TY - JOUR
T1 - Using Machine Learning to Derive Neurobiological Subtypes of General Psychopathology in Late Childhood
AU - Reimann, Gabrielle E.
AU - Dupont, Randolph M.
AU - Sotiras, Aristeidis
AU - Earnest, Tom
AU - Jeong, Hee Jung
AU - Durham, E. Leighton
AU - Archer, Camille
AU - Moore, Tyler M.
AU - Lahey, Benjamin B.
AU - Kaczkurkin, Antonia N.
N1 - Publisher Copyright:
© 2024 American Psychological Association
PY - 2024
Y1 - 2024
N2 - Traditional mental health diagnoses rely on symptom-based classifications. Yet this approach can oversimplify clinical presentations as diagnoses often do not adequately map onto neurobiological features. Alternatively, our study used structural imaging data and a semisupervised machine learning technique, heterogeneity through discriminative analysis, to identify neurobiological subtypes in 9- to 10-year-olds with high psychopathology endorsements (n =9,027). Our model revealed two stable neurobiological subtypes (adjusted Rand index =0.38). Subtype 1 showed smaller structural properties, elevated conduct problems and attention-deficit/hyperactivity disorder symptoms, and impaired cognitive performance compared to Subtype 2 and typically developing youth. Subtype 2 had larger structural properties, cognitive abilities comparable to typically developing youth, and elevated internalizing symptoms relative to Subtype 1 and typically developing youth. These subtypes remained stable in their neurobiological characteristics, cognitive ability, and associated psychopathology traits over time. Taken together, our data-driven approach uncovered evidence of neural heterogeneity as demonstrated by structural patterns that map onto divergent profiles of psychopathology symptoms and cognitive performance in youth.
AB - Traditional mental health diagnoses rely on symptom-based classifications. Yet this approach can oversimplify clinical presentations as diagnoses often do not adequately map onto neurobiological features. Alternatively, our study used structural imaging data and a semisupervised machine learning technique, heterogeneity through discriminative analysis, to identify neurobiological subtypes in 9- to 10-year-olds with high psychopathology endorsements (n =9,027). Our model revealed two stable neurobiological subtypes (adjusted Rand index =0.38). Subtype 1 showed smaller structural properties, elevated conduct problems and attention-deficit/hyperactivity disorder symptoms, and impaired cognitive performance compared to Subtype 2 and typically developing youth. Subtype 2 had larger structural properties, cognitive abilities comparable to typically developing youth, and elevated internalizing symptoms relative to Subtype 1 and typically developing youth. These subtypes remained stable in their neurobiological characteristics, cognitive ability, and associated psychopathology traits over time. Taken together, our data-driven approach uncovered evidence of neural heterogeneity as demonstrated by structural patterns that map onto divergent profiles of psychopathology symptoms and cognitive performance in youth.
KW - attention-deficit/hyperactivity disorder
KW - conduct problems
KW - general psychopathology
KW - internalizing
KW - machine learning subtypes
UR - http://www.scopus.com/inward/record.url?scp=85208224880&partnerID=8YFLogxK
U2 - 10.1037/abn0000898
DO - 10.1037/abn0000898
M3 - Article
C2 - 39480333
AN - SCOPUS:85208224880
SN - 2769-7541
VL - 133
SP - 647
EP - 655
JO - Journal of Psychopathology and Clinical Science
JF - Journal of Psychopathology and Clinical Science
IS - 8
ER -