Press "Enter" to skip to content

How Clinical Trial Data Supports Accurate Pharma Forecasting

Copyright © DrugPatentWatch. Originally published at How Clinical Trial Data Supports Accurate Pharma Forecasting

Data from clinical trials can improve pharmaceutical forecasting

Pharmaceutical investing requires a level of attention to detail that is not as critical in less complex or less regulated industries. The pharmaceutical industry is under pressure to keep a lid on costs while pursuing bold research and development. To do both, pharmaceutical companies require the use of accurate forecasting models.

Forecasting models, naturally, are not perfect, and pharmaceutical forecasting is affected by more variables than most other industries. Clinical trial data is increasingly being used to inform pharmaceutical forecasting. For example, clinical trial data can be used to forecast new clinical indications, and is thus informative to the pharmaceutical investor.

The working assumption with clinical trials is that the drug will receive approval by regulating authorities, but that is not guaranteed. On the other hand, early stage market research does not always predict which drugs will become blockbusters, so the risk is offset to some extent by potentially big rewards. Accurate clinical forecasting can empower investors when it is used in sophisticated forecast models.

It Is Not Always Easy to Get Pharmaceutical Companies to Share Data

One problem, of course, is that pharmaceutical companies tend to want to keep clinical trial data proprietary. Yet widespread sharing of clinical trial data could benefit the entire industry. In fact, industry associations like the Pharmaceutical Research and Manufacturers of America (PhRMA) have publicly-accessible databases of trial results.

Acknowledgement by pharmaceutical companies of the importance of sharing trial data is not the same thing as willingness to actually share it. However, the use of Bayesian analysis is a more palatable option to many pharmaceutical manufacturers. Bayesian models estimate parameters of an distribution based on an observed distribution. They are valuable for early identification of problems with new drugs, and are used by the World Health Organization (WHO) for drug monitoring. In other words, there are ways to share data indirectly and improve forecasting without the risks of outright sharing of trial data.

Does Big Data Have a Role?

A case for big data analysis is particularly plausible in complex business environments, and pharmaceuticals definitely qualify. Furthermore, the pharmaceutical industry constantly generates data from R&D activities, patients, caregivers, and retailers. Newer big data analysis techniques will hopefully help pharmaceutical companies better identify good drug candidates and develop them more quickly and efficiently, while mitigating health or regulatory risks.

Big data and Bayesian modeling are expected to improve pharmaceutical forecasting

As big data analysis techniques mature, the possibilities are exciting:

  • More sophisticated predictive modeling of drugs and biological processes, potentially identifying new candidate molecules with a high probability of successful development into effective drugs
  • The ability to include patients in clinical trials based on more factors (like genetic information) to target specific populations, which could allow smaller, shorter, less expensive trials that are just as valuable
  • Real-time trial monitoring capability for quicker identification of safety or operational signs that require action to avoid unnecessary delays as well as adverse events
  • Better flow of data between, for example, discovery and clinical development functions within pharmaceutical companies, and with external partners like physicians and contract research organizations

Warming Up to the Concept of Collaboration

Better internal collaboration within pharmaceutical companies could lead to keener insights across drug portfolios, and better identification of follow-on potential for drugs that are developed. It also has the potential to allow unexpected options to emerge at the research stage based on early clinical data or simulations.

External collaboration is riskier, of course, but the benefits can be major. For example, collaboration with clinical research organizations could allow for easier scaling of capabilities, and easier access to expertise tailored to a pharmaceutical manufacturer’s clinical study management needs. Academic collaboration, like Eli Lilly’s Phenotypic Drug Discovery Initiative, allows researchers to submit compounds for screening to identify whether it is a potential drug candidate without giving up intellectual property.

Making Clinical Trial Forecasting Better

Improving clinical trial forecasting benefits all parties. When companies hold too much money in their clinical trial programs or have the opposite problem of constantly trying to generate additional funding, they limit their ability to fund other opportunities.

Unfortunately, pharmaceutical forecasting is based on an extensive combination of factors, but improvements to the ability to manage risk and track clinical trial budgets will ultimately make a positive difference by making successful trials more cost-effective and halting unsuccessful trials before too many resources are sunk into them.

It is not easy to discover actionable business intelligence on pharmaceuticals, but the DrugPatentWatch clinical trial database offers the pharmaceutical investor powerful information for making the most informed business decisions. Information includes regulatory status, patent expirations, patent maintenance lapses, and tentative approvals with advanced search and data export capabilities.

Make Better Decisions with DrugPatentWatch

» Start Your Free Trial Today «

Copyright © DrugPatentWatch. Originally published at How Clinical Trial Data Supports Accurate Pharma Forecasting
Find your next blockbuster

Get accurate and timely intelligence — in just a few clicks

✓ Free trial

✓ No credit card


DrugPatentWatch - Make Better Decisions