Method and system for evaluating use quality of digital medical thermometer in full life cycle

Abstract

The invention belongs to the technical field of medical equipment, and particularly discloses a use quality evaluation method and system for a digital medical thermometer in a full life cycle, and the method comprises the steps: constructing a parameter database of the digital medical thermometer in the full life cycle, constructing and fusing three monitored object learning models, obtaining a comprehensive evaluation model, and carrying out the evaluation of the use quality of the digital medical thermometer in the full life cycle. Obtaining theoretical monitoring data and actual monitoring data of the digital medical thermometer; establishing a full-life-cycle management model of the digital medical thermometer, performing model training, and then performing correction to obtain a corrected full-life-cycle management model; and adopting the corrected full-life-cycle management model to perform full-life-cycle management on the digital medical thermometers, evaluating the use quality of the whole process, and performing evaluation and grading on the use quality of the thermometers according to the obtained indexes. By adopting the technical scheme, the use quality of the digital medical thermometer in the whole life cycle is comprehensively evaluated, and the performance is accurately evaluated.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical equipment and relates to a method and system for evaluating the quality of use of a digital medical thermometer throughout its life cycle. Background Art

[0002] With the continuous advancement of health monitoring technology and the restrictions on mercury-containing medical devices in the Minamata Convention, digital thermometers have become a widely used temperature monitoring tool in homes and medical facilities due to their mercury-free, fast and accurate characteristics. The development of digital thermometers has greatly improved the convenience and accuracy of thermometers.

[0003] However, there are many brands of digital thermometers on the market, and the quality of products varies. Since the accuracy and stability of digital thermometers may change over time, frequency of use, and environmental conditions, existing evaluation methods are often based on test results in laboratory environments or single data sources. These methods are difficult to fully and truly reflect the performance of digital thermometers in actual use environments.

[0004] The existing evaluation methods may not match the actual usage conditions due to the differences between the laboratory test environment and the actual usage environment. In addition, the existing evaluation methods often focus on the performance of the product when it leaves the factory, but ignore the performance changes of the product during use, and lack comprehensive consideration of factors such as user usage habits and maintenance. These factors may affect the long-term performance of the thermometer, resulting in inaccurate evaluation. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for evaluating the quality of use of a digital medical thermometer throughout its life cycle, so as to more comprehensively and accurately evaluate the performance of the thermometer during actual use.

[0006] In order to achieve the above object, the basic scheme of the present invention is: a method for evaluating the quality of use of a digital medical thermometer throughout its life cycle, comprising the following steps:

[0007] Build a parameter database for the entire life cycle of digital medical thermometers;

[0008] Based on the parameter database, a monitoring object learning model is constructed, including: product quality assessment model, clinical use factor impact assessment model on thermometer quality, and management and maintenance result impact assessment model on thermometer use quality;

[0009] The three monitoring object learning models are integrated to obtain a comprehensive evaluation model;

[0010] Input the data of the parameter database into the comprehensive evaluation model to obtain the theoretical monitoring data of the digital medical thermometer;

[0011] Collect sample data during the use of medical thermometers, substitute the sample data into the comprehensive evaluation model, and obtain the actual monitoring data of the current digital medical thermometer;

[0012] Based on the machine learning algorithm, a full life cycle management model for digital medical thermometers is established, and theoretical monitoring data and actual monitoring data are substituted into the full life cycle management model for model training;

[0013] According to the actual life cycle process obtained from the digital medical thermometer test data, the trained life cycle management model is revised to obtain a revised life cycle management model;

[0014] The revised life cycle management model is used to manage the digital medical thermometer throughout its life cycle, evaluate the quality of use throughout the entire process, and evaluate and grade the quality of use of the thermometer based on the various indicators obtained.

[0015] The working principle and beneficial effects of this basic solution are as follows: This technical solution provides a scientific and comprehensive evaluation system for the quality evaluation of thermometers by constructing a product quality evaluation model, an evaluation model for the impact of clinical use factors on thermometer quality, an evaluation model for the impact of management and maintenance results on thermometer use quality, and model fusion and optimization. This not only helps medical institutions better understand and grasp the actual use of thermometers, but also provides data support for product improvement and optimization.

