Effect of admission in the stroke care unit versus intensive care unit on in-hospital mortality in patients with acute ischemic stroke
Ontology highlight
ABSTRACT:
SUBMITTER: Kanda M
PROVIDER: S-EPMC10641943 | biostudies-literature | 2023 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: Acute ischemic stroke is a leading cause of death in the United States. Identifying patients with stroke at high risk of mortality is crucial for timely intervention and optimal resource allocation. This study aims to develop and validate machine learning-based models to predict in-hospital mortality risk for intensive care unit (ICU) patients with acute ischemic stroke and identify important associated factors. Methods: Our data include 3,489 acute ischemic stroke admissions to the ICU for patients not discharged or dead within 48 h from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. Demographic, hospitalization type, procedure, medication, intake (intravenous and oral), laboratory, vital signs, and clinical assessment [e.g., Glasgow Coma Scale Scores (GCS)] during the initial 48 h of admissions were used to predict in-hospital mortality after 48 h of ICU admission. We explored 3 machine learning models (random forests, logistic regression, and XGBoost) and applied Bayesian optimization for hyperparameter tuning. Important features were identified using learned coefficients. Results: Experiments show that XGBoost tuned for area under the receiver operating characteristic curve (AUC ROC) was the best performing model (AUC ROC 0.86, F1 0.52), compared to random forests (AUC ROC 0.85, F1 0.47) and logistic regression (AUC ROC 0.75, F1 0.40). Top features include GCS, blood urea nitrogen, and Richmond RASS score. The model also demonstrates good fairness for males versus females and across racial/ethnic groups. Conclusions: Machine learning has shown great potential in predicting in-hospital mortality risk for people with acute ischemic stroke in the ICU setting. However, more ethical considerations need to be applied to ensure that performance differences across different racial/ethnic groups will not exacerbate existing health disparities and will not harm historically marginalized populations.
| S-EPMC11912875 | biostudies-literature
Project description:Background and purposeLittle is currently known about the cost-effectiveness of intensive care of acute ischemic stroke (AIS). We evaluated 1-year costs and outcome for patients with AIS treated in the intensive care unit (ICU).Materials and methodsA single-center retrospective study of patients admitted to an academic ICU with AIS between 2003 and 2013. True healthcare expenditure was obtained up to 1 year after admission and adjusted to consumer price index of 2019. Patient outcome was 12-month functional outcome and mortality. We used multivariate logistic regression analysis to identify independent predictors of favorable outcomes and linear regression analysis to assess factors associated with costs. We calculated the effective cost per survivor (ECPS) and effective cost per favorable outcome (ECPFO).ResultsThe study population comprised 154 patients. Reasons for ICU admission were: decreased consciousness level (47%) and need for respiratory support (40%). There were 68 (44%) 1 year survivors, of which 27 (18%) had a favorable outcome. High age (odds ratio [OR] 0.95, 95% confidence interval [CI] 0.91-0.98) and high hospital admission National Institutes of Health Stroke Scale score (OR 0.92, 95% CI 0.87-0.97) were independent predictors of poor outcomes. Increased age had a cost ratio of 0.98 (95% CI 0.97-0.99) per added year. The ECPS and ECPFO were 115,628€ and 291,210€, respectively.ConclusionsTreatment of AIS in the ICU is resource-intense, and in an era predating mechanical thrombectomy the outcome is often poor, suggesting a need for further research into cost-efficacy of ICU care for AIS patients.
| S-EPMC9304289 | biostudies-literature
Project description:BackgroundHypoxia and hypercapnia due to acute pulmonary failure in patients with coronavirus disease 2019 (COVID-19) can increase the intracranial pressure (ICP). ICP correlated with the optic nerve sheath diameter (ONSD) on ultrasonography and is associated with a poor prognosis.AimWe investigated the capability of ONSD measured during admission to the intensive care unit (ICU) in patients with critical COVID-19 in predicting in-hospital mortality.MethodsA total of 91 patients enrolled in the study were divided into two groups: survivor (n = 48) and nonsurvivor (n = 43) groups. ONSD was measured by ultrasonography within the first 3 h of ICU admission.ResultsThe median ONSD was higher in the nonsurvivor group than in the survivor group (5.95 mm vs. 4.15 mm, p < 0.001). The multivariate Cox proportional hazard regression analysis between ONSD and in-hospital mortality (contains 26 covariates) was significant (adjusted hazard ratio, 4.12; 95% confidence interval, 1.46-11.55; p = 0.007). The ONSD cutoff for predicting mortality during ICU admission was 5 mm (area under the curve, 0.985; sensitivity, 98%; and specificity, 90%). The median survival of patients with ONSD >5 mm (43%; n = 39) was lower than those with ONSD ≤ 5 mm (57%; n = 52) (11.5 days vs 13.2 days; log-rank test p = 0.001).ConclusionsONSD ultrasonography during ICU admission may be an important, cheap, and easy-to-apply method that can be used to predict mortality in the early period in patients with critical COVID-19.
