Author: Elizabeth

Awardee Organization(s): Kennesaw State University
Principal Investigator(s): Maria Valero, PhD, MsC | Katherine Ingram, PhD
Official Project Title: GlucoCheck: A Non-Invasive & AI-Assisted Blood Glucose Monitoring Device for Older Adults
AITC Partner: PennAITech
Website(s):
https://ccse.kennesaw.edu
Iotas.kennesaw.edu

The GlucoCheck project presents a significant advancement in the realm of diabetes management, with a specific focus on enhancing the quality of life for older adults. In light of the escalating global prevalence of diabetes and its associated complications, the imperative for non-invasive, accurate, and user-friendly blood glucose monitoring has never been more pronounced. Diabetes poses severe health risks, particularly for older adults, making effective and comfortable glucose monitoring paramount. Existing methods, characterized by frequent finger-pricking and subcutaneous needle implants, entail discomfort, infection risks, and potential tissue damage, particularly in individuals with diminished skin elasticity and compromised immune responses. GlucoCheck emerges as a pioneering solution, harnessing near-infrared spectroscopy (NIR) technology augmented by AI. This device offers a non-invasive means of consistently monitoring blood glucose levels by simply wearing it on one’s finger. Importantly, GlucoCheck integrates AI algorithms that adapt to individual skin attributes, including color and texture, enhancing precision across diverse demographics. This project’s core objectives encompass rigorous validation of GlucoCheck’s efficacy, with a primary emphasis on older adult demographic. Comparative analyses will be conducted, aligning GlucoCheck’s measurements with conventional blood glucose monitors to ascertain accuracy and reliability. Our mission is underscored by the desire to deliver an efficacious, user-centric device tailored to the unique requirements of older adults. The project’s outcomes will furnish valuable insights that drive refinements in GlucoCheck, propelling us closer to positively impacting the livesof millions of individuals grappling with diabetes.

Awardee Organization(s): etectRx
Principal Investigator(s): Tony C. Carnes, PhD
Official Project Title: Real-Time Remote Monitoring of Confirmed Medication Adherence
AITC Partner: PennAITech
Website(s): https://etectrx.com

Medication non-adherence is responsible for up to $300 billion of avoidable healthcare costs in the United States with patients over 60 years of age consuming 50% of dispensed prescription drugs. This project enables real-time, remote monitoring of medication ingestions and enhances patient and caregiver feedback to help patients stay adherent and thus extend the time they are able to age grace fully at home.
The existing FDA-cleared IDCap system detects ingested medication signals using a watch or lanyard-style reader worn by the patient and forwards information to a server through an app on a patient’s smart phone. In this proposal we are looking to remove the individuals’ worn reader from the system and replace it with a series of readers placed in multiple locations in a person’s home to ensure ingestion detection without the user changing their usual behavior. Additionally, the new readers will interface with Alexa to facilitate audible and visual reminders and confirmations of medication ingestion. If the end user allows, remote care providers will be able to participate in the adherence journey and intervene when needed.

Awardee Organization(s): New York University Rory Meyers College of Nursing
Principal Investigator(s): Ab Brody, PhD, RN, FAAN
Official Project Title: Aliviado Dementia Care Machine Learning Algorithm Development for Caregiving
AITC Partner: PennAITech
Website(s):
https://www.aliviado.org
http://nursing.nyu.edu
https://www.hign.org

Care partners (CP) of persons living with dementia (PLWD) provide crucial support and find significant meaning in the care they provide. They show compassion to those they are caring for, and resilience in the face of adversity. Yet, many CP lack high-quality, evidence-based guidance for addressing care needs of PLWD. One key area that is often challenging to CP, yet where they have little support, is in addressing neuropsychiatric symptoms (NPS) such as agitation or wandering. Most PLWD experience more than one NPS at a time and thus not only do CP lack support in managing these symptoms, they don’t know which symptom to focus on first to reduce their burden and improve the quality of life of the PLWD. This is particularly true in underserved and marginalized communities who are less likely to have access to comprehensive dementia care or supportive services. Higher NPS, particularly in marginalized CP, greatly increases the risk of CP burden, physical and mental health challenges. To help CP make decisions about what NPS to prioritize, we will use artificial intelligence/machine learning (AI/ML) to develop a precision clinical decision support algorithm to assist CP in prioritizing which NPS to treat. The algorithm will be inserted into a user-friendly smartphone application which CP can download through the iOS or Android app store. The app will increase access to high-quality dementia support, empower CP to better manage NPS and improve the quality of life for both themselves and the PLWD.

