The APACHE III (Acute Physiology and Chronic Health Evaluation) system was designed to provide objective estimates of severity of illness and to use this information to predict an individual's mortality risk, length of stay in the ICU and hospital and probable use of various ICU services.

It compares each individual's medical profile against nearly 40,000 cases in its developement database before reaching a prognosis that is, on average, 95 percent accurate. A physician can give the computer system 27 easily obtained facts, and the program would predict that patient’s risk of dying in the hospital. The system is also useful in answering the question: Is treatment making a difference? Subtile physiological change, and their subsequent impact on risk, can be observed and trended as a way of evaluation the effectiveness of various therapeutic interventions.

APACHE III has been installed or used to benchmark performance in over 400 hospitals in the U.S. There are approximately another 40 hospitals worldwide where the APACHE III Methodology has been used to compare actual ICU outcomes to those predicted by the Methodology. The entire database is the largrest of it´s kind, currently exceeding 750,000 cases.

Apache III is available as a hospital-based system, and is also available via an internet subscription. Using a standard web browser, a user can obtain comparison of actual to predicted performance for adult intensive care unit populations. All data is fully encripted and access is password-protected.

The system was developed by William A. Knaus, MD. In 1978 he and several colleagues at GWU 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, physiology and on admission to the ICU and daily thereafter, age, pre-existing medical problems, etc. APACHE is in its third iteration (APACHE III) and is used to evaluate not only quality outcomes such as mortality, but to help hospitals use scarce resources in the most effective way by evaluating numerous utilization measures.