| S-EPMC9619847 | biostudies-literature
Project description:BackgroundThe aim of this study was to investigate the predictors of intensive care unit (ICU) admission and mortality among stroke patients and the effects of a pulmonary rehabilitation program on stroke patients.MethodsThis prospective study enrolled 181 acute ischemic stroke patients aged between 40 and 90 years. Demographical characteristics, laboratory tests, diffusion-weighed magnetic resonance imaging (DWI-MRI) time, nutritional status, vascular risk factors, National Institute of Health Stroke Scale (NIHSS) scores and modified Rankin scale (MRS) scores were recorded for all patients. One-hundred patients participated in the pulmonary rehabilitation program, 81 of whom served as a control group.ResultsStatistically, one- and three-month mortality was associated with NIHSS and MRS scores at admission and three months (p<0.001; r=0.440, r=0.432, r=0.339 and r=0.410, respectively). One and three months mortality- ICU admission had a statistically significant relationship with parenteral nutrition (p<0.001; r=0.346, r=0.300, respectively; r=0.294 and r=0.294, respectively). Similarly, there was also a statistically significant relationship between pneumonia onset and one- and three-month mortality- ICU admission (p<0.05; r=0.217, r=0.127, r=0.185 and r=0.185, respectively). A regression analysis showed that parenteral nutrition (odds ratio [OR] =13.434, 95% confidence interval [CI] =1.148-157.265, p=0.038) was a significant predictor of ICU admission. The relationship between pulmonary physiotherapy (PPT) and ICU admission- pneumonia onset at the end of three months was statistically significant (p=0.04 and p=0.043, respectively).ConclusionThis study showed that PPT improved the prognosis of ischemic stroke patients. We believe that a pulmonary rehabilitation program, in addition to general stroke rehabilitation programs, can play a critical role in improving survival and functional outcomes.Trial registrationNCT03195907 . Trial registration date: 21.06.2017 'Retrospectively registered'.
| S-EPMC5504678 | biostudies-literature
Project description:BackgroundWe aimed to develop and validate models for predicting intensive care unit (ICU) mortality of critically ill adult patients as early as upon ICU admission.MethodsCombined data of 79,657 admissions from two teaching hospitals' ICU databases were used to train and validate the machine learning models to predict ICU mortality upon ICU admission and at 24 h after ICU admission by using logistic regression, gradient boosted trees (GBT), and deep learning algorithms.ResultsIn the testing dataset for the admission models, the ICU mortality rate was 7%, and 38.4% of patients were discharged alive or dead within 1 day of ICU admission. The area under the receiver operating characteristic curve (0.856, 95% CI 0.845-0.867) and area under the precision-recall curve (0.331, 95% CI 0.323-0.339) were the highest for the admission GBT model. The ICU mortality rate was 17.4% in the 24-hour testing dataset, and the performance was the highest for the 24-hour GBT model.ConclusionThe ADM models can provide crucial information on ICU mortality as early as upon ICU admission. 24 H models can be used to improve the prediction of ICU mortality for patients discharged more than 1 day after ICU admission.
