Follow me

Collaboration with Zenti Brings a New Way to Identify Vets in Trouble
November 8, 2016|Life

Collaboration with Zenti Brings a New Way to Identify Vets in Trouble

Collaboration with Zenti Brings a New Way to Identify Vets in Trouble

Article Originally Published on, Read Full Article HERE


Sometimes you just have to marvel at the way things come together. Take the case of the National Veterans Foundation’s partnering with Zenti, Inc. and Dr. Joe Franklin. Three separate entities embarked on an exciting project to identify veterans at risk of suicide through public social media content. You know the statistics…from 22-25 veteran suicides a day, we’re now at 20. Early detection and intervention are still the most successful means of suicide prevention, but identifying the symptoms and providing timely outreach remain an ongoing challenge. We’re working together on a tool to identify and intervene well before a vet makes that last phone call to a friend, family member or a crisis hotline.

Zenti's Kieren Prior, NVF Board President Frank Spady, and Steve Cracknell

Kieren Prior, NVF Board President Frank Spady, and Steve Cracknell with their “Stop 22” Veteran Suicide Prevention signs.

Time to meet the players: Steve Cracknell and Kieran Prior are, respectively, the CEO and CSO of Zenti, Inc., a software development company. Cracknell, whose career started out in marketing and advertising, emigrated from South Africa to England in 2001. Having also studied Finance at business school, he wanted a change and he found a position with a large financial company where he cut his teeth in financial technology software. He started out in Strategies, working with, as he tells it, “All PhD’s in math and science and me, Steve the Marketing Dude.”

While initially he felt out of place, he soon found his niche helping a department that was struggling to get workers to adopt the new and improved version of their internal proprietary software. “It wasn’t going well – no one wanted to use the new tool the company had spent millions of dollars developing and somehow I got the job of finding out why.” Steve went to the users and asked them about the software, listened to their complaints, and asked what they’d like to see. Then he took that information back to the IT developers. Simple. “I don’t answer the HOW it should be done. I answer the WHAT do you want…to get the result.” It’s a method that’s served him well.

Prior grew up outside Manchester, England, the son of a butcher. At eighteen months old, when he still couldn’t walk, he was diagnosed with dystonia, a neurological movement disorder. His parents re-designed their home to accommodate their son’s disability. It wasn’t until Kieran was ten or eleven that they recognized his extraordinary intelligence. By fifteen, Kieran realized that in order for him to live independently, he’d need a career that would allow him to afford full-time care. He chose finance and trading because it was based on mental capabilities, not physical, and because it could be lucrative. On his graduation from Manchester University, he applied to only one place, the firm he considered to be the top. He was the first disabled person interviewed for a trading role and basically every partner in the firm interviewed him. He got the job.

And that’s where he met Steve Cracknell. They collaborated on a product and became fast friends, then later went into business together. That was ten years ago. Steve says, “All the stuff we’ve built started with just an idea. Anything’s possible if you put your mind to it.” They’ve developed software to process language statistically as data, and applied it to detecting people on social media at risk for suicide. Because it’s statistical, processing it is faster. After processing, the data is scored. When applied in the context of processing and understanding human intent and emotion, this methodology proved to be incredibly effective. In this application, “the people most likely to hurt themselves have the largest score. Efficient use of time,” Cracknell says. And that efficiency is what will let us reach out to those vets sooner.

Dr. Joe Franklin is the director of the technology and psychopathology lab (TAP lab) at Florida State University. The TAP lab’s mission is “to ignite large-scale reductions in mental illness by harmonizing advances in technology with advances in psychology.” No stranger to veterans’ issues, Franklin was the co-investigator for the Military Suicide Research Consortium Grant from the US Department of Defense in 2015 – 2016. In 2016, he was named a Rising Star by the Association for Psychological Science. Joe’s work has been supported by the National Institutes of Mental Health, the U.S. Department of Defense, and the American Foundation for Suicide Prevention, among others. We’re delighted that Dr. Franklin joined our Advisory Board this year.

Zenti and Dr. Franklin worked together to create statistical classifiers based on keywords and phrases in public social media content that could indicate suicidal ideation. The unique software allows a subject matter expert to easily create and train their own classifier to identify content of interest.

The National Veterans Foundation was a natural partner for Zenti. Our Lifeline for Vets staff continues to help train the software to look for those language signals. Even during the “training” process we’ve found and been able to reach out to individual vets on social media who are struggling with VA benefits, PTSD symptoms, depression and other adjustment issues. We will be concentrating on broad proactive outreach to make them aware that our Lifeline for Vets is here to provide vet-to-vet readjustment services, and that they can call and get assistance with any issues they may be having.

no comments
Zenti Project with Vanderbilt University – Dramatically Improving the Accuracy and Scope of Suicide Prediction
July 30, 2015|Life

Zenti Project with Vanderbilt University – Dramatically Improving the Accuracy and Scope of Suicide Prediction

Zenti Project with Vanderbilt University – Dramatically Improving the Accuracy and Scope of Suicide Prediction

Originally Posted by TAP Lab at Vanderbilt




Nearly one million people die by suicide each year around the world. This means that suicide accounts for more annual deaths than things like war, AIDS, and car accidents. Although medical and technological advances have dramatically reduced the rates of many diseases over the past 100 years, the rate of suicide has not declined appreciably over the last century.


To reduce suicide, it is crucial to identify people at risk and quickly connect them with an effective intervention. Despite hundreds of studies involving millions of people over the past 50 years, our meta-analytic work has shown that science’s ability to predict suicidal behaviors has never improved. Similar to 50 years ago, current science is only slightly better than random guessing when it comes to predicting suicidal behaviors.


