Capturing additional variance in impact of adolescent depression from free text: proof of concept and preliminary results
- 1Machine Learning Core, National Institute of Mental Health, NIH
Abstract
Depression in adolescents has grown in prevalence in the past decade. Despite indications of differences in symptom presentation, measurement properties, and treatment response between adolescents and adults, research is dominated by adult participants. Qualitative work has identified symptomatic and functional domains important to depressed adolescents and those around them; however, there remains little quantitative evidence of how these domains relate to the functional impact of the disorder. In this preregistered study, we use adolescent self-report (n = 153) and parent-report (n = 106) responses in the depression section of the Development and Well-Being Assessment (DAWBA) to examine what information relevant to reported depression impact may be missing from its structured symptom-scale. We apply Large Language Models (LLMs) to participant free-text answers to extract information on a taxonomy of 80 outcomes. Through a sequential residual stacking framework that estimates incremental information in symptom sum-scores (S ), item-level symptom-scale answers (Q), and LLM-derived text representations (T ), we find that parent text contains information relevant to their report of depression impact that is not available in the structured symptom-scale, with the largest contributions concentrated in functioning-related domains (e.g., professional responsibilities, social exclusion, autonomy, coping). No such evidence was found in adolescent self-reports. Given the moderate sample size, these results are preliminary. Nonetheless, we provide a proof-of-concept framework for extracting information from open-ended free text in large existing datasets, and estimating incremental information across sources, which could be applied to uncover specific aspects of adolescent mental disorders across populations.
Related
- Cross-cultural adaptation and preliminary validation of the adolescent obesity environmental questionnaire (AOEQ) in LMICs: family, school, and peer contexts
- Is Emotional Allodynia in Fibromyalgia Reducible to Depression? A Preliminary Network Analysis in 149 Patients
- Sleep and the Daytime Course of Anhedonia in Adolescent Depression: An Ecological Momentary Assessment Study
- Association of low parental mental health literacy with adolescent depression and anxiety: a large-scale cross-sectional study in Guangdong, China
- Hypoxia-associated Birth Complications and Offspring Childhood Internalizing, Externalizing, and Adolescent Depression Symptoms
BibTeX
@misc{matar2026capturing,
title = {{Capturing additional variance in impact of adolescent depression from free text: proof of concept and preliminary results}},
author = {A. Y. Matar and J. A. Lossio-Ventura and F. Pereira and D. M. Nielson},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.02.26367115},
url = {https://www.medrxiv.org/content/10.64898/2026.11.02.26367115v1},
note = {CC0},
}
RIS
TY - UNPB
TI - Capturing additional variance in impact of adolescent depression from free text: proof of concept and preliminary results
AU - A. Y. Matar
AU - J. A. Lossio-Ventura
AU - F. Pereira
AU - D. M. Nielson
PY - 2026
DA - 2026/11/02
PB - medRxiv
DO - 10.64898/2026.11.02.26367115
UR - https://www.medrxiv.org/content/10.64898/2026.11.02.26367115v1
AB - Depression in adolescents has grown in prevalence in the past decade. Despite indications of differences in symptom presentation, measurement properties, and treatment response between adolescents and adults, research is dominated by adult participants. Qualitative work has identified symptomatic and functional domains important to depressed adolescents and those around them; however, there remains little quantitative evidence of how these domains relate to the functional impact of the disorder. In this preregistered study, we use adolescent self-report (n = 153) and parent-report (n = 106) responses in the depression section of the Development and Well-Being Assessment (DAWBA) to examine what information relevant to reported depression impact may be missing from its structured symptom-scale. We apply Large Language Models (LLMs) to participant free-text answers to extract information on a taxonomy of 80 outcomes. Through a sequential residual stacking framework that estimates incremental information in symptom sum-scores (S ), item-level symptom-scale answers (Q), and LLM-derived text representations (T ), we find that parent text contains information relevant to their report of depression impact that is not available in the structured symptom-scale, with the largest contributions concentrated in functioning-related domains (e.g., professional responsibilities, social exclusion, autonomy, coping). No such evidence was found in adolescent self-reports. Given the moderate sample size, these results are preliminary. Nonetheless, we provide a proof-of-concept framework for extracting information from open-ended free text in large existing datasets, and estimating incremental information across sources, which could be applied to uncover specific aspects of adolescent mental disorders across populations.
ER -