Dataset Information

Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults.

ABSTRACT: Unnecessary antibiotic regimens in the intensive care unit (ICU) are associated with adverse patient outcomes and antimicrobial resistance. Bacterial infections (BI) are both common and deadly in ICUs, and as a result, patients with a suspected BI are routinely started on broad-spectrum antibiotics prior to having confirmatory microbiologic culture results or when an occult BI is suspected, a practice known as empiric antibiotic therapy (EAT). However, EAT guidelines lack consensus and existing methods to quantify patient-level BI risk rely largely on clinical judgement and inaccurate biomarkers or expensive diagnostic tests. As a consequence, patients with low risk of BI often are continued on EAT, exposing them to unnecessary side effects. Augmenting current intuition-based practices with data-driven predictions of BI risk could help inform clinical decisions to shorten the duration of unnecessary EAT and improve patient outcomes. We propose a novel framework to identify ICU patients with low risk of BI as candidates for earlier EAT discontinuation. For this study, patients suspected of having a community-acquired BI were identified in the Medical Information Mart for Intensive Care III (MIMIC-III) dataset and categorized based on microbiologic culture results and EAT duration. Using structured longitudinal data collected up to 24-, 48-, and 72-hours after starting EAT, our best models identified patients at low risk of BI with AUROCs up to 0.8 and negative predictive values >93%. Overall, these results demonstrate the feasibility of forecasting BI risk in a critical care setting using patient features found in the electronic health record and call for more extensive research in this promising, yet relatively understudied, area.

SUBMITTER: Eickelberg G

PROVIDER: S-EPMC7530142 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults.

Eickelberg Garrett G Sanchez-Pinto L Nelson LN Luo Yuan Y

Journal of biomedical informatics 20200816

Unnecessary antibiotic regimens in the intensive care unit (ICU) are associated with adverse patient outcomes and antimicrobial resistance. Bacterial infections (BI) are both common and deadly in ICUs, and as a result, patients with a suspected BI are routinely started on broad-spectrum antibiotics prior to having confirmatory microbiologic culture results or when an occult BI is suspected, a practice known as empiric antibiotic therapy (EAT). However, EAT guidelines lack consensus and existing ...[more]

PMID: 32814200

Similar Datasets

Project description:Background: Systemic inflammation is a whole body reaction that can have an infection-positive (i.e. sepsis) or infection-negative origin. It is important to distinguish between septic and non-septic presentations early and reliably, because this has significant therapeutic implications for critically ill patients. We hypothesized that a molecular classifier based on a small number of RNAs expressed in peripheral blood could be discovered that would: 1) determine which patients with systemic inflammation had sepsis; 2) be robust across independent patient cohorts; 3) be insensitive to disease severity; and 4) provide diagnostic utility. The overall goal of this study was to identify and validate such a molecular classifier. Methods and Findings: We conducted an observational, non-interventional study of adult patients recruited from tertiary intensive care units (ICU). Biomarker discovery was conducted with an Australian cohort (n = 105) consisting of sepsis patients and post -surgical patients with infection-negative systemic inflammation. Using this cohort, a four-gene classifier consisting of a combination of CEACAM4, LAMP1, PLA2G7 and PLAC8 RNA biomarkers was identified. This classifier, designated SeptiCyteÂ® Lab, was externally validated using RT-qPCR and receiver operating characteristic (ROC) curve analysis in five cohorts (n = 345) from the Netherlands. Cohort 1 (n=59) consisted of unambiguous septic cases and infection-negative systemic inflammation controls; SeptiCyteÂ® Lab gave an area under curve (AUC) of 0.96 (95% CI: 0.91-1.00). ROC analysis of a more heterogeneous group of patients (Cohorts 2-5; 249 patients after excluding 37 patients with infection likelihood possible) gave an AUC of 0.89 (95% CI: 0.85-0.93). Disease severity, as measured by Sequential Organ Failure Assessment (SOFA) score or the Acute Physiology and Chronic Health Evaluation (APACHE) IV score, was not a significant confounding variable. The diagnostic utility o f SeptiCyteÂ® Lab was evaluated by comparison to various clinical and laboratory parameters that would be available to a clinician within 24 hours of ICU admission. SeptiCyteÂ® Lab was significantly better at differentiating sepsis from infection-negative systemic inflammation than all tested parameters, both singly and in various logistic combinations. SeptiCyteÂ® Lab more than halved the diagnostic error rate compared to PCT in all tested cohorts or cohort combinations. Conclusions: SeptiCyteÂ® Lab is a rapid molecular assay that may be clinically useful in the management of ICU patients with systemic inflammation. SIRS and Sepsis ICU patients, admission samples Retrospective, mutli-site sutdy using retrospective physician adjudication as a comparator

Project description:BackgroundPneumonia is the most common hospital-acquired infection affecting patients in the intensive care unit (ICU). However, current national guidelines for the treatment of hospital-acquired pneumonia (HAP) are several years old and the diagnosis of pneumonia in mechanically ventilated patients (VAP) has been subject to considerable recent attention. The optimal duration of antibiotic therapy for HAP in the critically ill is uncertain.ObjectivesTo assess the effectiveness of short versus prolonged-course antibiotics for HAP in critically ill adults, including patients with VAP.Search methodsWe searched CENTRAL (2015, Issue 5), MEDLINE (1946 to June 2015), MEDLINE in-process and other non-indexed citations (5 June 2015), EMBASE (2010 to June 2015), LILACS (1982 to June 2015) and Web of Science (1955 to June 2015).Selection criteriaWe considered all randomised controlled trials (RCTs) comparing a fixed 'short' duration of antibiotic therapy with a 'prolonged' course for HAP (including patients with VAP) in critically ill adults.Data collection and analysisTwo review authors conducted data extraction and assessment of risk of bias. We contacted trial authors for additional information.Main resultsWe identified six relevant studies involving 1088 participants. This included two new studies published after the date of our previous review (2011). There was substantial variation in participants, in the diagnostic criteria used to define an episode of pneumonia, in the interventions and in the reported outcomes. We found no evidence relating to patients with a high probability of HAP who were not mechanically ventilated. For patients with VAP, overall a short seven- or eight-day course of antibiotics compared with a prolonged 10- to 15-day course increased 28-day antibiotic-free days (two studies; N = 431; mean difference (MD) 4.02 days; 95% confidence interval (CI) 2.26 to 5.78) and reduced recurrence of VAP due to multi-resistant organisms (one study; N = 110; odds ratio (OR) 0.44; 95% CI 0.21 to 0.95), without adversely affecting mortality and other recurrence outcomes. However, for cases of VAP specifically due to non-fermenting Gram-negative bacilli (NF-GNB), recurrence was greater after short-course therapy (two studies, N = 176; OR 2.18; 95% CI 1.14 to 4.16), though mortality outcomes were not significantly different. One study found that a three-day course of antibiotic therapy for patients with suspected HAP but a low Clinical Pulmonary Infection Score (CPIS) was associated with a significantly lower risk of superinfection or emergence of antimicrobial resistance, compared with standard (prolonged) course therapy.Authors' conclusionsOn the basis of a small number of studies and appreciating the lack of uniform definition of pneumonia, we conclude that for patients with VAP not due to NF-GNB a short, fixed course (seven or eight days) of antibiotic therapy appears not to increase the risk of adverse clinical outcomes, and may reduce the emergence of resistant organisms, compared with a prolonged course (10 to 15 days). However, for patients with VAP due to NF-GNB, there appears to be a higher risk of recurrence following short-course therapy. These findings do not differ from those of our previous review and are broadly consistent with current guidelines. There are few data from RCTs comparing durations of therapy in non-ventilated patients with HAP, but on the basis of a single study, short-course (three-day) therapy for HAP appears not to be associated with worse clinical outcome, and may reduce the risk of subsequent infection or the emergence of resistant organisms when there is low probability of pneumonia according to the CPIS.

Project description:Background: Systemic inflammation is a whole body reaction that can have an infection-positive (i.e. sepsis) or infection-negative origin. It is important to distinguish between septic and non-septic presentations early and reliably, because this has significant therapeutic implications for critically ill patients. We hypothesized that a molecular classifier based on a small number of RNAs expressed in peripheral blood could be discovered that would: 1) determine which patients with systemic inflammation had sepsis; 2) be robust across independent patient cohorts; 3) be insensitive to disease severity; and 4) provide diagnostic utility. The overall goal of this study was to identify and validate such a molecular classifier. Methods and Findings: We conducted an observational, non-interventional study of adult patients recruited from tertiary intensive care units (ICU). Biomarker discovery was conducted with an Australian cohort (n = 105) consisting of sepsis patients and post -surgical patients with infection-negative systemic inflammation. Using this cohort, a four-gene classifier consisting of a combination of CEACAM4, LAMP1, PLA2G7 and PLAC8 RNA biomarkers was identified. This classifier, designated SeptiCyte® Lab, was externally validated using RT-qPCR and receiver operating characteristic (ROC) curve analysis in five cohorts (n = 345) from the Netherlands. Cohort 1 (n=59) consisted of unambiguous septic cases and infection-negative systemic inflammation controls; SeptiCyte® Lab gave an area under curve (AUC) of 0.96 (95% CI: 0.91-1.00). ROC analysis of a more heterogeneous group of patients (Cohorts 2-5; 249 patients after excluding 37 patients with infection likelihood possible) gave an AUC of 0.89 (95% CI: 0.85-0.93). Disease severity, as measured by Sequential Organ Failure Assessment (SOFA) score or the Acute Physiology and Chronic Health Evaluation (APACHE) IV score, was not a significant confounding variable. The diagnostic utility o f SeptiCyte® Lab was evaluated by comparison to various clinical and laboratory parameters that would be available to a clinician within 24 hours of ICU admission. SeptiCyte® Lab was significantly better at differentiating sepsis from infection-negative systemic inflammation than all tested parameters, both singly and in various logistic combinations. SeptiCyte® Lab more than halved the diagnostic error rate compared to PCT in all tested cohorts or cohort combinations. Conclusions: SeptiCyte® Lab is a rapid molecular assay that may be clinically useful in the management of ICU patients with systemic inflammation. SIRS and Sepsis ICU patients, admission samples

Dataset Information

Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults.

Publications

Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets