CN114822827B - System and method for predicting acute exacerbation of chronic obstructive pulmonary disease - Google Patents
System and method for predicting acute exacerbation of chronic obstructive pulmonary disease Download PDFInfo
- Publication number
- CN114822827B CN114822827B CN202210597499.3A CN202210597499A CN114822827B CN 114822827 B CN114822827 B CN 114822827B CN 202210597499 A CN202210597499 A CN 202210597499A CN 114822827 B CN114822827 B CN 114822827B
- Authority
- CN
- China
- Prior art keywords
- aecopd
- prediction
- module
- mir
- logistic regression
- 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
Images
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
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention relates to a prediction system and a prediction method for Acute Exacerbation of Chronic Obstructive Pulmonary Disease (AECOPD), wherein the prediction system comprises a detection module, a model building module and a prediction module; the detection module is used for detecting one or more of MiR-1258, NEU, CRP, NLR, LDH, PCT and WBC; the model building module is used for building an AECOPD prediction model based on the detection result of the detection module and by using a machine learning method; the prediction module is used for obtaining the probability of the AECOPD of the patient according to the AECOPD prediction model and the detection result of the detection module.
Description
Technical Field
The invention relates to the technical field of auxiliary medical treatment, in particular to a system and a method for predicting acute exacerbation of chronic obstructive pulmonary disease.
Background
Acute exacerbation of chronic obstructive pulmonary disease (acute exacerbations of chronic obstructive pulmonary disease, AECOPD) is one of the common complications of chronic obstructive pulmonary disease (chronic obstructive pulmonary disease, COPD) patients, with high mortality, and early identification and prediction of the occurrence of AECOPD from COPD patients is of great importance. However, current methods of identification of AECOPD are largely based on patient clinical symptoms and signs of change. The existing identification method meets the following criteria: (1) At least two of the three complications (sputum volume, suppuration and dyspnea); (2) At least one of the main symptoms (cold: runny nose and/or nasal obstruction, asthma and sore throat) and one of the secondary symptoms (cough and fever > 37.5 ℃) worsen, with the exception of other etiologies.
The prior art methods of predicting the appearance of AECOPD in patients based on clinical symptoms and signs lack objectivity and it is difficult to quickly and accurately identify AECOPD by symptoms alone, as many other diseases may also present similar symptoms. There are no biomarkers and relevant laboratory predictive models with good sensitivity and specificity for AECOPD prediction. Clinically common infection-related biomarkers, such as white blood cell count (WBC), lactate Dehydrogenase (LDH), neutrophil count (NEU), C-reactive protein (CRP), procalcitonin (PCT), although it can predict infection-induced AECOPD to some extent, considering the diversity of AECOPD etiology, the specificity and sensitivity of these indicators are currently poor, and the results of the team of the present inventors indicate that CRP predicts efficacy of AECOPD (area under the subject's working curve) of only 0.635, and sensitivity of only 42.42%; PCT has a prediction efficiency of only 0.663, a sensitivity of only 30.3%, and a prediction effect is not ideal. Therefore, the biomarker capable of accurately predicting the AECOPD is searched, and the establishment of the related prediction model has a good application prospect.
Disclosure of Invention
The invention aims to provide a system and a method for predicting acute exacerbation of chronic obstructive pulmonary disease, and aims to solve the technical problems of at least predicting the probability of AECOPD of a patient in advance.
In order to achieve the above object, the present invention provides a system for predicting acute exacerbation of chronic obstructive pulmonary disease, comprising a detection module, a model building module and a prediction module; the detection module is used for detecting one or more of MiR-1258, NEU, CRP, NLR, LDH, PCT and WBC; the model building module is used for building an AECOPD prediction model by using a machine learning method based on the detection result of the detection module; the prediction module is used for obtaining the probability of the AECOPD of the patient according to the AECOPD prediction model and the detection result of the detection module.
Preferably, the AECOPD prediction model is a support vector machine, a random forest, a gradient propulsion classifier, K nearest neighbors (K nearest neighbor algorithm), an artificial neuron network, a Gaussian
Bayes (naive Gao Sibei phylls model) or logistic regression (logistic regression) model.
