Workshop

Monday, October 24, 2016 in New York
Full-day: 9:00am - 4:30pm

Room:1A10

From Presentation to Prediction to Prescription: Predictive Analytics for Healthcare

Intended Audience:

Analysts, Students, CEO's and CIO's of Hospitals and Medical Clinics, Doctors, Nurses, and Medical Administrators and Technical Managers: Analysts who would like a tangible introduction to predictive analytics or who would like to experience analytics using a state-of-the-art data mining software tool.
Anyone who would like an introduction to the use of predictive analytics in medical settings, and would like to experience doing a modeling exercise in a laboratory format learning a state-of-the-art Predictive Analytic software tool.

Knowledge Level: Beginner through advanced. For the beginner this workshop takes them through a healthcare modeling exercise from start to finish without any required prior training. For the advanced student this workshop will teach where predictive analytics is being used in healthcare, techniques used, and challenges that are faced. This workshop is for anyone interested in learning about the "Re-engineering of Medical / Healthcare Delivery".

Workshop Description

Data science is a significant driver of innovation in healthcare today. In this one-day workshop, attendees will gain a solid introduction to predictive modeling, with practical examples drawn from Elder Research's many successful healthcare analytics projects. Through specific case studies, model building tips, and lessons learned from over two decades of data science experience, Elder Research will help attendees expand their knowledge of proven methods and best practices that enhance healthcare with thoughtful data science.

Attendees will walk away with:

An understanding of how to make analytics more actionable by choosing an appropriate dependent variable in their predictive model.
Strategies for selecting core predictive inputs and curating them in a consistent and timely fashion
A framework for understanding which inputs are most impactful to a specific predicted outcome, providing increased actionability.
Knowledge of specific models to apply to common problems in health care, including workload prioritization, provider best practices, and optimizing patient outcomes.
Tips, tricks, lessons learned, and pitfalls to avoid in the healthcare analytics space.
Strategies for realizing value from models: how to take action on the results of an analytic model

Schedule

Price and Registration Info:

Workshop program starts at 9:00 am
Morning Coffee Break at 10:30 - 11:00am
Lunch provided at 12:30 - 1:15pm
Afternoon Coffee Break at 3:00 – 3:30 pm
End of the Workshop: 4:30 pm

Instructors

Miriam Friedel, PhD, Research Scientist, Elder Research, Inc.

Dr. Miriam Friedel has over ten years of experience with scientific modeling, predictive analytics, and software engineering. She guides and leads the Commercial Analytics Group at Elder Research, and has prior experience as a management consultant and as a research scientist in a neuroimaging lab. Her academic and practitioner background enables her to bridge the gap between complex concepts and understandable, actionable results. Dr. Friedel has built and deployed models to predict customer churn and user segmentation, has done survey analytics for a major non-profit, understands the complexities of model validation and testing, and has wide experience analyzing complex scientific data, in physical and biological sciences -- including modeling competing effects in brain development to better understand psychiatric disorders. Miriam has a B.S. in Physics from Brown University and a Ph.D. in Physics from the University of California, Santa Barbara and is a co-author on over fifteen peer-reviewed articles.

Mike Thurber, Lead Data Scientist , Elder Research, Inc.

Mike Thurber is an analysis professional who listens carefully to his clients' business objectives and challenges and has a passion for extracting relevant and valuable insights from available data. As a Lead Data Scientist with Elder Research, his modeling work ranges from predicting high payouts on long term care claims to identifying healthcare provider fraud to measuring the effect of Cesarean delivery on infant health. Wide experience managing a variety of analytic initiatives consistently generates business value through expert collaboration, data integration, insightful data analysis, statistical testing, and predictive modeling. Other examples include gleaning insights on how complex consumer choices impact sales, predicting profitability of prospective customers, calculating fraud and financial risk of many kinds, showing how call center interactions affect customer retention, forecasting recovery of losses due to loan default, modeling maintenance events on natural gas wells, and predicting propensity to make voluntary monetary donations., Mike earned a BS degree in Chemical Engineering from Brigham Young University and a Master's degree in Statistics from Virginia Commonwealth University. For the last four years, Mike has been teaching principles and best practices of predictive modeling to a broad audience of emerging data scientists.