Repository logo

Browsing by Author "Kentopp, Shane, author"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Deep transfer learning for prediction of health risk behaviors in adolescent psychiatric patients
    (Colorado State University. Libraries, 2021) Kentopp, Shane, author; Conner, Bradley T., advisor; Prince, Mark A., committee member; Henry, Kimberly L., committee member; Anderson, Charles W., committee member
    Binge drinking and non-suicidal self-injury are significant health-risk behaviors that are often initiated during adolescence and contribute to a host of negative outcomes later in life. Selective prevention strategies are targeted toward individuals most at-risk for developing these behaviors. Traditionally, selective interventions are tailored based on risk factors identified by human experts. Machine learning algorithms, such as deep neural networks, may improve the effectiveness of selective interventions by accounting for complex interactions between large numbers of predictor variables. However, their use in psychological research is limited due to the tendency to overfit and the need for large volumes of training data. Deep transfer learning can overcome this limitation by leveraging samples of convenience to facilitate training deep neural networks in small, clinically relevant samples. The author trained deep neural networks on data from a sample of adolescent psychiatric inpatients to retrospectively classify individuals according to their history of alcohol misuse and nonsuicidal self-injury. Next, the performance of these models was compared to deep neural networks that were pretrained in a convenience sample of college undergraduates and fine-tuned in the sample of psychiatric patients. Deep transfer learning did not improve classification accuracy but buffered against overfitting. The deep neural networks that were not pretrained maintained maximum classification accuracy for a very small number of training epochs before performance deteriorated due to overfitting the training data. Conversely, the pretrained networks maintained their maximum classification accuracy across many training epochs and performance was not hindered by overfitting. This suggests that convenience samples can be utilized to reduce the risk of overfitting when training complex deep neural networks on small clinical samples. In the future, this process may be employed to facilitate powerful predictive models that inform selective prevention programs and contribute to the reduction of health risk behavior prevalence amongst vulnerable adolescent populations.
  • Thumbnail Image
    ItemOpen Access
    Optical imaging of emotional responding to sensational stimuli in high and low risk-seeking individuals
    (Colorado State University. Libraries, 2017) Kentopp, Shane, author; Conner, Bradley T., advisor; Rojas, Donald C., committee member; Riggs, Nathaniel R., committee member
    Sensation seeking is a reward-based personality construct linked to engagement in risky behavior. A neural and conceptual overlap between emotion and reward suggests there is an emotional component to sensation seeking. The current study sought to assess the theorized emotional component of sensation seeking by measuring a distinct pattern of visual cortex activation that accompanies the induction of emotion via visual stimuli. Undergraduate participants were recruited based on a prescreening personality assessment. Thirty-five participants were sorted into groups with either high or low scores on risk seeking (a facet of sensation seeking) and exposed to emotional, sensational, and neutral video stimuli. Participants rated their emotional response and reward valuation following each video. Activation in the primary visual cortex was measured using functional near-infrared spectroscopy (fNIRS). Activation during the sensational conditions was assessed for similarity to the emotional conditions and compared between risk seeking groups. Imaging results revealed no significant differences between conditions or groups. Participant responses to stimuli indicated that individuals high in risk seeking experienced a more positive emotional response to sensational videos than individuals low in risk seeking. Participant responses to stimuli also indicated that individuals high in risk seeking endorsed a stronger approach response to sensational stimuli. The study encountered methodological challenges, which limited its statistical power and ability to measure the hypothesized effects. Stimulus response data, however, provided preliminary support for the role of emotional processes in risky behavior amongst individuals high in sensation seeking. These findings suggest that targeting emotion regulation processes in individuals who are high in sensation seeking may be an effective approach to reducing engagement in risky behavior.