Machine Learning Algorithms to Predict the Mortality of Carbapenem Resistant Klebsiella Pneumoniae bacteremia

2019 ◽  
Author(s):  
Qiqiang Liang ◽  
Fang Qian ◽  
Yibing Chen ◽  
Zhijun Xu ◽  
Zhijiang Xu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Septic Shock ◽  
High Risk ◽  
Klebsiella Pneumoniae ◽  
Severe Thrombocytopenia ◽  
Acute Renal Injury ◽  
High Risk Factors ◽  
Carbapenem Resistant ◽  
Logical Regression

Abstract Purpose To establish mortality prediction models in 14 days of Carbapenem-Resistant Klebsiella Pneumoniae bacteremia using Machine learning.Materials and Methods It is a single-center retrospective study. We collect the relevant clinical information of all patients with Carbapenem-Resistant Klebsiella Pneumoniae (CRKP) bacteremia in the past 5 years using the local database. Data analysis and verification are carried out by multiple logical regression, decision tree, random forest, support vector machine (SVM), and XGBoost.Result This study includes 187 patients with 40 related variables. In multiple logical regression, acute renal injury (P=0.003), Apache II score (P=0.036), immunodeficiency (P=0.025), severe thrombocytopenia (P=0.025) and septic shock (P=0.044) are the high-risk factors for 14 days mortality of CRKP bloodstream infections. According to the importance of those parameters, risk scoring is established to predict the survival rate of CRKP bacteremia. The analysis of the five models, with 70% training set and 30% test set, show the comprehensive performance of random forest (AUROC=0.953, precision=91.85%) is slightly better than that of XGBoost (AUROC=0.912, precision=86.41%) and SVM (AUROC=0.936, precision=79.89%) in predicting 14-day mortality of CRKP bacteremia. The multiple logical regression model (AUROC=0.825, precision=81.52%) is the second, and the decision tree model (AUROC=0.712, precision=79.89%) is not very ideal.Conclusion Machine learning has good performances in predicting 14-day mortality of CRKP bacteremia than multiple logical regression. Acute renal injury, severe thrombocytopenia, and septic shock are the high-risk factors of CRKP bacteremia mortality.

Disease Severity Is an Independent Risk Factor of Mortality and Outcomes in Critically Ill Patients With Carbapenem-resistant Klebsiella Pneumoniae Bloodstream Infections: a 5-year Retrospective Analysis

2021 ◽  
Author(s):  
Yuzhen Qiu ◽  
Wen Xu ◽  
Yunqi Dai ◽  
Ruoming Tan ◽  
Jialin Liu ◽  
...  
Keyword(s):  
Risk Factors ◽  
Septic Shock ◽  
Klebsiella Pneumoniae ◽  
Critically Ill Patients ◽  
Bloodstream Infections ◽  
Polymyxin B ◽  
Mortality Rates ◽  
Carbapenem Resistant ◽  
All Cause Mortality ◽  
Independent Risk Factors

Abstract Background: Carbapenem-resistant Klebsiella pneumoniae bloodstream infections (CRKP-BSIs) are associated with high morbidity and mortality rates, especially in critically ill patients. Comprehensive mortality risk analyses and therapeutic assessment in real-world practice are beneficial to guide individual treatment.Methods: We retrospectively analyzed 87 patients with CRKP-BSIs (between July 2016 and June 2020) to identify the independent risk factors for 28-day all-cause mortality. The therapeutic efficacies of tigecycline-and polymyxin B-based therapies were analyzed.Results: The 28-day all-cause mortality and in-hospital mortality rates were 52.87% and 67.82%, respectively, arising predominantly from intra-abdominal (56.32%) and respiratory tract infections (21.84%). A multivariate analysis showed that 28-day all-cause mortality was independently associated with the patient’s APACHE II score (p = 0.002) and presence of septic shock at BSI onset (p = 0.006). All-cause mortality was not significantly different between patients receiving tigecycline- or polymyxin B-based therapy (55.81% vs. 53.85%, p = 0.873), and between subgroups mortality rates were also similar. Conclusions: Critical illness indicators (APACHE II scores and presence of septic shock at BSI onset) were independent risk factors for 28-day all-cause mortality. There was no significant difference between tigecycline- and polymyxin B-based therapy outcomes. Prompt and appropriate infection control should be implemented to prevent CRKP infections.

