Towards Transparent Mental Health Insights: An Explainable AI Model for Career-Related Depression and Anxiety Among University Students Using Structured Data

Arsham Azam; Rasikh Ali; Tayyaba Farhat; Sheeraz Akram

cs.AIJun 19, 2026

Towards Transparent Mental Health Insights: An Explainable AI Model for Career-Related Depression and Anxiety Among University Students Using Structured Data

Authors: Arsham Azam, Rasikh Ali, Tayyaba Farhat, Sheeraz Akram

Organizations: Faculty of Computer Science and Information Technology, The Superior University, Lahore 54600, Pakistan · Intelligent Data Visual Computing Research (IDVCR), Lahore 54600, Pakistan · Information Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 12571, Saudi Arabia

Abstract

Career anxiety and depression among university students present a growing challenge to mental health and academic achievement. This study proposes an Explainable AI (XAI) framework using multimodal data and Federated Learning (FL) to identify early indicators of career-related mental health problems in a privacy-preserving and culturally responsive manner. The framework combines structured behavioral data and facial emotion features from interview videos via an intermediate fusion neural network with attention mechanisms. Label smoothing was applied to improve model generalizability. FL was used across institutions to enable collaborative training without raw data sharing. Evaluation was conducted using the Student Mental Health Survey dataset from university students across Pakistan. Our model attained an F1-score of 89.12%, recall of 86.54%, accuracy of 92.08%, and precision of 91.88%. Using Integrated Gradients and SHAP, the model identified key behavioral markers of depression including avoidance of direct gaze, lower facial expressiveness, and social withdrawal, consistent with psychological theory. This research presents an interpretable, scalable, and context-sensitive AI system for mental health pre-diagnosis with potential integration into student support services globally.

Explore similar work

Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts
Jul 12, 2026Alireza Dehghan, Negin AshrafiXai Mental Health
FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
May 18, 2026Nuredin Ali Abdelkadir, Anjali Ratnam, Zeerak Talat +1Federated Learning Mental Health
Ensemble Feature Selection and Harris Hawks Optimization for Explainable Mental Health Risk Prediction in Female Sex Workers
Jun 23, 2026Ahnaf Atef Choudhury, Md. Parvej Hoque Palash, Shahriar Siddique Ayon +2Mental Health Xai

Jul 12, 2026 · cs.LGJ/K move · Enter open · S save

Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts

Alireza Dehghan, Negin Ashrafi

Sharif University of Technology, Tehran, Iran · University of Southern California, California, USA

Explainable machine learning (XML) pipelines applied to composite mental health outcomes can produce apparently-robust, cross-population-stable risk hierarchies that are largely artefacts of how the outcome was constructed. We demonstrate this using an ElasticNet pipeline applied to 886 medical students at the University of Lausanne (primary cohort, 2022), validated across 2,580 longitudinal observations at three time points and 701 non-medical students from eight faculties; all three datasets share identical instruments. The pipeline produces a hierarchy in which trait anxiety and health satisfaction dominate wherever the outcome is measured, with Kendall

τ= 1.0

for the top-two positions across all five evaluation sets and consistent transfer performance (

R^2

: 0.41-0.49). Two residualization experiments, which isolate shared variance between correlated variables via regression, reveal the mechanism: when trait anxiety (STAI-T) is residualized against the co-included depression subscale (CES-D,

r = 0.72

), model

R^2

drops from 0.41 to 0.16 and STAI-T falls from rank 1 to rank 6; when burnout subscales are residualized against CES-D,

R^2

collapses to 0.016. Prediction intervals average 35.4 units on a 0-100 scale (2.4 outcome standard deviations), independently ruling out individual-level deployment. The residualization protocol is the paper's transferable contribution: any XAI study combining correlated predictor and outcome constructs should apply this check before interpreting apparent stability as a finding.

Xai Mental Health Clinical Prediction Fears

Open paper Ask about it PDF

Abstract

Explore similar work

Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts

FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data

Ensemble Feature Selection and Harris Hawks Optimization for Explainable Mental Health Risk Prediction in Female Sex Workers