Machine Learning & AI In Healthcare - From the Healthcare Conference Network

This event ran May 3-4, 2017 and has now finished.

The agenda is currently being researched, and we are actively taking speaker submissions. If you are interested in speaking at the event, please contact:

Symon Rubens
Healthcare Conference Network
symon.rubens@healthcareconferencenetwork.com
Phone: +1 (832) 709-0098

 

7:30 am

Registration and Welcome Refreshments

8:45 am

Opening Remarks from the Chairman

Ajay K. Gupta, Chief Executive Officer
Health Solutions Research

Re-thinking How Healthcare is Done Through Technology Innovation & Data Usage

9:00 am

A Mind of its Own - Artificial Intelligence Changing the Face of Healthcare

  • AI in general – going back to basics
  • Why is it relevant now more than ever?
  • Leveraging AI benefits in your healthcare organization – creating new business models, reducing risk, improving efficiency and driving new competitive advantages
  • Going the extra mile – improving AI so that it reflects natural intelligence
  • Applying artificial intelligence to your electronic medical record (EMR) data

William Paiva, Executive Director - Center for Health Systems Innovation (CHSI)
Oklahoma State University

9:45 am

Machine Learning and Big Data in Healthcare 101 - Leveraging Large Amounts of Data to Achieve Data-Driven Insights

  • How is machine learning improving accuracy and efficiency in patient care and operations?
  • Improving patients’ health and care while decreasing the cost of care
  • Equipping providers with the advanced intelligent tools to improve accuracy in diagnosis and preventative treatment

Jim Fackler, Associate Professor
Johns Hopkins School of Medicine

10:30 am

Morning Break and Networking

11:00 am

Machine Learning and Artificial Intelligence in Healthcare: Breaking Down the Silos

  • Fundamental quality, safety and cost problems have not been resolved by the increasing digitization of health care
  • This digitization has progressed alongside the presence of a persistent divide between clinicians, the domain experts and the technical experts, such as data scientists
  • The divide can be narrowed by creating a culture of collaboration between these two disciplines. However, to more fully and meaningfully bridge the divide, the infrastructure of medical education, publication and funding processes must evolve to support and enhance a learning health care system

Dr. Patrick Tyler, Resident Physician: Internal Medicine
Beth Israel Deaconess Medical Center

11:45 am

Genomics: A Good Fit for Machine Learning

  • Genomics in healthcare
  • Machine learning in genomics
  • Sharing genomics information and interoperability

Gil Alterovitz, Director
Biomedical Cybernetics Laboratory

12:30 pm

Lunch Break and Networking

1:30 pm

Predicting Admissions and Emergency Visits from Time-lagged ACO-specific Data

  • The ability to predict adverse events, overcoming the 90-day billing lag
  • Identify patients who can benefit most from targeted outreach through predictions
  • The ability to identify high-risk patients when combined with targeted outreach through the Apollo CareConnect platform presents the possibility of reducing expensive admissions and improving overall patient quality

Chess Stetson, CEO
Helynx

2:15 pm

Addressing Health Challenges Through Spatial Analytics Using Geospatial Open Standards

The volume and variety of big data create a challenge when performing data processing and integration required for data analytics. Data can come from a variety of sources and in a variety of formats. The volume of data is greatly increasing due to the availability of sensors in the mass market, the development of new platforms (e.g. drones) and the growing contributions to social media platforms.

One common theme that can bring together heterogeneous sources of data to solve complex problems is “location.” For example, performing spatial analytics using air quality sensor data, health records, agriculture data, traffic density and asthma incidents can help spot patterns and predict an ideal (or non-ideal) region for a patient that suffers respiratory problems.

The use of open standards helps querying data remotely minimizing the need to download huge data sets and reusing of software instead of development software code for each source. These two benefits translate in cost reduction and a more efficient process when performing data analytics.

Dr. Luis Bermudez, Executive Director: Innovation Program
Open Geospatial Consortium

3:00 pm

Afternoon Break and Networking

3:30 pm

Patient Risk Stratification based on In-Hospital Opioid Treatment through Natural Language Processing

  • This talk discusses the need to stratify patients treated with opioids in-hospital for post-discharge risk of addiction and diversion.
  • A novel approach to risk stratification based on extracting situationally-relevant data from unstructured hospital records will be demonstrated.
  • The approach may contribute to both post-discharge point-of-care clinician decision support as well as in-hospital pain management protocols.

Dr. Wayne West, Senior Vice President and Chief Technologist
Crivella West Technologies, Inc.

4:00 pm

The GeoHealth Dashboard: A GIS Platform and Data Analytic Engine to Merge Disparate Health & Non-Health Data to Establish Geographic Regions for Total Cost of Care Containment

  • Use geographic regions to analyze populations from a healthcare cost and trend perspective
  • Reducing cost at a population level by merging health and non-health data that is correlated to healthcare outcomes

Dr. Ram Peruvemba, Chief Medical Officer
Health Solutions Research

4:30 pm

WellDoc's BlueStar - the North Star for Mobile Health IT

  • The IDEA Framework for Machine Learning in medicine
  • A risk stratification approach to determine the boundaries of AI in medical diagnosis and treatment
  • A view into the future regulatory ecosystem for mobile health IT

Anand Iyer Ph.D., Chief Strategy Officer
WellDoc

5:00 pm

Closing Remarks from the Chairman

7:30 am

Registration and Welcome Refreshments

8:45 am

Opening Remarks From The Chairman

Ajay K. Gupta, Chief Executive Officer
Health Solutions Research

The Human Element in Data-Driven Healthcare

9:00 am

Creating Value from Data Science and Algorithms in Health Care and the Life Sciences

  • Pursuing innovation and creating value in the healthcare and life sciences industry
  • Evaluating the challenges and opportunities faced by organizations in deciding how to accelerate the ability of data science to impact decision making and to pave the way to better outcomes for patients
  • Analyzing organizational culture and the different circumstances where data science can thrive as well as underperform.
  • Discussing several examples in which data science has been instrumental to improving decision making and increasing efficiency.

Nirmal Keshava, Ph.D., Sr. Principal Informatics Scientist
AstraZeneca

9:30 am

Influence is Behavior Change: Using Data to Help Others Change

  • Data is valuable for understanding what behaviors need to be changed
  • Turning data into action requires understanding principles of behavior change
  • Exploration of the structure of the human motivational system
  • Examination of specific methods for affecting the behavior of others with special attention to how data can be used to enhance these methods

Art Markman, Professor of Psychology
University of Texas at Austin

10:00 am

Identifying actionable alarms in obstructive sleep apnea patients receiving post-operative opioids

  • False positive or non-actionable alarm signals along with true alarm signals are produced by Multi-parameter monitors and other bedside medical equipment within emergency departments, intensive care and general care floors.
  • Reports published by the Association for the Advancement of Medical Instrumentation (AAMI) estimate that 90% of all alarm signals issued within ICUs are non-actionable, or false alarms.
  • Methods for discriminating actionable from non-actionable alarms involving combinatorial alarm signals show promise in areas outside of the intensive care unit in patients diagnosed with obstructive sleep apnea.

John Zaleski PhD, CAP, CPHIMS, Chief Analytics Officer
Bernoulli Enterprise

10:30 am

Morning Break and Networking

Application of Machine Learning and AI - Real Life Case Studies

10:50 am

Combating Sepsis, Cancer & Diabetes with Machine Learning

  • Translating healthcare questions to a Data Science framework
  • Applying Data Science in a healthcare context
  • Migrating from reports only to artificial intelligent

Damian Mingle, Chief Data Scientist
Intermedix

11:30 am

Machine Learning Applications in Precision Medicine: Improving Clinical Decision Support and Patient Outcomes – Success Stories and Lessons Learned

  • How machine learning and AI are now used for healthcare
  • Why is healthcare data analysis difficult, and therefore a perfect area for AI/ML
  • Case study involving a cohort of T2D patients using a ML data mining tool

Michael Nova, Chief Innovation Officer
Pathway Genomics

12:10pm

Machine Learning and Statistical Modeling with Noisy Health Care Data

Questions arise about the veracity of some of the vast amounts of data that is currently being collected, disseminated, and used in health care.  The large amount and diversity of data has received much attention. Some of the data is subject to potential quality issues including omissions, measurement errors, as well as other types of inaccuracies.  Such properties can induce uncertainties and biases in predictions and in inferences made from the data.  Focusing on examples of hospital and patient level data related to readmissions and length of stay, this talk will discuss the identification and management of data quality issues.  The problems of missing and noisy data in health care will be briefly related to similar types of problems in other fields, and the potential application of solutions from these other domains to health care data will be outlined.  Conventionally, machine learning is often used as a tool to make future predictions from data, while statistical modeling is often used to explain the data.  This talk will show examples of the joint use of machine learning and statistical modeling on complex and noisy health care data, and when inferences can, and can not, be made from such data.

Dr. Linda Zeger, Founder and Principal Consultant
Auroral

12:40 pm

Lunch Break and Networking

1:30 pm

Predictive Analytics: Harnessing Historical and Real Time Data to Improve Insight and Patient Care – Showcasing Best Practices for Optimum Results

  • A clear explanation of what machine learning is (and isn’t)
  • Specific examples and ROI from real-world implementations
  • Best practices from lessons learned working with hospitals, plans and managed care organizations

Dr. Leonard D’Avolio, Assistant Professor
Harvard Medical School and Brigham and Women's Hospital

2:15 pm

Uses and Misuses of Machine Learning in Health

  • Machine learning has enormous potential to transform medicine — but it also has the potential to automate errors and biases
  • Getting it right will require understanding what machine learning can do, and where it can go very wrong
  • Doctors and health systems must be out in front here, to catch problems early and do rapid-cycle innovation

Ziad Obermeyer, Assistant Professor of Emergency Medicine
Brigham and Women's Hospital, Harvard Medical School

3:00 pm

How the American Heart Association Precision Medicine Platform helps:

  • Overcome barriers and delays in acquiring and analyzing data
  • Promotes and facilitates the use ML and state of the art technology within the research community
  • Promotes and facilitates the sharing of code, data and knowledge within and outside of the research community
  • Connecting the research community to technologists through open forums

Larry Bradley, Vice President of Big Data Analytics
REAN Cloud
Prad Prasoon, Director - Business Strategies Emerging Technologies & Strategic Partnerships
AHA's Institute For Precision Cardiovascular Medicine
Sean Finnerty, Executive Director, Healthcare and Life Sciences
REAN Cloud
Abhiram Siripurapu, Application Development Engineer
REAN Cloud

4:00 pm

Closing Remarks from the Chairman