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.
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.
Project description:Coronavirus disease 2019 (COVID-19) can lead to multiorgan damage and fatal outcomes. MicroRNAs (miRNAs) are detectable in blood, reflecting cell activation and tissue injury. We performed small RNA-Seq in healthy controls (N=11), non-severe (N=18) and severe (N=16) COVID-19 patients
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.
Project description:BackgroundRecent interest in the 'weekend effect' has been expanded to cardiovascular intensive care units, yet the impact of off-hours admission on mortality and cardiovascular ICU (CICU) length of stay remains uncertain.ObjectivesWe examine the association between CICU admission day and time with mortality. Additionally, length-of-stay was also evaluated in relation to admission time.MethodsA single-center, retrospective cohort study was conducted including 10,638 adult patients admitted to a CICU in a tertiary-care academic medical center from July 1, 2012 to June 30, 2019. ICU mortality and length-of-stay were assessed by admission day and time adjusting for comorbid conditions and other clinical variables. We used logistic regression models to evaluate the factors associated with mortality and a generalized linear model (GLM) with log link function and gamma distribution was used to evaluate the factors associated with ICU length of stay.ResultsCompared to weekday-day admissions, we observed an increased mortality for weekend-day for all admissions (6.5 vs 9.6%, Adjusted OR: 1.32 (1.03-1.72)), and for medical CICU admissions (7.6 vs 9.9%, Adjusted OR: 1.35 (1.02-1.79)). Additionally, compared to weekday-day, weekday-night admission was associated with 7% longer ICU length of stay in surgical ICU patients, 7% shorter length of stay in medical ICU patients.ConclusionAdmission to this open-model CICU during weekend hours (Saturday 08:00-Sunday 17:59) versus nights or weekdays is associated with increased mortality. ICU staffing care models should not significantly change based on the day of the week.
Project description:BackgroundEffectively identifying deteriorated patients is vital to the development and validation of automated systems designed to predict clinical deterioration. Existing outcome measures used for this purpose have significant limitations. Published criteria for admission to high acuity inpatient areas may represent markers of patient deterioration and could inform the development of alternate outcome measures.ObjectivesIn this scoping review, we aimed to characterise published criteria for admission of adult inpatients to high acuity inpatient areas including intensive care units. A secondary aim was to identify variables that are extractable from electronic health records (EHRs).Data sourcesElectronic databases PubMed and ProQuest EBook Central were searched to identify papers published from 1999 to date of search. We included publications which described prescriptive criteria for admission of adult inpatients to a clinical area with a higher level of care than a general hospital ward.Charting methodsData was extracted from each publication using a standardised data-charting form. Admission criteria characteristics were summarised and cross-tabulated for each criterion by population group.ResultsFive domains were identified: diagnosis-based criteria, clinical parameter criteria, organ-support criteria, organ-monitoring criteria and patient baseline criteria. Six clinical parameter-based criteria and five needs-based criteria were frequently proposed and represent variables extractable from EHRs. Thresholds for objective clinical parameter criteria varied across publications, and by disease subgroup, and universal cut-offs for criteria could not be elucidated.ConclusionsThis study identified multiple criteria which may represent markers of deterioration. Many of the criteria are extractable from the EHR, making them potential candidates for future automated systems. Variability in admission criteria and associated thresholds across the literature suggests clinical deterioration is a heterogeneous phenomenon which may resist being defined as a single entity via a consensus-driven process.
Project description:Background There are no risk scores designed specifically for mortality risk prediction in unselected cardiac intensive care unit (CICU) patients. We sought to develop a novel CICU-specific risk score for prediction of hospital mortality using variables available at the time of CICU admission. Methods and Results A database of CICU patients admitted from January 1, 2007 to April 30, 2018 was divided into derivation and validation cohorts. The top 7 predictors of hospital mortality were identified using stepwise backward regression, then used to develop the Mayo CICU Admission Risk Score (M-CARS), with integer scores ranging from 0 to 10. Discrimination was assessed using area under the receiver-operator curve analysis. Calibration was assessed using the Hosmer-Lemeshow statistic. The derivation cohort included 10 004 patients and the validation cohort included 2634 patients (mean age 67.6 years, 37.7% females). Hospital mortality was 9.2%. Predictor variables included in the M-CARS were cardiac arrest, shock, respiratory failure, Braden skin score, blood urea nitrogen, anion gap and red blood cell distribution width at the time of CICU admission. The M-CARS showed a graded relationship with hospital mortality (odds ratio 1.84 for each 1-point increase in M-CARS, 95% CI 1.78-1.89). In the validation cohort, the M-CARS had an area under the receiver-operator curve of 0.86 for hospital mortality, with good calibration (P=0.21). The 47.1% of patients with M-CARS <2 had hospital mortality of 0.8%, and the 5.2% of patients with M-CARS >6 had hospital mortality of 51.6%. Conclusions Using 7 variables available at the time of CICU admission, the M-CARS can predict hospital mortality in unselected CICU patients with excellent discrimination.
Project description:ObjectiveTo compare the performance of machine learning models against the traditionally derived Combined Assessment of Risk Encountered in Surgery (CARES) model and the American Society of Anaesthesiologists-Physical Status (ASA-PS) in the prediction of 30-day postsurgical mortality and need for intensive care unit (ICU) stay >24 hours.BackgroundPrediction of surgical risk preoperatively is important for clinical shared decision-making and planning of health resources such as ICU beds. The current growth of electronic medical records coupled with machine learning presents an opportunity to improve the performance of established risk models.MethodsAll patients aged 18 years and above who underwent noncardiac and nonneurological surgery at Singapore General Hospital (SGH) between 1 January 2012 and 31 October 2016 were included. Patient demographics, comorbidities, preoperative laboratory results, and surgery details were obtained from their electronic medical records. Seventy percent of the observations were randomly selected for training, leaving 30% for testing. Baseline models were CARES and ASA-PS. Candidate models were trained using random forest, adaptive boosting, gradient boosting, and support vector machine. Models were evaluated on area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC).ResultsA total of 90,785 patients were included, of whom 539 (0.6%) died within 30 days and 1264 (1.4%) required ICU admission >24 hours postoperatively. Baseline models achieved high AUROCs despite poor sensitivities by predicting all negative in a predominantly negative dataset. Gradient boosting was the best performing model with AUPRCs of 0.23 and 0.38 for mortality and ICU admission outcomes respectively.ConclusionsMachine learning can be used to improve surgical risk prediction compared to traditional risk calculators. AUPRC should be used to evaluate model predictive performance instead of AUROC when the dataset is imbalanced.