Medication guidance method and system for multi-drug-resistant gram-negative bacillus severe pneumonia

Abstract

The invention relates to the technical field of medical treatment, and particularly discloses a medication guidance method and system for multi-drug-resistant gram-negative bacillus severe pneumonia, and the method comprises the following steps: acquiring initial examination information of a patient; the initial detection information comprises basic information of a patient, disease state information, multi-drug-resistant gram-negative bacillus infection risk information and in-use drug information; according to a detection sample collected from a patient, etiological diagnosis information of the patient is obtained; according to the initial examination information and the etiological diagnosis information, determining a preliminary treatment scheme of the patient by using a prediction model; the preliminary treatment scheme comprises a drug treatment scheme, an expected drug effect and an adverse reaction risk. Individualized analysis is carried out on the patient in combination with initial examination information and etiological diagnosis information of the patient, and whether various treatment schemes are matched with the patient or not is analyzed by utilizing the prediction model, so that the initial treatment scheme most suitable for the patient is selected. The preliminary treatment scheme can be used as a medication guidance basis for reasonable medication of clinicians, and individualized medication treatment guidance for patients is provided.

Description

Technical Field

[0001] The present invention relates to the field of medical technologies, and particularly to a method and a system for guiding drug use for severe pneumonia caused by multi-drug resistant Gram-negative bacilli. Background Art

[0002] Pulmonary infection is an infection caused by pathogenic microorganisms invading the lungs, which then results in focal and / or systemic inflammatory responses, such as coughing, expectoration, shivering, fever, etc. It is one of the common infectious diseases in clinical practice. Severe pneumonia (SP) is formed by the deterioration and aggravation of lung tissue (bronchioles, alveoli, interstitium) inflammation to a certain stage of the disease. The disease progresses rapidly and can lead to complications such as respiratory and circulatory failure, shock, and disseminated intravascular coagulation (DIC). If standardized treatment is not given in a timely manner, it is likely to cause multiple organ dysfunction and even endanger life, with a fatality rate as high as 30% - 50%. It is a respiratory infectious disease with extremely high morbidity and fatality rates globally.

[0003] Anti-infective treatment is the most important link in the management of severe pneumonia. The rational use of antibacterial drugs plays a crucial role in the prognosis and clinical outcome of severe pneumonia. In the existing anti-infective treatment, initial broad-spectrum antibacterial drugs are usually given to patients clinically diagnosed with severe pneumonia, which is likely to increase the risk of drug resistance. Moreover, in the existing prescription / doctor's order review, there are prone to irrational drug use phenomena such as inappropriate usage and dosage, inappropriate drug selection, and drug contraindications. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and a system for guiding drug use for severe pneumonia caused by multi-drug resistant Gram-negative bacilli in view of the problems existing in the existing anti-infective treatment.

[0005] A method for guiding drug use for severe pneumonia caused by multi-drug resistant Gram-negative bacilli includes obtaining the initial examination information of a patient; the initial examination information includes the patient's basic information, disease status information, multi-drug resistant Gram-negative bacilli infection risk information, and information on drugs in use; obtaining the etiological diagnosis information of the patient according to the test samples collected from the patient; determining the preliminary treatment plan for the patient using a prediction model according to the initial examination information and the etiological diagnosis information; the preliminary treatment plan includes a drug treatment plan, expected drug efficacy, and adverse reaction risks.

[0006] In one embodiment, after determining the preliminary treatment plan for the patient, the method further includes obtaining the review information of the patient after adopting the preliminary treatment plan; obtaining the drug exposure level information of the patient to anti-infective drugs according to the test samples collected from the patient; evaluating the treatment effect of the preliminary treatment plan using an evaluation model according to the review information and the drug exposure level information; adjusting the preliminary treatment plan according to the treatment effect to obtain an optimized treatment plan.

[0007] In one embodiment, determining a preliminary treatment plan for a patient using a prediction model based on the preliminary examination information and the etiological diagnosis information includes: judging whether the patient is infected with the multi-drug resistant Gram-negative bacilli according to the preliminary examination information and the etiological diagnosis information; in response to the judgment result that the patient is infected with the multi-drug resistant Gram-negative bacilli, evaluating the sensitivity of the patient to carbapenem antibiotics based on the pathogen detection result; according to the sensitivity of the patient to carbapenem antibiotics, using a prediction model to evaluate the predicted treatment result and predicted drug adverse reactions of different drug treatment plans for the patient, and selecting the best drug treatment plan; determining the usage and dosage of the best drug treatment plan according to the liver and kidney function status of the patient and the patient's basic information.

[0008] In one embodiment, determining the usage and dosage of the best drug treatment plan by combining the liver and kidney function status of the patient and the patient's basic information includes: judging the liver and kidney function status of the patient; when the liver and kidney function of the patient is abnormal, when selecting drugs according to the best drug treatment plan, avoiding selecting drugs with great liver and kidney function damage and adjusting the dosage; when the liver and kidney function of the patient is normal, judging whether the patient has individualized drug taboos according to the patient's basic information; when the patient has individualized drug taboos, when selecting drugs according to the best drug treatment plan, avoiding selecting taboo drugs and adjusting the dosing frequency and dosage according to the patient's weight.

[0009] In one embodiment, according to the patient's sensitivity to carbapenem antibiotics, a prediction model is used to evaluate the predicted treatment outcomes and predicted drug adverse reactions of different drug treatment regimens for the patient. Selecting the optimal drug treatment regimen includes: when the pathogen test result shows the production of KPC enzyme, according to the predicted treatment outcome and the predicted drug adverse reaction output by the prediction model, selecting ceftazidime-avibactam as the drug treatment regimen; when the pathogen test result shows the production of OXA-48 enzyme, according to the predicted treatment outcome and the predicted drug adverse reaction output by the prediction model, selecting ceftazidime-avibactam and aztreonam as the combined drug treatment regimen; when the pathogen test result shows the production of MBL enzyme, according to the predicted treatment outcome and the predicted drug adverse reaction output by the prediction model, selecting ceftazidime-avibactam and aztreonam as the combined drug treatment regimen; when the minimum inhibitory concentration of meropenem in the pathogen test result is 2 ≤ MIC < 8, according to the predicted treatment outcome and the predicted drug adverse reaction output by the prediction model, selecting to extend the infusion time of high-dose carbapenem and colistin / tigecycline / fosfomycin / aminoglycoside antibiotics as the combined drug treatment regimen; when the minimum inhibitory concentration of meropenem in the pathogen test result is MIC < 2, according to the predicted treatment outcome and the predicted drug adverse reaction output by the prediction model, selecting third-generation cephalosporins / cefoperazone sodium sulbactam / piperacillin tazobactam / carbapenem combined with quinolones / aminoglycosides as the drug treatment regimen; when the minimum inhibitory concentration of meropenem in the pathogen test result is MIC ≥ 16, according to the predicted treatment outcome and the predicted drug adverse reaction output by the prediction model, selecting colistin / tigecycline and fosfomycin / aminoglycosides / quinolones as the combined drug treatment regimen.

[0010] In one embodiment, the treatment effect includes drug effectiveness. Adjusting the initial treatment regimen according to the treatment effect to obtain an optimized treatment regimen includes: after treating the patient according to the initial treatment regimen for a preset time, obtaining the patient's infection detection information; judging whether the patient's symptoms have improved according to the infection detection information; when the patient's symptoms improve, reducing the dosage in the initial treatment regimen or changing the combined drug treatment to monotherapy or changing the drug from intravenous infusion to oral administration; when the patient's symptoms remain unchanged or worsen, adjusting the initial treatment regimen according to the patient's blood drug concentration.

[0011] In one embodiment, the treatment effect includes drug safety. Adjusting the initial treatment plan according to the treatment effect and obtaining an optimized treatment plan includes determining whether the patient has symptoms of antibiotic-related side effects; when the patient has symptoms of antibiotic-related side effects, reducing the dosage or stopping the administration in the initial treatment plan; when the patient does not have symptoms of antibiotic-related side effects, determining whether the liver and kidney functions of the patient are abnormal; when the liver and kidney functions of the patient are abnormal, reducing the dosage or stopping the administration in the initial treatment plan; when the liver and kidney functions of the patient are normal, adjusting the initial treatment plan according to the blood drug concentration of the patient.

