The non-existent average individual: Automated personalization in psychopathology research by leveraging the capabilities of data science

The importance of the 'person' in a 'person with an illness' can not be overstated, a quote originating from Hippocrates as early as 400 BC. The importance of the individual is even more prevalent in fields of medicine in which notions of disease, illness, and patient are inherently heterogeneous. This heterogeneity suggests that 'one-size-fits-all' treatments might not be the way forward, and tailored treatments need to be devised. A field of medicine in which this holds is the field of psychopathology.

In the present work we approach the collection of data on a large scale, and the analysis thereof, from a personalized and continuous perspective. We do not make assumptions that psychopathology is strictly a constant phenomenon, but varies over time and within individuals. We describe the various platforms we developed to collect psychopathological and physiological data one a large scale, that is, HowNutsAreTheDutch, Leefplezier, and Physiqual. Then we describe methods to analyze these data, first from a statistical time-series analysis perspective, and then from a state of the art machine learning perspective.

We conclude the work with an analysis of our developed platforms and the data collected. We then reflect on the developed analysis tools and their practical implications.