Prospective evaluation of a decision support system for setting inspired oxygen in intensive care patients

Abstract

Purpose: The aim of the study was to prospectively evaluate a decision support system for its ability to provide appropriate suggestions of inspired oxygen fraction in intensive care patients comparing with levels used by clinicians in attendance.

Materials and methods: Thirteen mechanically ventilated patients were studied in an intensive care unit where up to 4 experiments were performed during 2 consecutive days. Inspired oxygen fraction was selected in each experiment by both the decision support system and attending clinicians, and each selection was evaluated by measuring arterial oxygen saturation.

Results: Median (interquartile range [range]) changes in inspired oxygen fraction from baseline level by attending clinicians and the decision support system were 0.00 (-0.05 to 0.00 [-0.10 to 0.05]) and -0.03 (-0.07 to 0.01 [-0.16 to 0.12]), respectively. Clinician ranges of inspired oxygen fraction and arterial oxygen saturation were 0.25 to 0.70 and 0.92 to 0.99, respectively. Decision support system ranges of inspired oxygen fraction and arterial oxygen saturation were 0.26 to 0.54 and 0.94 to 0.99, respectively.

Conclusions: The decision support system selects appropriate levels of inspired oxygen fraction in intensive care patients and could be used for automatic frequent assessment of patients, freeing the focus of clinicians to concentrate on more challenging therapy.