The paper introduces Score-Guided Classification (SGC), a novel framework that uses an unsupervised anomaly score as a 'Pathological Prior' to guide EEG-based depression detection, overcoming the limi…

A self-evolving annotation framework for Major Depressive Disorder using large language models and expert verification is proposed to improve annotation consistency and explainability.

This study compares multiple post-hoc explainable AI methods (e.g., DeepSHAP, GradCAM) to interpret how deep learning models use EEG data to detect Major Depressive Disorder, finding that while method…

A patient-independent multimodal depression detection framework is proposed, which incorporates domain generalization and jointly leverages acoustic and textual modalities.

This paper proposes CLeaD, a framework for cross-lingual depression detection using contrastive alignment of WavLM embeddings from English and Mandarin.

This paper conducts a systematic review of non-social media, free-text datasets for mental health research, revealing their predominant focus on English and depression detection, and identifying key g…

This paper compares six aggregation architectures for speech-based depression detection using a controlled benchmark with six frozen speech backbones on English and Mandarin depression corpora.

This paper evaluates the predictive role of Linguistic Inquiry and Word Count (LIWC) in modern multimodal systems for depression-related language using five English and Chinese corpora and asks whethe…

This paper investigates why self-harm prediction models struggle to generalize across different hospitals, finding that variations in local lexical expression and feature importance are the primary ca…

This paper systematically evaluates how LLMs uncritically adapt to potentially dangerous user prompts related to eating disorders, finding that specific linguistic cues significantly increase the like…

The paper finds that while LLMs can detect distress regardless of delusional framing, they significantly fail to intervene safely when distress is intertwined with delusion, suggesting a critical reco…

The paper proposes TAAC, a novel framework that enables accurate depression detection from audio while ensuring user privacy by selectively encrypting sensitive identity information.

This paper introduces a Generative AI-augmented UXR methodology, grounded in the UXR Point of View (PoV) Playbook, to design Neuroinclusive digital interventions for emotional regulation in adults wit…

This paper proposes a multimodal cognitive impairment detection framework using large language models that integrates speech audio and transcripts, achieving a high classification accuracy.

The paper proposes GraD-IBD, a graph-based model that reformulates longitudinal ICD diagnosis codes into temporally directed graphs to efficiently and accurately detect the risk of Inflammatory Bowel…

This paper proposes PsyBridge, a hybrid intelligent decision-support framework for multi-dimensional mental health assessment using clinically validated screening tools, cognitive evaluation, and pers…

This paper derives deterministic equivalents for the prediction risk of over-parameterized linear regression with degenerate covariance matrices and dependent covariates, and identifies the configurat…

This paper proposes a voice concept bottleneck framework for interpretable health assessment using an audio language model.

The study demonstrates that LLMs exhibit significant, language-driven disparities in medical triage recommendations, recommending emergency care more frequently for English and Arabic prompts, even wh…

UniD$^3$ is a novel Knowledge Graph-enhanced RAG framework that processes vast biomedical literature to systematically extract, organize, and validate comprehensive drug-disease knowledge, achieving h…