Abstract 15875: Prediction of Intensive Care Unit Admission Among Patients Hospitalized for COVID-19: The Intermountain Coronavirus ICU Risk Model (CORONA-ICU)

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Heidi T May ◽  
Joseph B Muhlestein ◽  
Benjamin D Horne ◽  
Kirk U Knowlton ◽  
Tami L Bair ◽  
...  
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Risk Prediction ◽  
Prediction Models ◽  
Risk Model ◽  
Beta Blockers ◽  
Risk Scores ◽  
Channel Blockers ◽  
Icu Patients

Background: Treatment for COVID-19 has created surges in hospitalizations, intensive care unit (ICU) admissions, and the need for advanced medical therapy and equipment, including ventilators. Identifying patients early on who are at risk for more intensive hospital resource use and poor outcomes could result in shorter hospital stays, lower costs, and improved outcomes. Therefore, we created clinical risk scores (CORONA-ICU and -ICU+) to predict ICU admission among patients hospitalized for COVID-19. Methods: Intermountain Healthcare patients who tested positive for SARS-CoV-2 and were hospitalized between March 4, 2020 and June 8, 2020 were studied. Derivation of CORONA-ICU risk score models used weightings of commonly collected risk factors and medicines. The primary outcome was admission to the ICU during hospitalization, and secondary outcomes included death and ventilator use. Results: A total of 451 patients were hospitalized for a SARS-CoV-2 positive infection, and 191 (42.4%) required admission to the ICU. Patients admitted to the ICU were older (58.2 vs. 53.6 years), more often male (61.3% vs. 48.5%), and had higher rates of hyperlipidemia, hypertension, diabetes, and peripheral arterial disease. ICU patients more often took ACE inhibitors, beta-blockers, calcium channel blockers, diuretics, and statins. Table 1 shows variables that were evaluated and included in the CORONA-ICU risk prediction models. Models adding medications (CORONA-ICU+) improved risk-prediction. Though not created to predict death and ventilator use, these models did so with high accuracy (Table 2). Conclusion: The CORONA-ICU and -ICU+ models, composed of commonly collected risk factors without or with medications, were shown to be highly predictive of ICU admissions, death, and ventilator use. These models can be efficiently derived and effectively identify high-risk patients who require more careful observation and increased use of advanced medical therapies.

scholarly journals Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation

10.2196/23128 ◽  
2020 ◽  
Vol 22 (11) ◽  
pp. e23128
Author(s):  
Pan Pan ◽  
Yichao Li ◽  
Yongjiu Xiao ◽  
Bingchao Han ◽  
Longxiang Su ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Prediction Model ◽  
Risk Prediction ◽  
Risk Prediction Model ◽  
Data Set ◽  
Icu Patients ◽  
Potential Risk Factors

Background Patients with COVID-19 in the intensive care unit (ICU) have a high mortality rate, and methods to assess patients’ prognosis early and administer precise treatment are of great significance. Objective The aim of this study was to use machine learning to construct a model for the analysis of risk factors and prediction of mortality among ICU patients with COVID-19. Methods In this study, 123 patients with COVID-19 in the ICU of Vulcan Hill Hospital were retrospectively selected from the database, and the data were randomly divided into a training data set (n=98) and test data set (n=25) with a 4:1 ratio. Significance tests, correlation analysis, and factor analysis were used to screen 100 potential risk factors individually. Conventional logistic regression methods and four machine learning algorithms were used to construct the risk prediction model for the prognosis of patients with COVID-19 in the ICU. The performance of these machine learning models was measured by the area under the receiver operating characteristic curve (AUC). Interpretation and evaluation of the risk prediction model were performed using calibration curves, SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), etc, to ensure its stability and reliability. The outcome was based on the ICU deaths recorded from the database. Results Layer-by-layer screening of 100 potential risk factors finally revealed 8 important risk factors that were included in the risk prediction model: lymphocyte percentage, prothrombin time, lactate dehydrogenase, total bilirubin, eosinophil percentage, creatinine, neutrophil percentage, and albumin level. Finally, an eXtreme Gradient Boosting (XGBoost) model established with the 8 important risk factors showed the best recognition ability in the training set of 5-fold cross validation (AUC=0.86) and the verification queue (AUC=0.92). The calibration curve showed that the risk predicted by the model was in good agreement with the actual risk. In addition, using the SHAP and LIME algorithms, feature interpretation and sample prediction interpretation algorithms of the XGBoost black box model were implemented. Additionally, the model was translated into a web-based risk calculator that is freely available for public usage. Conclusions The 8-factor XGBoost model predicts risk of death in ICU patients with COVID-19 well; it initially demonstrates stability and can be used effectively to predict COVID-19 prognosis in ICU patients.

Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation (Preprint)

2020 ◽  
Author(s):  
Pan Pan ◽  
Yichao Li ◽  
Yongjiu Xiao ◽  
Bingchao Han ◽  
Longxiang Su ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Prediction Model ◽  
Risk Prediction ◽  
Risk Prediction Model ◽  
Data Set ◽  
Icu Patients ◽  
Potential Risk Factors

BACKGROUND Patients with COVID-19 in the intensive care unit (ICU) have a high mortality rate, and methods to assess patients’ prognosis early and administer precise treatment are of great significance. OBJECTIVE The aim of this study was to use machine learning to construct a model for the analysis of risk factors and prediction of mortality among ICU patients with COVID-19. METHODS In this study, 123 patients with COVID-19 in the ICU of Vulcan Hill Hospital were retrospectively selected from the database, and the data were randomly divided into a training data set (n=98) and test data set (n=25) with a 4:1 ratio. Significance tests, correlation analysis, and factor analysis were used to screen 100 potential risk factors individually. Conventional logistic regression methods and four machine learning algorithms were used to construct the risk prediction model for the prognosis of patients with COVID-19 in the ICU. The performance of these machine learning models was measured by the area under the receiver operating characteristic curve (AUC). Interpretation and evaluation of the risk prediction model were performed using calibration curves, SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), etc, to ensure its stability and reliability. The outcome was based on the ICU deaths recorded from the database. RESULTS Layer-by-layer screening of 100 potential risk factors finally revealed 8 important risk factors that were included in the risk prediction model: lymphocyte percentage, prothrombin time, lactate dehydrogenase, total bilirubin, eosinophil percentage, creatinine, neutrophil percentage, and albumin level. Finally, an eXtreme Gradient Boosting (XGBoost) model established with the 8 important risk factors showed the best recognition ability in the training set of 5-fold cross validation (AUC=0.86) and the verification queue (AUC=0.92). The calibration curve showed that the risk predicted by the model was in good agreement with the actual risk. In addition, using the SHAP and LIME algorithms, feature interpretation and sample prediction interpretation algorithms of the XGBoost black box model were implemented. Additionally, the model was translated into a web-based risk calculator that is freely available for public usage. CONCLUSIONS The 8-factor XGBoost model predicts risk of death in ICU patients with COVID-19 well; it initially demonstrates stability and can be used effectively to predict COVID-19 prognosis in ICU patients.

scholarly journals Corneal injuries: incidence and risk factors in the Intensive Care Unit

2011 ◽  
Vol 19 (5) ◽  
pp. 1088-1095 ◽  
Author(s):  
Andreza Werli-Alvarenga ◽  
Flávia Falci Ercole ◽  
Fernando Antônio Botoni ◽  
José Aloísio Dias Massote Mourão Oliveira ◽  
Tânia Couto Machado Chianca
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Risk Prediction ◽  
Prediction Models ◽  
Corneal Ulcer ◽  
Ventilatory Support ◽  
Corneal Injury ◽  
Corneal Ulcers ◽  
Duration Of Hospitalization

Patients hospitalized in the Intensive Care Unit (ICU) may present risk for corneal injury due to sedation or coma. This study aimed to estimate the incidence of corneal injuries; to identify the risk factors and to propose a risk prediction model for the development of corneal injury, in adult patients, in an intensive care unit of a public hospital. This is a one year, prospective cohort study with 254 patients. The data were analyzed using descriptive statistics, univariate and logistic regression. Of the 254 patients, 59.4% had corneal injuries and the mean time to onset was 8.9 days. The independent variables that predispose to risk for punctate type corneal injury were: duration of hospitalization, other ventilatory support device, presence of edema and blinking less than five times a minute. The Glasgow Coma Scale and exposure of the ocular globe were the variables related to corneal ulcer type corneal injury. The injury frequencies were punctate type (55.1%) and corneal ulcers (11.8%). Risk prediction models for the development of punctate and corneal ulcer type corneal injury were established.

