP and financial systems, we can use data on unit time depreciation cost, monthly maintenance cost rate, revenue per patient visit, and return on investment (ROI) in terms of economic benefits, as well as energy efficiency ratio in terms of equipment operation.

[0045] Equipment calibration records (number of successful calibrations and total number of calibrations) are obtained through the equipment management system and used to measure the calibration compliance rate in terms of equipment operation.

[0046] The data integration module 21 also includes a manual data entry interface 211, which provides standardized web forms, retains only data items that cannot be automatically retrieved, and supports batch import and single entry. The manually entered data through the manual data entry interface 211 specifically includes: basic equipment records, a list of key diseases, and a list of difficult and complex diseases.

[0047] In the HIS system, the number of clinically diagnosed key disease cases can be obtained from the list of key diseases, and the number of difficult cases can be obtained from the list of difficult diseases.

[0048] The list of key diseases and the number of clinically diagnosed cases of key diseases can be used to assess the dimension of discipline development. The list of difficult and complex diseases and the number of difficult and complex cases can be used to assess the dimension of clinical diagnosis and treatment.

[0049] The basic equipment file includes the equipment purchase cost, design service life, and commissioning date (used for depreciation cost per unit time; if the financial system cannot provide this information, it will be manually supplemented).

[0050] The manual input interface 211 is also used to supplement calibration data: if the system cannot be connected, the number of qualified calibrations and the total number of calibrations can be entered manually.

[0051] In a preferred embodiment, the data integration module 21 also performs data cleaning: automatically removing null values, outliers, and duplicate data, and using methods such as "mean filling" and "trend completion" to repair missing data, ensuring data integrity ≥98%.

[0052] The evaluation model 22 includes: a basic score calculation unit 221, a correction factor calibration unit 222, and a scoring and rating and procurement decision unit 223.

[0053] The basic score calculation unit 221 is configured to: establish an association mapping between the multi-source data using the asset code as an index; and obtain the multi-source data associated with the medical device based on the association mapping.

[0054] In this embodiment, the association mapping is a four-dimensional standardized mapping relationship of "equipment asset code - medical insurance charging code - ICD diagnosis and treatment code - department affiliation". The unique asset code of the radio frequency identification tag 13 is used as the core association key to realize the accurate binding of hardware collection data, system business data and manually entered data, ensuring that each piece of data can be traced back to the specific equipment, department and business scenario.

[0055] The basic score calculation unit 221 is configured to select data associated with the indicators from the multi-source data received by the data integration module 21 to generate the original values ​​of the indicators (see Table 2 for details). Table 2 shows the indicators under the five evaluation dimensions of this invention, the calculation formulas for the original values ​​of the indicators, the indicator types, and the sources of data used to calculate the original values ​​of the indicators. Table 2 shows the primary and secondary indicators. Unless otherwise specified, the indicators in this invention are the secondary indicators in Table 2.

[0056] Table 2

[0057] The calculation and statistical period for all indicators can be customized. The default period is divided into daily / monthly / quarterly / yearly. In special scenarios (such as centralized procurement demonstration), it can be set to the entire life cycle of the equipment / preset service life (such as 5 years / 10 years).

[0058] The basic score calculation unit 221 is further configured to: perform standardized calculations on the original values ​​of the indicators based on the indicator type to generate standardized values ​​for the indicators. Since the indicator dimensions for each evaluation dimension are different (e.g., yuan, hour, times, percentage), direct weighted calculations are not possible. Therefore, a standardized formula is used to convert all original indicator values ​​into standardized values ​​between 0 and 1, which is simple to calculate and highly verifiable.

[0059] The indicators include positive and negative indicators. The raw values ​​of positive indicators are positively correlated with the effectiveness of medical equipment, such as the number of visits and the equipment's uptime. The raw values ​​of negative indicators are negatively correlated with the effectiveness of medical equipment, such as the failure rate, energy consumption per unit of treatment, and maintenance costs. The calculation of standardized values ​​for these indicators is detailed later.

