Acute Physiology and Chronic Health Evaluation (APACHE) IV: Hospital mortality assessment for today’s critically ill patients*

By Jack E. Zimmerman, Andrew A. Kramer, Douglas S. McNair, F. Malila. 2006

1,695 citations recorded by the source corpus.

Subfields: Cardiology and Cardiovascular Medicine, Epidemiology, Surgery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Epidemiology

In Surgery

Citations in the corpus

AutoScore: A Machine Learning–Based Automatic Clinical Score Generator and Its Application to Mortality Prediction Using Electronic Health Records (2020, methodology): “…have previously created several scoring models for predicting mortality, such as the Modified Early Warning Score [46], the VitalPAC Early Warning Score [47], and the Acute Physiology And Chronic Health Evaluation [48], mainly utilizing vital signs to predict mortality for hospitalized patients.”
Clinical review: Scoring systems in the critically ill (2010, methodology): “Most recently, APACHE IV was developed using a database of over 100,000 patients admitted to 104 ICUs in 45 hospitals in the USA in 2002/2003, and remodeling APACHE III with the same physiological variables and weights but diff erent predictor variables and refi ned statistical methods [8].”
Hydrocortisone, Vitamin C, and Thiamine for the Treatment of Severe Sepsis and Septic Shock: A Retrospective Before‐After Study (2017, methodology): “The APACHE II score (incrementing score of 0 to 71) and APACHE IV score (incrementing score of 0 to 286) are standardized measures of disease severity that are used to predict hospital mortality.(39,40) The SOFA (Sepsis-Related Organ Failure Assessment) score was calculated daily for 4 days.”
Assessing the calibration of mortality benchmarks in critical care: The Hosmer-Lemeshow test revisited* (2007, methodology): “The intercept ( 0) was set equal to 4.60 so that the mean probability of mortality was 14%, which is the recently reported mortality probability for patients admitted to ICUs in the United States (2, 3).”
The Sequential Organ Failure Assessment score for predicting outcome in patients with severe sepsis and evidence of hypoperfusion at the time of emergency department presentation (2009, methodology): “T0, time zero; T72, time 72 hr after admission; SOFA, sequential organ failure assessment; CNS, central nervous system; SBP, systolic blood pressure; RR, respiratory rate; CVP, central venous pressure; ScvO2, central venous oxygen saturation; SaO2, peripheral arterial oxygen saturation; GCS, Glasgow”
Multitask learning and benchmarking with clinical time series data (2017, background): “Such problems are not new,1 but the increased availability of digital clinical data and recent high-pro le machine learning successes [20, 57] have sparked a renewed interest in them.”
Machine Learning and Decision Support in Critical Care (2016, methodology): “Shah et al. [101] used an iterative approach incorporating singular value decomposition to impute missing data under the assumption that data were MAR. Waljee et al. [102] compared missing value imputation methods and demonstrated that a RF based missing value imputation method performs best in thei”
Dynamic data during hypotensive episode improves mortality predictions among patients with sepsis and hypotension (2013, methodology): “The baseline predicted mortality was obtained with APACHE-IV (1) in the test set.”
Calibrating predictive model estimates to support personalized medicine (2011, methodology): “Like subgroups in the HL test, we have two choices for constructing these bins: (1) equal number of elements in the bins, sorted by probability estimates, that is, Pn=10R elements per cell; or (2) fixed, equal length intervals of probability estimates, that is, 0<p<1⁄40.”
Risk Stratification of ICU Patients Using Topic Models Inferred from Unstructured Progress Notes (2012, methodology): “Nursing notes (during the 1st 24 hrs of patient’s ICU stay) for 14,739 adult patients from the MIMIC II database were included in this study.”