scholarly journals Risk prediction models for intensive care unit-acquired weakness in intensive care unit patients: A systematic review

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0257768
Author(s):  
Wei Zhang ◽  
Yun Tang ◽  
Huan Liu ◽  
Li ping Yuan ◽  
Chu chu Wang ◽  
...  
Keyword(s):  
Systematic Review ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Risk Prediction ◽  
Prediction Models ◽  
Risk Groups ◽  
Icu Patients ◽  
Risk Prediction Models ◽  
Verification Methods

Background and objectives Intensive care unit-acquired weakness (ICU-AW) commonly occurs among intensive care unit (ICU) patients and seriously affects the survival rate and long-term quality of life for patients. In this systematic review, we synthesized the findings of previous studies in order to analyze predictors of ICU-AW and evaluate the discrimination and validity of ICU-AW risk prediction models for ICU patients. Methods We searched seven databases published in English and Chinese language to identify studies regarding ICU-AW risk prediction models. Two reviewers independently screened the literature, evaluated the quality of the included literature, extracted data, and performed a systematic review. Results Ultimately, 11 studies were considered for this review. For the verification of prediction models, internal verification methods had been used in three studies, and a combination of internal and external verification had been used in one study. The value for the area under the ROC curve for eight models was 0.7–0.923. The predictor most commonly included in the models were age and the administration of corticosteroids. All the models have good applicability, but most of the models are biased due to the lack of blindness, lack of reporting, insufficient sample size, missing data, and lack of performance evaluation and calibration of the models. Conclusions The efficacy of most models for the risk prediction of ICU-AW among high-risk groups is good, but there was a certain bias in the development and verification of the models. Thus, ICU medical staff should select existing models based on actual clinical conditions and verify them before applying them in clinical practice. In order to provide a reliable basis for the risk prediction of ICU-AW, it is necessary that large-sample, multi-center studies be conducted in the future, in which ICU-AW risk prediction models are verified.

scholarly journals Beta-Lactams Toxicity in the Intensive Care Unit: An Underestimated Collateral Damage?

2021 ◽  
Vol 9 (7) ◽  
pp. 1505
Author(s):  
Claire Roger ◽  
Benjamin Louart
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Clinical Manifestations ◽  
Acute Interstitial Nephritis ◽  
Convulsive Status Epilepticus ◽  
Beta Lactam ◽  
Beta Lactams ◽  
Drug Induced ◽  
Icu Patients

Beta-lactams are the most commonly prescribed antimicrobials in intensive care unit (ICU) settings and remain one of the safest antimicrobials prescribed. However, the misdiagnosis of beta-lactam-related adverse events may alter ICU patient management and impact clinical outcomes. To describe the clinical manifestations, risk factors and beta-lactam-induced neurological and renal adverse effects in the ICU setting, we performed a comprehensive literature review via an electronic search on PubMed up to April 2021 to provide updated clinical data. Beta-lactam neurotoxicity occurs in 10–15% of ICU patients and may be responsible for a large panel of clinical manifestations, ranging from confusion, encephalopathy and hallucinations to myoclonus, convulsions and non-convulsive status epilepticus. Renal impairment, underlying brain abnormalities and advanced age have been recognized as the main risk factors for neurotoxicity. In ICU patients, trough concentrations above 22 mg/L for cefepime, 64 mg/L for meropenem, 125 mg/L for flucloxacillin and 360 mg/L for piperacillin (used without tazobactam) are associated with neurotoxicity in 50% of patients. Even though renal complications (especially severe complications, such as acute interstitial nephritis, renal damage associated with drug induced hemolytic anemia and renal obstruction by crystallization) remain rare, there is compelling evidence of increased nephrotoxicity using well-known nephrotoxic drugs such as vancomycin combined with beta-lactams. Treatment mainly relies on the discontinuation of the offending drug but in the near future, antimicrobial optimal dosing regimens should be defined, not only based on pharmacokinetics/pharmacodynamic (PK/PD) targets associated with clinical and microbiological efficacy, but also on PK/toxicodynamic targets. The use of dosing software may help to achieve these goals.

scholarly journals Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Comparative Machine Learning Study (Preprint)

2020 ◽  
Author(s):  
Sujeong Hur ◽  
Ji Young Min ◽  
Junsang Yoo ◽  
Kyunga Kim ◽  
Chi Ryang Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Patient Safety ◽  
Intensive Care ◽  
Predictive Value ◽  
Prediction Models ◽  
Support Vector ◽  
Unplanned Extubation ◽  
Electronic Health Record Data ◽  
Icu Patients

