Dataset Information

Using electronic health record collected clinical variables to predict medical intensive care unit mortality.

ABSTRACT: BACKGROUND:Clinical decision support systems are used to help predict patient stability and mortality in the Intensive Care Unit (ICU). Accurate patient information can assist clinicians with patient management and in allocating finite resources. However, systems currently in common use have limited predictive value in the clinical setting. The increasing availability of Electronic Health Records (EHR) provides an opportunity to use medical information for more accurate patient stability and mortality prediction in the ICU. OBJECTIVE:Develop and evaluate an algorithm which more accurately predicts patient mortality in the ICU, using the correlations between widely available clinical variables from the EHR. METHODS:We have developed an algorithm, AutoTriage, which uses eight common clinical variables from the EHR to assign patient mortality risk scores. Each clinical variable produces a subscore, and combinations of two or three discretized clinical variables also produce subscores. A combination of weighted subscores produces the overall score. We validated the performance of this algorithm in a retrospective study on the MIMIC III medical ICU dataset. RESULTS:AutoTriage 12 h mortality prediction yields an Area Under Receiver Operating Characteristic value of 0.88 (95% confidence interval 0.86 to 0.88). At a sensitivity of 80%, AutoTriage maintains a specificity of 81% with a diagnostic odds ratio of 16.26. CONCLUSIONS:Through the multidimensional analysis of the correlations between eight common clinical variables, AutoTriage provides an improvement in the specificity and sensitivity of patient mortality prediction over existing prediction methods.

SUBMITTER: Calvert J

PROVIDER: S-EPMC5037117 | biostudies-literature | 2016 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using electronic health record collected clinical variables to predict medical intensive care unit mortality.

Calvert Jacob J Mao Qingqing Q Hoffman Jana L JL Jay Melissa M Desautels Thomas T Mohamadlou Hamid H Chettipally Uli U Das Ritankar R

Annals of medicine and surgery (2012) 20160906

<h4>Background</h4>Clinical decision support systems are used to help predict patient stability and mortality in the Intensive Care Unit (ICU). Accurate patient information can assist clinicians with patient management and in allocating finite resources. However, systems currently in common use have limited predictive value in the clinical setting. The increasing availability of Electronic Health Records (EHR) provides an opportunity to use medical information for more accurate patient stability ...[more]

PMID: 27699003

Similar Datasets

Project description:RationalePatients transferred from the intensive care unit to the wards who are later readmitted to the intensive care unit have increased length of stay, healthcare expenditure, and mortality compared with those who are never readmitted. Improving risk stratification for patients transferred to the wards could have important benefits for critically ill hospitalized patients.ObjectivesWe aimed to use a machine-learning technique to derive and validate an intensive care unit readmission prediction model with variables available in the electronic health record in real time and compare it to previously published algorithms.MethodsThis observational cohort study was conducted at an academic hospital in the United States with approximately 600 inpatient beds. A total of 24,885 intensive care unit transfers to the wards were included, with 14,962 transfers (60%) in the training cohort and 9,923 transfers (40%) in the internal validation cohort. Patient characteristics, nursing assessments, International Classification of Diseases, Ninth Revision codes from prior admissions, medications, intensive care unit interventions, diagnostic tests, vital signs, and laboratory results were extracted from the electronic health record and used as predictor variables in a gradient-boosted machine model. Accuracy for predicting intensive care unit readmission was compared with the Stability and Workload Index for Transfer score and Modified Early Warning Score in the internal validation cohort and also externally using the Medical Information Mart for Intensive Care database (n = 42,303 intensive care unit transfers).ResultsEleven percent (2,834) of discharges to the wards were later readmitted to the intensive care unit. The machine-learning-derived model had significantly better performance (area under the receiver operating curve, 0.76) than either the Stability and Workload Index for Transfer score (area under the receiver operating curve, 0.65), or Modified Early Warning Score (area under the receiver operating curve, 0.58; P value < 0.0001 for all comparisons). At a specificity of 95%, the derived model had a sensitivity of 28% compared with 15% for Stability and Workload Index for Transfer score and 7% for the Modified Early Warning Score. Accuracy improvements with the derived model over Modified Early Warning Score and Stability and Workload Index for Transfer were similar in the Medical Information Mart for Intensive Care-III cohort.ConclusionsA machine learning approach to predicting intensive care unit readmission was significantly more accurate than previously published algorithms in both our internal validation and the Medical Information Mart for Intensive Care-III cohort. Implementation of this approach could target patients who may benefit from additional time in the intensive care unit or more frequent monitoring after transfer to the hospital ward.