[0016] By building a full life cycle quality assessment method, monitoring and managing the entire life cycle of thermometers, and more comprehensively and accurately evaluating the performance of thermometers during actual use, existing problems can be discovered and resolved in a timely manner, thereby extending the service life of thermometers and reducing the operating costs of medical institutions.

[0017] Furthermore, a parameter database for the entire life cycle of a digital medical thermometer is constructed, specifically:

[0018] Create a parameter database that fully covers the entire life cycle of the thermometer. The parameter database is initialized when the thermometer is accepted and the information is associated with a unique factory number and management number.

[0019] The parameter database includes:

[0020] The name, manufacturer, specification model, factory number, management number, production date, batch, expiration date, usage duration, and frequency of use of the thermometer;

[0021] Thermometer usage: temperature measurement method, department from which the thermometer was shipped, ward of use, patient ID, gender, age, main disease type, and DRG disease group;

[0022] Record the maintenance and inspection data of the thermometer: factory number, management number, calibration point, standard temperature, indication temperature, indication error, inspection conditions, and inspection time.

[0023] Obtain parameter data that fully covers the entire life cycle of the thermometer, which is convenient for subsequent use.

[0024] Furthermore, a product quality assessment model is constructed as follows:

[0025] Select brand, specification, model, usage duration or frequency of use as key features;

[0026] Use machine learning algorithms to build models based on key features:

[0027] f(a)=Ma1*Na1+Ma2*Na2+Ma3*Na3+Ma4*Na4

[0028] Among them, Ma1 represents brand weight and Na1 represents brand factor; Ma2 represents specification model weight and Na2 represents specification model factor; Ma3 represents usage time weight and Na3 represents usage time factor; Ma4 represents usage frequency weight and Na4 represents usage frequency factor.

[0029] Simple structure and easy to use.

[0030] Furthermore, an evaluation model of the impact of clinical use factors on thermometer quality was constructed, specifically:

[0031] Select features from the parameter database: type of department that ships out, ward that uses, gender, age, and main disease type;

[0032] Build a model based on the selected features:

[0033] f(b)=Mb1*Nb1+Mb2*Nb2+Mb3*Nb3+Mb4*Nb4+Mb5*Nb5

[0034] Among them, Mb1 represents the department weight and Nb1 represents the department factor; Mb2 represents the ward weight and Nb2 represents the ward factor; Mb3 represents the gender weight and Nb3 represents the gender factor; Mb4 represents the age weight and Nb4 represents the age factor; Mb5 represents the disease type weight and Nb5 represents the disease type factor.

[0035] The impact of clinical use factors on thermometer quality was evaluated using the evaluation model of clinical use factors on thermometer quality.

[0036] Furthermore, an evaluation model of the impact of management and maintenance results on the quality of thermometer use is constructed as follows:

[0037] Build a model based on the calibration test results, calibration test conditions, calibration times, and battery replacement data in the parameter database:

[0038] f(c)=Mc1*Nc1+Mc2*Nc2+Mc3*Nc3+Mc4*Nc4

[0039] Among them, Mc1 represents the weight of the calibration result, and Nc1 represents the calibration result factor; Mc2 represents the weight of the calibration detection condition, and Nc2 represents the calibration detection condition factor; Mc3 represents the weight of the calibration times, and Nc3 represents the gender factor; Mc4 represents the weight of the new battery use, and Nc4 represents the new battery use factor.

[0040] Use the management and maintenance results on the thermometer usage quality assessment model to evaluate the impact of management and maintenance results on the thermometer.

[0041] Furthermore, the three monitoring object learning models are integrated to obtain a comprehensive evaluation model:

[0042] f=f(a)*f(b)*f(c)

[0043] Among them, f(a) is the product quality assessment result value, f(b) is the assessment result value of the impact of clinical use factors on the quality of the thermometer, f(c) is the assessment result value of the impact of management and maintenance results on the quality of thermometer use, and * represents the multiplication sign.

