AI systems in clinical practice

Quality assurance and administration systems, Decision support systems
Acute Physiology And Chronic Health Evaluation
Prognostic scoring system for intensive care units

developed by clinical domains keywords
William A. Knaus, an intensive-care physician at George Washington University, and colleagues. Intensive Care Units, critical care Expert systems, risk assesement, risk adjustment, prognostic scoring systems, database of critical care data, prognosis, prediction, quality assurance, decision support
location commissioned status
Sites have included Catherine McAuley Health System, Ann Arbor, Michigan; Beaumont Hospital, Royal Oak, Michigan; Ford Hospital, Detroit, Michigan. Case Study reports are available from Cerner Corp. on Sarasota Memorial Hospital and St. Mary's Medical Center, Evansville, IN. APACHE I was developed in 1981; APACHE II was introduced in 1985 and APACHE III in 1991. APACHE III proprietary database and decision support system were originally distributed by Apache Medical Systems (McLean, VA), before being bought in 2001 by Cerner Corporation where the system is now marketed as Cerner APACHE III
APACHE was one of the first medical decision support systems to be commercialised - in 1988 by a company founded specifically to carry this out: Apache Medical Systems Inc.

The APACHE III system was designed to predict an individual's risk of dying in a hospital. It compares each individual's medical profile against nearly 18,000 cases in its memory before reaching a prognosis that is, on average, 95 percent accurate. APACHE III is in use at many hospitals in the U.S. There have been at least 40 hospitals worldwide where the APACHE III Methodology is being or has been used to generate reports which compare their actual average ICU outcomes to ones predicted by APACHE III.

The APACHE I system was developed by William A. Knaus, an intensive-care physician at George Washington University Hospital, Washington DC, and colleagues from 1978 on. They began collecting and computerizing the experience of intensive care patients from dozens of hospitals. The computer considered each patient as a complicated sum of several variables: diagnosis and physiological abnormalities on admission to the ICU, age, pre-existing medical problems, etc. The system was designed as a way to judge how the hospitals were doing in terms of the mortality rate of its patients.

A physician can give the computer system 27 easily obtained facts, and the program predicts that patient's risk of dying in the hospital. The system is also useful in answering the question: is treatment making a difference? Studies have shown that about half the deaths in American Intensive Care Units now occur after a deliberate decision has been made to stop "heroic" measures. While APACHE does not make such decisions, its advocates say it helps those who must make them ponder the issues in the fairest and most realistic way.

W.A. Knaus. APACHE 19782001: The development of a quality assurance system based on prognosis: Milestones and personal reflections. Arch Surg 137 (2002), pp. 3741.

[PubMed]   []
" The development of APACHE (Acute Physiology and Chronic Health Evaluation) began on a Saturday in late June 1978 when I walked into the intensive care unit (ICU) of George Washington University Hospital in Washington, DC. I had come to Washington in 1972 and, with the exception of a year spent working in the former Soviet Union, had completed all of my internal medicine and critical care training in DC. This Saturday morning, however, was unique. It was my first as an attending physician, the last day of fellowship training being the previous day. The ICU was very busy but the charge nurse immediately directed me to one bedside, that of a young woman in severe septic shock following a major surgical procedure. Her room was crowded with house staff and nurses, all frantically attempting to resuscitate and reverse her circulatory collapse... "
Wong DT, Knaus WA. Predicting outcome in critical care: the current status of the APACHE prognostic scoring system. Can J Anaesth. 1991 Apr;38(3):374-83.

[PubMed]   [Can J Anaesth.]
" The APACHE (Acute Physiology and Chronic Health Evaluation) prognostic scoring system was developed in 1981 at the George Washington University Medical Center as a way to measure disease severity. APACHE II, introduced in 1985, was a simplified modification of the original APACHE. The APACHE II score consisted of three parts: 12 acute physiological variables, age and chronic health status. Probability of death can be derived by using the disease category and the APACHE II score. The uses of APACHE II include risk stratification to account for case mix in clinical studies, comparison of the quality of care among ICUs, and assessment of group and individual prognoses. APACHE III, a refinement of APACHE II, will be introduced in late 1990. The APACHE III data base includes 17,457 patients from a representative sample of 40 American hospitals. Additional potential uses of APACHE III include the identification of factors in the ICU which contribute to outcome and assistance in individual patient decision-making. This article reviews the development, current uses and potential applications of the APACHE system. "

Zimmerman JE, Wagner DP, Draper EA et al. Evaluation of acute physiology and chronic health evaluation III predictions of hospital mortality in an independent database. Crit Care Med. 1998 Aug;26(8):1317-26.

[PubMed]   []

" OBJECTIVE: To assess the accuracy and validity of Acute Physiology and Chronic Health Evaluation (APACHE) III hospital mortality predictions in an independent sample of U.S. intensive care unit (ICU) admissions. DESIGN: Nonrandomized, observational, cohort study. SETTING: Two hundred eighty-five ICUs in 161 U.S. hospitals, including 65 members of the Council of Teaching Hospitals and 64 nonteaching hospitals. PATIENTS: A consecutive sample of 37,668 ICU admissions during 1993 to 1996; including 25,448 admissions at hospitals with >400 beds and 1,074 admissions at hospitals with less than 200 beds. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We used demographic, clinical, and physiologic information recorded during ICU day 1 and the APACHE III equation to predict the probability of hospital mortality for each patient. We compared observed and predicted mortality for all admissions and across patient subgroups and assessed predictive accuracy using tests of discrimination and calibration. ... CONCLUSIONS: APACHE III accurately predicted aggregate hospital mortality in an independent sample of U.S. ICU admissions. Further improvements in calibration can be achieved by more precise disease labeling, improved acquisition and weighting of neurologic abnormalities, adjustments that reflect changes in treatment outcomes over time, and a larger national database. "

contact links

W.A. Knaus
Department of Health Evaluation Sciences
University of Virginia School of Medicine
Box 800717
Charlottesville, VA 22908, USA

 bullet  Cerner APACHE III

Archive of AI systems in clinical practice previously administered by Enrico Coiera. Used with permission. Maintained and extended since 2001 by OpenClinical.

Entry on archive: November 27 1995
Last main updates: January 25 2005, March 03 2005
Search this site


Privacy policy User agreement Copyright Feedback

Last modified:
© Copyright OpenClinical 2002-2011