[0012] In one embodiment, when the initial treatment plan is to treat multidrug-resistant Klebsiella pneumoniae with meropenem and the treatment effect of the initial treatment plan is not obvious, adjusting the initial treatment plan according to the blood drug concentration of the patient includes when the trough concentration of the patient's blood drug concentration is <8 μg / ml, increasing the dosage or prolonging the intravenous drip time in the initial treatment plan; when the trough concentration of the patient's blood drug concentration is 8 μg / ml ≤ trough concentration ≤ 45 μg / ml, replacing meropenem with other anti-infective drugs; when the trough concentration of the patient's blood drug concentration is >45 μg / ml, adjusting the dosage according to the creatinine clearance rate of the patient.

[0013] A medication guidance system for severe pneumonia caused by multidrug-resistant Gram-negative bacilli, including a patient information recording module for storing the initial examination information of the patient; the initial examination information includes patient basic information, disease status information, multidrug-resistant Gram-negative bacilli infection risk information, and current medication information; an etiological information recording module for storing the etiological diagnosis information of the patient; the etiological diagnosis information of the patient is determined based on the test samples collected from the patient; a plan formulation module, connected to the patient information recording module and the etiological information recording module, for determining the initial treatment plan of the patient using a prediction model according to the initial examination information and the etiological diagnosis information; the initial treatment plan includes a drug treatment plan, expected drug efficacy, and adverse reaction risk.

[0014] A computer device includes a memory and a processor. When the processor executes the computer program, the steps of the medication guidance method for severe pneumonia caused by multidrug-resistant Gram-negative bacilli according to any one of the above embodiments are implemented.

[0015] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the medication guidance method for severe pneumonia caused by multidrug-resistant Gram-negative bacilli according to any one of the above embodiments are implemented.

[0016] A computer program product includes a computer program which, when executed by a processor, implements the steps of the method for guiding drug use for severe pneumonia caused by multi-drug resistant Gram-negative bacilli described in any one of the above embodiments.

[0017] For the above method for guiding drug use for severe pneumonia caused by multi-drug resistant Gram-negative bacilli, initial examination information of a patient is obtained, and etiological diagnosis information of the patient is obtained based on the test samples collected from the patient. According to the initial examination information and the etiological diagnosis information, a preliminary treatment plan for the patient is determined using a prediction model. Among them, the preliminary treatment plan may include a drug treatment plan, expected drug efficacy, and the risk of adverse reactions. The patient is analyzed individually in combination with information such as the patient's basic information, disease status information, the risk information of multi-drug resistant Gram-negative bacilli infection, and the information of drugs in use, and the prediction model is used to analyze whether various treatment plans match the patient, so as to select the most suitable preliminary treatment plan for the patient. The preliminary treatment plan can be used as the basis for guiding rational drug use by clinicians, and solves the problem of formulating a drug use plan in the process of individualized treatment of patients. Based on the method for guiding drug use provided in this application, individualized drug treatment guidance opinions for patients can be provided quickly and accurately. While ensuring the anti-infection treatment effect, the occurrence of drug adverse reactions is prevented and reduced, and finally the clinical prognosis of patients with severe pneumonia is improved. Description of the Drawings

[0018] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a schematic flowchart of the method for guiding drug use for severe pneumonia caused by multi-drug resistant Gram-negative bacilli in one embodiment of this application;

[0020] Figure 2 It is a schematic flowchart of the method for optimizing the preliminary treatment plan in one embodiment of this application;

[0021] Figure 3 It is a schematic flowchart of the method for determining the preliminary treatment plan of a patient in one embodiment of this application;

[0022] Figure 4 It is a schematic flowchart of the method for determining the usage and dosage of drugs in one embodiment of this application;

[0023] Figure 5Schematic flowchart of a method for selecting an optimal drug treatment plan in one embodiment of the present application;

[0024] Figure 6 Schematic flowchart of a method for adjusting a preliminary treatment plan according to drug effectiveness in one embodiment of the present application;

[0025] Figure 7 Schematic flowchart of a method for adjusting a preliminary treatment plan according to drug safety in one embodiment of the present application;

[0026] Figure 8 Schematic flowchart of a method for adjusting a preliminary treatment plan according to blood drug concentration in one embodiment of the present application;

[0027] Figure 9 Schematic structural diagram of a drug guidance system for severe pneumonia caused by multi-drug resistant Gram-negative bacilli in one embodiment of the present application;

[0028] Figure 10 Schematic structural diagram of a system for implementing a drug guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli in one embodiment of the present application;

[0029] Figure 11 Internal structural diagram of a computer device in one embodiment of the present application. Detailed implementation manners

[0030] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant accompanying drawings. The preferred embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to understand the disclosure of the present invention more thoroughly and comprehensively.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0032] Evidence-based pharmacy (EBP) is an extension of evidence-based medicine in the field of pharmacy, which refers to the practice method and process in which clinical pharmacists systematically collect literature and evidence on relevant drug research, obtain information on drug safety, effectiveness, economy, etc., and make a clinical rational drug use plan based on this. Evidence-based pharmacy is an important decision-making method for pharmacy management and has played an irreplaceable guiding role in the field of pharmacy.

[0033] This application applies the pharmaceutical theory to the medication guidance for critically ill pneumonia patients infected with multi-drug resistant Gram-negative bacilli. By using a medication guidance method for multi-drug resistant Gram-negative bacilli in critically ill pneumonia provided by this application, it can assist physicians in providing accurate pharmaceutical opinions in the anti-infection treatment of critically ill pneumonia patients infected with multi-drug resistant Gram-negative bacilli.

[0034] Figure 1 It is a schematic flow chart of the medication guidance method for multi-drug resistant Gram-negative bacilli in critically ill pneumonia in one embodiment of this application. In one embodiment, the medication guidance method for multi-drug resistant Gram-negative bacilli in critically ill pneumonia may include the following steps S110 to step S130.

[0035] Step S110: Obtain the initial examination information of the patient; the initial examination information includes the patient's basic information, disease status information, multi-drug resistant Gram-negative bacilli infection risk information, and currently used drug information.

[0036] Before initiating anti-infection treatment for the patient, the initial examination information of the patient can be obtained first to facilitate a comprehensive assessment of the patient's individual status based on the initial examination information. In this embodiment, the initial examination information may include, but is not limited to, the patient's basic information, disease status information, multi-drug resistant Gram-negative bacilli infection risk information, and currently used drug information.

[0037] The patient's basic information may include, but is not limited to, individual information such as the patient's gender, age, height, weight, etc. The disease status information may refer to indicators that can assist in judging the patient's current individual status or are related to the disease, such as body temperature, respiratory symptoms, white blood cells, neutrophil ratio, C-reactive protein, procalcitonin, serum amyloid protein, erythrocyte sedimentation rate, etc. In some preferred embodiments, the disease status information may also include imaging examination results (such as pulmonary infection, pulmonary inflammation, etc.) and liver and kidney function indicators (such as transaminase levels, albumin, creatinine clearance rate, urea levels), etc.

[0038] The occurrence and outcome of severe pneumonia are usually related to factors such as the patient's living environment, underlying diseases, immune function, local pathogen epidemic status and drug resistance, and the choice of anti-infection treatment regimens, and there are individual differences in the absorption and metabolism of anti-infective drugs in patients. Therefore, the risk information of multidrug-resistant Gram-negative bacilli infection can refer to the individualized information related to the patient's multidrug-resistant Gram-negative bacilli, which is convenient for subsequent individualized precision treatment in the clinic based on the patient's multidrug-resistant Gram-negative bacilli infection risk information. For example, whether the patient is old, the use of broad-spectrum antibiotics in the past three months, whether there is a history of colonization or infection with multidrug-resistant bacteria, previous multiple or long-term hospitalizations, invasive operations such as mechanical ventilation, and whether the immune function is impaired (for example, patients with diabetes, cirrhosis, uremia, long-term use of immunosuppressants, tumor patients receiving radiotherapy or chemotherapy, etc. can be regarded as having a history of immunosuppression). Based on the risk information of multidrug-resistant Gram-negative bacilli infection, the resistance of the pathogens that may infect patients can be analyzed according to the recent characteristics of bacterial and fungal resistance in the country, province, and hospital.

