Hopkins AITC announces awardees of second funding round

The Johns Hopkins Artificial Intelligence and Technology Collaboratory for Aging Research (JH AITC) has announced its second round of grant funding, totaling just over $1 million, to support artificial intelligence technologies that will improve the long-term health and independence of older adults.

Through a competitive national grant review process, five applicants from academia, industry, and clinical practice were selected for funding. The awards will support a diverse set of research projects and technologies that are poised to better the health and quality of life of millions of older Americans and their caregivers. Earlier this year, the first round distributed nearly $3 million to 14 pilot projects that are now underway.

Launched in 2021 with a $20 million grant from the National Institute on Aging, the JH AITC is a hub for innovations related to aging and cross-disciplinary collaboration throughout the Johns Hopkins community. A primary goal of the AITC is to connect this research network with outside stakeholders, including older Americans and caregivers, technology developers, and industry partners.

The five grant awardees will each receive up to $200,000 in direct costs over a one-year period, during which awardees also receive access to resources and mentorship from JHU experts in fields including computer science, nursing, medicine, and technology commercialization.

"At the intersection of technology and geriatrics, we are pioneering a future where artificial intelligence brings resilience and autonomy back into the lives of older adults. The projects we support are more than just advances in health care: They are our commitment to nurturing a society where aging is associated with opportunities for growth, not decline," said Peter Abadir, associate professor of medicine and co-principal investigator of the JH AITC. "We are investing in a future that empowers our seniors."

This round, the JH AITC has invested in research that leverages AI to address cognitive decline in older adults. Tracy Vannorsdall, an associate professor in the Department of Psychiatry and Behavior Sciences and the Department of Neurology at Johns Hopkins School of Medicine, is leading a project that will apply machine learning to predict post-COVID-19 cognitive decline and dementia.

While COVID-19 can be associated with cognitive changes in patients of any age, it may also increase older adults' risk for Alzheimer's disease, said Vannorsdall.

"The COVID-19 pandemic has widened health disparities such that older adults and members of underrepresented minority groups have been disproportionately impacted. These groups, as well as older adults in rural communities, face challenges in accessing dementia care. We are working to develop a novel means of evaluating the impact of COVID-19 on the cognitive health and dementia risk of older at-risk adults, and to do so in a manner that facilitates access for those in low resource settings," she said.

Utilizing a mobile app called the DANA Cognitive Assessment Tool, the team will assess cognitive functioning in a cohort of older adults who received care for COVID-19 in the Johns Hopkins Medical System. The study will gather cognitive data from participants in their own homes, in real time, over a three-month period.

The team aims to apply machine learning techniques to the DANA data to develop algorithms that more accurately predict risk for post-COVID-19 cognitive decline. Vannorsdall says the project's long-term goal is to design a tool to predict Alzheimer's disease-related cognitive decline earlier and with greater accuracy than existing methods, while minimizing patient burden and maximizing accessibility to those in resource-limited areas.

Other projects and researchers funded this round include:

• Neuroanatomic validation of digital voice (Vijaya Kolachalama, Boston University): The project will use speech recordings, neuroimaging, and neuropathology data from the Framingham Heart Study to develop and validate interpretable deep learning models for ADRD assessment.
• EZ-Aware: Digital Twin for wearable-enabled, AI-supported assessment of cognitive impairment (Kunal Mankodiya, EchoWear LLC): Assessment of cognitive functioning for early detection is critical to identify individuals who might benefit from treatment with the available symptomatic medications for mild dementia. This project aims to improve the early detection of mild cognitive impairment (MCI) in older adults using a prototype of a Digital Twin technology that is integrated into age-friendly digital health services hosted by the EZ-Aware platform. If successful, the system will produce the first type of ecologically valid data on older adults, combining the cognitive and function measures in daily life settings.
• Geriatric functional assessment system using passive wearable sensing and deep learning (John A. Batsis, The University of North Carolina at Chapel Hill School of Medicine): The team will develop a clinic-based Geriatric Functional Assessment System (GFAS). During primary care visits, an older adult will wear a badge-like wearable in common clinical areas to collect visual and motion data in a non-intrusive way. The GFAS will simplify the extraction of clinically useful functional data from the clinic visit as a first step to monitoring physical function in older adults. Ultimately, the system will allow clinicians to implement interventions to promote and maintain healthy aging.
• A novel insole solution used in daily life to identify and mitigate falls and frailty (Linda Denney, Tufts University School of Medicine): The team will validate a new portable pressure sensing insole technology, enabling more efficient and effective collection of clinically relevant balance data to predict and treat falls in the elderly.