Preferably, the model building module screens out effective characteristic variables with predictive value for AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP; the prediction module obtains the probability of the patient to generate AECOPD according to a Logistic regression equation, wherein the Logistic regression equation is as follows:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR-1258 is the expression of MiR-1258 in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
The chronic obstructive pulmonary disease acute exacerbation prediction system also comprises a decision tree establishment module, which is used for establishing a decision tree according to the selected index through logistic regression model verification.
Preferably, the chronic obstructive pulmonary disease acute exacerbation prediction system further comprises a verification module for evaluating the validity of the AECOPD prediction model by using a 5-fold cross-validation method.
Further preferably, CRP and LDH detection is performed using Beckmann Coulter AU2700 latex immunonephelometry kit.
Preferably, said PCT is detected using rogowski E401.
Further preferably, the detection module uses a full-automatic blood analyzer of the hson mecamylum 9000 for white blood cell count and sort count.
Further preferably, the detection module extracts exosomes by using an ultra-high speed centrifugation method, identifies exosomes by using an electron microscope, a Western blot and an exosome particle size analyzer, extracts sample RNA by using a TRIZOL reagent, and detects MiR-1258 by using an ABI 7500PCR amplification instrument.
The invention also provides a method for predicting acute exacerbation of chronic obstructive pulmonary disease, which comprises the following steps:
firstly, screening effective characteristic variables with predictive value for AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP;
secondly, obtaining the probability of the patient to generate AECOPD according to a Logistic regression equation, wherein the Logistic regression equation is as follows:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR-1258 is the expression of MiR-1258 in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
Advantageous effects
Compared with the prior art, the invention has the beneficial effects that:
according to the chronic obstructive pulmonary disease acute exacerbation prediction system and the prediction method, the exosome MiR-1258 is screened out, the occurrence of AECOPD can be effectively predicted, 7 AECOPD prediction models are established by utilizing a machine learning method based on blood biomarkers, a Logistic regression model with the optimal AECOPD prediction effect is obtained, a Logistic regression equation is established, the prediction of the AECOPD occurrence probability is used, an AECOPD prediction decision tree is established based on the exosome MiR-1258, NEU and NLR, the discrimination capability of the AECOPD is further improved, the AECOPD occurrence probability is accurately quantized by the establishment equation, and the defects of the existing AECOPD prediction method are well overcome.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate and do not limit the invention.
FIG. 1 is a schematic representation of the expression levels of MiR-1258 in serum and exosomes in different populations.
Figure 2 is a schematic representation of ROC analysis of exosome MiR-1258 and conventional laboratory indicators for COPD and AECOPD discriminatory power assessment.
FIGS. 3A and 3B are schematic diagrams of decision trees identifying AECOPD based on exosomes MiR-1258, NLR and/or neutrophil counts, wherein FIG. 3A is a representation of the identification of AECOPD from a normal control; fig. 3B is the identification of AECOPD from the SCOPD.
Fig. 4 is a schematic structural diagram of a chronic obstructive pulmonary disease acute exacerbation prediction system according to the present invention.
Detailed Description
The present invention is described in more detail below to facilitate an understanding of the present invention.
In order to predict in advance the probability of a patient developing AECOPD, it is necessary to find biomarkers that can effectively predict AECOPD and to build a biomarker-based AECOPD prediction model.
The inventor of the invention researches and discovers that MiR-1258 in exosomes has better efficacy (sensitivity is 74.24%, specificity is up to 97.62%, and area under the working curve (AUC) of a subject is 0.851, which is obviously higher than traditional infection indexes such as CRP (AUC is 0.635), PCT (AUC is 0.663), WBC (AUC is 0.654), NEU (AUC is 0.727), neutrophil/lymphocyte ratio (NLR) (AUC is 0.797) and the like.
In addition, the inventor groups screen effective characteristic variables with predictive value on AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP, and 7 AECOPD predictive models are established through machine learning according to the indexes. The effectiveness of the model was evaluated using a 5-fold cross-validation method. The research shows that the logistic regression model based on exosome MiR-1258, NLR and neutrophil count has the best prediction effect. The chronic obstructive pulmonary disease acute exacerbation prediction system further improves the discrimination capability of AECOPD, and establishes an equation to precisely quantify the occurrence probability of AECOPD, thereby well overcoming the defects of the existing AECOPD prediction method.
