Applied AI in Healthcare | A Data Discovery Discussion


Details
A panel of local leading AI + Healthcare innovators will share their AI application experiences and focus. Particular attention will be paid to the data resources they are using to build their models. How were the data sets located, acquired, validated and subsequently augmented.
Register for FREE by Friday July 20th; $15 thereafter and at door
*******************************************************************
AGENDA
5:30PM to 6:00PM – Networking
6:00PM to 7:00PM – Individual Presentations
> Alex Leow - Biaffect
> Mark Albert _ Loyola University
> Sasha Gutfraind - Blue Health Intelligence
7:00PM to 7:45PM - Panel data discovery discussion
> Khan Siddiqui of Higi will moderate
> features all three speakers above, focusing on better understanding the data that drives AI
7:45PM to 8:30PM- Networking
MODERATOR ************************************************
KHAN M. SIDDIQUI, MD Co-Founder, Chief Technology Officer, Chief Medical Officer, higi
Dr. Khan Siddiqui is a serial entrepreneur and currently CTO and CMO of higi, a consumer centric health engagement company, uses a combination of interactive and social tools to help consumers to take small but meaningful engagement steps in their health and wellness to create lasting habits. higi has built the largest self-service health kiosk network in the US where 78% of US population lives within 5 miles of a higi station.
Prior to higi, Dr. Siddiqui was a Physician Executive and Principal Program Manager at Microsoft responsible for platform engineering for the health solutions group. One of his key achievements at Microsoft was stimulating computer vision and deep learning research that led to the development of classification forest algorithms, which are the foundation technology in Xbox Kinect. A widely respected healthcare and technology expert focusing on deep learning, persuasive technologies in healthcare, Dr. Siddiqui is also a visiting Associate Professor at John Hopkins University School of Medicine.
SPEAKERS **************************************************
ALEX LEOW
Associate Professor in Psychiatry and Bioengineering, University of Illinois, College of Medicine.
Co-Director, the Collaborative Neuroimaging Environment for Connectomics (CoNECt)
Attending physician, University of Illinois Hospital
Codirector, the BiAffect study (Biaffect.com), the first researchkit study to understand mood and cognition in bipolar disorder using iphones
A rare physician-mathematician, Alex Leow is an Associate Professor at the University of Illinois College of Medicine and cofounder of the Collaborative Neuroimaging Environment for Connectomics (CoNECt) (brain.uic.edu), an inter-departmental research team devoted to the study of the human brain using multidisciplinary approaches . She is the lead of the award- winning BiAffect study (first prize, the Mood Challenge for ResearchKit). BiAffect is the first scientific study that seeks to turn smartphones into “brain fitness trackers”, by unobtrusively inferring neuropsychological functioning using passively-collected keystroke dynamics and kinematics metadata (i.e., not what you type but how you type it). The BiAffect team was the first to publish scientific studies that demonstrated the feasibility of leveraging keystroke dynamics and kinematics, and the BiAffect study iOS app now powers the first-ever crowd- sourced research study to unobtrusively measure mood and cognition in real-time in Bipolar Disorder using iPhones. The study app is publicly available on the App Store and as of July 2018 more than 5500 hours of typing dynamics have been recorded.
MARK V ALBERT
Assistant Professor of Computer Science at Loyola University Chicago
Directing the Pervasive and Ambient Computing (PAC) lab and the Theoretical Neuroscience Lab
Dr. Albert is a postdoctoral research associate at the Rehabilitation Institute of Chicago and Northwestern University. His current research applies machine learning to automatically interpret data collected from remote sensors carried by patients, including the accelerometers in their mobile phones. He has published a number of papers measuring motor adaptation, detecting falls, and recognizing patient activities.
Prior to Chicago, he received his Ph.D. in computational biology from Cornell University, with an emphasis on applying efficient coding principles to computational neuroscience. While a graduate student there, he was also part of the mobile phone-based startup company Instinctiv. Before Cornell, as research assistant at Carnegie Mellon University, he applied computational models to cognition through human fMRI experiments and to vision in primate neurophysiology. He is a Fulbright Scholar from the University of Vienna and a graduate from Pittsburgh State University.
SASHA GUTFRAIND Senior Healthcare Data Scientist at Blue Health Intelligence Data strategist with in-depth knowledge of Healthcare and over 10 years of experience in hands-on data science and analytics. Author of six patents in analytics and over 30 studies; mentor, team player and passionate leader. My core competencies are in R, Python, Java, Machine learning, Big data, Healthcare, Optimization, Risk analysis, Operations research, Simulation, Dynamic modeling, Networks analytics, Web development, Leadership, and Business development.
MORE PROGRAM BACKGROUND **************************************
The desire to personalize medicine and the proliferation of data aided diagnosis and treatment paths has opened up many disparate, yet sometimes related views of a patient’s well-being.
From the motion vectors of the physical body, to brain area activation tracking and analysis of the genetic material we are all made of; the onslaught on new patient generated data sets is relentless. This adds to the volumes of standardized clinical and pharmaceutical data available. Insurance claim and provider cost data are also increasingly utilized in the move towards outcome based healthcare. Navigating and making use of all these resources is not a trivial challenge.
More case specific data sets are being created within individual AI applications. In conjunction with these other data sets there are hypothetically more combinations of ways to further optimize an AI solution and ultimately patient outcomes.
Yet accessing and reconciling publicly available health data against the proprietary data streams and findings of one discreet healthcare AI application can be a challenge. Often there are barriers in gaining access to other relevant, actionable data. And then there is the use non-standardized clinical data, which AI practitioners are now finding ways to tap.
This program will take a look at this modern day data challenge through the eyes of a panel of AI practitioners, each focused on a different domain of patient data. We will explore common or complimentary use of data sets between the applications, as well as how each use of commonly accessible healthcare data resources. This discussion will look at how they can be combined to gain a more holistic view of overall patient health.

Applied AI in Healthcare | A Data Discovery Discussion