[0039] The information on the drugs currently in use may refer to the information on the drugs currently in use by the patient. Based on the information on the drugs in use, the drug interactions can be better analyzed in the subsequent analysis to help design a more reasonable individualized medication plan. In a specific embodiment, the information on the drugs in use may include, but is not limited to, the medications used to treat the patient's previous underlying diseases after the current hospitalization, the medications used to relieve respiratory symptoms, the medications used for nutritional support therapy, the medications used to prevent deep vein thrombosis, the medications used to prevent stress ulcers, and other medication information.

[0040] Step S120: Acquire the patient's etiological diagnosis information based on the test sample collected from the patient.

[0041] Before carrying out anti-infection treatment on the patient, the patient's test sample can also be collected first. Among them, the test sample may include the patient's sputum specimen, alveolar lavage and other microbial specimens. By conducting microbial culture on the patient's test sample through traditional microbial culture (such as smear staining microscopy, microbial culture identification, antigen antibody detection, etc.) or sending it to mNGS (Metagenomics Next Generation Sequencing, metagenomic second generation sequencing) for microbial culture, the patient's etiological diagnosis information can be obtained according to the detection results. In a specific embodiment, the etiological diagnosis information may refer to the patient's pathogenic bacteria and drug resistance.

[0042] Step S130: Determine the patient's preliminary treatment plan using a prediction model based on the initial examination information and etiological diagnosis information; the preliminary treatment plan includes a drug treatment plan, expected drug efficacy, and adverse reaction risks.

[0043] In the embodiments of the present application, the prediction model may be a model pre-constructed based on big data algorithms. Among them, the big data algorithms may include, but are not limited to, decision trees, logistic regression, cluster analysis, or neural network methods, etc. Based on input information such as the initial examination information and etiological diagnosis information of the patient, the prediction model can predict information such as the individual treatment efficacy of drugs and drug adverse reactions for the patient. Among them, the input information may include, but is not limited to, information such as patient age, weight, creatinine clearance rate, liver function data, information on drugs in use, and the detection results of pathogenic microorganisms in the patient, etc. By analyzing and estimating the safety risks and expected efficacy of different drug treatment regimens for individual patients, the prediction model can select the best, safe and effective treatment regimen from different drug treatment regimens as the initial treatment regimen for the patient and output it.

[0044] In a specific implementation manner, data from different sources are uniformly stored in a database, and the above data is pre-processed such as cleaning, extraction, transformation, loading, and standardization processing to ensure consistent format and integrity and suitability for subsequent analysis. The database may store clinical usage information of different candidate drugs for treating multi-drug resistant Gram-negative bacilli, clinical pharmacokinetic research data of clinical drugs, and data such as the theoretical basis of etiology and pharmacology. Among them, the theoretical basis of etiology and pharmacology may include that clinical pharmacists in the field of anti-infection rely on authoritative books or guidelines. The theoretical basis of etiology and pharmacology may also include the diagnostic criteria for severe pneumonia, the selection of clinical treatment drugs for multi-drug resistant Gram-negative bacilli, data on the PK / PD (Pharmacokinetics / Pharmacodynamics) characteristics of anti-microbial drugs, a summary of adverse reactions of anti-bacterial drugs, a summary of drug use taboos and drug interactions, information on the antibacterial spectrum and tissue permeability of anti-microbial drugs, etc. The clinical usage information may include dosage adjustment methods for patients with liver and kidney insufficiency or obese patients, etc.

[0045] The data in the database is divided into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to optimize the model, and the test set is used to evaluate the performance of the model. In this embodiment, the clinical usage information of different candidate drugs for treating multi-drug resistant Gram-negative bacilli and the clinical pharmacokinetic research data stored in the database and other data may be as shown in Table A and Table B below. The theoretical basis of etiology and pharmacology stored in the database may include the classification and enzyme resistance characteristics of different types of enzyme inhibitors, the infection treatment regimens for different types of pathogenic bacteria, etc., as shown in Table C, Table D, Table E, Table F, Table G, Table H, and Table I below.

[0046]

[0047]

[0048]

[0049]

[0050] Calculate the Pearson correlation coefficient or other statistics between each feature and the target variable in the database, and screen out strongly correlated features. Extract the features that are most valuable for the prediction result. For example, according to the pathogen sensitivity profile, determine which antibiotics are most effective against the patient's infection; based on the patient's physiological parameters, consider the patient's liver and kidney function status to adjust the drug dosage; combine drug interactions to identify drug combinations that may affect the efficacy or increase the risk of side effects. Use machine learning algorithms to automatically select the most influential feature subset. For dynamically changing data (such as the change of drug concentration over time), features such as moving window averages and difference terms can be constructed. Create products or ratios between features to capture potential non-linear relationships. Select an appropriate model architecture according to the actual application scenario, train the model using the training set, tune the model using the validation set, and evaluate the performance of the model using the test set to ensure that the prediction model can accurately predict the effects of different treatment plans on the patient based on the input information.

[0051] Optimizing and adjusting the prediction model based on data such as the etiological and pharmacological theoretical basis stored in the database can help the prediction model accurately predict the individualized treatment effects of different treatment plans on the patient by referring to evidence-based bases such as the pathogen distribution and drug resistance characteristics of severe pneumonia patients in medical institutions, and the pharmacokinetics / pharmacodynamics characteristics of antibacterial drugs, and considering interaction factors such as the patient's liver and kidney function, age, and drugs.

[0052] In a specific implementation manner, the initial treatment plan may further include the variety selection, treatment dose, administration frequency, administration route, infusion rate, treatment course, usage and dosage of the recommended drug and off-label use restrictions, annotation of the drug's contraindications and the risk of interaction with other drugs or serious adverse reactions, and the experimental design plan for the next drug concentration monitoring.

[0053] The medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli provided in this application obtains the initial examination information of the patient, and obtains the etiological diagnosis information of the patient according to the test samples collected from the patient. According to the initial examination information and the etiological diagnosis information, a preliminary treatment plan for the patient is determined using a prediction model. Among them, the preliminary treatment plan may include a drug treatment plan, expected drug efficacy, and the risk of adverse reactions. The patient is analyzed individually by combining information such as the patient's basic information, disease status information, multi-drug resistant Gram-negative bacilli infection risk information, and information on medications in use, and the prediction model is used to analyze whether various treatment plans match the patient, so as to select the most suitable preliminary treatment plan for the patient. Based on the preliminary treatment plan report provided in this application, individualized medication treatment guidance opinions for the patient can be provided quickly and accurately. While ensuring the anti-infection treatment effect, the occurrence of drug adverse reactions is prevented and reduced, and finally the clinical prognosis of patients with severe pneumonia is improved.

[0054] In one embodiment, the database module is continuously updated according to data such as the latest drug clinical application information and clinical actual case information. At the same time, the prediction model can be further trained according to the updated data to optimize the accuracy of the prediction model.

[0055] In one embodiment, after determining the patient's preliminary treatment plan, a preliminary treatment plan report of the patient can also be output. The preliminary treatment plan report may include information such as past reference treatment cases, contraindications for using the drug, and the risk of interactions with other drugs, as well as the experimental design plan for the next drug concentration monitoring. The preliminary treatment plan report can be used as the basis for guiding rational drug use by clinicians, and helps to solve the problem of formulating a medication plan during the individualized treatment of patients.

