Complexity-driven modelling of macro-conditions in patients with Bodily Distress Syndrome

The complex adaptive systems perspective might lead to new insights into the bodily distress syndrome (BDS), an umbrella term for disorders which are characterised by symptoms without clear biological cause. It tells us that such symptoms might stem from a disruption of the human regulatory system, which can be observed through a reduced complexity in physiological signals like heart-rate variability (HRV) and micromovements. For example, in the case of chronic fatigue syndrome (CFS), clinical tests have confirmed a reduced complexity in patients’ physical activity and HRV signals. This opens up new opportunities for diagnosis and treatment, though suitable techniques to reliably track the personalised evolution of complexity within patients are currently non-existent. My proposed research intends to fill this gap from an engineering perspective. I will design new techniques to quantify non-stationary complexity in various physiological signals. From there on, I will investigate whether measured complexity can serve as a biomarker for tracking changes in the macro-condition of BDS patients. The final step is to devise a multi-modal predictive model which takes several types of past observations as an input in order to predict changes in BDS patients’ level of functioning. The proposed research is motivated by the need for smart self-monitoring, which could in the end allow BDS patients to gain back control over their lives which they often feel is missing.