Our work has identified several key barriers that have substantially limited progress on this front for several decades:

1. Very long studies. The average study that tries to predict suicidal behaviors is nearly 10 years long. The major problem with this is that most of what determines whether or not a suicidal behavior will occur happens in the minutes, hours, or days before the behavior. But less than 1% of existing studies have tried to predict suicidal behaviors over time periods of even a month or less (and none over time periods of less than a week). This is primarily because it is extremely difficult to conduct such short studies using traditional research methods. The result is that science has not been able to tap into the most important time period for suicidal behaviors — the moments before the behaviors occur.

2. Continued use of old (and ineffective) predictors. Since the beginning of suicide prediction research, science has stuck to a very small number of predictors, with 5 basic categories accounting for 80% of predictors and 9 basic categories accounting for over 95% of predictors. For example, a huge proportion of studies include depression (or something closely related to depression) as a predictor. It is impossible to advance the ability to predict suicide if the field continues to repeat the same studies. The inherent limitations of this repetitiveness are compounded by the fact that these popular factors (e.g., depression) are extremely poor predictors of future suicidal behaviors.

3. Predictors tested as constant factors. Most studies have treated predictors as constant phenomena. For example, many studies measure how depressed someone is and then test whether this depression level predicts suicidal behavior 10 years later. But psychological science has shown us that most predictors are not constant. Over the course of just a few minutes, someone may go from feeling fine to feeling extremely depressed. Such rapid changes may be strong predictors of suicidal behaviors, but very few studies have been able to measure such changes.

4. Predictors tested in isolation. It is extremely unlikely that a single factor can accurately predict future suicidal behaviors; accurate prediction will likely require a combination of several predictors. For example, a given person who feels hopeless is unlikely to attempt suicide in the near future. However, a white male who lives near a bridge, has few friends, and shows a rapid elevation in hopelessness in the hours after the breakup of a long-term relationship may be highly likely to attempt suicide in the near future. Once again, due to the constraints of traditional research methods, very few studies have tested such complex prediction models.

5. Limited scope and reach. Even if science had the ability to accurately predict suicidal behaviors, it currently has no platform through which to immediately identify those at high risk on a large scale. Most research to date has aimed to one day provide healthcare professionals with tools for accurate prediction. Although this is a laudable goal (and we aim to do the same), most individuals who engage in suicidal behaviors are not currently in contact with a healthcare professional. It is accordingly necessary to greatly expand the scope and reach of suicide prediction efforts.


Zenti provides a potential path through the barriers to progress noted above. First, Zenti gives us the ability to collect rich data on individuals in the moments before suicidal behavior occurs. This capability finally gives us a window into the most important time period for suicidal behaviors. Second, through its unique machine learning technology, Zenti allows us to develop a wide range of novel but theoretically-informed predictors that are likely to be far more accurate than traditional predictors.Third, Zenti enables us to examine the waxing and waning of predictors throughout a person’s social media history. This allows us to monitor rapid changes in potential risk factors with unprecedented accuracy and resolution. Fourth, we are able to employ Zenti’s flexible technology to develop and combine a large number and wide variety of predictors. Fifth, Zenti gives us the ability to screen over 100 million social media communications per day in real time to detect individuals at risk for suicidal behaviors. This represents a scope and reach large enough to have an impact on national and international rates of these behaviors. In short, with Zenti’s technology, we could revolutionize the ability to predict suicidal behaviors and immediately translate this ability into real world progress.


Identification of suicide decedents. For our initial project, we will use Zenti’s technology to formulate several theoretically-informed predictors (i.e., “classes” that we train using a supervised machine learning algorithm interface) and use these predictors to identify suicide decedents within a massive backlog of social media communications collected over the past few years. This project will allow us to develop and refine powerful tools for suicide prediction that will serve as a crucial foundation for subsequent projects.

Prediction of future suicidal behaviors. Drawing on the algorithms developed during our initial project, we will conduct a series of studies designed to further refine our ability to accurately predict future suicide ideation, plans, gestures, attempts, and deaths. Within each study we will recruit and follow thousands of at-risk individuals and repeatedly assess their suicidal behaviors. Each study will provide an opportunity to improve our algorithms, further reducing false positives and false negatives. By the end of this project, we hope to have generated algorithms that produce near-perfect accuracy.


Our ultimate goal is to identify thousands of people at high risk for suicidal behaviors each day in real time, and to immediately connect them with a brief, game-like treatment app that dramatically reduces their risk of engaging in these behaviors. We believe that Zenti’s technology will allow us to accomplish the first half of this goal, and our own recently developed treatment apps will allow us to accomplish the second half of this goal. If we are successful, we will ignite the first meaningful worldwide reduction in suicidal behavior.

10 / 6
Hi I'm Kieran
I'm a proud husband, football fan and Dog Dad to @finchy_the_frenchie
Instagram has returned invalid data.

My next blog will be around those brave people to serve in our armed forces and the difficulty they may have in establishing themselves as productive members of society, if you have friends who have serve their country please let me ask you to share this page. My blog posting will appear by Friday this week. ... See MoreSee Less

View on Facebook
Happy St Patrick’s Day to everyone today and my individual beloved memories of my grandfather Jack Prior #family
@dc_mma happy birthday Marquita. Your dad is a class act and the Champ!
RT @BernieSanders: We're in Chicago to launch our campaign and fight for racial and economic justice. #BernieInChicago…