[0056] Figure 2 This is a schematic flowchart of the method for optimizing the preliminary treatment plan in one embodiment of this application. In one embodiment, after determining the patient's preliminary treatment plan, the method may further include the following steps S210 to step S240.

[0057] Step S210: Obtain the review information of the patient after adopting the preliminary treatment plan.

[0058] Collect the patient's preliminary treatment plan and record the patient's review information. Among them, the review information may include, but is not limited to, disease efficacy status indicators and drug adverse reaction status indicators.

[0059] Step S220: Obtain the drug exposure level information of the patient to the anti-infection drug according to the test samples collected from the patient.

[0060] Before optimizing and adjusting the initial treatment plan, it is also possible to first collect the patient's test samples. Among them, the test sample can be the patient's plasma sample. By testing the patient's test sample, the drug content in the patient's body can be measured, and indicators such as AUC (Area Under the Curve, the area under the ROC curve), trough concentration, and half-life can be calculated to obtain information on the patient's individual drug exposure level and metabolism level.

[0061] In some feasible embodiments, at least one detection method among liquid chromatography, liquid chromatography-mass spectrometry, immunoassay, and chemiluminescence method can be used to obtain information on the in vivo exposure level of the patient's individual to the anti-infective drug from the patient sample.

[0062] Step S230: According to the review information and drug exposure level information, use the evaluation model to evaluate the treatment effect of the initial treatment plan.

[0063] In the embodiments of the present application, the evaluation model can also be a model constructed in advance based on big data algorithms. Among them, the big data algorithms can include but are not limited to decision trees, logistic regression, clustering analysis, or neural network methods, etc. The evaluation model can be based on the patient's review results and actual drug exposure level information or metabolism level information.

[0064] In a specific embodiment, the clinical evidence-based basis for the anti-infective treatment of multi-drug resistant Gram-negative bacilli and the research results of the pharmacokinetics of anti-infective drugs stored in the database can be used to establish an evaluation model that can be used to evaluate the treatment effect of the drug treatment plan by using big data algorithms. According to the patient's review results and actual drug exposure level or metabolism level and other information, the evaluation model can judge the treatment effect of the initial treatment plan. Further, it can be determined whether the treatment effect of the initial treatment plan meets the expectations, whether the adverse reactions are controllable, and whether the plan needs to be adjusted.

[0065] Step S240: Adjust the initial treatment plan according to the treatment effect to obtain an optimized treatment plan.

[0066] According to the comprehensive analysis of the treatment effect of the initial treatment plan in step S230, the initial treatment plan can be further optimized and adjusted to obtain an optimized treatment plan. By using the drug guidance method for multi-drug resistant Gram-negative bacilli severe pneumonia provided in the present application, the formulation of the provided drug treatment plan covers the entire process from initial diagnosis to late treatment, and can make the accuracy of the individualized treatment plan higher. For the combined drug use plan for anti-infection, analyze the drug interactions, select appropriate drug varieties, reduce the risk of potential drug adverse reactions, provide pharmaceutical opinions for the precise treatment of patients, and assist physicians in optimizing the drug use plan in a timely manner.

[0067] In one embodiment, after determining the optimized treatment plan for a patient, a report on the determined optimized treatment plan can also be generated. The report on the optimized treatment plan may include problems with the existing treatment plan, suggestions for adjusting the plan and specific methods, as well as information such as the expected drug efficacy and adverse reaction risks after the adjustment.

[0068] Figure 3 This is a schematic flowchart of the method for determining the initial treatment plan for a patient in one embodiment of the present application. In one embodiment, according to the initial examination information and etiological diagnosis information, using a prediction model to determine the initial treatment plan for the patient may include the following steps S310 to S340.

[0069] Step S310: According to the initial examination information and etiological diagnosis information, determine whether the patient is infected with multi-drug resistant Gram-negative bacteria.

[0070] Combining information such as the patient's body temperature, respiratory symptoms, blood routine, CRP (C-reactive protein), PCT (procalcitonin), SAA (serum amyloid A), imaging results, drug sensitivity results / NGS (Next Generation Sequencing) drug resistance detection results, and MDR-KP (multi-drug resistant Klebsiella pneumoniae) infection risk factor assessment, determine whether the patient is infected with multi-drug resistant Gram-negative bacteria.

[0071] In one embodiment, when it is determined that the patient is colonized with MDR-KP, the patient can be isolated and actively monitored. MDR-KP colonization refers to the presence of multi-drug resistant Klebsiella pneumoniae in the human body, but at this time the bacteria do not cause obvious infection symptoms, and this state is called "colonization" or "carriage". For patients colonized with MDR-KP, although they may not have current infection symptoms, they are at high risk because the colonized bacteria may turn into active infections at some point in the future, especially when the patient's immune system is impaired or affected by other factors. In addition, colonized patients can also be a source of pathogens, spreading the bacteria to other more susceptible populations. Therefore, isolating and actively monitoring patients colonized with MDR-KP can control the spread of MDR-KP.

[0072] Step S320: In response to the determination result that the patient is infected with multi-drug resistant Gram-negative bacteria, evaluate the patient's sensitivity to carbapenem antibiotics based on the pathogen detection results.

[0073] When it is determined that the patient is infected with multi-drug resistant Gram-negative bacteria, the patient's sensitivity to carbapenem antibiotics can be evaluated based on the pathogen detection results.

[0074] Step S330: Based on the patient's sensitivity to carbapenem antibiotics, use the prediction model to evaluate the predicted treatment outcomes and predicted drug adverse reactions of different drug treatment regimens for the patient, and select the best drug treatment regimen.

[0075] Import the patient's individual information such as the NGS test results, specific symptoms, metabolic status, drug interactions, etc., and the drugs in use and the microorganism test results into the prediction model. Use the prediction model to estimate the predicted treatment effects and predicted drug adverse reactions of the patient after using different treatment regimens, and select the best drug treatment regimen for the patient from them.

[0076] Step S340: Determine the dosage and administration method of the best drug treatment regimen based on the patient's liver and kidney function status and the patient's basic information.

[0077] After determining the best drug treatment regimen, the specific dosage and administration method of the best drug treatment regimen can be further determined according to the patient's liver and kidney metabolism status and individual drug taboos, etc., to determine the patient's initial treatment plan.

[0078] Figure 4 This is a schematic diagram of the method flow for determining the dosage and administration method of drugs in one embodiment of the present application. In one embodiment, determining the dosage and administration method of the best drug treatment regimen in combination with the patient's liver and kidney function status and the patient's basic information may include the following steps S410 to S440.

[0079] Step S410: Judge the patient's liver and kidney function status.

[0080] Step S420: When the patient's liver and kidney function is abnormal, when selecting drugs according to the best drug treatment regimen, avoid selecting drugs with great liver and kidney function damage, and adjust the dosage.

[0081] Step S430: When the patient's liver and kidney function is normal, judge whether the patient has individual drug taboos according to the patient's basic information.

[0082] Step S440: When the patient has individual drug taboos, when selecting drugs according to the best drug treatment regimen, avoid selecting taboo drugs, and adjust the dosing frequency and dosage according to the patient's weight.

[0083] When the patient's liver and kidney function is abnormal, when selecting drugs according to the best drug treatment regimen, drugs with great liver and kidney function damage should be avoided, and the dosage should be adjusted. Further, during the treatment process, the changes in the patient's liver and kidney function can also be closely monitored.

[0084] When the liver and kidney functions of the patient are normal, it is determined whether the patient has individualized drug contraindications based on the patient's basic information. In this embodiment, it can be determined whether the patient has individualized drug contraindications from the patient's basic information such as body surface area, serum albumin level status, whether the patient is pregnant, or whether the patient is a child, elderly, or other special group.

[0085] When the patient has individualized drug contraindications, when selecting drugs according to the optimal drug treatment plan, the contraindicated drugs should be avoided, and the drug administration and dosage adjustment should be carried out according to the patient's kilogram weight / corrected weight. Further, during the treatment process, the patient can also be monitored by TDM (therapeutic drug monitoring).

