; for the PRONIA Consortium IMPORTANCE Social and occupational impairments contribute to the burden of psychosis and depression. There is a need for risk stratification tools to inform personalized functional-disability preventive strategies for individuals in at-risk and early phases of these illnesses. OBJECTIVE To determine whether predictors associated with social and role functioning can be identified in patients in clinical high-risk (CHR) states for psychosis or with recent-onset depression (ROD) using clinical, imaging-based, and combined machine learning; assess the geographic, transdiagnostic, and prognostic generalizability of machine learning and compare it with human prognostication; and explore sequential prognosis encompassing clinical and combined machine learning. DESIGN, SETTING, AND PARTICIPANTS This multisite naturalistic study followed up patients in CHR states, with ROD, and with recent-onset psychosis, and healthy control participants for 18 months in 7 academic early-recognition services in 5 European countries. Participants were recruited between February 2014 and May 2016, and data were analyzed from April 2017 to January 2018. AIN OUTCOMES AND MEASURES Performance and generalizability of prognostic models. RESULTS A total of 116 individuals in CHR states (mean [SD] age, 24.0 [5.1] years; 58 [50.0%] female) and 120 patients with ROD (mean [SD] age, 26.1 [6.1] years; 65 [54.2%] female) were followed up for a mean (SD) of 329 (142) days. Machine learning predicted the 1-year social-functioning outcomes with a balanced accuracy of 76.9% of patients in CHR states and 66.2% of patients with ROD using clinical baseline data. Balanced accuracy in models using structural neuroimaging was 76.2% in patients in CHR states and 65.0% in patients with ROD, and in combined models, it was 82.7% for CHR states and 70.3% for ROD. Lower functioning before study entry was a transdiagnostic predictor. Medial prefrontal and temporo-parietooccipital gray matter volume (GMV) reductions and cerebellar and dorsolateral prefrontal GMV increments had predictive value in the CHR group; reduced mediotemporal and increased prefrontal-perisylvian GMV had predictive value in patients with ROD. Poor prognoses were associated with increased risk of psychotic, depressive, and anxiety disorders at follow-up in patients in the CHR state but not ones with ROD. Machine learning outperformed expert prognostication. Adding neuroimaging machine learning to clinical machine learning provided a 1.9-fold increase of prognostic certainty in uncertain cases of patients in CHR states, and a 10.5-fold increase of prognostic certainty for patients with ROD. CONCLUSIONS AND RELEVANCE Precision medicine tools could augment effective therapeutic strategies aiming at the prevention of social functioning impairments in patients with CHR states or with ROD.

The field should move towards the development of a multimodal model of resilience. Researchers should now focus on producing empirical research which clarifies the specific protective factors and mechanisms of the process, aligning with the core concepts of resilience. This growing, more homogeneous evidence base, can then inform new intervention strategies.

This prognostic study evaluates whether psychosis transition can be predicted in patients with clinical high-risk syndromes or recent-onset depression by multimodal machine learning that optimally integrates clinical and neurocognitive data, structural magnetic resonance imaging, and polygenic risk scores for schizophrenia.

No abstract

Background The majority of people with mental illness do not seek help at all or only with significant delay. To reduce help-seeking barriers for people with mental illness, it is therefore important to understand factors predicting help-seeking. Thus, we prospectively examined potential predictors of help-seeking behaviour among people with mental health problems (N = 307) over 3 years. Methods Of the participants of a 3-year follow-up of a larger community study (response rate: 66.4%), data of 307 (56.6%) persons with any mental health problems (age-at-baseline: 16–40 years) entered a structural equation model of the influence of help-seeking, stigma, help-seeking attitudes, functional impairments, age and sex at baseline on subsequent help-seeking for mental health problems. Results Functional impairment at baseline was the strongest predictor of follow-up help-seeking in the model. Help-seeking at baseline was the second-strongest predictor of subsequent help-seeking, which was less likely when help-seeking for mental health problems was assumed to be embarrassing. Personal and perceived stigma, and help-seeking intentions had no direct effect on help-seeking. Conclusions With only 22.5% of persons with mental health problems seeking any help for these, there was a clear treatment gap. Functional deficits were the strongest mediator of help-seeking, indicating that help is only sought when mental health problems have become more severe. Earlier help-seeking seemed to be mostly impeded by anticipated stigma towards help-seeking for mental health problems. Thus, factors or beliefs conveying such anticipated stigma should be studied longitudinally in more detail to be able to establish low-threshold services in future.