CN117612687B - Medical equipment monitoring and analyzing system based on artificial intelligence - Google Patents
Medical equipment monitoring and analyzing system based on artificial intelligence Download PDFInfo
- Publication number
- CN117612687B CN117612687B CN202410086956.1A CN202410086956A CN117612687B CN 117612687 B CN117612687 B CN 117612687B CN 202410086956 A CN202410086956 A CN 202410086956A CN 117612687 B CN117612687 B CN 117612687B
- Authority
- CN
- China
- Prior art keywords
- medical equipment
- output
- data
- equipment
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 87
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 29
- 238000012502 risk assessment Methods 0.000 claims abstract description 20
- 230000005856 abnormality Effects 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims description 42
- 238000012360 testing method Methods 0.000 claims description 19
- 230000035945 sensitivity Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 14
- 238000002560 therapeutic procedure Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007726 management method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000013468 resource allocation Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 238000009659 non-destructive testing Methods 0.000 claims description 3
- 238000013097 stability assessment Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 abstract description 19
- 238000010586 diagram Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/40—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Business, Economics & Management (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a medical equipment monitoring and analyzing system based on artificial intelligence, which particularly relates to the technical field of medical equipment monitoring, and comprises a sensor quality analyzing module, an operating environment analyzing module and an operating condition analyzing module, wherein the operating environment of medical equipment is monitored to obtain an operating environment abnormality evaluation index, so that abnormal operation of the medical equipment and abnormal output data caused by abnormal operating environment are avoided; the reliability of the sensor data is obtained through monitoring the sensor data, so that the problem of inaccurate acquired data caused by abnormal sensor in the prior art is solved; acquiring an output accuracy index of the medical equipment based on the equipment operation information; obtaining an equipment operation risk assessment coefficient based on the quality stability index of the sensor, the operation environment abnormality assessment index and the output accuracy index; and (5) taking corresponding treatment measures based on the equipment operation risk assessment coefficient to complete the real-time monitoring treatment of the medical equipment.
Description
Technical Field
The invention relates to the technical field of medical equipment monitoring, in particular to a medical equipment monitoring analysis system based on artificial intelligence.
Background
The medical equipment monitoring and analyzing system is mainly used for monitoring the running state of medical equipment in real time, detecting the abnormal condition of the equipment and carrying out early warning and fault diagnosis in time. The system generally includes sensors, data collectors, data processing servers, and user interfaces. The sensor is used for monitoring various parameters of the equipment, such as temperature, humidity, pressure, flow and the like; the data acquisition device is responsible for acquiring data of the sensor and transmitting the data to the data processing server; the data processing server is in charge of processing and analyzing the acquired data and extracting the running state and abnormal information of the equipment; the user interface is used for displaying the processing result and the early warning information, and is convenient for a user to check and manage.
However, in actual use, the method still has more defects, such as abnormal operation of medical equipment and abnormal output data caused by abnormal operation environment; the sensor abnormality causes the problem of inaccurate acquired data; the data output by the medical equipment is inaccurate, so that the judgment on the state of a patient is influenced, the dosage output is unstable, the treatment condition of the patient is influenced, the existing medical equipment monitoring and analyzing system is not intelligent enough, real-time monitoring cannot be carried out based on the risk of the medical equipment, and corresponding treatment measures cannot be adopted based on the risk.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a medical equipment monitoring and analyzing system based on artificial intelligence, which monitors the operation data and the operation environment data of medical equipment to realize the quality monitoring of the medical equipment and ensure the accuracy and the precision of the output data and the behaviors of the medical equipment so as to solve the problems in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions: an artificial intelligence based medical device monitoring analysis system comprising:
The medical equipment monitoring module is used for monitoring sensor state information, operation environment parameters and equipment operation information of the medical equipment;
the sensor quality analysis module is used for obtaining reliability evaluation parameters and stability evaluation parameters of the sensor based on the sensor time zero drift, the zero temperature drift and the sensitivity temperature drift, and obtaining a quality stability index Cz of the sensor based on the reliability evaluation parameters K1 and the data stability evaluation parameters K2 of the sensor through joint analysis;
The operation condition analysis module is used for acquiring an output accuracy index SC of the medical equipment based on the equipment operation information;
The operation environment analysis module is used for obtaining an operation environment abnormality assessment index Hn based on preset operation environment parameters, actual operation environment parameters and an influence weight coefficient of the operation environment parameter deviation rate on the accuracy of data of the medical equipment;
The equipment risk assessment module is used for estimating an index Hn of abnormality of the running environment, and outputting an index SC of accuracy based on a quality stability index Cz of a sensor through a formula Obtaining a device operation risk assessment coefficient Zp;
the equipment risk judging module is used for judging the equipment operation risk assessment coefficient Zp and a preset value And comparing, and generating corresponding measures based on the judging result.
Preferably, the calculation of the reliability evaluation parameter K1 satisfies a modelWherein tz_ave, zpz_ave and Td_ave respectively represent average values of time zero drift, zero temperature drift and sensitivity temperature drift; calculation of the stability assessment parameter K2 satisfies the model/>Wherein Tzv, zpzv, tdv respectively represents standard deviations of time zero drift, zero temperature drift and sensitivity temperature drift; by the formulaThe mass stability index Cz of the sensor is calculated, wherein α1, α2 are the influencing factors of the individual items, and α1+α2=1.0.
Preferably, the method is carried out by the formula:
Calculating to obtain an output accuracy index SC of the medical equipment, wherein F represents the number of the output data types, F represents the F output data types of the medical equipment, lsf represents the theoretical output value of the F output data types, and Sf represents the actual output value of the F output data types; j denotes the number of output dose types, m denotes that the medical device has m output therapy types, zlj denotes the theoretical dose of the j-th class of output therapy, zsj denotes the actual dose of the j-th class of output therapy, where β1, β2 are the influencing factors of each item, and β1+β2=1.0.
Preferably, acquiring an operation parameter requirement corresponding to the medical equipment, acquiring an actual operation environment parameter of the medical equipment, vectorizing the operation environment parameter, marking an ith preset operation environment parameter of the medical equipment as h0i, and marking the corresponding actual operation environment parameter as hi; by the formulaAnd calculating an operation environment abnormality assessment index Hn, wherein khi represents an influence weight coefficient khi of the i-th operation environment parameter deviation rate on the accuracy of the data, n represents the number of operation environment parameters, and i represents the number of the operation environment parameters.
Preferably, the process for obtaining the weight coefficient of the influence of the deviation rate of the running environment parameters on the accuracy of the data comprises the following steps: acquiring output accuracy indexes of medical equipment with normal quality under different environments, and acquiring a plurality of groups of test data; analyzing and obtaining an influence weight coefficient khi of each class of operating environment parameter deviation rate on the data accuracy by taking the medical equipment output accuracy index as an objective function, wherein the method comprises the following steps of:
step S01, selecting representative medical equipment, ensuring the normal quality and stable performance of the medical equipment, and preparing test scenes under different environments, including adjustment of temperature, humidity, pressure and air quality parameters, so as to ensure that diversified environmental data are obtained;
Step S02, under each test scene, operating the medical equipment, collecting output data of the medical equipment, and recording corresponding operating environment parameters;
Step S03, carrying out accuracy assessment on output data and dosage of medical equipment, and obtaining an output accuracy index SC;
Preferably, the specific contents of the accuracy assessment of the output data and the dosage of the medical equipment are as follows: the accuracy of the medical device is evaluated based on the gap between the actual output data and the theoretical output data of the medical device, based on the gap between the actual output dose and the theoretical output dose of the medical device.
Step S04, repeating the steps for a plurality of times to obtain a plurality of groups of test data, wherein each group of data comprises operation environment parameters and corresponding output accuracy indexes;
Step S05, based on a plurality of groups of test data and corresponding output accuracy indexes SC, analyzing the influence weight coefficient khi of each class of operation environment parameter deviation rate on the data accuracy.
Preferably, the equipment risk judging module is used for indicating that the output of the medical equipment is unstable when the acquired equipment operation risk assessment coefficient exceeds a preset value, giving an early warning to a manager, prompting the manager to maintain the medical equipment and generating a fault cause analysis instruction; when the acquired equipment operation risk assessment coefficient does not exceed a preset value, the medical equipment operation is relatively stable, the output data and the output dosage are corrected based on the influence weight coefficient of the operation environment parameter deviation rate on the data accuracy, and the corrected data are transmitted to the user interaction interface.
Preferably, the data correction method is as follows: by the formulaCalculating to obtain corrected output data Si' of the medical equipment, wherein Si represents the actual output value of the i-th output data; by the formula/>The theoretical output dose Zlj "corrected by the medical device is calculated, zlj represents the theoretical dose for the j-th class of output therapy.
Preferably, the system comprises a fault cause analysis module for analyzing the fault of the medical equipment and starting the fault cause analysis module based on the fault cause analysis instruction; the failure cause analysis module carries out nondestructive testing on the medical equipment to obtain the failure type of the medical equipment, and calculates the failure evaluation coefficient of the medical equipment based on the weighted summation of the failure type weight coefficient, the failure duration and the failure times of the medical equipment; the failure cause analysis module is connected with the failure processing knowledge graph to help management personnel to process the failure of the medical equipment.
