Karcher NR, Sotiras A, Niendam TA, Walker EF, Jackson JJ, Barch DM. Examining the Most Important Risk Factors Predicting Persistent and Distressing Psychotic-like Experiences in Youth.
BIOLOGICAL PSYCHIATRY. COGNITIVE NEUROSCIENCE AND NEUROIMAGING 2024:S2451-9022(24)00142-3. [PMID:
38849031 DOI:
10.1016/j.bpsc.2024.05.009]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/06/2024] [Revised: 05/17/2024] [Accepted: 05/23/2024] [Indexed: 06/09/2024]
Abstract
BACKGROUND
Persistence and distress distinguish more clinically significant psychotic-like experiences (PLEs) from those that are less likely to be associated with impairment and/or need for care. Identifying risk factors that differentiate clinically relevant PLEs early in development is important for improving our understanding of the etiopathogenesis of these experiences. Machine learning analyses examined the most important baseline factors distinguishing persistent distressing PLEs.
METHODS
Using Adolescent Brain Cognitive Development Study PLEs data over three time points (ages 9-13), individuals with persistent distressing PLEs (n=303), transient distressing PLEs (n=374), and demographically matched low-level PLEs groups were created. Random forest classification models were trained to distinguish among persistent distressing vs. low-level PLEs, transient distressing vs. low-level PLEs, and persistent distressing vs. transient distressing PLEs. Models were trained using identified baseline predictors as input features (i.e., cognitive, neural [cortical thickness, resting state functional connectivity (RSFC)], developmental milestone delays, internalizing symptoms, adverse childhood events).
RESULTS
The model distinguishing persistent distressing vs. low-level PLEs showed the highest accuracy (test sample accuracy=69.33%; 95% CI:61.29%-76.59%). The most important predictors included internalizing symptoms, adverse childhood events, and cognitive functioning. Models distinguishing persistent vs. transient distressing PLEs generally performed poorly.
CONCLUSIONS
Model performance metrics indicated that while most important factors overlapped across models (e.g., internalizing symptoms), adverse childhood events were especially important for predicting persistent distressing PLEs. Machine learning analyses proved useful for distinguishing the most clinically relevant group from the least clinically relevant group but showed limited ability to distinguish among clinically relevant groups that differed in PLE persistence.
Collapse