[0044] The impact assessment models of various parameters are integrated to conduct a comprehensive assessment, which is more comprehensive and accurate.

[0045] Furthermore, based on the machine learning algorithm, the method for establishing a full life cycle management model for digital medical thermometers is as follows:

[0046] Select machine learning algorithms to build a full life cycle management model;

[0047] Preprocess the collected theoretical monitoring data and actual monitoring data, including data cleaning and data standardization, to ensure data quality and consistency;

[0048] Extract key features from preprocessed data as input to the full life cycle management model;

[0049] Substitute the preprocessed feature data into the selected machine learning algorithm for model training. During the training process, the algorithm will automatically learn the relationship between the features and the quality of thermometer use and establish a corresponding model.

[0050] The trained model was validated using cross-validation and independent test datasets to ensure the accuracy and generalization ability of the model.

[0051] Furthermore, according to the actual life cycle process obtained from the digital medical thermometer test data, the trained life cycle management model is revised to obtain a revised life cycle management model. The specific steps are as follows:

[0052] The test data of digital medical thermometers includes product information data, management information data, quality control and clinical application information of the thermometer throughout its life cycle;

[0053] Align actual usage data with theoretical monitoring data, and adjust the model parameters based on deviations and anomalies found in the actual usage data;

[0054] The corrected parameters and actual usage data are re-substituted into the model for retraining, and the accuracy and generalization ability of the corrected model are verified through cross-validation and actual data testing to ensure that the model can accurately predict the performance of the thermometer in actual use.

[0055] Further classification:

[0056] According to the scope and distribution of evaluation indicators, formulate reasonable grading standards and divide the use quality of thermometers into excellent, good, general and poor grades;

[0057] According to the specific values ​​of the evaluation indicators, the temperature plan is divided into different levels:

[0058] Temperature programs with a quality score of more than 90 points are classified as excellent, those with a score of 70 to 89 points are classified as good, those with a score of 50 to 69 points are classified as fair, and those with a score of less than 50 points are classified as poor;

[0059] The results of thermometer use quality assessment and grading will be used to manage the clinical use of thermometers:

[0060] Thermometers with a score of 90 or above can be used normally; those with a score of 70-89 should have their measurement quality inspected more frequently; those with a score of 50-70 should be maintained; and those with a score below 50 are recommended to be eliminated.

[0061] The present invention also provides a use quality assessment system for a digital medical thermometer throughout its life cycle, comprising a data acquisition unit and a processing unit, wherein the data acquisition unit is used to obtain parameter database information of the digital medical thermometer throughout its life cycle;

[0062] The input end of the processing unit is connected to the output end of the data acquisition unit, and the processing unit executes the method of the present invention to evaluate the use quality of the digital medical thermometer throughout its life cycle.

[0063] This system uses a data acquisition unit and a processing unit to comprehensively collect thermometer parameters and conduct usage quality assessment to obtain more comprehensive and accurate assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flow chart of the method for evaluating the quality of use of a digital medical thermometer throughout its life cycle according to the present invention. DETAILED DESCRIPTION

[0065] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0066] In the description of the present invention, it is necessary to understand that the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0067] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0068] The present invention discloses a method for evaluating the quality of use of a digital medical thermometer throughout its life cycle, which comprehensively evaluates the quality of use of a digital medical thermometer throughout its life cycle, including its performance under different use environments, use frequencies, and maintenance conditions. The method can more comprehensively and accurately evaluate the performance of the thermometer during actual use, thereby improving the accuracy and reliability of temperature measurement and protecting the health of users.

