A stochastic control program to predict outcome and to support therapeutic decisions: a preliminary report

Abstract

Background and objectives: Early noninvasive hemodynamic monitoring with an outcome predictor and a therapeutic decision support system may be useful to identify and correct hemodynamic deficiencies in emergency patients. The first aim was to apply a stochastic (probability) search and display model to predict outcome as early as possible. The second aim was to explore the usefulness of a therapeutic decision support system to evaluate the relative effectiveness of various therapies.

Methods: A stochastic control and display program based on noninvasive hemodynamic monitoring was applied in 100 consecutive critically ill patients admitted to the emergency department of an inner city public hospital. The program continuously displayed the noninvasive hemodynamic data and the patient's predicted survival probability (SP) that was based on the patient's diagnosis, covariates, and hemodynamic data. The accuracy of the SP at the initial resuscitation on admission to the emergency department (ED) was evaluated by the actual outcome at hospital discharge. The therapeutic decision support program evaluated the relative effectiveness of various therapies on based on their hemodynamic and SP responses and outcome of patients with similar clinical-hemodynamic states.

Results: The cardiac index, mean arterial pressure, arterial saturation, transcutaneous oxygen and carbon dioxide tensions were appreciably higher in survivors than in nonsurvivors in the initial resuscitation. Heart rate was higher in the nonsurvivors. The calculated Survival Probability (SP) of survivors averaged 81 +/- 1.4% in the first 24-hour observation period. It was 58 +/- 2.2% for nonsurvivors during this period. Misclassifications were 10/100 or 10%.