SSE_SAVOIE MICHELLE- SORINTELLIS-Célia Thouin

The high attrition rates in clinical drug development and more especially in the late-stages drug clinical development is among the major challenges facing the pharmaceutical industry since failures in late-stage of clinical development are the costliest. The multitude of risks inherent in clinical drug development makes Go/No- Go decisions even more complex for pharmaceutical portfolio managers. Bode Greuel defines portfolio management as the process of maximizing the value of R&D portfolios through the appropriate allocation of resources, requiring alignment of portfolio management with the company’s strategic objectives. In the pharmaceutical industry, this value maximization concerns both therapeutic and commercial value, to sustain the innovative pharmaceutical company’s business model. However, many authors have pointed to a productivity crisis in the R&D pharmaceutical pipeline which the most visible symptoms are the fall in the number of new molecular entities (NMEs) versus an ever-increasing rise in R&D expenditures. Moreover, in a dynamic where few approved and marketed drugs generate revenues greater than or equal to the R&D expenditures that led to their development, it has therefore become essential for pharmaceutical portfolio managers to find new, effective approaches to better decision-making. Artificial intelligence, through its computing power, the availability of massive data and major advances in the development of algorithms, offers opportunities theses complex decision- making processes. The aim of this project is to review traditional approaches to pharmaceutical portfolio management, challenges and present the prospects in the age of artificial intelligence.

Faculty Supervisor:

Michelle Savoie

Student:

Partner:

Sorintellis

Discipline:

Life Sciences

Sector:

Professional, scientific and technical services

University:

Université de Montréal

Program: