Projects

Our Projects

Our research focuses on understanding affective disorders (e.g., depression and anxiety) by studying how symptoms vary across individuals (heterogeneity), how conditions develop and change over time (course and prognosis), and how people respond to different treatments. We also use modern methods, such as machine learning and computational approaches, and social media data to improve how mental health problems are identified, understood, and treated.

Heterogeneity of Depression

Depression can present in many different ways, with people experiencing a wide range of symptom combinations (Buss et al., 2023; Fried et al., 2020; Lorenzo-Luaces, Buss, et al., 2021). Most research has studied this by counting symptom profiles, but this approach can oversimplify differences between individuals. We use methods from information theory to better measure how diverse depression symptoms are and to evaluate whether common subtypes, such as melancholic and atypical depression, actually make diagnoses more consistent. Across approaches, we find that these subtypes do not meaningfully reduce symptom heterogeneity. We also study whether different symptom patterns predict who benefits most from different treatments using machine learning. Overall, specific symptom combinations rarely predict treatment outcomes, with a few exceptions (e.g., positive emotionality, insomnia). Instead, greater overall symptom severity is a more consistent predictor of better outcomes with higher-intensity treatments. The projects include:

  • Measuring depression heterogeneity using symptom profiles and information theory methods
  • Testing whether DSM subtypes (e.g., melancholic, atypical) reduce symptom heterogeneity
  • Using machine learning to examine whether symptom patterns predict treatment outcomes
  • Comparing outcomes across treatments, including CBT, medication, positive psychotherapy, and interpersonal therapy
    Identifying specific symptoms (e.g., positive emotionality, insomnia) that may influence outcomes
  • Examining how overall symptom severity predicts response to higher-intensity treatments

Personalized Medicine

Depression varies widely in how long it lasts and how it progresses, making it important to study predictors of its course and prognosis (Lorenzo-Luaces, 2015; 2018; Lorenzo-Luaces et al., 2017a; 2021b). About half of individuals experience relatively brief episodes (e.g., 3–6 months), while the other half have chronic or relapsing courses. Despite these differences, all cases are grouped under a single diagnosis—a shift that began with DSM-III—which limits the usefulness of the diagnosis for guiding treatment. As a result, some individuals receive more intensive care than needed, while others do not receive enough support. Our work uses machine learning to predict individual prognosis and improve treatment decisions. Findings suggest that most patients respond similarly across different treatments, including lower-intensity options, but a smaller group with more difficult prognoses benefits more from higher-intensity treatments like CBT. We have also examined treatment response across CBT, antidepressants, interpersonal therapy, and positive psychology interventions. A key challenge is that these predictive models require large datasets to be reliable. Overall, this work highlights the limitations of one-size-fits-all approaches and supports more personalized treatment strategies. The projects include: 

  • Studying variation in the course and prognosis of depression 
  • Examining how DSM diagnostic practices group individuals with different outcomes 
  • Investigating risks of over- and under-treatment under current guidelines 
  • Using machine learning to predict individual prognosis 
  • Developing treatment rules to guide assignment to low- vs. high-intensity care 
  • Comparing outcomes across CBT, medications, interpersonal therapy, and positive psychology interventions 
  • Identifying key predictors (e.g., severity, insomnia, unemployment, hostility, positive emotionality) 
  • Evaluating scalability of lower-intensity treatments for most patients 
  • Addressing challenges of large sample sizes needed for predictive models 

Low-Intensity Treatments

Psychological interventions are effective treatments for depression, anxiety, stress, insomnia, and other common mental health concerns. Despite this, it is very difficult for most people to access treatments because they are expensive, time-consuming, and difficult to find. We have several projects studying interventions that are not as expensive as face-to-face psychotherapy with trained therapists, including internet apps and books. The projects include:

  • Leveraging computational social sciences and natural language processing to optimize engagement and response to low-intensity CBT for depression and anxiety
  • Feasibility of stepped care with single-session interventions and guided self-help CBT
  • Psychologists’ use of waiting lists and willingness to use low-intensity treatments (PI: Peipert)
  • Barriers to internet-based CBT use (PI: Peipert)
  • Racial-ethnic diversity in trials of internet-based cognitive-behavioral therapy (PI: De Jesús-Romero)
  • Willingness of individuals to use different low-intensity treatments (PI: De Jesús-Romero)
  • Predictors of engagement with guided self-help (PI: Starvaggi)

Emotion Regulation

One commonality of depression, anxiety, stress, insomnia, and other common mental health concerns may be that people have a hard time regulating their emotions, especially negative emotions. When we conduct studies, we usually include measures of emotion regulation, usually the Emotion Regulation Questionnaire (Gross and John, 2003). The ERQ measures the habitual or regular use of two emotion regulation strategies: cognitive reappraisal and expressive suppression. Projects that specifically focus on emotion regulation include:

  • Cognitive reappraisal of LGB-identity vs. non-LGB-identity stress in LGBT young adults (PI: De Jesús-Romero)
  • Mechanisms of change in transdiagnostic guided self-help (PI: De Jesús-Romero)

Social Media

Social media is a relatively recent development. As of 2021, over 75% of adults in the United States are on a social media platform. That alone makes social media an interesting topic to study.

For more information about our social media research, please refer to our SOCIAL surveys section!