Mental well-being is a worldwide priority of health systems. Nevertheless, the diagnosis and recovery rates are still low. Thiswork demonstrates an Artificial Intelligence (AI)-based, entertainment-oriented, engaging assistant that can deliver on-demand,non-judgmental assessment in an accessible, scalable, and personalised way to people affected by anxiety and depression. Forthis purpose, we combine Machine Learning (ML) and Large Language Models (LLMs) in a stream-based framework. Here,the LLMs are exploited to extract high-level reasoning features from natural language utterances for an accurate ML predictionmodel. During a study lasting for 14 months, the participants, 146 users mostly within the 65–80 age range, used the conversa-tional assistant. Each user was free to participate as they pleased, with average individual activity times of 4.5 months. Duringtheir participation, each user completed an average of two standard mental condition tests, which allowed updating the mentalcondition tags for classifier retraining in streaming mode. Our solution achieved promising results for detecting anxiety and de-pression in free dialogues, with accuracy metrics exceeding 90%, outperforming competing works from the literature. Moreover,prior research on anxiety and depression detection has often been limited to providing binary outcomes without explanationsbehind their rationale. Therefore, this work also addresses interpretability by automatically explaining its prediction in naturallanguage. The contributions of this work are threefold: (i) detecting mental conditions from free dialogues in real-time withminimal supervision, (ii) conducting a non-invasive longitudinal analysis based on user engagement, and (iii) automaticallyproviding explanations of the predictive capabilities of the solution. Our approach, supporting continuous interactions suitablefor longitudinal studies, combined with explainability mechanisms, connects directly with several strategic lines promoted bythe European Union (EU). In particular, the emphasis on early prevention and detection is aligned with a conversational toolthat monitors indicators over time. Similarly, the EU promotes transparency, ethical governance, and trust in digital health tech-nologies, as well as data interoperability and common standards as part of the push toward the European Health Data Space. Inthis context, incorporating explainability, that is, providing the user or researcher with understandable reasons for the model'sinferences, strengthens acceptability, accountability, and alignment with good digital governance principles. In this way, ourapproach contributes to translating the European objectives of promoting accessible, safe, ethical, and evidence-based digitalmental health tools into practice, while facilitating longitudinal monitoring and proactive intervention.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium,provided the original work is properly cited.© 2026 The Author(s). Expert Systems published by John Wiley & Sons Ltd.
Méndez et al. (Thu,) studied this question.