4.4 Article

Machine learning-derived blood culture classification with both predictive and prognostic values in the intensive care unit: A retrospective cohort study

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Editorial Material Critical Care Medicine

When the kidneys hurt, the other organs suffer

Celine Monard et al.

INTENSIVE CARE MEDICINE (2023)

Article Critical Care Medicine

Epidemiology and outcomes of hospital-acquired bloodstream infections in intensive care unit patients: the EUROBACT-2 international cohort study

Alexis Tabah et al.

Summary: This study investigated hospital-acquired bloodstream infections (HA-BSI) in 2600 adult patients from 333 ICUs in 52 countries. HA-BSI were frequently caused by Gram-negative, carbapenem-resistant, and difficult-to-treat pathogens. Antimicrobial resistance led to delays in adequate antimicrobial therapy, resulting in high mortality rates.

INTENSIVE CARE MEDICINE (2023)

Article Nursing

Heterogeneity hampers the identification of general pressure injury risk factors in intensive care populations: A predictive modelling analysis

Mieke Deschepper et al.

Summary: The study found that risk factors for pressure injury vary among different types of intensive care admissions, with admission type being a key differentiating factor. Patients admitted for medical reasons, elective surgery, and emergency surgery have distinct prediction models for pressure injury.

INTENSIVE AND CRITICAL CARE NURSING (2022)

Article Infectious Diseases

Use of Antimicrobials for Bloodstream Infections in the Intensive Care Unit, a Clinically Oriented Review

Alexis Tabah et al.

Summary: Bloodstream infections in critically ill patients have a high mortality rate. Patients with septic shock should be treated with antibiotics within one hour, taking into consideration local epidemiology and risk factors for bacterial resistance. It is crucial to perform blood cultures and other tests before antibiotic administration to enable microbiological diagnosis and antimicrobial stewardship. Rapid diagnostic testing can provide faster identification of pathogens and resistance patterns, allowing for optimized antibiotic treatment.

ANTIBIOTICS-BASEL (2022)

Article Critical Care Medicine

Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study

Cecilia A. Akerlund et al.

Summary: Using data-driven clustering analysis, we identified six stable clinical subtypes of traumatic brain injury with distinct neurological and systemic metabolic stress profiles, which were associated with outcomes.

CRITICAL CARE (2022)

Article Infectious Diseases

Comparing mortality between positive and negative blood culture results: an inverse probability of treatment weighting analysis of a multicenter cohort

Aibo Liu et al.

Summary: This study found that culture-positive sepsis patients had comparable early mortality but worse late mortality than culture-negative sepsis patients. Persistent Staphylococcal bacteremia may have contributed to the increased late mortality.

BMC INFECTIOUS DISEASES (2021)

Article Respiratory System

Microorganisms and clinical outcomes of early- and late-onset ventilator-associated pneumonia at Srinagarind Hospital, a tertiary center in Northeastern Thailand

Pavarit Arayasukawat et al.

Summary: This study compared the MDR pathogens, treatment outcomes, and factors associated with hospital mortality of VAP. The results showed that LOVAP patients had more MDR pathogens and higher MV days, ICU LOS, hospital LOS, and hospital mortality compared to EOVAP patients.

BMC PULMONARY MEDICINE (2021)

Article Infectious Diseases

Duration of antibiotic therapy in central venous catheter-related bloodstream infection due to Gram-negative bacilli

María Ruiz-Ruigómez et al.

CURRENT OPINION IN INFECTIOUS DISEASES (2021)

Article Medicine, General & Internal

An Artificial Intelligence Approach to Bloodstream Infections Prediction

Kai-Chih Pai et al.

Summary: This study developed an early prediction model to identify patients with bloodstream infections in the ICU using machine learning algorithms. The XGBoost and random forest models showed high prediction performance, with alkaline phosphatase and central venous catheter period as the most important predictors. The visualized SHAP method revealed the impact of features like prothrombin time, platelet count, and albumin on bloodstream infections.

JOURNAL OF CLINICAL MEDICINE (2021)

Article Medicine, General & Internal

Diagnosing hospital bacteraemia in the framework of predictive, preventive and personalised medicine using electronic health records and machine learning classifiers

Oscar Garnica et al.

Summary: Predicting bacteraemia using machine learning techniques can aid in rapid diagnosis and personalized treatment, reducing medical errors and improving patient outcomes. The results of this study demonstrate high accuracy and sensitivity in predicting blood culture outcomes, showing promise in enhancing predictive and personalized medicine practices.

EPMA JOURNAL (2021)

Article Critical Care Medicine

Identification of distinct clinical phenotypes of acute respiratory distress syndrome with differential responses to treatment

Xiaowei Liu et al.

Summary: The study identified three clinical phenotypes of ARDS with different clinical characteristics and outcomes, showing evidence of a phenotype-specific treatment benefit in the ALVEOLI and FACTT trials. These findings could help in identifying distinct subsets of ARDS patients for exploration in future RCTs.

CRITICAL CARE (2021)

Article Cardiac & Cardiovascular Systems

Phenomapping of patients with heart failure with preserved ejection fraction using machine learning-based unsupervised cluster analysis

Matthew W. Segar et al.

EUROPEAN JOURNAL OF HEART FAILURE (2020)

Article Medical Informatics

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

Ming Cheng et al.

BMC MEDICAL INFORMATICS AND DECISION MAKING (2020)

Article Computer Science, Artificial Intelligence

Accurate prediction of blood culture outcome in the intensive care unit using long short-term memory neural networks

Tom Van Steenkiste et al.

ARTIFICIAL INTELLIGENCE IN MEDICINE (2019)

Article Medicine, General & Internal

Intravascular Complications of Central Venous Catheterization by Insertion Site

Jean-Jacques Parienti et al.

NEW ENGLAND JOURNAL OF MEDICINE (2015)

Article Critical Care Medicine

Duration of antibiotic therapy for bacteremia: a systematic review and meta-analysis

Thomas C. Havey et al.

CRITICAL CARE (2011)

Article Health Care Sciences & Services

Missing covariate data in medical research: To impute is better than to ignore

Kristel J. M. Janssen et al.

JOURNAL OF CLINICAL EPIDEMIOLOGY (2010)

Article Mathematical & Computational Biology

Dose-response analyses using restricted cubic spline functions in public health research

Loic Desquilbet et al.

STATISTICS IN MEDICINE (2010)

Article Critical Care Medicine

Incidence, organ dysfunction and mortality in severe sepsis: a Spanish multicentre study

Jesus Blanco et al.

CRITICAL CARE (2008)

Article Immunology

Postoperative bacteremia secondary to surgical site infection

CA Petti et al.

CLINICAL INFECTIOUS DISEASES (2002)

Article Medicine, General & Internal

Serial evaluation of the SOFA score to predict outcome in critically ill patients

FL Ferreira et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2001)

Article Medicine, General & Internal

Complications of femoral and subclavian venous catheterization in critically ill patients - A randomized controlled trial

J Merrer et al.

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION (2001)