Skip to main content
eScholarship
Open Access Publications from the University of California

Scholarly Works (4 results)

  • Thesis
  • Peer Reviewed
UC Irvine Electronic Theses and Dissertations (2018)

This work consists of four projects that explore human behavior from two perspectives: language use and neural patterns.

In my first and second projects, I focused on language, which can be used to categorize human behavior. In the first project, I used topic models to categorize the subjects and symptoms a patient discussed during psychotherapy treatment. The model functions by identifying topics that are representative of each subject or symptom. The model can predict the subjects and symptoms discussed in new therapy sessions with higher accuracy than discriminative techniques. Furthermore, the model can identify specific passages of text representative of a given subject or symptom.

My second project developed an automated system for routing citizen requests to federal agencies within the Mexican government. The automated system functions by linking pat- terns in language and the appropriate federal agency. The automated system routes requests more efficiently than the current routing system.

The third and fourth projects focused on neuroimaging, which is used to understand the underlying neural processes associated with human behavior. My neuroimaging work related blood-oxygen-level-dependent (BOLD) variability (BV) to experimental condition, behavior, and subject identity. The first phase of the neural work built on previous analyses showing that functional connectivity (FC) is predictive of the task a subject is performing and the identity of the subject performing a task. We extended these analyses to BV and compared its predictive accuracy with that of FC to assess whether some of the predictive power of FC is due to changes in BV. BV performed well compared to FC, suggesting that some of the predictive performance based on FC might be attributed to independent region-specific fluctuations.

Given the predictive relationship between BV and task/subject, the second phase of my neu- ral work developed the Variance Design General Linear Model (VDGLM), a novel framework to facilitate the detection of BV effects. The framework models the mean and variance in the BOLD time course as functions of experimental design. This allows the VDGLM to i) simul- taneously make inferences about a mean or variance effect while controlling for the other and ii) test for variance effects that could be associated with multiple conditions and/or noise regressors. We demonstrated the use of the VDGLM in a working memory application and showed that engagement in a working memory task is associated with whole-brain decreases in BOLD variance.

    Cover page: Understanding Human Behavior Using Language and BOLD Variability
    • Article
    • Peer Reviewed
    UC Irvine Previously Published Works (2019)
    Typical fMRI studies have focused on either the mean trend in the blood-oxygen-level-dependent (BOLD) time course or functional connectivity (FC). However, other statistics of the neuroimaging data may contain important information. Despite studies showing links between the variance in the BOLD time series (BV) and age and cognitive performance, a formal framework for testing these effects has not yet been developed. We introduce the variance design general linear model (VDGLM), a novel framework that facilitates the detection of variance effects. We designed the framework for general use in any fMRI study by modeling both mean and variance in BOLD activation as a function of experimental design. The flexibility of this approach allows the VDGLM to (a) simultaneously make inferences about a mean or variance effect while controlling for the other and (b) test for variance effects that could be associated with multiple conditions and/or noise regressors. We demonstrate the use of the VDGLM in a working memory application and show that engagement in a working memory task is associated with whole-brain decreases in BOLD variance.
      Cover page: Experimental design modulates variance in BOLD activation: The variance design general linear modelCreative Commons 'BY' version 4.0 license
      • Article
      • Peer Reviewed
      UC Irvine Previously Published Works (2019)
      Previous research has found that functional connectivity (FC) can accurately predict the identity of a subject performing a task and the type of task being performed. These results are replicated using a large data set collected at the Ohio State University Center for Cognitive and Behavioral Brain Imaging. This work introduces a novel perspective on task and subject identity prediction: blood-oxygen-level-dependent variability (BV). Conceptually, BV is a region-specific measure based on the variance within each brain region. BV is simple to compute, interpret, and visualize. This work shows that both FC and BV are predictive of task and subject, even across scanning sessions separated by multiple years. Subject differences rather than task differences account for the majority of changes in BV and FC. Similar to results in FC, BV is reduced during cognitive tasks relative to rest.
        Cover page: Predicting Task and Subject Differences with Functional Connectivity and Blood-Oxygen-Level-Dependent VariabilityCreative Commons 'BY' version 4.0 license
        • Article
        • Peer Reviewed
        UC Irvine Previously Published Works (2017)
        Psychotherapy represents a broad class of medical interventions received by millions of patients each year. Unlike most medical treatments, its primary mechanisms are linguistic; i.e., the treatment relies directly on a conversation between a patient and provider. However, the evaluation of patient-provider conversation suffers from critical shortcomings, including intensive labor requirements, coder error, nonstandardized coding systems, and inability to scale up to larger data sets. To overcome these shortcomings, psychotherapy analysis needs a reliable and scalable method for summarizing the content of treatment encounters. We used a publicly available psychotherapy corpus from Alexander Street press comprising a large collection of transcripts of patient-provider conversations to compare coding performance for two machine learning methods. We used the labeled latent Dirichlet allocation (L-LDA) model to learn associations between text and codes, to predict codes in psychotherapy sessions, and to localize specific passages of within-session text representative of a session code. We compared the L-LDA model to a baseline lasso regression model using predictive accuracy and model generalizability (measured by calculating the area under the curve (AUC) from the receiver operating characteristic curve). The L-LDA model outperforms the lasso logistic regression model at predicting session-level codes with average AUC scores of 0.79, and 0.70, respectively. For fine-grained level coding, L-LDA and logistic regression are able to identify specific talk-turns representative of symptom codes. However, model performance for talk-turn identification is not yet as reliable as human coders. We conclude that the L-LDA model has the potential to be an objective, scalable method for accurate automated coding of psychotherapy sessions that perform better than comparable discriminative methods at session-level coding and can also predict fine-grained codes.
          Cover page: Content Coding of Psychotherapy Transcripts Using Labeled Topic Models
          Top