Message Passing on Factor Graph: A Novel Approach for Orphan Drug Physician Targeting

Abstract

To successfully market an orphan drug requires a different business model than traditional blockbuster drugs. An orphan drug that treats a rare disease condition affects only a small patient population. Pharmaceutical companies rely on effective sales and marketing models under limited budget. The small sales field force has limited reach ability and relies on a well defined target list. But in practice it is often difficult to accurately identify physicians who are treating diagnosed or underdiagnosed rare disease patients. The challenges come from the extreme data imbalance and look-alike patient physician profiles between true and negative classes. Many classical targeting tools such as segmentation and profiling developed for mass market are unsuitable for orphan drug market. In addressing this task, the authors propose a graphical model approach to predict targets by jointly modeling physician and patient features from different data spaces and utilizing the extra relational information. Through an empirical example with medical claim and prescription data, the proposed approach demonstrates enhanced accuracy in identifying targets. The graph representation also provides visual interpretability of relationship among physicians and patients. The model can be extended to incorporate more complex dependency structures.