# Identifying Neurophysiological Markers of Emotion Regulation Relevant to Adolescent Depression Diagnosis and Prognosis: A Comparison of Classification Models

> **NIH NIH F31** · VANDERBILT UNIVERSITY · 2022 · $47,443

## Abstract

PROJECT SUMMARY
Adolescence is a high-risk developmental period for the first onset of depression, and epidemiological research
reveals a sharp increase in incidence rates for depressive disorders during this time. Considering earlier
onsets of depression are associated with a more debilitating course of the disorder throughout the lifespan, the
identification of vulnerability factors is critical for early and personalized intervention. Depression is
characterized by widespread alterations in emotion processing, and difficulties regulating responses to
dysphoric, sad emotions are thought to be central to the onset and maintenance of depression. Given
compelling evidence that some alterations in emotion processing precede the development of depression,
neurophysiological markers of dysregulated responses to dysphoric stimuli could potentially identify those at
greatest risk for recurrence and new depressive episodes. Previous research demonstrates event-related
potentials (ERPs) derived from the electroencephalogram (EEG) reliably and economically capture the
temporal dynamics of emotion processing. Further, studies on emotion regulation demonstrate EEG markers in
both the time and frequency domains are modifiable by regulation efforts, such as cognitive reappraisal.
Despite this promise, complex emotion regulation tasks with extended stimuli presentations result in high-
dimensional data, amplifying ambiguities and discrepancies in quantifying ERPs relevant to the emergence
and maintenance of depression. One established solution is to use principal components analysis (PCA) to
reduce the dimensionality of the data and identify task-relevant ERPs. Yet, translational research examining
associations between ERPs to emotion and depression is further limited by issues of replicability and clinical
relevance. The primary goal of the proposed research is to compare classification algorithms to clarify the
neurophysiological substrates of emotion regulation that optimize diagnostic and prognostic predictions of
adolescent (age 14-17) depression in order to facilitate early, personalized intervention and prevention efforts.
Aim 1: Examine within-subjects effects of emotion regulation on ERP and time-frequency EEG components.
Aim 2: Iteratively investigate which neurophysiological emotion regulation features and classification algorithms
most accurately classify adolescents with and without current depression at baseline. Aim 3: Identify which
emotion regulation features and classification algorithms most accurately predict future onsets of depressive
episodes in adolescents. Exploratory analyses will examine potential sex differences and compare model
performance when including self-reports of emotion regulation. In addition to these research goals, this award
will support my predoctoral training goals to expand my developing expertise in diagnostic clinical interviewing,
conceptual understanding of emotion regulation, advanced EEG/ERP methods, and rigoro...

## Key facts

- **NIH application ID:** 10461562
- **Project number:** 1F31MH127863-01A1
- **Recipient organization:** VANDERBILT UNIVERSITY
- **Principal Investigator:** Lindsay Dickey
- **Activity code:** F31 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2022
- **Award amount:** $47,443
- **Award type:** 1
- **Project period:** 2022-05-16 → 2025-05-15

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10461562

## Citation

> US National Institutes of Health, RePORTER application 10461562, Identifying Neurophysiological Markers of Emotion Regulation Relevant to Adolescent Depression Diagnosis and Prognosis: A Comparison of Classification Models (1F31MH127863-01A1). Retrieved via AI Analytics 2026-05-24 from https://api.ai-analytics.org/grant/nih/10461562. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*