Knowledge of different disease phenotypes can help understand (a) which patient subpopulations seek treatment and (b) the response to treatment within each subgroup. In this paper, we presented a workflow to (i) determine distinct phenotypes of medical conditions in high-dimensional data, (ii) visualize these phenotypes to explore and compare essential subpopulation characteristics, and (iii) interactively inspect them and their change over time with an interactive web application. We evaluated our workflow by identifying four distinct phenotypes of tinnitus patients.
Study examining (1) how male and female tinnitus patients differ, (2) the extent to which gender is related to (tinnitus) questionnaire responses, and (3) which baseline questionnaire items are related to tinnitus distress, depression, and treatment response, only one gender.
Study predicting depression severity in tinnitus patients after treatment based on self-report questionnaire data acquired at baseline and ranking of features w.r.t. their attribution towards model prediction.
A machine learning workflow to predict tinnitus distress after treatment based on self-report questionnaire data acquired at baseline and extraction of statistics and visualizations representing feature importance on a population-, subpopulation- and individual level.