Loneliness and social isolation are not associated with executive functioning in a cross-sectional study of cognitively healthy older adults.

The literature on the relationship between social interaction and executive functions (EF) in older age is mixed, perhaps stemming from differences in EF measures and the conceptualization/measurement of social interaction. We investigated the relationship between social interaction and EF in 102 cognitively unimpaired older adults (ages 65-90). Participants received an EF battery to measure working memory, inhibition, shifting, and global EF. We measured loneliness subjectively through survey and social isolation objectively through naturalistic observation. Loneliness was not significantly related to any EF measure (p-values = .13-.65), nor was social isolation (p-values = .11-.69). Bayes factors indicated moderate to extremely strong evidence (BF01 = 8.70 to BF01 = 119.49) in support of no relationship.. Overall, these findings suggest that, among cognitively healthy older adults, there may not be a robust cross-sectional relationship between EF and subjective loneliness or objective social isolation.

The paucity of morality in everyday talk.

Given its centrality in scholarly and popular discourse, morality should be expected to figure prominently in everyday talk. We test this expectation by examining the frequency of moral content in three contexts, using three methods: (a) Participants' subjective frequency estimates (N = 581); (b) Human content analysis of unobtrusively recorded in-person interactions (N = 542 participants; n = 50,961 observations); and (c) Computational content analysis of Facebook posts (N = 3822 participants; n = 111,886 observations). In their self-reports, participants estimated that 21.5% of their interactions touched on morality (Study 1), but objectively, only 4.7% of recorded conversational samples (Study 2) and 2.2% of Facebook posts (Study 3) contained moral content. Collectively, these findings suggest that morality may be far less prominent in everyday life than scholarly and popular discourse, and laypeople, presume.

Predicting Working Memory in Healthy Older Adults Using Real-Life Language and Social Context Information: A Machine Learning Approach.

BACKGROUND: Language use and social interactions have demonstrated a close relationship with cognitive measures. It is important to improve the understanding of language use and behavioral indicators from social context to study the early prediction of cognitive decline among healthy populations of older adults. OBJECTIVE: This study aimed at predicting an important cognitive ability, working memory, of 98 healthy older adults participating in a 4-day-long naturalistic observation study. We used linguistic measures, part-of-speech (POS) tags, and social context information extracted from 7450 real-life audio recordings of their everyday conversations. METHODS: The methods in this study comprise (1) the generation of linguistic measures, representing idea density, vocabulary richness, and grammatical complexity, as well as POS tags with natural language processing (NLP) from the transcripts of real-life conversations and (2) the training of machine learning models to predict working memory using linguistic measures, POS tags, and social context information. We measured working memory using (1) the Keep Track test, (2) the Consonant Updating test, and (3) a composite score based on the Keep Track and Consonant Updating tests. We trained machine learning models using random forest, extreme gradient boosting, and light gradient boosting machine algorithms, implementing repeated cross-validation with different numbers of folds and repeats and recursive feature elimination to avoid overfitting. RESULTS: For all three prediction routines, models comprising linguistic measures, POS tags, and social context information improved the baseline performance on the validation folds. The best model for the Keep Track prediction routine comprised linguistic measures, POS tags, and social context variables. The best models for prediction of the Consonant Updating score and the composite working memory score comprised POS tags only. CONCLUSIONS: The results suggest that machine learning and NLP may support the prediction of working memory using, in particular, linguistic measures and social context information extracted from the everyday conversations of healthy older adults. Our findings may support the design of an early warning system to be used in longitudinal studies that collects cognitive ability scores and records real-life conversations unobtrusively. This system may support the timely detection of early cognitive decline. In particular, the use of a privacy-sensitive passive monitoring technology would allow for the design of a program of interventions to enable strategies and treatments to decrease or avoid early cognitive decline.

A multimodal imaging study in U.S. veterans of Operations Iraqi and Enduring Freedom with and without major depression after blast-related concussion.

