The Next Big (Data) Thing

The role of Pittsburgh’s universities, leading health system, and tech industry in creating value from data

The Pittsburgh Health Data Alliance presents

The Next Big (Data) Thing

The role of Pittsburgh’s universities, health system, and tech industry in creating value from data.


April 18, 2017

1:00 p.m. – 5:00 p.m. with reception to follow

Westin Convention Center Hotel


Opening Session

1:00 p.m.
Free Your Data and Your Health Will Follow

By working together to turn data into improved human health, the Pittsburgh Health Data Alliance (PHDA) will change the practice of medicine.  Hear how the PHDA is leveraging big data, and what the future of health care innovation holds.


This session will feature Tal Heppenstall, President, UPMC Enterprises; Farnam Jahanian, Provost and Chief Academic Officer, and Joe Marks, PhD, Executive Director of the Center for Machine Learning and Health at Carnegie Mellon University; and Michael J. Becich, MD, PhD, and Donald P. Taylor, PhD, MBA, Directors, Center for Commercial Applications of Healthcare Data, at the University of Pittsburgh.

Breakout Sessions

2:00 p.m.
Pittsburgh Health Data Alliance Project Breakout Sessions

Learn more about the work underway at the Center for Machine Learning and Health at Carnegie Mellon University and the Center for Commercial Applications of Healthcare Data at the University of Pittsburgh.  Each session will feature projects aligned with a key focus area for the PHDA.

Spatial Pathology Powers Cancer Diagnostics – SPDx: A computational cancer pathology analytics company that enhances the practice of digital pathology through the development of machine learning software tools to computationally guide decisions on diagnoses, prognoses and therapeutic treatments. SPDx provides objective and measurable spatial guidance for tissue structures and biomarker relationships that include measures of spatial patterns of cancer cells relative to stromal cells and immune cell infiltration that alters the microenvironment and therefore the responsiveness of the tumor to therapy.

Phylogenetic Models for Predicting Cancer Progression: Novel models, algorithms, and software tools to better understand the origin and evolution of tumor cells and to predict how a patient’s tumors are likely to progress.

Tumor Driver Identification – TDI: Provides personalized genomic information to cancer clinicians about the genetic drivers of an individual patient’s tumors. Tumor-specific algorithms will be used for real-time mining of genetic “big data” that will enable personalized treatments for cancer patients. TDI also is expected to lead to the discovery of new cancer drivers and may be used by pharmaceutical companies to identify novel drugs.

Encouraging Better Physician-Patient Conversations about Medical Regimens: Communicative and behavioral approaches for getting physicians and patients to better understand medication options and to improve medication adherence.

MEDIvate: Provides intelligent medication management and creates a personalized learning experience through reinforcement, data collection and monitoring for side effects, as well as providing feedback to reinforce medication adherence.

Clinical Genomics Modeling Platform: Algorithms and tools for understanding the relationship between genetic variation and medical outcomes in large populations with various diseases.

EKG Methods for Pre-and-Inhospital Recognition of NSTEMI Events (EMPIRE): A medical monitoring that measures 15 novel EKG metrics that can improve the real-time detection of non-STE ischemia.

Pressure Ulcer Monitoring Platform – PUMP: A solution aimed at reducing hospital-acquired pressure ulcers, affecting an estimated 3 million patients annually. The monitoring and alert solutions, using wearable devices and hospital bed sensors, will provide real-time documentation of patient repositioning and a process to improve compliance with these preventative measures.

Telewellness for Individuals with Disabilities and Chronic and Complex Conditions (iMHere): Allows clinicians to easily monitor and triage the needs of a large caseload of patients by providing a visual dashboard of patients’ identified needs and problems in a web-based portal, and mechanisms to respond quickly and remotely, including the ability to engage the patient in effective self‐management routines.

Health Care Trails: Health-care “trails” – the sequences in which a patient obtains services such as dialysis, bloodwork, or psychological counseling – are analyzed to identify those that generate the best outcomes in the most cost-effective manner.

A Programming Framework for Managing Patient Privacy: A framework for managing the privacy of health data by allowing privacy policies to be attached directly to the data and to be enforced systemically and automatically.

Understanding Intestinal Activity by Analyzing Gut Sounds: A non-invasive device for analyzing sounds from the intestinal tract to help physicians diagnose and monitor a variety of gastric illnesses, and to predict post-operative bowel function.

MultiSense Biomarker Discoveries: Sensing technologies for recognizing subtle changes in a patient’s facial expressions and eye-gaze patterns that are indicative of mental state and behavior.

DysphasiaDx: High-resolution accelerometers and microphones applied to the anterior throat to capture swallowing vibrations and sounds, and analyzing these signals objectively with computer-mediated methods, to make decisions about swallowing safety for patients suffering from dysphagia.