[0060] The basic score calculation unit 221 is further configured to: calculate the final weight within the dimension for each indicator under the evaluation dimension (details below); and calculate the basic score of the evaluation dimension based on the standardized value of each indicator and the final weight within the dimension under the evaluation dimension (details below).

[0061] The correction factor calibration unit 222 is configured to: perform reliability cross-validation on the multi-source data associated with the medical device based on preset constraint rules, generate a correction factor for the corresponding basic score based on the validation result, and correct the basic score based on the correction factor to obtain the corresponding effective score.

[0062] The preset constraint rules include: economic benefit dimension constraint rules, equipment operation dimension constraint rules, clinical diagnosis and treatment dimension constraint rules, discipline development dimension constraint rules, and comprehensive value dimension constraint rules.

[0063] The economic benefit dimension constraint rules include: ;and .

[0064] in, , , , These are the total revenue from equipment-based medical services, the compliant fee per equipment session, the number of valid medical services provided by the equipment, and revenue from consumables, respectively, within the business data. This is a preset percentage threshold.

[0065] The economic benefit dimension constraint rules can identify abnormal scenarios such as logical mismatches between revenue and patient visits. If the economic benefit dimension constraint rules are not met, the correction factor calibration unit 222 is configured to generate an anomaly score D1 under the economic benefit dimension based on the deviation between the total equipment revenue and the revenue due calculated based on patient visits, and the deviation between the proportion of consumable revenue in the total equipment revenue and the preset proportion threshold. For example, let... .in , These are preset weight parameters. .

[0066] The device operation dimension constraint rules include: .

[0067] in, , , These are the total device startup time in the operation status data, the startup time in the log data, and the effective working time of the device in the operation status data, respectively.

[0068] The device operation dimension constraint rules are used to identify abnormal scenarios such as log tampering, false power-on duration reporting, and fake fault shutdowns. If the device operation dimension constraint rules are not met, the correction factor calibration unit 222 is configured to, based on , Calculate the anomaly score D2 under the device operation dimension. For example, .in , These are preset weight parameters. .

[0069] The constraints on the clinical diagnosis and treatment dimensions include: ,and .

[0070] in, , These are the longest average treatment time per case and the longest total effective treatment time in the business data. This represents the industry's lowest time consumption for examination items corresponding to a single case of diagnosis and treatment; This refers to the effective operating time of the device in the log data.

[0071] Clinical diagnosis and treatment dimension constraint rules are used to identify abnormal scenarios with falsely high diagnosis and treatment volumes. If the clinical diagnosis and treatment dimension constraint rules are not met, the correction factor calibration unit 222 is configured to, based on , Calculate the abnormality score D3 under the clinical diagnosis and treatment dimension. For example, .in , For preset weight parameters, .

[0072] The constraints on the discipline development dimension include: The number of key disease cases diagnosed clinically is greater than the number of key cases treated using equipment.

[0073] The discipline development dimension constraint rule is used to identify whether the equipment truly supports the diagnosis and treatment of key diseases. If the discipline development dimension constraint rule is not met, the correction factor calibration unit 222 is configured to set the anomaly score D4 to a predetermined score, for example, D4=20.

[0074] The comprehensive value dimension constraint rules include: ; ; The equipment reliability score, Equipment failure rate This is a score for the linkage between reagents and consumables. The percentage of reagent and consumable costs in total equipment revenue; This characterizes the degree of dependence on equipment consumables and the difficulty in controlling consumable costs; , Scoring is done by experts, while data is entered manually. .

[0075] The comprehensive value dimension constraint rule is used to identify abnormal scenarios such as distorted expert scoring in manually entered data. If the comprehensive value dimension constraint rule is not met, the correction factor calibration unit 222 is configured to, based on... , Calculate the anomaly score D5 under the comprehensive value dimension. For example, the equipment reliability score given by experts. =80, but ,but ;like , , =5. Therefore, the anomaly score for the comprehensive value dimension is 25.

[0076] Anomaly score (0≤) ≤100 points The higher the value, the higher the risk of false efficiency and the more serious the data anomalies in the corresponding evaluation dimension.

[0077] The correction factors under the dimensions of economic benefits, equipment operation, clinical diagnosis and treatment, discipline development, and comprehensive value are denoted as K1, K2, K3, K4, and K5, respectively.