Preferably, the system comprises a monitoring resource allocation module, a monitoring resource analysis module and a maintenance module, wherein the monitoring resource allocation module is used for allocating monitoring resources of the medical equipment, obtaining a monitoring resource demand index of the equipment through joint analysis based on equipment operation risk assessment coefficients and medical equipment fault assessment coefficients of the medical equipment, allocating the monitoring resources of the medical equipment based on the monitoring demand index, and setting maintenance frequency of the medical equipment.
The invention has the technical effects and advantages that:
According to the medical equipment monitoring and analyzing system, the operating environment of the medical equipment is monitored to obtain the operating environment abnormality assessment index, so that abnormal operation of the medical equipment and abnormal output data caused by abnormal operating environment are avoided; the reliability of the sensor data is obtained through monitoring the sensor data, so that the problem of inaccurate acquired data caused by abnormal sensor in the prior art is solved;
According to the medical equipment monitoring and analyzing system provided by the invention, abnormal data are analyzed through machine learning to obtain the fault type of the medical equipment, and the medical equipment fault evaluation coefficient of the medical equipment is obtained based on the fault type, the fault duration time and the fault occurrence times; based on the equipment operation risk assessment coefficient and the medical equipment fault assessment coefficient of the medical equipment, the monitoring resource demand index of the equipment is obtained through joint analysis, the monitoring resource of the medical equipment is distributed based on the monitoring demand index, the maintenance frequency of the medical equipment is set, and the management efficiency of the medical equipment can be effectively improved.
Drawings
Fig. 1 is a block diagram of a medical device monitoring and analyzing system according to the present invention.
Fig. 2 is a block diagram of a medical device monitoring module according to the present invention.
Fig. 3 is a block diagram showing an improved structure of the medical equipment monitoring and analyzing system of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure is embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the application, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
The computer system/server is described in the general context of computer-system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules include routines, programs, objects, components, logic, data structures, which perform particular tasks or implement particular abstract data types. Computer systems/servers are implemented in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules are located in both local and remote computing system storage media including memory storage devices.
Referring to a structural block diagram of a medical device monitoring and analyzing system in fig. 1, an embodiment of the present invention provides a medical device monitoring and analyzing system based on artificial intelligence, including:
the medical equipment monitoring module is used for monitoring sensor state information, operation environment parameters and equipment operation information of the medical equipment, and transmitting acquired data to the sensor quality analysis module, the operation environment analysis module and the operation condition analysis module respectively;
The sensor state information comprises a sensor time zero drift, a zero temperature drift and a sensitivity temperature drift; the operation environment parameters at least comprise environment temperature and humidity and dust level; the device operation information includes: outputting an actual output value of the data and an actual dosage of the treatment;
Referring to the block diagram of the medical equipment monitoring module shown in fig. 2, the medical equipment monitoring module includes an environment monitoring unit, a sensor monitoring unit, and an operating condition monitoring unit, where the environment monitoring unit is used to collect actual operating environment parameters of the medical equipment during operation; the sensor monitoring unit is used for collecting sensor information of the medical equipment and at least comprises a sensor time zero drift, a zero temperature drift and a sensitivity temperature drift; the running condition monitoring unit is used for collecting the completion condition of the medical equipment executing function instruction.
The sensor quality analysis module is used for obtaining reliability evaluation parameters and stability evaluation parameters of the sensor based on the sensor time zero drift, the zero temperature drift and the sensitivity temperature drift, and obtaining a quality stability index Cz of the sensor based on the reliability evaluation parameters K1 and the data stability evaluation parameters K2 of the sensor through joint analysis;
The operation condition analysis module is used for acquiring an output accuracy index SC of the medical equipment based on the equipment operation information;
The operation environment analysis module is used for obtaining an operation environment abnormality assessment index Hn based on preset operation environment parameters, actual operation environment parameters and an influence weight coefficient of the operation environment parameter deviation rate on the accuracy of data of the medical equipment;
The equipment risk assessment module is used for estimating an index Hn of abnormality of the running environment, and outputting an index SC of accuracy based on a quality stability index Cz of a sensor through a formula Obtaining a device operation risk assessment coefficient Zp;
the equipment risk judging module is used for judging the equipment operation risk assessment coefficient Zp and a preset value And comparing, and generating corresponding measures based on the judging result. When the acquired equipment operation risk assessment coefficient exceeds a preset value, indicating that the output of the medical equipment is unstable, giving an early warning to a manager, prompting the manager to maintain the medical equipment, and generating a fault cause analysis instruction; when the acquired equipment operation risk assessment coefficient does not exceed a preset value, the medical equipment operation is relatively stable, the output data is corrected based on the influence weight coefficient of the operation environment parameter deviation rate on the data accuracy, and the corrected data is transmitted to the user interaction interface.
