CN112274741A - Method for judging expected effect by respiratory support equipment and respiratory support equipment - Google Patents
Method for judging expected effect by respiratory support equipment and respiratory support equipment Download PDFInfo
- Publication number
- CN112274741A CN112274741A CN202010961481.8A CN202010961481A CN112274741A CN 112274741 A CN112274741 A CN 112274741A CN 202010961481 A CN202010961481 A CN 202010961481A CN 112274741 A CN112274741 A CN 112274741A
- Authority
- CN
- China
- Prior art keywords
- training
- invasive treatment
- data
- expected effect
- judging
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000000241 respiratory effect Effects 0.000 title claims abstract description 37
- 230000003631 expected effect Effects 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 230000000694 effects Effects 0.000 claims abstract description 11
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 53
- 206010066901 Treatment failure Diseases 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 10
- 238000003066 decision tree Methods 0.000 claims description 9
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 8
- 239000008280 blood Substances 0.000 claims description 8
- 210000004369 blood Anatomy 0.000 claims description 8
- 229910052760 oxygen Inorganic materials 0.000 claims description 8
- 239000001301 oxygen Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000036387 respiratory rate Effects 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 230000035487 diastolic blood pressure Effects 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 230000035488 systolic blood pressure Effects 0.000 claims description 4
- 230000036760 body temperature Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 7
- 238000010219 correlation analysis Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 206010012601 diabetes mellitus Diseases 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000036391 respiratory frequency Effects 0.000 description 1
- 208000023504 respiratory system disease Diseases 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M16/00—Devices for influencing the respiratory system of patients by gas treatment, e.g. mouth-to-mouth respiration; Tracheal tubes
Landscapes
- Health & Medical Sciences (AREA)
- Emergency Medicine (AREA)
- Pulmonology (AREA)
- Engineering & Computer Science (AREA)
- Anesthesiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Hematology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to a method for judging an expected effect by a respiration support device and the respiration support device. A method of determining an expected effect for a respiratory support apparatus, comprising the steps of: s1, obtaining basic sign data of a user, wherein the basic sign data at least comprises basic characteristics, medical history characteristics and detection data; and S2, comprehensively judging the basic sign data by using a judgment network model, and determining the expected effect of the non-invasive treatment. The method for judging the expected effect is based on the multi-feature and multi-sample basic sign data set, obtains the expected effect of the non-invasive treatment through the screening and judging of the judging network model, can analyze the effect of the non-invasive treatment by controlling the comprehensive condition, and has the accuracy rate of more than 90%.
Description
Technical Field
The present invention relates to electronic devices, and more particularly, to a method for determining an expected effect of a respiratory support device and a respiratory support device.
Background
Noninvasive ventilator although the invention is relatively late with respect to invasive ventilators, treatment with noninvasive ventilators is the preferred method for patients with less symptoms of respiratory disease. However, when the symptoms of patients get worse, how to switch to invasive treatment at proper time is always a key topic of clinical attention. At present, medical staff analyze the concerned indexes according to past experience based on related monitoring indexes (such as PaCO2 indexes) so as to judge the invasive treatment time. However, the prior art has the following disadvantages: (1) the subjectivity is strong: the factors of non-invasive treatment failure are many, the age, basic diseases, clinical monitoring indexes and the like of a patient can influence the non-invasive treatment result, medical staff analyzes according to the past experience, the effect is difficult to judge due to the common influence of a plurality of factors, and the judgment result is possibly different if the indexes of subjective attention of the medical staff are different. (2) The accumulation time is longer: the method requires years of clinical experience accumulation.
Patent document No. CN201780068395.0 discloses an early warning scoring system and method. The system comprises: a computing device, a plurality of sensors for acquiring physiological signals from a patient, wherein the sensors are functionally connected to the computing device, and at least one alarm adapted to output an alarm when an Early Warning Score (EWS) exceeds a predetermined level. The computing device receives the physiological signal from the sensor, analyzes the physiological signal, and calculates an early warning score based on the analyzed signal, and compares the early warning score to a predetermined limit, and if the score is outside the limit, triggers an alarm or initiates or modifies a therapy or medical intervention. The above problems have not yet been solved.
