Back to all papers

Identification of distinct clinical phenotypes and their neurobiological signatures in stress-exposed individuals: A multimodal machine learning approach.

May 26, 2026pubmed logopapers

Authors

Hong H,Jeong H,Joo Y,Shim Y,Kim Y,Jin Y,Choi Y,Yoon S,Lyoo IK

Affiliations (3)

  • Ewha Brain Institute, https://ror.org/053fp5c05Ewha Womans University, Seoul, Republic of Korea.
  • Department of Brain and Cognitive Sciences, https://ror.org/053fp5c05Ewha Womans University, Seoul, Republic of Korea.
  • Graduate School of Pharmaceutical Sciences, https://ror.org/053fp5c05Ewha Womans University, Seoul, Republic of Korea.

Abstract

Individual responses to stress are highly heterogeneous, resulting in diverse psychopathological outcomes. This variability poses challenges for traditional diagnostic frameworks and underscores the need for a transdiagnostic approach to guide interventions. This study aimed to identify distinct phenotypes within a stress-exposed population and to characterize their biological profiles using a multimodal machine learning framework. A total of 809 stress-exposed adults (mean age 40.5 ± 8.74 years; 53.7% female) underwent clinical, laboratory, and structural MRI assessments. Data-driven clustering of clinical variables identified phenotypes, followed by machine learning classifiers trained on neuroimaging and laboratory data to predict phenotype membership. SHapley Additive exPlanations (SHAP) analysis was used to identify key biological features distinguishing each phenotype. Three phenotypes were identified: a multi-risk group (<i>n</i> = 321) characterized by prominent depression, anxiety, and sleep disturbances; an alcohol-related risk group (<i>n</i> = 226) with high alcohol misuse and minimal comorbidity; and a resilient low-risk group (<i>n</i> = 262). Machine learning models accurately classified these phenotypes, indicating distinct biological profiles. SHAP analysis revealed phenotype-specific signatures: the multi-risk phenotype was associated with frontal-subcortical structural alterations and dysregulated cortisol, whereas the alcohol-related risk phenotype was characterized by frontal-insular structural alterations and metabolic abnormalities. This study demonstrates the stratification of stress-exposed individuals into clinically and biologically distinct phenotypes. By integrating multimodal data with machine learning, we identified phenotype-specific neurobiological and metabolic profiles that extend beyond conventional diagnostic frameworks. These findings support a transdiagnostic, data-driven approach to improve risk stratification and inform personalized interventions in stress-exposed populations.

Topics

Machine LearningPhenotypeStress, PsychologicalSleep Wake DisordersJournal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.