Using Big Data and Machine Learning to Change the Future of Healthcare

Watch the Recorded Web Stream

Recorded on March 8, 2016

Talk Highlights

Click for timestamps ↓

Introduction

0.00.00 -0.00.15

Increasing Health Care Costs

The current costs of health care in the United States are outlined: knowledge blindspots cost the economy hundreds of billions of dollars.

0.00.16 - 0.02.00 : Increasing Number and Cost of Drugs
0.02.01 - 0.03.38 : Rising Cost of Health Care
0.03.39 - 0.05.00 : Solving the Wanamaker Problem in Health Care
0.05.01 - 0.07.58 : Current Knowledge Blindspots in Health Care
0.07.59 - 0.09.29 : Treating Patients as Averages
0.09.30 - 0.10.54 : Lecture Outline

Why Now? Changes in Data & Technology Throughout the Years

How datafication is increasing both the scope of health care data sources and pportunities to revolutionize the health care system.

0.10.55 - 0.11.47 : Traditional Health Care Data Sources
0.11.47 - 0.14.13 : New Health Care Data Sources
0.14.14 - 0.15.40 : Rise in Computing Power
0.15.41 - 0.16.39 : The Perfect Opportunity

GNS Healthcare

Colin Hill introduces his company, GNS Healthcare, and addresses how he plans to improve health outcomes with high-throughput precision health care.

0.16.40 - 0.18.59 : Founding GNS Healthcare
0.19.00 - 0.21.29 : Audience Question - Accessibility of Data
0.21.30 - 0.23.35 : Audience Question - Evolving Data Models
0.23.36 - 0.25.17 : GNS Healthcare in the Media
0.25.18 - 0.25.54 : GNS Healthcare Partners

Proprietary REFS Platform - Modelling & Machine Learning

REFS machine learning platform (that relies on “supercomputing” and “regression on steroids”) is introduced and explained. Colin Hill responds to question regarding disparities in population health: will the benefits of complex (and potentially difficult to procure) precision medicine methods benefit only those already able to obtain the best health outcomes money can buy?

0.25.55 - 0.28.11 : Types of Data Analytics
0.28.12 - 0.29.14 : Machine Learning & Simulation - What if?
0.29.15 - 0.33.32 : GNS Healthcare Machine Learning Platform: REFS - Reverse Engineering Forward Simulation Algorithm
0.33.33 - 0.35.22 : Audience Question - Model Readout & Validation
0.35.23 - 0.36.44 : Audience Question - Genomic Data in Modelling
0.36.45 - 0.38.30 : Audience Question - Potential GNS Partnership
0.38.31 - 0.40.06 : Audience Question - Genomic Sequencing
0.40.07 - 0.44.42 : Audience Question - REFS Algorithms
0.44.43 - 0.52.28 : Audience Question - Disparities in Population Health exacerbated by Precision medicine?

Examples of GNS Healthcare Solutions

How REFS can reduce the cost of and improve the precision of treating metabolic syndrome.

0.52.29 - 0.53.54 : The Impact of GNS Causal Models
0.53.55 - 0.57.34 : Coronary Artery Disease
0.57.35 - 1.01.19 : Preterm Birth
1.01.20 - 1.07.11 : Metabolic Syndrome

What Happens if Precision Medicine Wins?

An ideal future, with a personalized treatment landscape available to individual patients facing debilitating disease.

1.07.12 - 1.08.52 : Personalized Treatment Landscape
1.08.53 - 1.10.04 : Can Big Data Save My Dad From Cancer?
1.10.05 - 1.13.49 : Transforming Medicine - The Elizabeth Kauffman Institute

Closing Remarks

1.13.50 - 1.14.50 : Thank You - Catherine Murray, Associate Dean, SFU Undergraduate Academic Programs & Enrolment Management
1.14.51 - 1.17.33 : Question from student host - Joseph Yeates, SFU Beedie School of Business
1.17.34 - 1.20.59 : Question from student host - Chandra Lebovitz, Doctoral Candidate, SFU Department of Molecular Biology and Biochemistry
1.21.00 - 1.22.14 : Gift Presentation - student host Joseph Yeates, SFU Beedie School of Business

Engaging Big Data

Lecture Topics

Current President Dream's Colloquium

One Health: Connections and Collaborations

Learn about the Public Lectures starting January 25

Learn more

About the Lecture

Big data and machine learning can yield great rewards in healthcare, accelerating the use of precision medicine to solve our most pressing population health challenges. Specifically, there is a key emerging opportunity to use machine learning and big data to better match drugs and other health interventions to individual patients to improve outcomes and lower costs. Key example applications include preterm birth; medication nonadherence; metabolic syndrome; comparative effectiveness in diabetes, arthritis and oncology; end of life care; and patient stratification in clinical trials, to name a few.

Big data flows from the obvious places like sophisticated imaging technologies, activity trackers, electronic health records, genomics and claims data; but also can be found in our consumer shopping data, socioeconomic and demographic makeup and geographic location. Machine learning simulates outcomes from many possible interventions, making medicine and healthcare more predictable, personalized, and precise.

This session will discuss the enormous opportunities to leverage big data and machine learning in medicine and healthcare, explore the new and innovative data that is being applied, and highlight key areas where governments, health plans, employers, biopharmaceutical companies, and academic medical centers are solving problems that, until recently, were unsolvable.

About the Speaker

Colin Hill
CEO of GNS Healthcare, Chairman of Via Science

GNS Healthcare is a big data analytics company that Colin Hill cofounded in 2000. Since its inception, Colin has made a huge impact in the healthcare industry by empowering health plans, providers, pharmaceutical companies, and foundations to make intelligent data-driven decisions. In addition to his role as CEO of GNS Healthcare, Colin also serves as the Chairman of Via Science, helped found the Board of Directors of AesRx, and initiated O’Reilly Media’s Strata Rx — the first healthcare big data conference.

In 2004, Colin was named to MIT Technology Review’s TR100 list of the top innovators in the world under the age of 35. He is a frequent speaker at national and international scientific and industry conferences and has been quoted in in numerous publications and television programs, including The Wall Street Journal, CNBC Morning Call, Nature, Forbes, Wired, and The Economist. He graduated from Virginia Tech with a degree in physics and earned master's degrees in physics from both McGill University and Cornell University.

Graduate Studies

President's Dream Colloquium on Engaging Big Data