Therefore, the existing noninvasive treatment technology has defects and needs to be improved.
Disclosure of Invention
In view of the above-mentioned disadvantages of the prior art, it is an object of the present invention to provide a method for determining a desired effect of a respiratory support apparatus and a respiratory support apparatus, which can solve the technical problems mentioned in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method of determining an expected effect for a respiratory support apparatus, comprising the steps of:
s1, obtaining basic sign data of a user, wherein the basic sign data at least comprises basic characteristics, medical history characteristics and detection data;
and S2, comprehensively judging the basic sign data by using a judgment network model, and determining the expected effect of the non-invasive treatment.
Preferably, the method for judging the expected effect by the respiratory support apparatus, wherein the judgment network model is obtained by training an algorithm model, and the training steps are as follows:
s01, collecting training data including basic sign data and carrying out label calibration to form a training database;
s02, dividing all training data in the training database into a training set and a test set according to a preset proportion;
s03, training the algorithm model by using a training set, and testing through the test set to obtain an evaluation index;
s04, judging whether the evaluation index is larger than a set value, if so, outputting to obtain a judgment network model; if not, step S02 is executed.
Preferably, the method for judging the expected effect by the respiratory support equipment comprises a logistic regression model, a support vector classification model, a neural network model and a decision tree model.
Preferably, the respiratory support apparatus determines the expected effect method, and the label content comprises noninvasive treatment failure, noninvasive treatment success and unknown result; in generating the training database:
respectively forming a non-invasive treatment failure database, a non-invasive treatment success database and an unknown result database.
Preferably, the respiratory support apparatus determines the expected effect method, and performs steps S02-S04 for different training databases.
Preferably, the respiratory support apparatus determines the expected effect method, and the expected effect of the non-invasive treatment is a probability value of the failure of the non-invasive treatment; the method further comprises the steps of:
s3, judging whether the non-invasive treatment failure probability value is larger than a set failure threshold value, if so, judging that the failure risk is too high, and giving an alarm to the outside; and if not, displaying the failure probability value.
Preferably, the respiratory support apparatus determines the expected effect method, and the detection data includes a volumeTemperature, diastolic pressure, systolic pressure, respiratory rate, heart rate, CO2Partial pressure, O2Partial pressure, blood pH, blood oxygen concentration, oxygen fraction FiO in inhaled air2。
Preferably, the respiratory support apparatus determines a desired effect method, and the respiratory support apparatus acquires the updated value of the detection data in real time, and the method further includes:
when the amount of change in any one of the pieces of detection data is larger than the corresponding change threshold, step S1 is performed.
A computer readable medium storing computer software which, when executed by a processor, enables the method of determining a desired effect in a respiratory support apparatus.
A respiratory support apparatus comprising an input module, a processing module and an output module; the processing module is used for combining the input data of the input module to realize the method for judging the expected effect by the respiratory support equipment, and simultaneously, the output module is used for outputting the result.
Compared with the prior art, the method for judging the expected effect by the respiratory support equipment and the respiratory support equipment have the following beneficial effects:
the method for judging the expected effect is based on the multi-feature and multi-sample basic sign data set, obtains the expected effect of the non-invasive treatment through the screening and judging of the judging network model, can analyze the effect of the non-invasive treatment by controlling the comprehensive condition, and has the accuracy rate of more than 90%.
Drawings
FIG. 1 is a flow chart of a method for determining expected effects provided by the present invention;
FIG. 2 is a flow chart of decision network model training provided by the present invention;
FIG. 3 is a histogram of the correlation analysis between respiratory rate and the probability of non-invasive treatment failure provided by the present invention;
fig. 4 is a block diagram of a respiratory support apparatus according to the present invention.
Detailed Description
In order to make the objects, technical solutions and effects of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1-2, the present invention provides a method for determining a desired effect of a respiratory support apparatus, comprising the steps of:
s1, obtaining basic sign data of a user, wherein the basic sign data at least comprises basic characteristics, medical history characteristics and detection data;
specifically, the basic sign data of the user is collected through clinical, wherein the basic signs data include but are not limited to gender and age, the medical history characteristics include but are not limited to the diagnosis disease, the high blood pressure history, the diabetes history, the cerebrovascular disease history and the high risk disease history, and the detection data include but are not limited to body temperature, diastolic pressure, systolic pressure, respiratory rate, heart rate, CO2Partial pressure, O2Partial pressure, blood pH, blood oxygen concentration, oxygen fraction FiO in inhaled air2Of course, the detected data is also updated in real time, so that the initial set value can be directly replaced by the data only with a slight change, and the basic physical sign data of the user can be determined in real time. In the existing judgment, an empirical judgment method is mainly used for determining whether the noninvasive ventilator is suitable for treatment, and probability values obtained by respectively carrying out related judgment on success probability aiming at different physical sign data cannot be comprehensively judged and have no system, so that the method has great uncertainty. Correspondingly, the respiration support equipment for realizing the steps also has a corresponding detection function, if the respiration support equipment is not accompanied by the corresponding detection function, the external equipment can be used for realizing the detection and the update of corresponding data, and meanwhile, the data can be updated in a manual input mode.
And S2, comprehensively judging the basic sign data by using a judgment network model, and determining the expected effect of the non-invasive treatment.
Specifically, the judgment network model is obtained by training based on a network model with learning ability commonly used in the field, and the data used for training has the basic sign data, so that the expected effect can be comprehensively evaluated, and adverse consequences caused by missing evaluation can be avoided. Of course, in the evaluation process, a part of the basic sign data is subjected to refined evaluation, for example, for the history of diabetes, refined analysis of like risks is performed for different levels of diabetes, and the evaluation is more comprehensive and detailed. Preferably, the respiratory support apparatus is a non-invasive respiratory support apparatus.
As a preferred scheme, in this embodiment, the decision network model is obtained by training an algorithm model, and the training steps are as follows:
s01, collecting training data including basic sign data and carrying out label calibration to form a training database; specifically, the training data is preferably from a medical record library, and is subjected to targeted extraction, wherein the extraction standard includes all relevant data in the basic feature data; when calibration is performed, in this embodiment, the label content includes non-invasive treatment failure (e.g., calibration in the case that the patient dies directly, the patient is intubated after disease deterioration, the patient is discharged from the hospital but the prognosis is poor, etc.), non-invasive treatment success (e.g., calibration in the case that the patient is discharged successfully, etc.), and unknown result (e.g., medical staff cannot know follow-up conditions because the patient is discharged forcibly); in generating the training database: respectively forming a non-invasive treatment failure database, a non-invasive treatment success database and an unknown result database. Of course, in specific use, the training data calibrated as unknown results takes up less, and the database of unknown results is not effective enough to be deleted in subsequent analysis.
S02, dividing all training data in the training database into a training set and a test set according to a preset proportion; specifically, the training set accounts for 60% -80% of the corresponding database, the rest is the test set, and the predetermined proportion is preferably the training set: test set 8:2 (i.e. the training set is 80%); of course, since there may be a plurality of databases participating in the training (for example, two databases, i.e., a non-invasive treatment success database and a non-invasive treatment failure database, respectively), at this time, the corresponding training databases are respectively split and respectively put into training; of course, it is also possible to summarize all training data into one database for training without distinction, but to ensure that the training data calibrated as non-invasive treatment failure and non-invasive treatment success are relatively balanced, for example, the quantitative ratio may be: non-invasive treatment failure data: the data of success of noninvasive treatment is 1.2:1, and the ratio is similar to the above ratio, and is not particularly limited to be close to 1:1 optimal. Certainly, in further implementation, before training the algorithm model, preliminary screening between data and non-invasive treatment failure is required, and of course, the preliminary screening generally performs correlation analysis on a certain item of data to preliminarily determine the cause of the non-invasive treatment failure, for example, as shown in fig. 3, it is a correlation analysis histogram between respiratory frequency and non-invasive treatment failure probability, and other items of data requiring correlation analysis are analyzed in the same map manner, which is not described herein again.