| S-EPMC11656927 | biostudies-literature
Project description: Not available
| S-EPMC3359892 | biostudies-literature
Project description:BackgroundMultiple factors contribute to mortality after ICU, but it is unclear how the predictive value of these factors changes during ICU admission. We aimed to compare the changing performance over time of the acute illness component, antecedent patient characteristics, and ICU length of stay (LOS) in predicting 1-year mortality.MethodsIn this retrospective observational cohort study, the discriminative value of four generalized mixed-effects models was compared for 1-year and hospital mortality. Among patients with increasing ICU LOS, the models included (a) acute illness factors and antecedent patient characteristics combined, (b) acute component only, (c) antecedent patient characteristics only, and (d) ICU LOS. For each analysis, discrimination was measured by area under the receiver operating characteristics curve (AUC), calculated using the bootstrap method. Statistical significance between the models was assessed using the DeLong method (p value < 0.05).ResultsIn 400,248 ICU patients observed, hospital mortality was 11.8% and 1-year mortality 21.8%. At ICU admission, the combined model predicted 1-year mortality with an AUC of 0.84 (95% CI 0.84-0.84). When analyzed separately, the acute component progressively lost predictive power. From an ICU admission of at least 3 days, antecedent characteristics significantly exceeded the predictive value of the acute component for 1-year mortality, AUC 0.68 (95% CI 0.68-0.69) versus 0.67 (95% CI 0.67-0.68) (p value < 0.001). For hospital mortality, antecedent characteristics outperformed the acute component from a LOS of at least 7 days, comprising 7.8% of patients and accounting for 52.4% of all bed days. ICU LOS predicted 1-year mortality with an AUC of 0.52 (95% CI 0.51-0.53) and hospital mortality with an AUC of 0.54 (95% CI 0.53-0.55) for patients with a LOS of at least 7 days.ConclusionsComparing the predictive value of factors influencing 1-year mortality for patients with increasing ICU LOS, antecedent patient characteristics are more predictive than the acute component for patients with an ICU LOS of at least 3 days. For hospital mortality, antecedent patient characteristics outperform the acute component for patients with an ICU LOS of at least 7 days. After the first week of ICU admission, LOS itself is not predictive of hospital nor 1-year mortality.
| S-EPMC7291572 | biostudies-literature
Project description:BackgroundRisk stratification of elderly patients with ischemic stroke (IS) who are admitted to the intensive care unit (ICU) remains a challenging task. This study aims to establish and validate predictive models that are based on novel machine learning (ML) algorithms for 28-day in-hospital mortality in elderly patients with IS who were admitted to the ICU.MethodsData of elderly patients with IS were extracted from the electronic intensive care unit (eICU) Collaborative Research Database (eICU-CRD) records of those elderly patients admitted between 2014 and 2015. All selected participants were randomly divided into two sets: a training set and a validation set in the ratio of 8:2. ML algorithms, such as Naïve Bayes (NB), eXtreme Gradient Boosting (xgboost), and logistic regression (LR), were applied for model construction utilizing 10-fold cross-validation. The performance of models was measured by the area under the receiver operating characteristic curve (AUC) analysis and accuracy. The present study uses interpretable ML methods to provide insight into the model's prediction and outcome using the SHapley Additive exPlanations (SHAP) method.ResultsAs regards the population demographics and clinical characteristics, the analysis in the present study included 1,236 elderly patients with IS in the ICU, of whom 164 (13.3%) died during hospitalization. As regards feature selection, a total of eight features were selected for model construction. In the training set, both the xgboost and NB models showed specificity values of 0.989 and 0.767, respectively. In the internal validation set, the xgboost model identified patients who died with an AUC value of 0.733 better than the LR model which identified patients who died with an AUC value of 0.627 or the NB model 0.672.ConclusionThe xgboost model shows the best predictive performance that predicts mortality in elderly patients with IS in the ICU. By making the ML model explainable, physicians would be able to understand better the reasoning behind the outcome.
| S-EPMC9878123 | biostudies-literature
Project description:ObjectiveTo compare the incidence of, and mortality after, intensive care unit (ICU) admission as well as the characteristics of critical illness in the multiple sclerosis (MS) population vs the general population.MethodsWe used population-based administrative data from the Canadian province of Manitoba for the period 1984 to 2010 and clinical data from 93% of admissions to provincial high-intensity adult ICUs. We identified 5,035 prevalent cases of MS and a cohort from the general population matched 5:1 on age, sex, and region of residence. We compared these populations using incidence rates and multivariable regression models adjusting for age, sex, comorbidity, and socioeconomic status.ResultsFrom January 2000 to October 2009, the age- and sex-standardized annual incidence of ICU admission among prevalent cohorts was 0.51% to 1.07% in the MS population and 0.34% to 0.51% in matched controls. The adjusted risk of ICU admission was higher for the MS population (hazard ratio 1.45; 95% confidence interval [CI] 1.19-1.75) than for matched controls. The MS population was more likely to be admitted for infection than the matched controls (odds ratio 1.82; 95% CI 1.10-1.32). Compared with the matched controls admitted to ICUs, 1-year mortality was higher in the MS population (relative risk 2.06; 95% CI 1.32-3.07) and was particularly elevated in patients with MS who were younger than 40 years (relative risk 3.77; 95% CI 1.45-8.11). Causes of death were MS (9.3%), infections (37.0%), and other causes (52.9%).ConclusionsCompared with the general population, the risk of ICU admission is higher in MS, and 1-year mortality after admission is higher. Greater attention to preventing infection and managing comorbidity is needed in the MS population.
| S-EPMC4118502 | biostudies-literature