Hadoop-Based Data Exploration for the Healthcare Safety Net—Technical and Sociocultural Challenges to Big Data Usability

MIT SDM Systems Thinking Webinar SeriesDavid Hartzband

David Hartzband, D.Sc., Research Affiliate, MIT Sociotechnical Systems Research Center

Date: April 6, 2015

Time: Noon — 1 p.m. EDT

Free and open to all

Download the presentation slides


About the Presentation

The concept of mining large, heterogeneous data sets (“big data”) to improve clinical outcomes and operational processes holds great promise for the healthcare industry. However, analytics have so far been underutilized by an essential component of the healthcare safety net—community health centers (CHCs), critical access hospitals, rural hospitals, and clinics. A look at the systemic reasons behind this lag offers useful lessons not only for healthcare, but also for many other industries.

In this webinar, David Hartzband, D.Sc., will outline a nonprofit-funded project designed to introduce Hadoop-based analytics into three CHCs and report preliminary results regarding data usability. Focusing on one clinical data set that goes back to 2009 and contains about 1 million diagnosis events, he will describe common challenges, including:

  • Accurately determining the annual number of patients served;
  • Addressing data quality idiosyncrasies, such as the mismatch of specific diagnosis codes with descriptions;
  • Tackling the substantial misalignment of clinical and financial data, which can make cost analysis impossible.

Data anomalies will be presented in the context of a large-scale cost/patient analysis, and the implications of these data anomalies will be discussed. Webinar attendees will gain insight into how to apply Hadoop-based analysis to a wide range of challenges in virtually any field.

A Q&A will follow the presentation. We invite you to join us!

About the Speaker

David Hartzband, D.Sc., is a research affiliate of the MIT Sociotechnical Systems Research Center. After a 25+-year career designing and developing software technologies—during which time he twice created billion-dollar revenue streams with products that he designed—he left industry to concentrate on healthcare information technology (HIT).

In the last 10 years, he has worked on the architecture of several of the largest health information exchanges in the country, designing and leading development of both practice management and electronic health records systems. In addition, he has consulted with many HIT companies, especially startups.

Hartzband recently served as principal investigator for a Department of Commerce/National Institute of Standards and Technology grant on providing trusted identities in cyberspace through the National Strategy for Trusted Identities in Cyberspace program, a White House initiative. He has also served as co-principal investigator for a Department of Health and Human Services project researching the use of electronic records to provide combined records for medical and behavioral health treatment. He continues to consult with several national groups working on healthcare transformation.

About the Series

The MIT System Design and Management Program Systems Thinking Webinar Series features research conducted by SDM faculty, alumni, students, and industry partners. The series is designed to disseminate information on how to employ systems thinking to address engineering, management, and socio-political components of complex challenges.