Validation of a Prospective Urinalysis-Based Prediction Model for ICU Resources and Outcome of COVID-19 Disease: A Multicenter Cohort Study.
Ontology highlight
ABSTRACT:
SUBMITTER: Gross O
PROVIDER: S-EPMC8306631 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundIntensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes.MethodsA Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported.Results1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict "survival". Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients' age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy.ConclusionsUsing Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models. Trial registration "ClinicalTrials" (clinicaltrials.gov) under NCT04455451.
| S-EPMC8370055 | biostudies-literature
Project description:BackgroundThe identification of critically ill COVID-19 patients at risk of fatal outcomes remains a challenge. Here, we first validated candidate microRNAs (miRNAs) as biomarkers for clinical decision-making in critically ill patients. Second, we constructed a blood miRNA classifier for the early prediction of adverse outcomes in the ICU.MethodsThis was a multicenter, observational and retrospective/prospective study including 503 critically ill patients admitted to the ICU from 19 hospitals. qPCR assays were performed in plasma samples collected within the first 48 h upon admission. A 16-miRNA panel was designed based on recently published data from our group.ResultsNine miRNAs were validated as biomarkers of all-cause in-ICU mortality in the independent cohort of critically ill patients (FDR < 0.05). Cox regression analysis revealed that low expression levels of eight miRNAs were associated with a higher risk of death (HR from 1.56 to 2.61). LASSO regression for variable selection was used to construct a miRNA classifier. A 4-blood miRNA signature composed of miR-16-5p, miR-192-5p, miR-323a-3p and miR-451a predicts the risk of all-cause in-ICU mortality (HR 2.5). Kaplan‒Meier analysis confirmed these findings. The miRNA signature provides a significant increase in the prognostic capacity of conventional scores, APACHE-II (C-index 0.71, DeLong test p-value 0.055) and SOFA (C-index 0.67, DeLong test p-value 0.001), and a risk model based on clinical predictors (C-index 0.74, DeLong test-p-value 0.035). For 28-day and 90-day mortality, the classifier also improved the prognostic value of APACHE-II, SOFA and the clinical model. The association between the classifier and mortality persisted even after multivariable adjustment. The functional analysis reported biological pathways involved in SARS-CoV infection and inflammatory, fibrotic and transcriptional pathways.ConclusionsA blood miRNA classifier improves the early prediction of fatal outcomes in critically ill COVID-19 patients.
| S-EPMC10276486 | biostudies-literature
Project description:RationalTo evaluate the respective impact of standard oxygen, high-flow nasal cannula (HFNC) and noninvasive ventilation (NIV) on oxygenation failure rate and mortality in COVID-19 patients admitted to intensive care units (ICUs).MethodsMulticenter, prospective cohort study (COVID-ICU) in 137 hospitals in France, Belgium, and Switzerland. Demographic, clinical, respiratory support, oxygenation failure, and survival data were collected. Oxygenation failure was defined as either intubation or death in the ICU without intubation. Variables independently associated with oxygenation failure and Day-90 mortality were assessed using multivariate logistic regression.ResultsFrom February 25 to May 4, 2020, 4754 patients were admitted in ICU. Of these, 1491 patients were not intubated on the day of ICU admission and received standard oxygen therapy (51%), HFNC (38%), or NIV (11%) (P < 0.001). Oxygenation failure occurred in 739 (50%) patients (678 intubation and 61 death). For standard oxygen, HFNC, and NIV, oxygenation failure rate was 49%, 48%, and 60% (P < 0.001). By multivariate analysis, HFNC (odds ratio [OR] 0.60, 95% confidence interval [CI] 0.36-0.99, P = 0.013) but not NIV (OR 1.57, 95% CI 0.78-3.21) was associated with a reduction in oxygenation failure). Overall 90-day mortality was 21%. By multivariable analysis, HFNC was not associated with a change in mortality (OR 0.90, 95% CI 0.61-1.33), while NIV was associated with increased mortality (OR 2.75, 95% CI 1.79-4.21, P < 0.001).ConclusionIn patients with COVID-19, HFNC was associated with a reduction in oxygenation failure without improvement in 90-day mortality, whereas NIV was associated with a higher mortality in these patients. Randomized controlled trials are needed.
