Background:

Functional impairments associated with mental health conditions are on the rise. Predicting functional outcomes may improve the targeting of preventive interventions. While prognostic models have primarily focused on psychosis, early recognition services require a transdiagnostic approach.

Objective:

Predict global functioning within 2-year follow-up using baseline clinical and structural MRI data in a population-based sample of young, help-seeking individuals presenting with affective and anxiety symptoms as well as ADHD.

Methods:

We classified 357 help-seeking individuals aged 18-35 years recruited from 9 sites as “impaired” (Global Assessment of Functioning (GAF)≤60; N=228) or “non-impaired” (GAF>60; N=129) at year one and/or year two follow-up. GAF classification group status at follow up was predicted using linear support vector machine (SVM), decision tree and large language model (LLM) Llama-3 using clinical assessments and/or structural MRI. Leave-one-site-out (SVM) or external sample (LLM) were used for validation.

Results:

SVM achieved balanced accuracy 69.2% using clinical features only. Items related to baseline occupational functioning, interpersonal relationships, cognitive functioning, psychotic and affective symptoms as well as presence of anxiety disorder were most predictive. The decision tree further reduced the feature set to 5 predictive items achieving balanced accuracy 76.6%. Although amygdala and hippocampal subregions achieved balanced accuracy 57.1%, structural MRI did not improve the overall prediction. Llama-3 performed comparably well to SVM, (balanced accuracy 72.6%).

Conclusions:

Machine learning demonstrated good performance in predicting global functioning. Interestingly, the out-of-the-box LLM performed comparably well without being trained or fine-tuned, highlighting the potential of leveraging free-text data for mental health prognosis.