[0078] m is a positive integer. A and B are correction parameters. .

[0079] How to adjust the base score based on the adjustment factor will be explained in detail later.

[0080] The scoring and procurement decision unit 223 is configured to: calculate and generate a comprehensive performance score for the medical equipment based on the effective scores of each evaluation dimension and the preset dimension weights, and generate a comprehensive performance rating and procurement decision based on the comprehensive performance score.

[0081] In this embodiment, based on the comprehensive performance score The equipment performance is divided into 5 levels to provide a clear level reference for procurement decisions. The rating criteria and procurement decision table are shown in Table 3. Table 3

[0082] like Figure 1 As shown, the evaluation device 2 also includes a storage module 23 and a visualization module 24.

[0083] The storage module 23 is primarily used to store the multi-source data. Storage module 23 employs a hybrid storage architecture of "relational database + time-series database"—MySQL stores structured data (such as equipment files, manually entered data, and standardized indicator data), while InfluxDB stores frequently collected time-series data (such as real-time energy consumption and operating status); it supports scheduled backups. In a preferred embodiment, storage module 23 is also used to store at least one of the following for each evaluation dimension: base score, correction factor, effective score, comprehensive performance score, comprehensive performance rating, and procurement decision.

[0084] The visualization module 24 is used to display the multi-source data in the visualization interface, including at least one of the following: basic score, correction factor, effective score, comprehensive performance score, comprehensive performance rating, and procurement decision under each evaluation dimension.

[0085] In this embodiment, the visualization module 24 is implemented based on a B / S architecture, achieving the technical goals of "data visualization - actionable decisions - traceable operations". Through a unified interface framework and logical functional layout, it transforms the calculation results of the evaluation model 22 into standardized and interactive decision information. It breaks through the traditional single report display mode and constructs a three-level visualization system of "global monitoring - precise traceability - scenario-based decision-making".

[0086] This invention also provides a method for evaluating the effectiveness of medical devices, implemented using the medical device effectiveness evaluation system as described in this invention, such as... Figure 2 As shown, the steps include: S1. Acquire multi-source data, including medical equipment log data and operating status data collected by the onboard hardware terminal, business data from the hospital's electronic information system, and manually entered data.

[0087] S2. Using the asset code of the medical equipment as an index, establish a correlation mapping between multi-source data; based on the correlation mapping, obtain the multi-source data associated with the medical equipment, and calculate multiple basic scores for the medical equipment under multiple evaluation dimensions.

[0088] In step S2, the basic scores for each evaluation dimension of the medical device are calculated, including: S21. From the multi-source data associated with the medical device, select the data associated with the indicator, and calculate and generate the original value of the indicator according to the preset calculation formula. S22. Based on the indicator type, perform a standardization operation on the original value of the indicator to generate a standardized value of the indicator; Let the original value of the j-th indicator in the m-th evaluation dimension be denoted as The minimum and maximum original values ​​of the corresponding indicators for the same type of medical equipment are respectively denoted as: , ; If the j-th indicator of the m-th evaluation dimension is a positive indicator. ; If the j-th indicator of the m-th evaluation dimension is a negative indicator. ; S23. The multiple evaluation dimensions include the Mth evaluation dimension of the first evaluation dimension; calculate the final weight within the dimension for each indicator under the mth evaluation dimension, and calculate the basic score of the mth evaluation dimension based on the standardized value of the indicator and the final weight within the dimension. ; ; n m This represents the total number of indicators corresponding to the m-th evaluation dimension. ; This represents the standardized value of the j-th indicator in the m-th evaluation dimension, and the final weight within the dimension.

