“The Durkheim Project” Will Analyze Opt-In Data From Veterans’ Social Media And Mobile Content — Seeking Real-Time Predictive Analytics for Suicide Risk

Posted on: July 2nd, 2013

(Boston, MA, White River Junction, VT & Menlo Park, CA) – “The Durkheim Project” Will Analyze Opt-In Data From Veterans’ Social Media And Mobile Content — Seeking Real-Time Predictive Analytics for Suicide Risk.

Project to Monitor Veterans’ Suicide Risk is Launched by Team Led by Patterns and Predictions, and the Veterans Education and Research Association of Northern New England, with Support from Facebook, Inc.

Patterns and Predictions, and the Veterans Education and Research Association of Northern New England, with help from Facebook, Inc., today launched a research project designed to help mental health professionals detect and monitor communications and behavioral patterns predictive of suicide risk — informed by a related study of an anonymous population of risk in U.S. veterans. Called “The Durkheim Project,”* this initiative will create a voluntary, opt-in database of participants’ social media and mobile phone data — information that eventually could provide clinicians with real-time assessments of psychological risk factors for suicide and other destructive behaviors.

The Durkheim Project’s core methodology employs a suite of applications (available on Facebook as well as for iPhone and Android devices) that automatically uploads relevant content (from online activity of veterans who have volunteered to be part of the study) into an integrated medical database. The resulting repository of text (and other mobile and social-networking data) will be continuously updated and analyzed by artificial intelligence (machine learning) systems. Durkheim’s predictive analytics applications then will provide real-time monitoring of text content and behavioral patterns statistically correlated with tendencies for harmful behaviors — such as suicide.

These often-subtle changes in a population’s aggregate psychological risk indicators would otherwise be undetectable by mental health clinicians at the scale envisioned. As a result, The Durkheim Project’s moment-to-moment findings could foster significantly improved understanding of mental health risk factors — and eventually may enhance a clinician’s ability to make timely decisions about individual mental health intervention options. (Important Note: During the study phase announced today The Durkheim Project findings will be non-interventional. That is, no official diagnoses are yet authorized for this investigation; nor are the Durkheim researchers empowered to intervene in any individual participant’s mental health situation.)

In terms of privacy, Durkheim mobile app users can opt-in (or out) for any/all social networks monitored for the study; this same opt-in functionality will apply to all other data-collection features made possible by the Durkheim app. In its initial version (beta) the application allows collected data to be seen only by an individual user and an automated statistical engine that is entirely focused on refining future algorithms for psychological risk-factor analysis. “Ensuring data security and confidentiality is essential for building and maintaining trust with our study participants,” said Chris Poulin, the Durkheim Project’s Principal Investigator.

Specific data collected will include social networking profiles such as Facebook, Twitter, and LinkedIn.  In addition, mobile information (including user location, de-identified text-messaging content, etc.) will also be stored in the Geisel School of Medicine at Dartmouth’s onsite database. Sharing personally identifiable information with external/third parties is strictly forbidden by the study’s medical protocol — and will be safeguarded by HIPAA standards of medical privacy. “We have created a secure data-storage environment behind the medical school’s IT firewall to ensure participant privacy — both during this study phase and for any future interventions that may be indicated by the insights generated here,” said Paul Thompson, study co-investigator, and an instructor at the Geisel School of Medicine at Dartmouth.  The Durkheim Project has contracted with the Geisel School of Medicine at Dartmouth to host the data, and Thompson is providing data curation.

Foundations for The Durkheim Project were established by Durkheim team members’ prior research (Phase One began in 2011 and was completed in February, 2013) on mental health in a control group of veterans. Results from that precursor investigation (led by Poulin — formerly of Dartmouth Thayer School of Engineering— in collaboration with researchers Paul Thompson, Thomas McAllister, MD, and Laura Flashman, PhD, from the Geisel School of Medicine at Dartmouth, as well as Brian Shiner, MD, and Vince Watts, MD, from the U.S. Department of Veterans Affairs), indicated that the text-mining methods employed were statistically significant (correlations of 65% or more) in predicting suicidality on an initial data set. Those findings confirmed the theoretical underpinnings of the Durkheim Project’s current inquiry, and set the stage for the broader tests now underway.

“The study we’ve begun with our research partners will build a rich knowledge base that eventually could enable timely interventions by mental health professionals,” said Poulin, who led the development of the algorithms and the mobile network that conducts predictive analytics on these diverse information inputs. In addition to the text-based signals, The Durkheim Project’s database also will incorporate internal and external risk factors (such as concussions, post-traumatic-stress, deployments served, family stresses and numerous other variables) that may contribute to the disturbingly high suicide rates among active-duty military personnel and veterans.