scholarly journals Risk Factors for Treatment Failure of Polymyxin B Monotherapy for Carbapenem-Resistant Klebsiella pneumoniae Infections

2013 ◽  
Vol 57 (11) ◽  
pp. 5394-5397 ◽  
Author(s):  
Yanina Dubrovskaya ◽  
Ting-Yi Chen ◽  
Marco R. Scipione ◽  
Diana Esaian ◽  
Michael S. Phillips ◽  
...  
Keyword(s):  
Risk Factors ◽  
Septic Shock ◽  
Klebsiella Pneumoniae ◽  
Renal Insufficiency ◽  
Treatment Failure ◽  
Clinical Cure ◽  
Polymyxin B ◽  
Antimicrobial Treatment ◽  
Carbapenem Resistant

ABSTRACTPolymyxins are reserved for salvage therapy of infections caused by carbapenem-resistantKlebsiella pneumoniae(CRKP). Though synergy has been demonstrated for the combination of polymyxins with carbapenems or tigecycline,in vitrosynergy tests are nonstandardized, and the clinical effect of synergy remains unclear. This study describes outcomes for patients with CRKP infections who were treated with polymyxin B monotherapy. We retrospectively reviewed the medical records of patients with CRKP infections who received polymyxin B monotherapy from 2007 to 2011. Clinical, microbiology, and antimicrobial treatment data were collected. Risk factors for treatment failure were identified by logistic regression. Forty patients were included in the analysis. Twenty-nine of 40 (73%) patients achieved clinical cure as defined by clinician-documented improvement in signs and symptoms of infections, and 17/32 (53%) patients with follow-up culture data achieved microbiological cure. End-of-treatment mortality was 10%, and 30-day mortality was 28%. In a multivariate analysis, baseline renal insufficiency was associated with a 6.0-fold increase in clinical failure after adjusting for septic shock (odds ratio [OR] = 6.0; 95% confidence interval [CI] = 1.22 to 29.59). Breakthrough infections with organisms intrinsically resistant to polymyxins occurred in 3 patients during the treatment. Eighteen of 40 (45%) patients developed a new CRKP infection a median of 23 days after initial polymyxin B treatment, and 3 of these 18 infections were polymyxin resistant. The clinical cure rate achieved in this retrospective study was 73% of patients with CRKP infections treated with polymyxin B monotherapy. Baseline renal insufficiency was a risk factor for treatment failure after adjusting for septic shock. Breakthrough infections with organisms intrinsically resistant to polymyxin B and development of resistance to polymyxin B in subsequent CRKP isolates are of concern.

scholarly journals Risk Identification, Assessments, and Prediction for Mega Construction Projects: A Risk Prediction Paradigm Based on Cross Analytical-Machine Learning Model

Buildings ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 172
Author(s):  
Debalina Banerjee Chattapadhyay ◽  
Jagadeesh Putta ◽  
Rama Mohan Rao P
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Risk Management ◽  
High Risk ◽  
Risk Prediction ◽  
Learning Model ◽  
Risk Identification ◽  
Large Set ◽  
High Risk Factors ◽  
Machine Learning Model

Risk identification and management are the two most important parts of construction project management. Better risk management can help in determining the future consequences, but identifying possible risk factors has a direct and indirect impact on the risk management process. In this paper, a risk prediction system based on a cross analytical-machine learning model was developed for construction megaprojects. A total of 63 risk factors pertaining to the cost, time, quality, and scope of the megaproject and primary data were collected from industry experts on a five-point Likert scale. The obtained sample was further processed statistically to generate a significantly large set of features to perform K-means clustering based on high-risk factor and allied sub-risk component identification. Descriptive analysis, followed by the synthetic minority over-sampling technique (SMOTE) and the Wilcoxon rank-sum test was performed to retain the most significant features pertaining to cost, time, quality, and scope. Eventually, unlike classical K-means clustering, a genetic-algorithm-based K-means clustering algorithm (GA–K-means) was applied with dual-objective functions to segment high-risk factors and allied sub-risk components. The proposed model identified different high-risk factors and sub-risk factors, which cumulatively can impact overall performance. Thus, identifying these high-risk factors and corresponding sub-risk components can help stakeholders in achieving project success.