BACKGROUND Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered as the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care. OBJECTIVE This study aimed to develop and validate prediction models for UE in ICU patients using machine learning. METHODS This study was conducted an academic tertiary hospital in Seoul. The hospital had approximately 2,000 inpatient beds and 120 intensive care unit (ICU) beds. The number of patients, on daily basis, was approximately 9,000 for the out-patient. The number of annual ICU admission was approximately 10,000. We conducted a retrospective study between January 1, 2010 and December 31, 2018. A total of 6,914 extubation cases were included. We developed an unplanned extubation prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model’s performance, we used area under the receiver operator characteristic curve (AUROC). Sensitivity, specificity, positive predictive value negative predictive value, and F1-score were also determined for each model. For performance evaluation, we also used calibration curve, the Brier score, and the Hosmer-Lemeshow goodness-of-fit statistic. RESULTS Among the 6,914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was more likely to occur during the night shift compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality was higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.762, and for SVM was 0.740. CONCLUSIONS We successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787, which was obtained using RF. CLINICALTRIAL N/A

Risk Factors Associated With Resistance to Ciprofloxacin in Clinical Bacterial Isolates From Intensive Care Unit Patients

2007 ◽  
Vol 28 (3) ◽  
pp. 331-336 ◽  
Author(s):  
Phillip D. Levin ◽  
Robert A. Fowler ◽  
Cameron Guest ◽  
William J. Sibbald ◽  
Alex Kiss ◽  
...  
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Prior Treatment ◽  
Bacterial Isolates ◽  
Icu Patients ◽  
Gram Negative ◽  
Factors Associated ◽  
Icu Admission ◽  
Ciprofloxacin Resistance

Objective.To determine risk factors and outcomes associated with ciprofloxacin resistance in clinical bacterial isolates from intensive care unit (ICU) patients.Design.Prospective cohort study.Setting.Twenty-bed medical-surgical ICU in a Canadian tertiary care teaching hospital.Patients.All patients admitted to the ICU with a stay of at least 72 hours between January 1 and December 31, 2003.Methods.Prospective surveillance to determine patient comorbidities, use of medical devices, nosocomial infections, use of antimicrobials, and outcomes. Characteristics of patients with a ciprofloxacin-resistant gram-negative bacterial organism were compared with characteristics of patients without these pathogens.Results.Ciprofloxacin-resistant organisms were recovered from 20 (6%) of 338 ICU patients, representing 38 (21%) of 178 nonduplicate isolates of gram-negative bacilli. Forty-nine percent ofPseudomonas aeruginosaisolates and 29% ofEscherichia coliisolates were resistant to ciprofloxacin. In a multivariate analysis, independent risk factors associated with the recovery of a ciprofloxacin-resistant organism included duration of prior treatment with ciprofloxacin (relative risk [RR], 1.15 per day [95% confidence interval {CI}, 1.08-1.23];P< .001), duration of prior treatment with levofloxacin (RR, 1.39 per day [95% CI, 1.01-1.91];P= .04), and length of hospital stay prior to ICU admission (RR, 1.02 per day [95% CI, 1.01-1.03];P= .005). Neither ICU mortality (15% of patients with a ciprofloxacin-resistant isolate vs 23% of patients with a ciprofloxacin-susceptible isolate;P= .58 ) nor in-hospital mortality (30% vs 34%;P= .81 ) were statistically significantly associated with ciprofloxacin resistance.Conclusions.ICU patients are at risk of developing infections due to ciprofloxacin-resistant organisms. Variables associated with ciprofloxacin resistance include prior use of fluoroquinolones and duration of hospitalization prior to ICU admission. Recognition of these risk factors may influence antibiotic treatment decisions.

scholarly journals Staphylococcus aureusNasal Colonization and Subsequent Infection in Intensive Care Unit Patients: Does Methicillin Resistance Matter?

