Healthcare-associated ventriculitis and meningitis in a neuro-ICU: Incidence and risk factors selected by machine learning approach

Савин, И А; Ershova, Ksenia; Kurdyumova, N V; Ershova, Olga; Хоменко, О. И.; Danilov, Gleb; Shifrin, Michael; Zelman, Vladimir

doi:10.1016/j.jcrc.2018.01.022

Cited by 43 publications

(30 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…During an IC intervention to improve staff adherence to IC practices, we observed that the infection rate decreased from 17.3 per 1000 drain days before the intervention to 7.9/1000 after the intervention. Our rate of EVD-related meningitis specifically, during and following the intervention period (9.5-8.6/1000 EVD days), was in the low range of rates in previous studies reporting on EVD-related meningitis per catheter day (4.8-17.2/1000 EVD days) in the UK and Ireland [12], Russia [27], and Switzerland [32]. In the analysis per patient, patientrelated factors dominated, while the effect of the IC intervention was observed in the analysis per catheter.…”

Section: Discussioncontrasting

confidence: 50%

Risk factors for meningitis in neurosurgical patients with cerebrospinal fluid drains: prospective observational cohort study

et al. 2019

View full text Add to dashboard Cite

Background Cerebrospinal fluid (CSF) drainage or intracranial pressure (ICP) monitoring devices are life-saving devices. We examined the risk factors for infections related to them and assessed the effect of an infection control (IC) intervention. Methods A prospective observational study was conducted in the Neurosurgical Department of our hospital between 2014 and 2017. We included all consecutive patients undergoing CSF catheter insertions, including external ventricular drainage (EVD), lumbar drainage (LD), and ICP catheters. An IC intervention was implemented between March and August 2016. We examined risk factors for meningitis or ventriculitis, defined according to Healthcare-associated infections surveillance definitions, on univariate and multivariate analysis. Results A total of 232 patients with 437 drains (212 EVDs, 92 LDs, and 133 ICPs) were included. On univariate and multivariate analysis, the infection incidence was 13.7 per 1000 drain days (17.3/1000 before IC intervention, 7.9/1000 during, and 9.2/1000 after the intervention). Most episodes were caused by Gram-negative bacteria, and the most common pathogen was Acinetobacter baumanii. Risk factors for infection per patient included diabetes mellitus (p = 0.017), CSF leak (p = 0.032), drain opening (p = 0.027), and the duration of the drain in days (p = 0.035). Risk factors per catheter included drain opening (p < 0.001), drain days (p = 0.001), and the IC intervention period compared to before the intervention period (p = 0.037). When restricting the analysis to EVDs, drain days (p = 0.001) was the only significant risk factor. Conclusions Strict adherence to IC, shortening drain duration, and avoiding unnecessary opening and manipulation of the drains are crucial to preventing neurosurgical drain infections.

show abstract

Section: Discussioncontrasting

confidence: 50%

Risk factors for meningitis in neurosurgical patients with cerebrospinal fluid drains: prospective observational cohort study

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Such rich data sources have been shown to be especially useful for developing hypotheses about previously unknown risk factors and for building accurate prediction models for various outcome of interest (eg, specific healthcare-acquired infections, hospital complications). 20,[28][29][30] Linkage of electronic medical records data with high-quality cohort or registry data has become a valuable option to add exposures, potential confounders, effect modifiers, and outcomes of interest with strict definition criteria that may not be present in routine medical records. 31 This option is particularly valuable because data from electronic medical records (and other routine data sources) have been reported to sometimes be of lower quality than data acquired during prospective investigations due to changing and varying definition criteria/coding practices, and missing data.…”

Section: Machine Learning: Recent Applications In Digital Healthcare mentioning

confidence: 99%

Section: Machine Learning: Recent Applications In Digital Healthcare mentioning

confidence: 99%

Introduction to Machine Learning in Digital Healthcare Epidemiology

Roth

Battegay

Juchler

et al. 2018

Infect. Control Hosp. Epidemiol.

View full text Add to dashboard Cite

To exploit the full potential of big routine data in healthcare and to efficiently communicate and collaborate with information technology specialists and data analysts, healthcare epidemiologists should have some knowledge of large-scale analysis techniques, particularly about machine learning. This review focuses on the broad area of machine learning and its first applications in the emerging field of digital healthcare epidemiology.

show abstract

“…Savin et al ( 39 ) studied two groups of high-risk Neuro ICU patients, one group with hospital-acquired ventriculitis and meningitis (HAVM, n = 216) and one group without HAVM ( n = 2,070) ( 39 ). They identified with the advanced ensemble method, XGBoost, the four most important risk factors involved with HAVM: (1) presence of external ventricular device, (2) recent craniotomy, (3) presence of superficial surgical-site infection, and (4) CSF leaks.…”

Section: Machine Learning To Predict and Diagnose Nosocomial Cns Infementioning

confidence: 99%

Machine Learning Applications in the Neuro ICU: A Solution to Big Data Mayhem?

et al. 2020

View full text Add to dashboard Cite

The neurological ICU (neuro ICU) often suffers from significant limitations due to scarce resource availability for their neurocritical care patients. Neuro ICU patients require frequent neurological evaluations, continuous monitoring of various physiological parameters, frequent imaging, and routine lab testing. This amasses large amounts of data specific to each patient. Neuro ICU teams are often overburdened by the resulting complexity of data for each patient. Machine Learning algorithms (ML), are uniquely capable of interpreting high-dimensional datasets that are too difficult for humans to comprehend. Therefore, the application of ML in the neuro ICU could alleviate the burden of analyzing big datasets for each patient. This review serves to (1) briefly summarize ML and compare the different types of MLs, (2) review recent ML applications to improve neuro ICU management and (3) describe the future implications of ML to neuro ICU management.

show abstract

Healthcare-associated ventriculitis and meningitis in a neuro-ICU: Incidence and risk factors selected by machine learning approach

Cited by 43 publications

References 24 publications

Risk factors for meningitis in neurosurgical patients with cerebrospinal fluid drains: prospective observational cohort study

Risk factors for meningitis in neurosurgical patients with cerebrospinal fluid drains: prospective observational cohort study

Introduction to Machine Learning in Digital Healthcare Epidemiology

Machine Learning Applications in the Neuro ICU: A Solution to Big Data Mayhem?

Contact Info

Product

Resources

About