Application of SRH model to prediction of health problem of novel coronavirus patient

Through the Nomogram chart and scoring system of the SRH model, combining data collection, prediction and intervention modules, we can identify high-risk novel coronavirus patients and conduct early intervention, solving the lack of comprehensive and systematic prediction problems in the existing technology and improving the treatment effect and quality of life, reducing medical costs.

CN118919064APending Publication Date: 2024-11-08THE SECOND AFFILIATED HOSPITAL OF HARBIN MEDICAL UNIV (THE SECOND CLINICAL SCHOOL OF HARBIN MEDICAL UNIV)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410618466.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-05-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing prediction models for health problems of patients with novel coronavirus lack comprehensiveness and systemicity, and cannot comprehensively predict health problems in multiple systems throughout the body, resulting in difficulty in optimizing clinical decision-making and treatment plans and increased medical burden.

Method used

Using the SRH model, by collecting three indicators of shock, using ribavirin and hemoptysis, Nomogram chart and scoring system are established to predict the probability of patients' health problems, identify high-risk patients and conduct early intervention and treatment, including data collection modules and prediction modules , the combination of identification module and intervention module.

Benefits of technology

A comprehensive assessment of multiple systems of health problems in patients with novel coronavirus has been achieved, which has improved diagnosis and treatment efficiency, reduced medical costs, and significantly improved patients' quality of life and medical management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure SMS_1
    Figure SMS_1
  • Figure SMS_2
    Figure SMS_2
  • Figure SMS_3
    Figure SMS_3
Patent Text Reader

Abstract

The invention discloses an application of an SRH model for predicting health problems of a novel coronavirus patient, which comprises the following steps: step 1, collecting clinical data of the patient, including three indexes of shock, ribavirin use and hemoptysis; step 2, establishing a Nomogram graph and a scoring system based on the indexes; 3, predicting the probability of the health problem of the patient through a Nomogram graph and a scoring system; 4, the patient with the high score is identified as a high-risk patient; 5, performing early intervention and treatment on the high-risk patient to reduce the incidence rate of health problems; the Nomogram graph and the score for predicting the novel coronavirus health problem are established according to the three indexes of shock occurrence, ribavirin use and hemoptysis, the higher the score is, the higher the probability that the patient has the health problem is, clinical early recognition of the patient possibly having the health problem is facilitated, intervention can be performed as early as possible, the occurrence rate of the health problem is reduced, and the clinical development of the novel coronavirus health problem is promoted. Living quality of patients is improved and medical burden is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of predicting health problems of novel coronavirus patients, and specifically relates to the application of SRH model in predicting health problems of novel coronavirus patients. Background Art

[0003] The novel coronavirus (COVID-19) not only damages the respiratory system, but may also cause health problems in multiple organ systems, thus increasing the complexity of the patient's condition and the difficulty of treatment. Clinical observations and studies have shown that the health problems of COVID-19 involve multiple systems throughout the body, including but not limited to fibrotic changes in lung CT, damage to organs such as the heart, kidneys, and liver, thrombotic events, and negative mental states such as depression that patients may experience. These health problems are important reasons for the deterioration of patients' conditions, reduced quality of life, and increased medical burdens.

[0004] Although many clinical prediction models have attempted to discover the risk factors for health problems after the new coronavirus and have made some progress, there is currently no model that can comprehensively predict health problems in multiple systems of the body. Existing prediction tools often only target specific health problems or specific organ systems, lacking comprehensiveness and systematicness. Therefore, there is an urgent need for a risk assessment model that can comprehensively predict health problems in multiple systems of the body in order to better guide clinical decision-making, optimize treatment plans, and reduce the risk of health problems and medical burdens on patients. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the existing defects and provide an application of the SRH model to predict the health problems of patients with the new coronavirus, so as to solve the problem raised in the above background technology that there is currently no model that can comprehensively predict the health problems of multiple systems in the body, and the existing prediction tools often only target specific health problems or specific organ systems, lacking comprehensiveness and systematicness.

[0006] To achieve the above object, the present invention provides the following technical solution: Application of the SRH model to predict health problems of patients with new coronavirus, comprising the following steps:

[0007] Step 1: Collect clinical data of patients, including three indicators: shock, use of ribavirin, and hemoptysis;

[0008] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0009] Step 3: Predict the probability of patients developing health problems through the nomogram and scoring system;

[0010] Step 4: Identify patients with higher scores as high-risk patients;

[0011] Step Five: Provide early intervention and treatment for high-risk patients to reduce the incidence of health problems.