In the course of the study of one particular embodiment, the inventors team of the present invention selected the following study subjects:
serum samples of 66 patients diagnosed with AECOPD at third hospital of beijing university, 42 patients with chronic obstructive pulmonary disease (Severe Chronic Obstructive Pulmonary Disease, SCOPD) in stationary phase, and 45 apparent healthy human serum samples were collected from 12 months 2019 to 7 months 2021. And recording basic information, clinical related information and conventional test results of the group crowd.
Inclusion and exclusion criteria:
1) Apparent healthy people: has no history of various acute and chronic diseases and normal routine laboratory detection results.
2) SCOPD and AECOPD patients: meets the current diagnostic criteria of SCOPD and AECOPD, excluding patients with a history of neoplasms.
3) Excluding serum samples which are not in accordance with the relevant requirements from being collected, transported and stored;
4) Excluding samples with incomplete information records;
5) Contaminated and insufficient sample size samples are excluded.
The instruments and reagents used in the study include:
CRP and LDH detection is carried out by adopting a Beckmann Coulter AU2700 latex immunonephelometry kit; PCT was tested using rogowski E401; white blood cell count and differential count using a full-automatic blood analyzer of hessian mecngxn 9000; exosomes were extracted by ultra-high speed centrifugation, identified by electron microscopy, western blot and exosome particle size analyzer, sample RNAs were extracted with TRIZOL (TAKARA corporation) reagent, and MiR-1258 was detected using ABI 7500PCR amplicon.
Statistical analysis of the data was performed using SPSS 26.0. Continuous variable comparisons were performed using the t-test and the Man-Whitney U test, and class variable comparisons were performed using the chi-square test. The sensitivity and specificity of the biomarkers were assessed by analyzing the subject's working characteristics curve (ROC) using MedCalc 19.6.4.
And establishing a mathematical model and a decision tree by using Python software, and verifying the accuracy and reliability of the model through five-fold cross test. The present inventors team established 7 models for the identification of AECOPD and SCOPD based on exosomes MiR-1258 and conventional infection-related indicators, including: (1) a Support Vector Machine (SVM); (2) a random forest; (3) gradient propulsion classifier; (4) k nearest neighbors (K nearest neighbor algorithm); (5) an artificial neuron network; (6) gaussian
Bayes (naive Gao Sibei phyllus model); (7) logistic regression (logistic regression) model. The research results show that:
1) Mirs-1258 expression in AECOPD patient exosomes was significantly higher than in COPD patients and apparent healthy control groups (see figure 1).
NC in fig. 1 is a healthy control group; SCOPD is a group of patients with stationary phase chronic obstructive pulmonary disease; AECOPD is a group of patients with acute exacerbations of chronic obstructive pulmonary disease; serum is the detection result of MiR-1258 in Serum; exosomes are the detection results of MiR-1258 in serum Exosomes; * Representing the difference as statistically significant, p <0.01; * The differences are statistically significant, p <0.001.
2) Evaluation of ability of exosome MiR-1258 to predict AECOPD
To evaluate the efficacy of MiR-1258 in AECOPD prediction, the inventors calculated and compared the area under the ROC curve (AUC). To distinguish AECOPD from SCOPD, the aposome MiR-1258 has an AUC of 0.851 (95% ci 0.769-0.902), significantly higher than MiR-1258 (auc= 0.790,95%CI 0.701-0.863), NLR (auc= 0.797,95%CI 0.708-0.868), NEU (auc= 0.727,95%CI 0.633-0.808), WBC (auc= 0.654,95%CI 0.556-0.743) and CRP (auc= 0.635,95%CI 0.635-0.808) in serum, see fig. 2.
The optimal cut-off, specificity, sensitivity of each biomarker are shown in Table 1. Among all the indices, exosome MiR-1258 has the highest specificity in distinguishing AECOPD and SCOPD, 97.62%, and higher sensitivity, 74.2%. The combination of exosome MiR-1258 with NLR increased AUC to 0.944 and sensitivity to 81.82% while maintaining higher specificity (97.62%).
TABLE 1 evaluation of efficacy of different metrics for predicting AECOPD
3) Accuracy evaluation of 7 AECOPD prediction models established based on machine learning method
The inventor groups screen effective characteristic variables with predictive value on AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP, and 7 AECOPD predictive models are established through machine learning according to the indexes. The effectiveness of the model was evaluated using a 5-fold cross-validation method. The model predictive effect evaluation is shown in table 2. Machine learning results display: the best efficacy of SCOPD and AECOPD was identified using a logistic regression model.
