<![CDATA[Advances in digital sensor technology and artificial intelligence (AI) are expanding approaches to mental health monitoring through continuous data collection in everyday settings. Smartphones, wearable sensors, and digital monitoring systems enable the acquisition of behavioral, physiological, and cognitive data that can reflect an individual’s emotional dynamics, stress levels, mood changes, and psychological state. This article presents a narrative literature review that synthesizes developments in the integration of psychophysiological data and AI in digital mental health monitoring. The review covers various data sources, including neural signals, physiological indicators from wearable sensors, behavioral patterns obtained through smartphone sensing, and psychometric indicators. The analysis also covers AI approaches for multimodal data processing, ranging from machine learning and deep learning architectures to multimodal fusion strategies. The literature indicates that integrating various modalities through AI approaches has the potential to yield a more comprehensive representation of mental state dynamics by linking biological responses, daily behavioral patterns, and cognitive indicators. Despite this potential, the development of digital mental health systems still faces challenges related to dataset limitations, the heterogeneity and synchronization of multimodal data, model generalization, as well as issues of privacy and algorithmic transparency. This synthesis positions digital psychophysiology as an integrative framework that links psychophysiological measurements, digital phenotyping, and AI-based analytics to support the development of adaptive, multimodal, and sustainable mental health monitoring systems]]>
Copyrights © 2026
