Calibrated Deep-Learning Risk Indexing and Latent Behavioural Profiling for Occupational Mental-Health Risk Assessment.

Occupational mental-health risk in knowledge-work settings is an important public-health and psychosocial-support concern because workload demands, career insecurity, limited mentoring, uneven institutional support and barriers to care can increase psychological risk, including in early-career academic environments. Workplace well-being assessments rely on aggregate survey summaries or conventional prediction models, limiting calibration, interpretability, subgroup evaluation and transfer validation. This study develops a computational-intelligence framework for public mental-health decision support using heterogeneous workplace survey data with early-career academics treated as a motivating knowledge-work context rather than as the direct empirical cohort. The proposed approach combines attention-based tabular learning, variational autoencoder latent profiling, stacked ensemble prediction, probability calibration, feature attribution, perturbation analysis, fairness assessment and cross-dataset adaptation. Calibrated probabilities are converted into a transparent 0-100 risk index to support preventive outreach, psychosocial-support planning and resource-allocation decisions. The model is compared with baselines, including logistic regression, support vector machine, random forest, XGBoost, LightGBM, CatBoost, TabNet, FT-Transformer, NODE and DCN. Results show strong held-out performance with AUC = 0.885, average precision = 0.872, F1 = 0.808, Brier score = 0.145 and expected calibration error = 0.022, outperforming tested baselines. Five-fold robustness analysis produced a conservative mean test AUC of 0.809±0.044, indicating moderate partition sensitivity. Key predictors include work interference, perceived stress, care access and support variables. Latent profiling identifies two behavioural subgroups with distinct risk patterns. After feature harmonization, target-domain adaptation and recalibration, external evaluation on an occupational burnout dataset achieves AUC = 0.941 and average precision = 0.936, supporting calibrated, interpretable and subgroup-aware decision support under dataset shift.