Further, the system according to the embodiment of the invention comprises: the fault cause analysis module is used for analyzing the faults of the medical equipment and starting the fault cause analysis module based on the fault cause analysis instruction; the failure cause analysis module carries out nondestructive testing on the medical equipment to obtain the failure type of the medical equipment, and calculates the failure evaluation coefficient of the medical equipment based on the weighted summation of the failure type weight coefficient, the failure duration and the failure times of the medical equipment; the failure cause analysis module is connected with the failure processing knowledge graph to help management personnel to process the failure of the medical equipment.
Further, the medical equipment fault evaluation coefficient Gx satisfies the formulaWherein Gx represents a medical device failure evaluation coefficient, n represents the number of failures of the medical device, gti represents the failure duration of the ith failure, gki represents a failure type weight coefficient of the ith failure.
Further, the system of the invention comprises a visual interface: the real-time state, abnormal condition and maintenance advice of the medical equipment are displayed through the visual interface, so that a user can conveniently check and manage the equipment.
Referring to fig. 3, an improved structural block diagram of a medical device monitoring and analyzing system is disclosed, wherein the system comprises a monitoring resource allocation module for allocating monitoring resources of a medical device, obtaining a monitoring resource demand index of the device based on a device running risk evaluation coefficient and a medical device fault evaluation coefficient of the medical device through joint analysis, allocating the monitoring resources of the medical device based on the monitoring demand index, and setting a maintenance frequency of the medical device.
The monitoring resources comprise monitoring frequency and monitoring coverage range of the medical equipment, the more the monitoring resources of the medical equipment are, the higher the monitoring frequency and the longer the monitoring coverage time of the medical equipment are, the reasonable distribution of the monitoring resources can help users to find problems of the medical equipment in time, the monitoring resources are saved, the monitoring frequency refers to the number of times of checking the medical equipment, and the high-frequency monitoring means that the equipment is checked for multiple times in a short time, so that potential problems or faults can be found in time. While monitoring coverage involves inspection integrity, some devices may require comprehensive inspection, including their individual components and functions, to ensure their proper operation. When having more monitoring resources, this means more frequent and longer monitoring of the medical device, which not only increases the likelihood of problems and malfunctions being found, but also provides more time for timely repair. Reasonable resource allocation is critical to ensure that resources are not over-utilized and that the device gets sufficient attention.
Further, based on time zero drift, zero temperature drift and sensitivity temperature drift analysis of the sensor, reliability evaluation parameters K1 and stability evaluation parameters K2 of the sensor are obtained, based on the reliability evaluation parameters K1 and data stability evaluation parameters K2 of the sensor, a quality stability index Cz of the sensor is obtained through joint analysis, and the reliability of sensor data is judged according to the index. When the reliability is lower than a preset value, the system gives an early warning to the manager to prompt the replacement or maintenance of the sensor.
The time zero drift refers to the condition that the output zero point of the sensor drifts along with time; zero temperature drift refers to the condition that the output zero point of a sensor drifts along with the change of temperature; the sensitivity temperature drift refers to the condition that the sensitivity of the sensor varies with temperature. These drift phenomena may affect the accuracy and reliability of the sensor, and therefore require monitoring and analysis thereof. Sensor data is collected over a period of time, including time, temperature, and output values. Then, a time zero drift, a zero temperature drift, and a sensitivity temperature drift in each period of time are calculated. Specifically, the time zero drift is calculated by comparing output zero points in adjacent time periods; the zero temperature drift is calculated by comparing the relationship between the output zero point and the temperature in the adjacent time period; the sensitivity temperature drift is calculated by comparing the output values over adjacent time periods with the temperature. After the time zero drift, the zero temperature drift, and the sensitivity temperature drift in each period are obtained, their average value and standard deviation are calculated. The average value reflects the drift of the sensor over the entire period of time, while the standard deviation reflects the degree of fluctuation of the sensor drift. After the quality stability index Cz of the sensor is provided, a preset quality stability index threshold is set, when the quality stability index of the sensor is lower than the threshold, the reliability of the sensor is lower, and at the moment, the system gives an early warning to a manager to prompt the manager to replace or repair the sensor. Conversely, if the sensor quality stability index is higher than the threshold value, the sensor reliability is higher and the use is guaranteed.
