Outreach for Young Adult African Americans with Risk Factors for Stroke.

BACKGROUND: Research suggests that younger adult African American people (age 18-35 years) have more than double the risk of having a stroke than White people. Stroke risk education is lacking for this cohort; there is a dearth of materials that are targeted and focused for young adult African Americans. There is also little research on developing and testing age and culturally appropriate health literate materials that may help this population better understand personal risk factors for stroke. OBJECTIVE: The aim of this study was to understand factors to guide creating and disseminating plain language health messages about stroke risk awareness among young adult African Americans. METHODS: African American participants age 18 years and older completed an online survey (N = 413). Descriptive statistics, one-way analysis of variance, and two-step cluster analyses were used to evaluate stroke risk awareness, perceived risk of stroke, message creation factors, and online health information seeking behavior. Open-ended survey items described modifiable and non-modifiable reasons for perceived risk of stroke. KEY RESULTS: Participants reported differences on overall stroke risk factor awareness by perceived risk of stroke was significant (F[2, 409] = 4.91, p = .008) with the very low/low group (M = 1.66, p < .01), showing significantly lower overall stroke risk factor awareness compared to the moderate and high/very high groups. Both respondents who thought their stroke risk was very low/low and moderate/high/very high commented about family history (54.1% and 45.9%, respectively) as the reason and 88.2% of very low/low commented that they did not have risk factors for stroke because they were young. Cluster analysis indicated the Mostly Clear Preferences cluster was more likely to select mostly/very on positive, informational, and long-term messages and medical authority sources. The largest of three clusters reported medical sources as the highest rated source for both finding and trusting health information (47.2%, n = 195). CONCLUSION: Young adult African Americans have a scarce understanding of modifiable stroke risk factors; health education materials should focus on positive information messaging that shows a long-term result and is presented by a medical authority. We did not observe any age or sex differences among the data, which suggests different message modalities may not be needed. [HLRP: Health Literacy Research and Practice. 2024;8(1):e38-e46.].

PLAIN LANGUAGE SUMMARY: In this study, we collected data to create a targeted stroke risk awareness health education video for young African American adults (age 18 years and older). The video was based on analysis of data from 413 participants focusing on perception of stroke risk, stroke risk knowledge, as well as preference for message type, source credibility, and modality.

A deep learning approach for mental health quality prediction using functional network connectivity and assessment data.

While one can characterize mental health using questionnaires, such tools do not provide direct insight into the underlying biology. By linking approaches that visualize brain activity to questionnaires in the context of individualized prediction, we can gain new insights into the biology and behavioral aspects of brain health. Resting-state fMRI (rs-fMRI) can be used to identify biomarkers of these conditions and study patterns of abnormal connectivity. In this work, we estimate mental health quality for individual participants using static functional network connectivity (sFNC) data from rs-fMRI. The deep learning model uses the sFNC data as input to predict four categories of mental health quality and visualize the neural patterns indicative of each group. We used guided gradient class activation maps (guided Grad-CAM) to identify the most discriminative sFNC patterns. The effectiveness of this model was validated using the UK Biobank dataset, in which we showed that our approach outperformed four alternative models by 4-18% accuracy. The proposed model's performance evaluation yielded a classification accuracy of 76%, 78%, 88%, and 98% for the excellent, good, fair, and poor mental health categories, with poor mental health accuracy being the highest. The findings show distinct sFNC patterns across each group. The patterns associated with excellent mental health consist of the cerebellar-subcortical regions, whereas the most prominent areas in the poor mental health category are in the sensorimotor and visual domains. Thus the combination of rs-fMRI and deep learning opens a promising path for developing a comprehensive framework to evaluate and measure mental health. Moreover, this approach had the potential to guide the development of personalized interventions and enable the monitoring of treatment response. Overall this highlights the crucial role of advanced imaging modalities and deep learning algorithms in advancing our understanding and management of mental health.