[0086] When the patient does not have individualized drug contraindications, when selecting drugs according to the optimal drug treatment plan, the conventional usage and dosage can be adopted, the patient can be educated about drug use, and the treatment effect and safety can be closely monitored.

[0087] Figure 5 This is a schematic flowchart of the method for selecting the optimal drug treatment plan in one embodiment of the present application. In one embodiment, according to the sensitivity of the patient to carbapenem antibiotics, the prediction model is used to evaluate the predicted treatment results and predicted drug adverse reactions of different drug treatment plans for the patient. Selecting the optimal drug treatment plan may include the following steps S510 to step S560.

[0088] Step S510: When the pathogen detection result is the production of KPC enzyme, according to the predicted treatment result and predicted drug adverse reaction output by the prediction model, ceftazidime-avibactam is selected as the drug treatment plan.

[0089] Step S520: When the pathogen detection result is the production of OXA-48 enzyme, according to the predicted treatment result and predicted drug adverse reaction output by the prediction model, ceftazidime-avibactam and aztreonam are selected as the combined drug treatment plan.

[0090] Step S530: When the pathogen detection result is the production of MBL enzyme, according to the predicted treatment result and predicted drug adverse reaction output by the prediction model, ceftazidime-avibactam and aztreonam are selected as the combined drug treatment plan.

[0091] Step S540: When the minimum inhibitory concentration of meropenem in the pathogen detection result is 2 ≤ MIC < 8, according to the predicted treatment result and predicted drug adverse reaction output by the prediction model, extending the infusion time of high-dose carbapenem and colistin / tigecycline / fosfomycin / aminoglycoside antibiotics are selected as the combined drug treatment plan.

[0092] Step S550: When the minimum inhibitory concentration of meropenem in the pathogen detection result is MIC < 2, select third-generation cephalosporins / cefoperazone sodium sulbactam / piperacillin tazobactam / carbapenems combined with quinolones / aminoglycosides as the drug treatment plan according to the predicted treatment result and predicted drug adverse reaction output by the prediction model.

[0093] Step S560: When the minimum inhibitory concentration of meropenem in the pathogen detection result is MIC ≥ 16, select colistin / tigecycline and fosfomycin / aminoglycosides / quinolones as the combined drug treatment plan according to the predicted treatment result and predicted drug adverse reaction output by the prediction model.

[0094] Based on the clinical use information of drugs in the database, a prediction model established by using big data algorithms will combine the pathogen detection results, infection symptoms, liver and kidney metabolism status, drug interactions, etc. of the patient to estimate the expected drug efficacy and expected drug adverse reactions for the patient.

[0095] In this embodiment, the process of determining the initial treatment plan for the patient by using the drug guidance method for severe pneumonia caused by multidrug-resistant Gram-negative bacilli provided by the present application is described, but it should not be construed as a limitation on the scope of the invention patent.

[0096] Example 1

[0097] The initial examination information and etiological diagnosis information of Patient A include the following data: male, 78 years old, 76 kg, admitted to the hospital due to fever accompanied by cough, expectoration, and dyspnea for 3 days, and aggravated with vomiting for 4 hours. The patient had a fever 3 days ago after getting cold, with the highest body temperature of 39.0°C, accompanied by cough and expectoration of white sticky sputum, accompanied by dyspnea, without chest pain, abdominal pain, diarrhea and other discomforts. Four hours ago, the above symptoms worsened, accompanied by nausea and vomiting of gastric contents. Relevant tests were completed upon admission: C-reactive protein 79.87 mg / L↑; blood routine: white blood cells 17.25 × 109 / L↑, neutrophil ratio 94.30%↑; blood gas analysis + potassium, sodium, chloride, calcium + lactate: partial pressure of oxygen 85.50 mmHg; chest CT showed that most of the upper lobe of the left lung was not clear, multiple bronchial walls in the left lung were thickened, the lumen was dilated, and there were infectious lesions in both lungs. The initial diagnosis was severe pneumonia, and anti-infective drug treatment was planned.

[0098] Collect the alveolar lavage specimens of the patient for traditional microbial culture and NGS detection, and the detection results are shown in the following table:

[0099] Table 1 Microbial detection results of the patient

[0100]

[0101]

[0102] The NGS monitoring result of the patient's bronchoalveolar lavage fluid showed Klebsiella pneumoniae. The enzyme type was identified as producing AmpC enzyme, and the patient had severe pneumonia symptoms such as fever, cough with expectoration, dyspnea, and type I respiratory failure. By using a prediction model to predict different drug treatment regimens for patient A, the summary table of the predicted efficacy and adverse reactions as shown in Table 2 below can be obtained.

[0103] Table 2 Summary Table of Predicted Efficacy and Adverse Reactions of Drugs

[0104]

[0105]

[0106] Note: √√ indicates that the prediction result of the prediction model has good efficacy for most of the patient's symptoms or has no side effect risk for the patient; √ indicates that the prediction result of the prediction model has a certain therapeutic effect on some of the patient's symptoms or has a relatively low side effect risk for the patient; × indicates that the prediction result of the prediction model has little efficacy on the patient's symptoms or has a certain side effect risk; ×× indicates that the prediction result of the prediction model is that the drug has no obvious efficacy or can cause serious adverse reactions.

[0107] According to the above table, the optimal drug regimen for patient A is to use meropenem as the treatment drug. Further, based on the liver and kidney metabolism function, liver and kidney metabolism status, and individual drug taboos of patient A, determine the best dose with the best efficacy and fewer adverse reactions in the optimal drug treatment plan, and refer to the clinical use guidelines and industry guidelines for anti-infection treatment.

[0108] In this application example, the creatinine clearance rate of patient A is 44.31 ml / min. The optimal dosing frequency can be determined as q12h, 0.5 g each time. It is expected that the respiratory symptoms such as fever and cough with expectoration of the patient can be basically improved 72 hours after treatment, and the probability of serious adverse reactions in this plan is relatively low. Meropenem is a time-dependent antibacterial drug. The percentage of the time that the blood drug concentration remains above the minimum inhibitory concentration (MIC) (i.e., T > MIC) in the dosing interval (i.e., %T > MIC) is the main index of its pharmacokinetic / pharmacodynamic (PK / PD) parameters. The free drug concentration (Cf) in the blood plasma can play an effective antibacterial role when it is maintained at 30%-40%T > MIC, and the maximum bactericidal effect can be achieved when it is maintained at 60%-70%T > MIC. Thus, it can be seen that the effective drug concentration of meropenem is the key factor in treating patient A. Further, drug concentration monitoring for patient A can be started 24-48 hours after the administration of the drug to patient A, and blood is collected 30 minutes before the next dose to monitor the trough concentration.

[0109] Summarize the above information to generate a preliminary treatment plan report. The preliminary treatment plan report may include information such as the best treatment drugs, dosage, administration method, and administration frequency, the expected treatment effects and adverse reactions, the contraindications of the drugs and the risk of interactions with other drugs, as well as the most similar clinical actual treatment cases, etc., for reference by physicians and patients.

[0110] Figure 6 This is a schematic flowchart of the method for adjusting the preliminary treatment plan according to drug effectiveness in one embodiment of the present application. In one embodiment, the treatment effect may include drug effectiveness. Adjusting the preliminary treatment plan according to the treatment effect to obtain an optimized treatment plan may include the following steps S610 to S640.

[0111] Step S610: After treating the patient for a preset time according to the preliminary treatment plan, obtain the patient's infection detection information.

[0112] In this embodiment, the preset time may be 48 - 72 hours. That is, after treating the patient for 48 - 72 hours according to the preliminary treatment plan, collect the patient's infection detection information. Among them, the infection detection information may include but is not limited to infection indicators, blood routine, CRP, PCT indicators, etc.

[0113] Step S620: Judge whether the patient's symptoms have improved according to the infection detection information.

[0114] Step S630: When the patient's symptoms improve, reduce the dosage in the preliminary treatment plan or change the combination drug treatment to monotherapy or change the drug administration from intravenous drip to oral administration.