[0089] In step S23, the final weights within the dimension are calculated for each indicator under the m-th evaluation dimension. Including the following steps: S231. Calculate the coefficient of variation of the j-th indicator in the m-th evaluation dimension. ,in ; , They represent the m-th evaluation dimension and the th evaluation dimension, respectively. Standard deviation and mean of each indicator; S232. Perform Pearson correlation analysis on the standardized values ​​of all indicators in the m-th evaluation dimension to establish a correlation coefficient matrix. ; For the m-th evaluation dimension, the first... The first indicator, the first The correlation coefficient of each indicator ; This represents the number of all indicators under the m-th dimension; S233. Calculate the conflict coefficient of the j-th indicator in the m-th evaluation dimension. , ; S234. Calculate the information content of the j-th indicator in the m-th evaluation dimension. , ; S235. Calculate the basic weight of the j-th indicator in the m-th evaluation dimension. ,

[0090] The constraints are satisfied: .

[0091] Step S23 involves calculating the final weights within each indicator of the m-th evaluation dimension, including the following steps: S236. Construct the judgment matrix ,in Used to characterize the m-th evaluation dimension. The first indicator is relative to the first The importance of each indicator is assigned manually, with higher values ​​indicating greater importance. .

[0092] S237. Calculate the product of each row of the judgment matrix: ; calculate of The right root: ; right Normalization is performed to obtain the feature vector. That is, the initial value of the industry weight; Calculate the largest eigenvalue .

[0093] S238. Calculate the consistency index ; Calculate the consistency ratio , is the average random consistency index obtained by looking up a table according to ; If CR<a, the judgment matrix meets the consistency requirement, and the industry weight of the j-th indicator under the m-th evaluation dimension is equal to the j-th element in the eigenvector ; ; where satisfies the constraint condition: .

[0094] If CR≥a, adjust the judgment matrix , and repeat steps S236 to S238.

[0095] S239. The final weight within the dimension of the j-th indicator in the m-th evaluation dimension is obtained by the following formula: ; and are respectively preset weight coefficients. In this embodiment, and are adjusted by the hospital expert team (clinical / scientific research) and the administrative department (procurement / equipment / hospital office) using the Delphi method according to the procurement scenario (volume-based procurement / discipline construction / routine renewal).

[0096] , , and satisfy the constraint condition: ; .

[0097] S3. Based on preset constraint rules, perform reliability cross-verification on the multi-source data associated with the medical equipment to determine whether each evaluation dimension is abnormal; if there is an abnormality, generate a correction factor for the corresponding base score, and correct the base score based on the correction factor to obtain the corresponding effective score.

[0098] Let represent the correction factor of the m-th evaluation dimension, represent the effective score of the m-th evaluation dimension, ; ​S4. Based on the effective scores of each evaluation dimension and the preset dimension weights, generate a comprehensive performance score for the medical equipment, and generate a comprehensive performance rating and procurement decision based on the comprehensive performance score.

[0099] make , Represent the overall performance score and the preset dimension weights for the m-th evaluation dimension, respectively. .

[0100] Example 1: Calculation of Comprehensive Performance Score for a 1.5T MR Equipment Table 4. Examples of basic parameters for Example 1:

[0101] (1) Calculation of the basic assessment layer First evaluation dimension: Economic benefits (preset dimension weight 0.25) Table 5. Intermediate parameters for calculating the baseline score of the first assessment dimension

[0102] The sum of weighted contribution values ​​= 0.03125 + 0.07975 + 0.06725 + 0.09850 + 0.12500 + 0.11113 + 0.09713 + 0.11150 = 0.72151 The base score for the economic efficiency dimension is 0.72151 × 100 = 72.15 points. Second evaluation dimension: Equipment operation dimension (preset dimension weight 0.25) Table 6. Intermediate parameters for calculating the baseline score of the second assessment dimension

[0103] The sum of weighted contribution values ​​= 0.1586 + 0.1070 + 0.2000 + 0.1500 + 0.1666 = 0.7822 The base score for the equipment operation dimension is 0.7822 × 100 = 78.22 points. Third assessment dimension: Clinical diagnosis and treatment dimension (preset dimension weight 0.25) Table 7. Intermediate parameters for calculating the baseline score of the third assessment dimension

[0104] The sum of weighted contribution values ​​= 0.1042 + 0.1084 + 0.1000 + 0.0715 + 0.1200 + 0.1334 = 0.6375 The baseline score for the clinical diagnosis and treatment dimension is 0.6375 × 100 = 63.75 points. Fourth evaluation dimension: Discipline development dimension (preset dimension weight 0.15) Table 8. Intermediate parameters for calculating the baseline score of the fourth assessment dimension

[0105] The sum of weighted contribution values ​​= 0.2915 + 0.2500 = 0.5415 The basic score for the subject development dimension = 0.5415 × 100 = 54.15 points Fifth evaluation dimension: Comprehensive value dimension (preset dimension weight 0.1) Table 9. Intermediate parameters for calculating the baseline score of the fifth assessment dimension

[0106] Sum of weighted contributions across all value dimensions: 0.0833 + 0.0911 + 0.0867 + 0.0944 + 0.0800 + 0.0778 + 0.0889 + 0.0844 + 0.0889 = 0.7755 The base score for the overall value dimension is 0.7755 × 100 = 77.55 points. (2) Calculation of correction factor ① Dimensional anomaly score (D) m )set up Table 10 Abnormality Scores for Each Assessment Dimension

[0107] ② Correction factor (K) m )calculate Table 11 Correction Factors for Each Evaluation Dimension

[0108] In Table 11, the correction parameters are A=1.2 and B=0.4. ③ Calculation of scores after dimensional calibration Table 12 Effective Scores for Each Assessment Dimension

[0109] (3) Final comprehensive performance score and performance evaluation 80.81×0.25+93.86×0.25+68.85×0.25+64.98×0.15+89.96×0.10=79.623, corresponding to Grade B (good performance).

[0110] Recommendation: This equipment meets the hospital's routine diagnostic and treatment needs and its efficiency is up to standard; therefore, it can be included in the procurement shortlist.

[0111] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0112] In the description of this invention, it should be understood that the terms "center," "height," "thickness," "upper," "lower," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," and "circumferential," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0113] In the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0114] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can include direct contact between the first and second features, or contact between the first and second features through another feature between them. Furthermore, "above," "over," and "on top" of the second feature includes the first feature directly above or diagonally above the second feature, or simply indicates that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature includes the first feature directly below or diagonally below the second feature, or simply indicates that the first feature is at a lower horizontal level than the second feature.

[0115] Although the present invention has been described in detail through the preferred embodiments above, it should be understood that the above description should not be considered as a limitation of the present invention. Various modifications and substitutions to the present invention will be apparent to those skilled in the art after reading the above description. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. A medical device performance evaluation system, characterized in that, include: Built-in hardware terminal and evaluation device; The mounted hardware terminal includes a log acquisition sensor, a non-contact current sensing sensor, and an RFID tag. The log acquisition sensor is used to collect log data of the medical device, the non-contact current sensing sensor is used to collect operating status data of the medical device, and the radio frequency identification tag stores an asset code that uniquely identifies the medical device. The evaluation device includes: a data integration module and an evaluation model; The data integration module is configured to receive multi-source data, including log data, operational status data, business data from the hospital's electronic information system, and manually entered data. The evaluation model includes: a basic score calculation unit, a correction factor calibration unit, and a scoring and rating and procurement decision unit; The basic score calculation unit is configured to: establish a mapping relationship between the multi-source data using the asset code as an index; Based on the aforementioned association mapping, the multi-source data associated with the medical device is obtained, and a basic score for the medical device under the corresponding evaluation dimension is calculated. The correction factor calibration unit is configured to: perform reliability cross-validation on the multi-source data associated with the medical device based on preset constraint rules, generate a correction factor for the corresponding basic score based on the validation result, and correct the basic score based on the correction factor to obtain the corresponding effective score. The scoring and procurement decision unit is configured to: calculate and generate a comprehensive performance score for medical equipment based on the effective scores of each evaluation dimension and the preset dimension weights, and generate a comprehensive performance rating and procurement decision based on the comprehensive performance score.

2. The medical device performance evaluation system as described in claim 1, characterized in that, Each evaluation dimension includes multiple indicators; the basic score calculation unit is configured as follows: Data associated with the indicator is selected from the multi-source data received by the data integration module to generate the original value of the indicator; The original values ​​of the indicators are standardized based on the indicator type to generate standardized values ​​for the indicators. Calculate the final weight within the dimension for each indicator under the evaluation dimension; Based on the evaluation dimension, the standardized values ​​of each indicator and the final weights within the dimension are used to calculate the basic score of the evaluation dimension.

3. The medical device performance evaluation system as described in claim 1, characterized in that, The hospital electronic information system includes at least one of the following: HIS system, PACS system, RIS system, financial system, and equipment management system; The multiple evaluation dimensions include economic benefits, equipment operation, clinical diagnosis and treatment, discipline development, and comprehensive value. The preset constraint rules include: economic benefit dimension constraint rules, equipment operation dimension constraint rules, clinical diagnosis and treatment dimension constraint rules, discipline development dimension constraint rules, and comprehensive value dimension constraint rules; The economic benefit dimension constraint rules include: ;and ; , , , These are the total revenue from equipment-based medical services, the compliant fee per equipment session, the number of valid medical services provided by the equipment, and revenue from consumables, respectively, within the business data. This is a preset percentage threshold; The device operation dimension constraint rules include: ;in, , , These are the total device power-on time in the operating status data, the power-on time in the log data, and the effective working time of the device in the operating status data, respectively. The constraints on the clinical diagnosis and treatment dimensions include: ,and ; , These are the longest average treatment time per case and the longest total effective treatment time in the business data. This represents the industry's lowest time consumption for examination items corresponding to a single case of diagnosis and treatment; This refers to the effective operating time of the device in the log data; The constraints on the discipline development dimension include: The number of key disease cases diagnosed clinically is greater than the number of key cases treated using equipment. The comprehensive value dimension constraint rules include: ,and ; The equipment reliability score, Equipment failure rate The value for the linkage between reagents and consumables. The percentage of reagent and consumable costs in total equipment revenue; This characterizes the degree of dependence on equipment consumables and the difficulty in controlling consumable costs; , Scoring is done by experts, while data is entered manually. .

4. The medical device performance evaluation system as described in claim 1, characterized in that, If the economic benefit dimension constraint rules are not met, the correction factor calibration unit is configured to generate an anomaly score D1 under the economic benefit dimension based on the deviation between the total equipment revenue and the revenue due calculated based on the number of outpatient visits, and the deviation between the proportion of consumable revenue in the total equipment revenue and the preset proportion threshold. If the device operation dimension constraint rules are not met, the correction factor calibration unit is configured to, based on , Calculate the anomaly score D2 under the equipment operation dimension; If the clinical diagnosis and treatment dimension constraint rules are not met, the correction factor calibration unit is configured to, based on , Calculate the abnormality score D3 under the clinical diagnosis and treatment dimension; If the constraints of the discipline development dimension are not met, the correction factor calibration unit is configured to set the abnormality score D4 under the discipline development dimension to a predetermined score. If the comprehensive value dimension constraint rules are not met, the correction factor calibration unit is configured to, based on , Calculate the anomaly score D5 under the comprehensive value dimension; The correction factors under the dimensions of economic benefits, equipment operation, clinical diagnosis and treatment, discipline development, and comprehensive value are denoted as K1, K2, K3, K4, and K5, respectively. m is a positive integer. ; A and B are correction parameters. .

5. The medical device performance evaluation system as described in claim 1, characterized in that, Also includes: The evaluation device also includes a storage module and a visualization module; The storage module is primarily used to store the multi-source data; The visualization module is used to display the multi-source data in a visualization interface, including at least one of the following under each evaluation dimension: base score, correction factor, effective score, comprehensive performance score, comprehensive performance rating, and procurement decision.

6. A method for evaluating the effectiveness of medical equipment, implemented using the medical equipment effectiveness evaluation system as described in any one of claims 1 to 5, characterized in that, Including the following steps: S1. Acquire multi-source data, including medical equipment log data and operating status data collected by the onboard hardware terminal, business data of the hospital's electronic information system, and manually entered data; S2. Using the asset code of the medical equipment as an index, establish a correlation mapping between multi-source data; based on the correlation mapping, obtain the multi-source data associated with the medical equipment, and calculate multiple basic scores for the medical equipment under multiple evaluation dimensions respectively; S3. Based on preset constraint rules, perform reliability cross-validation on the multi-source data associated with medical devices to determine whether any abnormalities occur in each evaluation dimension; If an anomaly is found, a correction factor is generated for the corresponding base score, and the base score is corrected based on the correction factor to obtain the corresponding effective score. S4. Based on the effective scores of each evaluation dimension and the preset dimension weights, generate a comprehensive performance score for the medical equipment, and generate a comprehensive performance rating and procurement decision based on the comprehensive performance score.

7. The medical device performance evaluation method as described in claim 6, characterized in that, Each assessment dimension includes multiple indicators; in step S2, the basic score for each assessment dimension for the medical device is calculated, including: S21. From the multi-source data associated with the medical device, select the data associated with the indicator, and calculate and generate the original value of the indicator according to the preset calculation formula. S22. Based on the indicator type, perform a standardization operation on the original value of the indicator to generate a standardized value of the indicator; The indicators include positive and negative indicators; the original values ​​of the positive and negative indicators are positively and negatively correlated with the effectiveness of medical equipment, respectively. Let the original value of the j-th indicator in the m-th evaluation dimension be denoted as The minimum and maximum original values ​​of the corresponding indicators for the same type of medical equipment are respectively denoted as: , ; If the j-th indicator of the m-th evaluation dimension is a positive indicator. ； If the j-th indicator of the m-th evaluation dimension is a negative indicator. ； S23. The multiple evaluation dimensions include the Mth evaluation dimension of the first evaluation dimension; calculate the final weight within the dimension for each indicator under the mth evaluation dimension, and calculate the basic score of the mth evaluation dimension based on the standardized value of the indicator and the final weight within the dimension. ; ； n m This represents the total number of indicators corresponding to the m-th evaluation dimension. ; This represents the standardized value of the j-th indicator in the m-th evaluation dimension, and the final weight within the dimension.

8. The medical device performance evaluation method as described in claim 7, characterized in that, make This represents the correction factor for the m-th evaluation dimension. This represents the effective score of the m-th evaluation dimension. ； make , Represent the overall performance score and the preset dimension weights for the m-th evaluation dimension, respectively. 。 9. The medical device performance evaluation method as described in claim 8, characterized in that, Step S23 involves calculating the final weights within each indicator of the m-th evaluation dimension, including the following steps: S231. Calculate the coefficient of variation of the j-th indicator in the m-th evaluation dimension. ,in ； , They represent the m-th evaluation dimension and the th evaluation dimension, respectively. Standard deviation and mean of each indicator; S232. Perform Pearson correlation analysis on the standardized values ​​of all indicators in the m-th evaluation dimension to establish a correlation coefficient matrix. ; For the m-th evaluation dimension, the first... The first indicator, the first The correlation coefficient of each indicator ; This represents the number of all indicators under the m-th dimension; S233. Calculate the conflict coefficient of the j-th indicator in the m-th evaluation dimension. , ； S234. Calculate the information content of the j-th indicator in the m-th evaluation dimension. , ； S235. Calculate the basic weight of the j-th indicator in the m-th evaluation dimension. , 10. The medical device performance evaluation method as described in claim 9, characterized in that, Step S23 involves calculating the final weights within each indicator of the m-th evaluation dimension, including the following steps: S236. Construct the judgment matrix ,in Used to characterize the m-th evaluation dimension. The first indicator is relative to the first The importance of each indicator is manually assigned. ; S237. Calculate the product of each row of the judgment matrix: ; calculate of The right root: ; right Normalization is performed to obtain the feature vector. That is, the initial value of the industry weight; Calculate the largest eigenvalue ; S238, Calculate the consistency index ; Calculate the consistency ratio , According to The average random consistency index obtained by looking up a table; If CR<a, it is determined that the matrix satisfies the consistency requirement, and the industry weight of the th indicator under the m-th evaluation dimension is equal to the j-th element in the eigenvector ; ; If CR ≥ a, then adjust the judgment matrix. Repeat steps S236~238; S239. The final weight within the dimension of the j-th indicator of the m-th evaluation dimension is obtained by the following formula: ； , These are the preset weighting coefficients.

Images