Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches.

As mental health (MH) disorders become increasingly prevalent, their multifaceted symptoms and comorbidities with other conditions introduce complexity to diagnosis, posing a risk of underdiagnosis. While machine learning (ML) has been explored to mitigate these challenges, we hypothesized that multiple data modalities support more comprehensive detection and that non-intrusive collection approaches better capture natural behaviors. To understand the current trends, we systematically reviewed 184 studies to assess feature extraction, feature fusion, and ML methodologies applied to detect MH disorders from passively sensed multimodal data, including audio and video recordings, social media, smartphones, and wearable devices. Our findings revealed varying correlations of modality-specific features in individualized contexts, potentially influenced by demographics and personalities. We also observed the growing adoption of neural network architectures for model-level fusion and as ML algorithms, which have demonstrated promising efficacy in handling high-dimensional features while modeling within and cross-modality relationships. This work provides future researchers with a clear taxonomy of methodological approaches to multimodal detection of MH disorders to inspire future methodological advancements. The comprehensive analysis also guides and supports future researchers in making informed decisions to select an optimal data source that aligns with specific use cases based on the MH disorder of interest.

What drives low-income older adults' intention to use mobility applications?

AIM: Mobility applications have the potential to support low-income older adults in facing mobility challenges. However, there is a generally lower uptake of technology in this segment. To understand factors affecting the intention to use a mobility app, we drew upon the Protection Motivation Theory, and tested a model of low-income older adults' technology adoption. METHODS: A cross-sectional survey was conducted across seven states in Malaysia among community-dwelling low-income older adults aged ≥60 years old (n = 282). Measurement items were adapted from pre-validated scales and 7-point Likert Scales were used. Partial least squares structural equation modeling was utilized to assess the hypothesized model. RESULTS: Mobility technology awareness was found to shape an individual's threat and coping appraisals associated with their intention to use a mobility app. The decision of a low-income older adult to adopt a mobility app as a protective action is not a direct function of threat and coping appraisals but is indirect, and mediated by the underlying cost-benefit perceptions of non-adoption and adoption of the mobility app. In terms of technology perceptions, perceived usefulness is a significant predictor, but not perceived ease of use. CONCLUSIONS: This study entails a new model by uncovering the psychological factors encompassing mobility technology awareness, threat-coping appraisals, and cost-benefit perceptions on Technology Acceptance Model studies. These insights have important implications for the development and implementation of a mobility app among low-income older adults. Geriatr Gerontol Int 2024; 24: 342-350.