Peer-reviewed article
Predicting psychopathology symptom trajectories using machine learning: a 33-year prospective study.
Seda Sacu, Fabian Streit, Stephanie H Witt, Tobias Banaschewski, Nathalie E Holz et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This is a longitudinal study that tracked psychopathology symptoms in a birth cohort from age 8 to 33 using machine learning to predict symptom trajectories. The research identified different patterns of externalizing and internalizing symptoms over time and found that both genetic and environmental risk factors influenced these trajectories. While the study concludes that understanding risk factors can support early identification, it does not evaluate a specific intervention for child well-being.
Key points
- Three distinct trajectories identified for both externalizing and internalizing symptoms: low, increasing (late-adolescent emergence), and decreasing (childhood-limited)
- Machine learning models achieved fair discriminatory power for externalizing symptoms (AUC 0.77-0.88) and modest power for internalizing symptoms (AUC 0.75-0.83)
- Both genetic factors (polygenic scores for cognition and mental disorders) and environmental factors (adverse family characteristics, poor social functioning) predicted symptom trajectories
- Study tracked psychopathology symptoms continuously over 25 years from age 8 to 33 in a birth cohort of 317 participants
Limitations
This study is primarily a methodological analysis of risk prediction rather than an evaluation of an intervention designed to improve child well-being. The findings cannot tell us whether any specific prevention or treatment program actually reduces symptoms or improves outcomes in children.
Abstract
BACKGROUND: While previous literature has established a link between psychopathology symptom trajectories and psychosocial risk, most studies have not extended into adulthood or incorporated comprehensive risk measures. We aimed to identify symptom trajectories for externalizing and internalizing symptoms over a 25-year span and predict them using machine learning. METHODS: We used data from a longitudinal birth cohort study (N = 317, 171 females). Psychopathology symptoms were measured between age 8 and 33. Symptom trajectories were identified using growth mixture models. An extensive battery of risk and protective measures over the lifespan (e.g., polygenic scores, psychosocial risk factors, temperament) was used to train machine learning-based classification models. RESULTS: We identified three trajectories for both externalizing and internalizing symptoms (entropy > 0.8, likelihood ratio test p < .05): Low, increasing (late-adolescent emergence), and decreasing (childhood-limited) symptoms classes. Both genetic (e.g., polygenic scores for cognition and mental disorders) and environmental factors (e.g., adverse family characteristics, poor social functioning) predicted symptom trajectories. For externalizing symptoms trajectories, random forest achieved fair discriminatory power with a multiclass macro-average AUC of 0.77 and a multiclass micro-average of 0.88. For internalizing symptoms trajectories, logistic regression achieved modest discriminatory power with a multiclass macro-average AUC of 0.75 and a multiclass micro-average of 0.83. CONCLUSIONS: Psychopathology risk trajectories vary across development and are influenced by diverse risk factors. Understanding these risk factors can support early identification of at-risk individuals and inform targeted prevention and intervention efforts.