[0115] Step S640: When the patient's symptoms remain unchanged or worsen, adjust the preliminary treatment plan according to the patient's blood drug concentration.

[0116] Based on the infection detection information, judge whether the patient's symptoms have improved. When the patient's symptoms improve significantly, the dosage in the preliminary treatment plan can be reduced or the combination drug treatment can be changed to monotherapy or the drug administration can be changed from intravenous drip to oral administration. When the patient's symptoms do not improve significantly or worsen, adjust the preliminary treatment plan according to the patient's blood drug concentration.

[0117] Figure 7 This is a schematic flowchart of the method for adjusting the preliminary treatment plan according to drug safety in one embodiment of the present application. In one embodiment, the treatment effect may also include drug safety. Adjusting the preliminary treatment plan according to the treatment effect to obtain an optimized treatment plan may further include the following steps S710 to S750.

[0118] Step S710: Determine whether the patient has symptoms of antibiotic-related side effects.

[0119] Step S720: When the patient has symptoms of antibiotic-related side effects, reduce the dosage in the initial treatment plan or stop administering the drug.

[0120] Step S730: When the patient does not have symptoms of antibiotic-related side effects, determine whether the patient's liver and kidney functions are abnormal.

[0121] Step S740: When the patient's liver and kidney functions are abnormal, reduce the dosage in the initial treatment plan or stop administering the drug.

[0122] Step S750: When the patient's liver and kidney functions are normal, adjust the initial treatment plan according to the patient's blood drug concentration.

[0123] Determine whether the patient has symptoms of antibiotic-related side effects. When obvious symptoms of antibiotic-related side effects occur, the dosage in the initial treatment plan can be reduced or the drug administration can be stopped. In some specific embodiments, the symptoms of antibiotic-related side effects may include, but are not limited to, diarrhea and neurological toxicity manifestations such as flushing, dizziness, and blurred vision.

[0124] When the patient does not have symptoms of antibiotic-related side effects, it is possible to further determine whether the patient's liver and kidney functions are abnormal. When the patient's liver and kidney functions are abnormal, similarly, the dosage in the initial treatment plan can be reduced or the drug administration can be stopped. When the patient's liver and kidney functions are normal, the initial treatment plan can be adjusted according to the patient's blood drug concentration.

[0125] Figure 8 This is a schematic flowchart of the method for adjusting the initial treatment plan according to the blood drug concentration in one embodiment of the present application. In one embodiment, taking the initial treatment plan of using meropenem to treat multidrug-resistant Klebsiella pneumoniae as an example, the optimization and adjustment method of the initial treatment plan will be described. Adjusting the initial treatment plan according to the patient's blood drug concentration may include the following steps S810 to S830.

[0126] Step S810: When the patient's blood drug concentration is the trough concentration < 8 ug / ml, increase the dosage in the initial treatment plan or extend the intravenous drip time.

[0127] Step S820: When the patient's blood drug concentration is 8 ug / ml ≤ trough concentration ≤ 45 ug / ml, replace meropenem with other anti-infective drugs.

[0128] Step S830: When the patient's blood drug concentration is the trough concentration > 45 ug / ml, adjust the dosage according to the patient's creatinine clearance rate.

[0129] In this embodiment, taking the initial treatment plan of using meropenem to treat multidrug-resistant Klebsiella pneumoniae with an insignificant treatment effect of the initial treatment plan as an example, an optimization method for adjusting the initial treatment plan according to the patient's blood drug concentration will be described. When the average blood drug concentration of the patient in the stable state is the trough concentration < 8 μg / ml, the dosage in the initial treatment plan can be increased or the intravenous drip time can be extended (such as increased to 3 hours); when the average blood drug concentration of the patient in the stable state is 8 μg / ml ≤ trough concentration ≤ 45 μg / ml, meropenem can be replaced with other anti-infective drugs; when the average blood drug concentration of the patient in the stable state is the trough concentration > 45 μg / ml, the dosage is adjusted according to the patient's creatinine clearance rate.

[0130] In some other feasible embodiments, when the initial treatment plan is to use polymyxin B to treat multidrug-resistant Pseudomonas aeruginosa with an insignificant treatment effect of the initial treatment plan, when the average blood drug concentration of the patient in the stable state is the trough concentration < 2 mg / L, the dosage in the initial treatment plan can be increased, but it is not recommended to exceed the conventional dosage, and nebulized inhalation treatment can also be added if necessary; when the average blood drug concentration of the patient in the stable state is 2 mg / L ≤ trough concentration ≤ 4 mg / L, the anti-infective drug does not need to be adjusted; when the average blood drug concentration of the patient in the stable state is the trough concentration > 4 mg / L, the dosage is adjusted according to the patient's creatinine clearance rate.

[0131] In this embodiment, the workflow of obtaining the patient's initial treatment plan by using the drug guidance method for severe pneumonia caused by multidrug-resistant Gram-negative bacilli provided in this application and optimizing the initial treatment plan is described, but it should not be construed as a limitation on the scope of the invention patent.

[0132] Example 2

[0133] Patient B, male, 78 years old, 76 kg, was admitted to the hospital due to fever accompanied by cough, expectoration, and dyspnea for 3 days, and aggravated with vomiting for 4 hours. The patient had a fever 3 days ago after getting cold, with a maximum body temperature of 39.0°C, accompanied by cough and expectoration of white sticky sputum, accompanied by dyspnea, without chest pain, abdominal pain, diarrhea and other discomforts. Four hours ago, the above symptoms aggravated, accompanied by nausea and vomiting of gastric contents. The initial diagnosis was severe pneumonia. After determining the patient's initial treatment plan by using the drug guidance method for severe pneumonia caused by multidrug-resistant Gram-negative bacilli provided in this application, patient B was given an initial treatment of meropenem 0.5 g q12h by intravenous drip according to the initial treatment plan.

[0134] After 72 hours of drug administration, the infection detection information of Patient B was collected, and the following evaluation of the treatment effect was made based on the infection detection information: The respiratory symptoms of Patient B improved significantly, coughing and expectoration were reduced compared to before, dyspnea was relieved, and the body temperature was normal. The review information of Patient B is shown in Table 3 below.

[0135] Table 3 Patient's basic information and drug concentration monitoring results

[0136]

[0137] A drug concentration monitoring experiment was carried out on Patient B. Before the first drug administration on the 3rd day of treatment based on the initial treatment plan, the serum sample of the patient was collected, and the trough drug concentration level of Patient B was detected to be 7 μg / mL by liquid chromatography-mass spectrometry. An evaluation model for the meropenem dosing regimen was constructed using the clinical guidelines and dose adjustment methods for meropenem stored in the database. Combining the patient's blood drug concentration value, liver and kidney function and other information of Patient B, the treatment information and drug concentration monitoring results of this patient were imported into the model. The initial treatment plan was evaluated from the aspects of drug effectiveness and drug safety and other treatment effects, and further based on the evaluation results, the optimization method for the initial treatment plan as shown in Table 4 could be determined.

[0138] Table 4 Evaluation results of the treatment effect of the initial treatment plan

[0139]

[0140] The evaluation model evaluated the initial treatment plan from two perspectives: drug effectiveness and drug safety. From the perspective of drug effectiveness (i.e., the efficacy perspective), the meropenem blood drug concentration in Patient B's body was lower than the lower limit of the normal value reference range. After retesting the renal function 72 hours after treatment, the patient's renal function (creatinine clearance rate) improved compared to before treatment. Therefore, it was predicted that the subsequent treatment effect of the initial treatment plan would be good. According to the evaluation results of drug effectiveness and the meropenem blood drug concentration in Patient B's body, it could be recommended to increase the dosing frequency or increase the single-dose administration amount. For example, the dosing amount in the initial treatment plan was adjusted to 0.5 g q8h.

