With the rise of wearable sensors, advancement in comprehensible artificial intelligence (AI) algorithms, and growing acceptance of AI in medicine, AI has great potential to more reliably diagnose, prognose, and treat mental illnesses. The rapidly rising number of older adults worldwide presents a unique challenge for clinicians due to increased mental health needs in the setting of a dwindling clinical workforce. AI has enabled researchers to better understand mental illnesses by taking advantage of ‘big data.’

This symposium will present an overview of novel research leveraging AI (machine learning, natural language processing) to better track, understand, and support mental health and cognitive functioning in older adults.

Helmet Karim, PhD will present on prediction of treatment response in late-life major depressive disorder and the implications of those models.

Ellen Lee, MD will present on using natural language processing to understand psychosocial functioning in older adults.

Ipsit Vahia, MD will present on radio-based sensors to phenotype changes in behavior patterns that may correlate with a range of geropsychiatric symptoms.

Andrea Iaboni, MD DPhil FRCPC will present on multimodal wearable and vision-based sensors for the detection and categorization of behavioural symptoms of dementia.

The symposium includes three physician-scientists (Iaboni, Lee, Vahia), two women (Iaboni, Lee), and two early career faculty (Lee, Karim – co-chairs). The symposium represents four different institutions across the country (McLean/Harvard, Toronto Rehabilitation Institute/University of Toronto, UC San Diego, University of Pittsburgh) and four very different approaches using AI technology to improve understanding and outcomes in the field of geriatric mental health.

The symposium seeks to address the underutilization of AI in psychiatric research, especially in the field of aging research. The increased individual-level heterogeneity associated with aging; complex trajectories of decline in cognitive, mental, and physical health; and lack and slow adoption of older adult-centered technologies present great challenges to advancing the field. However, advances in the field of explainable AI and transdisciplinary development of AI approaches can address the unique challenges of aging research.

Alzheimer’s disease (AD) and dementia has emerged as a significant societal issue and a global priority. The prevalence of dementia is rising more rapidly in low and middle income countries (LMIC) than in high income countries. A growing body of evidence shows that prevention through risk factor management is the key to reducing the burden of dementia in the society, especially in LMIC. However, a one-size-fits all approach to health promotion is neither efficient nor effective. Latin American countries (LAC) have unique challenges related to dementia, including rapid aging population, high admixture degree and risk factors profile, which influence the prevalence and presentation of dementia. During this session, we will present findings and tools that will help tailor and personalize risk factor management in Hispanics populations. Participants will be first introduced to genetics of Alzheimer disease in Hispanic populations relative to non-Hispanics and the influence of gene by environment interactions. The second presentation will report on the epidemiology and risk factors of AD using cross countries/society comparisons (Non-Hispanics whites vs Hispanics living in US vs Hispanics living in Latin America.) The third presenter will discuss the development of a tool that visualizes how each risk factor contributes to the risk of dementia and how one may lower their risk by addressing the risk factors. The tool can be used in primary care settings in Cuba, Dominican Republic and Puerto Rico. Finally, the fourth presenter uses state-of-the-art digital assessment tools (brain health assessment), for low-cost monitoring of cognitive functioning, MCI and dementia. Such instruments are important for future evaluation of the impact of preventive strategies. At the end of the presentations, attendees will be able to identify the unique genetic and social determinants that drive AD in LAC. Recommendations will be given for preventive strategies tailored to LMIC. The findings to be shared will be essential for building evidence-based interventions tailored to reducing the burden of dementia in the Hispanic populations.

Session Chair:

Juan Llibre Rodriguez

Alzheimer Disease and genetics in Hispanic Populations

Jorge J Llibre-Guerra

Alzheimer disease epidemiology and risk factors in Caribbean and non-Caribbean Hispanics populations.

Ivonne Z. Jiménez Velázquez

Development of a tool to motivate for healthy behaviors to prevent dementia in the Caribbean.

Daisy Acosta

A brief digital cognitive assessment for detection of cognitive impairment in Hispanics populations.

Ana Rodriguez-Salgado