[0069] like Figure 1 As shown in the figure, the quality assessment method for the use of digital medical thermometers throughout their life cycle includes the following steps:

[0070] Build a parameter database for the entire life cycle of digital medical thermometers;

[0071] Based on the parameter database and various related data of the thermometer, a monitoring object learning model is constructed, including: product quality assessment model, clinical use factor impact assessment model on thermometer quality, and management and maintenance result impact assessment model on thermometer use quality;

[0072] The three monitoring object learning models are integrated to obtain a comprehensive evaluation model;

[0073] Input the data of the parameter database into the comprehensive evaluation model to obtain the theoretical monitoring data of the digital medical thermometer;

[0074] Collect sample data during the use of medical thermometers, substitute the sample data into the comprehensive evaluation model, and obtain the actual monitoring data of the current digital medical thermometer;

[0075] Based on machine learning algorithms (such as neural networks, etc.), a full life cycle management model for digital medical thermometers is established, and theoretical monitoring data and actual monitoring data are substituted into the full life cycle management model for model training;

[0076] According to the actual life cycle process obtained from the digital medical thermometer test data, the trained life cycle management model is revised to obtain a revised life cycle management model;

[0077] The revised life cycle management model is used to manage the digital medical thermometer throughout its life cycle, evaluate the quality of use throughout the entire process, and evaluate and grade the quality of use of the thermometer based on the various indicators obtained.

[0078] In a preferred embodiment of the present invention, a parameter database for the entire life cycle of a digital medical thermometer is constructed, specifically:

[0079] Create a parameter database that fully covers the entire life cycle of the thermometer. The parameter database is initialized when the thermometer is accepted and the information is associated with a unique factory number and management number.

[0080] The parameter database includes:

[0081] Basic information of the thermometer, including name, manufacturer, specification model, factory number, management number, production date, batch, expiration date, usage duration, and frequency of use;

[0082] Thermometer usage: temperature measurement method, department from which the thermometer was shipped, ward in which the thermometer was used, patient ID, gender, age, main disease type, DRG disease group, etc.

[0083] Record the maintenance and inspection data of the thermometer: factory number, management number, calibration point, standard temperature, indication temperature, indication error, inspection conditions (temperature, humidity), inspection time, etc.

[0084] In a preferred embodiment of the present invention, a product quality assessment model is constructed as follows:

[0085] Select brand, specification, model, usage duration or frequency of use as key features;

[0086] Use machine learning algorithms to build models based on key features:

[0087] f(a)=Ma1*Na1+Ma2*Na2+Ma3*Na3+Ma4*Na4

[0088] Among them, Ma1 represents brand weight and Na1 represents brand factor; Ma2 represents specification model weight and Na2 represents specification model factor; Ma3 represents usage time weight and Na3 represents usage time factor; Ma4 represents usage frequency weight and Na4 represents usage frequency factor.

[0089] Models are constructed based on factors such as the quality, usage time, and frequency of use of thermometers of different brands and specifications. Common thermometers on the market can be selected for testing and clinical application to obtain relevant data and conduct analysis. The analysis results are calculated and simulated through mathematical formulas, and the results are fitted to give the usage changes and attenuation laws of thermometer product quality, and a model for changes in thermometer quality during use is obtained, which can then be used to obtain quality evaluation levels and related values ​​for thermometers of different specifications.

[0090] In a preferred embodiment of the present invention, a model for evaluating the impact of clinical use factors on thermometer quality is constructed, specifically:

[0091] Select features from the parameter database: type of department that ships out, ward that uses, gender, age, and main disease type;

[0092] Build a model based on the selected features:

[0093] f(b)=Mb1*Nb1+Mb2*Nb2+Mb3*Nb3+Mb4*Nb4+Mb5*Nb5

[0094] Among them, Mb1 represents the department weight and Nb1 represents the department factor; Mb2 represents the ward weight and Nb2 represents the ward factor; Mb3 represents the gender weight and Nb3 represents the gender factor; Mb4 represents the age weight and Nb4 represents the age factor; Mb5 represents the disease type weight and Nb5 represents the disease type factor.

[0095] In practical applications, the quality of use of digital thermometers is evaluated. First, a special study is conducted on the factors affecting the clinical use quality of thermometers, including the use department, use ward, user characteristics, disease type, etc. Through the analysis of relevant usage data, a model of factors affecting the use quality of thermometers is established, and the impact results and evaluation values ​​of the use quality of thermometers under different factors are calculated based on the model.

