A model-based approach to the automatic diagnosis of von Willebrand disease

Von Willebrand disease (VWD) is the most common inherited coagulation disorder to be seen in humans. It originates from a deficiency and/or dysfunction of the von Willebrand factor (VWF), a large multimeric glycoprotein playing a central role in the hemostasis process. VWD occurs in a large variety of forms, and its symptoms may range from sporadic nosebleeds and mild bleeding from small lesions in skin, to acute thrombocytopenia or prolonged bleeding episodes. Diagnosing VWD may be complicated because of the heterogeneous nature of the disorder. Two mechanistic models of VWD are proposed in this article, and their performance is assessed using clinical data. Models allow for the automatic detection of the disease, as well as for a quantitative assessment of VWF multimer distribution patterns, thus elucidating the critical pathways involved in the disease recognition and characterization.