Dataset Information

Early identification of patients at risk of acute lung injury: evaluation of lung injury prediction score in a multicenter cohort study.

ABSTRACT: Accurate, early identification of patients at risk for developing acute lung injury (ALI) provides the opportunity to test and implement secondary prevention strategies.To determine the frequency and outcome of ALI development in patients at risk and validate a lung injury prediction score (LIPS).In this prospective multicenter observational cohort study, predisposing conditions and risk modifiers predictive of ALI development were identified from routine clinical data available during initial evaluation. The discrimination of the model was assessed with area under receiver operating curve (AUC). The risk of death from ALI was determined after adjustment for severity of illness and predisposing conditions.Twenty-two hospitals enrolled 5,584 patients at risk. ALI developed a median of 2 (interquartile range 1-4) days after initial evaluation in 377 (6.8%; 148 ALI-only, 229 adult respiratory distress syndrome) patients. The frequency of ALI varied according to predisposing conditions (from 3% in pancreatitis to 26% after smoke inhalation). LIPS discriminated patients who developed ALI from those who did not with an AUC of 0.80 (95% confidence interval, 0.78-0.82). When adjusted for severity of illness and predisposing conditions, development of ALI increased the risk of in-hospital death (odds ratio, 4.1; 95% confidence interval, 2.9-5.7).ALI occurrence varies according to predisposing conditions and carries an independently poor prognosis. Using routinely available clinical data, LIPS identifies patients at high risk for ALI early in the course of their illness. This model will alert clinicians about the risk of ALI and facilitate testing and implementation of ALI prevention strategies. Clinical trial registered with www.clinicaltrials.gov (NCT00889772).

SUBMITTER: Gajic O

PROVIDER: S-EPMC3056224 | biostudies-literature | 2011 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Early identification of patients at risk of acute lung injury: evaluation of lung injury prediction score in a multicenter cohort study.

Gajic Ognjen O Dabbagh Ousama O Park Pauline K PK Adesanya Adebola A Chang Steven Y SY Hou Peter P Anderson Harry H Hoth J Jason JJ Mikkelsen Mark E ME Gentile Nina T NT Gong Michelle N MN Talmor Daniel D Bajwa Ednan E Watkins Timothy R TR Festic Emir E Yilmaz Murat M Iscimen Remzi R Kaufman David A DA Esper Annette M AM Sadikot Ruxana R Douglas Ivor I Sevransky Jonathan J Malinchoc Michael M

American journal of respiratory and critical care medicine 20100827 4

<h4>Rationale</h4>Accurate, early identification of patients at risk for developing acute lung injury (ALI) provides the opportunity to test and implement secondary prevention strategies.<h4>Objectives</h4>To determine the frequency and outcome of ALI development in patients at risk and validate a lung injury prediction score (LIPS).<h4>Methods</h4>In this prospective multicenter observational cohort study, predisposing conditions and risk modifiers predictive of ALI development were identified ...[more]

PMID: 20802164

Similar Datasets

Project description:Background:Early recognition of the risks of acute respiratory distress syndrome (ARDS) and prevention of the development of ARDS may be more effective in improving patient outcomes. We performed the present study to determine the ARDS risk factors in a Chinese population and validate a score to predict the development of ARDS. Methods:This was an observational multicenter cohort study performed in 13 tertiary hospitals in China. Patients admitted into participating intensive care units (ICUs) from January 1 to January 31, 2012, and from January 1 to January 10, 2013, were enrolled in a retrospective derivation cohort and a prospective validation cohort, respectively. In the derivation cohort, the potential risk factors of ARDS were collected. The confirmed risk factors were determined with univariate and multivariate logistic regression analyses, and then the modified ARDS prediction score (MAPS) was established. We prospectively enrolled patients to verify the accuracy of MAPS. Results:A total of 479 and 198 patients were enrolled into the retrospective derivation cohort and the prospective validation cohort, respectively. A total of 93 (19.4%) patients developed ARDS in the derivation cohort. Acute pancreatitis, pneumonia, hypoalbuminemia, acidosis, and high respiratory rate were the risk factors for ARDS. The MAPS discriminated patients who developed ARDS from those who did not, with an area under the curve (AUC) of 0.809 [95% confidence interval (CI), 0.758-0.859, P<0.001]. In the prospective validation cohort, performance of the MAPS was similar to the retrospective derivation cohort, with an AUC of 0.792 (95% CI, 0.717-0.867, P<0.001). The lung injury prediction score (LIPS) showed a predicted value of an AUC of 0.770 (95% CI, 0.728-0.812, P<0.001) in our patients, which was significantly lower than our score (P<0.046). Conclusions:The MAPS based on risk factors could help the clinician to predict patients who will develop ARDS. Trial registration:ClinicalTrials.gov NCT01666834.

