Routine assessment of the anaesthetic fitness before surgery is carried out by assessing static, subjective, and/or anatomical data. Dynamic and objective examinations are rarely carried out before surgery due to time cost constrains and only in patients at obvious risk.

A novel methodology and electromedical device are proposed, which predict the dynamic-functional anaesthetic fitness and individual ventilation parameters.

Voluntary cessation of breathing (apnea) is used here as a mild stressor of the body, which induces regulatory time-dependent changes in non-invasive physiological biosignals (diving reflex). The prominence of these regulatory actions reflects the dynamic adaptive capacity of cardiovascular and pulmonary systems of the patient and is monitored in order to individualize aneasthesia and propose individual ventilation parameters. An in-silico/AI twin is developed that models this dynamic physiology and is continuously personalized via recorded non-invasive biosignals, and thus predicts anaesthetic fitness in real time. A lung model is established to depict the relationships between individual physiological parameters.

Pre-clinical studies are performed to validate this novel predictive technology.