Although the exact number of affected individuals is unknown, it has been estimated that approximately 20% of U.S. veterans of Operations Enduring Freedom (OEF) and Iraqi Freedom (OIF) have experienced mild traumatic brain injury (mTBI) (i.e., concussion), which is defined as a brief loss or alteration of consciousness from a blow or jolt to the head. Blast exposure is among the most common causes of concussion in OEF-OIF warriors. Although the mechanism is unknown, major depressive disorder (MDD) after head injury is common. The purpose of this study was to use diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI) to examine the structural and functional neural correlates of MDD in OEF-OIF combat veterans with a self-reported history of blast-related concussion. We hypothesized that subjects in the MDD group (i.e., individuals with a history of blast-related concussion who were experiencing current MDD) relative to individuals in the non-MDD group (i.e., individuals with a history of blast-related concussion but no current or lifetime history of MDD) would show amygdala hyperactivity and disruption of white matter tracts connecting prefrontal and limbic brain regions. To test these hypotheses, 11 MDD and 11 non-MDD individuals underwent DTI and performed a validated emotional face matching task during fMRI. MDD relative to non-MDD individuals showed greater activity during fear matching trials in the amygdala and other emotion processing structures, lower activity during fear matching trials in emotional control structures such as the dorsolateral prefrontal cortex and lower fractional anisotropy (FA) in several white matter tracts including the superior longitudinal fasciculus (SLF). Greater depressive symptom severity correlated negatively with FA in the SLF. These results suggest a biological basis of MDD in OEF-OIF veterans who have experienced blast-related concussion, and may contribute to the development of treatments aimed at improving the clinical care of this unique population of wounded warriors.

Deep multiple instance learning for foreground speech localization in ambient audio from wearable devices.

Over the recent years, machine learning techniques have been employed to produce state-of-the-art results in several audio related tasks. The success of these approaches has been largely due to access to large amounts of open-source datasets and enhancement of computational resources. However, a shortcoming of these methods is that they often fail to generalize well to tasks from real life scenarios, due to domain mismatch. One such task is foreground speech detection from wearable audio devices. Several interfering factors such as dynamically varying environmental conditions, including background speakers, TV, or radio audio, render foreground speech detection to be a challenging task. Moreover, obtaining precise moment-to-moment annotations of audio streams for analysis and model training is also time-consuming and costly. In this work, we use multiple instance learning (MIL) to facilitate development of such models using annotations available at a lower time-resolution (coarsely labeled). We show how MIL can be applied to localize foreground speech in coarsely labeled audio and show both bag-level and instance-level results. We also study different pooling methods and how they can be adapted to densely distributed events as observed in our application. Finally, we show improvements using speech activity detection embeddings as features for foreground detection.

Natural, Everyday Language Use Provides a Window Into the Integrity of Older Adults' Executive Functioning.

OBJECTIVES: Language markers derived from structured clinical interviews and assessments have been found to predict age-related normal and pathological cognitive functioning. An important question, then, is the degree to which the language that people use in their natural daily interactions, rather than their language elicited within and specifically for clinical assessment, carries information about key cognitive functions associated with age-related decline. In an observational study, we investigated how variability in executive functioning (EF) manifests in patterns of daily word use. METHOD: Cognitively normal older adults (n = 102; mean age 76 years) wore the electronically activated recorder, an ambulatory monitoring device that intermittently recorded short snippets of ambient sounds, for 4 days, yielding an acoustic log of their daily conversations as they naturally unfolded. Verbatim transcripts of their captured utterances were text-analyzed using linguistic inquiring and word count. EF was assessed with a validated test battery measuring WM, shifting, and inhibitory control. RESULTS: Controlling for age, education, and gender, higher overall EF, and particularly working memory, was associated with analytic (e.g., more articles and prepositions), complex (e.g., more longer words), and specific (e.g., more numbers) language in addition to other language markers (e.g., a relatively less positive emotional tone, more sexual and swear words). DISCUSSION: This study provides first evidence that the words older adults use in daily life provide a window into their EF.