S03, training the algorithm model by using a training set, and testing through the test set to obtain an evaluation index; the specific evaluation index is the test accuracy of the algorithm model.
S04, judging whether the evaluation index is larger than a set value, if so, outputting to obtain a judgment network model; if not, step S02 is executed. Specifically, the training process of the algorithm model in this step is not described in detail, and a training mode commonly used in the art is used, that is, corresponding training data is input, internal parameters of the algorithm model are adjusted, and after the algorithm model is run for a plurality of times, the test set is used for verification, if the evaluation index reaches a high level (for example, the accuracy reaches 95%, and the evaluation accuracy in the noninvasive treatment failure database reaches 90%), the evaluation index is proved to be high, and the learned algorithm model can be determined to meet the identification standard. Preferably, the algorithm model includes a logistic regression model (LR algorithm), a support vector classification model (SVC algorithm), a neural network model (BP algorithm), a decision tree model (XGboost algorithm, GBDT algorithm, Lightgbm algorithm). Network data adjustment adaptive to different algorithm models is used; for example, in the embodiment, it is preferable that the Lightgbm algorithm model is trained by using training data, a core algorithm of the Lightgbm algorithm model is developed from a Decision Tree, and compared with other Decision Tree (such as GBDT) algorithms, the Lightgbm algorithm model has the characteristics of "low memory, high operating efficiency, higher accuracy, parallelization operation" and the like, and a core improvement point thereof is that the Decision Tree is generated based on a leaf-wise policy, but an overfitting risk needs to be focused on, and for an algorithm for generating the Decision Tree, reference may be made to a paper "Lightgbm: a high efficiency Efficient knowledge Gradient Boosting Decision Tree". In the invention, the key parameters can be initialized: the learning rate (learning _ rate) can be set to 0.1, the tree depth (max _ depth) can be set to 4, the number of leaf nodes (num _ leaves) can be set to 8, the number of toolboxes (max _ bin) can be set to 50, and other parameters can be modified and refined according to actual conditions. After training by using the training step, obtaining a corresponding Lightgbm judgment network model; if other algorithm models are used for construction, the steps are similar, and different decision network models are generated, such as an LR decision network model and a BP decision network model. Preferably, the set value is 85% to 95%, and more preferably 90%.
Preferably, in this embodiment, the algorithm model includes a logistic regression model (LR algorithm), a support vector classification model (SVC algorithm), a neural network model (BP algorithm), and a decision tree model (XGboost algorithm, GBDT algorithm, Lightgbm algorithm). Preferably, in this embodiment, the steps S02-S04 are performed for different training databases, so that different decision network models can be obtained. In particular implementations, the decision network model that refers to the early warning analysis is one or more of: the LR judgment network model, the BP judgment network model and the Lightgbm judgment network model can be used for analysis respectively, or the first three (if other judgment network models exist, a plurality of judgment network models can be used) judgment network models can be used for combined analysis; in the joint analysis, it may be set that, as long as there is a high risk in determining the determination result of the network model, it is determined that the noninvasive ventilator cannot be used for treatment, or other design schemes may be used.
Preferably, in this embodiment, the expected effect of the non-invasive treatment is a probability value of failure of the non-invasive treatment; the method further comprises the steps of:
s3, judging whether the non-invasive treatment failure probability value is larger than a set failure threshold value, if so, judging that the failure risk is too high, and giving an alarm to the outside; and if not, displaying the failure probability value. Preferably, the failure threshold is preferably 30% to 70%, and more preferably 50%. In the further judgment process, not only the corresponding failure probability value but also the success probability value are correspondingly output, and the comprehensive analysis between the failure probability value and the success probability value is carried out to give reference to doctors or family members.
Preferably, in this embodiment, the detection data includes body temperature, diastolic pressure, systolic pressure, respiratory rate, heart rate, and CO2Partial pressure, O2Partial pressure, blood pH, blood oxygen concentration, oxygen fraction FiO in inhaled air2。
Preferably, in this embodiment, the respiratory support apparatus obtains the updated value of the detection data in real time, and the method further includes:
when the amount of change in any one of the pieces of detection data is larger than the corresponding change threshold, step S1 is performed. Preferably, the change threshold is a change ratio of a certain data, and the change ratio is preferably 3% to 10%, and more preferably 5%.