| S-EPMC8653629 | biostudies-literature
Project description:PurposeTo compare the characteristics, management, and prognosis of patients admitted to intensive care units (ICU) for coronavirus disease (COVID)-19 during the first two waves of the outbreak and to evaluate the relationship between ICU strain (ICU demand due to COVID-19 admissions) and mortality.MethodsIn a multicentre retrospective study, 1166 COVID-19 patients admitted to five ICUs in France between 20 February and 31 December 2020 were included. Data were collected at each ICU from medical records. A Cox proportional-hazards model identified factors associated with 28-day mortality.Results640 patients (55%) were admitted during the first wave (February to June 2020) and 526 (45%) during the second wave (July to December 2020). ICU strain was lower during the second wave (-0.81 [-1.04 --0.31] vs. 1.18 [-0.34-1.29] SD when compared to mean COVID-19 admission in each center during study period, P<0.001). Patients admitted during the second wave were older, had more profound hypoxemia and lower SOFA. High flow nasal cannula was more frequently used during the second wave (68% vs. 39%, P<0.001) and intubation was less frequent (46% vs. 69%, P<0.001). Neither 28-day mortality (30% vs. 26%, P = 0.12) nor hospital mortality (37% vs. 31%, P = 0.27) differed between first and second wave. Overweight and obesity were associated with lower 28-day mortality while older age, underlying chronic kidney disease, severity at ICU admission as assessed by SOFA score and ICU strain were associated with higher 28-day mortality. ICU strain was not associated with hospital mortality.ConclusionThe characteristics and the management of patients varied between the first and the second wave of the pandemic. Rather than the wave, ICU strain was independently associated with 28-day mortality, but not with hospital mortality.
| S-EPMC9295940 | biostudies-literature
Project description:BackgroundVaricella-zoster virus (VZV) is one of the main viruses responsible of acute encephalitis. However, data on the prognosis and neurologic outcome of critically ill patients with VZV encephalitis are limited. We aimed to describe the clinical features of VZV encephalitis in the ICU and to identify factors associated with a favorable neurologic outcome. We performed a multicenter cohort study of patients with VZV encephalitis admitted in 18 ICUs in France between 2000 and 2017. Factors associated with a favorable neurologic outcome, defined by a modified Rankin Score (mRS) of 0-2 1 year after ICU admission, were identified by multivariable regression analysis.ResultsFifty-five patients (29 (53%) men, median age 53 (interquartile range 36-66)) were included, of whom 43 (78%) were immunocompromised. ICU admission occurred 1 (0-3) day after the onset of neurological symptoms. Median Glasgow Coma Score at ICU admission was 12 (7-14). Cerebrospinal fluid examination displayed a median leukocyte count of 68 (13-129)/mm3, and a median protein level of 1.37 (0.77-3.67) g/L. CT scan and MRI revealed brain lesions in 30% and 66% of the cases, respectively. Invasive mechanical ventilation was implemented in 46 (84%) patients for a median duration of 13 (3-30) days. Fourteen (25%) patients died in the ICU. One year after ICU admission, 20 (36%) patients had a favorable neurologic outcome (mRS 0-2), 12 (22%) had significant disability (mRS 3-5), and 18 (33%) were deceased (lost to follow-up n = 5, 9%). On multivariable analysis, age (OR 0.92 per year, (0.88-0.97), p = 0.01), and invasive mechanical ventilation (OR 0.09 CI 95% (0.01-0.84), p = 0.03) reduced the likelihood of favorable neurologic outcome.ConclusionOne in every three critically ill patients with VZV encephalitis had a favorable neurologic outcome 1 year after ICU admission. Older age and invasive mechanical ventilation were associated with a higher risk of disability and death.