TABLE 2 evaluation of prediction effect of different prediction models
The Logistic regression equation is:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR-1258 is the expression of MiR-1258 in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
4) Establishment of AECOPD prediction model decision tree
The decision tree facilitates the establishment of a clinical strategy for AECOPD prediction. And according to the selected index, establishing a decision tree through logistic regression model verification. It was found that of 108 patients with SCOPD and AECOPD, 50 patients with MiR-1258 > 0.197 have 49 (98%) NEU > 2.705 ×10 9 L was successfully predicted as AECOPD in the training set, with only 1 patient predicted as SCOPD (coefficient of base 0.0). Whereas of the 58 aposome MiR-1258.ltoreq.0.197 patients, 35 patients had NLR.ltoreq. 3.645, of which 32 (91.4%) were successfully predicted as SCOPD and only 3 were AECOPD patients (with a coefficient of base of 0.157) (see FIGS. 3A and 3B), further demonstrating the important role of the aposome MiR-1258, NLR and NEU in AECOPD identification and prediction.
In FIGS. 3A and 3B, 1258 is exosome MiR-1258; gini is the coefficient of base; samples are the number of samples meeting the judgment standard; value= [ number of healthy people (a) or number of patients in the SCOPD group (B), number of AECOPD patients ].
AECOPD has the characteristics of urgent disease, high mortality and poor prognosis, and has great clinical significance in predicting the occurrence of AECOPD of patients in advance. However, no ideal laboratory index is available to effectively predict AECOPD, and there is no relevant prediction model based on machine learning technology, but the sensitivity and specificity of the index used conventionally in clinic are low (NLR: AUC 0.797, cut-off 3.57: sensitivity 71.21%, specificity 78.57%, neutrophil: AUC 0.727, cut-off 6.38X10) 9 L, sensitivity 39.39% and specificity 95.24%; CRP: AUC 0.635, cut-off 2.26mg/dL: sensitivity 42.42%, specificity 85.71%; WBC: AUC 0.654, cut-off 5.50X10 9 /L: sensitivity 81.82%, specificity 47.62%).
Through research, the team of inventors found that exosome MiR-1258 has a better predictive value for AECOPD (AUC 0.851, cut-off 0.1927: sensitivity 74.24%, specificity 97.62%). Meanwhile, in order to achieve a better prediction effect, the inventor performs joint detection on MiR-1258 and other indexes, screens out a model with the best prediction efficiency by using a machine learning technology, and obtains a Logistic regression equation which can be used for predicting the occurrence probability of AECOPD.
The research not only discovers that biomarker exosome MiR-1258 of AECOPD can be effectively predicted, but also establishes a prediction model of AECOPD, and verifies that the model has better accuracy, provides a quantization equation for predicting the occurrence rate of AECOPD, and is beneficial to identifying AECOPD patients clinically and earlier.
Based on the above study, the invention provides a chronic obstructive pulmonary disease acute exacerbation prediction system, as shown in fig. 4, comprising a detection module, a model building module and a prediction module; the detection module is used for detecting one or more of MiR-1258, NEU, CRP, NLR, LDH, PCT and WBC; the model building module is used for building an AECOPD prediction model by using a machine learning method based on the detection result of the detection module; the prediction module is used for obtaining the probability of the AECOPD of the patient according to the AECOPD prediction model and the detection result of the detection module.
Preferably, the AECOPD prediction model is a support vector machine, a random forest, a gradient propulsion classifier, K nearest neighbors (K nearest neighbor algorithm), an artificial neuron network, a Gaussian
Bayes (naive Gao Sibei phylls model) or logistic regression (logistic regression) model.
Preferably, the model building module screens out effective characteristic variables with predictive value for AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP; the prediction module obtains the probability of the patient to generate AECOPD according to a Logistic regression equation, wherein the Logistic regression equation is as follows:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR-1258 is the expression of MiR-1258 in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
The chronic obstructive pulmonary disease acute exacerbation prediction system also comprises a decision tree establishment module, which is used for establishing a decision tree according to the selected index through logistic regression model verification.