[0012] Preferably, in step 1, shock indicators include systolic blood pressure less than 90 mmHg and / or mean arterial pressure less than 65 mmHg.

[0013] Preferably, in step 1, the ribavirin use indicator refers to whether the patient receives ribavirin treatment.

[0014] Preferably, in step 1, the hemoptysis index includes blood in sputum, blood in coughing and hemoptysis.

[0015] Preferably, in step 2, the Nomogram is constructed based on univariate and multivariate Cox regression analysis.

[0016] Preferably, in step 2, the scoring system calculates the score based on the weight of each indicator in the Nomogram and the actual situation of the patient.

[0017] Preferably, in step 4, patients with higher scores are identified as high-risk patients through a scoring system.

[0018] Preferably, in step five, early intervention and treatment are performed on high-risk patients, including enhanced monitoring, adjustment of treatment plans and enhanced supportive treatment, so as to improve the quality of life of patients and reduce the medical burden by reducing the incidence of health problems.

[0019] Preferably, it includes a data collection module, a prediction module, an identification module and an intervention module, wherein the data collection module is used to collect clinical data of patients, including three indicators: shock, use of ribavirin and hemoptysis; the prediction module establishes a Nomogram and a scoring system based on the indicators, and predicts the probability of health problems in patients through the Nomogram and the scoring system; the identification module is used to identify patients with higher scores as high-risk patients; and the intervention module is used to perform early intervention and treatment on high-risk patients to reduce the incidence of health problems.

[0020] Preferably, the data collection module includes a prediction algorithm, using a logistic regression model to analyze the relationship between the patient's clinical data and the occurrence of health problems, and the formula is as follows:

[0021]

[0022] Where P(y=1|x) represents the probability of a patient having a health problem given the patient's characteristic x;

[0023] e is the base of natural logarithms;

[0024] β0 ,β1 , β2 , β3 are model parameters, representing the coefficients of the intercept term and three characteristics (shock, ribavirin use, and hemoptysis);

[0025] x1, x2, and x3 are three characteristic values ​​of the patient, which may be binary indicator variables or standardized numerical values;

[0026] The prediction algorithm uses the support vector machine (SVM) model to improve the prediction accuracy by optimizing the penalty parameters and kernel function. The formula is as follows:

[0027]

[0028] Among them, f(x) is the decision function, which is used to determine whether the patient will have health problems;

[0029] α i is the Lagrange multiplier, obtained by solving the optimization problem;

[0030] y i is the label of the i-th training sample, which takes a value of +1 or -1;

[0031] K(x,x i ) is the kernel function, which is used to calculate the two sample points x and x i The inner product or some similarity between them;

[0032] b is the bias term;

[0033] N is the number of training samples.

[0034] Compared with the prior art, the present invention provides an application of the SRH model to predict health problems of patients with novel coronavirus, which has the following beneficial effects:

[0035] 1. The present invention establishes a Nomogram and a score for predicting health problems of the new coronavirus based on the three indicators of shock, ribavirin use, and hemoptysis. The higher the score, the greater the probability that the patient will have health problems, which helps to identify patients who may have health problems at an early stage in the clinic, and can intervene as early as possible to reduce the incidence of health problems, improve the quality of life of patients, and reduce the medical burden;

[0036] 2. The present invention forms a complete system through the organic combination of data collection module, prediction module, identification module and intervention module, which can realize comprehensive evaluation and personalized management of patients. This system not only improves the efficiency of diagnosis and treatment, but also reduces medical costs, with significant economic and social benefits. In addition, the system can also provide important data support for clinical research and promote the further improvement of the treatment and management level of the new coronavirus. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] The present invention provides a technical solution: application of the SRH model to predict health problems of patients with novel coronavirus, comprising the following steps:

[0039] Step 1: Collect clinical data of patients, including three indicators: shock, use of ribavirin, and hemoptysis;

[0040] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0041] Step 3: Predict the probability of patients developing health problems through the nomogram and scoring system;

[0042] Step 4: Identify patients with higher scores as high-risk patients;

[0043] Step Five: Provide early intervention and treatment for high-risk patients to reduce the incidence of health problems.

