Impact of ICU strain on outcomes

Duggal, Abhijit; Mathews, Kusum S.

doi:10.1097/mcc.0000000000000993

Cited by 8 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of space and equipment, one may use the ICU as an excellent model for highlighting the difficulties of determining what resources are needed. Simply increasing bed numbers does not necessarily translate into higher survival rates [18]. The UK prepandemic had four ICU beds per 100 000 of the population yet had similar mortality outcomes to Germany with 27 ICU beds per 100 000 [19].…”

Section: What Resources Require Allocation?mentioning

confidence: 99%

Resource allocation

McConnell

Einav

2023

Current Opinion in Anaesthesiology

View full text Add to dashboard Cite

Purpose of reviewThe coronavirus disease 2019 pandemic and recent global recessions have brought to the forefront of the medical-political discussion the fact that medical resources are finite and have focused a spotlight on fair allocation and prioritization of healthcare resources describe why this review is timely and relevant. Recent findingsThis review presents past and present concepts related to the ethics of resource allocation. Included are discussions regarding the topics of who should determine resource allocation, what types of research require allocation, methods currently in use to determine what resources are appropriate and which should be prioritized. describe the main themes in the literature covered by the article.

show abstract

Section: What Resources Require Allocation?mentioning

confidence: 99%

Resource allocation

McConnell

Einav

2023

Current Opinion in Anaesthesiology

View full text Add to dashboard Cite

show abstract

“…Published studies demonstrate a powerful influence of severe surge and ICU strain on mortality, and needed future planning 10,56,57,61 . Equipment shortages, including ventilators and dialysis equipment were limiting primarily during the first wave of the pandemic (March and April 2020); thereafter, the most significant limiting resource were healthcare staff 25,62,63 .…”

Section: Covid-19 Pandemicmentioning

confidence: 99%

Intensive Care Strain Indicators: Recommendations for Critical Care Processes and Research Objectives

Starcher¹,

Weinert²,

Henry³

et al. 2023

J Anesthesiol & Pain Therapy

View full text Add to dashboard Cite

Intensive care units (ICU’s) are particularly susceptible to resource and personnel strain given the complexity and unpredictability of care. This featured prominently in the early course of the SARS-CoV-2 (COVID-19) pandemic, where poor patient outcomes were clearly linked to the increasing severity of ICU strain associated with decreased ICU capacity. Despite attempts at measuring ICU strain, there exists no operational model that ICU directors can implement to monitor strain or researchers can use to examine its effects. This article reviews ICU strain indicators including census load (census, acuity, and admissions), ICU flow characteristics (admission/discharge criteria, sufficient staffing levels, and ICU performance), and consequence mediators (ICU queuing time and high-risk discharges) with attention to common themes and measures. Census load data suggests mortality risk is greater when ICU census starts higher, has high overall acuity, and with greater numbers of admissions especially when they arrive close together. Optimal ICU flow depends on maintaining a “strain mindset” when prioritizing patients, optimal ICU professional staffing, and maintaining high level ICU performance processes. Finally, delaying ICU admissions beyond six hours, or “after hours” or rushed ICU discharges result in increased mortality risk. Incorporating these ICU strain factors into an outcomes-focused model is proposed based on a conceptual framework with future research objectives recommended.

show abstract

“…A less addressed yet critical effect of the pandemic has been the sudden increased burden on healthcare facilities, namely hospitals. The influx of severe COVID-19 patients overwhelms intensive care units (ICU), which results in increased mortality [1], especially in regions in the U.S. with less health resources (e.g., ICU and general hospital beds) across the pandemic ( [14], [18]). These challenges require solutions geared towards effectively optimizing healthcare resources.…”

Section: Introductionmentioning

confidence: 99%

Evaluating biomedical feature fusion on machine learning’s predictability and interpretability of COVID-19 severity types

West-Page,

McGoff,

Latimer

et al. 2024

Preprint

View full text Add to dashboard Cite

BackgroundAccurately differentiating severe from non-severe COVID-19 clinical types is critical for the healthcare system to optimize workflow, as severe patients require intensive care. Current techniques lack the ability to accurately predict COVID-19 patients’ clinical type, especially as SARS-CoV-2 continues to mutate.ObjectiveIn this work, we explore both predictability and interpretability of multiple state-of-the-art machine learning (ML) techniques trained and tested under different biomedical data types and COVID-19 variants.MethodsComprehensive patient-level data were collected from 362 patients (214 severe, 148 non-severe) with the original SARS-CoV-2 variant in 2020 and 1000 patients (500 severe, 500 non-severe) with the Omicron variant in 2022-2023. The data included 26 biochemical features from blood testing and 26 clinical features from each patient’s clinical characteristics and medical history. Different types of ML techniques, including penalized logistic regression (LR), random forest (RF),k-nearest neighbors (kNN), and support vector machines (SVM) were applied to build predictive models based on each data modality separately and together for each variant set.ResultsAll ML models performed similarly under different testing scenarios. The fused characteristic modality yielded the highest area under the curve (AUC) score achieving 0.914 on average. The second highest AUC was 0.876 achieved by the biochemical modality alone, followed by 0.825 achieved by clinical modality alone. All ML models were robust when cross-tested with original and Omicron variant patient data. Upon model interpretation, our models ranked elevated d-dimer (biochemical feature), elevated high sensitivity troponin I (biochemical feature), and age greater than 55 years (clinical feature) as the most predictive features of severe COVID-19.ConclusionsWe found ML to be a powerful tool for predicting severe COVID-19 based on comprehensive individual patient-level data. Further, ML models trained on the biochemical and clinical modalities together witness enhanced predictive power. The improved performance of these ML models when trained and cross-tested with Omicron variant data supports the robustness of ML as a tool for clinical decision support.

show abstract

Impact of ICU strain on outcomes

Cited by 8 publications

References 46 publications

Resource allocation

Resource allocation

Intensive Care Strain Indicators: Recommendations for Critical Care Processes and Research Objectives

Evaluating biomedical feature fusion on machine learning’s predictability and interpretability of COVID-19 severity types

Contact Info

Product

Resources

About