Getting the Most Out Of Data Mining for Pharmacovigilance and Risk Management

Drug-safety programs in both large and small pharmaceutical companies are now incorporating some sort of data mining process for spontaneous reports of safety issues, as a supplement to traditional case-by-case medical review. While data mining not a regulatory requirement, it can contribute valuable information, and is viewed favorably by regulators as a component of a proactive approach to safety. The growth of data mining has been encouraged by clarification of its technical capabilities and limitations, and by the availability of powerful software tools. This presentation will give an overview of data mining systems, for the safety or regulatory professional who collaborates with data miners, and for the executive decision-maker who oversees the implementation of data mining as a component of pharmacovigilance.

Areas Covered in the seminar:

• What is data mining?
• How does it fit with traditional pharmacovigilance?
• Can you explain data mining algorithms to a non-mathematician?
• What information can I gain from data mining?
• What are the capabilities and limitations of data mining?
• How do I manage the information provided by data mining?
• I’ve found a signal, now what? What procedures and policies are involved?
• What does the future hold for data mining?

Who will benefit:

• Safety and regulatory professionals who work with data miners, or who will be working with data miners in the future, particularly those who are involved in the development of safety processes and procedures.
• Executive decision-makers who are considering whether or not to implement data mining as a component of pharmacovigilance, and if so, how.
• Safety consultants who currently rely primarily on tradtional medical review, and who are interested in adding a data mining capability.

Instructor Profile:

Alan Hochberg, is Vice President of Research for ProSanos Corp., a biomedical informatics company in Harrisburg, PA, where he is involved in the development and evaluation of algorithms for drug safety signal detection and investigation. He has worked as a technical professional in biostatistics, bioinformatics and biomedical engineering for the past 29 years. He joined ProSanos from DuPont, where he was developed pattern-matching methods for bacterial DNA fingerprints. Previously, he worked for Hologic, Inc., Ortho Diagnostics (J&J), and American Science & Engineering, and has participated in all phases of bioanalytical instrument development, from initial concept to final product validation, with an emphasis on signal detection, and on algorithms for the use of quantitative data in medical decision-making. Mr. Hochberg holds several patents on optical immunoassay devices, and on data analysis methods for biologically-derived signals. He received his B.S. degree in Electrical Engineering from Princeton University.

Follow us :