Depression is a prevalent mental health disorder that often remains unrecognized in real-world settings, and although artificial intelligence approaches using digital signals show promise for screening, many lack interpretability and rely on cloud-based processing that limits clinical use. This study developed and evaluated V3-Gemma, an on-device multimodal framework for depression screening based on a Clinical-Computational Alignment (CCA) approach that integrates visual, vocal, and verbal cues within a structured clinical reasoning architecture. A total of 130 adults (65 with depression and 65 controls) completed a one-minute picture-description task; 20 observable multimodal features were defined by clinicians and refined to a final set of 19, then implemented as structured prompts for a vision-audio-language model with hierarchical agent-based orchestration, with core inference running locally on-device. In the feature-based analysis, the random forest performed best on an independent test set (50 participants; AUC 0.779, sensitivity 0.84, specificity 0.52). In the criterion-level analysis, features mapped to DSM-5 symptom domains and combined using the DSM-5 rule yielded a test-set accuracy of 0.64 with high sensitivity (0.88) but limited specificity (0.40). Given the small test set, these results represent exploratory feasibility evidence. This proof-of-concept demonstrates a privacy-preserving, interpretable screening approach aligned with DSM-5 symptom domains, pending validation in larger, more diverse samples.
M. Jhon, Eunkyoung Jeon, Dae-Kwang Kim et al.· Scientific Reports· 0 citations
Abstract Background and Hypothesis Sleep disturbance is a well-established risk factor for suicide, though few studies to date have examined whether sleep disturbance contributes to suicide risk among individuals at clinical high risk for psychosis (CHR). The current study addressed this gap in the literature. We hypothesized that sleep disturbance would have a unique relationship with suicidal ideation/attempts when accounting for other variables in the model. We also hypothesized that the interaction between sleep disturbance/attenuated positive symptoms and sleep disturbance/stress would be related to suicidal ideation/attempts in CHR. Study Design The current study used data generated by the Accelerating Medicines Partnership® Schizophrenia Observational Study. The total sample included 1,048 participants (827 CHR and 221 community controls). Participants completed measures of suicidal ideation/attempts, attenuated positive symptoms, depressive symptoms, perceived stress, and sleep disturbance. Study Results Results supported a relationship between sleep disturbance and suicidal ideation/attempts in CHR, with participants who had lifetime ideation and attempts experiencing more sleep disturbance than those with no ideation or attempts. We also found small, but significant positive correlations between sleep disturbance and suicide risk in CHR. When accounting for other variables in the model, the effect of sleep disturbance remained significant for past month ideation, but not lifetime ideation or attempts. Both interaction models were non-significant. Conclusions Our findings highlight the potential value of sleep measures in early identification and treatment of suicide risk in CHR. Further research in this area is warranted.
H. Wastler, Aubrey M. Moe, Alexandra M Blouin et al.· Schizophrenia Bulletin Open· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