Accordingly, the present invention also provides a computer readable medium storing computer software which, when executed by a processor, enables the method of determining an intended effect by a respiratory support apparatus. In a specific implementation, the medium may exist separately, and the method for determining the expected effect may be implemented by connecting the medium with a corresponding configuration device; or attached to a corresponding respiratory support device and executed by a processor therein to implement a corresponding method of determining the desired effect.
Referring to fig. 4, correspondingly, the present invention further provides a respiratory support apparatus, including an input module, a processing module and an output module; the processing module is used for combining the input data of the input module to realize the method for judging the expected effect by the respiratory support equipment, and simultaneously, the output module is used for outputting the result. The input module realizes the input of basic sign data and the real-time detection and update of corresponding detection data, and sends all the data to the processing module; the output module realizes direct display of the judgment result, including but not limited to text display, color display, light display and the like.
It should be understood that equivalents and modifications of the technical solution and inventive concept thereof may occur to those skilled in the art, and all such modifications and alterations should fall within the scope of the appended claims.
Claims (10)
1. A method of determining an expected effect for a respiratory support apparatus, comprising the steps of:
s1, obtaining basic sign data of a user, wherein the basic sign data at least comprises basic characteristics, medical history characteristics and detection data;
and S2, comprehensively judging the basic sign data by using a judgment network model, and determining the expected effect of the non-invasive treatment.
2. The method of claim 1, wherein the decision network model is trained using an algorithmic model, the training steps comprising:
s01, collecting training data including basic sign data and carrying out label calibration to form a training database;
s02, dividing all training data in the training database into a training set and a test set according to a preset proportion;
s03, training the algorithm model by using a training set, and testing through the test set to obtain an evaluation index;
s04, judging whether the evaluation index is larger than a set value, if so, outputting to obtain a judgment network model; if not, step S02 is executed.
3. The method of claim 2, wherein the algorithmic model comprises a logistic regression model, a support vector classification model, a neural network model, a decision tree model.
4. The method of claim 2, wherein the label content includes non-invasive treatment failure, non-invasive treatment success, and unknown outcome; in generating the training database:
respectively forming a non-invasive treatment failure database, a non-invasive treatment success database and an unknown result database.
5. The method of claim 4, wherein the steps S02-S04 are performed separately for different training databases.
6. The method of determining an expected effect by a respiratory support apparatus of claim 4, wherein the expected effect of the non-invasive treatment is a probability value of failure of the non-invasive treatment; the method further comprises the steps of:
s3, judging whether the non-invasive treatment failure probability value is larger than a set failure threshold value, if so, judging that the failure risk is too high, and giving an alarm to the outside; and if not, displaying the failure probability value.
7. The method of claim 1, wherein the sensed data includes body temperature, diastolic pressure, systolic pressure, respiratory rate, heart rate, CO2Partial pressure, O2Partial pressure, blood pH, blood oxygen concentration, oxygen fraction FiO in inhaled air2。
8. The method of claim 7, wherein the respiratory support apparatus obtains the update of the sensed data in real time, the method further comprising:
when the amount of change in any one of the pieces of detection data is larger than the corresponding change threshold, step S1 is performed.
9. A computer readable medium having stored thereon computer software which, when executed by a processor, is capable of implementing the method of determining a desired effect in a respiratory support apparatus according to any one of claims 1 to 8.
10. A respiratory support apparatus comprising an input module, a processing module, and an output module; the processing module is used for combining the input data of the input module to realize the method for judging the expected effect of the respiration support equipment according to any one of claims 1-8, and simultaneously outputting the result by using the output module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010961481.8A CN112274741A (en) | 2020-09-14 | 2020-09-14 | Method for judging expected effect by respiratory support equipment and respiratory support equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010961481.8A CN112274741A (en) | 2020-09-14 | 2020-09-14 | Method for judging expected effect by respiratory support equipment and respiratory support equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112274741A true CN112274741A (en) | 2021-01-29 |
Family
ID=74420881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010961481.8A Pending CN112274741A (en) | 2020-09-14 | 2020-09-14 | Method for judging expected effect by respiratory support equipment and respiratory support equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112274741A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113599647A (en) * | 2021-08-18 | 2021-11-05 | 深圳先进技术研究院 | Ventilation mode matching method and device for mechanical ventilation of respirator and related equipment |
| CN113782210A (en) * | 2021-09-14 | 2021-12-10 | 湖南明康中锦医疗科技发展有限公司 | Method for predicting treatment failure probability of noninvasive ventilator |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110732068A (en) * | 2019-11-14 | 2020-01-31 | 北华大学 | cloud platform-based respiratory state prediction method |
-
2020
- 2020-09-14 CN CN202010961481.8A patent/CN112274741A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110732068A (en) * | 2019-11-14 | 2020-01-31 | 北华大学 | cloud platform-based respiratory state prediction method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113599647A (en) * | 2021-08-18 | 2021-11-05 | 深圳先进技术研究院 | Ventilation mode matching method and device for mechanical ventilation of respirator and related equipment |
| CN113599647B (en) * | 2021-08-18 | 2024-02-13 | 深圳先进技术研究院 | Ventilation pattern matching method, device and related equipment for mechanical ventilation of breathing machine |
| CN113782210A (en) * | 2021-09-14 | 2021-12-10 | 湖南明康中锦医疗科技发展有限公司 | Method for predicting treatment failure probability of noninvasive ventilator |
| CN113782210B (en) * | 2021-09-14 | 2024-04-12 | 湖南明康中锦医疗科技发展有限公司 | Method for predicting treatment failure probability of noninvasive ventilator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110459328B (en) | Clinical monitoring equipment | |
| WO2020181805A1 (en) | Diabetes prediction method and apparatus, storage medium, and computer device | |
| CN111986784B (en) | Metadata prediction device and method for medical image | |
| CN107436993B (en) | Method and server for establishing ICU patient condition evaluation model | |
| CN111080643A (en) | Method and device for classifying diabetes and related diseases based on fundus images | |
| CN112274741A (en) | Method for judging expected effect by respiratory support equipment and respiratory support equipment | |
| Casal et al. | Classifying sleep–wake stages through recurrent neural networks using pulse oximetry signals | |
| JP2023527001A (en) | Method and system for personalized risk score analysis | |
| WO2021184802A1 (en) | Blood pressure classification prediction method and apparatus | |
| Ossai et al. | Intelligent decision support with machine learning for efficient management of mechanical ventilation in the intensive care unit–A critical overview | |
| JP2022508221A (en) | Prediction of critical alarm | |
| CN112183572A (en) | Method and device for generating prediction model for predicting pneumonia severity | |
| Islam et al. | Predictive analysis for risk of stroke using machine learning techniques | |
| CN112542242A (en) | Data transformation/symptom scoring | |
| CN113744865B (en) | Regression analysis-based pressure damage risk prediction model correction method | |
| CN111047590A (en) | Hypertension classification method and device based on fundus images | |
| CN115024725A (en) | Tumor treatment aid decision-making system integrating psychological state multi-parameter detection | |
| CN108109696B (en) | Data processing method and device | |
| Srimedha et al. | A comprehensive machine learning based pipeline for an accurate early prediction of sepsis in ICU | |
| KR20210112041A (en) | Smart Healthcare Monitoring System and Method for Heart Disease Prediction Based On Ensemble Deep Learning and Feature Fusion | |
| CN116664966A (en) | Infrared image processing system | |
| CN115273176A (en) | Pain multi-algorithm objective assessment method based on vital signs and expressions | |
| Paetz et al. | A neuro-fuzzy based alarm system for septic shock patients with a comparison to medical scores | |
| US20210225517A1 (en) | Predictive model for adverse patient outcomes | |
| CN113178254A (en) | Intelligent medical data analysis method and device based on 5G and computer equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210129 |
|
| RJ01 | Rejection of invention patent application after publication |