U.S. flag

An official website of the United States government, Department of Justice.

Dot gov

The .gov means it’s official.
Federal government websites always use a .gov or .mil domain. Before sharing sensitive information online, make sure you’re on a .gov or .mil site by inspecting your browser’s address (or “location”) bar.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Pattern Classification of Neurocognitive and Socio-Emotional Developmental Factors Underlying Violent Outcomes in Adolescents

Award Information

Award #
2016-R2-CX-0019
Location
Status
Open
Funding First Awarded
2016
Total funding (to date)
$150,000

Description of original award (Fiscal Year 2016, $50,000)

As submitted by the proposer: The incidence rate of violent crimes follows a similar developmental trajectory as neurobehavioral metrics of risk taking, rewardsensitivity, inhibitory control and aggression; rapidly increasing following puberty and approaching a peak at ages 1719 before leveling off towards the middle of young adulthood Neuroscience research suggests the emergence of youth violence may be explained by an interaction between detrimental environmental factors and physiological changes during the critical period of adolescent development that predispose vulnerable youths to adverse outcomes. Specifically, family conflict, victimization and social adversity combined with violence exposure are hypothesized to impair brain development, promote aggression and increase risk for violent outcomes. The existence of a critical period for violent outcomes in adolescents provides an excellent opportunity for preventative measures. However, the impact of intervention programs is limited by a lack of knowledge about the interaction between environmental influences and the neurocognitive development of adolescents susceptible to violent outcomes. In this proposal, we will refine existing risk and outcome assessment metrics by applying machine learning to classify the reliability of environmental adversity scores (i.e., family conflict, exposure to violence, victimization and social adversity) in predicting developmental changes in brain activity and behavior that characterize violent and antisocial behavior in 135 preadolescents participating in an ongoing NIH youth development study from ages 11-17. The classifier will be validated by annual measurement of cognitive performance, brain activity and aggressive/antisocial behavior from 2016-2018 in an additional 78 adolescents (aged 12-15 at baseline) sampled from communities with the lowest average income and highest crimerates in D.C. Risk for violence, environmental adversity, aggression and violent outcomes will be measured with a repertoire of instruments commonly applied in youth violence prevention. Behavioral performance and functional magnetic resonance imaging (fMRI) will be used to track neurocognitive changes in inhibitory control, emotion and risk/reward processing tasks that explain variances in individual outcomes. A longitudinal support vector machine will be used to identify the combination of testing instruments that best predict and distinguish between violent outcomes on an individual basis . Refined metrics will be implemented in youth violence prevention practices via collaboration with the Pierce Prevention Research Center at Pennsylvania State University.

Note: This project contains a research and/or development component, as defined in applicable law.
ca/ncf

As submitted by the proposer: The incidence rate of violent crimes follows a similar developmental trajectory as neurobehavioral metrics of risk-taking, reward-sensitivity, impulsivity and aggression; rapidly increasing following puberty and approaching a peak at ages 17-19 before leveling off towards the middle of young adulthood.

Neuroscience research suggests the emergence of youth violence may be explained by an interaction between detrimental environmental factors and physiologicalchanges during the critical period of adolescent development that predispose vulnerable youths to adverse outcomes.

Family conflict, victimization and social adversity combined with violence exposure are hypothesized to impair brain development, promote aggression and increase risk for violent outcomes. The existence of a critical period for violent outcomes in adolescents provides an excellent opportunity for preventative measures. However, the impact of intervention programs is limited by a lack of knowledge about the interaction between environmental influences and the neurocognitive development of adolescents susceptible to violent outcomes.

The researcher will refine existing risk and outcome assessment metrics by applying machine learning to classify the reliability of environmental adversity scores (i.e., family conflict, exposure to violence, victimization and social adversity) in predicting developmental changes in brain activity and behavior that characterize violent and antisocial behavior in 135 pre-adolescents participating in an ongoing NIH youth development study from ages 11-17.

Risk for violence, environmental adversity, aggression and violent outcomes will be measured with a repertoire of instruments commonly applied in youth violence prevention. Behavioral performance and functional magnetic resonance imaging (fMRI) will be used to track neurocognitive changes in inhibitory control, emotion and risk/reward processing tasks that explain variances in individual outcomes.

A longitudinal support vector machine will be applied for identifying the combination of testing instruments that best predict and distinguish between violent outcomes on an individual basis. An additional 54 high-risk youths will be sampled to assess classifier validity using those instruments with the highest correspondence to neurocognitive development and prediction accuracy for violent outcomes. Participants will be recruited from communities with the highest crime-rates in D.C using an overlapping cohort design with three groups (12-14, 14-16 and 16-18) and tested once a year from 2017-2019.

Final refined metrics will be implemented in youth violence prevention practices via collaboration with the Edna Bennett Pierce Prevention Research Center at Pennsylvania State University.

This project contains a research and/or development component, as defined in the applicable law, and complies with Part 200 Uniform Requirements – 2 CFR 200.210(a) (14). nca/ncf

The applicant proposes to develop and test a software program using machine learning technology to predict developmental changes in youth brain activity and behavior that characterize violent and antisocial behavior.

"Note: This project contains a research and/or development component, as defined in applicable law," and complies with Part 200 Uniform Requirements - 2 CFR 200.210(a)(14).

NCA/NCF

Date Created: July 17, 2016