# Agitation in Alzheimer's Disease: Identification and Prediction Using Digital Behavioral Markers and Indoor Environmental Factors

> **NIH NIH K25** · OREGON HEALTH & SCIENCE UNIVERSITY · 2024 · $145,515

## Abstract

PROJECT SUMMARY
Agitation is one of the most common and unmanageable neuropsychiatric symptoms experienced by persons
with dementia (PWD), affecting 45-83% of this ever-growing population. Agitation brings much stress and
detriment to patients and caregivers. Treatment of agitation is often pharmacological intervention which can
have adverse side effects. There is a great need for identification of early behavioral warning signs and
environmental precipitants of agitation so that it can pave the way for proactive management of agitation and
lower the burden on caregivers. The overall goal of this project is to address this critical unmet need through
the proposed research and mentored training of the applicant. The Oregon Center for Aging & Technology
(ORCATECH), under the direction of Dr. Kaye (proposed primary mentor), has more than a decade of
experience developing and deploying a digital behavioral assessment platform in older adults' homes and has
the experience analyzing the data collected in the clinical context of older adults. The scientific goals of this
proposal are to develop digital behavioral markers that identify episodes of agitation, identify early behavioral
warning signs and environmental precipitants of agitation, and build a risk prediction model of episodes of
agitation using environmental and behavioral sensors and techniques from machine learning and time series
analysis. The applicant will collect behavioral data from 10 study participants with later-stage dementia living in
memory care units and 10 study participants with later-stage dementia living at their own homes using passive
infrared motion sensors, wearable actigraphy devices, and bed pressure mats and follow them for 2 years.
Such behavioral data will be used to identify digital behavioral markers that indicate or predict episodes of
agitation. The applicant will also collect environmental data (ambient light level, noise level, temperature,
relative humidity, and barometric pressure) from their living environments, and such data will be used to
identify environmental precipitants of agitation. In order to conduct the proposed study and prepare for an
independent research career, the applicant will be trained through taking courses and attending workshops in
the following areas: (1) the different diagnosis and standard of care for PWD, their neuropsychiatric symptoms
and their precipitants; (2) methods of using technology in dementia research; (3) novel methods from deep
learning and time series analysis for building risk prediction models of agitation; and (4) development of
professional skills for conducting successful and ethically responsible clinical research. The proposed team of
mentors and consultant each provide expertise in one or more of these areas and are together committed to
collaboratively facilitating the applicant's training. The applicant will apply these new skills to the proposed
research project and obtain R01 support in order to use the me...

## Key facts

- **NIH application ID:** 10789997
- **Project number:** 5K25AG071841-04
- **Recipient organization:** OREGON HEALTH & SCIENCE UNIVERSITY
- **Principal Investigator:** Wan-Tai Au-Yeung
- **Activity code:** K25 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $145,515
- **Award type:** 5
- **Project period:** 2021-05-15 → 2026-02-28

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10789997

## Citation

> US National Institutes of Health, RePORTER application 10789997, Agitation in Alzheimer's Disease: Identification and Prediction Using Digital Behavioral Markers and Indoor Environmental Factors (5K25AG071841-04). Retrieved via AI Analytics 2026-05-25 from https://api.ai-analytics.org/grant/nih/10789997. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*