[0044] In the present invention, preferably, in step 1, the shock index includes systolic blood pressure less than 90 mmHg and / or mean arterial pressure less than 65 mmHg.

[0045] In the present invention, preferably, in step 1, the ribavirin use indicator refers to whether the patient receives ribavirin treatment.

[0046] In the present invention, preferably, in step 1, the hemoptysis index includes blood in sputum, blood in coughing and hemoptysis.

[0047] In the present invention, preferably, in step 2, the Nomogram is constructed based on univariate and multivariate Cox regression analysis.

[0048] In the present invention, preferably, in step 2, the scoring system calculates the score according to the weight of each indicator in the Nomogram and the actual situation of the patient.

[0049] In the present invention, preferably, in step 4, patients with higher scores are identified as high-risk patients through a scoring system.

[0050] In the present invention, preferably, in step five, early intervention and treatment are performed on high-risk patients, including enhanced monitoring, adjustment of treatment plans and enhanced supportive treatment, so as to improve the quality of life of patients and reduce the medical burden by reducing the incidence of health problems.

[0051] In the present invention, preferably, it includes a data collection module, a prediction module, an identification module and an intervention module. The data collection module is used to collect clinical data of patients, including three indicators of shock, use of ribavirin and hemoptysis; the prediction module is to establish a Nomogram and a scoring system based on the indicators, and predict the probability of health problems in patients through the Nomogram and the scoring system; the identification module is used to identify patients with higher scores as high-risk patients; the intervention module is used to perform early intervention and treatment on high-risk patients to reduce the incidence of health problems.

[0052] In the present invention, preferably, the data collection module includes a prediction algorithm, using a logistic regression model to analyze the relationship between the patient's clinical data and the occurrence of health problems, and the formula is as follows:

[0053]

[0054] Among them, P(y=1x) represents the probability of a patient having a health problem given the patient's characteristic x;

[0055] e is the base of natural logarithms;

[0056] β0 , β1 , β2 , β3 are model parameters, representing the coefficients of the intercept term and three characteristics (shock, ribavirin use, and hemoptysis);

[0057] x1, x2, and x3 are three characteristic values ​​of the patient, which may be binary indicator variables or standardized numerical values.

[0058] The prediction algorithm uses the support vector machine (SVM) model to improve the prediction accuracy by optimizing the penalty parameters and kernel function. The formula is as follows:

[0059]

[0060] Among them, f(x) is the decision function, which is used to determine whether the patient will have health problems;

[0061] α i is the Lagrange multiplier, obtained by solving the optimization problem;

[0062] y i is the label of the i-th training sample, which takes a value of +1 or -1;

[0063] K(x,x i ) is the kernel function, which is used to calculate the two sample points x and x i The inner product or some similarity between them;

[0064] b is the bias term;

[0065] N is the number of training samples.

[0066] Example

[0067] Embodiment 1

[0068] The application of the SRH model to predict health problems in patients with the novel coronavirus includes the following steps:

[0069] Step 1: Collect clinical data of patients, including shock (no), use of ribavirin (no), and hemoptysis (no);

[0070] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0071] Step 3: The Nomogram and scoring system are used to predict that the probability of the patient developing health problems is 5%;

[0072] Step 4: Identify patients with lower scores as low-risk patients;

[0073] Step 5: Provide routine treatment for low-risk patients without special intervention.

[0074] The patient did not have shock, ribavirin use, or hemoptysis, and was predicted to be a low-risk patient based on the SRH model, with a 5% incidence of health problems. Due to the low incidence of health problems, no intervention was performed.

[0075] Embodiment 2

[0076] The application of the SRH model to predict health problems in patients with the novel coronavirus includes the following steps:

[0077] Step 1: Collect clinical data of patients, including shock (no), use of ribavirin (yes), and hemoptysis (no);

[0078] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0079] Step 3: The Nomogram and scoring system are used to predict that the probability of the patient developing health problems is 10%;

[0080] Step 4: Identify patients with higher scores as intermediate-risk patients;

[0081] Step 5: Early intervention for moderate-risk patients, including adjusting treatment plans and strengthening supportive treatment.

[0082] The patient was not in shock but was taking ribavirin. He had no hemoptysis and was predicted to be a moderate-risk patient according to the SRH model, with a 10% incidence of health problems. Due to the high incidence of health problems, early intervention was performed.

