Assess the Risk/Return Profile of Pipeline Drugs

Pharmaceutical companies have constant pressure to continue to innovate and grow. This is particularly acute now, as the industry faces a veritable cliff of impending patent expirations. There is a vital need for companies to fill their pipelines with new therapies to replace lost revenue. At the same time, developing and gaining approval for new drugs has become more difficult. These factors mean big pharma needs to employ new strategies to maintain and grow business. This is done through a better assessment of the risk/return profile of drugs in their pipelines. Forecasting plays an essential role in determining which drugs will lead to the best returns and which drugs should be dropped before they consume too many resources. Patient-based forecasting is a reliable approach to use when analyzing a marketplace and the potential a therapy may have within it, It is very important forecasts because a well-defined segmentation is approach is required to understand primary drivers behind a forecast to enables an organization to create a dynamic therapeutic model, project the impact of future events, and quickly adjust the forecast as these events occur

To make any successful forecasting model, the first step is to identify the key supporting metrics required to build an accurate forecast model using patient level data, because this provides the most accurate results as its based out of real-world data. There are two major challenges faced during the process, firstly, to efficiently gather and consolidate all the information for the drugs using secondary research related to approval, market entry etc. and secondly, handling unstructured EMR and claims data. We leveraged our knowledge and capabilities to efficiently merge information from both sources and build robust KPIs which can support development of efficient forecast model, these KPIs helped multiple pharmaceuticals clients to

1. Understand incidence and prevalence of the disease within a select category and later understand the diagnosed and treated population for the same
2. Build robust forecasting assumption in terms of patient share, peak patient share, time to peak, analogue analysis, adherence, persistence and median duration of treatment

Request a demo to find out how D Cube can help you to develop KPIs that can further support to build a forecast model to assess risk/ return profile for the drugs in pipeline