Loading…
This event has ended. Visit the official site or create your own event on Sched.

Log in to bookmark your favorites and sync them to your phone or calendar.

4 - Mostly Technical [clear filter]
Friday, October 6
 

9:15am

From Genomics to Personalized Healthcare
With the advent of Next Generation Sequencing (NGS) technologies that have significantly reduced the cost and time required to sequence human genomes, personalized healthcare is becoming a reality.  Genomic information is increasingly an important determinant of clinical diagnosis and treatment. A bioinformatics challenge central to personalized healthcare is to identify the associations between genotypic and phenotypic observations.  Several analytics approaches will be discussed in the presentation.

Speakers
avatar for Kathy Tzeng, PhD

Kathy Tzeng, PhD

Distinguished Engineer, Optum Technology (NY)


Friday October 6, 2017 9:15am - 10:00am
Room 7 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

9:15am

Natural Networks: A New Way to Design and Manage Provider Networks

There is evidence that when providers collaborate in the care of patients they achieve both better cost and better quality outcomes.  Currently there are no tools available to identify and leverage existing collaboration among providers to deliver greater value to health plan members through lower costs and/or better quality. With Natural Networks™, we aim to change that. 

Learn how we are applying graph analytics to identify existing clusters of provider collaboration and evaluate their performance to help inform provider network design (whether for the increasing trend towards high performance networks (HPNs), or next generation accountable care organizations (ACOs)) and network management (whether by designing centers of excellence (CoEs), or helping identify best practice).


Speakers
avatar for Sanji Fernando

Sanji Fernando

Vice President, OptumLabs Center for Applied Data Science, OptumLabs


Friday October 6, 2017 9:15am - 10:00am
Room 1, 2 & 3 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

10:15am

Patient-Generated Data and Precision Medicine
Data science is rapidly growing in many industries, including healthcare. However, the amount of healthcare information available for longitudinal research is often relatively small, with only sporadic data being available for any single patient. For example, information within the electronic health record (EHR) is typically obtained at large time intervals (usually hours or days), and nearly no data are captured from patients between healthcare encounters.

In this session, Dr. Schulz will describe the benefits of incorporating patient-generated data into clinical care and translational research. He will also describe how other large data sets can be combined with this information to advance precision medicine. From a technical perspective, this session will describe how Yale New Haven Health has worked to collect patient-generated data and integrate provider-generated data, such as genomics and continuous patient monitoring, into their data science platform.

Speakers
avatar for Wade Schulz, MD,PhD

Wade Schulz, MD,PhD

Clinical Fellow, Senior Solution Architect, Yale


Friday October 6, 2017 10:15am - 11:00am
Room 4 & 5 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

11:15am

Analyzing the Patient Care Continuum: 99M patients, Hadoop and Spotfire
Managing patient outcomes is becoming business critical for care providers, payers and the medtech industry. Registries are difficult and expensive to build but needed for true patient reported outcomes analysis. Before large investments are made we need to analyze a proxy of the opportunity to see if it makes sense to build these. This presentation will cover using deidentified complete longitudinal patient  data on 99 million patients over the course of 8 years, leveraging Hadoop for storage, Impala for querying and Spotfire for advanced slice and dice reporting. This process allows queries to go from many hours of processing to minutes and democratizes data and analytics.

Speakers
avatar for Shihe Ma, MS, MBA

Shihe Ma, MS, MBA

Senior Database Marketing Manager, Medtronic


Friday October 6, 2017 11:15am - 12:00pm
Room 4 & 5 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

11:15am

EHR in Medical Research, From a Tower of Babel to Coherent Real World Evidence
Data scientists and technologies have made notable progress towards overcoming the initial barriers to utilizing electronic medical record (EMR) data for the purposes of medical research.  However, inherent features of EMR data provide further hurdles for researchers attempting to draw valid inferences. This presentation will describe barriers and solutions to generating coherent real world evidence from EMR data with an applied example assessing cardiovascular risks associated with hypoglycemia. 

The discussion will focus on epidemiological methods to address ambiguous observation periods (duration and completeness of data), algorithm building (including special considerations for natural language processing of the free text clinical notes), and quantitative analysis (including analytic considerations for bias and confounding).

Speakers
avatar for Tony Nunes, PhD

Tony Nunes, PhD

Epidemiologist, Optum Analytics


Friday October 6, 2017 11:15am - 12:00pm
Room 7 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

11:15am

Innovation Networks and Regional Competitiveness in Med Tech / Biotech
Human capital is a critical resource in advanced technology. The ability of a region to compete on a global scale is dependent on a highly skilled labor supply. Innovation networks are a "force multiplier" for converting technical expertise into enterprise value. We can identify and quantify innovation networks using graph theory.

In this session, we'll use patent analytics to evaluate collaborative innovation in the U.S. med tech / biotech space from a regional perspective. Regional planners and economic developers can use this perspective to promote and improve regional competitiveness. Corporate planners and leaders can apply this perspective at the enterprise level to improve performance and increase enterprise value.

As a related concept, we'll explore the relevance of this approach for the Amazon site search that is currently challenging regional planners across the continent to differentiate the potential value of their locations.

Speakers
avatar for David Quimby

David Quimby

Principal, Innovation Radiation
I am a mathematical economist and systems analyst. I have rotated through various cycles at the extremes of large enterprise and small enterprise as a technology executive and a software entrepreneur. My expertise includes knowledge management, technological forecasting, and systematic... Read More →


Friday October 6, 2017 11:15am - 12:00pm
Room 8 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

1:15pm

The Science of Sweet Dreams: Predicting Sleep Efficiency from Wearable Device Data

Sleep research is a translational science field, and can greatly benefit from improved computational technologies.  Automated, robust, interpretable, and high-fidelity models are vital to its success. The pervasive adoption of wearable devices provides a unique opportunity.  Wearable devices monitor a user for an extended period of time and can generate a large amount of data. The current sleep analysis processes are manual and unable to scale, creating a bottleneck for sleep research. Automation allows for immediate analysis on large-scale clinical trials, and provides a platform for affordable widespread population screening of sleep disorders. Particularly for population screening, it is critical that the methods and knowledge extracted are generalizable and thus robust to noise and variance amongst sub-populations.  For example, teenagers follow very different sleep patterns compared to the elderly. Moreover, sleep experts use software tools such as ActiLife to manually annotate datasets.  This leaves the data interpretation prone to human error.

This talk presents a translational science approach to human health through sleep analysis, creating novel state-of-the-art computer science algorithms to empower clinicians and patients alike. We introduce the basics of sleep science, highlighting the computing challenges in the field, and proposing computational solutions to improve the sleep science process. By providing tools for sleep and activity behavior analysis, clinical decision- makers can deliver improved and informed healthcare.  Moreover, this research also empowers patients from a quantified-self perspective, by conveying real-time recommendations to optimize productivity and improve quality of life.


Speakers
avatar for Jaideep Srivastava

Jaideep Srivastava

Professor, University of Minnesota CSE
Jaideep Srivastava is Professor of Computer Science at the University of Minnesota, where he directs a laboratory focusing on research in Web Mining, Social Analytics, and Health Analytics. He is a Fellow of the Institute of Electrical and Electronics Engineers (IEEE), has been an... Read More →


Friday October 6, 2017 1:15pm - 2:00pm
Room 4 & 5 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

2:15pm

Utilizing Electronic Health Record for Genetic Research
Geisinger Health system (GHS) is an integrated health care provider located in central and northeastern PA with an established electronic health record (EHR) that captures a median of 14 years of health data. The Geisinger MyCode® initiative started in 2007 as a system-wide biobanking program. Through a collaboration with the Regeneron Genetic Center (the Geisinger-Regeneron DiscovEHR collaboration,) whole exome sequence and genome wide genotype data is available from more than 90,000 MyCode® participants. The integration of genomic and EHR data provides an ideal platform for precision health. Analysis from 50,000 sequenced participants identified more than 4 million rare single nucleotide variants and insertion-deletion events, of which over 176,000 are predicted to result in loss of gene function.

To promote collaboration, we developed an open-access DiscovEHR web browser accessable through discovehrshare.com.  In this browser, variant frequency data is made publicly available to enable allele frequency comparisons with other population-based and biobank resources. In 2015 the MyCode DNA repository became CLIA certified, thus allowing samples to be used for clinical testing. We have also deposited CLIA-confirmed rare variants with clinical relevance from our “Geisinger-76” based on the ACMG 56 genes with additional 20 genes selected by Geisinger as clinically actionable. To date, 4.4% of MyCode participants harbor deleterious variants in these 76 genes and we have begun to return the results to more than 180 of our patients. In conclusion, The GHS MyCode project has created a unique biorepository that enables precision medicine research. For this presentation, I will also present some of the projects currently ongoing in my lab.

Speakers
avatar for Mike Lee, PhD

Mike Lee, PhD

Assoc. Professor & Director, Geisinger Biobank


Friday October 6, 2017 2:15pm - 3:00pm
Room 6 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

3:15pm

Building a Scalable Data Science System for Neuroscience and Device Research
In this presentation, I introduce the four main neuromodulation therapies that our program supports, describe the spectrum of value that data science can add to the medical device industry, and then dive into our analysis infrastructure and work using data sensed from the brain’s electrical rhythms.  I end by highlighting work with the Mayo Clinic as part of an NIH BRAIN Initiative grant, which combines remote data collection from animals (IoT), cloud, and Hadoop into a remote device monitoring platform for research and engineering.

Speakers
avatar for Jadin Jackson, PhD

Jadin Jackson, PhD

Sr. Engineering Manager, Medtronic


Friday October 6, 2017 3:15pm - 4:00pm
Room 8 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

3:15pm

Real-time patient monitoring and situational awareness in the ICU
Architecture for real-time monitoring and situational awareness of 100+ patients across multiple ICUs, challenges of building and deploying real-time analytics algorithms and machine learning models, and clinical and business aspects

Speakers
avatar for Sharath Cholleti, PhD

Sharath Cholleti, PhD

Chief Technology Officer, CleMetric


Friday October 6, 2017 3:15pm - 4:00pm
Room 7 Optum, 13625 Technology Drive, Eden Prairie, MN, United States

3:15pm

Two Use-cases and a Summary: AI in Health for Diabetes and Communicable Disease
A surge in health care data, including electronic health records and medical sensor data, is providing new opportunities to uncover data-driven insights and patterns of disease using machine learning techniques. Sanjay Joshi and Karen Hayrapetyan will present a summary of AI in Health and two separate use cases that could reduce cost and increase care.

The first use case is predicting diabetes hospital readmissions using H2O's gradient boosted trees using the diabetes dataset from 130 US hospitals For the second use case we present a geo-spatial forecasting system for seasonal communicable disease that has the potential to aid public health planning and help reduce the impact of outbreaks, specifically for time-series forecasts of Influenza-like illness (ILI) encounters at county and zip-code levels with increased performance compared to conventional systems that predict ILI incidents at isolated spatial scales

Speakers
avatar for Karen Hayrapetyan

Karen Hayrapetyan

Senior Data Scientist, H2O.ai
Karen Hayrapetyan is a senior data scientist at H2O.ai. Karen works with H2O.ai customers to derive substantive business value from machine learning technologies. Prior to joining H2o.ai, he spent three years at startups working on growth and analytics problems. He holds a Ph.D. in... Read More →
avatar for Sanjay Joshi

Sanjay Joshi

Chief of Technology, Healthcare and Life Sciences, H2O.ai
Sanjay Joshi is the Chief of Technology, Healthcare and Life Sciences at H2O.ai. Based in Seattle, Sanjay's 25+ year career has spanned the entire gamut of life-sciences and healthcare from clinical and biotechnology research to healthcare informatics to medical devices to IT infrastructures... Read More →

Sponsors

Friday October 6, 2017 3:15pm - 4:00pm
Room 1, 2 & 3 Optum, 13625 Technology Drive, Eden Prairie, MN, United States