There is currently no universally accepted approach to weaning patients fro
m mechanical ventilation, but there is clearly a feeling within the medical
community that it may be possible to formulate the weaning process algorit
hmically in some manner. Fuzzy logic seems suited this task because of the
way it so naturally represents the subjective human notions employed in muc
h of medical decisionmaking. The purpose of the present study was to develo
p a fuzzy logic algorithm for controlling pressure support ventilation in p
atients in the intensive care unit, utilizing measurements of heart rate, t
idal volume, breathing frequency, and arterial oxygen saturation. In this r
eport we describe the fuzzy logic algorithm, and demonstrate its use retros
pectively in 13 patients with severe chronic obstructive pulmonary disease,
by comparing the decisions made by the algorithm with what actually transp
ired. The fuzzy logic recommendations agreed with the status quo to within
2 cm H2O an average of 76% of the time, and to within 4 cm H2O an average o
f 88% of the time (although in most of these instances no medical decisions
were taken as to whether or not to change the level of ventilatory support
). We also compared the predictions of our algorithm with those cases in wh
ich changes in pressure support level were actually made by an attending ph
ysician, and found that the physicians tended to reduce the support level s
omewhat more aggressively than the algorithm did. We conclude that our fuzz
y algorithm has the potential to control the level of pressure support vent
ilation from ongoing measurements of a patient's vital signs.