Individuals with schizophrenia have higher mortality and shorter lifespans. There are a multitude of factors which create these conditions, but one aspect is worse physical health, particularly cardiovascular and metabolic health. Many interventions to improve the health of individuals with schizophrenia have been created, but on the whole, there has been limited effectiveness in improving quality of life or lifespan. One potential new avenue for inquiry involves a more patient-centric perspective; understanding aspects of physical health most important, and potentially most amenable to change, for individuals based on their life narratives. This study used topic modeling, a type of Natural Language Processing (NLP) on unstructured speech samples from individuals (n = 366) with serious mental illness, primarily schizophrenia, in order to extract topics. Speech samples were drawn from three studies collected over a decade in two geographically distinct regions of the United States. Several health-related topics emerged, primarily centered around food, living situation, and lifestyle (e.g., routine, hobbies). The implications of these findings for how individuals with serious mental illness and schizophrenia think about their health, and what may be most effective for future health promotion policies and interventions, are discussed.

Objective: Evaluating pauses in natural speech is a promising strategy for improving reliability, validity, and efficiency in assessing cognitive functions in people with mild cognitive impairment (MCI) and Alzheimer’s dementia (AD). Method: We conducted a quantitative meta-analysis of studies employing automated pause analysis. We included measures of speaking rate for comparison. Results: We identified 13 studies evaluating pause measures and 8 studies of speaking rate in people with MCI ( n ’s = 276 & 109, respectively) and AD ( n ’s = 170 & 81, respectively) and healthy aged controls ( n ’s = 492 & 231, respectively). Studies evaluated speech across various tasks, including standard neuropsychological, reading, and free/conversational tasks. People with AD and MCI showed longer pauses than controls at approximately 1.20 and 0.62 standard deviations, respectively, though there was substantial heterogeneity across studies. A more modest effect, of 0.66 and 0.27 SD s, was observed between these groups in speech rate. The largest effects were observed for standardized memory tasks. Conclusions: Of the many ways that speech can be objectified, pauses appear particularly important for understanding cognition in AD. Pause analysis has the benefit of being face valid, interpretable in ratio format as a reaction time, tied to known socio-cognitive functions, and relatively easy to measure, compute, and interpret. Automation of speech analysis can greatly expand the assessment of AD and potentially improve early identification of one of the most devastating and costly diseases affecting humans.

Developing digital technologies for quantifying symptoms of serious mental illness (SMI) has been a focus of research for over 7 decades. Recent efforts have focused on multimodal feature integration, which captures conceptually distinct behavioral domains. We evaluated links between nonverbal digital features and human-rated negative symptoms, with the expectation that their relationship would depend on verbal information (i.e., be moderated by language emotional tone). We believe this better approximates how humans integrate verbal and nonverbal information when making clinical ratings. Mobile video diaries were evaluated for people with SMI, those at clinical high risk for developing SMI, and control groups (Ns = 48, 20, 36, and 21, respectively; K videos = 902, 440, 602, and 399, respectively). We identified six features (i.e., capturing positive and neutral facial expressions, vocal intonation and emphasis, and speaking pause length and articulation rate) that showed acceptable reliability (final N and K for video/audio analysis = 109/912 and 120/2,200, respectively), but most features failed to show acceptable reliability. Videos were behaviorally rated for alogia and blunted vocal and facial affect. Relationships between nonverbal features and human ratings were dependent on verbal tone, but only when verbal tone was positive in valence. For example, behaviorally rated alogia was associated with longer pauses, but primarily when language had a positive tone. These results support a relatively novel approach to multimodal digital phenotyping, one that emphasizes using multimodal features to provide "context" in the way that humans likely interpret and integrate multimodal streams of information. (PsycInfo Database Record (c) 2026 APA, all rights reserved).