[0141] From the perspective of drug safety (i.e., the risk of side effects), the renal function of Patient B has improved compared to that before treatment, and Patient B has no adverse reactions such as antibiotic-associated diarrhea. Therefore, it is predicted that the risk of side effects of the initial treatment plan in the future is relatively low. According to the evaluation results of drug safety and the meropenem blood drug concentration in Patient B, it can be judged that it is recommended to increase the dosing frequency and / or extend the infusion time to increase the time that the blood drug concentration is maintained within the normal reference range of the minimum inhibitory concentration (MIC). Considering that meropenem has linear pharmacokinetic characteristics, a short half-life, the blood drug concentration decreases rapidly, and the %T > MIC decreases. The pharmacokinetics during continuous dosing is almost the same as that during single dosing, without accumulation. Therefore, it is recommended to extend the infusion time to 3 hours, which can extend the %T > MIC.

[0142] Furthermore, by combining the improvement suggestions from the two perspectives of drug efficacy and drug safety, the optimized treatment plan can be determined as adjusting the dosing frequency to 0.5 g q8h and extending the infusion time to 3 h. Conduct anti-infection treatment for Patient B based on the adjusted optimized treatment plan. It is expected that the efficacy will improve significantly compared to the previous treatment, and the risk of adverse reactions will not increase significantly.

[0143] It should be understood that although the steps in the flowchart of the accompanying drawings of the specification are shown in sequence according to the indication of the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings of the specification may include multiple steps or multiple stages. These steps or stages do not necessarily need to be completed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of the steps or stages in other steps or other steps.

[0144] Based on the description of the above-mentioned multi-drug resistant Gram-negative bacilli severe pneumonia medication guidance method embodiment, the present disclosure also provides a multi-drug resistant Gram-negative bacilli severe pneumonia medication guidance system. The system may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiment of this specification and combined with a device for implementing the necessary hardware. Based on the same innovative concept, the system in one or more embodiments provided by the embodiment of the present disclosure is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the system are similar, the implementation of the specific system of the embodiment of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for predetermined functions. Although the system described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0145] The present application also provides a medication guidance system for severe pneumonia caused by multidrug-resistant Gram-negative bacteria. Figure 9 This is a structural diagram of a medication guidance system for severe pneumonia caused by multidrug-resistant Gram-negative bacteria in one of the embodiments of the present application. In one of the embodiments, the medication guidance system for severe pneumonia caused by multidrug-resistant Gram-negative bacteria may include a patient information recording module 100, a pathogen information recording module 200 and a regimen formulation module 300.

[0146] The patient information recording module 100 can be used to store the patient's initial examination information; the initial examination information may include the patient's basic information, disease status information, multidrug-resistant Gram-negative bacillus infection risk information and information on medications in use.

[0147] The etiology information recording module 200 can be used to store the etiology diagnosis information of the patient; the etiology diagnosis information of the patient is determined based on the test sample collected from the patient.

[0148] The plan formulation module 300 can be connected to the patient information recording module 100 and the etiology information recording module 200 respectively. The plan formulation module 300 can be used to determine the patient's preliminary treatment plan based on the initial examination information and etiology diagnosis information using a prediction model; the preliminary treatment plan may include a drug treatment plan, expected drug efficacy and adverse reaction risks.

[0149] The medication guidance system for severe pneumonia caused by multi-drug resistant Gram-negative bacilli provided by this application. The patient information recording module 100 stores the initial examination information of the patient. The etiological information recording module 200 obtains the etiological diagnosis information of the patient from the test samples collected from the patient and stores it. The treatment plan formulation module 300 obtains the initial examination information and etiological diagnosis information of the patient from the patient information recording module 100 and the etiological information recording module 200, and uses a prediction model to determine the initial treatment plan for the patient. Among them, the initial treatment plan may include a drug treatment plan, expected drug efficacy, and adverse reaction risk.

[0150] In one embodiment, the medication guidance system for severe pneumonia caused by multi-drug resistant Gram-negative bacilli may further include a database, in which clinical use information of different candidate drugs for treating multi-drug resistant Gram-negative bacilli, clinical pharmacokinetic research data of clinical drugs, and other data can be stored. The data from different sources are uniformly stored in the database, and the above data are preprocessed such as cleaning, extraction, transformation, loading, and standardization to ensure consistent format and integrity and suitability for subsequent analysis. The system can divide the data stored in the database into a training set, a validation set, and a test set, use the training samples to train the prediction model, and optimize and adjust the prediction model based on data such as the theoretical basis of etiology and pharmacology stored in the database to ensure the accuracy of the prediction model.

[0151] Among them, the theoretical basis of etiology and pharmacology may include that clinical pharmacists in the field of anti-infection rely on authoritative books or guidelines. The theoretical basis of etiology and pharmacology may also include the diagnostic criteria for severe pneumonia, the selection of clinical treatment drugs for multi-drug resistant Gram-negative bacilli, data on the PK / PD (Pharmacokinetics / Pharmacodynamics) characteristics of anti-microbial drugs, a summary of adverse reactions of anti-bacterial drugs, information on drug use taboos and drug interactions, information on the antibacterial spectrum and tissue permeability of anti-microbial drugs, etc. The clinical use information may include dosage adjustment methods for patients with liver and kidney insufficiency or obese patients, etc.

[0152] Optimizing and adjusting the prediction model based on data such as the theoretical basis of etiology and pharmacology can help the prediction model accurately predict the individualized treatment effects of different treatment plans on patients by referring to evidence-based bases such as the distribution and drug resistance characteristics of pathogens in severe pneumonia patients in medical institutions and the PK / PD characteristics of anti-bacterial drugs, considering interaction factors such as the patient's liver and kidney function, age, and drugs.

[0153] Using the above system to conduct individualized analysis of patients by combining information such as the patient's basic information, disease status information, multi-drug resistant Gram-negative bacillus infection risk information, and information on drugs in use. The prediction model is used to analyze whether various treatment plans match the patient, so as to select the most suitable initial treatment plan for the patient. Based on the initial treatment plan report provided by this application, individualized medication treatment guidance for the patient can be quickly and accurately provided to the physician. While ensuring the anti-infection treatment effect, prevent and reduce the occurrence of drug adverse reactions, and ultimately improve the clinical prognosis of patients with severe pneumonia. The drug treatment plan formulated by the system covers the entire process from initial diagnosis to later treatment. For the combined medication plan for anti-infection, it can analyze drug interactions, select appropriate drug varieties, and reduce the risk of potential drug adverse reactions.

[0154] In one embodiment, the medication guidance system for multi-drug resistant Gram-negative bacillus severe pneumonia may further include a treatment information update module and an optimization and adjustment module. The treatment information update module can obtain the review information of the patient after adopting the initial treatment plan, and obtain the drug exposure level information of the patient to anti-infection drugs according to the test samples collected from the patient.

[0155] The optimization and adjustment module can obtain the review information and drug exposure level information of the patient through the treatment information update module, and use the evaluation model to evaluate the treatment effect of the initial treatment plan according to the review information and drug exposure level information, and adjust the initial treatment plan according to the treatment effect to obtain an optimized treatment plan.

[0156] In one embodiment, the medication guidance system for multi-drug resistant Gram-negative bacillus severe pneumonia may further include a report module. The report module can generate an initial treatment plan report according to the initial treatment plan output by the plan formulation module 300 in combination with a report template. The initial treatment plan report may include a specific drug treatment plan, expected drug efficacy, and possible drug adverse reactions. In some preferred embodiments, the initial treatment plan report may further include the variety selection, dosage, administration frequency, administration route, treatment course of antibacterial drugs, notes on the contraindications of the drug and the risk of drug interactions with other drugs, and the experimental design plan for the next drug concentration monitoring.

[0157] In one embodiment, the report module can also adjust the initial treatment plan report according to the optimized treatment plan output by the optimization and adjustment module to obtain an optimized treatment plan report. Alternatively, the report module can also generate an optimized treatment plan report according to the optimized treatment plan output by the optimization and adjustment module in combination with a report template. The optimized treatment plan report may include problems with the existing treatment plan, adjustment suggestions and specific methods for the plan, and information such as the expected drug efficacy and adverse reaction risk after adjustment.