Awardee Organization(s): VNS Health | Columbia University Irving Medical Center
Principal Investigator(s): Maryam Zolnoori, PhD
Official Project Title: A Speech-Processing Algorithm for Automatic Screening of African American Patients with Mild Cognitive Impairment and Early Dementia in Home Health Settings
AITC Partner: PennAITech
Website(s):
https://www.cuimc.columbia.edu
http://vnshealth.org

Mild cognitive impairment (MCI) and early-stage dementia (ED) are prevalent concerns, impacting one-in-five adults over age 60. Alarmingly, a significant percentage of these cases remain undiagnosed, leading to missed timely interventions. Our data emphasizes that African American seniors are particularly vulnerable, with existing disparities in healthcare access, biases, and varying health literacy levels exacerbating the situation. A novel observation we intend to leverage is the correlation between linguistic shifts and the onset of cognitive issues. Language, a foundational element of cognition, exhibits early perturbations during cognitive decline. The nuances of these changes can vary across racial boundaries, influenced by dialectic variations such as African American Vernacular English. In this pivotal study, our objective is to architect a diagnostic tool to detect nascent signs of MCI-ED by analyzing African American patients’ verbal communications during regular health consultations. By meticulously recording, processing, and extracting linguistic and phonetic features from these conversations, complemented by additional clinical data, we aim to devise a potent screening algorithm. This initiative aligns seamlessly with the National Institute on Aging’s focus on early identification of cognitive impairment in the elderly. The prospective outcome, an innovative algorithm, holds promise to enhance timely MCI-ED diagnosis efficacy, especially among African American individuals, thereby optimizing care quality and addressing longstanding disparities.

Awardee Organization(s): Foresite Healthcare
Principal Investigator(s): Nicholas Kalaitzandonakes, PhD
Official Project Title: AI/ML Analyses of Mobility Changes Among Elderly Using Continuous Gait Data
AITC Partner: PennAITech
Website(s): https://www.foresitehealthcare.com/

Novel pharmacological and non-pharmacological interventions for Alzheimer’s Disease (AD) and Alzheimer’s Disease and Related Dementias (ADRD) (e.g., physical therapy, occupational therapy, exercise, etc.) can slow the disease progression, but timely diagnosis is necessary for such interventions to be effective. Yet, early diagnosis of the disease remains difficult. Various biomarkers and specialized brain scans are accurate and effective in diagnosing the disease early, but they are expensive, invasive, and difficult to execute in practice.
In previous studies, gait (e.g., walking speed) and motion characteristics (e.g., cadence, stride time and variability, step length, step width, sacrum mediolateral range of motion) have been found to strongly associate with the onset of AD/ADRD and to, often, precede cognitive decline and the presence of other dementia symptoms. As such, it may be possible to use gait and mobility features as diagnostics for AD/ADRD.
In this project, we will identify and develop gait- and motion-related predictive biomarkers for AD/ADRD. For this purpose, we will analyze multiyear gait and motion data from more than 5,000 older adults in assisted living (AL) and memory care (MC) communities around the US. Residents in MC units are all professionally diagnosed with AD/ADRD.
The identified biomarkers will be used as digital diagnostics for early, easy, and inexpensive identification of AD/ADRD, including through passive monitoring of populations in communities with care management and those aging in place (e.g., via passive, physiological, sensors and wearables).

Awardee Organization(s): Beth Israel Deaconess Medical Center
Principal Investigator(s): Chun Lim, MD, PhD
Official Project Title: Mobile Technology as a Cognitive Biomarker of Alzheimer’s Disease
AITC Partner: PennAITech
Website(s):
https://www.bidmc.org/

HOME

https://bidmcneurology.org/

Alzheimer’s disease’s hallmark is insidious memory loss often accompanied by a lack of awareness of the deficit. Its diagnosis requires evidence of cognitive impairment and remains reliant on clinical assessments, primarily traditional pen and paper cognitive tasks, which, with its many limitations results in only one-half of patients ever diagnosed by physicians. Thus, a simple, inexpensive, and at-home method to capture more of these patients earlier in their disease process could facilitate earlier therapy and planning.
We propose to modernize the clinical diagnosis of Alzheimer’s disease by taking advantage of smartphones to collect multiple streams of behavioral information including active data such as reaction/response time to cognitive tasks and games as well as data captured passively on the smartphone such as movement, location, and typing speed. Using advanced analytical tools, we propose to develop a new smartphone-based app for use in the home environment that detect signs and symptoms of early cognitive impairment and to continuously monitor for progression by capturing passive, real-world information, and active data.