It is stated that in the medical field, the reliability and accuracy of sensors is critical to ensuring patient safety and improving medical quality of service. However, for various reasons, the sensor may be abnormal, resulting in unsatisfactory acquired data. To discover and solve these problems in time, the status of the sensor needs to be monitored.
Further, the calculation of the reliability evaluation parameter K1 satisfies the modelWherein tz_ave, zpz_ave and Td_ave respectively represent average values of time zero drift, zero temperature drift and sensitivity temperature drift; calculation of the stability assessment parameter K2 satisfies the model/>Wherein Tzv, zpzv, tdv respectively represents standard deviations of time zero drift, zero temperature drift and sensitivity temperature drift; the mass stability index Cz of the sensor is calculated by a formula,Wherein α1, α2 are influence factors of each item, and α1+α2=1.0.
Further, by the formulaCalculating to obtain an output accuracy index SC of the medical equipment, wherein F represents the number of the output data types, F represents the F output data types of the medical equipment, lsf represents the theoretical output value of the F output data types, and Sf represents the actual output value of the F output data types; j denotes the number of output dose types, m denotes that the medical device has m output therapy types, zlj denotes the theoretical dose of the j-th class of output therapy, zsj denotes the actual dose of the j-th class of output therapy, where β1, β2 are the influencing factors of each item, and β1+β2=1.0.
The medical equipment in the embodiment of the invention is divided into state monitoring equipment, treatment equipment and state monitoring and treatment equipment according to types, wherein the state monitoring equipment is used for monitoring state parameters of users and environments and at least comprises an electrocardiograph, a sphygmomanometer, an oximeter and the like, and the state monitoring equipment can help doctors to know the health condition of patients in time and guide treatment and nursing; the treatment equipment is used for providing treatment operation for a user and at least comprises a laser therapeutic instrument, an X-ray machine, an electric shock device and a breathing machine, and can help patients relieve pain, improve physiological functions, promote healing and rehabilitation and improve life quality of the patients.
By monitoring the operation environment of the medical equipment, the equipment operation abnormality and the data output abnormality caused by the environment abnormality are effectively avoided. The operating environment has a critical impact on the performance and stability of the medical device, and therefore monitoring the operating environment is a key element in ensuring proper operation of the device. The operating environment of a medical device includes various aspects of temperature, humidity, pressure, air quality, and the like. If the operating environment parameters are abnormal, such as too high or too low temperature, too high or too low humidity, excessive standard harmful substances in the air and the like, the performance and the operating stability of the equipment can be influenced, and the monitoring data of the equipment can be influenced. By monitoring the running environment in real time, the abnormal situation is found in time, and corresponding measures are taken to correct the abnormal situation. For example, when the temperature is too high, the air conditioner or the fan is turned on to reduce the temperature; when the humidity is too low, starting the humidifier to increase the humidity; when the air quality is poor, the air purifier is started to improve the air quality. Upon finding an operating environment anomaly, the device management system generates an operating environment anomaly evaluation index for evaluating the severity and scope of impact of the anomaly based on the monitored data. The index helps management personnel to know the condition of the equipment operation environment in time, and take corresponding measures to intervene and adjust, wherein the measures comprise correction of output data of medical equipment and correction of theoretical output dosage of the medical equipment; by correcting the actual output data of the medical equipment, the influence of environmental factors on the output data can be eliminated; by correcting the theoretical output dose of the medical equipment, the output dose of the medical equipment can meet the preset requirement.
Further, based on preset operation environment parameters and actual operation environment parameters of the medical equipment and the influence weight coefficient of the deviation rate of the operation environment parameters on the accuracy of the data, an operation environment abnormality assessment index Hn is obtained; acquiring an operation environment requirement corresponding to medical equipment, acquiring actual operation environment parameters of the medical equipment, vectorizing the operation environment parameters, marking the ith preset operation environment parameter of the medical equipment as h0i, and marking the corresponding actual operation environment parameter as hi;
By the formula And calculating an operation environment abnormality assessment index Hn, wherein khi represents an influence weight coefficient khi of the i-th operation environment parameter deviation rate on the accuracy of the data, n represents the number of operation environment parameters, and i represents the number of the operation environment parameters.