Project description:Purpose: To determine whether inotrope administration is associated with increased all-cause mortality in cardiogenic shock (CS) patients and to identify inotropes superior for improving mortality. Methods: This retrospective cohort study analyzed data retrieved from the Philips Electronic ICU (eICU) database, a clinical database of 200,859 patients from over 208 hospitals located throughout the United States. The database was searched for patients admitted with CS to the intensive care unit (ICU) between 2014 and 2015. We evaluated 34,381 CS patients. They were classified into the inotrope and non-inotrope groups based on whether inotropes were administered during hospitalization. The primary endpoint was all-cause hospital mortality. Findings: In total, 15,021 (43.69%) patients received inotropes during hospitalization. The in-hospital mortality rate was significantly higher in the inotrope group than in the non-inotrope group (2,999 [24.03%] vs. 1,547 [12.40%], adjusted hazard ratio: 2.24; 95% confidence interval [CI]: 2.09-2.39; p < 0.0001). After propensity score matching according to the cardiac index, 359 patients were included in each group. The risk of ICU (OR 5.65, 95% CI, 3.17-10.08, p < 0.001) and hospital (OR 2.63, 95% CI: 1.75-3.95, p < 0.001) mortality in the inotrope group was significantly higher. In the inotrope group, the administration of norepinephrine ≤0.1 μg/kg/min and dopamine ≤15 μg/kg/min did not increase the risk of hospital mortality, and milrinone administration was associated with a lower mortality risk (odds ratio: 0.559, 95% CI: 0.430-0.727, p < 0.001). Meanwhile, the administration of >0.1 μg/kg/min dobutamine, epinephrine, and norepinephrine and dopamine >15 μg/kg/min was associated with a higher risk of hospital mortality. Conclusions: Inotropes should be used cautiously because they may be associated with a higher risk of mortality in CS patients. Low-dose norepinephrine and milrinone may associated with lower risk of hospital mortality in these patients, and supportive therapies should be considered when high-dose inotropes are administered.

Project description:PurposeThe final decision for discharge from the intensive care unit (ICU) is uncertain because it is made according to various patient parameters; however, it should be made on an objective evaluation. Previous reports have been inconsistent and unreliable in predicting post-ICU mortality. To identify predictive factors associated with post-ICU mortality, we analyzed physiological and laboratory data at ICU discharge.MethodsPatients admitted to our ICU between September 2012 and August 2013 and staying for critical care>2 days were included. Sequential Organ Failure Assessment (SOFA) score; systemic inflammatory response syndrome score; white blood cell count; and serum C reactive protein, procalcitonin (PCT), interleukin-6 (IL-6), lactate, albumin, and hemoglobin levels were recorded. The primary end point was 90-day mortality after ICU discharge. Two hundred eighteen patients were enrolled (195 survivors, 23 non-survivors).ResultsNon-survivors presented a higher SOFA score and serum PCT, and IL-6 levels, as well as lower serum albumin and hemoglobin levels. Serum PCT, albumin, and SOFA score were associated with 90-day mortality in multiple logistic regression analysis. Hosmer-Lemeshow test showed chi-square value of 6.96, and P value of 0.54. The area under the curve (95% confidence interval) was 0.830 (0.771-0.890) for PCT, 0.688 (0.566-0.810) for albumin, 0.861 (0.796-0.927) for SOFA score, and increased to 0.913 (0.858-0.969) when these were combined. Serum PCT level at 0.57 ng/mL, serum albumin at 2.5 g/dL and SOFA score at 5.5 predict 90-day mortality, and high PCT, low albumin and high SOFA groups had significantly higher mortality. Serum PCT and SOFA score were significantly associated with survival days after ICU discharge in Cox regression analysis.ConclusionsSerum PCT level and SOFA score at ICU discharge predict post-ICU mortality and survival days after ICU discharge. The combination of these two and albumin level might enable accurate prediction.

Project description:Background & aimsDespite advances in critical care medicine, the mortality rate is high among critically ill patients with cirrhosis. We aimed to identify factors that predict early (7 d) mortality among patients with cirrhosis admitted to the intensive care unit (ICU) and to develop a risk-stratification model.MethodsWe collected data from patients with cirrhosis admitted to the ICU at Indiana University (IU-ICU) from December 1, 2006, through December 31, 2009 (n = 185), or at the University of Pennsylvania (Penn-ICU) from May 1, 2005, through December 31, 2010 (n = 206). Factors associated with mortality within 7 days of admission (7-d mortality) were determined by logistic regression analyses. A model was constructed based on the predictive parameters available on the first day of ICU admission in the IU-ICU cohort and then validated in the Penn-ICU cohort.ResultsMedian Model for End-stage Liver Disease (MELD) scores at ICU admission were 25 in the IU-ICU cohort (interquartile range, 23-34) and 32 in the Penn-ICU cohort (interquartile range, 26-41); corresponding 7-day mortalities were 28.3% and 53.6%, respectively. MELD score (odds ratio, 1.13; 95% confidence interval [CI], 1.07-1.2) and mechanical ventilation (odds ratio, 5.7; 95% CI, 2.3-14.1) were associated independently with 7-day mortality in the IU-ICU. A model based on these 2 variables separated IU-ICU patients into low-, medium-, and high-risk groups; these groups had 7-day mortalities of 9%, 27%, and 74%, respectively (concordance index, 0.80; 95% CI, 0.72-0.87; P < 10(-8)). The model was applied to the Penn-ICU cohort; the low-, medium-, and high-risk groups had 7-day mortalities of 33%, 56%, and 71%, respectively (concordance index, 0.67; 95% CI, 0.59-0.74; P < 10(-4)).ConclusionsA model based on MELD score and mechanical ventilation on day 1 can stratify risk of early mortality in patients with cirrhosis admitted to the ICU. More studies are needed to validate this model and to enhance its clinical utility.

Dataset Information

Using electronic health record collected clinical variables to predict medical intensive care unit mortality.

Publications

Using electronic health record collected clinical variables to predict medical intensive care unit mortality.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets