W12: DATA SCIENCE DRIVING BETTER INFORMED DECISIONS
waterfront 3

Tuesday, April 16 12:30 – 4:00 pm

Instructors:

Farhan (CJ) Hameed, MD, MS, Senior Director, Global Real World Evidence Center of Excellence, Patient & Health Impact, Pfizer, Inc.

Meeta Pradhan, PhD, Senior Data Scientist, Indiana Biosciences Research Institute

Nigel Greene, PhD, Director, Head, Data Science and Artificial Intelligence, Drug Safety and Metabolism, AstraZeneca

Meghan Raman, Director, Digital Capability Management, R&D Data Lake and Integration, Bristol-Myers Squibb

ABOUT THIS WORKSHOP:

This course will highlight how data science is succeeding in helping Pharma organizations make data driven decisions to gain efficiencies and let companies grow their research programs effectively. Attendees will learn how to bridge between the worlds of data scientists and bench researchers and see how novel tools and applications can impact their research.

WORKSHOP AGENDA:

12:30 Handling Real World Data to Inform Healthcare Decisions: Case Study Diabetes

Meeta Pradhan, PhD, Senior Data Scientist, Indiana Biosciences Research Institute

Despite progress in treatment of Type 2 Diabetes (T2D), T2D remains a growing global health issue. In Indiana approximately 12.9% of adult population have diabetes. Due to the multiple factors driving the increase in T2D, there is a need for precision approach to T2D that would enable better treatment to patients. This talk demonstrates the complexity of real-world data, how to prepare it for research, and its utility in understanding T2D leveraging different machine learning approaches to support better decision making.

1:15 Leveraging Data Science for Evidence Generation by Integrating Real World Data from Research and Practice

Farhan (CJ) Hameed, MD, MS, Senior Director, Global Real World Evidence Center of Excellence, Patient & Health Impact, Pfizer, Inc.

Is current state of healthcare industry really transformative? There is certainly a paradigm shift in adopting and developing new and robust methodologies to collect and analyze the data. Does it really provide a meaningful feedback to patients, providers, regulators and researchers? We will discuss some of the key challenges such as selection of the right tools for advanced analytics and type of data sets, accessibility issues and lack of data standardization, and hidden challenges to generate regulatory grade evidence. Using a patient-centric approach based on evidence generated medicine (EGM) through utilization of real world data and novel digital end points to enable a robust learning health system (LHS).

2:00 Refreshment Break

2:15 Application of Data Science and AI to Improve the Safety of New Drug Candidates

Nigel Greene, PhD, Director, Head, Data Science and Artificial Intelligence, Drug Safety and Metabolism, AstraZeneca

Drug discovery and development is a multiparameter optimization problem that requires a fine balance between efficacy, ADME and safety.  Although the number of clinical failures from safety has been reduced, there are still improvements that could be made.  In addition, there are strong economic drivers to reduce the costs of discovering new medicines.  Data science and artificial intelligence is being seen as a potential method to both improve the safety profile of new drugs as well as reduce the costs and time to bring these to the clinic.  This talk will highlight some of the current investments in computational methods and highlight some of the key gaps in realizing these benefits.

3:00 Finding Diamonds in the Rough - Discoverability and Analytics

Meghan Raman, Director, Digital Capability Management, R&D Data Lake and Integration, Bristol-Myers Squibb

We currently have large volumes of data across the enterprise. It is very difficult to search or find relevant information quickly. Finding the right samples, searching for products and experiments, searching patient data across real world data sets to identify patient cohorts are arduous tasks. There is also an increasing need for improved collaboration and knowledge sharing across the analytic communities. This presentation will cover some of the key needs or use cases across translational, clinical and real world data domains. It will also cover details on enabling search and reproducible analytic capabilities to satisfy these use cases.