[0083] Embodiment 3

[0084] The application of the SRH model to predict health problems in patients with the novel coronavirus includes the following steps:

[0085] Step 1: Collect clinical data of patients, including three indicators: shock (yes), use of ribavirin (no), and hemoptysis (yes);

[0086] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0087] Step 3: The Nomogram and scoring system are used to predict that the probability of the patient developing health problems is 25%;

[0088] Step 4: Identify patients with higher scores as high-risk patients;

[0089] Step 5: Provide intensive treatment for high-risk patients, including enhanced monitoring and adjustment of treatment plans.

[0090] The patient had shock, but ribavirin was not used. Hemoptysis was positive, and the SRH model predicted that he was a high-risk patient with a 25% incidence of health problems. Due to the very high incidence of health problems, intensive treatment was performed.

[0091] Embodiment 4

[0092] The application of the SRH model to predict health problems in patients with the novel coronavirus includes the following steps:

[0093] Step 1: Collect clinical data of patients, including three indicators: shock (no), use of ribavirin (no), and hemoptysis (yes);

[0094] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0095] Step 3: The Nomogram and scoring system predict that the probability of the patient developing health problems is 15%;

[0096] Step 4: Identify patients with higher scores as intermediate-risk patients;

[0097] Step 5: Early intervention for moderate-risk patients, including adjusting treatment plans and strengthening supportive treatment.

[0098] The patient was not in shock but was taking ribavirin and had hemoptysis. According to the SRH model, he was predicted to be a medium-risk patient with a 15% incidence of health problems. Due to the high incidence of health problems, early intervention was performed.

[0099] Embodiment 5

[0100] The application of the SRH model to predict health problems in patients with the novel coronavirus includes the following steps:

[0101] Step 1: Collect clinical data of patients, including three indicators: shock (yes), use of ribavirin (yes), and hemoptysis (no);

[0102] Step 2: Establish a Nomogram and scoring system based on the indicators;

[0103] Step 3: The Nomogram and scoring system are used to predict that the probability of the patient developing health problems is 20%;

[0104] Step 4: Identify patients with higher scores as high-risk patients;

[0105] Step 5: Provide intensive treatment for high-risk patients, including enhanced monitoring and adjustment of treatment plans.

[0106] The patient was in shock and was taking ribavirin. He had no hemoptysis and was predicted to be a high-risk patient according to the SRH model. The incidence of health problems was 20%. Due to the very high incidence of health problems, intensive treatment was performed.

[0107]

[0108] Through the comparison of these five examples, we can see the prediction results and intervention effects of the SRH model in predicting the health problems of patients with new coronavirus in different situations. This helps clinicians to formulate corresponding treatment strategies according to the specific conditions of the patients, thereby improving the treatment effect and improving the patient's prognosis.

[0109] The present invention collects clinical data of patients, including three indicators, namely shock, use of ribavirin and hemoptysis, and establishes a nomogram and a scoring system based on these indicators to predict the probability of health problems in patients. By identifying patients with higher scores as high-risk patients, early intervention and treatment are carried out on high-risk patients to reduce the incidence of health problems, improve the quality of life of patients, and reduce the medical burden.

[0110] The application of the SRH model to predict the health problems of patients with the new coronavirus forms a complete system through the organic combination of data collection module, prediction module, identification module and intervention module, which can achieve comprehensive evaluation and personalized management of patients. This system not only improves the efficiency of diagnosis and treatment, but also reduces medical costs, with significant economic and social benefits. In addition, the system can also provide important data support for clinical research and promote the further improvement of the treatment and management level of the new coronavirus.

[0111] The application of the SRH model to predict the health problems of patients with the new coronavirus uses prediction algorithms such as logistic regression models and SVM models to analyze the relationship between patients' clinical data and the occurrence of health problems and improve prediction accuracy. Through univariate and multivariate Cox regression analysis, a Nomogram is constructed, and scores are calculated based on the weights of each indicator in the Nomogram and the actual situation of the patient, identifying patients with higher scores as high-risk patients. Early intervention and treatment of high-risk patients, including enhanced monitoring, adjustment of treatment plans, and enhanced supportive treatment, can reduce the incidence of health problems, improve the quality of life of patients, and reduce the medical burden.

[0112] The application of the SRH model provided by the present invention to predict the health problems of patients with new coronavirus realizes comprehensive assessment and personalized management of patients through the organic combination of prediction model and intervention measures. This system not only improves the efficiency of diagnosis and treatment, but also reduces medical costs, with significant economic and social benefits. In addition, the system can also provide important data support for clinical research and promote the further improvement of the treatment and management level of new coronavirus.

