Patterns and Predictions Develops AI Applications in Clinical Practice with Cloudera, Elicits Congressional Support
Washington, D.C., November 11, 2015 — In commemoration of Veterans Day, a new initiative seeks to reduce the suicide crisis (as many as 22 per day) among American veterans. Patterns and Predictions, a predictive analytics firm whose Predictus® technology provides unstructured and linguistics driven prediction, and Cloudera, the global provider of the fastest, easiest, and most secure data management and analytics platform built on the latest open source technologies, announced today the collaborative development of an artificial intelligence (AI) solution that predicts mental health risk through opt-in analysis of social media and mobile text.
The primary goal of this solution is to identify indicators of suicidality, particularly among veterans, so that preventative action can be taken to save those at risk. The basis for the AI solution was recently documented in the book “Artificial Intelligence in Behavioral and Mental Health Care, 1st Edition,” officially announced here: http://scitechconnect.elsevier.com/artificial-intelligence-mental-health-care/
Patterns and Predictions has now teamed with Cloudera to build a second generation AI solution that leverages predictive analytics on the Hadoop ecosystem of big data technologies. The solution represents an extension of previous collaborations between the two organizations as part of The Durkheim Project, a DARPA-funded research program that ran from 2011 to 2015 and demonstrated the capability of big data technologies to effectively detect suicide risk at Internet scale. The Durkheim Project and its results are chronicled in the aforementioned book.
The research has also received Congressional support to aid in the veteran suicide crisis. On October 8, 2015, the House Armed Services Committee's Subcommittee on Military Personnel held hearings whose testimony illustrated that suicide among military veterans remains a persistent problem, despite the deployment of numerous traditional medical approaches. “Based on this testimony, there is a persistent statistical reality that the Department of Defense (DoD) needs a more aggressive approach, using emerging technologies that have proved efficacious — both in terms of suicide intervention and mental health issues more generally,” said Chris Poulin, principal of Patterns and Predictions, former principal investigator for The Durkheim Project, and lead author of the Public Health Surveillance: Predictive Analytics and Big Data chapter in the aforementioned book.
In further response to the testimony, on October 22, 2015, Rep. Duncan Hunter (R-CA) issued an urgent letter calling on Secretary of Defense Ashton Carter to bolster the DoD’s core strategies for suicide risk reduction among veterans, arguing that veterans would be better protected with a national strategy “…which would provide a more accurate indicator of at-risk service members and allow for successful intervention and treatment.” In particular, he advocated for the use of artificial intelligence technology (citing The Durkheim Project research) which was proven more effective than traditional medical methods in health monitoring and suicidality risk detection among at-risk veterans. Hunter, a veteran of Iraq and Afghanistan, is a member of the House Armed Services Committee, whose Subcommittee on Military Personnel held the October 8 hearings on DoD suicide.
Poulin noted, “We deeply appreciate Congressman Hunter’s recognition for what we accomplished under our research program, as well as what we continue to develop.”
America’s active duty and veteran soldiers are still facing challenging mental health issues. Therefore, Poulin’s team is now proposing an end-to-end national strategy. The new system will incorporate both recent technological advances and integration with medical resources. He outlined four essential aspects for an effective program to reduce suicide among soldiers and veterans:
1. Outreach: Engage hundreds of thousands of soldiers and veterans (rather than the small, isolated pilot programs currently in place).
2. Digital Risk Assessment: Use state-of-the-art data mining to isolate mental health risk factors for participating soldiers and veterans.
3. Resource Allocation: Maximize available resources — through enabling interventions by both medical professionals and peers.
4. Effective Intervention: Both quantify and qualify the efficacy of risk remediation efforts.
Bill Boykin, a veteran and former submarine commander, stated, "I am truly excited to see that the technology exists to predict suicidal tendencies in our service members and veterans. This analysis will make a tremendous difference in a commander’s ability to plan for his operations, and to help his personnel face the difficulties of extended deployment and combat."
"On Veterans Day and every day, it is important to honor America's veterans for their patriotism and willingness to serve our country. We need to take care of our veterans, and Cloudera is humbled by the opportunity to contribute to this innovative work, in hopes that our combined technology has real potential to save lives," said Tom Reilly, CEO, Cloudera. "This is a tremendous program, and one we'd love to see expand to a nationwide scope."