Further, the obtaining of the influence weight coefficient of the deviation rate of the running environment parameters on the accuracy of the data comprises the following steps: acquiring output accuracy indexes of medical equipment with normal quality under different environments, and acquiring a plurality of groups of test data; analyzing and obtaining an influence weight coefficient khi of each class of operating environment parameter deviation rate on the data accuracy by taking the medical equipment output accuracy index as an objective function, wherein the method comprises the following steps of:
step S01, selecting representative medical equipment, ensuring the normal quality and stable performance of the medical equipment, and preparing test scenes under different environments, including adjustment of temperature, humidity, pressure and air quality parameters, so as to ensure that diversified environmental data are obtained;
Step S02, operating the medical equipment and collecting output data of the medical equipment under each test scene, and recording corresponding operating environment parameters such as temperature, humidity, pressure and air quality;
Step S03, carrying out accuracy assessment on output data and dosage of medical equipment, and obtaining an output accuracy index;
step S04, repeating the steps for a plurality of times to obtain a plurality of groups of test data, wherein each group of data comprises operation environment parameters and corresponding output accuracy indexes;
Step S05, based on a plurality of groups of test data and corresponding output accuracy indexes SC, analyzing the influence weight coefficient khi of each class of operation environment parameter deviation rate on the data accuracy.
Further, in step S05, statistical analysis is performed on each set of test data to understand the relationship between the operating environment parameter and the output accuracy index; establishing a mathematical model or regression equation between the operation environment parameters and the output accuracy index by using regression analysis and principal component analysis methods; calculating an influence weight coefficient khi of each type of operating environment parameter deviation rate on the accuracy of the data through a mathematical model or a coefficient of a regression equation; or mapping the operation environment parameter vector to an output accuracy index by using a machine learning algorithm to obtain an influence weight coefficient khi of each type of operation environment parameter deviation rate of each operation environment parameter on the accuracy of the data, and selecting a proper machine learning algorithm, such as a support vector machine, a neural network and a decision tree; dividing test data into a training set and a testing set, and training a machine learning algorithm by using the training set to obtain a model; verifying and evaluating the model by using a test set, and knowing the prediction precision and stability of the model; and analyzing the parameter and the feature importance of the machine learning algorithm to obtain the influence weight coefficient of each class of operating environment parameter deviation rate on the data accuracy.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention, but rather to enable any modification, equivalent replacement or improvement made within the spirit and principles of the invention.
Claims (6)
1. An artificial intelligence based medical device monitoring and analysis system, comprising:
The medical equipment monitoring module is used for monitoring sensor state information, operation environment parameters and equipment operation information of the medical equipment;
the sensor quality analysis module is used for obtaining reliability evaluation parameters and stability evaluation parameters of the sensor based on the sensor time zero drift, the zero temperature drift and the sensitivity temperature drift, and obtaining a quality stability index Cz of the sensor based on the reliability evaluation parameters K1 and the data stability evaluation parameters K2 of the sensor through joint analysis;
Calculation satisfaction model of reliability evaluation parameter K1 Wherein tz_ave, zpz_ave and Td_ave respectively represent average values of time zero drift, zero temperature drift and sensitivity temperature drift; calculation of the stability assessment parameter K2 satisfies the model/>Wherein Tzv, zpzv, tdv respectively represents standard deviations of time zero drift, zero temperature drift and sensitivity temperature drift; by the formulaCalculating to obtain a quality stability index Cz of the sensor, wherein alpha 1 and alpha 2 are influence factors of each item, and alpha 1 plus alpha 2 = 1.0;
The operation condition analysis module is used for acquiring an output accuracy index SC of the medical equipment based on the equipment operation information; by the formula Calculating to obtain an output accuracy index SC of the medical equipment, wherein F represents the number of the output data types, F represents the F output data types of the medical equipment, lsf represents the theoretical output value of the F output data types, and Sf represents the actual output value of the F output data types; j represents the number of output dose types, m represents m output therapy types for the medical device, zlj represents the theoretical dose for the j-th class of output therapy, zsj represents the actual dose for the j-th class of output therapy, where β1, β2 are the influencing factors for each item, and β1+β2=1.0;
The operation environment analysis module is used for obtaining an operation environment abnormality assessment index Hn based on preset operation environment parameters, actual operation environment parameters and an influence weight coefficient of the operation environment parameter deviation rate on the accuracy of data of the medical equipment; acquiring an operation parameter requirement corresponding to medical equipment, acquiring an actual operation environment parameter of the medical equipment, vectorizing the operation environment parameter, marking the ith preset operation environment parameter of the medical equipment as h0i, and marking the corresponding actual operation environment parameter as hi; by the formula Calculating to obtain an operating environment abnormality assessment index Hn, wherein khi represents an influence weight coefficient khi of the i-th operating environment parameter deviation rate on data accuracy, n represents the number of the operating environment parameters, and i represents the number of the operating environment parameters;
The equipment risk assessment module is used for estimating an index Hn of abnormality of the running environment, and outputting an index SC of accuracy based on a quality stability index Cz of a sensor through a formula Obtaining a device operation risk assessment coefficient Zp;
the equipment risk judging module is used for judging the equipment operation risk assessment coefficient Zp and a preset value And comparing, and generating corresponding measures based on the judging result.
