International Journal of Clinical Monitoring and Computing 7: 177-185, 1990. 1990 Kluwer Academic Publishers. Printed in the Netherlands. Clinical evaluation of computer-based respiratory care algorithms Dean F. Sittig 1, Reed M. Gardner 1, Alan H. Morris 2 & C. Jane Wallace 2 1Department of Medical Informatics, University of Utah/LDS Hospital, Salt Lake City, Utah, USA; 2Pulmonary Division, University of Utah/LDS Hospital, Salt Lake City, Utah, USA Accepted 21 June 1990 Key words: algorithm, computer, evaluation, respiratory care, ventilator management, clinical information systems, expert systems Abstract A collection of computer-based respiratory care algorithms were implemented as a prototype computer- based patient advice system (COMPAS) within the existing HELP hospital information system. Detailed medical logic recommended ventilator adjustments for 5 different modes of ventilation: assist/control (A/C), intermittent mandatory ventilation (IMV), continuous positive airway pressure (CPAP), pressure con- trolled inverted ratio ventilation (PC-IRV), and extracorporeal carbon dioxide removal (ECCO2R). Sugges- tions for adjusting the mode of ventilation, fraction of inspired oxygen (FiO2), positive end-expiratory pressure (PEEP), peak inspiratory pressure, and several other therapeutic measures related to the treatment of severe arterial hypoxemia in adult respiratory distress syndrome (ARDS) patients were automatically presented to the clinical staff via bedside computer terminals. COMPAS was clinically evaluated for 624 hours of patient care on the first 5 ARDS patients in a randomized clinical trial. The clinical staff carried out 84% (320/379) of the computerized therapy suggestions. In response to a questionnaire distributed to clinical users of the system, 86% judged the system to be potentially valuable. Through implementation of COMPAS, a computer-based ventilatory therapy advice system, we have laid the groundwork for standardi- zation of ventilator management of arterial hypoxemia in critically ill ARDS patients. Introduction 'Physicians have developed a splendid clinical science for explanatory decisions, and a magnif- icent technologic armamentarium of therapy, but our managerial desicions generally continue to be made as doctrinaire dogmas, immersed in dissention and doubt' [1]. A sound clinical care algorithm must be specific enough to treat common situations, broad enough to handle common exceptions and flexible enough to handle unusual complications. In light of the potential benefits to patients from the use of clin- ical care algorithms, [2], we developed and tested a prototype computer-based patient advice system (COMPAS) [3] on the HELP [4--6] clinical infor- mation system. COMPAS was designed to direct the ventilatory support of arterial hypoxemia in severe adult respiratory distress syndrome (ARDS) patients enrolled in a clinical trial compar- ing a new form of respiratory support [7, 8] with traditional respiratory therapy. No attempt was made to implement algorithms for the treatment of any of the other problems commonly associated with ARDS including for example: 1) therapy to correct hemodynamic abnormalities, 2) the utiliza- tion of changes in position or chest physiotherapy