2010 ◽  
Vol 31 (6) ◽  
pp. 584-591 ◽  
Author(s):  
Hitoshi Honda ◽  
Melissa J. Krauss ◽  
Craig M. Coopersmith ◽  
Marin H. Kollef ◽  
Amy M. Richmond ◽  
...  
Keyword(s):  
Risk Factors ◽  
Intensive Care Unit ◽  
Intensive Care ◽  
Confidence Interval ◽  
Methicillin Resistance ◽  
Hazard Ratio ◽  
Adjusted Hazard Ratio ◽  
Patient Specific ◽  
Icu Patients ◽  
Icu Admission

Background.Staphylococcus aureusis an important cause of infection in intensive care unit (ICU) patients. Colonization with methicillin-resistantS. aureus(MRSA) is a risk factor for subsequentS. aureusinfection. However, MRSA-colonized patients may have more comorbidities than methicillin-susceptibleS. aureus(MSSA)-colonized or noncolonized patients and therefore may be more susceptible to infection on that basis.Objective.To determine whether MRSA-colonized patients who are admitted to medical and surgical ICUs are more likely to develop anyS. aureusinfection in the ICU, compared with patients colonized with MSSA or not colonized withS. aureus,independent of predisposing patient risk factors.Design.Prospective cohort study.Setting.A 24-bed surgical ICU and a 19-bed medical ICU of a 1,252-bed, academic hospital.Patients.A total of 9,523 patients for whom nasal swab samples were cultured forS. aureusat ICU admission during the period from December 2002 through August 2007.Methods.Patients in the ICU for more than 48 hours were examined for an ICU-acquired S.aureusinfection, defined as development ofS. aureusinfection more than 48 hours after ICU admission.Results.S. aureuscolonization was present at admission for 1,433 (27.8%) of 5,161 patients (674 [47.0%] with MRSA and 759 [53.0%] with MSSA). An ICU-acquiredS. aureusinfection developed in 113 (2.19%) patients, of whom 75 (66.4%) had an infection due to MRSA. Risk factors associated with an ICU-acquiredS. aureusinfection included MRSA colonization at admission (adjusted hazard ratio, 4.70 [95% confidence interval, 3.07-7.21]) and MSSA colonization at admission (adjusted hazard ratio, 2.47 [95% confidence interval, 1.52-4.01]).Conclusion.ICU patients colonized with S.aureuswere at greater risk of developing aS. aureusinfection in the ICU. Even after adjusting for patient-specific risk factors, MRSA-colonized patients were more likely to developS. aureusinfection, compared with MSSA-colonized or noncolonized patients.

scholarly journals Development and Evaluation of Models to Predict Readmission or Death After Discharge from Intensive Care 

2021 ◽  
Author(s):  
Jamie M Boyd ◽  
Matthew T James ◽  
Danny J Zuege ◽  
Henry Thomas Stelfox
Keyword(s):  
Risk Factors ◽  
Systematic Review ◽  
Intensive Care ◽  
Risk Prediction ◽  
Prediction Models ◽  
Meta Analysis ◽  
Local Data ◽  
Predictive Values ◽  
Risk Prediction Models ◽  
Icu Discharge

Abstract Background Patients being discharged from the intensive care unit (ICU) have variable risks of subsequent readmission or death; however, there is limited understanding of how to predict individual patient risk. We sought to derive risk prediction models for ICU readmission or death after ICU discharge to guide clinician decision-making. Methods Systematic review and meta-analysis to identify risk factors. Development and validation of risk prediction models using two retrospective cohorts of patients discharged alive from medical-surgical ICUs (n = 3 ICUs, n = 11,291 patients; n = 14 ICUs, n = 11,400 patients). Models were developed using literature and data-derived weighted coefficients. Results Sixteen variables identified from the systematic review were used to develop four risk prediction models. In the validation cohort there were 795 (7%) patients who were re-admitted to ICU and 703 (7%) patients who died after ICU discharge. The area under the curve (AUROC) for ICU readmission for the literature (0.615 [95%CI: 0.593, 0.637]) and data (0.652 [95%CI: 0.631, 0.674]) weighted models showed poor discrimination. The AUROC for death after ICU discharge for the literature (0.708 [95%CI: 0.687, 0.728]) and local data weighted (0.752 [95%CI: 0.733, 0.770]) models showed good discrimination. The negative predictive values for ICU readmission and death after ICU discharge ranged from 94%-98%. Conclusions Identifying risk factors and weighting coefficients using systematic review and meta-analysis to develop prediction models is feasible and can identify patients at low risk of ICU readmission or death after ICU discharge.

Sign in / Sign up

Export Citation Format

Share Document