[0113] In summary, the application of the SRH model provided by the present invention to predict the health problems of patients with new coronavirus has high prediction accuracy, can effectively identify high-risk patients, conduct early intervention and treatment, thereby improving the treatment effect and improving the patient's prognosis. The system has significant economic and social benefits, provides important data support for clinical research, and promotes the further improvement of the treatment and management level of new coronavirus.

[0114] Although 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 appended claims and their equivalents.

Claims

1. The application of SRH model to predict health problems of patients with novel coronavirus is characterized by: The following steps are involved: Step 1: Collect clinical data of patients, including three indicators: shock, use of ribavirin, and hemoptysis; Step 2: Establish a Nomogram and scoring system based on the indicators; Step 3: Predict the probability of patients developing health problems through the nomogram and scoring system; Step 4: Identify patients with higher scores as high-risk patients; Step Five: Provide early intervention and treatment for high-risk patients to reduce the incidence of health problems.

2. The application of the SRH model according to claim 1 to predict health problems of patients with new coronavirus, characterized in that: In step 1, the shock indicators include systolic blood pressure less than 90 mmHg and / or mean arterial pressure less than 65 mmHg.

3. The application of the SRH model according to claim 1 to predict health problems of patients with new coronavirus, characterized in that: In the step 1, the ribavirin use indicator refers to whether the patient receives ribavirin treatment.

4. The application of the SRH model according to claim 1 to predict health problems of patients with new coronavirus, characterized in that: In the step 1, the hemoptysis index includes blood in sputum, blood in coughing and hemoptysis.

5. The application of the SRH model according to claim 1 to predict health problems of patients with new coronavirus, characterized in that: In the step 2, the Nomogram is constructed based on univariate and multivariate Cox regression analysis.

6. The application of the SRH model according to claim 1 to predict health problems of patients with new coronavirus, characterized in that: In step 2, the scoring system calculates the score based on the weight of each indicator in the Nomogram and the actual situation of the patient.

7. The application of the SRH model according to claim 1 to predict health problems of patients with new coronavirus, characterized in that: In step 4, the patients with higher scores are identified as high-risk patients through a scoring system.

8. The application of the SRH model according to claim 1 to predict health problems of patients with novel coronavirus, characterized in that: In step five, early intervention and treatment are carried out for high-risk patients, including enhanced monitoring, adjustment of treatment plans and strengthening of supportive treatment, so as to improve the quality of life of patients and reduce the medical burden by reducing the incidence of health problems.

9. The application of the SRH model according to claims 1-8 to predict health problems of patients with novel coronavirus, characterized in that: It includes a data collection module, a prediction module, an identification module and an intervention module. The data collection module is used to collect clinical data of patients, including three indicators: shock, use of ribavirin and hemoptysis; the prediction module establishes a nomogram and a scoring system based on the indicators, and predicts the probability of patients having health problems through the nomogram and the scoring system; the identification module is used to identify patients with higher scores as high-risk patients; and the intervention module is used to perform early intervention and treatment on high-risk patients to reduce the incidence of health problems.

10. The application of the SRH model according to claim 9 to predict health problems of patients with novel coronavirus, characterized in that: The data collection module includes a prediction algorithm, which uses a logistic regression model to analyze the relationship between the patient's clinical data and the occurrence of health problems. The formula is as follows: Where P(y=1|x) represents the probability of a patient having a health problem given the patient's characteristic x; e is the base of natural logarithms; β0 , β1 , β2 , β3 are model parameters, representing the coefficients of the intercept term and three characteristics (shock, ribavirin use, and hemoptysis); x1, x2, and x3 are three characteristic values ​​of the patient, which may be binary indicator variables or standardized numerical values; The prediction algorithm uses the support vector machine (SVM) model to improve the prediction accuracy by optimizing the penalty parameters and kernel function. The formula is as follows: Among them, f(x) is the decision function, which is used to determine whether the patient will have health problems; α i is the Lagrange multiplier, obtained by solving the optimization problem; y i is the label of the i-th training sample, which takes a value of +1 or -1; K(x,x i ) is the kernel function, which is used to calculate the two sample points x and x i The inner product or some similarity between them; b is the bias term; N is the number of training samples.