Project description:ObjectiveThe Lung Injury Prediction Score identifies patients at risk for acute respiratory distress syndrome in the emergency department, but it has not been validated in non-emergency department hospitalized patients. We aimed to evaluate whether Lung Injury Prediction Score identifies non-emergency department hospitalized patients at risk of developing acute respiratory distress syndrome at the time of critical care contact.DesignRetrospective study.SettingFive academic medical centers.PatientsNine hundred consecutive patients (≥ 18 yr old) with at least one acute respiratory distress syndrome risk factor at the time of critical care contact.InterventionsNone.Measurements and main resultsLung Injury Prediction Score was calculated using the worst values within the 12 hours before initial critical care contact. Patients with acute respiratory distress syndrome at the time of initial contact were excluded. Acute respiratory distress syndrome developed in 124 patients (13.7%) a median of 2 days (interquartile range, 2-3) after critical care contact. Hospital mortality was 22% and was significantly higher in acute respiratory distress syndrome than non-acute respiratory distress syndrome patients (48% vs 18%; p < 0.001). Increasing Lung Injury Prediction Score was significantly associated with development of acute respiratory distress syndrome (odds ratio, 1.31; 95% CI, 1.21-1.42) and the composite outcome of acute respiratory distress syndrome or death (odds ratio, 1.26; 95% CI, 1.18-1.34). A Lung Injury Prediction Score greater than or equal to 4 was associated with the development of acute respiratory distress syndrome (odds ratio, 4.17; 95% CI, 2.26-7.72), composite outcome of acute respiratory distress syndrome or death (odds ratio, 2.43; 95% CI, 1.68-3.49), and acute respiratory distress syndrome after accounting for the competing risk of death (hazard ratio, 3.71; 95% CI, 2.05-6.72). For acute respiratory distress syndrome development, the Lung Injury Prediction Score has an area under the receiver operating characteristic curve of 0.70 and a Lung Injury Prediction Score greater than or equal to 4 has 90% sensitivity (misses only 10% of acute respiratory distress syndrome cases), 31% specificity, 17% positive predictive value, and 95% negative predictive value.ConclusionsIn a cohort of non-emergency department hospitalized patients, the Lung Injury Prediction Score and Lung Injury Prediction Score greater than or equal to 4 can identify patients at increased risk of acute respiratory distress syndrome and/or death at the time of critical care contact but it does not perform as well as in the original emergency department cohort.

Project description:BACKGROUND:There has been a global increase in the incidence of acute kidney injury (AKI), including among critically-ill surgical patients. AKI prediction score provides an opportunity for early detection of patients who are at risk of AKI; however, most of the AKI prediction scores were derived from cardiothoracic surgery. Therefore, we aimed to develop an AKI prediction score for major non-cardiothoracic surgery patients who were admitted to the intensive care unit (ICU). METHODS:The data of critically-ill patients from non-cardiothoracic operations in the Thai Surgical Intensive Care Unit (THAI-SICU) study were used to develop an AKI prediction score. Independent prognostic factors from regression analysis were included as predictors in the model. The outcome of interest was AKI within 7?days after the ICU admission. The AKI diagnosis was made according to the Kidney Disease Improving Global Outcomes (KDIGO)-2012 serum creatinine criteria. Diagnostic function of the model was determined by area under the Receiver Operating Curve (AuROC). Risk scores were categorized into four risk probability levels: low (0-2.5), moderate (3.0-8.5), high (9.0-11.5), and very high (12.0-16.5) risk. Risk of AKI was presented as likelihood ratios of positive (LH+). RESULTS:A total of 3474 critically-ill surgical patients were included in the model; 333 (9.6%) developed AKI. Using multivariable logistic regression analysis, older age, high Sequential Organ Failure Assessment (SOFA) non-renal score, emergency surgery, large volume of perioperative blood loss, less urine output, and sepsis were identified as independent predictors for AKI. Then AKI prediction score was created from these predictors. The summation of the score was 16.5 and had a discriminative ability for predicting AKI at AuROC?=?0.839 (95% CI 0.825-0.852). LH+ for AKI were: low risk?=?0.117 (0.063-0.200); moderate risk?=?0.927 (0.745-1.148); high risk?=?5.190 (3.881-6.910); and very high risk?=?9.892 (6.230-15.695), respectively. CONCLUSIONS:The function of AKI prediction score to predict AKI among critically ill patients who underwent non-cardiothoracic surgery was good. It can aid in early recognition of critically-ill surgical patients who are at risk from ICU admission. The scores could guide decision making for aggressive strategies to prevent AKI during the perioperative period or at ICU admission. TRIAL REGISTRATION:TCTR20190408004, registered on April 4, 2019.

