presented BioIT World Boston MA April 2015
Abstract: Software for predictive analytics is making this activity more accessible to people without deep programming or statistical experience. Pharmaceutical predictive analytics applications include business/competitive intelligence, clinical trial modeling, outcome prediction, predictive toxicology, patent analysis, technology sensing and others,. Related topics include data visualization, data integration, data mining, deep learning, machine learning, probabilistic forecasting, text mining and knowledge management. Information professionals can bring relevant experience in data curation and query formulation to contribute to this process.

Overviews:
How Big Data Can Revolutionize Pharmaceutical R&D, Jamie Cattell, Sastry Chilukuri, and Michael Levy, McKinsey, April  2013 After transforming customer-facing functions such as sales and marketing, big data is extending its reach to other parts of the enterprise. In research and development, for example, big data and analytics are being adopted across industries, including pharmaceuticals.
http://www.mckinsey.com/insights/health_systems_and_services/how_big_data_can_revolutionize_pharmaceutical_r_and_d

making enterprise elephants dance (gangnam style) , Andy Palmer, Tamr, Boston Data Festival, 2014
Start with the questions not the answer… Ask aspiration/transformational questions…. embrace the ambiguity…. Do not boil the ocean. Internal and external data BOTH important.
http://www.bostondatafest.com/wp-content/uploads/2014/11/Palmer_Presentation_Boston_Data_Festival.pdf

Nate Silver, The Signal and the Noise: Why most predictions fail – but some don’t, Allen Lane, 2012. The fashionable term now is “Big Data”… This exponential growth in information is sometimes seen as a cure-all…. Before we demand more of our data, we need to demand more of ourselves.

Google Trends Predictive analytics 2005-2014  % increase 1,486%

PubMed articles predictive analytics 1975-2014 1990-2014 1107% increase

Terminology and key concepts
Predictive analytics: encompasses a variety of statistical techniques from modeling, machine learning, and data mining that analyze current and historical facts to make predictions about future, or otherwise unknown, events. .. The core of predictive analytics relies on capturing relationships between explanatory variables and the predicted variables from past occurrences, and exploiting them to predict the unknown outcome. It is important to note, however, that the accuracy and usability of results will depend greatly on the level of data analysis and the quality of  assumptions. Wikipedia accessed April 12 2015  http://en.wikipedia.org/wiki/Predictive_analytics                                                                                                                             

Predictive Model Markup Language, Data Monitor Group http://www.dmg.org/

Predictive modeling: leverages statistics to predict outcomes. Most often the event one wants to predict is in the future, but predictive modelling can be applied to any type of unknown event, regardless of when it occurred. For example, predictive models are often used to detect crimes and identify suspects, after the crime has taken place. In many cases the model is chosen on the basis of detection theory to try to guess the probability of an outcome given a set amount of input data, Wikipedia accessed April 12, 2015  http://en.wikipedia.org/wiki/Predictive_modelling

Related concepts: deep learning, machine learning, neural nets, text mining, data integration, collaboration, next generation sequence data analytics, correlating patient genotypes and clinical trial results, biosensors and remote monitoring and wearable devices, real world data

Biopharmaceutical glossaries & taxonomies: informatics Overview Informatics_Overview.asp
Gartner IT Glossary http://www.gartner.com/it-glossary/
StatSoft Statistics Glossary http://www.statsoft.com/Textbook/Statistics-Glossary

Predictive Analytics Software
Accenture, Predictive Health Analytics
http://www.accenture.com/us-en/Pages/service-life-sciences-predictive-health-intelligence-analytics-solutions.aspx
BioMedTracker, Informa http://www.biomedtracker.com/
Cortellis Regulatory Analytics, Thomson http://thomsonreuters.com/cortellis-regulatory-intelligence-analytics/
IBM Business Analytics for life sciences  http://m.ibm.com/http/www-01.ibm.com/software/au/analytics/pharmaceuticals-life-sciences/
Recorded Future, Competitive Intelligence https://www.recordedfuture.com/competitive-intelligence/
SAS Analytics for Life Sciences http://www.sas.com/en_us/industry/life-sciences.html#more-solutions
StatSoft, Pharmaceutical Solutions http://www.statsoft.com/Solutions/Pharmaceutical

Data Visualization software
Excel Power Pivot  https://support.office.com/en-us/article/Power-Pivot-Add-in-a9c2c6e2-cc49-4976-a7d7-40896795d045
Palantir https://www.palantir.com/
Tableau http://www.tableausoftware.com/
Tibco Spotfire http://spotfire.tibco.com/

Other companies of interest include: Tamr http://www.tamr.com/  Exaptive https://exaptive.com/   GNS Healthcare, http://www.gnshealthcare.com/    Innovaccer http://www.innovaccer.com/

Government
FDA Sentinel Initiative A national electronic system that will transform FDA’s ability to track the safety of drugs, biologics, and medical devices once they reach the market is now on the horizon. Launched in May 2008 by FDA, the Sentinel Initiative aims to develop and implement a proactive system that will complement existing systems that the Agency has in place to track reports of adverse events linked to the use of its regulated products. http://www.fda.gov/Safety/FDAsSentinelInitiative/ucm2007250.htm

Journals:
Articles appear in a wide and scattered variety of journals. Relevant titles include
American Health & Drug Benefits, Engage Communications http://www.ahdbonline.com/
Big Data, Mary Ann Liebert http://www.liebertpub.com/overview/big-data/611/
Bioanalysis, Future Science http://www.future-science.com/loi/bio
Healthcare financial management : journal of the Healthcare Financial Management Association.
Journal of Pharmaceutical & Biomedical Analysis, Elsevier http://www.sciencedirect.com/science/journal/07317085 
Statistical Methods in Medical Research, Sage Publications http://smm.sagepub.com/
Statistics in Medicine, Wiley http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)1097-0258
Value in Health, Elsevier http://www.valueinhealthjournal.com/

Newsletters
Fierce Big data http://www.fiercebigdata.com/
Predictive Analytics Today http://www.predictiveanalyticstoday.com/

Conclusion: Predictive analytics can be used to identify pharmaceuticals trends and predict outcomes and identify probabilities for R&D successes and failures. Similar questions can be asked for various drug targets or indications and replicated.  This is a work in progress.  Please let me know of other useful resources and developments.

Electronic version with links available at predictiveanalytics.ASP

Thanks to Eric Stubbs, Information Specialist, Otsuka and Richard Steel, Science Intelligence Analyst, Genzyme for their lists of software summarized for the Pharmaceutical & Health Technologies Division Listserv, and to Mark Burfoot, Novartis, particularly for his observation about the power of articulating what you are not interested in,

Bibliography
 
How to look for other unfamiliar  terms

IUPAC definitions are reprinted with the permission of the International Union of Pure and Applied Chemistry.