Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*

Saeed, Mohammed; Villarroel, Mauricio; Reisner, Andrew; Clifford, Gari D.; Lehman, Li Wei H.; Moody, G.B.; Heldt, Thomas; Kyaw, Tin Htet; Moody, Benjamin; Mark, Roger G.

doi:10.1097/ccm.0b013e31820a92c6

Cited by 923 publications

(567 citation statements)

References 20 publications

Supporting

Mentioning

552

Contrasting

Unclassified

Order By: Relevance

“…We hypothesized that propofol use could be associated with a decrease in the incidence and severity of AKI in critically ill patients. (12). The database is freely available, so that any researcher who accepts the data use agreement and has attended "protecting human subjects training" can apply for permission to access the data.…”

Section: Introductionmentioning

confidence: 99%

Renal Outcomes in Critically Ill Patients Receiving Propofol or Midazolam

Leite

Macedo

Martins

et al. 2015

Clinical Journal of the American Society of Nephrology

View full text Add to dashboard Cite

Background and objectives Propofol has been shown to provide protection against renal ischemia/reperfusion injury experimentally, but clinical evidence is limited to patients undergoing cardiac surgery. There are no data about its association with oliguria and AKI in critically ill patients.Design, setting, participants, & measurements We obtained data from the Multiparameter Intelligent Monitoring in Intensive Care II database (2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008). Patient selection criteria included adult patients in their first intensive care unit (ICU) admission, need for mechanical ventilation, and treatment with propofol or midazolam. Propensity score analysis (1:1) was used and renal-related outcomes (AKI, oliguria, cumulative fluid balance, and need for RRT) were evaluated during the first 7 days of ICU stay.Results There were 1396 propofol/midazolam-matched patients. AKI in the first 7-day ICU time period was statistically lower in propofol-treated patients compared with midazolam-treated patients (55.0% versus 67.3%, P,0.001). Propofol was associated with lower AKI incidence using both urine output (45.0% versus 55.7%, P,0.001) and serum creatinine criteria (28.8% versus 37.2%, P=0.001). Patients receiving propofol had oliguria (,400 ml/d) less frequently (12.4% versus 19.6%, P=0.001) and had diuretics prescribed less often (8.5% versus 14.3%, P=0.001). In addition, during the first 7 days of ICU stay, patients receiving propofol less frequently achieved cumulative fluid balance .5% of body weight (50.1% versus 58.3%, P=0.01). The need for RRT in the first 7 days of ICU stay was also less frequent in propofol-treated patients (3.4% versus 5.9%, P=0.03). ICU mortality was lower in propofol-treated patients (14.6% versus 29.7%, P,0.001). ConclusionsIn this large, propensity-matched ICU population, patients treated with propofol had a lower risk of AKI, fluid-related complications, and need for RRT.

show abstract

Section: Introductionmentioning

confidence: 99%

Renal Outcomes in Critically Ill Patients Receiving Propofol or Midazolam

Leite

Macedo

Martins

et al. 2015

Clinical Journal of the American Society of Nephrology

View full text Add to dashboard Cite

show abstract

“…In this paper, we aim to make such a comparison using the MIMIC-II dataset [7] to predict mortality among ICU patients by using their EMR data between ICU intake and discharge. We re-implement the approach developed in [4] for the predictive modeling category and make it available as a benchmark.…”

Section: Introductionmentioning

confidence: 99%

Prediction using patient comparison vs. modeling: A case study for mortality prediction

Hoogendoorn

Hassouni²,

Mok³

et al. 2016

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Abstract-Information in Electronic Medical Records (EMRs) can be used to generate accurate predictions for the occurrence of a variety of health states, which can contribute to more pro-active interventions. The very nature of EMRs does make the application of off-the-shelf machine learning techniques difficult. In this paper, we study two approaches to making predictions that have hardly been compared in the past: (1) extracting high-level (temporal) features from EMRs and building a predictive model, and (2) defining a patient similarity metric and predicting based on the outcome observed for similar patients. We analyze and compare both approaches on the MIMIC-II ICU dataset to predict patient mortality and find that the patient similarity approach does not scale well and results in a less accurate model (AUC of 0.68) compared to the modeling approach (0.84). We also show that mortality can be predicted within a median of 72 hours.

show abstract

“…The MIMIC-II study [22][23][24] includes all patients admitted to an ICU at the Beth Israel Deaconess Medical Center (BIDMC) in Boston, MA since 2001. For the sake of the present study, only data from MIMIC-II version 26 (2001-2008) on adult ICU patients were included.…”

Section: Data Collection and Patients Characteristicsmentioning

confidence: 99%

“…The primary aim of this study was to develop a scoring procedure for ICU patients based on the Super Learner using data from the Medical Information Mart for Intensive Care II (MIMIC-II) study [22][23][24], and to determine whether it results in improved mortality prediction relative to the SAPS II, the APACHE II and the SOFA scores. Complete results of this study have been published in 2015 in the Lancet Respiratory Medicine [25].…”

Section: Introductionmentioning

confidence: 99%

Mortality Prediction in the ICU Based on MIMIC-II Results from the Super ICU Learner Algorithm (SICULA) Project

Pirracchio

2016

Secondary Analysis of Electronic Health Records

View full text Add to dashboard Cite

Learning ObjectivesIn this chapter, we illustrate the use of MIMIC II clinical data, non-parametric prediction algorithm, ensemble machine learning, and the Super Learner algorithm. IntroductionPredicting mortality in patients hospitalized in intensive care units (ICU) is crucial for assessing severity of illness and adjudicating the value of novel treatments, interventions and health care policies. Several severity scores have been developed with the objective of predicting hospital mortality from baseline patient characteristics, defined as measurements obtained within the first 24 h after ICU admission. The first scores proposed, APACHE [1] (Acute Physiology and Chronic Health Evaluation), APACHE II [2], and SAPS [3] (Simplified Acute Physiology Score), relied upon subjective methods for variable importance measure, namely by prompting a panel of experts to select and assign weights to variables according to perceived relevance for mortality prediction. Further scores, such as the SAPS II [4] were subsequently developed using statistical modeling techniques [4][5][6][7]. To this day, the SAPS II [4] and APACHE II [2] scores remain the most widely used in clinical practice. However, since first being published, they have been modified several times in order to improve their predictive performance [6][7][8][9][10][11]. Despite these extensions of SAPS, predicted hospital mortality remains generally overestimated [8,9,[12][13][14]. As an illustration, Poole et al. [9] compared the SAPS II and the SAPS3 performance in a cohort of more than 28,000 admissions to 10 different Italian ICUs. They concluded that both scores provided unreliable predictions, but unexpectedly the newer SAPS 3 turned out to overpredict mortality more than the

show abstract

Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*

Cited by 923 publications

References 20 publications

Renal Outcomes in Critically Ill Patients Receiving Propofol or Midazolam

Renal Outcomes in Critically Ill Patients Receiving Propofol or Midazolam

Prediction using patient comparison vs. modeling: A case study for mortality prediction

Mortality Prediction in the ICU Based on MIMIC-II Results from the Super ICU Learner Algorithm (SICULA) Project

Contact Info

Product

Resources

About