2. The medical device monitoring and analysis system based on artificial intelligence according to claim 1, wherein the process of obtaining the weighting coefficients of the influence of the deviation rate of the operating environment parameters on the accuracy of the data comprises: acquiring output accuracy indexes of medical equipment with normal quality under different environments, and acquiring a plurality of groups of test data; analyzing and obtaining an influence weight coefficient khi of each class of operating environment parameter deviation rate on the data accuracy by taking the medical equipment output accuracy index as an objective function, wherein the method comprises the following steps of:
step S01, selecting representative medical equipment, ensuring the normal quality and stable performance of the medical equipment, and preparing test scenes under different environments, including adjustment of temperature, humidity, pressure and air quality parameters, so as to ensure that diversified environmental data are obtained;
Step S02, under each test scene, operating the medical equipment, collecting output data of the medical equipment, and recording corresponding operating environment parameters;
Step S03, carrying out accuracy assessment on output data and dosage of medical equipment, and obtaining an output accuracy index SC;
step S04, repeating the steps for a plurality of times to obtain a plurality of groups of test data, wherein each group of data comprises operation environment parameters and corresponding output accuracy indexes;
Step S05, based on a plurality of groups of test data and corresponding output accuracy indexes SC, analyzing the influence weight coefficient khi of each class of operation environment parameter deviation rate on the data accuracy.
3. The medical equipment monitoring and analyzing system based on artificial intelligence according to claim 1, wherein the equipment risk judging module is used for indicating that the output of the medical equipment is unstable when the acquired equipment operation risk assessment coefficient exceeds a preset value, giving an early warning to a manager, prompting the manager to maintain the medical equipment and generating a fault cause analysis instruction; when the acquired equipment operation risk assessment coefficient does not exceed a preset value, the medical equipment operation is relatively stable, the output data and the output dosage are corrected based on the influence weight coefficient of the operation environment parameter deviation rate on the data accuracy, and the corrected data are transmitted to the user interaction interface.
4. The medical device monitoring and analyzing system based on artificial intelligence according to claim 3, wherein the data correction method is as follows: by the formulaCalculating to obtain corrected output data Si' of the medical equipment, wherein Si represents the actual output value of the i-th output data; by the formula/>The theoretical output dose Zlj "corrected by the medical device is calculated, zlj represents the theoretical dose for the j-th class of output therapy.
5. The medical equipment monitoring and analyzing system based on artificial intelligence according to claim 3, comprising a fault reason analyzing module for analyzing faults of the medical equipment, wherein the fault reason analyzing module is started based on the fault reason analyzing instruction; the failure cause analysis module carries out nondestructive testing on the medical equipment to obtain the failure type of the medical equipment, and calculates the failure evaluation coefficient of the medical equipment based on the weighted summation of the failure type weight coefficient, the failure duration and the failure times of the medical equipment; the failure cause analysis module is connected with the failure processing knowledge graph to help management personnel to process the failure of the medical equipment.
6. The system of claim 5, wherein the system comprises a monitoring resource allocation module for allocating monitoring resources of the medical device, obtaining a monitoring resource demand index of the device based on the device running risk assessment coefficient and the medical device fault assessment coefficient by joint analysis, allocating the monitoring resources of the medical device based on the monitoring demand index, and setting maintenance frequency of the medical device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410086956.1A CN117612687B (en) | 2024-01-22 | 2024-01-22 | Medical equipment monitoring and analyzing system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410086956.1A CN117612687B (en) | 2024-01-22 | 2024-01-22 | Medical equipment monitoring and analyzing system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117612687A CN117612687A (en) | 2024-02-27 |
| CN117612687B true CN117612687B (en) | 2024-04-26 |
Family
ID=89953832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410086956.1A Active CN117612687B (en) | 2024-01-22 | 2024-01-22 | Medical equipment monitoring and analyzing system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117612687B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117909703B (en) * | 2024-03-18 | 2024-05-31 | 山东省国土空间数据和遥感技术研究院(山东省海域动态监视监测中心) | Data quality evaluation method and system based on alarm threshold trigger |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110764441A (en) * | 2019-09-10 | 2020-02-07 | 山东博鹏信息科技有限公司 | Information monitoring system for hospital equipment |