Computational Modeling of Behavioral Rhythms to Predict Readmissions: A generalizable and scalable approach that holistically looks at patients’ behavior before and after surgery, with the goal of understanding and predicting likely readmissions.

Fall Sentinel: Automated system for clinical pharmacists to continuously monitor patients in nursing homes, especially for potential drug combinations that increase fall risk.

Surgical Risk Analysis Index: Intersecting novel clinical data and algorithms to help stratify patients based on their risk of adverse events following surgical procedures.

Closing Session

4:00 p.m.
Pittsburgh: The Nation’s Beta Site
How Pittsburgh Became a Proving Ground for Innovation in Meds, Eds, and Tech

From Uber’s self-driving car, to cutting edge research from Carnegie Mellon University and the University of Pittsburgh, to UPMC’s patient-focused analytics, Pittsburgh has firmly established its reputation as a technology hub.  Learn how the city is uniquely positioned to address the challenges of big data.  Moderated by Bob Evans, former Oracle Chief Communications Officer and veteran technology journalist, the session will explore how Pittsburgh has transformed its city.


Moderator Bob Evans helps companies grow by creating and executing world-class communications strategy and programs that amplify the CEO’s and CMO’s vision. He was recruited by Larry Ellison to do this at Oracle where he was SVP and Chief Communications Officer, and before that by Bill McDermott at SAP as VP of strategic communications. Those corporate positions followed an extensive career in business media as an editor-in-chief, columnist, analyst, and chief content officer.

Adam Berger, PhD, is the Executive Vice President and Chief Technology Officer of UPMC Enterprises. As CTO, Adam oversees the technology development supporting UPMC’s new business development and investment activities. He also manages the architecture, engineering, and client services teams on projects across all Enterprises’ focus areas: translational science, improving outcomes, consumer-centric health care, and business services and infrastructure.  Adam’s expertise lies at the intersection of technology strategy, product development, and intellectual property. He is both a technology executive and a computer scientist who has founded and grown two companies, as well as working at Nokia and IBM.


Harvey Borovetz, PhD, MS, is distinguished professor and former chair (2002-2013) in the Department of Bioengineering, Swanson School of Engineering at the University of Pittsburgh and the Robert L. Hardesty Professor in the Department of Surgery, University of Pittsburgh School of Medicine.  Dr. Borovetz’s current research interests are focused on the design and clinical utilization of cardiovascular organ replacements for both adult and pediatric patients. Since 1986, Borovetz has served as the academic liaison for the University’s Clinical Bioengineering Program in Mechanical Circulatory Support. This program supports patients who are implanted with a left ventricular assist device, or bi-ventricular assist devices, as a bridge to cardiac transplantation or bridge to recovery. This work in mechanical circulatory support follows Dr. Borovetz’s early efforts in which he helped cardiac surgeons apply extracorporeal membrane oxygenation (ECMO) to treat successfully a large series of neonates in respiratory distress.

Andrew W. Moore, PhD, a distinguished computer scientist with expertise in machine learning and robotics, became dean of the Carnegie Mellon University School of Computer Science in August 2014. He had previously served as a professor of computer science and robotics before taking a leave of absence to become founding director of Google’s Pittsburgh engineering office in 2006.  Moore’s research interests broadly encompass the field of “big data” – applying statistical methods and mathematical formulas to massive quantities of information, ranging from Web searches to astronomy to medical records, in order to identify patterns and extract meaning from that information.

SCS, Dean, Andrew Moore, August 27 2014

Jeff Schneider, PhD, is the engineering lead for machine learning at Uber’s Advanced Technologies Center.  He is currently on leave from Carnegie Mellon University where he is a research professor in the school of computer science.  He has 20 years experience developing, publishing, and applying machine learning algorithms in government, science, and industry. He has over 100 publications and regularly gives talks and tutorials on the subject.

Luis von Ahn, PhD is an entrepreneur and computer science professor at Carnegie Mellon University who is considered one of the pioneers of crowdsourcing. He is known for co-inventing CAPTCHAs, being a MacArthur Fellow and selling two companies to Google in his 20s. He is currently the co-founder and CEO of Duolingo, a language-learning platform created to bring free language education to the world. With over 170 million users, it is now the most popular language-learning platform and the most downloaded app in the Education category worldwide on both iTunes and Google Play.  Luis has been named one of the 10 Most Brilliant Scientists by Popular Science Magazine, one of the 50 Best Brains in Science by Discover, one of the Top Young Innovators Under 35 by MIT Technology Review, and one of the 100 Most Innovative People in Business by Fast Company Magazine.

Luis von Ahn

Please join us for a reception following our Closing Session. Investigators and researchers of the Pittsburgh Health Data Alliance will be on-hand for additional conversation.