Further announcements on an official release date are planned.
About Patterns and Predictions™
Patterns and Predictions (P&P) analyzes social, mobile, and linguistics data – in real time – to assess behaviors, such as mental health risk. Specifically, P&P is a predictive analytics firm with a core technology (Predictus®) that provides unstructured and linguistics driven prediction. Chris Poulin is Principal Partner of the firm. He recently served as Director of The Durkheim Project, a non-profit big data collaboration with the U.S. Department of Veterans Affairs and Facebook, Inc. Poulin also was Co-Director of the Dartmouth Metalearning Working Group at Dartmouth College, focused on large-scale machine learning. He has lectured on Artificial Intelligence and Big Data at the U.S. Naval War College, and is co-author of an upcoming book on Artificial Intelligence in Mental Health. Additional background information — can be found at: www.patternsandpredictions.com
Cloudera delivers the modern data management and analytics platform built on Apache Hadoop and the latest open source technologies. The world’s leading organizations trust Cloudera to help solve their most challenging business problems with Cloudera Enterprise, the fastest, easiest and most secure data platform available for the modern world. Our customers efficiently capture, store, process and analyze vast amounts of data, empowering them to use advanced analytics to drive business decisions quickly, flexibly and at lower cost than has been possible before. To ensure our customers are successful, we offer comprehensive support, training and professional services. Learn more at https://cloudera.com.
About The Durkheim Project
“The Durkheim Project” was a non-profit research effort running from late 2011-early 2015. This 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. Funded by DARPA, The Durkheim Project was comprised of a multi-disciplinary team of artificial intelligence and medical experts from Geisel School of Medicine at Dartmouth, the U.S. Department of Veterans Affairs, and Cloudera, Inc. Together these professionals have formed a team dedicated to applied research on suicide. Historical information about the study — can be found at The Durkheim Project website: www.durkheimproject.org
About Representative Duncan Hunter (R-CA)
Congressman Duncan D. Hunter represents California's 50th Congressional District consisting of East and Northern County San Diego. In 2008, Hunter was elected to his first term in the House of Representatives, succeeding his father, Duncan L. Hunter, who retired after serving 14 consecutive terms in Congress. Hunter is a native of San Diego. He graduated from Granite Hills High School in El Cajon and earned a degree in Business Administration from San Diego State University. Hunter worked to pay for his education by creating websites and programming databases and ecommerce systems for high-tech companies. Immediately after graduation, he went to work full time in San Diego as a Business Analyst. Soon after our nation was attacked on September 11, 2001, Hunter quit his job and joined the United States Marine Corps. Hunter entered active service as a Lieutenant in 2002 and excelled in the area of field artillery, much like his grandfather, Robert O. Hunter, who was a Marine Corps artillery officer in World War II. Over the course of his service career, Hunter served three combat tours overseas: two in Iraq and one in Afghanistan. In 2003, Hunter deployed to Iraq with the 1st Marine Division. Hunter completed his second tour in 2004, where he and his fellow Marines were at the center of combat operations in Fallujah, Iraq. In September 2005, four years after he quit his job and joined the Marine Corps, Hunter was honorably discharged from active military service and started a successful residential development company. Still a Marine Reservist, he was promoted to the rank of Captain in 2006, and to the rank of Major in 2012. Less than two years before Hunter was elected, he was recalled to active duty and deployed to Afghanistan. Hunter returned home after more than six months on the front lines and, with the support of the San Diego community, became the first Marine combat veteran of the wars in Iraq and Afghanistan elected to Congress. Hunter is a strong conservative who is committed to strengthening national security, enforcing our borders, creating opportunities for American workers and protecting the interests of taxpayers. He is also a strong proponent of the Second Amendment, protecting traditional marriage and the rights of the unborn. Congressman Hunter and his wife live in Alpine, California. They are the proud parents of three children: Duncan, Elizabeth and Sarah.
1 Luxton, David D. “Artificial Intelligence in Behavioral and Mental Health Care.” October 2015.
Elsevier Publishing. https://store.elsevier.com/Artificial-Intelligence-in-Behavioral-and-Mental-Health-Care/isbn-9780124202481/