| CN114242216A (en) * | 2021-11-01 | 2022-03-25 | 孙如江 | Block chain-based medical equipment use data management method and system |
| CN115359868A (en) * | 2022-09-14 | 2022-11-18 | 亿慧云智能科技（深圳）股份有限公司 | Intelligent medical monitoring method and system based on cloud computing technology |
| WO2023281425A1 (en) * | 2021-07-09 | 2023-01-12 | Ayur.Ai (Opc) Private Limited | A digital kiosk for performing integrative analysis of health and disease condition and method thereof |
| CN116386832A (en) * | 2023-06-01 | 2023-07-04 | 武汉一刻钟医疗科技有限公司 | Medical equipment monitoring analysis management cloud system based on artificial intelligence |
| CN116433009A (en) * | 2023-03-08 | 2023-07-14 | 广东电网有限责任公司 | Abnormality monitoring method and device for power transformation equipment and storage medium |
| CN116844708A (en) * | 2023-07-14 | 2023-10-03 | 山东中医药大学附属医院 | Medical equipment fault prediction method and system based on artificial intelligence |
| CN116962471A (en) * | 2023-08-01 | 2023-10-27 | 上海昆亚医疗器械股份有限公司 | Medical equipment management system based on Internet of things |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190331701A1 (en) * | 2018-04-30 | 2019-10-31 | Lonza Limited | System and Method for Environmental Monitoring |
-
2024
- 2024-01-22 CN CN202410086956.1A patent/CN117612687B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110764441A (en) * | 2019-09-10 | 2020-02-07 | 山东博鹏信息科技有限公司 | Information monitoring system for hospital equipment |
| WO2023281425A1 (en) * | 2021-07-09 | 2023-01-12 | Ayur.Ai (Opc) Private Limited | A digital kiosk for performing integrative analysis of health and disease condition and method thereof |
| CN114242216A (en) * | 2021-11-01 | 2022-03-25 | 孙如江 | Block chain-based medical equipment use data management method and system |
| CN115359868A (en) * | 2022-09-14 | 2022-11-18 | 亿慧云智能科技（深圳）股份有限公司 | Intelligent medical monitoring method and system based on cloud computing technology |
| CN116433009A (en) * | 2023-03-08 | 2023-07-14 | 广东电网有限责任公司 | Abnormality monitoring method and device for power transformation equipment and storage medium |
| CN116386832A (en) * | 2023-06-01 | 2023-07-04 | 武汉一刻钟医疗科技有限公司 | Medical equipment monitoring analysis management cloud system based on artificial intelligence |
| CN116844708A (en) * | 2023-07-14 | 2023-10-03 | 山东中医药大学附属医院 | Medical equipment fault prediction method and system based on artificial intelligence |
| CN116962471A (en) * | 2023-08-01 | 2023-10-27 | 上海昆亚医疗器械股份有限公司 | Medical equipment management system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117612687A (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117612687B (en) | Medical equipment monitoring and analyzing system based on artificial intelligence | |
| CN109947088B (en) | Equipment fault early warning system based on model full life cycle management | |
| CN117060594B (en) | Power distribution operation monitoring system based on Internet of things | |
| CN115101187B (en) | Anesthesia machine operation fault prediction system based on big data | |
| CN110865924B (en) | Health degree diagnosis method and health diagnosis framework for internal server of power information system | |
| CN116701886B (en) | Intelligent analysis management system for exercise lung test data | |
| CN116649987A (en) | Electrocardiogram abnormality real-time monitoring system based on Internet | |
| CN112951400A (en) | Information acquisition management system and method for clinical emergency medical equipment | |
| CN116345700A (en) | Energy consumption monitoring method and monitoring system for energy storage power station | |
| CN114662619B (en) | Bridge monitoring system based on multi-source data fusion | |
| KR20140051678A (en) | Apparatus and method for fault management of smart devices | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN112202630A (en) | Network quality abnormity detection method and device based on unsupervised model | |
| CN117497162A (en) | Abnormal operation feedback early warning system of oral cavity laser therapeutic instrument based on data analysis | |
| CN115966287A (en) | Medical information management system and medical information management method | |
| CN110379503A (en) | A kind of online fault detection and diagnosis system based on continuous blood sugar monitoring system | |
| CN113870988A (en) | Anesthesia workstation operation supervisory systems based on big data analysis | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN112660957B (en) | Early warning method and early warning system for elevator operation risk | |
| CN116032016A (en) | Intelligent wind power plant running state on-line monitoring and early warning system and early warning method | |
| CN115586321A (en) | Method, system, memory and equipment for identifying online monitoring data of dissolved gas in oil | |
| CN113323819B (en) | Fan safety chain fault analysis method and system based on fuzzy expert system | |
| CN109947615A (en) | The monitoring method and device of distributed system | |
| Wroblewski et al. | Neural networks for smoothing of helicopter rotors | |
| CN114091618A (en) | Industrial equipment health state diagnosis management method and device and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |