Forecasting Physicians’ Choice Of Prescriptions

Physicians' choice of prescriptions are often influenced by patients, with patient experience with specific drugs playing a strong role, according to Management Science, a journal of the Institute for Operations Research and the Management Sciences (INFORMS). The results have important implications for those who market pharmaceuticals.

Management Insights, a regular feature of the journal, is a digest of important research in business, management, operations research, and management science. It appears in every issue of the monthly journal.

"A Dynamic Competitive Forecasting Model Incorporating Dyadic Decision-Making" is by Min Ding of Smeal College of Business at Pennsylvania State University and Jehoshua Eliashberg of the Wharton School.

The researchers addressed several questions: Do physicians incorporate patients' inputs into their prescription decisions? If so, to what extent modeling such inputs improves the forecasting performance compared to models that do not explicitly incorporate patients' inputs? Additionally, to what extent do the patients' inputs depend on the type of patients, disease, and the physicians themselves?

Using prescription data from different therapeutic classes and physician specialties, the empirical results indicate improvement in forecasting when patients' inputs are explicitly considered.

The authors find that, in most cases, the inherent preference for a drug, by both patients and physicians, increases once a patient has used the drug. They also find that patients play an important role in prescription decisions, but that their influence diminishes when the doctor is a specialist, and that they have no influence in situations where specialists are treating patients with severe symptoms.

These results have forecasting implications, as well as fundamental implications for how pharmaceutical executives should allocate their promotional resources.