“As we build upon the promising findings of our Phase One investigation, the Durkheim team is pleased to have Facebook’s partnership in helping us connect with the community of veterans, as Facebook’s capability for outreach is unparalleled.” said Poulin. Joel Kaplan, Facebook’s US VP of Public Policy, himself a veteran, confirmed the strategic role in the social network’s relationship with The Durkheim Project “At Facebook, we have a unique opportunity to provide the right resources to our users in distress, when and where they need them most. We are proud to be partnering with the Department of Veterans Affairs research on the Durkheim Project, so we can bring a better understanding to this important issue and equip those that use our service with even better tools to keep them safe. Through a concerted and coordinated effort on the part of private industry, government, and concerned family and friends, we believe we can make a real difference in preventing suicide and saving lives.” Finally, “the Durkheim Project also welcomes inquiries from other potential partners who want to help reduce suicide among the military personnel who have served this nation so well,” Thompson concluded.

# # #

About The Durkheim Project

*”The Durkheim Project” Dartmouth Committee for the Protection of Human Subjects Study #23781) is a non-profit effort powered by the technology of Patterns and Predictions. The initiative was named in honor of Emile Durkheim, a pioneering sociologist whose 1897 publication of “Suicide” defined early text analysis for suicide risk and provided important theoretical explanations. The Durkheim Project is further comprised of a multi-disciplinary team of artificial intelligence and medical experts, including personnel from Dartmouth, and the U.S. Department of Veterans Affairs. Together these professionals have formed a team dedicated to applied research on suicide.  More information about the study announced today — and additional background information — can be found at The Durkheim Project website: www.durkheimproject.org

About Patterns and Predictions

Patterns and Predictions is a predictive analytics firm. Its core Centiment® technology provides unstructured and linguistics driven prediction. It is the technology powering the Durkheim Project’s ‘big data’ analytics network for the assessment of mental health risks. Partners include Bloomberg, The Geisel School of Medicine at Dartmouth, Cloudera, and Attivio. Funding sources include the U.S. Government (DARPA), and customers include Global 100 companies.

About Facebook

Founded in 2004, Facebook’s mission is to make the world more open and connected. People use Facebook to stay connected with friends and family, to discover what’s going on in the world, and to share and express what matters to them. ® Facebook is a registered trademark of Facebook, Inc.

About The Researchers

Chris Poulin is the Director of the Durkheim Project and the study’s Principal Investigator. He is also Principal Partner of Patterns and Predictions, where he is co-inventor of Centiment, a semantic-analysis based event-prediction system, with recent clients such as the U.S. Navy. Poulin also was co-author of the Patterns and Predictions software tool, a statistical classification and decision engine used worldwide in universities and industry. He was most recently Co-Director of the Dartmouth College Metalearning Working Group at Dartmouth Thayer School of Engineering. Poulin’s other research affiliations include the University of Massachusetts — in the area of high performance computing (HPC).

Paul Thompson, Study Co-Principal Investigator: Thompson is currently an instructor at the Geisel School of Medicine at Dartmouth’s Department of Genetics. He has published numerous papers, journal articles and book chapters, and has served as a reviewer for various conferences, journals, and the National Science Foundation. Thompson has worked with the Santa Fe Institute, General Motors Research & Development, The Sedona Conference and the TREC conferences.

Brian Shiner, Key Personnel: Brian Shiner MD, MPH is a board-certified psychiatrist and preventive medicine physician. He is on staff at the White River Junction VA Medical Center. He did his training at Dartmouth, where he is a faculty member. His academic interests are in operations research and in helping to promote a safe, effective, timely, efficient, patient-centered, and equitable health care system.


Funding Support/Disclaimers

This material is based upon work supported by the Defense Advance Research Project Agency (DARPA), and Space Warfare Systems Center Pacific under Contract N66001-11-4006. Also supported by, the Intelligence Advanced Research Projects Activity (IARPA) via the Department of Interior National Business Center contract number N10PC20221. The opinions, findings and conclusions or recommendations expressed in this material are those of the authors(s) and do not necessarily reflect the views of the Defense Advance Research Program Agency (DARPA), and the Space Naval Warfare Systems Center Pacific, IARPA, DOI/NBC, or the U.S. Government.