[0096] In a preferred embodiment of the present invention, a model for evaluating the impact of management and maintenance results on the quality of thermometer use is constructed as follows:

[0097] Build a model based on the calibration test results, calibration test conditions, calibration times, and battery replacement data in the parameter database:

[0098] f(c)=Mc1*Nc1+Mc2*Nc2+Mc3*Nc3+Mc4*Nc4

[0099] Among them, Mc1 represents the weight of the calibration result, and Nc1 represents the calibration result factor; Mc2 represents the weight of the calibration detection condition, and Nc2 represents the calibration detection condition factor; Mc3 represents the weight of the calibration times, and Nc3 represents the gender factor; Mc4 represents the weight of the new battery use, and Nc4 represents the new battery use factor.

[0100] In practical applications, the management and maintenance results are used to evaluate the quality of digital thermometers. By combining the changing patterns of the digital thermometer's usage cycle with the regular inspection results, a model of the influence relationship between the regular calibration inspection results and the quality of thermometer usage is established to determine the relevant factors.

[0101] In a preferred embodiment of the present invention, the three monitoring object learning models are integrated to obtain a comprehensive evaluation model:

[0102] f=f(a)*f(b)*f(c)

[0103] Among them, f(a) is the product quality assessment result value, f(b) is the assessment result value of the impact of clinical use factors on the quality of the thermometer, f(c) is the assessment result value of the impact of management and maintenance results on the quality of thermometer use, and * represents the multiplication sign.

[0104] Preferably, the accuracy and generalization ability of the model are improved by adjusting model parameters and using ensemble learning methods.

[0105] In a preferred embodiment of the present invention, a method for establishing a full life cycle management model for a digital medical thermometer based on a machine learning algorithm is as follows:

[0106] Select machine learning algorithms (such as neural networks, support vector machines (SVM), decision trees, random forests, etc.) to build a full life cycle management model;

[0107] Preprocess the collected theoretical monitoring data and actual monitoring data, including data cleaning and data standardization, to ensure data quality and consistency;

[0108] Extract key features (such as product quality indicators, clinical use factors, maintenance and testing indicators, etc.) from the preprocessed data as input to the full life cycle management model;

[0109] Substitute the preprocessed feature data into the selected machine learning algorithm for model training. During the training process, the algorithm will automatically learn the relationship between the features and the quality of thermometer use and establish a corresponding model.

[0110] The trained model was validated using cross-validation and independent test datasets to ensure the accuracy and generalization ability of the model.

[0111] In a preferred embodiment of the present invention, the trained life cycle management model is corrected according to the actual life cycle process obtained from the test data of the digital medical thermometer to obtain a corrected life cycle management model, and the specific steps are as follows:

[0112] The test data of digital medical thermometers includes product information data, management information data, quality control and clinical application information of the thermometer throughout its life cycle;

[0113] Align actual usage data with theoretical monitoring data to ensure data accuracy and consistency. Adjust model parameters (such as weights, thresholds, etc.) based on deviations and anomalies found in actual usage data to improve the model's predictive performance;

[0114] The corrected parameters and actual usage data are re-substituted into the model for retraining to improve the accuracy and generalization ability of the model. The accuracy and generalization ability of the corrected model are verified through cross-validation and actual data testing to ensure that the model can accurately predict the performance of the thermometer in actual use.

[0115] In a preferred embodiment of the present invention, the levels are divided into:

[0116] According to the scope and distribution of evaluation indicators, formulate reasonable grading standards and divide the use quality of thermometers into excellent, good, general and poor grades;

[0117] According to the specific values ​​of the evaluation indicators, the temperature plan is divided into different levels:

[0118] Temperature programs with a quality score of more than 90 points are classified as excellent, those with a score of 70 to 89 points are classified as good, those with a score of 50 to 69 points are classified as fair, and those with a score of less than 50 points are classified as poor;

[0119] The results of thermometer use quality assessment and grading will be used to manage the clinical use of thermometers:

[0120] Thermometers with a score of 90 or above can be used normally; those with a score of 70-89 should have their measurement quality inspected more frequently; those with a score of 50-70 should be maintained; and those with a score below 50 are recommended to be eliminated.

[0121] The present invention also provides a usage quality assessment system for a digital medical thermometer throughout its life cycle, comprising a data acquisition unit and a processing unit, wherein the data acquisition unit is used to obtain parameter database information for the digital medical thermometer throughout its life cycle.

[0122] The input end of the processing unit is electrically connected to the output end of the data acquisition unit, and the processing unit executes the method of the present invention to evaluate the quality of use of the digital medical thermometer throughout its life cycle. The system uses the data acquisition unit and the processing unit to comprehensively collect thermometer parameters and conduct a quality evaluation to obtain a more comprehensive and accurate evaluation result.

[0123] The evaluation method of the present invention can truly reflect the performance of digital thermometers in actual use environments, cover performance changes during product use, and comprehensively evaluate the long-term stability and reliability of thermometers. By comprehensively considering factors such as user usage habits and maintenance, it can effectively distinguish the quality differences of thermometers of different brands and models in real-world use.

[0124] The present invention can monitor and evaluate the quality of thermometer use in real time, ensure the accuracy and reliability of the thermometer, thereby improving the quality of medical services and ensuring patient safety. The present invention is not only applicable to the quality evaluation of digital medical thermometers, but can also be extended to the quality management of other medical equipment, with good versatility and expansibility. The present invention actively responds to the national policy requirements for the quality management of medical equipment use, and helps promote the healthy development of the medical industry.

[0125] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0126] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A method for evaluating the quality of use of a digital medical thermometer throughout its life cycle, characterized in that: The steps include: Build a parameter database for the entire life cycle of digital medical thermometers; Based on the parameter database, a monitoring object learning model is constructed, including: product quality assessment model, clinical use factor impact assessment model on thermometer quality, and management and maintenance result impact assessment model on thermometer use quality; The three monitoring object learning models are integrated to obtain a comprehensive evaluation model; Input the data of the parameter database into the comprehensive evaluation model to obtain the theoretical monitoring data of the digital medical thermometer; Collect sample data during the use of medical thermometers, substitute the sample data into the comprehensive evaluation model, and obtain the actual monitoring data of the current digital medical thermometer; Based on the machine learning algorithm, a full life cycle management model for digital medical thermometers is established, and the theoretical monitoring data and actual monitoring data are substituted into the full life cycle management model for model training; according to the actual full life cycle process obtained from the test data of the digital medical thermometer, the trained full life cycle management model is revised to obtain a revised full life cycle management model; The revised life cycle management model is used to manage the digital medical thermometer throughout its life cycle, evaluate the quality of use throughout the entire process, and evaluate and grade the quality of use of the thermometer based on the various indicators obtained.

2. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 1, characterized in that: Construct a parameter database for the entire life cycle of a digital medical thermometer, specifically: Create a parameter database that fully covers the entire life cycle of the thermometer. The parameter database is initialized when the thermometer is accepted and the information is associated with a unique factory number and management number. The parameter database includes: The name, manufacturer, specification model, factory number, management number, production date, batch, expiration date, usage duration, and frequency of use of the thermometer; Thermometer usage: temperature measurement method, department from which the thermometer was shipped, ward of use, patient ID, gender, age, main disease type, and DRG disease group; Record the maintenance and inspection data of the thermometer: factory number, management number, calibration point, standard temperature, indication temperature, indication error, inspection conditions, and inspection time.

3. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 1, characterized in that: Construct product quality assessment model for: Select brand, specification, model, usage duration or frequency of use as key features; Use machine learning algorithms to build models based on key features: f(a)=Ma1*Na1+Ma2*Na2+Ma3*Na3+Ma4*Na4 Among them, Ma1 represents brand weight and Na1 represents brand factor; Ma2 represents the specification model weight, and Na2 represents the specification model factor; Ma3 represents the usage time weight, and Na3 represents the usage time factor; Ma4 represents the usage frequency weight, and Na4 represents the usage frequency factor.

4. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 1, characterized in that: Construct an evaluation model for the impact of clinical use factors on thermometer quality, specifically: Select features from the parameter database: type of department that ships out, ward that uses, gender, age, and main disease type; Build a model based on the selected features: f(b)=Mb1*Nb1+Mb2*Nb2+Mb3*Nb3+Mb4*Nb4+Mb5*Nb5 Among them, Mb1 represents the department weight and Nb1 represents the department factor; Mb2 represents the ward weight and Nb2 represents the ward factor; Mb3 represents the gender weight and Nb3 represents the gender factor; Mb4 represents the age weight and Nb4 represents the age factor; Mb5 represents the disease type weight and Nb5 represents the disease type factor.

5. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 1, characterized in that: Construct an assessment model of the impact of management and maintenance results on the quality of thermometer use, as follows: Build a model based on the calibration test results, calibration test conditions, calibration times, and battery replacement data in the parameter database: f(c)=Mc1*Nc1+Mc2*Nc2+Mc3*Nc3+Mc4*Nc4 Among them, Mc1 represents the weight of the calibration result, and Nc1 represents the calibration result factor; Mc2 represents the weight of the calibration detection condition, and Nc2 represents the calibration detection condition factor; Mc3 represents the weight of the calibration times, and Nc3 represents the gender factor; Mc4 represents the weight of the new battery use, and Nc4 represents the new battery use factor.

6. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 1, characterized in that: The three monitoring object learning models are integrated to obtain the comprehensive evaluation model: f=f(a)*f(b)*f(c) Among them, f(a) is the product quality assessment result value, f(b) is the assessment result value of the impact of clinical use factors on the quality of the thermometer, f(c) is the assessment result value of the impact of management and maintenance results on the quality of thermometer use, and * represents the multiplication sign.

7. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 1, characterized in that: Based on the machine learning algorithm, the method of establishing a full life cycle management model for digital medical thermometers is as follows: Select machine learning algorithms to build a full life cycle management model; Preprocess the collected theoretical monitoring data and actual monitoring data, including data cleaning and data standardization, to ensure data quality and consistency; Extract key features from preprocessed data as input to the full life cycle management model; Substitute the preprocessed feature data into the selected machine learning algorithm for model training. During the training process, the algorithm will automatically learn the relationship between the features and the quality of thermometer use and establish a corresponding model. The trained model was validated using cross-validation and independent test datasets to ensure the accuracy and generalization ability of the model.

8. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 7, characterized in that: According to the actual life cycle process obtained from the test data of the digital medical thermometer, the trained life cycle management model is revised to obtain the revised life cycle management model. The specific steps are as follows: The test data of digital medical thermometers includes product information data, management information data, quality control and clinical application information of the thermometer throughout its life cycle; Align actual usage data with theoretical monitoring data and adjust the model parameters based on deviations and anomalies found in the actual usage data; The corrected parameters and actual usage data are re-substituted into the model for retraining, and the accuracy and generalization ability of the corrected model are verified through cross-validation and actual data testing to ensure that the model can accurately predict the performance of the thermometer in actual use.

9. The method for evaluating the quality of use of a digital medical thermometer throughout its life cycle as claimed in claim 8, characterized in that: Classification: According to the scope and distribution of evaluation indicators, formulate reasonable grading standards and divide the use quality of thermometers into excellent, good, general and poor grades; According to the specific values ​​of the evaluation indicators, the temperature plan is divided into different levels: Temperature programs with a quality score of more than 90 points are classified as excellent, those with a score of 70 to 89 points are classified as good, those with a score of 50 to 69 points are classified as fair, and those with a score of less than 50 points are classified as poor; The results of thermometer use quality assessment and grading will be used to manage the clinical use of thermometers: Thermometers with a score of 90 or above can be used normally; those with a score of 70-89 should have their measurement quality inspected more frequently; those with a score of 50-70 should be maintained; and those with a score below 50 are recommended to be eliminated.

10. A digital medical thermometer full life cycle quality assessment system, characterized in that: It includes a data acquisition unit and a processing unit, wherein the data acquisition unit is used to obtain parameter database information of the digital medical thermometer throughout its life cycle; The input end of the processing unit is connected to the output end of the data acquisition unit, and the processing unit executes the method described in one of claims 1-9 to evaluate the quality of use of the digital medical thermometer throughout its life cycle.

Images