3:45 Extended Q&A with Workshop Instructors

4:00 End of Workshop

INSTRUCTOR BIOGRAPHIES:

Nigel Greene, PhD, Director, Head, Data Science and Artificial Intelligence, Drug Safety and Metabolism, AstraZeneca

Nigel Greene leads the Data Science and Artificial Intelligence department in Drug Safety & Metabolism at AstraZeneca and is interested in the application of artificial intelligence methods to understand of mechanisms of drug-induced toxicity and their translation to a clinical patient population. Previously Dr. Greene was a head of the Predictive Compound ADME and Safety group at AstraZeneca. Dr Greene also spent 14 years at Pfizer Inc. where he started in Drug Safety R&D and later transitioned to the Compound Safety Prediction group in Medicinal Chemistry. In his early career, Dr. Greene worked for Lhasa Ltd. where he pioneered computational toxicology, and for Tripos Inc.
Nigel’s other activities outside of AstraZeneca have included being the Chair of the Board of Trustees for Lhasa Ltd. and he has served on multiple National Research Council committees sponsored by the US Environmental Protection Agency, US Food and Drug Administration, and the National Institutes of Health.
Dr. Greene received his B.Sc. and PhD from the University of Leeds in the UK.

Farhan (CJ) Hameed, MD, MS, Senior Director, Global Real World Evidence Center of Excellence, Patient & Health Impact, Pfizer, Inc.

Farhan "CJ" Hameed is a biomedical informatician and real-world data strategist with diverse experience in healthcare, spanning academia, patient care, clinical research and informatics for over 18 years. In his current role at Pfizer, he focuses on development and harvesting strategic alliances for end-to-end utilization of real world data (RWD) in drug development to generate regulatory grade real world evidence (RWE). In his earlier work at Pfizer, CJ led Informatics initiative at the Quantitative Medicine and Neuroscience Research Units and steered the development and implementation of semantically driven interoperable drug discovery analytics platforms and knowledge management systems for multiple therapeutic areas. In Digital Medicine group and Pfizer Innovative Research (PfIRe) Lab, his team led the development of analytics-based reporting systems leveraging AI & Machine Learning by incorporating ontologies, clinical and wearables data standards for the real world and clinical trial studies. Prior to joining Pfizer, CJ led several clinical informatics projects, built multi-specialty evidence-based knowledgebase systems in partnership with several international academic institutes and publicly funded organizations and steered development of international drug databases, and clinical decision support systems (CDSS). He also held several academic positions in the past - an Associate Professor at the College of Pharmacy at Chicago State University and Midwestern University and, currently, teaches at Northeastern University, Boston Health Informatics graduate program. CJ holds a master's degree in health informatics from Northeastern University and a medical degree from Dow University of Health Sciences. He is a HIMSS fellow and recently attained American Medical Informatics Association fellowship status.

Meeta Pradhan, PhD, Senior Data Scientist, Indiana Biosciences Research Institute

Meeta Pradhan, a Senior Data Scientist at Indiana Biosciences Research Institute (IBRI). Her research focuses on integration and analysis of ‘OMiCS’ and real-world data to inform healthcare decisions. Her expertise is investigating molecular mechanisms in a systems biology framework to better understand dysregulated pathways. Her recent work includes transforming Electronic Health Records to actionable knowledge for better decision. Prior to Joining IBRI, Meeta was a faculty member at Indiana University Purdue University, Indianapolis. She was advisor and co-advisor to more than 20 Masters in Bio-Health Informatics Students.

Meghan Raman, Director, Digital Capability Management, R&D Data Lake and Integration, Bristol-Myers Squibb

Meghan Raman has 20+ years of experience in successfully leading large scale business transformation programs. She has cross industry domain expertise including Life Sciences, Financial, Consulting, Insurance, Telecomm and Resellers. She is experienced in building and leading global, high performance teams. She has also built Analytics frameworks and applications in multiple domains to drive revenue uplift and productivity. Meghan has led process development and implementation activities in Clinical, Regulatory and Pharmacovigilance domains. She has set up Analytics-as-a-Service framework and integration efforts between Product Registration, Safety Reporting and Clinical Trial Management

She is currently leading the R&D Data Lake and Integration portfolio for multiple domains including Translational Medicine, Clinical, Safety, Regulatory and Medical. Her current work enables data scientist access to clinical, operational, biomarker and real world data in a standard location, R&D Data Lake.  Her work also enables scientist/clinicians capability to search biomedical terms. In addition her work provides data scientists a reproducible research environment with a business glossary, data catalog & lineage. Her other responsibilities include providing Study Start-up analytic capabilities and enabling a clinical metadata repository to store and manage clinical data standards.

Back To Workshops