Project description:BackgroundAcute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated machine learning (AutoML) algorithms for the early prediction of AKI in patients with AP.MethodsWe retrospectively analyzed patients who were diagnosed with AP in our hospital from January 2017 to December 2021. These patients were randomly allocated into a training set and a validation set at a ratio of 7:3. To develop predictive models for each set, we employed the least absolute shrinkage and selection operator (LASSO) algorithm along with AutoML. A nomogram was developed based on multivariate logistic regression analysis outcomes. The model's efficacy was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the performance of the model constructed via AutoML was evaluated using decision curve analysis (DCA), feature importance, SHapley Additive exPlanations (SHAP) plots, and locally interpretable model-agnostic explanations (LIME).ResultsThis study incorporated a total of 437 patients who met the inclusion criteria. Out of these, 313 were assigned to the training cohort and 124 to the validation cohort. In the training and validation cohorts, AKI occurred in 68 (21.7%) and 29(23.4%) patients, respectively. Comparative analysis revealed that the AutoML models exhibited enhanced performance over traditional logistic regression (LR). Furthermore, the deep learning (DL) model demonstrated superior predictive accuracy, evidenced by an area under the ROC curve of 0.963 in the training set and 0.830 in the validation set, surpassing other comparative models. The key variables identified as significant in the DL model within the training dataset included creatinine (Cr), urea (Urea), international normalized ratio (INR), etiology, smoking, alanine aminotransferase (ALT), hypertension, prothrombin time (PT), lactate dehydrogenase (LDH), and diabetes.ConclusionThe AutoML model, utilizing DL algorithm, offers considerable clinical significance in the early detection of AKI among patients with AP.

Project description:Acute kidney injury occurs early in PICU admission and increases risks for poor outcomes. We evaluated the feasibility of a multicenter acute kidney injury biomarker urine collection protocol and measured diagnostic characteristics of urine neutrophil gelatinase-associated lipocalin, interleukin-18, and liver fatty acid binding protein to predict acute kidney injury and prolonged acute kidney injury.Prospective observational pilot cohort study.Four Canadian tertiary healthcare PICUs.Eighty-one children 1 month to 18 years old. Exclusion criteria were as follows: cardiac surgery, baseline severe kidney disease, and inadequate urine or serum for PICU days 1-3.PICUs performed standardized urine collection protocol to obtain early PICU admission urine samples, with deferred consent.Study barriers and facilitators were recorded. Acute kidney injury was defined based on Kidney Disease: Improving Global Outcomes serum creatinine criteria (acute kidney injuryserum creatinine) and by serum creatinine and urine output criteria (acute kidney injuryserum creatinine+urine output) Prolonged acute kidney injury was defined as acute kidney injury duration of 48 hours or more. PICU days 1-3 neutrophil gelatinase-associated lipocalin, interleukin-18, and liver fatty acid binding protein were evaluated for acute kidney injury prediction (area under the curve). Biomarkers on the first day of acute kidney injury attainment (day 1 acute kidney injury) were evaluated for predicting prolonged acute kidney injury. Eighty-two to 95% of subjects had urine collected from PICU days 1-3. Acute kidney injuryserum creatinine developed in 16 subjects (20%); acute kidney injuryserum creatinine+urine output developed in 38 (47%). On PICU day 1, interleukin-18 predicted acute kidney injuryserum creatinine with area under the curve=0.82, but neutrophil gelatinase-associated lipocalin and liver fatty acid binding protein predicted acute kidney injuryserum creatinine with area under the curve of less than or equal to 0.69; on PICU day 2, area under the curve was higher (not shown). Interleukin-18 and liver fatty acid binding protein on day 1 acute kidney injury predicted prolonged acute kidney injuryserum creatinine (area under the curve=0.74 and 0.83, respectively). When acute kidney injuryserum creatinine+urine output was used to define acute kidney injury, biomarker area under the curves were globally lower.Protocol urine collection to procure early admission samples is feasible. Individual biomarker acute kidney injury prediction performance is highly variable and modest. Larger studies should evaluate utility and cost effectiveness of using early acute kidney injury biomarkers.

Dataset Information

Early identification of patients at risk of acute lung injury: evaluation of lung injury prediction score in a multicenter cohort study.

Publications

Early identification of patients at risk of acute lung injury: evaluation of lung injury prediction score in a multicenter cohort study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets