Using big data to assess suicide risk

A big data initiative, The Durkheim Project, has been launched to help prevent suicide among veterans. The initiative by the predictive analytics company Patterns and Predictions uses its machine learning data fabric built on technologies from Attivio and Cloudera.

Patterns and Predictions is providing technology enabling opt-in participation from more than 100,000 U.S. veterans to build a medical database that will help military mental health experts fight an alarming incidence of suicide among veterans, according to Patterns and Predictions.

Patterns and Predictions’ founder Chris Poulin has been working with Dartmouth researchers to address the problem since 2010. “The next generation of predictive analytics tools gives scientific and clinical investigators new hope and resources for solving even the most intractable problems,” says Poulin.

In 2011, Patterns and Predictions engaged big data analytics experts Attivio and Cloudera, and secured a contract with the Defense Advanced Research Projects Agency (DARPA). Staff from Patterns and Predictions, Dartmouth and the U.S. Veterans Administration conducted an investigation to validate the machine learning data fabric. Initial findings indicated the data model’s predictive accuracy was statistically significant (65 percent or more) in predicting suicidality risk among a veteran control group.

Now, having confirmed the theoretical underpinnings of the work, Patterns and Predictions is leading the second phase of the project, a tightly integrated big data initiative. Poulin says, “The promise of Durkheim lies in its ability to collect and monitor a diverse repository of complex data, with the hope of eventually providing a real-time triage of interventional actions upon detection of a critical event.” At this time, the associated medical study is authorized as observation only and non-interventional.

Durkheim’s event-driven predictions are made possible by Patterns and Predictions’ integration of its suicide risk prediction technology (including a Facebook app and mobile app for iPhone and Android) and database connections with complementary capabilities from Attivio’s unified information access platform and Cloudera’s Apache Hadoop-based software and services for the enterprise.

(Image courtesy of ShutterStock.com)