Preferably, the chronic obstructive pulmonary disease acute exacerbation prediction system further comprises a verification module for evaluating the validity of the AECOPD prediction model by using a 5-fold cross-validation method.
Further preferably, CRP and LDH detection is performed using Beckmann Coulter AU2700 latex immunonephelometry kit.
Preferably, said PCT is detected using rogowski E401.
Further preferably, the detection module uses a full-automatic blood analyzer of the hson mecamylum 9000 for white blood cell count and sort count.
Further preferably, the detection module extracts exosomes by using an ultra-high speed centrifugation method, identifies exosomes by using an electron microscope, a Western blot and an exosome particle size analyzer, extracts sample RNA by using a TRIZOL reagent, and detects MiR-1258 by using an ABI 7500PCR amplification instrument.
The invention also provides a method for predicting acute exacerbation of chronic obstructive pulmonary disease, which comprises the following steps:
firstly, screening effective characteristic variables with predictive value for AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP;
secondly, obtaining the probability of the patient to generate AECOPD according to a Logistic regression equation, wherein the Logistic regression equation is as follows:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR-1258 is the expression of MiR-1258 in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the simple modifications belong to the protection scope of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various possible combinations are not described further.
Moreover, any combination of the various embodiments of the invention can be made without departing from the spirit of the invention, which should also be considered as disclosed herein.
The foregoing describes preferred embodiments of the present invention, but is not intended to limit the invention thereto. Modifications and variations to the embodiments disclosed herein may be made by those skilled in the art without departing from the scope and spirit of the invention.
Claims (5)
1. The chronic obstructive pulmonary disease acute exacerbation prediction system is characterized by comprising a detection module, a model building module and a prediction module; the detection module is used for detecting one or more of MiR-1258, NEU, CRP, NLR, LDH, PCT and WBC; the model building module is used for building an AECOPD prediction model based on the detection result of the detection module and by using a machine learning method; the prediction module is used for obtaining the probability of AECOPD of the patient according to the AECOPD prediction model and the detection result of the detection module;
the detection module uses a full-automatic blood analyzer of the Hissen Meikang xn9000 to count white blood cells and classify the white blood cells;
the detection module extracts exosomes by using an ultra-high speed centrifugation method, identifies the exosomes by using an electron microscope, a Western blot and an exosome particle size analyzer, extracts sample RNA by using a TRIZOL reagent, and detects MiR-1258 by using an ABI 7500PCR amplification instrument;
CRP and LDH detection is carried out by adopting a Beckmann Coulter AU2700 latex immunonephelometry kit;
the PCT is detected by using Roche E401;
the model building module screens out effective characteristic variables with predictive value for AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP; the prediction module obtains the probability of the patient to generate AECOPD according to a Logistic regression equation, wherein the Logistic regression equation is as follows:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR1258 is MiR-1258 expression in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
2. The system of claim 1, wherein the AECOPD prediction model is a support vector machine, a random forest, a gradient push classifier K nearest neighbor algorithm, an artificial neural network, a naive Gao Sibei phylls model, or a logistic regression model.
3. The system for predicting acute exacerbation of chronic obstructive pulmonary disease according to claim 1, further comprising a decision tree building module for building a decision tree according to the selected index through logistic regression model verification.
4. The system of claim 1, further comprising a validation module for evaluating the validity of the AECOPD prediction model using a 5-fold cross-validation method.
5. A method of predicting a chronic obstructive pulmonary disease acute exacerbation system according to any one of claims 1 to 4, comprising the steps of:
firstly, screening effective characteristic variables with predictive value for AECOPD by taking Logistic regression as a standard, wherein the effective characteristic variables comprise exosomes MiR-1258, NEU, NLR and CRP;
secondly, obtaining the probability of the patient to generate AECOPD according to a Logistic regression equation, wherein the Logistic regression equation is as follows:
wherein P is the probability of the patient developing AECOPD;
exp is an exponential function based on a natural constant e;
MiR1258 is MiR-1258 expression in exosomes;
NEU is neutrophil count;
CRP is C reactive protein;
NLR is the neutrophil/lymphocyte ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210597499.3A CN114822827B (en) | 2022-05-30 | 2022-05-30 | System and method for predicting acute exacerbation of chronic obstructive pulmonary disease |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210597499.3A CN114822827B (en) | 2022-05-30 | 2022-05-30 | System and method for predicting acute exacerbation of chronic obstructive pulmonary disease |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114822827A CN114822827A (en) | 2022-07-29 |
| CN114822827B true CN114822827B (en) | 2023-06-02 |
Family
ID=82518467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210597499.3A Active CN114822827B (en) | 2022-05-30 | 2022-05-30 | System and method for predicting acute exacerbation of chronic obstructive pulmonary disease |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114822827B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116612885B (en) * | 2023-04-26 | 2024-03-22 | 浙江大学 | Prediction device for acute exacerbation of chronic obstructive pulmonary disease based on multiple modes |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020194211A1 (en) * | 2019-03-26 | 2020-10-01 | The University Of British Columbia | Methods and compositions for monitoring acute exacerbation of copd |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897570B (en) * | 2017-03-02 | 2021-05-11 | 山东师范大学 | Chronic obstructive pulmonary disease testing system based on machine learning |
| CN112652391A (en) * | 2020-12-16 | 2021-04-13 | 浙江大学温州研究院 | System for identifying acute exacerbation of chronic obstructive pulmonary disease |
-
2022
- 2022-05-30 CN CN202210597499.3A patent/CN114822827B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020194211A1 (en) * | 2019-03-26 | 2020-10-01 | The University Of British Columbia | Methods and compositions for monitoring acute exacerbation of copd |
Non-Patent Citations (1)
| Title |
|---|
| 三指标联合检测对慢性阻塞性肺疾病急性加重期的预测价值;孟凡飞;李毅;孟凡娜;张立群;项贵明;;标记免疫分析与临床(09);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114822827A (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chowdhury et al. | An early warning tool for predicting mortality risk of COVID-19 patients using machine learning | |
| CN112970067A (en) | Cancer classifier model, machine learning system and method of use | |
| CN110577998A (en) | Construction of molecular model for predicting postoperative early recurrence risk of liver cancer and application evaluation thereof | |
| EP3607089A2 (en) | Plasma based protein profiling for early stage lung cancer prognosis | |
| JP7467447B2 (en) | Sample quality assessment method | |
| WO2005008254A1 (en) | Clinical examination analyzing device, clinical examination analyzing method, and program for allowing computer to execute the method | |
| Ren et al. | Identifying tuberculous pleural effusion using artificial intelligence machine learning algorithms | |
| WO2010049538A1 (en) | Biomarkers | |
| CN114822827B (en) | System and method for predicting acute exacerbation of chronic obstructive pulmonary disease | |
| CN111863250A (en) | Combined diagnosis model and system for early breast cancer | |
| CN112313497A (en) | Methods of diagnosing disease using microflow cytometry | |
| CN115798712B (en) | System for diagnosing whether person to be tested is breast cancer or not and biomarker | |
| Zhang et al. | Suggestions for designing studies investigating diagnostic accuracy of biomarkers | |
| CN115144599A (en) | Application of protein combination in preparation of kit for carrying out prognosis stratification on thyroid cancer of children, and kit and system thereof | |
| Aktas et al. | Deep convolutional neural networks for detection of abnormalities in chest X-rays trained on the very large dataset | |
| De Bruyne et al. | Applications of Artificial Intelligence in Urinalysis: Is the Future Already Here? | |
| CN112798678A (en) | Novel rapid detection method for coronavirus infection based on serum | |
| WO2023185067A1 (en) | Serum metabolic markers for detecting pulmonary tuberculosis and kit thereof | |
| CN115128285B (en) | Kit and system for identifying and evaluating thyroid follicular tumor by protein combination | |
| Alanee et al. | Using adaptive genetic algorithms combined with high sensitivity single cell-based technology to detect bladder cancer in urine and provide a potential noninvasive marker for response to anti-PD1 immunotherapy | |
| CN116287248B (en) | miRNA gene for diagnosis of intestinal adenoma adenocarcinoma and application thereof | |
| Zhao et al. | Predicting the risk of nodular thyroid disease in coal miners based on different machine learning models | |
| WO2023246808A1 (en) | Use of cancer-associated short exons to assist cancer diagnosis and prognosis | |
| Zheng et al. | Clinical Performance Study of a New Fully Automated Red Blood Cell Permeability Fragility Analyzer | |
| Fan et al. | A Three-Gene Based Diagnos Tic Model for Endometriosis |
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 |