# Passive digital phenotyping for capturing real-world neurobehavior in neurodegenerative disease

> **NIH NIH K23** · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · 2024 · $197,569

## Abstract

PROJECT SUMMARY/ABSTRACT
The objective of this K23 career development award is to support Dr. Emily Paolillo in acquiring the expertise
to become an independent clinical researcher focused on using passive digital health methodologies and
machine learning analytics to improve detection and monitoring of neurobehavioral change in Alzheimer's
disease and related dementias (ADRD). Through the support of this K23 and the enriched multidisciplinary
training environment at the UCSF Memory and Aging Center, Dr. Paolillo aims to accomplish targeted goals
within the following training domains: 1) passive digital phenotyping in ADRD; 2) big data/ machine learning
analytics; and 3) scientific leadership. Dr. Paolillo will translate the knowledge, skills, and findings from this K23
into an R01 to integrate multimodal digital health tools for comprehensive, person-specific assessment of realworld
neurobehavioral change. To achieve these goals, Dr. Paolillo has assembled an accomplished
mentorship team with specific project-relevant expertise, including: biobehavioral correlates of dementia
prevention and wearable actigraphy (Primary Mentor Dr. Kaitlin Casaletto ); neurobehavioral phenotyping of
age-related cognitive decline (Co-Primary Mentor Dr. Joel Kramer); smartphone-based cognitive assessment
(Co-Mentor Dr. Adam Staffaroni); in-home passive sensor technology (Co-Mentor Dr. Jeffrey Kaye); machine
learning and health data science (Co-Mentor Dr. Stathis Gennatas); longitudinal data analysis in dementia (CoMentor
Dr. John Karnak) and neurobehavioral assessment of frontotemporal dementia (Scientific Advisor Dr.
Howard Rosen). The overarching goal of the proposed study is to examine the utility of a cutting-edge digital
health approach, namely passive smartphone monitoring, to detect neurobehavioral impairment in
neurodegenerative disease. Smartphone-based digital assessment tools have potential to overcome
accessibility limitations of traditional in-person neuropsychological evaluations, as they are remote and utilize
ubiquitous mobile technology. Examining digital assessment methods strongly aligns with Actions 2.B.1
("Identify and disseminate appropriate assessment tools") and 2.B.2 ("Support technology to advance mobile
monitoring of cognitive changes") of the 2022 National Plan to Address Alzheimer's Disease. Passively
collected digital metrics based on naturalistic smartphone interactions represent a feasible, accessible, lowburden
tool for remote monitoring and early detection of neurobehavioral change. The aims of the proposed
study are to determine the utility of passive smartphone metrics to measure and monitor clinical outcomes in
frontotemporal dementia (FTD) and Alzheimer's disease (AD) by testing associations with gold-standard
measures of cognition, neurodegeneration, and functional impairment cross-sectionally and longitudinally. This
study will be among the first to examine passive smartphone monitoring in FTD and AD, which if successful,
woul...

## Key facts

- **NIH application ID:** 10985904
- **Project number:** 1K23AG084883-01A1
- **Recipient organization:** UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
- **Principal Investigator:** Emily Paolillo
- **Activity code:** K23 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2024
- **Award amount:** $197,569
- **Award type:** 1
- **Project period:** 2024-09-11 → 2029-05-31

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10985904

## Citation

> US National Institutes of Health, RePORTER application 10985904, Passive digital phenotyping for capturing real-world neurobehavior in neurodegenerative disease (1K23AG084883-01A1). Retrieved via AI Analytics 2026-05-24 from https://api.ai-analytics.org/grant/nih/10985904. Licensed CC0.

---

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