scholarly journals Risk Factors and Outcomes for Carbapenem-Resistant Klebsiella pneumoniae Isolation, Stratified by Its Multilocus Sequence Typing: ST258 Versus Non-ST258

2016 ◽  
Vol 3 (1) ◽  
Author(s):  
Sorabh Dhar ◽  
Emily T. Martin ◽  
Paul R. Lephart ◽  
John P. McRoberts ◽  
Teena Chopra ◽  
...  
Keyword(s):  
Risk Factors ◽  
High Risk ◽  
Klebsiella Pneumoniae ◽  
Molecular Epidemiology ◽  
Clinical Outcomes ◽  
Multilocus Sequence Typing ◽  
Clinical Impact ◽  
Sequence Type ◽  
Epidemiological Investigation ◽  
Carbapenem Resistant

Abstract A “high risk” clone of carbapenem-resistant Klebsiella pneumoniae (CRKP) identified by multilocus sequence typing (MLST) as sequence type (ST) 258 has disseminated worldwide. As the molecular epidemiology of the CRE pandemic continues to evolve, the clinical impact of non-ST258 strains is less well defined. We conducted an epidemiological investigation of CRKP based on strains MLST. Among 68 CRKP patients, 61 were ST258 and 7 belonged to non-ST258. Klebsiella pneumoniae ST258 strains were significantly associated with blaKPC production and with resistance to an increased number of antimicrobials. Clinical outcomes were not different. Based on this analysis, one cannot rely solely on the presence of blaKPC in order to diagnose CRKP.

scholarly journals The high-risk factors of different severities of bronchopulmonary dysplasia (BPD) based on the national institute of child health and human development (NICHD) diagnosis criteria in 2018

2021 ◽  
pp. e20210125
Author(s):  
Minqiao Jian1,2 ◽  
Shaoru He1,2 ◽  
Yumei Liu2 ◽  
Xiaoqing Liu3 ◽  
Juan Gui2 ◽  
...  
Keyword(s):  
Risk Factors ◽  
High Risk ◽  
Klebsiella Pneumoniae ◽  
Preterm Infants ◽  
Bronchopulmonary Dysplasia ◽  
Ductus Arteriosus ◽  
Severe Illness ◽  
Pulmonary Infections ◽  
High Risk Factors ◽  
Severe Group

Objective: To investigate the clinical characteristics of preterm infants with different severities of bronchopulmonary dysplasia (BPD) and disclose the high-risk factors of exacerbating BPD. Methods: Collection of clinical data of 91 preterm infants admitted to the NICU and diagnosed with BPD, categorized in groups according to the disease severity: 41 mild cases,, 24 moderate cases, and 26 severe cases. Comparison and analysis of perinatal risk factors, treatment, complications and prognosis of the infants with different severity degrees. Results: The severe group had a higher proportion of infants with congenital heart disease (CHD) higher than the moderate group (P < 0.05), and a higher ratio of pneumonia and mechanical ventilation (MV) = seven days than the mild group (P < 0.05). The severe group also presented higher reintubation incidence than both the mild and moderate groups (P < 0.05). The groups presented different (P < 0.05) incidence rates of hemodynamically significant patent ductus arteriosus (hsPDA) . Ridit analysis suggested that the premature infants (PIs) with hsPDA, multiple microbial pulmonary infections, or Klebsiella pneumoniae pneumonia had more severe illness. Conclusion: CHD, hsPDA, MV = seven days, reintubation, pneumonia, especially multiple microbial pulmonary infections, and Klebsiella pneumoniae pneumonia are correlated with the severity of BPD and can be used as BPD progression predictor.

Sign in / Sign up

Export Citation Format

Share Document