[0158] In one embodiment, the system can also continuously update the database, add drug clinical application information and clinical actual case information. At the same time, the system can further update the big data analysis model based on the above updates, thereby improving the accuracy of the system.

[0159] It can be understood that the various embodiments of the above methods, systems, etc. in this specification are all described in a progressive manner. For the same / similar parts between the various embodiments, reference can be made to each other, and the key points of each embodiment are the differences from other embodiments. For the relevant parts, reference can be made to the descriptions of other method embodiments.

[0160] Figure 10 It is a schematic structural diagram of a system for implementing a drug guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli in one embodiment of the present application. Refer to Figure 10 , the drug guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli may include a processing component S20, which further includes one or more processors, and memory resources represented by a memory S22 for storing instructions executable by the processing component S20, such as application programs. The application programs stored in the memory S22 may include one or more than one instruction, and each module corresponds to a set of instructions. In addition, the processing component S20 is configured to execute instructions to perform the above-mentioned drug guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli.

[0161] The drug guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli may further include: a power supply component S24 configured to perform power management of the drug guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli, a wired or wireless network interface S26 configured to connect the drug guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli based on a CGAN neural network to the network, and an input / output (I / O) interface S28. The drug guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli can operate based on an operating system stored in the memory S22, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD or the like.

[0162] In an exemplary embodiment, there is also provided a computer-readable storage medium including instructions, such as the memory S22 including instructions, and the above instructions can be executed by the processor of the drug guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli to complete the above method. The storage medium may be a computer-readable storage medium. For example, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0163] In an exemplary embodiment, a computer program product is further provided. The computer program product includes instructions that can be executed by a processor of a medication guidance system S00 for severe pneumonia caused by multi-drug resistant Gram-negative bacilli to complete the above method.

[0164] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 11 shown. Figure 11 This is the internal structure diagram of the computer device in one embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to users and tasks used in the above method for guiding the use of medications for severe pneumonia caused by multi-drug resistant Gram-negative bacilli. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a method for guiding the use of medications for severe pneumonia caused by multi-drug resistant Gram-negative bacilli.

[0165] Those skilled in the art can understand that Figure 11 the structure shown in

[0166] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, a database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include Read-Only Memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0167] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the hardware + program type embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0168] It should be noted that the above-mentioned devices, electronic devices, servers, etc. may also include other implementation manners according to the description of the method embodiments. The specific implementation manners may refer to the description of the relevant method embodiments. At the same time, the new embodiments formed by the mutual combination of the features among the various methods, as well as the device, equipment, and server embodiments, still fall within the scope of the embodiments covered by the present disclosure, and will not be elaborated one by one here.

[0169] In the description of this specification, the descriptions referring to terms such as "some embodiments", "other embodiments", "ideal embodiments", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example.

[0170] The technical features of the above-mentioned embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered that it is within the scope described in this specification.

[0171] The above-mentioned embodiments only represent several implementation manners of the present invention. The descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent should be subject to the appended claims.

Claims

1. A medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli, characterized in that, Comprising: Obtaining the initial examination information of the patient; the initial examination information includes patient basic information, disease status information, multi-drug resistant Gram-negative bacillus infection risk information, and information on medications in use; Obtaining the etiological diagnosis information of the patient based on the test samples collected from the patient; Determining a preliminary treatment plan for the patient using a prediction model based on the initial examination information and the etiological diagnosis information; the preliminary treatment plan includes a drug treatment plan, expected drug efficacy, and adverse reaction risks.

2. The medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli according to claim 1, characterized in that, After determining the preliminary treatment plan for the patient, the method further includes: Obtaining the review information of the patient after adopting the preliminary treatment plan; Obtaining the drug exposure level information of the patient to the anti-infective drugs based on the test samples collected from the patient; Evaluating the treatment effect of the preliminary treatment plan using an evaluation model based on the review information and the drug exposure level information; Adjusting the preliminary treatment plan based on the treatment effect to obtain an optimized treatment plan.

3. The medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli according to claim 1, characterized in that, The determining the preliminary treatment plan for the patient using a prediction model based on the initial examination information and the etiological diagnosis information includes: Judging whether the patient is infected with the multi-drug resistant Gram-negative bacillus based on the initial examination information and the etiological diagnosis information; In response to the judgment result that the patient is infected with the multi-drug resistant Gram-negative bacillus, evaluating the sensitivity of the patient to carbapenem antibiotics based on the pathogen detection results; Evaluating the predicted treatment results and predicted drug adverse reactions of different drug treatment plans for the patient using a prediction model based on the sensitivity of the patient to carbapenem antibiotics, and selecting the best drug treatment plan; Determining the dosage and usage of the best drug treatment plan based on the liver and kidney function status and basic information of the patient.

4. The medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli according to claim 3, wherein, The determining the dosage and usage of the drug of the best drug treatment plan by combining the liver and kidney function status and basic information of the patient includes: Judging the liver and kidney function status of the patient; When the liver and kidney function of the patient is abnormal, when selecting drugs according to the best drug treatment plan, avoid selecting drugs with great liver and kidney function damage, and adjust the dosage; When the liver and kidney function of the patient is normal, judging whether the patient has individualized drug taboos based on the basic information of the patient; When the patient has individualized drug taboos, when selecting drugs according to the best drug treatment plan, avoid selecting taboo drugs, and adjust the dosing frequency and dosage according to the patient's weight.

5. The medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli according to claim 2, characterized in that, The treatment effect includes drug effectiveness, and the adjusting the preliminary treatment plan based on the treatment effect to obtain an optimized treatment plan includes: After treating the patient according to the preliminary treatment plan for a preset time, obtaining the infection detection information of the patient; Judging whether the symptoms of the patient have improved based on the infection detection information; When the symptoms of the patient improve, reducing the dosage in the preliminary treatment plan, or changing the combined drug treatment to monotherapy, or changing the drug from intravenous drip to oral administration; When the symptoms of the patient remain unchanged or worsen, adjusting the preliminary treatment plan according to the blood drug concentration of the patient.

6. The medication guidance method for severe pneumonia caused by multi-drug resistant Gram-negative bacilli according to claim 2, wherein, The treatment effects include drug safety. Adjusting the preliminary treatment plan according to the treatment effects to obtain an optimized treatment plan includes: Determining whether the patient has symptoms of antibiotic-related side effects; When the patient has symptoms of antibiotic-related side effects, reducing the dosage of the preliminary treatment plan or stopping the administration of the drug; When the patient does not have symptoms of antibiotic-related side effects, determining whether the liver and kidney functions of the patient are abnormal; When the liver and kidney functions of the patient are abnormal, reducing the dosage of the preliminary treatment plan or stopping the administration of the drug; When the liver and kidney functions of the patient are normal, adjusting the preliminary treatment plan according to the blood drug concentration of the patient.

7. A medication guidance system for severe pneumonia caused by multi-drug resistant Gram-negative bacilli, characterized in that, Including: A patient information recording module for storing the initial examination information of the patient; the initial examination information includes patient basic information, disease status information, multi-drug resistant Gram-negative bacillus infection risk information, and information on drugs in use; A pathogen information recording module for storing the pathogen diagnosis information of the patient; the pathogen diagnosis information of the patient is determined based on the test samples collected from the patient; A plan formulation module, connected to the patient information recording module and the pathogen information recording module, for determining the preliminary treatment plan of the patient using a prediction model according to the initial examination information and the pathogen diagnosis information; the preliminary treatment plan includes a drug treatment plan, expected drug efficacy, and adverse reaction risks.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the drug guidance method for multi-drug resistant Gram-negative bacillus severe pneumonia according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the drug guidance method for multi-drug resistant Gram-negative bacillus severe pneumonia according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the drug guidance method for multi-drug resistant Gram-negative bacillus severe pneumonia according to any one of claims 1 to 6.

Images