A novel brain-inspired neuro-fuzzy hybrid system for artificial ventilation modeling

Artificial ventilation is a crucial supporting treatment for Intensive Care Unit. However, as the ventilator control becomes increasingly more complex, it is non-trivial for less experienced clinicians to control the settings. In this paper, the novel Hebbian based Rule Reduction (HeRR) neuro-fuzzy system is applied to model this control problem for intra-patient and inter-patient ventilator control. These two ICU care studies demonstrate the capability of HeRR neuro-fuzzy system in extracting the salient knowledge embedded in the training data. Experimental results on the two studies show promising use of the HeRR neuro-fuzzy system for artificial ventilation.

► A novel Hebbian based Rule Reduction (HeRR) neuro-fuzzy system is applied to intra/inter-patient ventilator control. ► Two ICU care studies demonstrate the capability of HeRR in extracting the salient knowledge from training data. ► Experimental results on the two studies show promising use of HeRR for artificial ventilation. ► HeRR uses the Hebbian ordering to determine the significance of each rule. ► An iterative tuning and reduction process is proposed to strike a trade-off between interpretability and accuracy.