A Hierarchical Self-Organising Fuzzy Logic-Based On-Line Advisor for the Management of Cardiac Septic Patients

An on-line intelligent advisory system (IAS) for the management of septic patients emerging from cardiopulmonary bypass (CPB) has been developed and evaluated on a comprehensive physiological model which incorporates sepsis-induced capillary leak and the hemodynamic response to Intensive Care Unit (ICU)-like therapeutic interventions. The IAS is composed of the expert's decision-making model which performs diagnosis and designates the appropriate therapeutic actions based on the patient's hemodynamic status and a multi-inputs multi-outputs self-organising fuzzy logic controller (SOFLC) for adjusting the infusion rates of the selected drugs to maintain the hemodynamics variables at the specified target values. Simulated patient scenarios reproducing post-CPB hemodynamic abnormalities were developed with the expert anesthetist to test the IAS ability to advice for the appropriate therapeutic interventions whilst controlling individual drugs infusion rates to maintain the hemodynamic parameters at the prescribed targets values.