| S-EPMC8982685 | biostudies-literature
Project description:IntroductionDelirium is a severe complication that is associated with short-term adverse events, prolonged hospital stay and neurological sequelae in survivors. Automated pupillometry is an easy-to-use device that allows for accurate objective assessment of the pupillary light responses in comatose patients in the intensive care unit (ICU). Whether automated pupillometry might predict delirium in critically ill patients is not known. We hypothesise that automated pupillometry could predict the occurrence of delirium in critically ill patients without primary brain injury, requiring more than 48 hours of invasive mechanical ventilation in the ICU.Methods and analysisThe PupillOmetry for preDIction of DeliriUM in ICU (PODIUM) study is a prospective cohort study, which will be conducted in eight French ICUs in the Paris area. We aim to recruit 213 adult patients requiring invasive mechanical ventilation for more than 48 hours. Automated pupillometry (Neurological Pupil Index; NPi-200, Neuroptics) will be assessed two times per day for 7 days. Delirium will be assessed using the Confusion Assessment Method in ICU two times per day over 14 days in non-comatose patients (Richmond Agitation and Sedation Scale ≥-3).The predictive performances of the seven automated pupillometry parameters (ie, pupillary diameter, variation of the pupillary diameter, pupillary constriction speed, pupillary dilatation speed, photomotor reflex latency, NPi and symmetry of pupillary responses) measured to detect the delirium occurrence within 14 days will be the main outcomes. Secondary outcomes will be the predictive performances of the seven automated pupillometry parameters to detect complications related to delirium, ICU length of stay, mortality, functional and cognitive outcomes at 90 days.Ethics and disseminationThe PODIUM study has been approved by an independent ethics committee, the Comité de Protection des Personnes (CPP) OUEST IV-NANTES (CPP21.02.15.45239 32/21_3) on 06 April 2021). Participant recruitment started on 15 April 2022. Results will be published in international peer-reviewed medical journals and presented at conferences.Trial registration numberNCT05248035; clinicaltrials.gov.
| S-EPMC10347512 | biostudies-literature
Project description:The incidence of secondary infections in critically ill coronavirus disease 2019 (COVID-19) patients is worrisome. We investigated whether selective digestive decontamination (SDD) added to infection control measures during an intensive care unit (ICU) stay modified these infection rates.MethodsA retrospective observational cohort study was carried out in four ICUs in Spain. All consecutive ventilated patients with a SARS-CoV-2 infection engaged in national infection control programs between 1 March and 10 December 2020 were investigated. Patients were grouped into two cohorts according to the site of ICU admission. Secondary relevant infections were included. Infection densities corresponding to ventilator-associated pneumonia (VAP), catheter bacteremia, secondary bacteremia, and multi-resistant germs were obtained as the number of events per 1000 days of exposure and were compared between SDD and non-SDD groups using Poisson regression. Factors that had an independent association with mortality were identified using multidimensional logistic analysis.ResultsThere were 108 patients in the SDD cohort and 157 in the non-SDD cohort. Patients in the SDD cohort showed significantly lower rates (p < 0.001) of VAP (1.9 vs. 9.3 events per 1000 ventilation days) and MDR infections (0.57 vs. 2.28 events per 1000 ICU days) and a non-significant reduction in secondary bacteremia (0.6 vs. 1.41 events per 1000 ICU days) compared with those in the non-SDD cohort. Infections caused by MDR pathogens occurred in 5 patients in the SDD cohort and 21 patients in the non-SDD cohort (p = 0.006). Differences in mortality according to SDD were not found.ConclusionThe implementation of SDD in infection control programs significantly reduced the incidence of VAP and MDR infections in critically ill SARS-CoV-2 infected patients.
| S-EPMC9405068 | biostudies-literature
Project description:The ability to accurately predict the prognosis and intervention requirements for treating highly infectious diseases, such as COVID-19, can greatly support the effective management of patients, especially in resource-limited settings. The aim of the study is to develop and validate a multimodal artificial intelligence (AI) system using clinical findings, laboratory data and AI-interpreted features of chest X-rays (CXRs), and to predict the prognosis and the required interventions for patients diagnosed with COVID-19, using multi-center data. In total, 2282 real-time reverse transcriptase polymerase chain reaction-confirmed COVID-19 patients' initial clinical findings, laboratory data and CXRs were retrospectively collected from 13 medical centers in South Korea, between January 2020 and June 2021. The prognostic outcomes collected included intensive care unit (ICU) admission and in-hospital mortality. Intervention outcomes included the use of oxygen (O2) supplementation, mechanical ventilation and extracorporeal membrane oxygenation (ECMO). A deep learning algorithm detecting 10 common CXR abnormalities (DLAD-10) was used to infer the initial CXR taken. A random forest model with a quantile classifier was used to predict the prognostic and intervention outcomes, using multimodal data. The area under the receiver operating curve (AUROC) values for the single-modal model, using clinical findings, laboratory data and the outputs from DLAD-10, were 0.742 (95% confidence interval [CI], 0.696-0.788), 0.794 (0.745-0.843) and 0.770 (0.724-0.815), respectively. The AUROC of the combined model, using clinical findings, laboratory data and DLAD-10 outputs, was significantly higher at 0.854 (0.820-0.889) than that of all other models (p < 0.001, using DeLong's test). In the order of importance, age, dyspnea, consolidation and fever were significant clinical variables for prediction. The most predictive DLAD-10 output was consolidation. We have shown that a multimodal AI model can improve the performance of predicting both the prognosis and intervention in COVID-19 patients, and this could assist in effective treatment and subsequent resource management. Further, image feature extraction using an established AI engine with well-defined clinical outputs, and combining them with different modes of clinical data, could be a useful way of creating an understandable multimodal prediction model.
| S-EPMC9269794 | biostudies-literature
Project description: Not available
| S-EPMC9799109 | biostudies-literature
Project description:Background: Tracheal stenosis represents a fearsome complication that substantially impairs quality of life. The recent SARS-CoV-2 pandemic increased the number of patients requiring invasive ventilation through prolonged intubation or tracheostomy, increasing the risk of tracheal stenosis. Study design and methods: In this prospective, observational, multicenter study performed in Lombardy (Italy), we have exanimated 281 patients who underwent prolonged intubation (more than 7 days) or tracheostomy for severe COVID-19. Patients underwent CT scan and spirometry 2 months after hospital discharge and a subsequent clinical follow-up after an additional 6 months (overall 8 months of follow-up duration) to detect any tracheal lumen reduction above 1%. The last follow-up evaluation was completed on 31 August 2022. Results: In the study period, 24 patients (8.5%, CI 5.6-12.4) developed tracheal stenosis in a median time of 112 days and within a period of 200 days from intubation. Compared to patients without tracheal stenosis, tracheostomy was performed more frequently in patients that developed stenosis (75% vs 54%, p = 0.034). Tracheostomy and alcohol consumption (1 unit of alcohol per day) increased risk of developing tracheal stenosis of 2.6-fold (p = 0.047; IC 0.99-6.8) and 5.4-fold (p = 0.002; CI 1.9-16), respectively. Conclusions: In a large cohort of patients, the incidence of tracheal stenosis increased during pandemic, probably related to the increased use of prolonged intubation. Patients with histories of prolonged intubation should be monitored for at least 200 days from invasive ventilation in order to detect tracheal stenosis at early stage. Alcohol use and tracheostomy are risk factors for developing tracheal stenosis.
| S-EPMC10817429 | biostudies-literature